dataset
stringclasses 45
values | id
stringlengths 17
64
| messages
listlengths 2
2
|
|---|---|---|
science.bc7_litcovid_topic_classification | science.bc7_litcovid_topic_classification.16744 | [
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nPatients infected with the SARS-CoV-2 virus can present with a wide variety of symptoms including being entirely asymptomatic. Despite having no or minimal symptoms, some patients may have markedly reduced pulse oximetry readings. This has been referred to as \"silent\" or \"apathetic\" hypoxia (Ottestad et al., 2020 [1]). We present a case of a 72-year-old male with COVID-19 syndrome who presented to the emergency department with minimal symptoms but low peripheral oxygen saturation readings. The patient deteriorated over the following days and eventually died as a result of overwhelming multi-organ system failure. This case highlights the utility of peripheral oxygen measurements in the evaluation of patients with SARS-CoV-2 infection. Self-monitoring of pulse oximetry by patients discharged from the emergency department is a potential way to identify patients needing to return for further evaluation.",
"role": "user"
},
{
"content": "[\"Case Report\"]",
"role": "assistant"
}
]
|
science.covidfact_entailment | science.covidfact_entailment.481 | [
{
"content": "Based on the abstract below, determine if the claim is supported or contradicted. Output a JSON object with the verdict (\"SUPPORT\" or \"CONTRADICT\") and evidence sentences from the abstract.\n\nClaim: Amilorides inhibit sars-cov-2 replication in vitro by targeting rna structures\n\nText:\nThe SARS-CoV-2 pandemic, and the likelihood of future coronavirus pandemics, has rendered our understanding of coronavirus biology more essential than ever.\nSmall molecule chemical probes offer to both reveal novel aspects of virus replication and to serve as leads for antiviral therapeutic development.\nThe RNA-biased amiloride scaffold was recently tuned to target a viral RNA structure critical for translation in enterovirus 71, ultimately uncovering a novel mechanism to modulate positive-sense RNA viral translation and replication.\nAnalysis of CoV RNA genomes reveal many conserved RNA structures in the 5’-UTR and proximal region critical for viral translation and replication, including several containing bulge-like secondary structures suitable for small molecule targeting.\nFollowing phylogenetic conservation analysis of this region, we screened an amiloride-based small molecule library against a less virulent human coronavirus, OC43, to identify lead ligands.\nAmilorides inhibited OC43 replication as seen in viral plaque assays.\nSelect amilorides also potently inhibited replication competent SARS-CoV-2 as evident in the decreased levels of cell free virions in cell culture supernatants of treated cells.\nReporter screens confirmed the importance of RNA structures in the 5’-end of the viral genome for small molecule activity.\nFinally, NMR chemical shift perturbation studies of the first six stem loops of the 5’-end revealed specific amiloride interactions with stem loops 4, 5a, and 6, all of which contain bulge like structures and were predicted to be strongly bound by the lead amilorides in retrospective docking studies.\nTaken together, the use of multiple orthogonal approaches allowed us to identify the first small molecules aimed at targeting RNA structures within the 5’-UTR and proximal region of the CoV genome.\nThese molecules will serve as chemical probes to further understand CoV RNA biology and can pave the way for the development of specific CoV RNA-targeted antivirals.",
"role": "user"
},
{
"content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"The RNA-biased amiloride scaffold was recently tuned to target a viral RNA structure critical for translation in enterovirus 71, ultimately uncovering a novel mechanism to modulate positive-sense RNA viral translation and replication.\"]}",
"role": "assistant"
}
]
|
science.bioasq_general_qa | science.bioasq_general_qa.149 | [
{
"content": "Answer the following question using the provided context. Only provide the answer without any additional text.\n\nQuestion: What pharmacological and non-pharmacological interventions can be considered as prophylactic therapies in Cluster Headache patients?\nContext: The calcium channel blocker verapamil is the drug of choice for CH prevention. Other drugs that may be used for this purpose include lithium carbonate, topiramate, valproic acid, gabapentin, and baclofen.\nRecently, the therapeutic options for refractory CH patients have expanded with the emergence of both peripheral (mostly occipital nerve) and central (hypothalamic) neurostimulation.\nWith the emergence of these novel treatments, the role of ablative surgery in CH has declined.\nThe mainstay of prophylactic therapy is verapamil. Yet, other medications, including lithium, divalproex sodium, topiramate, methysergide, gabapentin, and even indomethacin, may be useful when the headache fails to respond to verapamil.\nFor medically refractory patients, surgical interventions, occipital nerve stimulation, and deep brain stimulation remain an option.\nThe objective of this open single-centre study was to evaluate the efficacy and tolerability of botulinum toxin type-A (BTX-A) as add-on in the prophylactic treatment of cluster headache (CH).\nThese findings provide evidence that BTX-A may be beneficial as an add-on prophylactic therapy for a limited number of patients with chronic CH.\nThere are a variety of different medications for abortive and prophylactic therapy, accompanied by a variable amount of evidence-based medicine.\nMost procedures are directed against the sensory trigeminal nerve and associated ganglia, eg, anesthetizing the sphenopalatine ganglion.\nThe mainstay of prophylactic therapy is verapamil. Lithium, divalproex sodium, or topiramate may also be useful.\nBased on our clinical experience, we recommended the combination of nasal sumatriptan for acute attacks and verapamil 240 mg/day for prophylaxis.\nTopiramate also appears to be well tolerated and useful in the adjunctive treatment of cluster headache.\nThe cornerstone of maintenance prophylaxis is verapamil, yet methysergide, lithium, and divalproex sodium may also be employed. In some patients, melatonin or topiramate may be useful adjunctive therapies.\nProphylactic therapy in most cases consisted of verapamil, also with a good response.\nPatients with chronic cluster headache may achieve good results from long-term treatment with other therapies, including lithium carbonate, verapamil, and ketoprofen.",
"role": "user"
},
{
"content": "Verapamil, a calcium channel blocker, is considered the mainstay of prophylactic therapy of Cluster Headache patients. Lithium carbonate, topiramate, valproic acid, gabapentin, baclofen, methysergide, melatonin, ketoprofen and indomethacin can also be tried for prophylactic therapy of Cluster Headaches patients. Non-pharmacological prophylactic measures, such as peripheral (mostly occipital nerve) and central (hypothalamic) neurostimulation, ablative surgery, and botulinum toxin type-A (BTX-A) injection, can be also considered.",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.8582 | [
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: ImagesacquiredunderidenticalacquisitionparameterswereanalyzedusingMetamorphSoftwarev6.2(UniversalImaging,Glendale,Wisconsin,UnitedStates).",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.2645 | [
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: FurtherdissectingtheinteractionsbetweenPPARdeltaanditsregulatorycomponentswillbenecessarytofullyunderstandthemolecularbasisofmusclefiberdeterminationpertinenttoexercisetraining.",
"role": "user"
},
{
"content": "[\"molecular\"]",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.2693 | [
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nLong-term effects of ezetimibe-plus-statin therapy on low-density lipoprotein cholesterol levels as compared with double-dose statin therapy in patients with coronary artery disease . OBJECTIVE To assess the mechanism of long-term LDL-C-lowering effect of ezetimibe-plus-statin . METHODS Coronary artery disease patients whose LDL-C ≥ 70 mg/dL after treatment with atorvastatin 10 mg/day or rosuvastatin 2.5 mg/day were randomly assigned to receive ezetimibe 10 mg/day + statin ( n = 78 ) or double-dose statin ( n = 72 ) for 52 weeks . RESULTS Greater LDL-C reduction was observed and maintained until 52 weeks in ezetimibe-plus-statin , while LDL-C levels re-increased after 12 weeks in double-dose statin . Although lathosterol/TC increased , campesterol/TC decreased more in ezetimibe-plus-statin . In contrast , lathosterol/TC unchanged and campesterol/TC increased , increasing campesterol/lathosterol ratio for 52 weeks in double-dose statin . Plasma PCSK9 levels were higher in double-dose statin than in ezetimibe-plus-statin at 12 weeks , but similar at 52 weeks . CONCLUSION Although the difference in PCSK9 between 2 groups was transient , that in both campesterol and lathosterol persisted until 52 weeks . These results demonstrated simultaneous inhibition of cholesterol absorption and synthesis provides stable and greater decrease in LDL-C levels .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"double-dose statin therapy\", \"ezetimibe-plus-statin\"], \"Outcome\": [\"low-density lipoprotein cholesterol levels\"], \"Participant\": [\"patients with coronary artery disease .\", \"Coronary artery disease patients whose LDL-C \\u2265 70 mg/dL after treatment with atorvastatin 10 mg/day or rosuvastatin 2.5 mg/day\"]}",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.2986 | [
{
"content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: This problematic situation was alleviated by viewing the scanned areas with a wider window, such as a bone setting.(15) The author of case series of human patients stated that as the window width was increased, the foreign bodies were more easily identified and better differentiated from a gas or fluid build up due to the wood’s absorptive characteristics and the duration of the injury.",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.18162 | [
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Hypertree decompositions: A survey \nChapter Title: Theorem 8 ([17]). CSP(TW[k]) is LOGCFL-complete. \n1. Abstract of Cited Paper (BIB001): A number of efficient methods for evaluating first-order and monadic-second order queries on finite relational structures are based on tree-decompositions of structures or queries. We systematically study these methods.In the first part of the article, we consider arbitrary formulas on tree-like structures. We generalize a theorem of Courcelle [1990] by showing that on structures of bounded tree-width a monadic second-order formula (with free first- and second-order variables) can be evaluated in time linear in the structure size plus the size of the output.In the second part, we study tree-like formulas on arbitrary structures. We generalize the notions of acyclicity and bounded tree-width from conjunctive queries to arbitrary first-order formulas in a straightforward way and analyze the complexity of evaluating formulas of these fragments. Moreover, we show that the acyclic and bounded tree-width fragments have the same expressive power as the well-known guarded fragment and the finite-variable fragments of first-order logic, respectively.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Note that considering the primal graph associated to a hypergraph is not the one possible choice. Given a CSP instance I, the dual graph The dual graph often looks very intricate even for simple CSPs. For instance, in general, acyclic CSPs do not have acyclic dual graphs. However, it is well known that the dual graph G d I can be suitably simplified in order to obtain a \"better\" graph G which can still be used to solve the given CSP instance I. In particular, if I is an acyclic CSP, G d I can be reduced to an acyclic graph that represents a join tree of H I . In this case, the reduction is feasible in polynomial (actually, linear) time. (See, e.g., .) However, in general, it is not known whether there exists an efficient algorithm for obtaining the best simplified graph G with respect to the treewidth notion, i.e., the simplification of G d I having the smallest treewidth over all its possible simplifications (see for a formal statement of this open problem and BIB001 for a comparison of this notion with some hypergraph-based notions). Another possibility is considering the so called incidence graph . Given a CSP instance I, the incidence graph G i I (H I ) = (V , E) associated to the hypergraph H I = (V, H) has a vertex for each variable and for each hyperedge of H I . There is an edge {x, h} ∈ E between a variable x ∈ V and and hyperedge h ∈ H whenever x occurs in h. The class of all CSP instances whose dual graphs (resp. incidence graphs) have bounded treewidth are solvable in polynomial time and, actually, they are LOGCFL-complete. However, note that none of these classes of CSP instances generalize the class CSP(AH). Indeed, there are families of acyclic hypergraphs whose associated primal graphs, dual graphs (without considering simplification), and incidence graphs have unbounded treewidth. Note that by results of bounded treewidth is most likely the best and most general structural restriction for obtaining tractable CSP and BCQ instances, when the structure of a CSP or BCQ is described via a graph (e.g. the primal graph), rather than by a hypergraph. Further interesting material on BCQ and treewidth can be found in BIB002 .",
"role": "assistant"
}
]
|
science.chemsum_single_document_summarization | science.chemsum_single_document_summarization.105530 | [
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nDictating Thermodynamic Control through Tethering: Applications to Stereoselective Bis-Spiroketal Synthesis\n\nPaper sections:\n\n<p>Utilizing substrate-based thermodynamic control to dictate stereochemical outcomes avoids the complex catalysts or stoichiometric reagents that are required for reagent-controlled approaches. The formation of spiroketals from keto diols is a classic example of this strategy,[1] whereby the doubly anomeric stereoisomer often forms spontaneously. Extending this strategy to the synthesis of bis-spiroketals, such as those found in the marine shellfish toxins pinnatoxin A (1)[2] and spirolide C (2),[3] from diketo diols has not proven to be readily successful. The challenge results from the absence of anomeric stabilization in tetrahydrofuran rings.[4] The elegant syntheses of the pinnatoxin bis-spiroketal,[5] therefore, required substrates with multiple stereocenters and exploited remote hydrogen-bonding and steric effects, while the stereoselective synthesis of the spirolide bis-spiroketal remains an unsolved problem.[6] The construction of these units provides an excellent opportunity to demonstrate the merits of utilizing tethering to provide a thermodynamic bias the stereochemical outcomes of reactions. This manuscript describes the spirotricyclization of macrocyclic diketo diols in which a tether breaks the energetic degeneracy of the product stereoisomers. Coupling this approach with Re2O7-mediated allylic alcohol regio- and steroisomerization provides an enantioselective method for preparing the pinnatoxin bis-spiroketal, whereby numerous remote stereocenters are established with high control.</p><p>Employing precursors with stereodefined alcohols leads to the first stereoselective construction of the spirolide bis-spiroketal.</p><p>We have been exploring the use of Re2O7 as a catalyst for complexity-generating reactions from allylic alcohol substrates.[7] The spirocycle-forming examples in Scheme 1[7a] are particularly relevant to the objectives in this manuscript. The conversion of diol 3 to spiroketal 4 shows that the stereochemical information in a non-allylic alcohol can control the configuration of a remote stereocenter through thermodynamic control without loss of enantiomeric integrity. Bis-spiroketal formation proceeds smoothly and rapidly, as seen in the formation of 6 and 7 from 5, but the lack of a significant thermodynamic preference results in a 1:1 mixture of products. Examining the structures of the products reveals that the alkenyl groups in 6, which contains the stereochemical orientation present in pinnatoxin A, have a proximal relationship whereas those in 7 have a distal relationship. We postulated that tethering the alkenyl groups with a chain that allows for the formation of the stereochemical orientation in 6 while being too short to permit the alternate diastereomer would provide a unique and effective method for directing the outcomes of these reactions. Precedent from this strategy came from our studies in using tethering to control the stereochemistry of bridged tetrahydropyrans in oxidative Prins cyclizations[8] and from insightful examples showing that that a macrocyclic architecture can influence the relative stabilities of otherwise energetically similar spiroketals.[9]</p><p>This plan was tested as shown in Scheme 2. The 1,4-diketone substrate is available through an efficient Stetter reaction between enone 8 and aldehyde 9 in the presence of Glorius' pre-catalyst (10) to yield 11.[10],[11] A sequence of routine protecting group manipulations and acylations provided substrate 12. Proceeding through this sequence with a diastereomeric mixture facilitates the sequence but does not result in handling difficulties because the remote stereocenters result in spectroscopically and chromatographically identical isomers. The phthalate diester linkage was selected for synthetic ease, though numerous other connecting groups could, in principle, be employed. Exposing 12 to Re2O7•SiO2[7b] (5 mol%, selected based on its ease of handling for small scale reactions) initially provided a mixture of diastereomeric products that equilibrated to yield 13 as a single stereoisomer after 8.5 h, thereby demonstrating the ability of the tethering strategy to control the stereochemical orientation of the central tetrahydrofuran in a manner that is relevant to the synthesis of the pinnatoxin core. X-ray diffraction studies of the small crystals of 13 did not deliver a well-resolved structure but provided strong evidence for the stereochemical outcome.[12] The lower homologue 14, prepared through a similar sequence, also undergoes cyclization to form bis-spiroketals 15 and 16 in a 1:1 ratio. The structures of these isomers, which differ in the stereochemical orientations of their peripheral tetrahydrofuran rings, were determined based on extensive 1H and 13C NMR analyses and a crystal structure of 16.[12],[13] The ability to control the stereochemical orientation of the central tetrahydrofuran ring is unprecedented for this ring system.[6] Exposing either 15 or 16 to Re2O7•SiO2 regenerated the 1:1 mixture that was observed in the cyclization, indicating that the product ratio is due to thermodynamic, rather than kinetic, control. This result indicates that tethering will be useful in approaches to the spirolide core that utilize substrates with stereochemically defined alcohols. Indeed, acid-mediated silyl ether cleavage of 17 resulted in a remarkably efficient conversion to 18, delivering a single stereoisomer in 96% yield, demonstrating the first stereocontrolled synthesis of the spirolide bis-spiroketal. This outcome was verified through crystallographic analysis.</p><p>Exploiting the stereochemical equilibration that is inherent in the Re2O7-catalyzed transformations in enantioselective bis-spiroketal construction requires diastereocontrol relative to a non-equilibrating stereocenter (Scheme 3). The stereocenter that is embedded in the tricyclic core of the pinnatoxins became the initial focus of our studies. Acetoxy-substituted macrocycle 19 served as the initial substrate for diastereoselectivity studies since the product could be converted to a ketone that could eventually allow for tertiary alcohol formation. Exposing 19 to Re2O7•SiO2 successfully generated bis-spiroketals 20 and 21 in good yield, but without a stereochemical preference. These isomers could not be interconverted through re-exposure to the reaction conditions because both rings would need to undergo stereomutation, which would require the formation of high energy intermediates. Postulating that increasing the steric bulk of the substituent while minimizing the potential for anchimeric assistance would improve diastereocontrol led to the formation of methyl-containing substrate 22, with the expectation that the resulting methine group could serve as a substrate for stereospecific carbon–hydrogen bond functionalization to form the tertiary alcohol.[14] Spirocyclization indeed proceeded with greater stereocontrol, with 23 and 24 being formed in a 3.8:1 ratio. The orientations of the methyl groups in these compounds were determined through 1-D TOCSY experiments.[12] No effort was made to optimize the stereocontrol since the major isomer had the incorrect stereochemical orientation for stereoretentive oxidative tertiary alcohol formation. The led us to explore a variant of the strategy used for the conversion of 3 to 4 (Scheme 1) whereby the stereochemical information from a non-allylic secondary alcohol is transmitted across the ring system. Thus, 25 was deprotected and the resulting diol smoothly isomerized to bis-spiroketal 26. Equilibration was slow but ultimately led to a 17:1 diastereomeric ratio of products. Attempts to enhance the stereoselectivity further resulted in a lower yield. The two-step sequence was employed based on the difficulty in characterizing the mixture of stereo- and constitutional isomers that result from partial hemiketal formation in the deprotected cyclization substrate.</p><p>These results provided the framework for the enantioselective construction of the bis-spiroketal in the pinnatoxins (Scheme 4). This approach utilizes a dithiane as a precursor to the tertiary alcohol in the ring system, since the use of a ketone in this role could inhibit the generation of the adjacent oxocarbenium ion that is essential for cyclic ketal formation. The route commenced from dihydrofuran (27) through transketalization with propane dithiol[15] followed by oxidation to form aldehyde 28.[16] Coupling with allylic stannane 29[17] under Maruoka's enantioselective conditions[18] provided 30, with the minor enantiomer being undetectable. This reaction delivers the exocyclic alkene group for the pinnatoxin subunit synthesis, and also generates the stereocenter[19] that will control all other stereocenters in the sequence while providing an efficient fragment coupling. The four-step sequence of silyl ether formation, formylation, and vinylation provided allylic alcohol 31. The corresponding enone is somewhat unstable, so oxidation was delayed until immediately before coupling with the aldehyde. The synthesis of aldehyde 34 was initiated by the hydrozirconation and Me2Zn-mediated transmetallation[20] of alkyne 32 followed by quenching with aldehyde 33. Protection of the resulting secondary alcohol as a TIPS ether, selective TBS ether cleavage, and oxidation formed 34. Oxidation of 31 followed by Stetter coupling with 34 in the presence of 10 provided 1,4-diketone 35 in excellent yield. Cleaving the TBS ether under mildly acidic conditions, acylation with phthalic anhydride, and oxidative PMB ether cleavage generated seco-acid 36 efficiently. Macrocyclization under Shiina's conditions[21] provided lactone 37.</p><p>Spirocycle formation proceeded through deprotection of the silyl ethers of 37 (92% yield) followed by the addition of addition of Re2O7•SiO2 to the resulting isomeric mixture (Scheme 5). Tricyclic product was formed very quickly, presumably due to the conformational biasing by the dithiane. Equilibration was quite sluggish for this reaction, however, so we added hexafluoroisopropyl alcohol (HFIP) to the reaction upon the completion of the tricyclic unit based on our previous observation that HFIP is compatible with Re2O7 and facilitates ionization reactions.[22] Ultimately this resulted in the isolation of 38 in 81% yield as a 7.5:1 mixture of separable diastereomers. The minor diastereomer in this reaction places the alkenyl group in an axial orientation and this isomer undergoes equilibration under the reaction conditions to form the same 7.5:1 ratio of diastereomers. This verifies that the process is under thermodynamic control, with the increased complexity resulting in a minor erosion in diastereocontrol. Thus the tethering and isomerization strategy delivered the tricyclic unit efficiently and with high diastereocontrol. Cleaving the dithiane through alkylative conditions followed by the addition of MeMgI delivered the tertiary alcohol as a single diastereomer. The stereochemical outcome of this reaction was determined through a NOESY experiment and from the observation of a 0.6 Hz coupling constant for the axial methyl group in the 1H NMR spectrum, consistent with the known W-coupling of axially-oriented methyl groups adjacent to a carbon with an axially oriented hydrogen.[23] This is consistent with previous related examples.[5b],[6a,b] The phthalate diester was cleaved under standard conditions to deliver 39 in good yield. Thus the pinnatoxin bis-spiroketal was delivered with excellent stereocontrol form a sequence in which a single, stereochemically defined alcohol guided the generation of all subsequent stereogenic units.</p><p>We have described a strategy for controlling the stereochemical outcome of reactions that generate bis-spiroketals. This approach merges the use of Re2O7 as a catalyst to promote cyclization and thermodynamically controlled stereochemical equilibration with the incorporation of a tether to create an energetic bias for a specific stereoisomer. The method was applied to the synthesis of the pinnatoxin core, in which a single stereocenter directed the generation of three rings and three new stereocenters with a high degree of control. The tethering strategy also proved to be extremely effective in the preparation of the challenging spirolide bis-spiroketal. Applying this method to molecules of the complexity of the bis-spiroketals demonstrates a high degree of functional group compatibility that has also been observed in other applications of oxorhenium catalysts in natural product synthesis, whereby reactions proceed in the presence of essentially all non-basic moieties.[24] The phthalate diester linker allowed for the demonstration of concept. However the natural products that contain bis-spiroketals often embed these units in a macrocycle, indicating that the strategy will be applicable to natural product syntheses at a very late stage in the sequence. Notably a proposal for the biosynthesis of spirolide[25] postulates that the bis-spiroketal forms after the macrocycle is formed, indicating that the tethering strategy mimics nature's approach to the formation of these structures.</p>",
"role": "user"
},
{
"content": "Approaches to stereocontrol that invoke thermodynamic control fail when two or more potential products are energetically similar, but rational structural perturbations can be employed to break the energetic degeneracy and provide selective transformations. This manuscript illustrates that tethering is an effective approach for the stereoselective construction of bis-spiroketals with thermodynamically similar stereoisomers, providing a new approach to set remote stereocenters and prepare complex structures that have not previously been accessed stereoselectively.",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.3598 | [
{
"content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: For the historical data, intra-individual median LDL-C, HDL-C, TC, and HbA1c were used, and the CV of HbA1c (ratio of intrapersonal HbA1c standard deviation [SD]/mean HbA1c) was utilized as a measure of historical HbA1c variability (Waden et al., 2009).",
"role": "user"
},
{
"content": "Method",
"role": "assistant"
}
]
|
science.scientific_papers_summarization_single_doc_pubmed | science.scientific_papers_summarization_single_doc_pubmed.89086 | [
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\nalthough several theories have been proposed about the pathogenesis of vitiligo , the precise cause remains unknown .\ntheories on the destruction of melanocytes include autoimmune mechanisms , cytotoxic mechanisms , an intrinsic defect of melanocytes , oxidant - antioxidant mechanisms , and neural mechanisms .\nvitiligo is perhaps the most common pigmentation disorder , occurring at a frequency of approximately 0.2%-1.0% in different populations around the world . because of its visually striking phenotype\nepidemiological studies have shown that vitiligo is a complex trait , involving combinations of pathogenic effects of multiple susceptibility genes and environmental risk factors .\nclustering of vitiligo cases occurs in some families , almost always in non - mendelian patterns , indicative of polygenic , multifactorial causation .\nindeed , the concordance of vitiligo in monozygotic twins is only 23% , highlighting the importance of environmental triggers , which as yet remain unknown .\nthe aim of this study was to discover whether consanguinity increased the incidence of vitiligo in saudi patients from arar ( on the northern borders area ) , an area where there is a high incidence of the condition in families .\nthe aim of this study was to discover whether consanguinity increased the incidence of vitiligo in saudi patients from arar ( on the northern borders area ) , an area where there is a high incidence of the condition in families .\nthese patients were selected from the experience specialist dermatology center in arar , from april 2011 to april 2012 .\nthe patients were interviewed by a dermatologist to confirm the diagnosis and complete the questionnaire which had the following items : age , sex , age of onset , clinical classification , and course of the disease .\nalso information about first degree relation , that is , close blood relative such as the individual 's parents , full siblings , or children , second degree , that is , a blood relative such as the individual 's grandparents , grandchildren , aunts , uncles , nephews , nieces , or half - siblings ; and third degree blood relations including the individual 's first - cousins , great - grandparents , or great grandchildren , and also the number of vitiligo cases among relatives .\na verbal consent was obtained from the patients who were also informed that the data were being collected for scientific purposes and would remain confidential .\nstatistical analysis was done using spss 20 ; quantitative data were expressed in mean and standard deviation , and qualitative data were expressed in number and percentage .\nintergroup comparison was done using chi - square test ( x ) and z test for proportion to compare number and percentage in two numbers from the same group .\nthe observed relative frequency ( s / q ) was estimated by dividing frequency in the siblings ( s ) by the frequency in the general population ( q ) .\nsegregation analysis was done by comparing the observed sib frequency ( s / q ) to the expected frequency for various modes of inheritance .\nthe mean age of the onset of the disease was 27.9 12.9 years ; the mean duration of the disease was 9.7 5.3 years [ table 1 ] .\ndemographic data of the study group the frequency of focal , vulgaris , universal , and acrofacial subtypes was 22 ( 31.9% ) , 21 ( 30.4% ) , 8 ( 11.6% ) , and 18 ( 26.1% ) , respectively .\na positive family history of vitiligo was present in 45 ( 65.2% ) cases , which is statistically significantly higher [ table 2 ] .\nparticularly high first cousin consanguinity ( 27.5% ) resulted in a relatively high coefficient of inbreeding of 0.018 [ table 3 ] .\nstudy group according to family history consanguinity pattern and inbreeding co - efficient in vitiligo cases table 4 shows that consanguinity was statistically significantly higher in those with skin type iv than those with skin type iii ( p = 0.03 ) and there was no statistically significant difference between the three groups [ negative , first cousin , and others ) as regards clinical subtypes , mucosal involvement , white hair , and duration of the disease .\nconsanguinity pattern related to clinical subtype table 5 illustrates the relation between family history and clinical subtypes , mucosal involvement , white hair , skin type , and duration of the disease .\nthere was statistically significant difference between positive and negative family history as regards both clinical subtypes and skin subtype .\nthe positive family history was higher in acrofacial ( 94.4% ) , followed by vulgaris ( 85.7% ) by the universal ( 50% ) followed by focal type ( 27.3% ) ( p < 0.001 ) .\nas regard to skin type , a positive family history was statistically significantly higher in type iv ( p = 0.03 ) .\nthere was no statistically significant difference as regards mucosal involvement , white hair , and duration of the disease .\nfamily history related to clinical subtype , mucosal , and hair involvement and disease severity table 6 indicates that a comparison of the frequency of vitiligo among siblings in relation to the general population reveals an inheritance pattern more coincident with the multifactorial model especially for the vulgaris ( 11.7% ) subtype , followed by the universal ( 8.9% ) , acrofacial ( 8.1% ) , and focal subtypes ( 1.5% ) . inheritance pattern related to clinical subtype\nvitiligo is an acquired , idiopathic , worldwide common depigmentation disorder with an estimated prevalence from 0.1% to 8% .\nthese numbers are based on clinical population studies and field research that examined inhabitants of geographically enclosed areas .\nthe results of the genetic studies thus far show that generalized vitiligo is a typical polygenic , multifactorial disorder , involving numerous different susceptibility genes , and that the great majority of these genes encode proteins that regulate or mediate recognition or destruction of melanocytes by the immune system .\nthe most important recent developments in vitiligo occurred in two large - scale genome wide association studies of generalized vitiligo , one in caucasians and the other in chinese , which together identified and confirmed at least 16 different loci that contribute to the susceptibility of generalized vitiligo .\nthis current study done on a sample of vitiligo cases from arar [ northern borders area , kingdom of saudi arabia ( ksa ) ] confirmed the role of the genetic factor in the development of this disease .\nit indicated that focal subtype of vitiligo was the most common followed by vulgaris then acrofacial and universal subtypes .\nthe higher incidence of consanguineous marriages in our part of the world increases the importance of associated genetic factors in any given disease .\nthis study showed that 40.6% of the cases showed parental consanguinity which was higher in first cousins ( 27.5% ) clinical subtypes in first cousins was arranged in this order .\nfirst came , the universal followed by vulgaris , then acrofacial and lastly focal subtype . also , the rate of consanguinity was significantly higher in skin type iv than in skin type iii .\nthis is in agreement with the study done in the al - qassim region , ksa , which showed parental consanguinity as 32.4% and first cousins as 22.5% and also as regards skin type , the arrangement of subtypes , was different , universal as the first , followed by acrofacial , vulgaris , and finally focal . in this study , the positive family history cases ( 65.2% )\nthis is in agreement with zamani et al . , and some other studies which found vitiligo to be strongly associated with family history of the condition .\na positive family history was significantly higher in cases with acrofacial and vulgaris subtype , followed by universal and focal subtypes .\nfamily history was also significantly higher in type iv skin type compared to those with a negative family history .\nthis is similar to shekokar and ghubde who stated that vitiligo occurred more commonly in blood relatives .\nit is also similar to the findings of tanioka et al . , who stated that family members were predisposed to vitiligo itself .\nthey found that significant family inheritance presented itself as an appreciable factor for this disease .\nenvironmental factors should also be borne in mind as a cause or a trigger for the occurrence of vitiligo .\nthis study would help to alert the population to the consequences of consanguinity and its potential to increase the incidence of diseases such as vitiligo in which genetics play a role .\ngenetic counseling and premarital examination are , therefore , important means by which the prevalence of vitiligo can be reduced .",
"role": "user"
},
{
"content": "context : epidemiological studies have shown that vitiligo is a complex trait , involving combinations of pathogenic effects of multiple susceptibility genes as well as environmental risk factors.aim:to observe whether consanguinity increased the incidence of vitiligo in saudi patients from arar.patients and methods : this study included 69 saudi patients with vitiligo and their families . \n these patients , selected from the experience specialist dermatology center in arar , from april 2011 to 2012 , were interviewed by a dermatologist to confirm the diagnosis and complete a questionnaire.results:a total of 69 patients , 40 males and 29 females were selected . \n their mean age was 34.5 11.8 years with the median age of 23 years . \n the mean age at onset of disease was 27.9 12.9 years . \n the mean duration of the disease was 9.7 5.3 years . \n the frequency of focal , vulgaris , universal , and acrofacial subtypes was 22 ( 31.9% ) , 21 ( 30.4% ) , 8 ( 11.6% ) , and 18 ( 26.1% ) , respectively . \n a positive family history of vitiligo was obtained in 45 ( 65.2% ) cases . \n a comparison of the frequency of vitiligo among siblings in relation to the general population was more in accord with the multifactorial model.conclusion:consanguinity in marriage increases the incidence of the disease . \n therefore , genetic counseling and premarital examination would be important contributions to lower the prevalence of vitiligo .",
"role": "assistant"
}
]
|
science.data_reco_mcq_sc | science.data_reco_mcq_sc.9913 | [
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: In this paper, we introduce the natural-logarithm-rectified linear unit (NLReLU\n\nKeyphrases: image classification images\n\nDataset descriptions:\nMNIST-1D: A minimalist, low-memory, and low-compute alternative to classic deep learning benchmarks. The training examples are 20 times smaller than MNIST examples yet they differentiate more clearly between linear, nonlinear, and convolutional models which attain 32, 68, and 94% accuracy respectively (these models obtain 94, 99+, and 99+% on MNIST).\nCIFAR-10: The CIFAR-10 dataset (Canadian Institute for Advanced Research, 10 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The images are labelled with one of 10 mutually exclusive classes: airplane, automobile (but not truck or pickup truck), bird, cat, deer, dog, frog, horse, ship, and truck (but not pickup truck).\nTHEODORE: Recent work about synthetic indoor datasets from perspective views has shown significant improvements of object detection results with Convolutional Neural Networks(CNNs). In this paper, we introduce THEODORE: a novel, large-scale indoor dataset containing 100,000 high- resolution diversified fisheye images with 14 classes.\nSatStereo: Provides a set of stereo-rectified images and the associated groundtruthed disparities for 10 AOIs (Area of Interest) drawn from two sources: 8 AOIs from IARPA's MVS Challenge dataset and 2 AOIs from the CORE3D-Public dataset.\n\nOptions: A: MNIST-1D B: CIFAR-10 C: THEODORE D: SatStereo",
"role": "user"
},
{
"content": "CIFAR-10",
"role": "assistant"
}
]
|
science.qasa_abstractive_qa | science.qasa_abstractive_qa.1401 | [
{
"content": "Read this passage from a research paper and answer the question.\n\nContext: Feature maps from different levels within a network are known to have different (empirical) receptive field sizes [13]. Fortunately, within the SSD framework, the default boxes do not necessary need to correspond to the actual receptive fields of each layer.We design the tiling of default boxes so that specific feature maps learn to be responsive to particular scales of the objects. Suppose we want to use m feature maps for prediction. The scale of the default boxes for each feature map is computed as:s_{k}=s_{\\text{min}}+\\frac{s_{\\text{max}}-s_{\\text{min}}}{m-1}(k-1),\\quad k\\in[1,m](4)where s_{\\text{min}} is 0.2 and s_{\\text{max}} is 0.9, meaning the lowest layer has a scale of 0.2 and the highest layer has a scale of 0.9, and all layers in between are regularly spaced. We impose different aspect ratios for the default boxes, and denote them as a_{r}\\in\\{1,2,3,\\frac{1}{2},\\frac{1}{3}\\}. We can compute the width (w_{k}^{a}=s_{k}\\sqrt{a_{r}}) and height (h_{k}^{a}=s_{k}/\\sqrt{a_{r}}) for each default box. For the aspect ratio of 1, we also add a default box whose scale is s^{\\prime}_{k}=\\sqrt{s_{k}s_{k+1}}, resulting in 6 default boxes per feature map location. We set the center of each default box to (\\frac{i+0.5}{|f_{k}|},\\frac{j+0.5}{|f_{k}|}), where |f_{k}| is the size of the k-th square feature map, i,j\\in[0,|f_{k}|). In practice, one can also design a distribution of default boxes to best fit a specific dataset. How to design the optimal tiling is an open question as well.\n\nQuestion: How scales of the default bounding boxes for a particular feature map is computed?",
"role": "user"
},
{
"content": "The scale of the default boxes for each feature map is computed as:s_{k}=s_{\\text{min}}+\\frac{s_{\\text{max}}-s_{\\text{min}}}{m-1}(k-1),\\quad k\\in[1,m](4)where s_{\\text{min}} is 0.2 and s_{\\text{max}} is 0.9, meaning the lowest layer has a scale of 0.2 and the highest layer has a scale of 0.9, and all layers in between are regularly spaced.",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.3098 | [
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nMitigation of sociocommunicational deficits of autism through oxytocin-induced recovery of medial prefrontal activity : a randomized trial . IMPORTANCE Sociocommunicational deficits make it difficult for individuals with autism spectrum disorders ( ASD ) to understand communication content with conflicting verbal and nonverbal information . Despite growing prospects for oxytocin as a therapeutic agent for ASD , no direct neurobiological evidence exists for oxytocin 's beneficial effects on this core symptom of ASD . This is slowing clinical application of the neuropeptide . OBJECTIVE To directly examine whether oxytocin has beneficial effects on the sociocommunicational deficits of ASD using both behavioral and neural measures . DESIGN , SETTING , AND PARTICIPANTS At the University of Tokyo Hospital , we conducted a randomized , double-blind , placebo-controlled , within-subject-crossover , single-site experimental trial in which intranasal oxytocin and placebo were administered . A total of 40 highly functioning men with ASD participated and were randomized in the trial . INTERVENTIONS Single-dose intranasal administration of oxytocin ( 24 IU ) and placebo . MAIN OUTCOMES AND MEASURES Using functional magnetic resonance imaging , we examined effects of oxytocin on behavioral neural responses of the participants to a social psychological task . In our previous case-control study using the same psychological task , when making decisions about social information with conflicting verbal and nonverbal contents , participants with ASD made judgments based on nonverbal contents less frequently with longer time and could not induce enough activation in the medial prefrontal cortex . Therefore , our main outcomes and measures were the frequency of the nonverbal information-based judgments ( NVJs ) , the response time for NVJs , and brain activity of the medial prefrontal cortex during NVJs . RESULTS Intranasal oxytocin enabled the participants to make NVJs more frequently ( P = .03 ) with shorter response time ( P = .02 ) . During the mitigated behavior , oxytocin increased the originally diminished brain activity in the medial prefrontal cortex ( P < .001 ) . Moreover , oxytocin enhanced functional coordination in the area ( P < .001 ) , and the magnitude of these neural effects was predictive of the behavioral effects ( P ≤ .01 ) . CONCLUSIONS AND RELEVANCE These findings provide the first neurobiological evidence for oxytocin 's beneficial effects on sociocommunicational deficits of ASD and give us the initial account for neurobiological mechanisms underlying any beneficial effects of the neuropeptide . TRIAL REGISTRATION umin.ac.jp/ctr Identifier : UMIN000002241 and UMIN000004393 .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"oxytocin\", \"placebo\", \"oxytocin \\u0027s\", \"placebo-controlled\", \"oxytocin-induced\", \"oxytocin ( 24 IU )\"], \"Outcome\": [\"NVJs\", \") , the\", \".\", \"response time for NVJs\", \"behavioral neural responses\", \"brain activity of the medial prefrontal cortex during NVJs\", \", and\", \"frequency of the nonverbal information-based judgments ( NVJs\", \"effects of oxytocin\"], \"Participant\": [\"men\", \"total of 40\", \"autism\", \"individuals with autism spectrum disorders ( ASD\"]}",
"role": "assistant"
}
]
|
science.bc7_litcovid_topic_classification | science.bc7_litcovid_topic_classification.5172 | [
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nMany countries have been affected by the worldwide outbreak of COVID-19. Among Western countries, Italy has been particularly hit at the beginning of the pandemic, immediately after China. In Italy and elsewhere, women seem to be less affected than men by severe/fatal COVID-19 infection, regardless of their age. Although women and men are affected differently by this infection, very few studies consider different therapeutic approaches for the two sexes. Understanding the mechanisms underlying these differences may help to find appropriate and sex specific therapies. Here, we consider that other mechanisms are involved to explain this difference, in addition to the protection attributable to oestrogens. Several X-linked genes (such as ACE2) and Y-linked genes (SRY and SOX9) may explain sex differences. Cardiovascular comorbidities are among the major enhancers of virus lethality. In addition, the number of sex-independent, non-genetic factors that can change susceptibility and mortality is enormous, and many other factors should be considered, including gender and cultural habits in different countries.",
"role": "user"
},
{
"content": "[\"Treatment\", \"Mechanism\"]",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.8298 | [
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: TheRanBP2/Nup358isauniquevertebrateandlargescaffoldproteincomprisedofmultiplestructuralandfunctionaldomains[1-4].",
"role": "user"
},
{
"content": "[\"protein\"]",
"role": "assistant"
}
]
|
science.qasa_abstractive_qa | science.qasa_abstractive_qa.192 | [
{
"content": "Read this passage from a research paper and answer the question.\n\nContext: By comparing f_{VLAD} (-o-) methods with their corresponding f_{max} (-x-) counterpartsit is clear that VLAD pooling is much better than Max pooling for both off-the-shelf and trained representations.NetVLAD performance decreases gracefullywith dimensionality: 128-D NetVLAD performs similarly to 512-D Max(42.9% vs 38.4% recall@1 on Tokyo 24/7),resulting in four timesmore compact representation for the same performance.Furthermore, NetVLAD+whitening outperforms Max pooling convincingly whenreduced to the same dimensionality (60%).See appendix C for more details.\n\nQuestion: What metric is used to compare VLAD methods with their Max pooling counterparts?",
"role": "user"
},
{
"content": "They use in comparison the recall@1 on Tokyo 24/7",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.61303 | [
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A survey on statistical modeling and machine learning approaches to computer assisted medical intervention: Intraoperative anatomy modeling and optimization of interventional procedures \nChapter Title: Ultrasound Imaging \n1. Abstract of Cited Paper (BIB001): This article presents a feasibility and evaluation study for using 2D ultrasound in conjunction with our statistical deformable bone model within the scope of computer-assisted surgery. The final aim is to provide the surgeon with enhanced 3D visualization for surgical navigation in orthopedic surgery without the need for preoperative CT or MRI scans. We unified our earlier work to combine several automatic methods for statistical bone shape prediction and ultrasound segmentation and calibration to provide the intended rapid and accurate visualization. We compared the use of a tracked digitizing pointer and ultrasound for acquiring landmarks and bone surface points for the estimation of two cast proximal femurs. \n2. Abstract of Cited Paper (BIB002): A majority of pre-operative planning and navigational guidance during computer assisted orthopaedic surgery routinely uses threedimensional models of patient anatomy. These models enhance the surgeon’s capability to decrease the invasiveness of surgical procedures and increase their accuracy and safety. A common approach for this is to use computed tomography (CT) or magnetic resonance imaging (MRI). These have the disadvantages that they are expensive and/or induce radiation to the patient. In this paper we propose a novel method to construct a patient-specific three-dimensional model that provides an appropriate intra-operative visualization without the need for a pre or intra-operative imaging. The 3D model is reconstructed by fitting a statistical deformable model to minimal sparse 3D data consisting of digitized landmarks and surface points that are obtained intra-operatively. The statistical model is constructed using Principal Component Analysis from training objects. Our deformation scheme efficiently and accurately computes a Mahalanobis distance weighted least square fit of the deformable model to the 3D data. Relaxing the Mahalanobis distance term as additional points are incorporated enables our method to handle small and large sets of digitized points efficiently. Formalizing the problem as a linear equation system helps us to provide real-time updates to the surgeons. Incorporation of M-estimator based weighting of the digitized points enables us to effectively reject outliers and compute stable models. We present here our evaluation results using leave-one-out experiments and extended validation of our method on nine dry cadaver bones. � 2006 Elsevier B.V. All rights reserved. \n3. Abstract of Cited Paper (BIB003): Constructing a 3D surface model from sparse-point data is a nontrivial task. Here, we report an accurate and robust approach for reconstructing a surface model of the proximal femur from sparse-point data and a dense-point distribution model (DPDM). The problem is formulated as a three-stage optimal estimation process. The first stage, affine registration, is to iteratively estimate a scale and a rigid transformation between the mean surface model of the DPDM and the sparse input points. The estimation results of the first stage are used to establish point correspondences for the second stage, statistical instantiation, which stably instantiates a surface model from the DPDM using a statistical approach. This surface model is then fed to the third stage, kernel-based deformation, which further refines the surface model. Handling outliers is achieved by consistently employing the least trimmed squares (LTS) approach with a roughly estimated outlier rate in all three stages. If an optimal value of the outlier rate is preferred, we propose a hypothesis testing procedure to automatically estimate it. We present here our validations using four experiments, which include 1 leave-one-out experiment, 2 experiment on evaluating the present approach for handling pathology, 3 experiment on evaluating the present approach for handling outliers, and 4 experiment on reconstructing surface models of seven dry cadaver femurs using clinically relevant data without noise and with noise added. Our validation results demonstrate the robust performance of the present approach in handling outliers, pathology, and noise. An average 95-percentile error of 1.7-2.3 mm was found when the present approach was used to reconstruct surface models of the cadaver femurs from sparse-point data with noise added. \n4. Abstract of Cited Paper (BIB004): Abstract Statistical shape modelling potentially provides a powerful tool for generating patient-specific, 3D representations of bony anatomy for computer-aided orthopaedic surgery (CAOS) without the need for a preoperative CT scan. Furthermore, freehand 3D ultrasound (US) provides a non-invasive method for digitising bone surfaces in the operating theatre that enables a much greater region to be sampled compared with conventional direct-contact (i.e., pointer-based) digitisation techniques. In this paper, we describe how these approaches can be combined to simultaneously generate and register a patient-specific model of the femur and pelvis to the patient during surgery. In our implementation, a statistical deformation model (SDM) was constructed for the femur and pelvis by performing a principal component analysis on the B-spline control points that parameterise the freeform deformations required to non-rigidly register a training set of CT scans to a carefully segmented template CT scan. The segmented template bone surface, represented by a triangulated surface mesh, is instantiated and registered to a cloud of US-derived surface points using an iterative scheme in which the weights corresponding to the first five principal modes of variation of the SDM are optimised in addition to the rigid-body parameters. The accuracy of the method was evaluated using clinically realistic data obtained on three intact human cadavers (three whole pelves and six femurs). For each bone, a high-resolution CT scan and rigid-body registration transformation, calculated using bone-implanted fiducial markers, served as the gold standard bone geometry and registration transformation, respectively. After aligning the final instantiated model and CT-derived surfaces using the iterative closest point (ICP) algorithm, the average root-mean-square distance between the surfaces was 3.5 mm over the whole bone and 3.7 mm in the region of surgical interest. The corresponding distances after aligning the surfaces using the marker-based registration transformation were 4.6 and 4.5 mm, respectively. We conclude that despite limitations on the regions of bone accessible using US imaging, this technique has potential as a cost-effective and non-invasive method to enable surgical navigation during CAOS procedures, without the additional radiation dose associated with performing a preoperative CT scan or intraoperative fluoroscopic imaging. However, further development is required to investigate errors using error measures relevant to specific surgical procedures. \n5. Abstract of Cited Paper (BIB005): In Total Hip Replacement (THR) procedures, misalignment of the acetabular component can lead to dislocation and impingement. For the successful alignment of acetabular component, precise estimation of pelvic anatomical coordinate system is necessary. Conventional navigation systems use CT scan or fluoroscopy, or involve implanted bone fiducials or invasive probing of bony landmarks to locate the anatomical coordinate. In this paper, an ultrasound-based approach is proposed that exploits prior knowledge about the anatomy of the pelvis in the form of a 3D surface atlas. Tracked ultrasound images are utilized to extract sample points from the surface of the pelvis. A generic coordinate system in the specific patient is localized by registering these points to a statistical atlas of the pelvis in which a canonical anatomical coordinate system had been defined. This technique has been evaluated using simulation, dry bone, and cadaver experiments and was able to localize the anatomical coordinate system with the accuracy of about 1 degree. \n6. Abstract of Cited Paper (BIB006): Motivation: Spinal needle injections are technically demanding procedures. The use of ultrasound image guidance without prior CT and MR imagery promises to improve the efficacy and safety of these procedures in an affordable manner. Methodology: We propose to create a statistical shape model of the lumbar spine and warp this atlas to patient-specific ultrasound images during the needle placement procedure. From CT image volumes of 35 patients, statistical shape model of the L3 vertebra is built, including mean shape and main modes of variation. This shape model is registered to the ultrasound data by simultaneously optimizing the parameters of the model and its relative pose. Ground-truth data was established by printing 3D anatomical models of 3 patients using a rapid prototyping. CT and ultrasound data of these models were registered using fiducial markers. Results: Pairwise registration of the statistical shape model and 3D ultrasound images led to a mean target registration error of 3.4 mm, while 81% of all cases yielded clinically acceptable accuracy below the 3.5 mm threshold. \n7. Abstract of Cited Paper (BIB007): In the field of computer assisted orthopedic surgery (CAOS) the anterior pelvic plane (APP) is a common concept to determine the pelvic orientation by digitizing distinct pelvic landmarks. As percutaneous palpation is - especially for obese patients - known to be error-prone, B-mode ultrasound (US) imaging could provide an alternative means. Several concepts of using ultrasound imaging to determine the APP landmarks have been introduced. In this paper we present a novel technique, which uses local patch statistical shape models (SSMs) and a hierarchical speed of sound compensation strategy for an accurate determination of the APP. These patches are independently matched and instantiated with respect to associated point clouds derived from the acquired ultrasound images. Potential inaccuracies due to the assumption of a constant speed of sound are compensated by an extended reconstruction scheme. We validated our method with in-vitro studies using a plastic bone covered with a soft-tissue simulation phantom and with a preliminary cadaver trial \n8. Abstract of Cited Paper (BIB008): Identifying the proper orientation of the pelvis is a critical step in accurate placement of the femur prosthesis in the ::: acetabulum in Total Hip Replacement (THR) surgeries. The general approach to localize the orientation of the pelvis ::: coordinate system is to use X-ray fluoroscopy to guide the procedure. An alternative can be employing intra-operative ::: ultrasound (US) imaging with pre-operative CT scan or fluoroscopy imaging. In this paper, we propose to replace the ::: need of pre-operative imaging by using a statistical shape model of the pelvis, constructed from several CT images. We ::: then propose an automatic deformable intensity-based registration of the anatomical atlas to a sparse set of 2D ::: ultrasound images of the pelvis in order to localize its anatomical coordinate system. In this registration technique, we ::: first extract a set of 2D slices from a single instance of the pelvic atlas. Each individual 2D slice is generated based on ::: the location of a corresponding 2D ultrasound image. Next, we create simulated ultrasound images out of the 2D atlas ::: slices and calculate a similarity metric between the simulated images and the actual ultrasound images. The similarity ::: metric guides an optimizer to generate an instance of the atlas that best matches the ultrasound data. We demonstrated ::: the feasibility of our proposed approach on two male human cadaver data. The registration was able to localize a ::: patient-specific pelvic coordinate system with origin translation error of 2 mm and 3.45 mm, and average axes rotation ::: error of 3.5 degrees and 3.9 degrees for the two cadavers, respectively. \n9. Abstract of Cited Paper (BIB009): An accurate determination of the pelvic orientation is inevitable for the correct cup prosthesis placement of navigated total hip arthroplasties. Conventionally, this step is accomplished by percutaneous palpation of anatomic landmarks. Sterility issues and an increased landmark localization error for obese patients lead to the application of B-mode ultrasound imaging in the field of computer-assisted orthopedic surgery. Many approaches have been proposed in the literature to replace the percutaneous digitization by 3-D B-mode ultrasound imaging. However, the correct depth localization of the pelvic landmarks could be significantly affected by the acoustic properties of the penetrated tissues. Imprecise depth estimation could lead to a miscalculation of the pelvic orientation and subsequently to a misalignment of the acetabular cup implant. But so far, no solution has been presented, which compensates for acoustic property differences for correct depth estimation. In this paper, we present a novel approach to determine pelvic orientation from ultrasound images by applying a hierarchical registration scheme based on patch statistical shape models to compensate for differences in speed of sound. The method was validated based on plastic bones and a cadaveric specimen.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Since ultrasound (US) is portable and noninvasive modality, it is particularly suitable for intraoperative use. It has been utilized for soft tissue imaging but its bone imaging was not regarded as suitable for diagnostic purpose because US does not penetrate bone tissues. For surgical navigation purpose, however, a tracked and calibrated US can be used a non-invasive position data acquisition tool of bone surfaces instead of 3D digitizers and calibrated C-arm systems. The advantages of US are non-invasiveness and portability while the main disadvantage includes unclearness of bone boundaries and dependence of image quality on operators as well as patients. The initial validation of a US-based method was done for recovery of the cadaveric femur and pelvis using statistical deformation models (SDMs) by Chan et al. BIB001 . The SDM is regarded as a modified version of SSM and constructed from one reference pair of intensity and label images and a number of deformation fields obtained by nonrigid registration of each intensity image with the reference intensity image. SDM is regarded as an approximation of SSM. Considering accuracy and sparseness of US data, SDM is a practical choice because time-consuming preparation of a number of label images is not required. Through cadaveric validation, 3 or 4 mm accuracy was demonstrated. Its detailed descriptions are found in BIB005 . While the above works ( BIB001 , BIB005 ) required a wide area of dense US scans which were time-consuming, Talib BIB002 and Rajamani BIB003 developed a method for recovery from sparse data and applied to the proximal femur, which was further extended to combine the smoothness constraint using Mercer kernels to improve the accuracy although experiment using US data was not conducted. BIB004 . More recently, SSM-based shape reconstruction using 3D US data was also applied to the lumbar spine for needle insertion purpose BIB007 . In the above, shape recovery of the whole 3D shape of the bone was addressed. Because an US probe is scanned manually, it is a time-consuming task even using a 3D probe to scan the probe so as to cover the whole shape. This point is a limitation for clinical application. In the total hip arthroplasty (THA) surgery, determining the anatomical coordinate system of the pelvis is required to define the orientation of the acetabular cup implant. Instead of whole shape recovery, a small number of small local ares are scanned for the coordinate system determination. These areas are typical anatomical landmarks (pubic symphysis, left and right an-terior superior iliac spines) for palpation in clinical routine. Therefore, the palpations are naturally followed by US scans in the surgical procedure. Foroughi et al. first addressed this problem BIB006 , and attained clinically acceptable accuracy in dry bone and cadaver experiments. Schumann et al. applied patch-SSMs suitable for modeling multiple local areas for pelvis coordinate system determination in addition to sound speed compensation in SSM-fitting to US data BIB008 , BIB010 . One problem of SSM-fitting of US data is how to determine the bone surface edges in the US images. Although sophisticated automatic edge detection methods from US images were studied , this problem is still under investigation. Ghanavati et al. developed a SSM-fitting method which does not require pre-segmentation of US images by direct local volume matching BIB009 .",
"role": "assistant"
}
]
|
science.scientific_papers_summarization_single_doc_pubmed | science.scientific_papers_summarization_single_doc_pubmed.48758 | [
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\ninflammatory myofibroblastic tumors are an uncommon neoplasm , which are very rarely located in the pancreas .\nclinically and radiologically , this rare pancreatic tumor presents as an abdominal mass lesion that mimics other pancreatic tumors , and should therefore be considered in the differential diagnosis of pancreatic tumors .\nthe 15-year - old boy complained of abdominal pain over the left upper quadrant with intermittent fever for 7 days .\nabdominal sonography revealed one cystic lesion with a hyperechoic component in the left upper quadrant of the abdomen .\nthe pathology indicated inflammatory myofibroblastic tumors . to our knowledge , this patient is a unique case as the tumor was located in the pancreatic tail only , sparing the body .\nthe patient underwent tumor resection and segmental resection of the transverse colon with simple closure .\nsurgical excision is the standard treatment , and corticosteroids use in children need more large - scale studies .\nan inflammatory myofibroblastic tumor ( imt ) is characterized histologically by proliferation of fibrous tissue with associated moderate or marked inflammation , also called inflammatory pseudotumors or plasma cell granulomas .\nthere are not many reports on pancreatic imts because of the rare nature of the condition , so the incidence is difficult to obtain .\nthe most common gastrointestinal tract symptoms of this tumor are mass , pain , fever , weight loss , and malaise .\ndiagnosis is based on the histological findings , which consists of variable quantities of plasma cells , lymphocytes , eosinophils , foamy histiocytes , and mast cells with an inflammatory component .\nimts of the pancreas exhibit slow growth and do not undergo malignant transformation or exhibit distant metastasis , and most are surgically excised .\nwe report a 15-year - old male patient with an imt and a literature review regarding the differential diagnostic , histopathological , and therapeutic features of this condition .\na 15-year - old boy was admitted to e - da hospital , kaohsiung city , taiwan , with an intraabdominal tumor .\nhe complained of abdominal pain over the left upper quadrant with intermittent fever for 7 days .\nthe results of laboratory examinations were as follows : white blood cell count , 15,640 \n10 cells / l ; neutrophils , 79.9% ; hemoglobin , 9.7 g / dl ( or 1.50 mmol / l ) ; hematocrit , 31.1% ; platelet count , 432 10/l ; glucose , 93 mg / dl ; alanine transaminase , 14 u / l ( normal range 044 u / l ) ; aspartate transaminase , 21 u / l ( normal range 038 u / l ) ; carcinoembryonic antigen ( cea ) , 1.0 ng / ml ( normal < 5.0 ng / ml ) ; and carbohydrate antigen 199 ( ca 199 ) , 3.0 u / ml ( normal < 37.0 u / ml )\n. abdominal sonography revealed one 5.9 cm cystic lesion with a 3.7 cm hyperechoic component in the left upper quadrant of the abdomen ( fig .\nabdominal ultrasound reveals one 5.9 cm cystic lesion with a 3.7 cm hyperechoic component in the left - upper quadrant of the abdomen .\nan ultrasound - guided aspiration biopsy was performed , with aspiration cytology showing numerous neutrophils and few spindle cells , and immunohistochemical studies of the biopsy specimen indicating positivity for vimentin and muscle actin antibody ( hhf-35 ) .\nthese results indicate a tumor of a fibroblastic and muscular origin , respectively ( fig .\ntwo weeks later , postoperative findings indicated a pancreatic tail tumor , about 5 cm 5 cm 4.3 cm in size , with adhesion and invasion of the transverse colon .\nexternal to the main tumor mass , there was an inflammatory lesion with aggregates of foamy histiocytes .\nimmunohistochemical studies showed spindle cells that stained positive for actin , thereby matching the histopathological features of the biopsy specimen .\nthe patient had an uneventful hospital course , and was discharged 6 days after the operation .\nafter surgery , the patient had complete resolution of his abdominal pain , and there was no evidence of disease recurrence at 3 years follow - up .\nimts , also known as inflammatory pseudotumors or plasma cell granulomas , have been described in a wide variety of sites , including the orbit , head and neck region , salivary glands , lung and liver , spleen , retrorectal space , soft tissues , and peripheral nerves .\nthe mass may compress adjacent structures , leading to a variety of symptoms , depending on the organs involved , such as local pain , malaise , loss of appetite , wasting , and subfebrile elevation of temperature .\nhistologically , imt is composed of myofibroblastic spindle cells and inflammatory components of variable quantities of plasma cells , lymphocytes , eosinophils , foamy histiocytes , and mast cells .\nthe definitive etiology of imt is not clear ; however , some possible causes such as genetic predisposition and infection have been proposed .\nanaplastic lymphoma kinase and p80 expression as well as chromosomal rearrangements involving 2p23 have been reported to be related to imt .\nthe differential diagnoses of imc include low grade myofibroblastic sarcomas and some benign , neoplastic spindle cell lesions , such as leiomyoma and solitary fibrous tumor .\nthe concept of imt being a benign reactive lesion is doubtful owing to its high recurrence ( as high as 37% ) , the presence of regional metastases , and the evidence of acquired clonal chromosomal abnormality .\nan imt of the pancreas is not common , and clinically and radiologically , this rare pancreatic myofibroblastic tumor presents as an abdominal mass lesion that mimics a malignancy such as pancreatoblastoma , solid - pseudopapillary tumor , or insulinoma .\npancreatoblastoma , the most common pancreatic neoplasm in young children , should be considered in the differential diagnosis .\non computed tomography scan , pancreatoblastomas are heterogeneous and often multilocular with hyperechoic and enhancing septa , as opposed to imts , which usually appear as homogenous and well - defined solid masses .\nsolid - pseudopapillary tumors , which are slow - growing tumors usually located in the pancreatic tail , are often large and encapsulated or circumscribed , with marked degenerative and hemorrhagic components .\nsolid - pseudopapillary tumors are most commonly diagnosed in adolescent girls and young women ( 83%98.5% ) , especially in blacks and east asians . on ultrasonography , the tumors are usually visualized as an echogenic cyst .\ninsulinomas are composed of beta - cells and cause fasting hyperinsulinemic hypoglycemia , and are most common in the body and tail of the pancreas ( 65% ) .\nin contrast , the vast majority of gastrinomas involve the head of the pancreas ( 71% ) .\nevidence supporting an autoimmune etiology includes the association of imts with other autoimmune diseases such as sjgren syndrome and idiopathic thrombocytopenic purpura .\nnevertheless , there is no evidence that imts are associated with a preceding inflammatory or traumatic process .\nimts of the pancreas exhibit slow growth and do not undergo malignant transformation or exhibit distant metastasis .\ntheoretically , resection of the mass lesion would lead to the prompt resolution of symptoms .\nhowever , this rare pancreatic lesion may recur in some instances , such as after incomplete resection .\none adult patient was reported to experience local recurrence of a pancreatic myofibroblastic tumor about 1 year after the whipple procedure .\nimts of the pancreas are extremely rare in children , and only 11 cases have been reported in the literature ( table 1 ) .\nmost of the reported pediatric cases were girls ( 8/11 , 73% ) , with only 3 boys ( 3/11 , 27% ) .\nour patient is therefore the 4th reported male child to have this kind of pancreatic tumor .\nthere was no predominant location of the pediatric pancreatic imts in the literature review ( head : 7 cases , body with or without the tail : 4 cases ) .\nto the best of our knowledge , this boy is a unique case as the tumor was located in the pancreatic tail only , sparing the body .\ncompared to pediatric patients , in almost all adult cases , the mass lesions have been found in the pancreatic head .\nin addition , unlike in other pediatric patients , the tumor in this patient invaded the transverse colon .\nsince it is a benign lesion , the administration of corticosteroids instead of an operation has been reported in 4 adults and 1 child ( tumor size ranging from 2.24 cm ) , and all 5 cases showed remission or regression of the tumors .\nalthough there is only 1 reported case of treatment with corticosteroids in a child to date , such treatment could be considered in the future .\nin summary , imt is an uncommon mass rarely located in the pancreas , with only 11 cases reported in the literature .\nhowever , it must be included in the differential diagnosis , along with other pancreatic tumors .\nmost patients encountering imts of the pancreas undergo surgical excision , and only 4 adults and 1 child have been reported to receive medical treatment with corticosteroids .\nsuch treatment should consider in pediatric cases ; however , more studies are needed to assess corticosteroids as a treatment modality where complete surgical resection can not be performed .",
"role": "user"
},
{
"content": "abstractintroduction : inflammatory myofibroblastic tumors are an uncommon neoplasm , which are very rarely located in the pancreas . \n clinically and radiologically , this rare pancreatic tumor presents as an abdominal mass lesion that mimics other pancreatic tumors , and should therefore be considered in the differential diagnosis of pancreatic tumors.clinical findings and diagnosis : the 15-year - old boy complained of abdominal pain over the left upper quadrant with intermittent fever for 7 days . \n abdominal sonography revealed one cystic lesion with a hyperechoic component in the left upper quadrant of the abdomen . \n surgical excision was performed and postoperative findings indicated a pancreatic tail tumor . \n the pathology indicated inflammatory myofibroblastic tumors . to our knowledge , this patient is a unique case as the tumor was located in the pancreatic tail only , sparing the body.interventions and outcomes : the patient underwent tumor resection and segmental resection of the transverse colon with simple closure . \n the patient had no evidence of disease recurrence at 3 years follow-up.conclusion:inflammatory myofibroblastic tumors of the pancreas in children are extremely rare . \n surgical excision is the standard treatment , and corticosteroids use in children need more large - scale studies .",
"role": "assistant"
}
]
|
science.linnaeus_ner | science.linnaeus_ner.90 | [
{
"content": "Extract all unique entities of types [\"Species\"] from the following text.\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nRecombinant activated protein C in sepsis: endothelium protection or endothelium therapy?\nAbstract\nEndothelium dysfunction is one of the hallmarks of sepsis. Looney and Mattay, in the previous issue of Critical Care, highlight the role of activated protein C (APC) as a protective endothelial drug in septic situations. Nevertheless, the results of in vivo studies are less explicit and it remains uncertain whether these properties are relevant in human septic shock. Before considering recombinant APC (rAPC) as a therapeutic drug for the endothelium, we have to demonstrate its efficiency to protect or to reduce endothelium injury when infused a long time after the septic challenge. Nevertheless, if rAPC is efficient when infused in the early phase of septic challenge, we thus need to treat our patients earlier. At the least, genetically engineered variants have been designed with greater anti-apoptotic activity and reduced anticoagulant activity relative to wild-type APC. Further studies are needed to demonstrate the usefulness of these variants in septic shock therapy.\n\n\nThe use of recombinant activated protein C (rAPC) is one of the hottest topics in septic shock therapy. The pivotal phase 3 placebo-controlled Protein C Worldwide Evaluation in Severe Sepsis (PROWESS) clinical trial demonstrated a 19.4% relative risk reduction in 28-day mortality (6.1% absolute risk reduction) with an increased risk (3.5% versus 2.0%) of serious bleeding events compared with placebo.\nTwo recent and important articles have highlighted the role of APC as a protective endothelial drug [1] and as a cyto-protective drug [2]. Beneficial effects of rAPC in the PROWESS study were thought to be related to a reduction in coagulation and, to a lesser extent, to a reduction in inflammatory response to sepsis [3]. Post-PROWESS investigations have been associated with a myriad of cellular or animal studies demonstrating that rAPC, through reactions mediated by endothelial protein C receptor and the effector receptor, protease activated receptor-1, acts directly on cells to exert multiple cytoprotective effects including: down regulation of pro-inflammatory gene expression [4]; anti-inflammatory activities [5]; anti-apoptotic activity [6]; and protection of endothelial barrier function [1,2].\nEndothelium dysfunction is one of the hallmarks of sepsis [7]. Sepsis, per se, may induce phenotypic modulations of the endothelium through direct or indirect interaction of the endothelial layer with components of the bacterial wall, inducing a myriad of host-derived factors from endothelial cells. Phenotypic modifications include changes in pro-coagulant and proadhesive properties, increased endothelial permeability, endothelial cell apoptosis and changes in vasomotor properties; the last of these is crucial since vasoplegia is directly related to septic shock mortality. Recent animal and human data have suggested that rAPC may improve both vascular and myocardial dysfunction and vascular reactivity to catecholamine during endotoxin and/or septic challenge [8,9].\n\nFrom bench to bedside\nExperimental evidence supports a role of APC in maintaining the integrity of the endothelium through both direct and indirect mechanisms. Nevertheless, the results of in vivo studies are less explicit. In a retrospective study of septic shock in humans, Monnet and colleagues [9] demonstrated that APC infusion was associated with a decrease in the amount of delivered norepinephrine. Wiel and colleagues [10] demonstrated in a rabbit model of endotoxin induced shock that APC decreased aorta endothelial injury. By contrast, in a lung model of endotoxin induced inflammation, Robriquet and colleagues [11] demonstrated a trend to an increased vascular permeability using high doses of human APC. This last result was in sharp contrast with the results obtained by Nick and colleagues [12] in a human model of pulmonary endotoxin administration. APC appears to improve mortality in septic shock with a high APACHE 2 score and is potentially detrimental in severe sepsis. In rats, APC markedly decreased tumour necrosis factor concentrations whereas they remained unchanged in either human septic shock or endotoxemia. The question arises, therefore, as to whether it is truly possible to reconcile all these discrepancies? Moreover, can these stirring laboratory data be translated into clinical practice?\n\nLimitations of experimental studies: endothelium protection versus endothelium therapy\nClearly, in cellular and animal models, rAPC has been given either as a pre-treatment or concurrent with septic challenge. This mode of administration favours the anti-inflammatory effects of rAPC, which are particularly efficient in murine models in protecting the endothelium from cytokine-mediated apoptosis or upregulation of endothelial adhesion molecules. Thus, studies using post-injury treatment are needed in models that mimic septic shock, such as experimental pneumonia or peritonitis treated by antibiotics and volume resuscitation, and where the effects of rAPC would be investigated 16 to 24 hours after septic challenge. If we can demonstrate the efficiency of rAPC to protect or to reduce endothelium injury in these conditions, we can ultimately postulate that rAPC is also a therapeutic drug for the endothelium.\n\nThe earlier the better\nIf rAPC is efficient when infused in the early phase of septic challenge, we thus need to treat our patients earlier. At least two studies suggest that treatment with rAPC within 24 hours may carry a larger survival advantage for patients with severe sepsis, compared with those treated more than 24 hours after organ dysfunction [13]. Interventions directed at specific endpoints, when initiated early in the 'golden hours' of a patient's condition, seem to be promising [14]. The beneficial effects of earlier administration of rAPC to appropriate patients may fit into this paradigm.\n\nThe future\nExtensive in vivo and in vitro studies have focused on the cytoprotective effects of APC and most authors agree that its anticoagulant and cytoprotective effects are mediated by distinct APC structural features. Positively charged residues in surface loops in the APC protease domain have been identified as participating in the anticoagulant activity but not in cellular effects. Hence, variants have been designed with greater anti-apoptotic activity and reduced anticoagulant activity relative to wild-type APC [2]. Whether these genetically engineered variants actually provide superior pharmacological properties remains to be elucidated in vivo. Such investigations may allow the design of therapeutic APC variants with decreased anticoagulant activity to reduce the risk of bleeding on the one hand, but also with normal cytoprotective properties in order to retain full beneficial effects on sepsis outcome.\n\nAbbreviations\nPROWESS = Protein C Worldwide Evaluation in Severe Sepsis; rAPC = recombinant activated protein C.\n\nCompeting interests\nBL has received reimbursements and funding from Eli Lilly, France.",
"role": "user"
},
{
"content": "{\"Species\": [\"murine\", \"humans\", \"human\", \"patients\", \"rabbit\"]}",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.6291 | [
{
"content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: o) was administered 14 days after the induction of MFB lesion, for 10 consecutive days (Ferruzzi et al., 2009).",
"role": "user"
},
{
"content": "Method",
"role": "assistant"
}
]
|
science.data_reco_mcq_sc | science.data_reco_mcq_sc.5116 | [
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: This paper proposes a simple and efficient object relation module, which can be plugged into any modern object detection\n\nKeyphrases: object detection images\n\nDataset descriptions:\nSyn2Real: Syn2Real, a synthetic-to-real visual domain adaptation benchmark meant to encourage further development of robust domain transfer methods. The goal is to train a model on a synthetic \"source\" domain and then update it so that its performance improves on a real \"target\" domain, without using any target annotations.\nCOCO: The MS COCO (Microsoft Common Objects in Context) dataset is a large-scale object detection, segmentation, key-point detection, and captioning dataset. The dataset consists of 328K images.\nCaltech-101: The Caltech101 dataset contains images from 101 object categories (e.g., “helicopter”, “elephant” and “chair” etc.) and a background category that contains the images not from the 101 object categories.\nGuessWhat?!: GuessWhat?! is a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images.\n\nOptions: A: Syn2Real B: COCO C: Caltech-101 D: GuessWhat?!",
"role": "user"
},
{
"content": "COCO",
"role": "assistant"
}
]
|
science.chemsum_single_document_summarization | science.chemsum_single_document_summarization.49356 | [
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nC–H functionalization of amines with aryl halides by nickel-photoredox catalysis\n\nPaper sections:\nIntroduction\n<p>The direct functionalization of C(sp 3 )-H bonds constitutes a powerful method for the rapid elaboration of simple organic substrates. 1 A critical goal is to identify selective methods for converting common C-H bonds to useful functionality. Within this domain, transition metal catalysis has emerged as a prolic strategy, primarily due to its modularity and selectivity. 2 Herein, we report the selective functionalization of a-amino C(sp 3 )-H bonds with aryl halides using a nickel-photoredox dual catalyst system. This method delivers benzylic amines, a well-represented motif among bioactive natural products and pharmaceutical compounds. 3 Due to the importance and prevalence of saturated amines in organic synthesis, various mechanistically divergent strategies have been reported for the arylation of a-amino C(sp 3 )-H bonds by transition metal catalysis. 4 Seminal work from Sames and coworkers rst established the direct C(sp 3 )-H arylation of pyrrolidines catalyzed by Ru(0). 5 More recently, the Yu group has reported a Pd(II)-catalyzed a-C(sp 3 )-H arylation of thioamides using aryl boronic acids. 6 While enabling, these methods typically require elevated temperature and a metal-chelating directing group, and have not proven amenable to asymmetric catalysis. 7 In an effort to address these limitations, researchers have investigated approaches in which the C(sp 3 )-H activation and the metal-catalyzed functionalization mechanisms are decoupled (Scheme 1). Campos and co-workers at Merck pioneered a procedure for the enantioselective arylation of N-Bocpyrrolidine via an asymmetric lithiation/Pd-catalyzed Negishi coupling. 8 Additionally, the Li group described the Cu-catalyzed arylation of benzylic iminium ions derived from in situ oxidation of saturated amines. 9 Conceptually, these two approaches utilize a-anion and a-cation intermediates in cross coupling. Our laboratory sought to explore a third possibility in which a-amino radicals are engaged by a metal catalyst to achieve formal C(sp 3 )-H arylation. We expected that the ability to generate a-amino radicals at room temperature from simple amines would expand the scope and enhance the functional group tolerance within this important class of reactions. 10 Furthermore, the catalytic generation of these intermediates would obviate the need for stoichiometric activating reagents, as necessary for the a-anion and a-cation approaches.</p><p>The capture of organic radicals by transition metal catalysts remains an underexplored strategy in cross coupling. 11 Photoredox catalysis was selected for radical generation due to its complementarities with transition metal catalysis. For example, photoredox catalysts are capable of activating organic molecules at nontraditional sites (such as C-H and C-CO 2 H) and are procient in coupling saturated systems. 12 Unfortunately, the coupling partners have largely been limited to radicophiles or persistent radicals and achieving asymmetric catalysis has been challenging. The MacMillan group has reported the photoredoxcatalyzed a-C(sp 3 )-H arylation of N-aryl amines with cyanoarenes or heteroaryl halides. 13 This work highlights the ability of photoredox catalysis to generate a-amino radicals from C-H bonds under incredibly mild conditions. However, a limitation is the requirement for coupling partners derived only from electron-decient (hetero)arenes. We set out to demonstrate that combining the unique reactivity prole of photoredox catalyzed a-amino radical formation with the modularity conferred by a nickel catalyst in cross coupling would provide a useful complement to this system by signicantly expanding the scope of possible coupling partners and offering opportunities for catalyst-controlled stereoinduction. 14,15 Results and discussion 18 by a single electron transfer event to regenerate both catalysts simultaneously. 19 (1) Preliminary ndings from our laboratory in collaboration with the MacMillan laboratory using dimethylaniline as a model system revealed the feasibility of this approach. 14,20 Unfortunately, substrates containing b-hydrogens were not competent under our initially reported conditions (eqn (1)). We therefore sought to identify conditions that would enable coupling of a wider range of amine coupling partners. Our investigation began with the coupling of N-phenylpyrrolidine with 4-iodotoluene, using NiCl 2 $glyme as catalyst. The optimization efforts rst focused on identifying a ligand system for Ni capable of carrying out this reaction (Table 1, entries 1-8). Among the bi-and tridentate amine ligands evaluated, only two ligand classes, bis(pyrazolyl)pyridine (bpp) and bis(oxazoline) (BiOx), delivered measurable amounts of benzylic amine 1. Furthermore, the steric characteristics of the BiOx ligand proved to be critical to reaction efficiency. Contrary to most literature reports, 21 more encumbered ligands tended to generate more b-hydride elimination product N-phenylpyrrole. The optimized system utilizes the parent bis(oxazoline) ligand with hydrogens at the 2-position and performs a-arylation in 88% yield on 0.10 mmol scale (entry 8). Reactions employing bulkier ligands proceeded in diminished yield, with benzyl substitution delivering 54% yield and the iso-propyl variant not producing any product (entries 6 and 7). Air-stable Ni(II) salts proved most efficient in the reaction, with NiCl 2 $glyme being optimal. Ni(0) sources such as Ni(cod) 2 were not competent under the reported conditions (entry 9). 22 We also explored the reaction using lower ligand loadings. On small scale, there was virtually no difference observed between 30 mol% and 20 mol% ligand (entries 8 and 10). However, on 0.40 mmol scale, a lower variance in yield was observed at higher ligand loadings. Blue LED's are superior to compact uorescence lamps in this system due to superior overlap with the absorption spectrum of the photocatalyst (entry 11). Importantly, the amine stoichiometry can be halved with only a minor decrease in yield (entry 12). Performing the reaction under more concentrated reaction conditions resulted in erosion of reaction efficiency (entry 13). Finally, the reaction can be carried out on the benchtop, albeit in diminished yield (entry 14). As anticipated, control reactions performed without photocatalyst, Ni catalyst, or light each delivered no product. Notably, all reagents used in the optimized reaction conditions are commercially available. The electrophile scope of the reaction was evaluated (Table 2). 23 Substitution at the meta and para positions of the aryl halide is well-tolerated (1, 2), however ortho substitution results in diminished yield (3). The reaction allows for diverse electronic properties of the haloarene, including both electron-decient (4-6) and electron-rich (7-9) substrates. Notably, the high yields observed using electron-rich aryl halides demonstrate the complementarity between this approach and previously reported photoredox reactions that require electron-decient cyanoarenes. 13 A chlorinated iodoarene ( 10) is also competent in the reaction, highlighting the potential for further product elaboration. The coupling of pharmaceutically relevant heterocycles is also efficient, including indole (11) and quinoline (12). Furthermore, bromopyridines are tolerated in the reaction, albeit in diminished yield (13, 14). Finally, a vinyl triate delivers similar yields under these conditions, underscoring the potential to use other cross-coupling electrophiles under similar reaction conditions.</p><p>Next, the amine scope of the cross-coupling reaction was investigated (Table 3). An N-aryl amine is currently required for the photoredox voltage-gated mechanism of C-H activation; however, using a 2-pyridyl group in place of simple phenyl also affords product in good efficiency (16). Acyclic N-methyl-Nalkylanilines deliver good yields in the reaction (17, 18) and in the case of different alkyl groups, arylation takes place at the Table 3 Amine scope a,b,c a Yield of isolated product is the average of two runs (0.40 mmol). b 1.0 equiv. aryl iodide; 3.0 equiv. amine. c Ar ¼ p-tolyl.</p><p>methyl carbon with excellent regioselectivity. 24 A key factor for N-aryl amine success in the reaction appears to be radical nucleophilicity, with greater stereoelectronic overlap between the radical and amine lone pair providing enhanced efficiency. For instance, the yield is diminished for piperidine (21) but the atter morpholine performs well (22). Finally, N-phenylazepane is tolerated as the amine coupling partner (23).</p><p>The reaction is compatible with a number of pharmaceutically relevant functional groups (Table 4). Notably, complete retention of existing stereocenters bearing abstractable C-H bonds is observed, and the reaction takes place selectively in the presence weaker benzylic C-H bonds (24). 10 Aldehydes and electron-rich heterocycles are also well-tolerated (25). Finally, substrates bearing cyclopropanes and a,b-unsaturated amides are compatible with the reported conditions (26). These promising results indicate that this direct C-H, C-X cross-coupling technology may nd utility in the late-stage functionalization of bioactive compounds.</p><p>A key advantage of the metallophotoredox strategy over competing technologies is the ability to achieve catalystcontrolled selectivity under mild conditions. 15a, 25 The development of an enantioselective variant would circumvent the challenges associated with the harsh conditions of C-H activation and the difficulty of enantioinduction using a photoredox catalyst alone. Gratifyingly, the use of a chiral BiOx ligand generated product with modest enantioinduction, demonstrating the ability of the nickel catalyst to dictate facial selectivity in the arylation protocol (eqn (2)). 26 We hope this strategy will prove enabling in the asymmetric functionalization of C-H bonds.</p><p>(2)</p>\n\nConclusions\n<p>In summary, we have developed a direct cross-coupling of amines with aryl halides using a nickel-photoredox dual catalyst system. This mild cross coupling protocol provides direct access to benzylic amines from inexpensive and readily available starting materials without the need for prefunctionalization. The electrophile scope is also notable, with a range of electronically diverse (hetero)aryl halides and even a vinyl triate acting as viable coupling partners, making this technology complementary to existing photoredox methods. Finally, this chemistry is compatible with complex aryl halides, underscoring the opportunity for late-stage functionalization of bioactive molecules.</p><p>Table 4 Cross-coupling using complex aryl halides a,b a Yield of isolated product (0.40 mmol). b 1.0 equiv. aryl iodide; 3.0 equiv. amine.</p>",
"role": "user"
},
{
"content": "We describe the functionalization of a-amino C-H bonds with aryl halides using a combination of nickel and photoredox catalysis. This direct C-H, C-X coupling uses inexpensive and readily available starting materials to generate benzylic amines, an important class of bioactive molecules. Mechanistically, this method features the direct arylation of a-amino radicals mediated by a nickel catalyst. This reactivity is demonstrated for a range of aryl halides and N-aryl amines, with orthogonal scope to existing C-H activation and photoredox methodologies. We also report reactions with several complex aryl halides, demonstrating the potential utility of this approach in late-stage functionalization.Scheme 1 Strategies for a-amino C-H arylation where transition metals engage distinct intermediates.",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.3483 | [
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nSafety and benefit of discontinuing statin therapy in the setting of advanced , life-limiting illness : a randomized clinical trial . IMPORTANCE For patients with limited prognosis , some medication risks may outweigh the benefits , particularly when benefits take years to accrue ; statins are one example . Data are lacking regarding the risks and benefits of discontinuing statin therapy for patients with limited life expectancy . OBJECTIVE To evaluate the safety , clinical , and cost impact of discontinuing statin medications for patients in the palliative care setting . DESIGN , SETTING , AND PARTICIPANTS This was a multicenter , parallel-group , unblinded , pragmatic clinical trial . Eligibility included adults with an estimated life expectancy of between 1 month and 1 year , statin therapy for 3 months or more for primary or secondary prevention of cardiovascular disease , recent deterioration in functional status , and no recent active cardiovascular disease . Participants were randomized to either discontinue or continue statin therapy and were monitored monthly for up to 1 year . The study was conducted from June 3 , 2011 , to May 2 , 2013 . All analyses were performed using an intent-to-treat approach . INTERVENTIONS Statin therapy was withdrawn from eligible patients who were randomized to the discontinuation group . Patients in the continuation group continued to receive statins . MAIN OUTCOMES AND MEASURES Outcomes included death within 60 days ( primary outcome ) , survival , cardiovascular events , performance status , quality of life ( QOL ) , symptoms , number of nonstatin medications , and cost savings . RESULTS A total of 381 patients were enrolled ; 189 of these were randomized to discontinue statins , and 192 were randomized to continue therapy . Mean ( SD ) age was 74.1 ( 11.6 ) years , 22.0 % of the participants were cognitively impaired , and 48.8 % had cancer . The proportion of participants in the discontinuation vs continuation groups who died within 60 days was not significantly different ( 23.8 % vs 20.3 % ; 90 % CI , -3.5 % to 10.5 % ; P=.36 ) and did not meet the noninferiority end point . Total QOL was better for the group discontinuing statin therapy ( mean McGill QOL score , 7.11 vs 6.85 ; P=.04 ) . Few participants experienced cardiovascular events ( 13 in the discontinuation group vs 11 in the continuation group ) . Mean cost savings were $ 3.37 per day and $ 716 per patient . CONCLUSIONS AND RELEVANCE This pragmatic trial suggests that stopping statin medication therapy is safe and may be associated with benefits including improved QOL , use of fewer nonstatin medications , and a corresponding reduction in medication costs . Thoughtful patient-provider discussions regarding the uncertain benefit and potential decrement in QOL associated with statin continuation in this setting are warranted . TRIAL REGISTRATION clinicaltrials.gov Identifier : NCT01415934 .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"statins\", \"Statin therapy\", \"discontinue or continue\", \"receive\", \"statin\", \"statin therapy\"], \"Outcome\": [\"cost savings\", \"symptoms\", \"number of nonstatin medications\", \"quality of life ( QOL )\", \"death within 60 days ( primary outcome )\", \"Total QOL\", \"survival ,\", \"QOL\", \"corresponding reduction in medication costs\", \"Mean cost savings\", \"cardiovascular events\", \"fewer nonstatin medications\"], \"Participant\": [\"patients with limited prognosis\", \"patients with limited life expectancy\", \"cardiovascular disease\", \"381\", \"Mean ( SD ) age was 74.1 ( 11.6 ) years\", \"recent active cardiovascular disease\", \"patients in the palliative care setting\", \"advanced , life-limiting illness :\", \"adults\"]}",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.3346 | [
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Immunofluorescenceandimmunohistochemistry",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.healthver_entailment | science.healthver_entailment.4013 | [
{
"content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Young people are not immune from coronavirus and must avoid socialising and communicating it to older more vulnerable people\n\nAbstract:\nOBJECTIVES: To determine mortality rates among adults with critical illness from coronavirus disease 2019.\nDESIGN: Observational cohort study of patients admitted from March 6, 2020, to April 17, 2020.\nSETTING: Six coronavirus disease 2019 designated ICUs at three hospitals within an academic health center network in Atlanta, Georgia, United States.\nPATIENTS: Adults greater than or equal to 18 years old with confirmed severe acute respiratory syndrome-CoV-2 disease who were admitted to an ICU during the study period.\nINTERVENTIONS: None.\nMEASUREMENTS AND MAIN RESULTS: Among 217 critically ill patients, mortality for those who required mechanical ventilation was 35.7% (59/165), with 4.8% of patients (8/165) still on the ventilator at the time of this report.\nOverall mortality to date in this critically ill cohort is 30.9% (67/217) and 60.4% (131/217) patients have survived to hospital discharge.\nMortality was significantly associated with older age, lower body mass index, chronic renal disease, higher Sequential Organ Failure Assessment score, lower PaO2/FIO2 ratio, higher D-dimer, higher C-reactive protein, and receipt of mechanical ventilation, vasopressors, renal replacement therapy, or vasodilator therapy.\nCONCLUSIONS: Despite multiple reports of mortality rates exceeding 50% among critically ill adults with coronavirus disease 2019, particularly among those requiring mechanical ventilation, our early experience indicates that many patients survive their critical illness.",
"role": "user"
},
{
"content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Mortality was significantly associated with older age, lower body mass index, chronic renal disease, higher Sequential Organ Failure Assessment score, lower PaO2/FIO2 ratio, higher D-dimer, higher C-reactive protein, and receipt of mechanical ventilation, vasopressors, renal replacement therapy, or vasodilator therapy.\"]}",
"role": "assistant"
}
]
|
science.qasper_extractive_qa | science.qasper_extractive_qa.396.0 | [
{
"content": "Read the following paper excerpts and answer the question. Output a JSON object with \"answer\" and \"evidence\" fields. The answer must be extracted directly from the paper text.\n\nIf the question cannot be answered from the given text, respond with \"null\".\n\nPaper: Story Ending Generation with Incremental Encoding and Commonsense Knowledge\n\nGenerating a reasonable ending for a given story context, i.e., story ending generation, is a strong indication of story comprehension. This task requires not only to understand the context clues which play an important role in planning the plot but also to handle implicit knowledge to make a reasonable, coherent story. In this paper, we devise a novel model for story ending generation. The model adopts an incremental encoding scheme to represent context clues which are spanning in the story context. In addition, commonsense knowledge is applied through multi-source attention to facilitate story comprehension, and thus to help generate coherent and reasonable endings. Through building context clues and using implicit knowledge, the model is able to produce reasonable story endings. context clues implied in the post and make the inference based on it. Automatic and manual evaluation shows that our model can generate more reasonable story endings than state-of-the-art baselines.\n\nMulti-Source Attention (MSA)\nThe context vector ( $\\textbf {c}_{\\textbf {l}}$ ) plays a key role in representing the context clues because it captures the relationship between words (or states) in the current sentence and those in the preceding sentence. As aforementioned, story comprehension sometime requires the access of implicit knowledge that is beyond the text. Therefore, the context vector consists of two parts, computed with multi-source attention. The first one $\\textbf {c}_{\\textbf {h}j}^{(i)}$ is derived by attending to the hidden states of the preceding sentence, and the second one $\\textbf {c}_{\\textbf {x}j}^{(i)}$ by attending to the knowledge graph vectors which represent the one-hop graphs in the preceding sentence. The MSA context vector is computed as follows: \n$$\\textbf {c}_{\\textbf {l}j}^{(i)} = \\textbf {W}_\\textbf {l}([\\textbf {c}_{\\textbf {h}j}^{(i)}; \\textbf {c}_{\\textbf {x}j}^{(i)}])+\\textbf {b}_\\textbf {l},$$ (Eq. 17) \n where $\\oplus $ indicates vector concatenation. Hereafter, $\\textbf {c}_{\\textbf {h}j}^{(i)}$ is called state context vector, and $\\textbf {c}_{\\textbf {x}j}^{(i)}$ is called knowledge context vector.\nThe state context vector is a weighted sum of the hidden states of the preceding sentence $X_{i-1}$ and can be computed as follows: \n$$\\textbf {c}_{\\textbf {h}j}^{(i)} &= \\sum _{k = 1}^{l_{i-1}}\\alpha _{h_k,j}^{(i)}\\textbf {h}_{k}^{(i-1)}, \\\\\n\\alpha _{h_k,j}^{(i)} &= \\frac{e^{\\beta _{h_k,j}^{(i)}}}{\\;\\sum \\limits _{m=1}^{l_{i-1}}e^{\\beta _{h_m,j}^{(i)}}\\;},\\\\\n\\beta _{h_k,j}^{(i)} &= \\textbf {h}_{j-1}^{(i)\\rm T}\\textbf {W}_\\textbf {s} \\textbf {h}_k^{(i-1)},$$ (Eq. 18) \n where $\\beta _{h_k,j}^{(i)}$ can be viewed as a weight between hidden state $\\textbf {h}_{j-1}^{(i)}$ in sentence $X_i$ and hidden state $\\textbf {h}_k^{(i-1)}$ in the preceding sentence $X_{i-1}$ .\nSimilarly, the knowledge context vector is a weighted sum of the graph vectors for the preceding sentence. Each word in a sentence will be used as a query to retrieve a one-hop commonsense knowledge graph from ConceptNet, and then, each graph will be represented by a graph vector. After obtaining the graph vectors, the knowledge context vector can be computed by: \n$$\\textbf {c}_{\\textbf {x}j}^{(i)} &= \\sum _{k = 1}^{l_{i-1}}\\alpha _{x_k,j}^{(i)}\\textbf {g}(x_{k}^{(i-1)}), \\\\\n\\alpha _{x_k,j}^{(i)} &= \\frac{e^{\\beta _{x_k,j}^{(i)}}}{\\;\\sum \\limits _{m=1}^{l_{i-1}}e^{\\beta _{x_m,j}^{(i)}}\\;},\\\\\n\\beta _{x_k,j}^{(i)} &= \\textbf {h}_{j-1}^{(i)\\rm T}\\textbf {W} _\\textbf {k}\\textbf {g}(x_k^{(i-1)}),$$ (Eq. 19) \n where $\\textbf {g}(x_k^{(i-1)})$ is the graph vector for the graph which is retrieved for word $x_k^{(i-1)}$ . Different from $\\mathbf {e}(x_k^{(i-1)})$ which is the word vector, $\\textbf {g}(x_k^{(i-1)})$ encodes commonsense knowledge and extends the semantic representation of a word through neighboring entities and relations.\nDuring the decoding process, the knowledge context vectors are similarly computed by attending to the last input sentence $X_K$ . There is no need to attend to all the context sentences because the context clues have been propagated within the incremental encoding scheme.\n\nKnowledge Graph Representation\nCommonsense knowledge can facilitate language understanding and generation. To retrieve commonsense knowledge for story comprehension, we resort to ConceptNet BIBREF9 . ConceptNet is a semantic network which consists of triples $R=(h, r, t)$ meaning that head concept $h$ has the relation $r$ with tail concept $t$ . Each word in a sentence is used as a query to retrieve a one-hop graph from ConceptNet. The knowledge graph for a word extends (encodes) its meaning by representing the graph from neighboring concepts and relations.\nThere have been a few approaches to represent commonsense knowledge. Since our focus in this paper is on using knowledge to benefit story ending generation, instead of devising new methods for representing knowledge, we adopt two existing methods: 1) graph attention BIBREF30 , BIBREF22 , and 2) contextual attention BIBREF23 . We compared the two means of knowledge representation in the experiment.\nFormally, the knowledge graph of word (or concept) $x$ is represented by a set of triples, $\\mathbf {G}(x)=\\lbrace R_1, R_2, \\cdots , R_{N_x}\\rbrace $ (where each triple $R_i$ has the same head concept $x$ ), and the graph vector $\\mathbf {g}(x)$ for word $x$ can be computed via graph attention, as below: \n$$\\textbf {g}(x) &= \\sum _{i = 1}^{N_x}\\alpha _{R_i}[\\textbf {h}_i ; \\textbf {t}_i],\\\\\n\\alpha _{R_i} &= \\frac{e^{\\beta _{R_i}}}{\\;\\sum \\limits _{j=1}^{N_x}e^{\\beta _{R_j}}\\;},\\\\\n\\beta _{R_i} =\n(\\textbf {W}_{\\textbf {r}}&\\textbf {r}_i)^{\\rm T}\\mathop {tanh}(\\textbf {W}_{\\textbf {h}}\\textbf {h}_i+\\textbf {W}_{\\textbf {t}}\\textbf {t}_i),$$ (Eq. 23) \n where $(h_i, r_i, t_i) = R_i \\in \\mathbf {G}(x)$ is the $i$ -th triple in the graph. We use word vectors to represent concepts, i.e. $\\textbf {h}_i = \\mathbf {e}(h_i), \\textbf {t}_i = \\mathbf {e}(t_i)$ , and learn trainable vector $\\textbf {r}_i$ for relation $r_i$ , which is randomly initialized.\nIntuitively, the above formulation assumes that the knowledge meaning of a word can be represented by its neighboring concepts (and corresponding relations) in the knowledge base. Note that entities in ConceptNet are common words (such as tree, leaf, animal), we thus use word vectors to represent h/r/t directly, instead of using geometric embedding methods (e.g., TransE) to learn entity and relation embeddings. In this way, there is no need to bridge the representation gap between geometric embeddings and text-contextual embeddings (i.e., word vectors).\nWhen using contextual attention, the graph vector $\\textbf {g}(x)$ can be computed as follows: \n$$\\textbf {g}(x)&=\\sum _{i=1}^{N_x}\\alpha _{R_i}\\textbf {M}_{R_i},\\\\\n\\textbf {M}_{R_i}&=BiGRU(\\textbf {h}_i,\\textbf {r}_i,\\textbf {t}_i),\\\\\n\\alpha _{R_i} &= \\frac{e^{\\beta _{R_i}}}{\\;\\sum \\limits _{j=1}^{N_x}e^{\\beta _{R_j}}\\;},\\\\\n\\beta _{R_i}&= \\textbf {h}_{(x)}^{\\rm T}\\textbf {W}_\\textbf {c}\\textbf {M}_{R_i},$$ (Eq. 25) \n where $\\textbf {M}_{R_i}$ is the final state of a BiGRU connecting the elements of triple $R_i$ , which can be seen as the knowledge memory of the $i$ -th triple, while $\\textbf {h}_{(x)}$ denotes the hidden state at the encoding position of word $x$ .\n\nBaselines\nWe compared our models with the following state-of-the-art baselines:\nSequence to Sequence (Seq2Seq): A simple encoder-decoder model which concatenates four sentences to a long sentence with an attention mechanism BIBREF31 .\nHierarchical LSTM (HLSTM): The story context is represented by a hierarchical LSTM: a word-level LSTM for each sentence and a sentence-level LSTM connecting the four sentences BIBREF29 . A hierarchical attention mechanism is applied, which attends to the states of the two LSTMs respectively.\nHLSTM+Copy: The copy mechanism BIBREF32 is applied to hierarchical states to copy the words in the story context for generation.\nHLSTM+Graph Attention(GA): We applied multi-source attention HLSTM where commonsense knowledge is encoded by graph attention.\nHLSTM+Contextual Attention(CA): Contextual attention is applied to represent commonsense knowledge.\n\nManual Evaluation\nManual evaluations are indispensable to evaluate the coherence and logic of generated endings. For manual evaluation, we randomly sampled 200 stories from the test set and obtained 1,600 endings from the eight models. Then, we resorted to Amazon Mechanical Turk (MTurk) for annotation. Each ending will be scored by three annotators and majority voting is used to select the final label.\nWe defined two metrics - grammar and logicality for manual evaluation. Score 0/1/2 is applied to each metric during annotation.\nWhether an ending is natural and fluent. Score 2 is for endings without any grammar errors, 1 for endings with a few errors but still understandable and 0 for endings with severe errors and incomprehensible.\nWhether an ending is reasonable and coherent with the story context in logic. Score 2 is for reasonable endings that are coherent in logic, 1 for relevant endings but with some discrepancy between an ending and a given context, and 0 for totally incompatible endings.\nNote that the two metrics are scored independently. To produce high-quality annotation, we prepared guidelines and typical examples for each metric score.\nThe results of the manual evaluation are also shown in Table 1 . Note that the difference between IE and IE+MSA exists in that IE does not attend to knowledge graph vectors in a preceding sentence, and thus it does use any commonsense knowledge. The incremental encoding scheme without MSA obtained the best grammar score and our full mode IE+MSA(GA) has the best logicality score. All the models have fairly good grammar scores (maximum is 2.0), while the logicality scores differ remarkably, much lower than the maximum score, indicating the challenges of this task.\nMore specifically, incremental encoding is effective due to the facts: 1) IE is significantly better than Seq2Seq and HLSTM in grammar (Sign Test, 1.84 vs. $1.74/1.57$ , p-value= $0.046/0.037$ , respectively), and in logicality (1.10 vs. 0.70/0.84, p-value $<0.001/0.001$ ). 2) IE+MSA is significantly better than HLSTM+MSA in logicality (1.26 vs. 1.06, p-value= $0.014$ for GA; 1.24 vs. 1.02, p-value= $0.022$ for CA). This indicates that incremental encoding is more powerful than traditional (Seq2Seq) and hierarchical (HLSTM) encoding/attention in utilizing context clues. Furthermore, using commonsense knowledge leads to significant improvements in logicality. The comparison in logicality between IE+MSA and IE (1.26/1.24 vs. 1.10, p-value= $0.028/0.042$ for GA/CA, respectively), HLSTM+MSA and HLSTM (1.06/1.02 vs. 0.84, p-value $<0.001/0.001$ for GA/CA, respectively), and HLSTM+MSA and HLSTM+Copy (1.06/1.02 vs. 0.90, p-value= $0.044/0.048$ , respectively) all approve this claim. In addition, similar results between GA and CA show that commonsense knowledge is useful but multi-source attention is not sensitive to the knowledge representation scheme.\nMore detailed results are listed in Table 2 . Comparing to other models, IE+MSA has a much larger proportion of endings that are good both in grammar and logicality (2-2). The proportion of good logicality (score=2.0) from IE+MSA is much larger than that from IE (45.0%+5.0%/41.0%+4.0% vs. 36.0%+2.0% for GA/CA, respectively), and also remarkable larger than those from other baselines. Further, HLSTM equipped with MSA is better than those without MSA, indicating that commonsense knowledge is helpful. And the kappa measuring inter-rater agreement is 0.29 for three annotators, which implies a fair agreement.\n\nAppendix B: Error Analysis\nWe analyzed error types by manually checking all 46 bad endings generated by our model, where bad means the average score in terms of at least one metric is not greater than 1.\nThere are 3 typical error types: bad grammar (BG), bad logicality (BL), and other errors. The distribution of types is shown in Table 5 .\nWe also presented some typical cases for each error type in Table 6 . Note that we only took graph attention as example. The first case shows an instance of bad grammar for repetitive generation. The second case shows that our model predicted a wrong entity at the last position where car is obviously more appropriate than daughter. It happens when the attention focuses on the wrong position, but in more cases it happens due to the noise of the commonsense knowledge base. The ending of the third case contains a relevant event work on his own but the event is not consistent to the previous word relieved. Other cases show that our model is not good at dealing with rare words. However, this can be further improved by applying copy mechanism, as our future work. These errors also indicate that story ending generation is challenging, and logic and implicit knowledge plays a central role in this task.\n\nTable 1: Automatic and manual evaluation results.\n\nTable 4: Annotation statistics. n/3 agreement means n out of 3 annotators assigned the same score to an ending.\n\nQuestion: Which baselines are they using?",
"role": "user"
},
{
"content": "{\"answer\": [\"Seq2Seq\", \"HLSTM\", \"HLSTM+Copy\", \"HLSTM+Graph Attention\", \"HLSTM+Contextual Attention\"], \"evidence\": [\"We compared our models with the following state-of-the-art baselines:\", \"Sequence to Sequence (Seq2Seq): A simple encoder-decoder model which concatenates four sentences to a long sentence with an attention mechanism BIBREF31 .\", \"Hierarchical LSTM (HLSTM): The story context is represented by a hierarchical LSTM: a word-level LSTM for each sentence and a sentence-level LSTM connecting the four sentences BIBREF29 . A hierarchical attention mechanism is applied, which attends to the states of the two LSTMs respectively.\", \"HLSTM+Copy: The copy mechanism BIBREF32 is applied to hierarchical states to copy the words in the story context for generation.\", \"HLSTM+Graph Attention(GA): We applied multi-source attention HLSTM where commonsense knowledge is encoded by graph attention.\", \"HLSTM+Contextual Attention(CA): Contextual attention is applied to represent commonsense knowledge.\"]}",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.13228 | [
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nObjective assessment of image quality is fundamentally important in many image processing tasks. In this paper, we focus on learning blind image quality assessment (BIQA) models, which predict the quality of a digital image with no access to its original pristine-quality counterpart as reference. One of the biggest challenges in learning BIQA models is the conflict between the gigantic image space (which is in the dimension of the number of image pixels) and the extremely limited reliable ground truth data for training. Such data are typically collected via subjective testing, which is cumbersome, slow, and expensive. Here, we first show that a vast amount of reliable training data in the form of quality-discriminable image pairs (DIPs) can be obtained automatically at low cost by exploiting large-scale databases with diverse image content. We then learn an opinion-unaware BIQA (OU-BIQA, meaning that no subjective opinions are used for training) model using RankNet, a pairwise learning-to-rank (L2R) algorithm, from millions of DIPs, each associated with a perceptual uncertainty level, leading to a DIP inferred quality (dipIQ) index. Extensive experiments on four benchmark IQA databases demonstrate that dipIQ outperforms the state-of-the-art OU-BIQA models. The robustness of dipIQ is also significantly improved as confirmed by the group MAximum Differentiation competition method. Furthermore, we extend the proposed framework by learning models with ListNet (a listwise L2R algorithm) on quality-discriminable image lists (DIL). The resulting DIL inferred quality index achieves an additional performance gain.\n\nCited Abstract(s):\n[1]: Originally published in Contemporary Psychology: APA Review of Books, 1997, Vol 42(7), 649-649. In Foundations of Vision (see record 1995-98050-000), Brian Wandell divides the study of vision into three parts: encoding, representation, and interpretation. Each part is designed to inform students on",
"role": "user"
},
{
"content": "Existing L2R algorithms can be broadly classified into three categories based on the training data format and loss function: pointwise, pairwise, and listwise approaches. An excellent survey of L2R algorithms can be found in [1] . Here we only provide a brief overview.",
"role": "assistant"
}
]
|
science.mslr2022_cochrane_multidoc_summarization | science.mslr2022_cochrane_multidoc_summarization.68 | [
{
"content": "Based on the RCT reports below, write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article.\n\n\n\nTitle 1:\nControlled trial of anti-tuberculous chemotherapy for two years in Crohn's disease.\nAbstract 1:\nOne hundred and thirty patients with active symptoms of Crohn's disease were treated in a double blind randomised controlled trial with rifampicin, isoniazid, and ethambutol, or identical placebos for up to two years. All other treatment considered necessary was continued. Analyses were based on 126 patients, 63 in each treatment group. Thirty seven in the active and 30 in the placebo group had previous surgical procedures. There was no difference in concomitant treatment between the two groups. Thirty in the active and 46 in the placebo groups were taking corticosteroids at entry to the trial. Forty eight of 63 patients in the active and 49 of 63 in the placebo group, completed at least 12 months' therapy. Reasons for early withdrawal included pregnancy, adverse reaction, and failure to comply. There was no significant difference in the mean number of months completed between the two groups. Nineteen adverse reactions were recorded for 17 patients in the active group compared with three reactions in patients on placebo. All of the nine patients withdrawn early because of adverse reactions were in the active group. Fifteen patients on active treatment and 14 on placebo had surgery during the trial with no difference in the type of surgery required between the groups. Radiological assessments based on 98 patients at the end of the trial showed no significant differences between groups in changes of extent of disease. More patients developed strictures on placebo compared with active treatment but without a statistically significant difference. No differences were found between groups for the total prednisolone dose or the number of days on which prednisolone dose was 10 mg or above. Serial measurements of body weight and Crohn's disease activity index (CDAI) together with blood values for albumin, haemoglobin, white cell count, and platelets showed no consistent different differences between groups. There were occasional significant differences for some of these values between groups, which were not sustained. The trail provides little evidence of tangible benefit from the trail treatment.\n\n\nTitle 2:\nSulphadoxine-pyrimethamine therapy in Crohn's disease.\nAbstract 2:\nnan\n\n\nTitle 3:\nControlled trial of antimycobacterial therapy in Crohn's disease. Clofazimine versus placebo.\nAbstract 3:\nIn order to study the effect of clofazimine, a powerful antimycobacterial and antiinflammatory agent, 49 patients with active Crohn's disease were randomized to either corticosteroids plus clofazimine 100 mg daily (N = 25) or to steroids and matching placebo (N = 24). A total of 28 patients (58%) went into disease remission (clofazimine 16, placebo 12; P = NS) with a fall in disease activity score from 10.5 +/- 4.4 to 3.3 +/- 3.5. Patients were treated for a further eight months with clofazimine or placebo and 18 of 28 maintained their remission and completed the study (clofazimine 12, placebo 6; P = NS). Side effects were minor and consisted of skin rash and increased pigmentation. Clofazimine as a solitary antimycobacterial agent appears ineffective in inducing remission in Crohn's disease but may have a role in either disease maintenance or combination chemotherapy.\n\n\nTitle 4:\nAntimycobacterial therapy in Crohn's disease: results of a controlled, double-blind trial with a multiple antibiotic regimen.\nAbstract 4:\nSeveral recent reports have suggested an association of atypical mycobacteria with Crohn's disease.\n The goal of this double-blind, placebo-controlled trial was to determine the efficacy of treatment with antimycobacterial drugs in maintaining clinical remission and in reducing active inflammatory lesions.\n Forty patients (15 male) with refractory, steroid-dependent Crohn's disease were randomized to receive 2 months of tapering steroids plus either a 9-month regimen of ethambutol, clofazimine, dapsone and 1-day dose only of rifampicin (n = 22), or identical placebo.\n Three patients (two on active drug) were unable to discontinue steroids, and one patient on active drug was withdrawn for side effects during the first 2 months. Three of the remaining 19 patients on active drug relapsed during the study period, compared with 11 of 17 on placebo (log likelihood ratio = 4.6; p = 0.03). Another patient was withdrawn in remission at 5 months for anemia related to dapsone. Nine patients whose disease relapsed or persisted on placebo were crossed over to active drug; five achieved sustained remission, two failed, and two were withdrawn for side effects. Substantial endoscopic or radiologic healing did not occur.\n This study suggests that the treatment regimen with rifampicin, ethambutol, clofazimine, and dapsone is effective in relief of symptoms and maintenance of remission in some Crohn's disease patients.\n\n\nTitle 5:\nControlled trial of rifampicin and ethambutol in Crohn's disease.\nAbstract 5:\nWe pursued the possibility that Mycobacterium kansasii might be an aetiological agent in Crohn's disease by carrying out a trial of treatment with antimycobacterial drugs. Twenty seven patients with Crohn's disease took part in a two year randomised double blind, crossover, controlled trial of rifampicin plus ethambutol against placebo. Fourteen patients completed the trial; four required an operation; five were withdrawn as poor compliers, and four because of adverse effects. There was no significant difference in response to the active drugs compared with placebo when expressed in terms of a Crohn's disease activity index or any clinical indicator of disease activity. There was no suggestion that any subgroup of patients - for example, different regions of bowel affected or previous operation - were favourably affected by the drugs. There was no consistent pattern of change in prednisolone requirements although eight patients on long term sulphasalazine had a significant reduction in their plasma sulphapyridine concentrations during the active treatment period. A significant reduction in total white blood count and an increase in plasma ALT were seen during active therapy. The results of the study do not suggest that rifampicin and ethambutol have a role to play in the treatment of Crohn's disease.",
"role": "user"
},
{
"content": "Anti-tuberculous therapy may be effective in maintaining remission in patients with Crohn's disease when remission has been induced with corticosteroids combined with anti-tuberculous therapy. However, the results which support this conclusion come from a subgroup of only two trials with small numbers of patients and should be interpreted with caution. Use of this therapy cannot be recommended on the basis of this evidence.",
"role": "assistant"
}
]
|
science.healthver_entailment | science.healthver_entailment.2994 | [
{
"content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: The WHO says there is no reason to believe cold weather can kill the new coronavirus, or other diseases, for that matter.\n\nAbstract:\nThis paper investigates the correlation between the high level of coronavirus SARS-CoV-2 infection accelerated transmission and lethality, and surface air pollution in Milan metropolitan area, Lombardy region in Italy.\nFor January-April 2020 period, time series of daily average inhalable gaseous pollutants ozone (O3) and nitrogen dioxide (NO2), together climate variables (air temperature, relative humidity, wind speed, precipitation rate, atmospheric pressure field and Planetary Boundary Layer) were analyzed.\nIn spite of being considered primarily transmitted by indoor bioaerosols droplets and infected surfaces or direct human-to-human personal contacts, it seems that high levels of urban air pollution, and climate conditions have a significant impact on SARS-CoV-2 diffusion.\nExhibited positive correlations of ambient ozone levels and negative correlations of NO2 with the increased rates of COVID-19 infections (Total number, Daily New positive and Total Deaths cases), can be attributed to airborne bioaerosols distribution.\nThe results show positive correlation of daily averaged O3 with air temperature and inversely correlations with relative humidity and precipitation rates.\nViral genome contains distinctive features, including a unique N-terminal fragment within the spike protein, which allows coronavirus attachment on ambient air pollutants.\nAt this moment it is not clear if through airborne diffusion, in the presence of outdoor and indoor aerosols, this protein \"spike\" of the new COVID-19 is involved in the infectious agent transmission from a reservoir to a susceptible host during the highest nosocomial outbreak in some agglomerated industrialized urban areas like Milan is.\nAlso, in spite of collected data for cold season (winter-early spring) period, when usually ozone levels have lower values than in summer, the findings of this study support possibility as O3 can acts as a COVID-19 virus incubator.\nBeing a novel pandemic coronavirus version, it might be ongoing during summer conditions associated with higher air temperatures, low relative humidity and precipitation levels.",
"role": "user"
},
{
"content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Being a novel pandemic coronavirus version, it might be ongoing during summer conditions associated with higher air temperatures, low relative humidity and precipitation levels.\"]}",
"role": "assistant"
}
]
|
science.chemdner_ner | science.chemdner_ner.2390 | [
{
"content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nAbsence of correlation between oxysterol accumulation in lipid raft microdomains, calcium increase, and apoptosis induction on 158N murine oligodendrocytes. There is some evidence that oxidized derivatives of cholesterol, 7-ketocholesterol (7KC) and 7β-hydroxycholesterol (7βOHC), are increased in the plasma of patients with neurodegenerative diseases associated with demyelinization of the central nervous system (CNS). It was therefore of interest to investigate the effects of these oxysterols on oligodendrocytes, the myelin-forming cells in the CNS. To this end, 158N murine oligodendrocytes were treated with 7KC or 7βOHC inducing an apoptotic mode of cell death characterized by condensation/fragmentation of the nuclei, dephosphorylation of Akt and GSK3, mitochondrial depolarization involving Mcl-1, and caspase-3 activation. In contrast, under treatment with 27-hydroxycholesterol (27OHC), no cell death was observed. When the cells were stained with Fura-2, no significant Ca(2+) rise was found with the different oxysterols, whereas strong signals were detected with ionomycin used as positive control. At concentrations which induced apoptosis, 7KC but not 7βOHC accumulated in lipid rafts. Although not cytotoxic, 27OHC was mainly detected in lipid rafts. It is noteworthy that α-tocopherol (but not ellagic acid and resveratrol) was able to counteract 7KC- and 7βOHC-induced apoptosis and to decrease the accumulation of 7KC and 27OHC in lipid rafts. Thus, in 158N cells, the ability of oxysterols to trigger a mode of cell death by apoptosis involving GSK-3 and caspase-3 activation is independent of the increase in the Ca(2+) level and of their accumulation in lipid raft microdomains.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"\\u03b1-tocopherol\", \"resveratrol\", \"ellagic acid\", \"7\\u03b2OHC\", \"calcium\", \"7KC\", \"Fura-2\", \"ionomycin\", \"oxysterols\", \"7\\u03b2-hydroxycholesterol\", \"27OHC\", \"27-hydroxycholesterol\", \"oxysterol\", \"Ca(2+)\", \"7-ketocholesterol\", \"cholesterol\"]}",
"role": "assistant"
}
]
|
science.chemdner_ner | science.chemdner_ner.1380 | [
{
"content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nATP stimulates PGE(2)/cyclin D1-dependent VSMCs proliferation via STAT3 activation: role of PKCs-dependent NADPH oxidase/ROS generation. Vascular smooth muscle cells (VSMCs) that function as synthetic units play important roles in cardiovascular diseases. Extracellular nucleotides, such as ATP, have been shown to act via activation of P2 purinoceptors implicated in various inflammatory diseases, we hypothesized that extracellular nucleotides contribute to vascular diseases via up-regulation of inflammatory proteins, including cyclooxygenase-2 (COX-2) and cytosolic phospholipase A2 (cPLA2) in VSMCs. However, the mechanisms of ATP-induced cPLA2 and COX-2 expression and PGE2 synthesis remain largely unclear. We showed that pretreatment with the inhibitors of STAT3 (CBE), NADPH oxidase [diphenyleneiodonium chloride (DPI) or apocynin (APO)], ROS [N-acetyl-l-cysteine (NAC)], and PKC (Ro-318220, Gö6983, or Rottlerin) or transfection with siRNAs of STAT3 and p47(phox) markedly inhibited ATPγS-induced cPLA2 and COX-2 mRNA/protein expression and promoter activity and PGE2 secretion. ATPγS further stimulated PKC, p47(phox), and STAT3 translocation. Moreover, ATPγS-induced STAT3 phosphorylation and translocation was inhibited by pretreatment with the inhibitors of PKC, NADPH oxidase, and ROS. ATPγS enhanced NADPH oxidase activity and ROS generation in VSMCs, which were reduced by pretreatment with Ro-318220, Gö6983, or Rottlerin. Finally, we found that ATPγS significantly induced cyclin D1 expression and VSMCs proliferation, which were inhibited by pretreatment with NAC, APO, DPI, Ro-318220, Gö6983, Rottlerin, or CBE or transfection with siRNAs of COX-2 and cyclin D1. We also demonstrated that ATPγS induced cyclin D1 expression via a PGE2-dependent pathway. These results suggested that ATPγS-induced cPLA2/COX-2 expression and PGE2 secretion is mediated through a PKC/NADPH oxidase/ROS/STAT3-dependent pathway in VSMCs.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"DPI\", \"diphenyleneiodonium chloride\", \"NADPH\", \"nucleotides\", \"PGE(2)\", \"NAC\", \"apocynin\", \"N-acetyl-l-cysteine\", \"Rottlerin\", \"APO\", \"Ro-318220\", \"ATP\", \"G\\u00f66983\", \"PGE2\"]}",
"role": "assistant"
}
]
|
science.covidfact_entailment | science.covidfact_entailment.614 | [
{
"content": "Based on the abstract below, determine if the claim is supported or contradicted. Output a JSON object with the verdict (\"SUPPORT\" or \"CONTRADICT\") and evidence sentences from the abstract.\n\nClaim: Chloroquine is a potent inhibitor of sars coronavirus infection and spread\n\nText:\nBACKGROUND: Severe acute respiratory syndrome (SARS) is caused by a newly discovered coronavirus (SARS-CoV).\nNo effective prophylactic or post-exposure therapy is currently available.\nRESULTS: We report, however, that chloroquine has strong antiviral effects on SARS-CoV infection of primate cells.\nThese inhibitory effects are observed when the cells are treated with the drug either before or after exposure to the virus, suggesting both prophylactic and therapeutic advantage.\nIn addition to the well-known functions of chloroquine such as elevations of endosomal pH, the drug appears to interfere with terminal glycosylation of the cellular receptor, angiotensin-converting enzyme 2.\nThis may negatively influence the virus-receptor binding and abrogate the infection, with further ramifications by the elevation of vesicular pH, resulting in the inhibition of infection and spread of SARS CoV at clinically admissible concentrations.\nCONCLUSION: Chloroquine is effective in preventing the spread of SARS CoV in cell culture.\nFavorable inhibition of virus spread was observed when the cells were either treated with chloroquine prior to or after SARS CoV infection.\nIn addition, the indirect immunofluorescence assay described herein represents a simple and rapid method for screening SARS-CoV antiviral compounds.",
"role": "user"
},
{
"content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Favorable inhibition of virus spread was observed when the cells were either treated with chloroquine prior to or after SARS CoV infection.\"]}",
"role": "assistant"
}
]
|
science.healthver_entailment | science.healthver_entailment.5034 | [
{
"content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: the use of fever-lowering such as paracetamol (tylenol) and ibuprofen (advil) over-the-counter medicines to cope with COVID-19 symptoms is recommended.\n\nAbstract:\n: The COVID-19 pandemic is challenging our cardiovascular care of patients with heart diseases.\nIn the setting of pericardial diseases, there are two possible different scenarios to consider: the patient being treated for pericarditis who subsequently becomes infected with SARS-CoV-2, and the patient with COVID-19 who develops pericarditis or pericardial effusion.\nIn both conditions, clinicians may be doubtful regarding the safety of nonsteroidal anti-inflammatory drugs (NSAIDs), corticosteroids, colchicine, and biological agents, such as anti-IL1 agents (e.g. anakinra), that are the mainstay of therapy for pericarditis.\nFor NSAIDs, there is no clear scientific evidence linking ibuprofen and other NSAIDs to worsening of COVID-19; however, it seems prudent to continue them, if necessary to control pericarditis, and on the other hand, to prefer paracetamol for fever and systemic symptoms related to COVID-19.\nTreatments with corticosteroids, colchicine, and anakinra appear well tolerated in the context of COVID-19 infection and are currently actively evaluated as potential therapeutic options for COVID infection at different stages of the disease.\nOn this basis, currently most treatments for pericarditis do not appear contraindicated also in the presence of possible COVID-19 infection and should not be discontinued, and some (corticosteroids, colchicine, and anakinra) can be considered to treat both conditions.",
"role": "user"
},
{
"content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"For NSAIDs, there is no clear scientific evidence linking ibuprofen and other NSAIDs to worsening of COVID-19; however, it seems prudent to continue them, if necessary to control pericarditis, and on the other hand, to prefer paracetamol for fever and systemic symptoms related to COVID-19.\"]}",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.4723 | [
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nOptimization of acid suppression for patients with peptic ulcer bleeding : an intragastric pH-metry study with omeprazole . OBJECTIVE To study whether an intravenous infusion dose of omeprazole ( 80 mg + 8 mg/h ) during 24 h can be subsequently reduced with maintained effect . Second , to study the effect of oral omeprazole 20 mg given once or twice daily up to day 10 , after cessation of a 3-day intravenous infusion ( 80 mg + 8 mg/h ) . DESIGN Prospective , randomized , partly blinded study . METHODS Twelve Helicobacter pylori ( + ) patients and 12 H. pylori ( - ) subjects were included . In part I the patients received omeprazole , 80 mg + 8 mg/h , during 24 h followed by 8 , 4 or 2 mg/h . In part II the subjects received 80 mg + 8 mg/h during 3 days followed by 20 mg omeprazole orally , once or twice daily until day 10 . Intragastric pH was measured . RESULTS All H. pylori ( + ) patients showed a rapid increase of intragastric pH with a mean intragastric pH of 6.7 during the second half of the first day . After the subsequent dose reduction , the mean pH decreased to 6.1-6.2 . Patients continuing on 8 mg/h showed the best results . Likewise , all H. pylori ( - ) subjects showed a rapid and sustained reduction of intragastric acidity during the infusion . Subsequent dose reduction to 20 mg once daily led to a stable fraction of time with pH > 3 of 72 % . CONCLUSIONS Omeprazole given as a continuous infusion of 80 mg + 8 mg/h for 72 h followed by omeprazole 20 mg once daily raised the intragastric pH to and above levels alleged to allow haemostasis in patients with peptic ulcer bleeding and subsequent healing of the ulcer .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"omeprazole\", \"omeprazole .\", \"Omeprazole\"], \"Outcome\": [\"intragastric acidity\", \"intragastric pH with a mean intragastric pH\", \"mean pH\", \"intragastric pH\", \"Intragastric pH\"], \"Participant\": [\"H. pylori ( - ) subjects\", \"Helicobacter pylori ( + ) patients\", \"peptic ulcer bleeding\"]}",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.12442 | [
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nLinear regression is a classical paradigm in statistics. A new look at it is provided via the lens of universal learning. In applying universal learning to linear regression the hypotheses class represents the label @math as a linear combination of the feature vector @math where @math , within a Gaussian error. The Predictive Normalized Maximum Likelihood (pNML) solution for universal learning of individual data can be expressed analytically in this case, as well as its associated learnability measure. Interestingly, the situation where the number of parameters @math may even be larger than the number of training samples @math can be examined. As expected, in this case learnability cannot be attained in every situation; nevertheless, if the test vector resides mostly in a subspace spanned by the eigenvectors associated with the large eigenvalues of the empirical correlation matrix of the training data, linear regression can generalize despite the fact that it uses an over-parametrized'' model. We demonstrate the results with a simulation of fitting a polynomial to data with a possibly large polynomial degree.\n\nCited Abstract(s):\n[1]: During the past decade there has been an explosion in computation and information technology. With it have come vast amounts of data in a variety of fields such as medicine, biology, finance, and marketing. The challenge of understanding these data has led to the development of new tools in the field of statistics, and spawned new areas such as data mining, machine learning, and bioinformatics. Many of these tools have common underpinnings but are often expressed with different terminology. This book describes the important ideas in these areas in a common conceptual framework. While the approach is statistical, the emphasis is on concepts rather than mathematics. Many examples are given, with a liberal use of color graphics. It is a valuable resource for statisticians and anyone interested in data mining in science or industry. The book's coverage is broad, from supervised learning (prediction) to unsupervised learning. The many topics include neural networks, support vector machines, classification trees and boosting---the first comprehensive treatment of this topic in any book. @PARASPLIT This major new edition features many topics not covered in the original, including graphical models, random forests, ensemble methods, least angle regression and path algorithms for the lasso, non-negative matrix factorization, and spectral clustering. There is also a chapter on methods for wide'' data (p bigger than n), including multiple testing and false discovery rates. @PARASPLIT Trevor Hastie, Robert Tibshirani, and Jerome Friedman are professors of statistics at Stanford University. They are prominent researchers in this area: Hastie and Tibshirani developed generalized additive models and wrote a popular book of that title. Hastie co-developed much of the statistical modeling software and environment in R S-PLUS and invented principal curves and surfaces. Tibshirani proposed the lasso and is co-author of the very successful An Introduction to the Bootstrap. Friedman is the co-inventor of many data-mining tools including CART, MARS, projection pursuit and gradient boosting.",
"role": "user"
},
{
"content": "Another approach for finding the reliability of the prediction is to compose confidence intervals [1] . Confidence intervals are a pointwise measure that is sensitive to the variability of the features and sample size. Denote @math as the predicted value of @math and @math as the empirical error of the prediction, under the assumption of stochastic i.i.d data and existence of white noise, a confidence interval convergences in distribution to",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.4704 | [
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nBlind versus open approach to laparoscopic cholecystectomy : a randomized study . Intraabdominal structures may be damaged during blind introduction of the first trocar for laparoscopic operations . In this study , 150 patients with gallbladder lithiasis who underwent laparoscopy were randomly assigned to two groups , a blind ( V group ) or an open ( H group ) , in order to compare the results and the rate of complications . No mortality was observed . Major complications occurred in 3/75 ( 4 % ) patients of the V group and in 1/75 ( 1.3 % ) patient of the H group ( p < 0.05 ) . Minor complications occurred in 5/75 ( 6.7 % ) patients of either group . The achievement of pneumoperitoneum required 4.5+/-0.4 min in the V group and 3.2+/-0.2 min in the H group ( p < 0.05 ) . The open laparoscopic technique is safer and faster than the blind approach ; therefore , it is proposed that this approach be routinely used in all laparoscopic procedures .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"blind approach\", \"open laparoscopic technique\", \"Blind versus open approach to laparoscopic cholecystectomy :\", \"laparoscopic\"], \"Outcome\": [\"rate of complications\", \"mortality\", \"Minor complications\", \"Major complications\", \"achievement of pneumoperitoneum\"], \"Participant\": [\"gallbladder lithiasis\", \"laparoscopy\", \"150\"]}",
"role": "assistant"
}
]
|
science.bioasq_yesno_qa | science.bioasq_yesno_qa.812 | [
{
"content": "Based on the following biomedical documents, answer the question with either yes or no.\n\nQuestion: In clinical trials, the H3 R antagonist CEP-26401 has a positive effect on cognition, yes or no?\n\nContext: CEP-26401 is a novel orally active, brain-penetrant, high-affinity histamine H3 receptor (H3R) antagonist, with potential therapeutic utility in cognition enhancement\nhese results demonstrate potent behavioral effects of CEP-26401 in rodent models and suggest that this novel H₃R antagonist may have therapeutic utility in the treatment of cognitive and attentional disorders\nCEP-26401 is a novel orally active, brain-penetrant, high-affinity histamine H3 receptor (H3R) antagonist, with potential therapeutic utility in cognition enhancement.\nCEP-26401 (irdabisant), a potent and selective histamine H₃ receptor antagonist/inverse agonist with cognition-enhancing and wake-promoting activities.\nHowever, although a number of clinical studies examining the efficacy of H3 receptor antagonists for a variety of cognitive disorders are currently underway, no clinical proof of concept for an H3 receptor antagonist has been reported to date.\nFurther clinical studies are required to establish the potential of low-dose CEP-26401 in cognition enhancement.<br>",
"role": "user"
},
{
"content": "yes",
"role": "assistant"
}
]
|
science.chemprot_re | science.chemprot_re.1011 | [
{
"content": "Identify relationships between chemical compounds and genes in this abstract. Use only these relation types: ['DOWNREGULATOR', 'SUBSTRATE', 'INDIRECT-REGULATOR', 'PART-OF', 'MODULATOR-ACTIVATOR', 'REGULATOR', 'INHIBITOR', 'COFACTOR', 'UPREGULATOR', 'ACTIVATOR', 'ANTAGONIST', 'NOT', 'INDIRECT-DOWNREGULATOR', 'SUBSTRATE_PRODUCT-OF', 'INDIRECT-UPREGULATOR', 'AGONIST', 'PRODUCT-OF', 'MODULATOR', 'DIRECT-REGULATOR', 'UNDEFINED', 'AGONIST-INHIBITOR', 'AGONIST-ACTIVATOR', 'MODULATOR-INHIBITOR'].\n\nFormat your output as a JSON array with entries like [\"<Entity_A>\", \"<RELATION_A_B>\", \"<Entity_B>\"].\n\nAbstract:\nMonoacylglycerol lipase inhibition-induced changes in plasma corticosterone levels, anxiety and locomotor activity in male CD1 mice. The hypothalamus-pituitary-adrenal-axis is strongly controlled by the endocannabinoid system. The specific impact of enhanced 2-arachidonoylglycerol signaling on corticosterone plasma levels, however, was not investigated so far. Here we studied the effects of the recently developed monoacylglycerol lipase inhibitor JZL184 on basal and stress-induced corticosterone levels in male CD1 mice, and found that this compound dramatically increased basal levels without affecting stress responses. Since acute changes in corticosterone levels can affect behavior, JZL184 was administered concurrently with the corticosterone synthesis inhibitor metyrapone, to investigate whether the previously shown behavioral effects of JZL184 are dependent on corticosterone. We found that in the elevated plus-maze, the effects of JZL184 on \" classical \" anxiety-related measures were abolished by corticosterone synthesis blockade. By contrast, effects on the \" ethological \" measures of anxiety (i.e. risk assessment) were not affected by metyrapone. In the open-field, the locomotion-enhancing effects of the compound were not changed either. These findings show that monoacylglycerol lipase inhibition dramatically increases basal levels of corticosterone. This endocrine effect partly affects the anxiolytic, but not the locomotion-enhancing effects of monoacylglycerol lipase blockade.",
"role": "user"
},
{
"content": "[[\"JZL184\", \"INHIBITOR\", \"monoacylglycerol lipase\"]]",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.1942 | [
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Plasmamembraneswerepreparedaspreviouslydescribed[31].",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.mslr2022_ms2_multidoc_summarization | science.mslr2022_ms2_multidoc_summarization.4109 | [
{
"content": "Based on the RCT reports below, write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article.\n\n\n\nTitle 1:\nInhalation of diesel exhaust and allergen alters human bronchial epithelium DNA methylation\nAbstract 1:\nBackground : Allergic disease affects 30 % to 40 % of the world 's population , and its development is determined by the interplay between environmental and inherited factors . Air pollution , primarily consisting of diesel exhaust emissions , has increased at a similar rate to allergic disease . Exposure to diesel exhaust may play a role in the development and progression of allergic disease , in particular allergic respiratory disease . One potential mechanism underlying the connection between air pollution and increased allergic disease incidence is DNA methylation , an epigenetic process with the capacity to integrate gene‐environment interactions . Objective : We sought to investigate the effect of allergen and diesel exhaust exposure on bronchial epithelial DNA methylation . Methods : We performed a r and omized crossover‐controlled exposure study to allergen and diesel exhaust in humans , and measured single‐site ( CpG ) resolution global DNA methylation in bronchial epithelial cells . Results : Exposure to allergen alone , diesel exhaust alone , or allergen and diesel exhaust together ( coexposure ) led to significant changes in 7 CpG sites at 48 hours . However , when the same lung was exposed to allergen and diesel exhaust but separated by approximately 4 weeks , significant changes in more than 500 sites were observed . Furthermore , sites of differential methylation differed depending on which exposure was experienced first . Functional analysis of differentially methylated CpG sites found genes involved in transcription factor activity , protein metabolism , cell adhesion , and vascular development , among others . Conclusions : These findings suggest that specific exposures can prime the lung for changes in DNA methylation induced by a subsequent insult\n\n\nTitle 2:\nHistone acetylase and deacetylase activity in alveolar macrophages and blood mononocytes in asthma.\nAbstract 2:\nHistone acetylation status is a key factor in the regulation of inflammatory gene transcription . We investigated the activity of histone acetylases ( HAT ) and deacetylases ( HDAC ) , and the effect of glucocorticoids in alveolar macrophages ( AM ) and peripheral blood mononuclear cells ( P BMC ) from subjects with asthma . Bronchoalveolar lavage was performed in 10 patients with intermittent asthma , 8 with persistent asthma , and 10 healthy control subjects . P BMC s and granulocytes were isolated from six patients with mild and severe asthma , before and after a 7-day course of prednisolone ( 30 mg/day ) . AMs were isolated for HDAC assay or incubated with dexamethasone ( 1 microM ) . HAT activity was increased ( 1.43 + /- 0.1 vs. 1.01 + /- 0.1 st and ard units/10 microg , p < 0.05 ) , and HDAC activity was reduced ( 3031 + /- 243 vs. 5004 + /- 164 arbitrary fluorescence units/10 microg , p < 0.001 ) in AMs of subjects with asthma compared with control subjects . Dexamethasone suppressed LPS-induced granulocyte macrophage-colony stimulating factor , tumor necrosis factor-alpha , and interleukin-8 release by 83 + /- 1 % , 51 + /- 7 % and 20 + /- 9 % ( p < 0.001 ) , respectively . Similar effects were seen on nuclear factor-kappaB inhibition , and interleukin-8 release was further reduced by the HDAC enhancer , theophylline ( 37 + /- 6 % ) . Prednisolone increased HDAC activity in P BMC s from subjects with mild asthma . The increased inflammatory response in asthma may be due to reduced HDAC and enhanced HAT activity . Glucocorticoids and theophylline may downregulate the inflammatory response by modulating HAT and HDAC activity , and nuclear factor-kappaB activation\n\n\nTitle 3:\nThe development and prediction of atopy in high-risk children: follow-up at age seven years in a prospective randomized study of combined maternal and infant food allergen avoidance.\nAbstract 3:\nBACKGROUND The natural history of allergic disease and its potential for prevention merit close examination because of the explosive worldwide increase in the prevalence and morbidity of atopic disorders . This study examines the development of atopy at age 7 years in 165 children in a high-risk cohort , previously reported from birth to age 4 years . METHODS In this prospect i ve , r and omized , controlled study of food allergen avoidance in infancy , the prophylactic-treated group consisted of infants whose mothers avoided cow 's milk , egg , and peanut during the last trimester of pregnancy and lactation and who , themselves , avoided cow 's milk until age 1 year ( casein hydrolysate supplementation before age 1 ) , egg until age 2 years , and peanut and fish until age 3 years . The control group consisted of maternal/infant pairs who followed st and ard feeding practice s. RESULTS Despite a significant reduction in food allergy and milk sensitization before age 2 years , none of the following differed between the groups at age 7 years : food allergy , atopic dermatitis , allergic rhinitis , asthma , any atopic disease , lung function , food or aeroallergen sensitization , serum IgE level , or presence of nasal eosinophils or nasal basophilic cells . Children with food allergy by 4 years evidence d higher 7-year ( current ) prevalences of allergic rhinitis and asthma ( p < 0.01 ) . Atopic diseases/parameters at age 7 years were shown , by multivariate analysis ( p < 0.05 ) , to be associated with several genetic and environmental risk factors ( male gender , maternal nonwhite ethnicity and asthma , and household smoking ) , as well as predictive atopic markers during infancy ( elevated serum IgE level ; egg , cow 's milk , and peanut sensitization ; and nasal eosinophils and nasal basophilic cells ) . CONCLUSIONS These findings help to : ( 1 ) eluci date the natural history of atopic disease in high-risk children ; ( 2 ) document the progression of allergy from atopic dermatitis , food allergy , and food sensitization to respiratory allergy and aeroallergen sensitization despite food allergy prevention in infancy ; ( 3 ) identify allergy predictive markers ; and ( 4 ) exp and our appreciation of the interactions of genetic and environmental factors in the development of atopy",
"role": "user"
},
{
"content": "We found that environmental factors during early development are related to epigenetic effects that may be associated with a higher risk of CRDs .\nEpigenetic dysregulation of gene expression of the histone deacetylase ( HDAC ) and histone acetyltransferase gene families was likely involved in lung health of slum dwellers .\nRespiratory-related environmental exposures influence HDAC function and deoxyribonucleic acid methylation and are important risk factors in the development of CRD .",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.5008 | [
{
"content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: Finding a serum -hCG level greater than the discriminatory zone, in combination with an indeterminate ultrasonography, has been shown to be associated with ectopic pregnancy.(8,9) Typical transvaginal discriminatory zone values in the literature range from 1,500 to 3,000 mIU/mL and have largely been developed according to radiology-performed ultrasonography in outpatients,(10) with intrauterine pregnancy defined as the visualization of a gestational sac.",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_elife_single_doc_summ | science.scientific_lay_summarisation_elife_single_doc_summ.2168 | [
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Spatiotemporal dynamics of PIEZO1 localization controls keratinocyte migration during wound healing\nArticle:\nAbstract:\nKeratinocytes, the predominant cell type of the epidermis, migrate to reinstate the epithelial barrier during wound healing. Mechanical cues are known to regulate keratinocyte re-epithelialization and wound healing; however, the underlying molecular transducers and biophysical mechanisms remain elusive. Here, we show through molecular, cellular, and organismal studies that the mechanically activated ion channel PIEZO1 regulates keratinocyte migration and wound healing. Epidermal-specific Piezo1 knockout mice exhibited faster wound closure while gain-of-function mice displayed slower wound closure compared to littermate controls. By imaging the spatiotemporal localization dynamics of endogenous PIEZO1 channels, we find that channel enrichment at some regions of the wound edge induces a localized cellular retraction that slows keratinocyte collective migration. In migrating single keratinocytes, PIEZO1 is enriched at the rear of the cell, where maximal retraction occurs, and we find that chemical activation of PIEZO1 enhances retraction during single as well as collective migration. Our findings uncover novel molecular mechanisms underlying single and collective keratinocyte migration that may suggest a potential pharmacological target for wound treatment. More broadly, we show that nanoscale spatiotemporal dynamics of Piezo1 channels can control tissue-scale events, a finding with implications beyond wound healing to processes as diverse as development, homeostasis, disease, and repair.\nIntroduction:\nThe skin, the largest organ of the body, serves as a barrier against a myriad of external insults while also performing important sensory and homeostatic functions. Cutaneous wounds interfere with all these functions and expose the body to an increased risk of infection, disease, and scar formation( Evans et al., 2013). During the repair of wounded skin, the migration of keratinocytes from the wound edge into the wound bed plays an essential step in re-establishing the epithelial barrier and restoring its protective functions( Kirfel and Herzog, 2004; Gantwerker and Hom, 2011). Accumulating evidence has shown that mechanical cues and cell-generated traction forces in keratinocytes play an important role in regulating the healing process and wound closure( Evans et al., 2013; Rosińczuk et al., 2016; Brugués, 2014; Hiroyasu et al., 2016; Huang et al., 2017; Ladoux and Mège, 2017). However, the molecular identity of keratinocyte mechanotransducers that control re-epithelialization remains unknown. Cells are able to sense and detect mechanical forces, converting them into biochemical signals through the process of mechanotransduction. One class of mechanosensors utilized by cells are mechanically activated ion channels which offer the unique ability for cells to rapidly detect and transduce mechanical forces into electrochemical signals( Nourse and Pathak, 2017; Murthy et al., 2017). The Piezo1 ion channel has been shown to play an important role in a variety of cell types, and it regulates several key biological processes including vascular and lymphatic development, red blood cell volume regulation, stem cell fate, the baroreceptor response, cardiovascular homeostasis, cartilage mechanics, and others( Li et al., 2014; Ranade et al., 2014; Pathak et al., 2014; Rocio Servin-Vences et al., 2017; Zeng et al., 2018; Nonomura et al., 2018; Cahalan et al., 2015; Lee et al., 2014; Rode et al., 2017). Previous studies in MDCK cells and in zebrafish larvae have demonstrated the importance of the channel in homeostatic regulation of epithelial cell numbers( Gudipaty et al., 2017; Eisenhoffer et al., 2012). As yet, the role of Piezo1 in skin wound healing, an important epithelial function, has not been investigated. We asked whether PIEZO1 may function as a mechanosensor regulating keratinocyte re-epithelialization during the wound healing process. Here, we show that PIEZO1 activity increases cellular retraction, reducing the efficiency of keratinocyte migration and wound healing, and that inhibition of PIEZO1 results in faster wound healing in vitro and in vivo. The channel exhibits dynamic changes in its subcellular localization, concentrating at areas of the wound edge and causing local retraction at these regions.\nDiscussion:\nOur findings demonstrate that epidermal-specific Piezo1 knockout resulted in faster wound healing in mice, and conversely a Piezo1-GoF mutation slowed wound healing. We recapitulate this observation in vitro, and show through a combination of orthogonal assays in single cells and in monolayers that PIEZO1 activity modulated by dynamic spatial reorganization of the channel protein slows keratinocyte cell migration during re-epithelialization. These findings provide physiological evidence for the role of a mechanically activated ion channel in wound healing and suggest potential therapeutics through a targeted inhibition of PIEZO1, perhaps applied topically, that could help speed wound healing, potentially reducing risk of infection. However, further in-depth analysis regarding the quality of wound healing following PIEZO1 inhibition is required. Given that speedy wound healing affords an evolutionary advantage and that PIEZO1 activity slows wound healing, a puzzling question arises regarding the role of PIEZO1 expression in keratinocytes. Perhaps, there is an advantage to slower healing in the presence of PIEZO1, or the channel is important for other functions in keratinocytes. Consistent with the latter idea, a recent study by Moehring et al. reports that keratinocyte PIEZO1 is critical for sensory afferent firing and behavioral responses to innocuous and noxious mechanical stimulation( Moehring et al., 2020). As such, it would also be important to determine that inhibiting Piezo1 to speed wound healing does not have detrimental effects on normal mechanosensation. Ca2+ signals control many aspects of cell migration, including lamellipodial dynamics, traction force generation, rear retraction, focal adhesion turnover, and migration directionality( Wei et al., 2012; Tsai et al., 2015; Canales et al., 2019). While mechanically activated ion channels were proposed to contribute to Ca2+ signaling in single cell migration in vitro as early as 20 years ago( Lee et al., 1999; Doyle et al., 2004; Wei et al., 2009; Tsai and Meyer, 2012; Patkunarajah et al., 2020), many important questions have remained unanswered, including those related to channel identity, functional effects in collective cell migration, and physiological contribution during wound healing. Using chemical activation as well as genetic modulation of PIEZO1, we provide evidence for its involvement in regulating cellular retraction events in single cells as well as in collective cell migration during keratinocyte re-epithelialization. Notably, the effects we observed on scratch wound closure and cell edge retraction speeds following Yoda1 activation of PIEZO1 were consistently larger than the effects of Piezo1-GoF mutation. This is not surprising as the GoF mutation increases ion flux through PIEZO1 channels, without significantly affecting channel activation( Glogowska et al., 2017; Bae et al., 2013). Thus, channel activation in GoF keratinocytes is expected to occur based on subcellular localization of PIEZO1 and of the cellular forces that activate them. In contrast, Yoda1 treatment would globally activate PIEZO1 channels in the plasma membrane, leading to a larger effect. One of the most surprising findings to emerge from our studies is the highly dynamic nature of the spatial localization of PIEZO1 channels in migrating cells. Based on this finding, we propose a novel mechanism regulating cell migration wherein spatiotemporal enrichment of PIEZO1 channels serves to localize and amplify channel activity, and regulate contractile forces, to spatially control cellular retraction events. Piezo1 has been implicated in cell migration in different cell types in vitro( Maneshi et al., 2018; McHugh et al., 2012; Chubinskiy-Nadezhdin et al., 2019; Hung et al., 2016; Li et al., 2015; Yu et al., 2020); however, reports of the effect of the channel on migration have varied in the literature, with channel activity supporting migration in some cell types and inhibiting migration in others. Perhaps, a determining factor of the channel’s impact on cell migration is how spatiotemporal localization of the channel is regulated in a given cell type. Our observations spark several new questions regarding the regulation and functional impacts of PIEZO1’s localization and clustering dynamics. Interestingly, molecular dynamics simulations of PIEZO1 suggest that interactions between neighboring PIEZO1 channels may enable cooperative gating between channels( Jiang et al., 2021). Clustering of the bacterial mechanosensitive channel MscL has also been reported, but computational simulations predict these clusters in fact decrease channel open probability, providing a defence against unwanted channel gating that may cause osmotic shock( Paraschiv et al., 2020; Grage et al., 2011). Experimental evidence for functional interaction between PIEZO1 channels remains pending and two recent patch clamp studies examining this question come to divergent conclusions( Lewis and Grandl, 2021; Wijerathne et al., 2021). It is well established that retraction during cell migration occurs due to force generated by myosin II( Cramer, 2013; Ridley, 2011; Aguilar-Cuenca et al., 2014), and we previously showed that myosin II-mediated cellular traction forces elicit localized Piezo1 Ca2+ flickers( Ellefsen et al., 2019). Since myosin II activation is enhanced by intracellular Ca2+( Somlyo and Somlyo, 2003), we speculate that Piezo1 may induce cellular retraction through a feedforward loop between Piezo1 and myosin II: traction force generation by myosin II cause Piezo1-mediated Ca2+ influx, which in turn may increase myosin II phosphorylation and force generation through the Ca2+-regulated Myosin Light Chain Kinase. Enrichment of Piezo1 in subcellular regions would amplify this effect and result in a localized retraction. Supporting this model, Piezo1-mediated Ca2+ events were recently found to elicit retraction of developing endothelial tip cells during vascular pathfinding( Liu et al., 2020). Efficient migration requires protrusion of the cell lamellipodia which is stabilized via the formation of focal adhesions. Without stabilization, lamellipodia protrusions retract backward causing membrane ruffling and reducing migration speed( Borm et al., 2005). We observe an increase in cell edge velocity in keratinocytes with increased PIEZO1 activity( in both Piezo1-GoF and Yoda1-treated cells) indicating that PIEZO1-mediated effects on cell edge velocity may be the predominant mechanism contributing to inefficient migration. An intriguing paradox observed in our data is that both Piezo1-cKO and Piezo1-GoF keratinocytes exhibit straighter migration trajectories. We also observe that PIEZO1 localization and increased activity appears linked to cell polarization; thus one possible explanation that warrants further study is that the GoF mutation stabilizes PIEZO1 clusters so that once the channels localize to the rear of the cell, the cell retains its polarization and migration directionality. Cell migration involves a complex orchestration of events, including sub-cellular dynamics in which cytoskeletal processes in different compartments of the cell need to be implemented in a precise spatiotemporal order. How this is achieved remains an open question. Our findings suggest that spatiotemporal enrichment dynamics of Piezo1 play a role in this coordination. More broadly, our findings provide a mechanism by which nanoscale spatial dynamics of Piezo1 channels can control tissue-scale events, a finding with implications beyond wound healing to processes as diverse as development, homeostasis, disease, and repair.",
"role": "user"
},
{
"content": "The skin is the largest organ of the body . It enables touch sensation and protects against external insults . Wounding of the skin exposes the body to an increased risk of infection , disease and scar formation . During wound healing , the cells in the topmost layer of the skin , called keratinocytes , move in from the edges of the wound to close the gap . This helps to restore the skin barrier . Previous research has shown that the mechanical forces experienced by keratinocytes play a role in wound closure . Several proteins , called mechanosensors , perceive these forces and instruct the cells what to do . Until now , it was unclear what kind of mechanosensors control wound healing . To find out more , Holt et al . studied a recently discovered mechanosensor ( for which co-author Ardem Pataputian received the Nobel Prize in 2021 ) , called Piezo1 , using genetically engineered mice . The experiments revealed that skin wounds in mice without Piezo1 in their keratinocytes healed faster than mice with normal levels of Piezo1 . In contrast , skin wounds of mice with increased levels of Piezo1 in their keratinocytes healed slower than mice with normal levels of Piezo1 . The same pattern held true for keratinocytes grown in the laboratory that had been treated with chemicals to increase the activity of Piezo1 . To better understand how Piezo1 slows wound healing , Holt et al . tracked its location inside the keratinocytes . This revealed that the position of Piezo1 changes over time . It builds up near the edge of the wound in some places , and at those regions makes the cells move backwards rather than forwards . In extreme cases , an increased activity of Piezo1 can cause an opening of the wound instead of closing it . These findings have the potential to guide research into new wound treatments . But first , scientists must confirm that blocking Piezo1 would not cause side effects , like reducing the sensation of touch . Moreover , it would be interesting to see if Piezo1 also plays a role in other important processes , such as development or certain diseases .",
"role": "assistant"
}
]
|
science.bc7_litcovid_topic_classification | science.bc7_litcovid_topic_classification.10483 | [
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nObjectives: To determine whether the frequencies of SARS-CoV-2-specific T cells are sufficiently high in the blood of convalescent donors and whether it is technically feasible to manufacture clinical-grade products overnight for T-cell therapy and assessment of COVID-19 immunity. Methods: One unit of whole blood or leukapheresis was collected from each donor following standard blood bank practices. The leukocytes were stimulated using overlapping peptides of SARS-CoV-2, covering the immunodominant sequence domains of the S protein and the complete sequence of the N and M proteins. Thereafter, functionally reactive cells were enriched overnight using an automated device capturing IFNgamma-secreting cells. Results: From 1 x 10(9) leukocytes, a median of 0.98 x 10(6) (range 0.56-2.95) IFNgamma + T cells were produced from each of the six donors, suggesting a high frequency of SARS-CoV-2 reactive T cells in their blood, even though only one donor had severe COVID-19 requiring mechanical ventilation whereas the other five donors had minor symptoms. A median of 57% of the enriched T cells were IFNgamma+ (range 20%-74%), with preferential enrichment of CD56+ T cells and effector memory T cells. TCRVbeta-spectratyping confirmed distinctively tall oligoclonal peaks in final products. With just six donors, the probability that a recipient would share at least one HLA allele with one of the donors is >88% among Caucasian, >95% among Chinese, >97% among Malay, and >99% among Indian populations. Conclusions: High frequencies of rapid antigen-reactive T cells were found in convalescent donors, regardless of severity of COVID-19. The feasibility of clinical-grade production of SARS-CoV-2-specific T cells overnight for therapeutics and diagnostics is revealed.",
"role": "user"
},
{
"content": "[\"Treatment\", \"Mechanism\"]",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.10490 | [
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Survey: When semantics meet crowdsourcing to enhance big data variety \nChapter Title: IV. DISCUSSION \n1. Abstract of Cited Paper (BIB001): The interleaving of human, machine, and semantics have the potential to overcome some of the issues currently surrounding Big Data. Semantic technologies, in particular, have been shown to adequately address data integration when dealing with data size, variety, and complexity of data sources – the very definition of Big Data. Yet, for some tasks, semantic algorithms do not reach a level of accuracy that many production environments require. In this position paper, we argue that augmenting such algorithms with crowdsourcing is a viable solution. In particular, we examine Big Data within the geosciences and describe outstanding questions regarding the merger of crowdsourcing and semantics. We present our ongoing work in this area and discuss directions for future research. \n2. Abstract of Cited Paper (BIB002): The explosion of social and sensor data available on the Web provides both challenges and opportunities for their exploitation in contemporary decision support systems. In this paper, we propose a framework for aggregating and linking heterogeneous data from various sources and transforming them to Linked Data. This allows reuse and integration of the produced data with other data resources enabling spatial business intelligence for various domain-specific applications. Our framework can be easily applied to aggregate and interlink data from various types of sources: legacy systems, citizen sensor data, sensor data, and open web data. This paper outlines a number of possible applications of the framework and discusses in detail an example use case where the proposed methodology facilitates identification of business opportunities in London City through analysis of various information facets including property pricing, population spending, sensor, and social data. \n3. Abstract of Cited Paper (BIB003): Images depicting key findings of research papers contain rich information derived from a wide range of biomedical experiments, e.g. charts, gels, anatomical features, and protein or DNA sequence alignments. Efficient practices for accessing biomedical images are key to allowing the timely transfer of information from the research community to peer investigators and other healthcare practitioners. Searching for images of a certain type is error prone as images are still opaque to information retrieval and knowledge extraction engines due to the absence of explicit descriptions or annotation of the image contents. Moreover, traditional biomedical search engines which search image captions for relevant keywords only offer syntactic search mechanisms without regard for the exact meaning of the query. In order to resolve these challenges and to support interoperability and reusability of biomedical images, we propose a general framework for semantic enrichment of biomedical images called SEBI. SEBI utilizes the information extracted from images as seed data to harvest new annotations from heterogeneous online biomedical resources. The framework incorporates a variety of knowledge infrastructure components and services including image feature extraction, Semantic Web data services, linked open data and the crowd-sourced annotation. Together, these resources make it possible to automatically and/or semi-automatically discover and semantically interlink new information in a manner that supports semantic search for images. Project Page: https://code.google.com/p/sebi/\n\nLiterature Review:",
"role": "user"
},
{
"content": "The projects that were detailed in III, and summarized in table I, are analyzed and compared according to the following characteristics: 1) Domain: The problems of data integration that have been exposed in the current study arise each in a very distinctive domain e.g. geoscience research, sensor Data, urban environments and biomedical image. 2) Dataset: Each of these projects treats very diverse data sources, ranging from structured (Public transport timetables, professional society membership, Job density,) semi-structured (Yale Image Finder, OpenStreetMap,) and unstructured (Flicker, conference abstracts, social media,). 3) Semantic techniques: Among these projects, the LOD is a common technique that is used to integrate and access data at various levels of complexities. Additional techniques are also used: • Semantic Provenance, PAV ontology and Vocabulary of Interlinked Datasets for metadata and annotation. • Semantic Automatic Discovery and Integration (SADI) for data integration. • Linked Stream Middleware, Semantic Sensor Network for sensor data integration. • Ontology Design Patterns for ontology alignment. 4) Crowdsourcing techniques: The role of crowdsourcing varies according to the case study issue. It was used for data validation in Ocean sciences, for data integration in Urban-Match and Biomedical image, and for data annotation in Geoscience research. The notable difference is with Urban-Match project BIB001 , which identifies the mechanics used to enhance the crowdsourcing quality. We can deduce that each one of the projects adopts different techniques in order to accomplish its objective of data integration. The main common thing is the use of Linked Data technology as an information infrastructure for integration of data from disparate sources. Furthermore, the output of all the studied integration processes is a linked open data repository. It's clear that Linked Open data can solve some of the problems of Big Data integration and reduce heterogeneity aspect of Big Data. However, the case studies demonstrate that the integration of linked open data is challenged by the several quality issues and problems that the linked data paradigm is facing. Many of these quality issues require crowdsourcing techniques to be solved. As a result, all these case studies combine the use of LOD as a semantic web technology with different crowdsourcing techniques to solve the big data variety. We can see that: • Geosciences BIB002 uses Crowdsourcing Entity Linking to link two entities with a new relation. • Ocean link uses Crowdsourcing Ontology Alignment to specify the correspondences between ontology entities. • Linked Sensor Framework BIB003 uses crowdsourced data enrichment to clean and enrich data for accuracy. • UrbanMatch BIB001 uses Game With a Purpose to link points of interests with the most representative photos. • Biomedical Image BIB004 uses Crowdsourcing Image Annotation to allow users to annotate, delete, or update annotations. Even though different techniques were used in these exposed Crowd annotation case studies, we succeeded in identifying a common workflow that could be used in any scenario, as we will see in more detail in the next section.",
"role": "assistant"
}
]
|
science.data_reco_mcq_mc | science.data_reco_mcq_mc.2172 | [
{
"content": "Based on the dataset descriptions below, which datasets would be suitable for the following research question? Your response should be a JSON array.\n\nQuestion: PARIS is a probabilistic approach for automatic ontology alignment.\n\nKeywords: ontology alignment text\n\nDataset descriptions:\nYAGO: Yet Another Great Ontology (YAGO) is a Knowledge Graph that augments WordNet with common knowledge facts extracted from Wikipedia, converting WordNet from a primarily linguistic resource to a common knowledge base. YAGO originally consisted of more than 1 million entities and 5 million facts describing relationships between these entities.\nParis-Lille-3D: The Paris-Lille-3D is a Benchmark on Point Cloud Classification. The Point Cloud has been labeled entirely by hand with 50 different classes.\nSNIPS: The SNIPS Natural Language Understanding benchmark is a dataset of over 16,000 crowdsourced queries distributed among 7 user intents of various complexity: SearchCreativeWork (e.g. Find me the I, Robot television show), GetWeather (e.g.\nCCAligned: CCAligned consists of parallel or comparable web-document pairs in 137 languages aligned with English. These web-document pairs were constructed by performing language identification on raw web-documents, and ensuring corresponding language codes were corresponding in the URLs of web documents.\nFashionpedia: Fashionpedia consists of two parts: (1) an ontology built by fashion experts containing 27 main apparel categories, 19 apparel parts, 294 fine-grained attributes and their relationships; (2) a dataset with everyday and celebrity event fashion images annotated with segmentation masks and their associated per-mask fine-grained attributes, built upon the Fashionpedia ontology.\nOpusparcus: Opusparcus is a paraphrase corpus for six European languages: German, English, Finnish, French, Russian, and Swedish. The paraphrases are extracted from the OpenSubtitles2016 corpus, which contains subtitles from movies and TV shows.\nDBpedia: DBpedia (from \"DB\" for \"database\") is a project aiming to extract structured content from the information created in the Wikipedia project. DBpedia allows users to semantically query relationships and properties of Wikipedia resources, including links to other related datasets.\n\nOptions: A: YAGO B: Paris-Lille-3D C: SNIPS D: CCAligned E: Fashionpedia F: Opusparcus G: DBpedia",
"role": "user"
},
{
"content": "[\"YAGO\", \"DBpedia\"]",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.1623 | [
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nWe prove that every permutation of a Cartesian product of two finite sets can be written as a composition of three permutations, the first of which only modifies the left projection, the second only the right projection, and the third again only the left projection, and three alternations is indeed the optimal number. We show that for two countably infinite sets, the corresponding optimal number of alternations, called the alternation diameter, is four. The notion of alternation diameter can be defined in any category. In the category of finite-dimensional vector spaces, the diameter is also three. For the category of topological spaces, we exhibit a single self-homeomorphism of the plane which is not generated by finitely many alternations of homeomorphisms that only change one coordinate. The results on finite sets and vector spaces were previously known in the context of memoryless computation.\n\nCited Abstract(s):\n[1]: Code optimization is an important area of research that has remarkable contributions in addressing the challenges of information technology. It has introduced a new trend in hardware as well as in software. Efforts that have been made in this context led to introduce a new foundation, both for compilers and processors. In this report we study different techniques used for sequential decomposition of mappings without using extra variables. We focus on finding and improving these techniques of computations. Especially, we are interested in developing methods and efficient heuristic algorithms to find the decompositions and implementing these methods in particular cases. We want to implement these methods in a compiler with an aim of optimizing code in machine language. It is always possible to calculate an operation related to K registers by a sequence of assignments using only these K registers. We verified the results and introduced new methods. We described In Situ computation of linear mapping by a sequence of linear assignments over the set of integers and investigated bound for the algorithm. We introduced a method for the case of boolean bijective mappings via algebraic operations over polynomials in GF(2). We implemented these methods using Maple",
"role": "user"
},
{
"content": "It should be possible to extract, from the results of [1] , a natural category where alternation diameter is defined but infinite for some objects.",
"role": "assistant"
}
]
|
science.scientific_papers_summarization_single_doc_pubmed | science.scientific_papers_summarization_single_doc_pubmed.3008 | [
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\nmalignancy - producing granulocyte colony - stimulating factor ( g - csf ) is rare .\nrobinson first described a g - csf - producing tumor ( gcsf - pt ) in 1974 , and it has since been reported in various sites of cancer .\ng - csf is a glycoprotein that stimulates the proliferation and maturation of precursor cells in the bone marrow into fully differentiated neutrophils [ 2 , 3 ] .\ncarcinoma of unknown primary site ( cup ) is also a rare tumor , accounting for approximately 3% of all cancer diagnoses\n. cup often has a poor outcome due to its early dissemination , aggressive behavior and unpredictable nature as well as its metastatic potential and pattern .\nalthough platinum / taxane combination ( e.g. , cbdca + ptx ) chemotherapy is widely used for patients suffering from cup , its response rate is only about 3040% , with a median overall survival of merely 9 months . among new regimens , the combination of carboplatin , paclitaxel , bevacizumab and erlotinib is thought to be highly desirable .\nso far , cup which produces g - csf ( gcsf - cup ) is too uncommon to be treated with a precise chemotherapy regimen .\nwe herein report a challenging case of gcsf - cup with aggressive growth , treated with combination chemotherapy of carboplatin , paclitaxel , bevacizumab and erlotinib .\na 75-year - old man presented to his primary care clinic due to a left neck lump and was referred to our hospital .\nhe had broken his left ankle in a traffic accident , and he had been smoking half a pack of cigarettes per day for 55 years .\nhis complete blood count and blood chemistry were as follows : white blood cell ( wbc ) count 25,120/l ( normal range 3,5909,640/l ) with 82% neutrophils , 3% monocytes and 8% lymphocytes ; no immature granulocytes were observed ; platelet count 21.8 10/l ( normal range 14.833.9 10/l ) , and c - reactive protein level 4.45 mg / dl ( normal level < 0.3 mg / dl ) .\nvarious tumor markers were elevated , and scc , cyfra and ca19 - 9 were extremely increased ( table 1 ) .\nhis wbc count increased gradually up to 44,680/l , with a differential count of 94% neutrophils during a 6-week period after his first visit , while the serum g - csf concentration ( normal range 3.732.3 pg / ml ) was increased as high as 283 pg / ml during the same period , suggesting that the tumor grew rapidly .\na contrast - enhanced ct scan showed massive lymphadenopathy of the left cervix , left subclavian artery , left mediastinum , mesenteric and para - aortic lymph nodes , with peripheral rim enhancement , consolidation in the right lower lung and a 1-cm low - density liver lesion ( fig .\nf - fdg pet / ct demonstrated a high fdg accumulation in the lymph nodes , pulmonary consolidation and bone marrow ( fig .\na bone marrow smear showed that the rate of myelopoietic cells was increased but that of erythropoietic cells and megakaryocytes decreased , with normal cellularity .\nthe rate of eosinophils was not increased , and therefore , chronic myelocytic leukemia was not suspected ( fig .\n1c , d ) . a needle biopsy of the cervical lymph node and endobronchial ultrasound - guided transbronchial needle aspiration were performed , and cytological examinations of the cervical lymph node and bronchial lavage fluid indicated adenocarcinoma .\nimmunohistochemical ( ihc ) examination showed cytokeratin ( ck)7(+ ) , ck20(+ ) , muc1(+ ) , muc2( ) , cea(+ ) , p63(+ ) , cd5(/+ ) , cdx2( ) , human gastric mucin(/+ ) , n - cam( ) , thrombomodulin( ) , sp - a( ) , ttf-1( ) , alk( ) , psa( ) , er( ) , pgr( ) , her2( ) and egfr( ) expression ( fig .\nsince the clinical and pathological investigations could not detect the primary site , the patient was diagnosed with gcsf - cup .\nafter the approval of the intramural ethics committee and after having received the written informed consent from the patient , he was treated with carboplatin ( auc 6 ) , paclitaxel ( 175 mg / m ) , bevacizumab ( 15 mg / kg ) and erlotinib 150 mg / day . after the start of chemotherapy , g - csf slightly decreased , but no change was seen on the ct scan ( fig .\n3 ) . thirteen days later , intestinal perforation occurred . with the surgeon 's consultation ,\nthe patient was given palliative therapies and died 23 days after the start of chemotherapy .\ntreatment - related toxicity during chemotherapy was grade 4 anemia , grade 3 platelet count decrease , grade 1 aspartate aminotransferase elevation and grade 5 intestinal perforation .\nhis autopsy confirmed bulky lymph nodes of the neck , showing a remarkably shrunken appearance compared to before the therapy ( fig .\n1b ) , mediastinal and para - aortic lymphadenopathy and massive thickening of the mesentery .\nhistopathological assessment proved poorly differentiated adenocarcinoma with no specific morphologic features , invasion to the right lung and intestine as well as lymph node metastasis , and a well - differentiated hepatocellular carcinoma without any metastasis or invasion in the liver .\nihc examination of the mesentery showed the same results as those from the needle biopsy , and the tumor cells were positive for g - csf with immunohistochemistry ( fig .\nalthough several reports have reviewed each site of gcsf - pt ( e.g. , g - csf - producing gastric tumor ) , the frequency and histology are still unclear .\ng - csf , producing tumor and case reports ; 176 cases are reported and 171 described in japanese . additionally , we explored the japan medical abstracts society database looking for the key words \nproducing and case report in japanese ; 354 cases , including 102 cases from pubmed , have been described since june 2014 .\nhence , we reviewed 420 cases of gcsf - pt , with the exception of 4 cases that did not refer to the histopathology due to a lack of specimens .\ngcsf - pt cases are classified according to the primary site and pathologically ( table 2 ) .\nthe most common lesions of gcsf - pt are found in the lung , urinary tract ( renal pelvis , ureter , urethra and bladder ) , stomach and duodenum , and the esophagus .\nothers included 2 malignant fibrous histiocytomas , 1 epithelioid sarcoma and 1 undifferentiated sarcoma in the soft tissue and bone ; 1 squamous cell carcinoma in the middle ear ; 1 squamous cell carcinoma in the head and neck ; 1 squamous cell carcinoma of the urachus , and 1 prostate adenocarcinoma .\ngcsf - pt sometimes secretes other hormones simultaneously , such as parathyroid hormone - related protein c in 21 cases , -fetoprotein in 3 cases , -human chorionic gonadotropin in 2 cases , antidiuretic hormone in 1 case and erythropoietin in 1 case , respectively .\nour case did not have any clinical feature of abnormal hormone secretion other than g - csf .\ndiagnostic criteria for gcsf - pt are the following : ( 1 ) extreme leukocytosis , ( 2 ) elevated g - csf activity , ( 3 ) a decrease in the wbc count after tumor resection , or ( 4 ) proof of g - csf production in the tumor .\nour case matched criteria 1 , 2 and 4 and was therefore diagnosed with gcsf - pt .\npet - ct scans show an abnormally high f - fdg uptake , not only by the tumor itself but also diffusely throughout the bone marrow .\nthis finding could be explained by the elevated bone marrow metabolism associated with the excessively active production of granulocytes under g - csf stimulation and is considered to be useful for the diagnosis of gcsf - pt .\nmoreover , we confirmed no malignancy with bone marrow puncture , and the increase in only myelopoietic cells is compatible with excessive g - csf secretion .\nmeanwhile , cup is relatively rare , and standard clinical evaluation , unlike in most cancers , does not identify the anatomic primary site because of its extremely small size or possibly local regression due to antitumor immune defenses as well as its protracted clinical latency . since it is difficult to detect the primary organs , investigations with imaging , tumor and ihc markers are performed to at least classify the type of carcinoma for the purpose of a therapy guideline .\nhowever , 20% of cup patients show clinical and/or pathologic features that fit into one or several defined treatable subsets ( e.g. , isolated axillary lymph node tumors of female patients are treated as stage ii breast cancer ) .\nthese patients have clinical features that strongly suggest a specific diagnosis , even though an anatomic primary site can not be identified , and the prognosis is similar to these cancers .\nthe remaining 80% of patients with cup do not fall into any of these favorable subsets and have been treated with empiric chemotherapy . in our case ,\nct , mri and pet images as well as endoscopy did not detect the primary site .\nihc examinations showed adenocarcinoma and ck7/ck20 positivity , generally suggesting transient cell carcinoma , pancreatic ductal carcinoma , cholangiocellular carcinoma and gastric adenocarcinoma .\nthe results of muc1 , muc2 , cea and cdx2 pointed to a possible pancreatic ductal carcinoma , and p63 positivity indicates ureteral carcinoma ; however , thrombomodulin negativity suggests the opposite .\na slight positivity of human gastric mucin implies gastric carcinoma , a negativity of n - cam denies neurogenic tumor , and a cd5 result may show lymphocyte infiltration ; other ihc stains are not helpful in predicting a likely primary tumor . according to these clinical and histopathological results\n, the primary site could not be detected ; therefore , our case was diagnosed with cup .\nthe primary organ has been identified in 70% of cup patients by autopsy , but our case has also failed in this matter .\nso far , a combination of both gcsf - pt and cup does not seem to have been reported , and this study is likely the first case .\nalthough , because of the rarity of the disease , there is a lack of data from randomized phase iii trials which would be helpful for the treatment of patients with cup , the regimens with newer chemotherapeutic agents ( e.g. , taxanes , gemcitabine , irinotecan ) show modest improvement ; most of these newer regimens report response rates of 3050% , and the median survival time was 810 months .\na phase ii trial of the paclitaxel - carboplatin plus bevacizumab - erotinib regimen for cup patients was reported in 2009 .\nthis regimen produced a response rate of 53% ; the median overall survival time was 12.6 months , the median progression - free survival 8 months , and the 1- and 2-year survival rates 51 and 27% , respectively .\nboth the median progression - free survival and 2-year survival rate are the best among previously reported empiric chemotherapy regimens . similar to the reported effectiveness\n, this new regimen was also presumed to be efficacious in our case because a decrease in g - csf and wbc was observed after the treatment and because the appearance of the bulky neck lymph node remarkably shrank .\nif leukocytosis is detected in relation to a nonlymphoid hematopoietic malignant tumor , gcsf - pt should be reckoned .\ncareful observation is paramount in cup treatment due to the unpredictable nature of its metastatic potential and pattern .",
"role": "user"
},
{
"content": "granulocyte colony - stimulating factor ( g - csf)-producing nonhematopoietic malignancies have been reported in various organs and are associated with a poor clinical outcome . moreover , carcinoma of unknown primary site ( cup ) is an uncommon malignancy that occurs in about 26% of cancer patients \n . cup also has a poor prognosis due to its missing profile . \n since both g - csf - producing carcinoma and cup are rare , g - csf - producing cup ( gcsf - cup ) is considered to have an even poorer prognosis and is seldom encountered . \n herein , we report the case of a gcsf - cup patient . \n a 75-year - old man was admitted to our hospital complaining of cervical lymphadenopathy . \n multiple bulky lymph nodes without a primary site were revealed by image analysis . \n his complete blood count showed leukocytosis , and his blood chemistry panel indicated highly elevated levels of g - csf . although the patient was treated with combination chemotherapy of carboplatin , paclitaxel , bevacizumab and erlotinib , he died of intestinal perforation due to tumor invasion 23 days after the start of the therapy . \n an autopsy confirmed that the tumor was positive for anti - g - csf antibody , but the primary site was still not detected .",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.377 | [
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nInforming professionals about the latest research results in their field is a particularly important task in the field of health care, since any development in this field directly improves the health status of the patients. Meanwhile, social media is an infrastructure that allows public instant sharing of information, thus it has recently become popular in medical applications. In this study, we apply Multi Distance Knowledge Graph Embeddings (MDE) to link physicians and surgeons to the latest medical breakthroughs that are shared as the research results on Twitter. Our study shows that using this method physicians can be informed about the new findings in their field given that they have an account dedicated to their profession.\n\nCited Abstract(s):\n[1]: In this paper we address the problem of discovering missing hypertext links in Wikipedia. The method we propose consists of two steps: first, we compute a cluster of highly similar pages around a given page, and then we identify candidate links from those similar pages that might be missing on the given page. The main innovation is in the algorithm that we use for identifying similar pages, LTRank, which ranks pages using co-citation and page title information. Both LTRank and the link discovery method are manually evaluated and show acceptable results, especially given the simplicity of the methods and conservativeness of the evaluation criteria.\n\n[2]: Social network analysis has attracted much attention in recent years. Link prediction is a key research directions within this area. In this research, we study link prediction as a supervised learning task. Along the way, we identify a set of features that are key to the superior performance under the supervised learning setup. The identified features are very easy to compute, and at the same time surprisingly effective in solving the link prediction problem. We also explain the effectiveness of the features from their class density distribution. Then we compare different classes of supervised learning algorithms in terms of their prediction performance using various performance metrics, such as accuracy, precision-recall, F-values, squared error etc. with a 5-fold cross validation. Our results on two practical social network datasets shows that most of the well-known classification algorithms (decision tree, k-nn,multilayer perceptron, SVM, rbf network) can predict link with surpassing performances, but SVM defeats all of them with narrow margin in all different performance measures. Again, ranking of features with popular feature ranking algorithms shows that a small subset of features always plays a significant role in the link prediction job.\n\n[3]: With over 300 million active users, Twitter is among the largest online news and social networking services in existence today. Open access to information on Twitter makes it a valuable source of data for research on social interactions, sentiment analysis, content diffusion, link prediction, and the dynamics behind human collective behaviour in general. Here we use Twitter data to construct co-occurrence language networks based on hashtags and based on all the words in tweets, and we use these networks to study link prediction by means of different methods and evaluation metrics. In addition to using five known methods, we propose two effective weighted similarity measures, and we compare the obtained outcomes in dependence on the selected semantic context of topics on Twitter. We find that hashtag networks yield to a large degree equal results as all-word networks, thus supporting the claim that hashtags alone robustly capture the semantic context of tweets, and as such are useful and suitable for studying the content and categorization. We also introduce ranking diagrams as an efficient tool for the comparison of the performance of different link prediction algorithms across multiple datasets. Our research indicates that successful link prediction algorithms work well in correctly foretelling highly probable links even if the information about a network structure is incomplete, and they do so even if the semantic context is rationalized to hashtags.\n\n[4]: Prediction is one of the most attractive aspects in data mining. Link prediction has recently attracted the attention of many researchers as an effective technique to be used in graph based models in general and in particular for social network analysis due to the recent popularity of the field. Link prediction helps to understand associations between nodes in social communities. Existing link prediction-related approaches described in the literature are limited to predict links that are anticipated to exist in the future. To the best of our knowledge, none of the previous works in this area has explored the prediction of links that could disappear in the future. We argue that the latter set of links are important to know about; they are at least equally important as and do complement the positive link prediction process in order to plan better for the future. In this paper, we propose a link prediction model which is capable of predicting both links that might exist and links that may disappear in the future. The model has been successfully applied in two different though very related domains, namely health care and gene expression networks. The former application concentrates on physicians and their interactions while the second application covers genes and their interactions. We have tested our model using different classifiers and the reported results are encouraging. Finally, we compare our approach with the internal links approach and we reached the conclusion that our approach performs very well in both bipartite and non-bipartite graphs.",
"role": "user"
},
{
"content": "Classic link prediction methods on social media use graph properties of the social network or NLP feature of nodes to predict links between entities. For example, [3] is base solely on graph features and [4] uses a similar technique for the social networks in healthcare. Meanwhile, [1] uses common words to cluster and rank nodes and based on that predicts the closely-ranked nodes to be connected. Another Study [2] uses a combination of graph features and keyword matches to train classifiers(SVM, Naive Bayes, etc) to predict if a link exists between two nodes.",
"role": "assistant"
}
]
|
science.bc7_litcovid_topic_classification | science.bc7_litcovid_topic_classification.19103 | [
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nImportance: The influence on the psychology and ocular surface of ophthalmologists and ophthalmic nurses in Wuhan, China, during the coronavirus disease 2019 (COVID-19) pandemic is not yet fully understood. Objective: To characterize mental state and ocular surface state of ophthalmologists and ophthalmic nurses in Wuhan, China, and similar areas during the COVID-19 outbreak. Design, Setting, and Participants: This survey study assessed ophthalmologists and ophthalmic nurses in Wuhan, China, and Jiangxi, China, a province approximately 300 km south of Wuhan. The Hospital Anxiety and Depression Scale, the Van Dream Anxiety Scale, and the Ocular Surface Disease Index were used to conduct questionnaire surveys via a messaging and social media app. Main Outcomes and Measures: Mean scores from the Hospital Anxiety and Depression Scale (0-10 points), the Van Dream Anxiety Scale (0-100 points), and the Ocular Surface Disease Index (0-100 points). Results: Of 126 individuals, there were 42 ophthalmologists (33.3%) and 21 ophthalmic nurses (16.7%) from Wuhan and 42 ophthalmologists (33.3%) and 21 nurses (16.7%) from Jiangxi. The mean (SD) age of ophthalmologists was 36.1 (7.6) years in Wuhan and 41.2 (8.8) years in Jiangxi. For ophthalmic nurses, the mean (SD) age was 35.2 (7.4) years in Wuhan and 33.4 (7.9) years in Jiangxi. The response rate for ophthalmologists was 90.3% (84 of 93) and for nurses was 91.3% (42 of 46). The participation rate of ophthalmologists and nurses in Wuhan was 0.06% (42 of 70000) and 0.07% (21 of 30000), respectively; the participation rate in Jiangxi was 0.06% (42 of 70000; 21 of 35000) for both groups. In Wuhan, the mean (SD) Hospital Anxiety and Depression Scale (anxiety and depression were counted as separate scores), Van Dream Anxiety Scale, and the Ocular Surface Disease Index scores were 6.90 (2.30), 7.38 (2.19), 24.52 (5.86), and 43.90 (3.74), respectively, in ophthalmologists and 8.67 (3.04), 9.38 (2.64), 21.48 (6.15), and 40.05 (6.67), respectively, in ophthalmic nurses. In Jiangxi, these scores were 5.67 (2.89), 4.90 (3.15), 12.76 (7.27), and 38.79 (7.78), respectively, in ophthalmologists and 4.67 (3.20), 4.33 (3.23), 10.10 (7.62), and 41.52 (5.92), respectively, in ophthalmic nurses. The difference (95% CI) between the 2 regions for these scores in ophthalmologists was 2.48 (95% CI, 1.30-3.65), 11.76 (95% CI, 8.90-14.63), 5.12 (95% CI, 2.45-7.79), and 5.12 (95% CI, 2.47-7.77), respectively, and in ophthalmic nurses was 4.16 (95% CI, 2.05-5.95), 5.05 (95% CI, 3.21-6.89), 11.38 (95% CI, 7.06-15.70), and -1.48 (95% CI, -5.41 to 2.25), respectively. Conclusions and Relevance: These findings suggest that ophthalmologists and ophthalmic nurses in Wuhan experienced more anxiety and depression and reported greater ocular surface abnormalities than counterparts outside of Wuhan, but the wide CIs preclude concluding confidently that there were differences.",
"role": "user"
},
{
"content": "[\"Prevention\"]",
"role": "assistant"
}
]
|
science.bc7_litcovid_topic_classification | science.bc7_litcovid_topic_classification.6828 | [
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nCorona Virus disease 2019 (COVID-19) is a global pandemic and is caused by Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) group of viruses. To date, April 25, 2020, more than 2.4 million humans are infected and more than a hundred thousand deaths have been reported from more than 200 countries from COVID-19. There is no evidence-based treatment for the infection and prevention of transmission using social distancing, isolation and hygiene measures is widely recommended. Tobacco smoking is rampant in communities around the globe and the addiction to tobacco results in deaths of more than 8 million individuals each year. As COVID-19 transmits through salivary droplets and causes severe lung pneumonia, tobacco smokers are also at high risk of severe COVID-19 infection due to poor lung function, cross-infection and susceptible hygiene habits. Smoking tobacco (cigarette, e-cigarettes or waterpipe) produces exhaled smoke, coughing or sneezing, aerosols containing SARS-CoV-2 in the surroundings and contaminating surfaces. Therefore, smoking tobacco is a possible mode of transmission for the virus for both active and passive smokers. Smoking should be considered a risk factor for the disease transmission until further availability of evidence and measures to limit its direct and indirect effects should be implemented within the community.",
"role": "user"
},
{
"content": "[\"Transmission\", \"Prevention\"]",
"role": "assistant"
}
]
|
science.scientific_papers_summarization_single_doc_pubmed | science.scientific_papers_summarization_single_doc_pubmed.62157 | [
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\nthe term cycloid psychosis is not included explicitly in the international classification system and this has hampered both clinicians and researchers alike . in the present international diagnostic classification systems , in order to increase the diagnostic validity and reliability , such cases are categorized as acute polymorphic psychotic disorders , with or without symptoms of schizophrenia , f-23 in icd-10 , and brief psychotic disorder , 298.8 in dsm - iv , but these categories appears to have outlived its validity and reliability , utility though remains .\nalso the duration of remitting psychosis specified in these classification systems is less than 1 month .\nthe researchers in this study found a modal duration of 2 - 4 months , with 43% falling in this range and suggest that the forthcoming edition of icd look into this . in the literature\nthe varied presentation of acute psychotic episode is known by the synonyms of psychogenic psychosis ( coined by faegerman ) or reactive psychosis ( coined by eric stromgren)popular terms used in scandinavia .\nthe other synonyms are hysterical psychosis , atypical psychosis , bouffee delirante ( french psychiatry mangan first described this way back in 1880 ) , and cycloid psychosis ( german school ) .\nthis possibly highlights the cultural and sociological contexts of psychosis , but these differing terms lack reliability and validity , but possibly have utility in clinical practise .\nit was karl kleist in 1926 who introduced the term cycloid marginal psychosis to describe cases , which do not meet the typical presentation of schizophrenia or bipolar affective disorder .\nthese conditions include many cases of acute psychotic illnesses of limited duration , with recovery between recurrences .\nthe acute features are psychotic , as in schizophrenia , but the course is episodic , as in manic - depression .\nbut it was karl leonhard in 1957 who described cycloid psychosis and the three forms of cycloid psychosis .\nthe first one is anxiety - blissfulness psychosis , which may resemble agitated depression , i.e. in which affective symptoms predominate ( on one pole , there are periodic states of overwhelming anxiety and paranoid ideas of reference and sometimes hallucination .\nthe second type is called confusion psychosis , presents similar to manic episode , i.e. in which thought disorder is dominant and presents with anxiety , distractibility , and a degree of speech incoherence out of proportion to the severity of flight of ideas .\nthe clinical picture varies between excitement and a state of under activity with poverty of speech .\nthe third is motility psychosis , in which the striking changes are psychomotor activity ( akinetic which presents similar to catatonic stupor and hyperkinetic which resemble catatonic excitement ) . despite the fact that cycloid psychosis contains a high prevalence of mood symptoms , carlos perris felt that cycloid psychosis did not equal schizoaffective disorder and considered it a separate entity .\nperris and brockington published diagnostic guidelines for cycloid psychosis in 1981 [ table 1 ] .\ndiagnostic criteria for cycloid psychosis peralta and cuesta reported in their clinical and nosological study that with regards to most clinical variables and morbidity risk of mood disorders , cycloid psychosis was closer to mood disorders .\naffective and non - affective groups of cycloid psychosis differed in a number of variables indicating an overall better outcome for the non - affective group .\ni would now like to describe one such case , which got us thinking , a 40-year - old lady presenting the fourth time with brief and acute onset of confusion , hypo - motility , and psychotic features .\na , a 42-year - old caucasian lady , divorced but currently in a stable relationship since the last 10 years , and working full time as a cleaner in a school was admitted the fourth time with acute onset of confusion , hypo - motility , altered behaviour , and psychotic features .\nher first admission had been in the summer of 2006 followed by three more episodes .\nprior to 2006 , the only significant history was a high tpo ab ( antithyroid peroxidase antibodies ) which was diagnosed in december 2003 and she was started on thyroxine 50 g .\nthe dose was increased in june 2004 to 75 g , which was further increased to 100 g in july 2005 .\nshe was admitted with acute confusion , hyperpyrexia , agitation , and inability to walk and was also queried to have a seizure .\nextensive investigations including haematological and biochemical studies , antibody studies , cerebrospinal fluid analysis , ct and mr imaging found no abnormality , except for raised free t4 ( for which she was being treated with thyroxine ) .\neeg was reported to be normal , and so also serum prolactin ( the possibility of temporal lobe epilepsy was considered as a differential ) .\nlater on , in the ward she expressed thoughts that her body was dead and rotting , and that she was \nsatan. there were some olfactory and tactile disturbances as she could smell burning and feel ooze coming from her , although she could not see it .\nshe believed her family could hear her thoughts and was suspicious of them and also of the staff .\nher memory of past events remained intact and her mood was euthymic both during the current presentation and also prior to the admission .\nthere was no history of any illicit substance misuse , alcohol abuse , and no misuse of over the counter prescribed medication or other herbal medication .\nthe patient was started on olanzapine 10 mg od ( for psychosis ) and sodium valproate 200 mg bd ( for query seizure ) .\nshe was discharged and the episode was documented as an acute psychosis of unknown cause and was referred to the neurologist .\nthe olanzapine was stopped 6 months later as the patient continued to be well . in the outpatient follow up\nthe sodium valproate was stopped after a year , by the neurologist , just prior to the second episode .\nthe second episode , september 2007 , occurred after ms . a returned from a holiday .\nthere was no recent life event . within a few hours the patient experienced a sudden deterioration .\nshe was treated by the crisis resolution and home treatment team , in the community , on this occasion and was recomm enced on the olanzapine and sodium valproate , with a provisional diagnosis of intra - ictal psychosis / psychotic episode .\nthe patient 's family and her partner did not report any history to suggest recent seizures .\nthe neurologist did not find convincing evidence of intra - ictal or post - ictal psychosis ( three eegs were done in the tertiary hospital , as an out patient and no ictal events were recorded ) .\nthe olanzapine was stopped subsequently in the outpatient follow up and she remained on the sodium valproate .\nshe presented in the same way , 1 year later , october 2008 , after ms . a returned from a holiday with sudden deterioration and responded well , within a few weeks to treatment in the community with olanzapine and support from the crisis resolution and home treatment team .\nagain the family and the patient denied any drug misuse or alcohol misuse and urine drug screen was negative ( 15/10/08 ) .\nthere were no eye witness account of any seizures ( on 13/10/08 , the patient also had a video eeg during the episode of confusion and vagueness , which was again reported as normal ) . in january 2009 , because of weight gain , sodium valproate was tapered and stopped and she was commenced on levetiracetam by the neurologist , who continued with the follow up . the most recent episode presented in july 2009 , 3 days prior to going on a holiday .\nagain an acute presentation with confusion , answering in monosyllabic , looking perplexed , and believing that there were cameras in her flat and that she was part of a t.v .\nshe had symptoms of being unable to move her legs and was admitted to the hospital .\nshe had delusions about her being dead and her body rotting were more elaborate and included in her thinking that she had killed everyone and was a mass murderer .\nthis resulted in an incident of attempted hanging while in the ward , believing that she deserved to die as she had killed everyone .\nmri head was requested and this showed several , tiny , non - specific hyper intense foci within the subcortical and deep white matter of both cerebral hemispheres .\nmmse was done , 5 days after admission and it was reported to be normal .\nalso the family reported that the patient responded to olanzapine within 2 weeks , as evidenced on the previous three occasions .\nshe was started on olanzapine again and made a full recovery within a few weeks and was discharged .\na was seen in the opc , both by the psychiatrist and the neurologist and there was no evidence , either of psychosis or affective illness .\ngiven the fact that the first three episodes were following the holidays abroad , drug - induced psychosis was suspected but uds ( urine drug screen ) has been negative on all four occasion and the partner and her family categorically deny alcohol or drug intake .\nthe mood was euthymic prior to the first admission and the patient denied feeling low during the episodes and also after the episodes .\nit can be argued that the patient might have had an underlying mood disorder which was aggravated during times of stress .\nalso both olanzapine and sodium valproate have been used in treating atypical presentations of mood disorders . though in the above patient , olanzapine was used to treat acute psychosis and the sodium valproate to treat any underlying seizures , if any .\nepilepsy was queried ( post - ictal and inter - ictal psychosis ) , but eeg done during these episodes including video eeg was reported as normal .\nserum prolactin done in the first and fourth admission was negative . also the fact that there has been rather a consistent pattern , once every year , and that the epilepsy was well controlled makes epilepsy less accountable for the presentation .\nforced normalization was queried , but the episodes were not related to changes in dosage of anti- convulsants . there was no definite eyewitness account of seizures .\nthe consultant neurologist was not convinced and he reported that it was not linked to epilepsy .\nthe consultant neurologist queried hashimoto 's encephalopathy on the fourth presentation , but in the absence of raised csf protein , the absence of myoclonus and persistent cognitive decline , he dismissed it .\nmoreover , it is very rare and most cases of hashimoto 's encephalopathy present at a later stage in life , and the patient responded to olanzapine on each of the four occasions . a link with hormonal changes , especially estrogen , which has effects on the expression of a variety of forms of psychopathology , has been noted previously , but there was no link found in this patient .\nshe had normal menstrual cycle and did not have any symptoms of pmt ( premenstrual tension ) .\nthyroid disorder can not , however , be the direct cause in this case since the patient was being treated for hypothyroidism , well before ( 3 years prior ) the first presentation in 2006 .\ndissociative disorder was also queried , but there were no life events or precipitating events on each of the four episodes , nor was there any loss of personal identity or problems with self - perception . even though the patient was referred to the psychiatry team early on , it was only on the fourth admission that the team discussed cycloid psychosis and revisited perris criteria , after the diagnosis was suggested by an experienced second opinion psychiatrist who had come to give a second opinion and who had come across such cases previously .\nthe patient indeed met all the four points from the diagnostic criteria of cycloid psychosis as operationally defined by perris and brockington .\nrapid introduction of neuroleptics , followed by the addition of lithium , if required is advocated by brockington , perris , and kendell et al .\nif there is severe anxiety , which does not respond to neuroleptics , clonazepam may be helpful .\ncycloid psychosis recognition has an important implication in the assessment , investigation , treatment , and effective management of recurrent confusional states with alteration of psychomotor activity and brief psychotic episodes .\nthe current international classification system , i.e. the dsm iv and icd 10 , fails to categorize cycloid psychosis as a separate entity and this has hampered both clinicians and researchers alike .\nwill the forthcoming editions of dsm v and icd 11 in 2011 - 12 categorize cycloid psychosis in a separate category?there is no fixed combination of symptoms , and in contrast , the symptoms may change frequently during an episode , resulting in potentially unnecessary invasive investigations . educating medical doctors , psychiatrists and neurologist about cycloid psychosis\nthe current international classification system , i.e. the dsm iv and icd 10 , fails to categorize cycloid psychosis as a separate entity and this has hampered both clinicians and researchers alike .\nwill the forthcoming editions of dsm v and icd 11 in 2011 - 12 categorize cycloid psychosis in a separate category\n? there is no fixed combination of symptoms , and in contrast , the symptoms may change frequently during an episode , resulting in potentially unnecessary invasive investigations . educating medical doctors ,\n\n the accumulated evidence suggests that cycloid psychosis is a separate and an independent category .\nthe current international classification system , i.e. the dsm iv and icd 10 , fails to categorize cycloid psychosis as a separate entity and this has hampered both clinicians and researchers alike .\nwill the forthcoming editions of dsm v and icd 11 in 2011 - 12 categorize cycloid psychosis in a separate category?there is no fixed combination of symptoms , and in contrast , the symptoms may change frequently during an episode , resulting in potentially unnecessary invasive investigations . educating medical doctors , psychiatrists and neurologist about cycloid psychosis\nthe current international classification system , i.e. the dsm iv and icd 10 , fails to categorize cycloid psychosis as a separate entity and this has hampered both clinicians and researchers alike .\nwill the forthcoming editions of dsm v and icd 11 in 2011 - 12 categorize cycloid psychosis in a separate category ?\nthere is no fixed combination of symptoms , and in contrast , the symptoms may change frequently during an episode , resulting in potentially unnecessary invasive investigations . educating medical doctors ,",
"role": "user"
},
{
"content": "cases presenting with recurrent confusion , alteration of psychomotor activity , and brief psychosis with good inter - episode recovery have many differing etiologies . only rarely does one diagnose such cases as cycloid psychosis . even among budding psychiatrists \n , there seems to be a lack of awareness of this unique disorder . \n this may be because the present international diagnostic classification systems , icd10 and dsm iv , do not recognize it as a separate entity . \n a high index of suspicion is required to diagnose cycloid psychosis . \n awareness and recognizing such cases would be helpful clinically as cycloid psychosis entails a distinct prognosis and may require a specific treatment .",
"role": "assistant"
}
]
|
science.scientific_papers_summarization_single_doc_pubmed | science.scientific_papers_summarization_single_doc_pubmed.88320 | [
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\nhealth is a state of complete physical , mental , and social well - being and not merely an absence of disease or infirmity .\noral health is a standard of the oral and related tissues which enables an individual to eat , speak , and socialize without active disease , discomfort , or embarrassment and which contributes to general well - being .\noral health is a critical but overlooked component of overall health and well - being among children and adults .\nhealth is a fundamental right of every individual and oral health is an integral part of general health .\nsocioeconomic status , occupation , and education are playing a major role in the maintenance of good oral health .\naccess is one of the main barriers of health care delivery system which we want to overcome by primary health care .\neach population group comprises different individuals coming from various socioeconomic profiles , education levels , age groups , occupations , etc .\none of the strategies in public health is to identify unique population groups , study their health problems , and explore methods for health care . during the last decade\nthe prevalence of periodontal disease in india ranges from 90% to 95% in different population groups , only differing in severity between the various age groups .\nalthough the critical role of dental plaque in the etiology of periodontal disease is well - established , it does not explain the difference in susceptibility of given population or individuals to periodontitis .\nrelative role of various etiologic factors in periodontal disease have been investigated by means of epidemiologic surveys and clinical studies .\nthe community periodontal index of treatment needs ( cpitn ) provides a picture of the public health requirements in the periodontal field , which is essential for national oral health policy - making and specific interventions .\nthe cpitn index has been developed jointly by the international dental federation and the world health organization ( who ) to evaluate periodontal status and treatment needs ( tns ) of population .\npopulation group centers are classified as rural , semi - urban , urban , and metropolitan population based on the centers as available in the latest census of india ( census 2011 ) .\nthe population groups are classified as under : \n rural : population < 10,000semi - urban : 10,000 and < 1 lakhurban : 1 lakh and above and < 10 lakhmetropolitan : 10 lakh and above . \n \nrural : population < 10,000 semi - urban : 10,000 and < 1 lakh urban : 1 lakh and above and < 10 lakh metropolitan : 10 lakh and above . a large number of epidemiological studies have been carried out on the prevalence of periodontal disease in the populations of various parts of india .\nno studies have been conducted with respect to prevalence and tns in gurgaon district of haryana state .\nhence , the present study was conducted to find out the oral health status and periodontal tns among rural , semi - urban , urban , and metro population of gurgaon district , haryana state .\nthe subjects for the present study were selected at random from rural , semi - urban , urban , and metropolitan population of gurgaon district , haryana state .\nan epidemiological , cross - sectional survey was carried out on 4000 subjects of either sex .\nparticipants of age between 15 and 60 years were selected to assess their periodontal status and treatments needs .\nthe study groups were divided according to the population distribution as rural population , semi - urban population , urban population , and metropolitan population . ethical clearance to conduct the study\nwas obtained from the institutional review board or from the ethical committee of sgt college of dental sciences and research , gurgaon . \na dual proforma designed to know the age , sex , socioeconomic background , methods , frequency , and duration for oral hygiene and cpitn was prepared for the study .\nparticipants between the age of 15 and 60 years from both the sexes and who were willing to give consent were selected .\nchildren under 14 years of age , edentulous persons , and subjects with partial dentition having two or more missing teeth were excluded from the study .\na door - to - door survey was conducted with the help of auxiliary staff and personnel .\nthe oral examination of each individual was carried out using the who oral health form ( 1997 ) .\neach sextant was designated as healthy , when no treatment is required ( code 0 = tn0 ) . in case of bleeding without calculus\n, it was recommended to improve the oral hygiene ( code 1 = tn1 ) . if the calculus but no periodontal pocket was detected , oral hygiene instructions were provided and professional cleaning was carried out , if indicated ( code 2 = tn2 ) .\npresence of 45 mm pocket ( code 3 = tn2 ) and 6 mm or deeper ( code 4 = tn3 ) must need treatment by deep scaling and in these cases , root planing and more complex surgical procedures may be indicated .\nthe cpitn for a population group was calculated as follows : step 1 : number of charts with different code individually ( i.e. , 0 , 1 , 2 , 3 and 4 ) were counted .\nstep 2 : all the individuals were given tn ( i.e. tn0 , tn1 , tn2 , and tn3 ) according to their codes .\nstep 3 : each population group was assessed as per their tns and their percentage prevalence was obtained .\nall information and data were collected by the investigator by interview technique and oral cavity examination .\ndata were entered in microsoft excel spread sheet and analyzed using spss software ( ibm corp . released 2010 .\nthe subjects for the present study were selected at random from rural , semi - urban , urban , and metropolitan population of gurgaon district , haryana state .\nan epidemiological , cross - sectional survey was carried out on 4000 subjects of either sex .\nparticipants of age between 15 and 60 years were selected to assess their periodontal status and treatments needs .\nthe study groups were divided according to the population distribution as rural population , semi - urban population , urban population , and metropolitan population . ethical clearance to conduct the study\nwas obtained from the institutional review board or from the ethical committee of sgt college of dental sciences and research , gurgaon . \na dual proforma designed to know the age , sex , socioeconomic background , methods , frequency , and duration for oral hygiene and cpitn was prepared for the study .\nparticipants between the age of 15 and 60 years from both the sexes and who were willing to give consent were selected .\nchildren under 14 years of age , edentulous persons , and subjects with partial dentition having two or more missing teeth were excluded from the study .\na door - to - door survey was conducted with the help of auxiliary staff and personnel .\nthe oral examination of each individual was carried out using the who oral health form ( 1997 ) .\neach sextant was designated as healthy , when no treatment is required ( code 0 = tn0 ) . in case of bleeding without calculus ,\nit was recommended to improve the oral hygiene ( code 1 = tn1 ) . if the calculus but no periodontal pocket was detected , oral hygiene instructions were provided and professional cleaning was carried out , if indicated ( code 2 = tn2 ) .\npresence of 45 mm pocket ( code 3 = tn2 ) and 6 mm or deeper ( code 4 = tn3 ) must need treatment by deep scaling and in these cases , root planing and more complex surgical procedures may be indicated .\nthe cpitn for a population group was calculated as follows : step 1 : number of charts with different code individually ( i.e. , 0 , 1 , 2 , 3 and 4 ) were counted .\nstep 2 : all the individuals were given tn ( i.e. tn0 , tn1 , tn2 , and tn3 ) according to their codes .\nstep 3 : each population group was assessed as per their tns and their percentage prevalence was obtained .\nall information and data were collected by the investigator by interview technique and oral cavity examination .\ndata were entered in microsoft excel spread sheet and analyzed using spss software ( ibm corp . released 2010 .\nthere was no participant in any population group with healthy periodontal tissues , so code 0 was not assigned to anyone .\nthis was in accordance with the findings by mcgrath , james , and anup et al .\ntable 1 showed the percentage prevalence of tn1 , tn2 , and tn3 in group 1 ( rural ) , group 2 ( semi - urban ) , group 3 ( urban ) , and group 4 ( metropolitan ) population . in group 1 , 68.30% of population\nneeds tn2 whereas 16.80% needs tn1 and 14.90% needs tn3 . in group 2 , 56.40% of population needs tn2 whereas 23.70% needs tn3 and 19.90% needs tn1 . in group 3 ,\n57% of individuals need tn2 whereas 24.90% needs tn3 and 18.10% needs tn1 . in group 4 ,\npercentage prevalence of treatment need 1 , treatment need 2 , and treatment need 3 in rural , semi - urban , urban , and metropolitan population results in table 2 show that rural group population needs more tn2 when compared with semi - urban group whereas semi - urban group population needs more tn1 and tn3 when compared with rural group . there was significance present between the two groups ( p < 0.001 ) .\nsignificance of inter - group comparisons of treatment need 1 , treatment need 2 , and treatment need 3 rural group population needs more tn2 when compared with urban group whereas urban group population needs more tn1 and tn3 when compared with rural group .\nrural group needs less tn1 and tn2 and more tn3 when compared with metropolitan group population .\nthere was significance present between the two groups ( p < 0.001 ) . in semi - urban group ,\nmore participants needed tn1 whereas tn2 and tn3 were needed by more participants in urban group .\nthere was no significance between the two groups ( p < 0.554 ) . in semi - urban group , more participants needed tn1 and tn3 whereas tn2 was needed more in metropolitan population .\nurban group population needed more tn1 and tn3 when compared with the metropolitan group population which needed more tn2 .\nhence , an inference was drawn from the results that among 4000 participants from all the four population groups ' maximum , i.e. 63.80% of individuals needed tn 2 whereas 18.20% of individuals needed tn3 and 18.10% of individuals needed tn1 .\nin a developing country such as india which is undergoing social change , public health and primary health care should assume a place of importance .\nbeliefs based on ignorance , superstition , and taboos about dentistry still prevail in the minds of the people .\nall the population groups including rural , semi - urban , urban , and metropolitan are lacking in the maintenance of oral hygiene . over the past few years\n, cpitn index has been increasingly adopted as a procedure for classifying periodontal conditions with respect to complexity of care and personal oral health required to restore periodontal tissue to healthy conditions .\nthe index has met its expressed purpose to provide a global standard that can be uniformly used for the measurement of tns for use by health planners and administration .\nit is viewed by some as possibly the best tool currently available for measuring descriptive epidemiology of periodontal disease in diverse population .\nthe index is simple , rapid , inexpensive , easily applied , and requires minimum equipment . in the present study ,\ncpitn - c probe having color coding with a black mark starting at 3.5 mm and ending at 5.5 was used , not employing a force > 20 g. ainamo et al .\nmorris et al . used same probe during his study on the uk adult population .\nthe periodontal status assessment criteria that were proposed in the who 's 1997 oral health survey methods manual were used .\nthe data were collected by a single examiner . in the past , very few indian and international studies have been conducted to compare the prevalence of periodontal diseases and tns in urban and rural areas .\npresent study is the only study which compares the four groups of population , i.e. rural , semi - urban , urban , and metropolitan .\nthe results of the present study revealed that there was less need of tn1 in rural population when compared to the other three groups .\nthese results are in accordance with the studies of singh et al . and gupta et al .\nfound in his study that rural populations mostly use traditional therapy when they suffer from dental problems .\nramfjord et al . who observed in their study that there is 100% prevalence of periodontal disease in india .\nthis might be due to different lifestyle , exposure of certain risk factors such as smoking , chewing tobacco , and use of indigenous oral hygiene methods for cleaning teeth .\nin addition , lack of oral hygiene awareness among the rural population must have contributed to the increased risk of periodontal disease among the individuals .\nshowed that how a social environment , individual behavior , and the delivery system have significant effect on the use of dental services .\nshowed that education was not a decisive factor in determining the attitude of the people toward oral health care .\nlack of incentives for dentists to work in the rural areas is one of the major important determinants for unavailability of dentists in the rural areas .\nlack of routine medical check - up can be a risk factor for routine dental care also .\ndental schools organize oral health check up camps in rural areas and also inform / motivate people regarding the prevention and treatment of existing dental diseases , but it is little difficult for the population to get benefit of the facilities available in dental colleges located in nearby towns / city , because of some practical reasons such as conveyance . on the other hand , better periodontal health in urban and metropolitan areas\nmajority of the hospitals and teaching institutions ( dental colleges ) are located in urban areas .\nfurthermore , schools located in these areas are having regular oral checkups of the students by the dentists employed / empaneled by them , thus ensuring better oral hygiene standards .",
"role": "user"
},
{
"content": "background : role of various etiologic factors in periodontal disease has been investigated by means of epidemiologic surveys and clinical studies . \n the community periodontal index of treatment needs ( cpitn ) provides a picture of the public health requirements in the periodontal field , which is essential for national oral health policy - making and specific interventions.materials and methods : this study was conducted on 4000 individuals among rural , semi - urban , and metro population of gurgaon district , haryana state , to find out the oral health status and periodontal treatment needs ( tns ) using cpitn index.results:an inference was drawn from the results that among 4000 participants from all the four population groups ' maximum , i.e. , 63.80% of individuals needed tn2 whereas 18.20% of individuals needed tn3 and 18.10% of individuals needed tn1.conclusion:it can be concluded with a word of hope and a word of warning . \n hope lies in the fact that the measurement of periodontal diseases by epidemiological study of this condition is improving and receiving wide spread attention . \n the warning lies in the varied nature of the condition which goes to make up periodontal disease and perplexing ways in which these conditions blend . \n in addition to dental practitioner , periodontist and public health workers must devote more time and effort toward controlling periodontal disease than they seem to be devoting at present .",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.2702 | [
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nA comparison between oral ciprofloxacin and intra-peritoneal vancomycin and gentamicin in the treatment of CAPD peritonitis . Fifty-one patients were included in a prospective , randomized comparison of oral ciprofloxacin and intraperitoneal vancomycin/gentamicin in the treatment of CAPD peritonitis . Staphylococcal species accounted for 40 % of the isolates with an equal incidence of Staphylococcus aureus and coagulase negative staphylococci . Although , overall , there was no significant difference between the regimens in outcome , ciprofloxacin was significantly less effective when peritonitis was due to coagulase negative staphylococci .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"intra-peritoneal vancomycin\", \"ciprofloxacin\", \"oral ciprofloxacin\", \"intraperitoneal vancomycin/gentamicin\", \"gentamicin\"], \"Outcome\": [\"CAPD peritonitis\", \"Staphylococcus aureus\", \"coagulase negative staphylococci\", \"effective\"], \"Participant\": [\"CAPD peritonitis\", \"Fifty-one patients\"]}",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.7210 | [
{
"content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: …and Medical Services, Faculty of Pharmacy, Kermanshah University of Medical Sciences, PO Box 67346-67149, Kermanshah, Iran\nweight loss, amyloidosis, and osteopenia, all of which are a result of systemic inflammation (Hendrickson et al. 2002; Levine and Burakoff 2011; Schmidt et al. 2012).",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.9977 | [
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Channel Modeling for Future High-Speed Railway Communication Systems: A Survey \nChapter Title: A. MULTI-LINK HSR CHANNEL MODELING \n1. Abstract of Cited Paper (BIB001): The performance of distributed communication systems is commonly subject to the cross-correlation characteristics of multi-link channels. In this paper, we concentrate on the modeling of multi-link small-scale fading (SSF) channels in high-speed train (HST) communication networks with distributed base stations according to the classical geometry-based stochastic model (GBSM). To appropriately describe a multi-link propagation scenario in the HST communication network, a novel geometrical model considering a line-of-sight component, a single-bounced one-ring model, and a double-bounced ellipse-ring model is proposed. Based on the proposed GBSM, the expression of multi-link channel impulse responses (CIRs) is obtained, and multi-link cross-correlation functions are derived and used for numerical analysis. In addition, realistic channel measurements are conducted in the existing HST long-term evolution (LTE) networks and multi-link CIRs are acquired using a time delay window-based partitioning scheme. Finally, the SSF cross-correlation coefficient is extracted by the multi-link channel data and is used to validate the utility of the proposed model.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Since active channel sounders are not suitable for performing HSR measurements, reported measurement campaigns used HSR LTE networks, which can be helpful for multi-link channel characterization and modeling. In HSR outdoor scenarios the LoS component and common clusters produced by the shared scatterers, e.g., the steep walls of cutting, the awnings of station, or other local surroundings, are the main contributors of cross-correlations. An irregular shaped GBCM has been used to analyze the SSF cross-correlation in distributed MIMO systems BIB001 . The regular shapes of GBCM can also be a possible way for modeling of SSF cross-correlation in HSR outdoor scenarios. Fig. 2 illustrates a 2 × 2 MIMO GBCM with the one-ring two-ellipse architecture that includes two links from BS1 and BS2 to a MRS BIB002 . The one ring is used to describe the distribution of local scatterers S1, while the two ellipses are employed to represent the distribution of remote scatterers S2 and S3 in the two links. The proposed GBCM only focuses on NLoS components of the two links, including the single-bounced component from S1 as well as the double-bounced component from We assume that the center frequency is 5 GHz, the antenna spacing is 3 wavelengths, R = 30m, D = 1000m, d = 500m, d 1 = d 2 = 30m. We compare the results for single-bounced and double-bounced components, as shown in Fig. 3 . It can be seen that the coefficient of multi-link spatial correlation reduces as the azimuth AS increases, and the double-bounced component contributes a lower correlation than the single-bounce component. This is because the double-bounced component comprises a part of the uncommon cluster, which has no contribution on the multi-link spatial correlation.",
"role": "assistant"
}
]
|
science.drug_combo_extraction_re | science.drug_combo_extraction_re.826 | [
{
"content": "Extract drug combinations from this sentence and classify each combination into one of these categories:\n- POS: Positive interaction between drugs\n- NEG: Negative interaction between drugs\n- COMB: Drugs used together with unknown interaction type\n\nOutput only a JSON array where each entry is [drug_1, drug_2, ..., drug_n, category].\n\nparagraph: Clinical trials with halofantrine in acute uncomplicated falciparum malaria in Thailand. The antimalarial efficacy of halofantrine was compared with mefloquine in an open-label, randomized comparative trial in adult male patients with acute uncomplicated falciparum malaria. Twenty-eight patients received halofantrine and 27 received mefloquine. halofantrine was administered in 3 doses of 500 mg at 6 hour intervals and mefloquine was administered in divided doses of 1,250 mg or 1,500 mg depending on whether the patients weighed less than or more than 60 kg. The patients were followed for 42 days and observed for drug tolerance and evidence of recrudescence. Response to treatment was favorable with both drugs, but three patients (two treated with halofantrine and one with mefloquine) did not completely eliminate malaria parasites from peripheral blood films in seven days. The parasite and fever clearance times were 75.6 and 55.7 hours, and 80.1 and 61.3 hours, respectively for halofantrine and mefloquine. However, 12 patients recrudesced during the 42 day follow-up period. Nine of these had been treated with halofantrine and three with mefloquine. The 42-day cure rate for the two drugs was 56% and 84%, respectively. The side-effects of halofantrine and mefloquine were comparable and transient . These are diarrhea, dizziness, orthostatic hypotension and black out. However, vomiting was found to be more common in mefloquine group (41% vs 22%).\n\nsentence: The side-effects of halofantrine and mefloquine were comparable and transient .",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.cdr_ner | science.cdr_ner.128 | [
{
"content": "Find all entities of these types in the text: [\"Chemical\", \"Disease\"].\n\nOutput a JSON object.\n\nText:\nMemory facilitation and stimulation of endogenous nerve growth factor synthesis by the acetylcholine releaser PG-9. The effects of PG-9 (3alpha-tropyl 2-(p-bromophenyl)propionate), the acetylcholine releaser, on memory processes and nerve growth factor (NGF) synthesis were evaluated. In the mouse passive-avoidance test, PG-9 (10-30 mg/kg, i.p.), administered 20 min before the training session, prevented amnesia induced by both the non selective antimuscarinic drug scopolamine and the M1-selective antagonist S-(-)-ET-126. In the same experimental conditions, PG-9 (5-20 microg per mouse, i.c.v.) was also able to prevent antimuscarine-induced amnesia, demonstrating a central localization of the activity. At the highest effective doses, PG-9 did not produce any collateral symptoms as revealed by the Irwin test, and it did not modify spontaneous motility and inspection activity, as revealed by the hole-board test. PG-9 was also able to increase the amount of NGF secreted in vitro by astrocytes in a dose-dependent manner. The maximal NGF contents obtained by PG-9 were 17.6-fold of the control value. During culture, no morphological changes were found at effective concentrations of PG-9. The current work indicates the ability of PG-9 to induce beneficial effects on cognitive processes and stimulate activity of NGF synthesis in astroglial cells. Therefore, PG-9 could represent a potential useful drug able to improve the function of impaired cognitive processes.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"PG-9\", \"S-(-)-ET-126\", \"scopolamine\", \"3alpha-tropyl 2-(p-bromophenyl)propionate\", \"acetylcholine\"], \"Disease\": [\"amnesia\"]}",
"role": "assistant"
}
]
|
science.cdr_ner | science.cdr_ner.334 | [
{
"content": "Find all entities of these types in the text: [\"Chemical\", \"Disease\"].\n\nOutput a JSON object.\n\nText:\nNeuroprotective action of MPEP, a selective mGluR5 antagonist, in methamphetamine-induced dopaminergic neurotoxicity is associated with a decrease in dopamine outflow and inhibition of hyperthermia in rats. The aim of this study was to examine the role of metabotropic glutamate receptor 5 (mGluR5) in the toxic action of methamphetamine on dopaminergic neurones in rats. Methamphetamine (10 mg/kg sc), administered five times, reduced the levels of dopamine and its metabolites in striatal tissue when measured 72 h after the last injection. A selective antagonist of mGluR5, 2-methyl-6-(phenylethynyl)pyridine (MPEP; 5 mg/kg ip), when administered five times immediately before each methamphetamine injection reversed the above-mentioned methamphetamine effects. A single MPEP (5 mg/kg ip) injection reduced the basal extracellular dopamine level in the striatum, as well as dopamine release stimulated either by methamphetamine (10 mg/kg sc) or by intrastriatally administered veratridine (100 microM). Moreover, it transiently diminished the methamphetamine (10 mg/kg sc)-induced hyperthermia and reduced basal body temperature. MPEP administered into the striatum at high concentrations (500 microM) increased extracellular dopamine levels, while lower concentrations (50-100 microM) were devoid of any effect. The results of this study suggest that the blockade of mGluR5 by MPEP may protect dopaminergic neurones against methamphetamine-induced toxicity. Neuroprotection rendered by MPEP may be associated with the reduction of the methamphetamine-induced dopamine efflux in the striatum due to the blockade of extrastriatal mGluR5, and with a decrease in hyperthermia.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"dopamine\", \"methamphetamine\", \"2-methyl-6-(phenylethynyl)pyridine\", \"Methamphetamine\", \"MPEP\", \"glutamate\", \"veratridine\"], \"Disease\": [\"hyperthermia\", \"neurotoxicity\", \"toxicity\"]}",
"role": "assistant"
}
]
|
science.nlmgene_ner | science.nlmgene_ner.295 | [
{
"content": "Find all entities of these types in the text: [\"Gene\"].\n\nOutput a JSON object.\n\nText:\nNF-κB functions as a molecular link between tumor cells and Th1/Tc1 T cells in the tumor microenvironment to exert radiation-mediated tumor suppression. Radiation modulates both tumor cells and immune cells in the tumor microenvironment to exert its anti-tumor activity; however, the molecular connection between tumor cells and immune cells that mediates radiation-exerted tumor suppression activity in the tumor microenvironment is largely unknown. We report here that radiation induces rapid activation of the p65/p50 and p50/p50 NF-κB complexes in human soft tissue sarcoma (STS) cells. Radiation-activated p65/p50 and p50/p50 bind to the TNFα promoter to activate its transcription in STS cells. Radiation-induced TNFα induces tumor cell death in an autocrine manner. A sublethal dose of Smac mimetic BV6 induces cIAP1 and cIAP2 degradation to increase tumor cell sensitivity to radiation-induced cell death in vitro and to enhance radiation-mediated suppression of STS xenografts in vivo. Inhibition of caspases, RIP1, or RIP3 blocks radiation/TNFα-induced cell death, whereas inhibition of RIP1 blocks TNFα-induced caspase activation, suggesting that caspases and RIP1 act sequentially to mediate the non-compensatory cell death pathways. Furthermore, we determined in a syngeneic sarcoma mouse model that radiation up-regulates IRF3, IFNβ, and the T cell chemokines CCL2 and CCL5 in the tumor microenvironment, which are associated with activation and increased infiltration of Th1/Tc1 T cells in the tumor microenvironment. Moreover, tumor-infiltrating T cells are in their active form since both the perforin and FasL pathways are activated in irradiated tumor tissues. Consequently, combined BV6 and radiation completely suppressed tumor growth in vivo. Therefore, radiation-induced NF-κB functions as a molecular link between tumor cells and immune cells in the tumor microenvironment for radiation-mediated tumor suppression.",
"role": "user"
},
{
"content": "{\"Gene\": [\"IFN\\u03b2\", \"RIP3\", \"cIAP2\", \"TNF\\u03b1\", \"p50\", \"caspase\", \"caspases\", \"IRF3\", \"cIAP1\", \"CCL2\", \"perforin\", \"CCL5\", \"RIP1\", \"NF-\\u03baB\", \"p65\", \"FasL\"]}",
"role": "assistant"
}
]
|
science.acl_arc_intent_classification | science.acl_arc_intent_classification.1050 | [
{
"content": "Classify the intent of this citation from an NLP research paper. \n\nYour answer must be one word from: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. No other text allowed.\n\nSection Title:\nmethod\n\nContext before:\n⢠A user study was performed, but it was either very small compared to the corpus (Carmel, Shtalhaim, and Soffer 2000; Jijkoun and de Rijke 2005), or the corpus itself was significantly smaller than ours (Feng et al. 2006; Leuski et al. 2006). ⢠Only an automatic evaluation was performed, which relied on having model responses (Berger and Mittal 2000; Berger et al. 2000). ⢠Only qualitative observations of the responses were reported (no formal evaluation was performed) (Lapalme and Kosseim 2003; Roy and Subramaniam 2006).\n\nCitation:\n⢠A user study was performed , but it was either very small compared to the corpus ( Carmel , Shtalhaim , and Soffer 2000 ; Jijkoun and de Rijke 2005 ) , or the corpus itself was significantly smaller than ours ( Feng et al. 2006 ; Leuski et al. 2006 ) .\n\nContext after:\nThe representativeness of the sample size was not discussed in any of these studies. \u0000\u0000\u0000\u0000\u0000\u0000 There are significant practical difficulties associated with conducting the user studies needed to produce meaningful results for our system. Firstly, the size of our corpus and the number of parameters and settings that we need to test mean that in order for a user study to be representative, a fairly large sample involving several hundreds of requestâresponse pairs would have to be used. Further, user-based evaluations of the output produced by our system require the subjects to read relatively long requestâ response e-mails, which quickly becomes tedious.",
"role": "user"
},
{
"content": "CompareOrContrast",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_plos_single_doc_summ | science.scientific_lay_summarisation_plos_single_doc_summ.22130 | [
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: The Salmonella Deubiquitinase SseL Inhibits Selective Autophagy of Cytosolic Aggregates\nArticle:\nAbstract:\nCell stress and infection promote the formation of ubiquitinated aggregates in both non-immune and immune cells. These structures are recognised by the autophagy receptor p62/sequestosome 1 and are substrates for selective autophagy. The intracellular growth of Salmonella enterica occurs in a membranous compartment, the Salmonella-containing vacuole( SCV), and is dependent on effectors translocated to the host cytoplasm by the Salmonella pathogenicity island-2( SPI-2) encoded type III secretion system( T3SS). Here, we show that bacterial replication is accompanied by the formation of ubiquitinated structures in infected cells. Analysis of bacterial strains carrying mutations in genes encoding SPI-2 T3SS effectors revealed that in epithelial cells, formation of these ubiquitinated structures is dependent on SPI-2 T3SS effector translocation, but is counteracted by the SPI-2 T3SS deubiquitinase SseL. In macrophages, both SPI-2 T3SS-dependent aggregates and aggresome-like induced structures( ALIS) are deubiquitinated by SseL. In the absence of SseL activity, ubiquitinated structures are recognized by the autophagy receptor p62, which recruits LC3 and targets them for autophagic degradation. We found that SseL activity lowers autophagic flux and favours intracellular Salmonella replication. Our data therefore show that there is a host selective autophagy response to intracellular Salmonella infection, which is counteracted by the deubiquitinase SseL.\nIntroduction:\nSalmonella enterica is a facultative intracellular pathogen that survives and replicates in a variety of hosts. The virulence traits of Salmonella include the Salmonella pathogenicity-island( SPI)-1- and-2-encoded type 3 secretion systems( T3SSs), which are important for invasion of host cells[1] and intracellular replication[2],[3], respectively. Intracellular replication occurs in a membrane-enclosed compartment, the Salmonella-containing vacuole( SCV), and requires the delivery of an extensive repertoire of effectors to the host cytoplasm by the SPI-2 T3SS[4]. Ubiquitination is an essential process in eukaryotic cells that regulates protein degradation, localization and function. The ability to manipulate the ubiquitin system is a feature common to many intracellular pathogens, including Salmonella, which delivers several effectors to the cell cytosol that interfere with the host cell ubiquitination[5],[6]. Absence of the SPI-2 T3SS-delivered deubiquitinase SseL leads to an accumulation of ubiquitinated proteins within infected cells and attenuates Salmonella virulence in mice[7]. Intracellular bacteria generate a diverse array of substrates that are ubiquitinated during infection. These include vacuolar membrane remnants produced after intracellular lysis of bacterial vacuoles[8], bacterial cell wall products[9] and protein aggregates or aggresome-like induced structures( ALIS)[10]–[12]. In addition, bacterial LPS, cell stress and toll-like receptor( TLR) signalling can trigger the formation of ALIS in several cell types, including macrophages[13],[14]. ALIS and other ubiquitinated protein aggregates are targeted by ubiquitin binding proteins such as p62/sequestosome 1( p62 hereafter), which can lead to receptor-mediated selective macroautophagy( hereafter referred to as selective autophagy). In response to this cellular defence pathway, bacteria have evolved different ways to interfere with selective autophagy. Listeria ActA recruits the Arp2/3 complex and Ena/VASP to the surface of cytosolic bacteria to prevent recognition by ubiquitin and p62[15]. Likewise, Shigella camouflages its surface through binding of the T3SS effector protein IcsB to the bacterial surface protein IcsA/VirG, thereby preventing the recognition of VirG by the autophagy-related protein, Atg5[16], and avoiding recruitment of ubiquitin and p62[17]. The ubiquitination and selective autophagy of cytosolic Salmonella has been studied extensively by others[18]–[20]. In this work, we demonstrate that Salmonella within vacuoles induces a cellular response leading to the formation of SPI-2 T3SS-dependent ubiquitinated aggregates and ALIS during infection. We show that a SPI-2 T3SS effector, SseL, deubiquitinates these aggregates and prevents the recruitment of the autophagy markers p62 and LC3. SseL deubiquitinase activity leads to a reduction in autophagic flux during infection and promotes intracellular bacterial replication.\nDiscussion:\nWe have shown that intravacuolar Salmonella induces the formation of ubiquitinated aggregates containing autophagic markers in both epithelial cells and macrophages. In epithelial cells, rather diffuse ubiquitin puncta were found close to SCVs, and these partially co-localized with LAMP1 and electron-dense material. These structures were SPI-2 T3SS-dependent and required the combined activities of SifA and SseJ, effectors that regulate vacuolar membrane dynamics and which perturb the endosomal network[35]. Infected macrophages contained similar structures and also dense, more spherical aggregates that resemble ALIS. Although such ALIS have not been characterized previously in Salmonella-infected cells, they are similar to those induced in macrophages following bacterial LPS stimulation[13],[14]. The aggregates found in Salmonella-infected macrophages resembled LPS-induced ALIS in their size, shape and recruitment of p62 and LC3[14], suggesting that LPS signalling through TLR4 might trigger their formation. Remarkably, both aggregates and ALIS in epithelial cells and macrophages are targets for the SPI-2 T3SS effector, SseL, which deubiquitinates as yet unidentified p62-bound proteins and reduces the recruitment of autophagic machinery. It was reported recently that knockout of the deubiquitinase AMSH( associated molecule with the SH3 domain of STAM) in mice caused accumulation of ubiquitinated inclusions containing p62 in neurons[46]. In addition, LPS-induced autophagic signalling can be reduced by the deubiquitinase A20 which deubiquitinates K63-linked chains from Beclin-1[47]. However, it is not known whether A20 or AMSH act directly on substrates of autophagy or whether their effects are indirect. Therefore, to our knowledge SseL is the first deubiquitinase to be described that targets material destined for autophagic degradation, and this represents a new mechanism by which Salmonella counteracts a cellular response induced by an innate immune signalling pathway. It is likely that a proportion of the ubiquitinated aggregates found in macrophages form in response to LPS-TLR4 signalling, as S. Typhimurium LPS stimulates ALIS formation in RAW 264. 7 macrophages[13] and LPS-induced ALIS in macrophages have been shown to require TLR4 signalling[14]. However other bacterial products may also be involved; Listeria monocytogenes culture broth, zymosan beads as well as heat treatment and cell stress have been shown to induce ALIS formation in several cell types[11],[13]. The presence of ubiquitinated aggregates in Salmonella-infected macrophages might also be inhibited by other effectors that interfere with TLR-dependent immune signalling, such as the phosphothreonine lyase SpvC, which acts on MAP kinases downstream of MyD88[48]. Ubiquitinated aggregates that are targeted by selective autophagy have been described in cells exposed to other bacterial pathogens, but these have mainly been cytosolic or extracellular bacteria[8],[9],[49],[50]. However, expression of the Legionella pneumophila Dot/Icm type IV secretion system in macrophages was shown to reduce ALIS formation during infection[12]. Although a Legionella deubiquitinase has not yet been identified, these observations together with our results suggest that such an activity might exist. Indeed it is possible that deubiquitinases of other pathogens might target ubiquitinated aggregates in a similar way, and their activity could mask the presence of these aggregates. An inability to degrade misfolded or aggregated proteins can lead to cell death, as seen in neurodegenerative disorders[51]. Autophagy ameliorates the cellular stress induced by the presence of protein aggregates[52]. Therefore it is possible that the reduction in autophagic flux mediated by SseL accounts for its ability to induce delayed cytotoxicity in macrophages[7]. While the possible functions of ALIS remain unclear, they serve to sequester cytosolic proteins under a variety of stress conditions and are suggested to be involved in host immune defence[14],[53],[54]. The ubiquitinated proteins in ALIS are considered as a source of antigenic peptides for presentation on MHC class I molecules in dendritic cells[14],[53],[54]; therefore the deubiquitination of aggregates by SseL might regulate antigen presentation in infected macrophages. It will be important to determine the fate of proteins contained within Salmonella-induced aggregates following deubiquitination by SseL. As ubiquitin, p62 and LC3 are currently the only markers of these structures, we are unable to assess whether they persist in cells following their deubiquitination. The presence of non-ubiquitinated protein inclusions may also adversely affect the cell and impede bacterial replication. The identity of the substrates within aggregates that are targeted for deubiquitination by SseL remains elusive. The ability of exogenously expressed SseL to target puromycin-induced ALIS suggests that it may be a promiscuous deubiquitinase that can target a number of substrates and that its activity is regulated by its localization to the SCV during infection. It is known that the activity of SseL contributes to Salmonella growth in vivo[7]. In the present study we found that SseL also contributes to intracellular replication in macrophages. In the permissive RAW264. 7 macrophage cell line, no differences in replication were observed between wild-type bacteria and the ΔsseL mutant, but an increase in replication occurred upon over-expression of active SseL. However, in the more restrictive bone-marrow derived macrophages, which better represent the cells that Salmonella encounters in vivo, replication was reduced in the absence of SseL. Recent work has proposed that SseL binds to oxysterol-binding protein( OSBP)[55], and interferes with lipid metabolism, leading to the clearance of lipid droplets, which otherwise accumulate during infection of mice gallbladder epithelial cells[56]. Lipid droplet metabolism has been associated with autophagy[57]; therefore it would be interesting to study the possible relationship between the inhibition of selective autophagy by SseL and its interference with lipid droplet metabolism. Understanding how SseL interferes with selective autophagy and contributes to bacterial replication and cytotoxicity will be helped by the identification of molecules present in the ubiquitinated aggregates and the ubiquitin-conjugated proteins that are targeted by SseL. Many intracellular bacteria produce effectors that are known to interfere with ubiquitin-related processes, suggesting that modulating this pathway is important for bacterial growth and survival inside cells. During and following cell invasion, the ubiquitination machinery is used by Salmonella SPI-1 T3SS effectors to regulate both their degradation and cellular localization[58],[59]. Our work has shown that ubiquitinated aggregates are formed at late time-points in infected cells, in response to both SPI-2 T3SS-dependent rearrangement of endocytic compartments and to SPI-2 T3SS-independent signals. We found that Salmonella uses the SPI-2 T3SS effector SseL to deubiquitinate proteins in these aggregates, thereby impeding their autophagic degradation. The possible links between this interference of autophagy and SseL-associated cytotoxicity and replication will be the subject of future research.",
"role": "user"
},
{
"content": "Ubiquitination can target substrates to a number of fates , including autophagy , the essential cellular process that allows cells to degrade cytosolic material . Although Salmonella enterica resides in a vacuolar compartment during infection , it translocates several virulence proteins into the host cell cytoplasm . We have found that intracellular Salmonella induces the formation of ubiquitinated aggregates near the Salmonella-containing vacuole and that these aggregates are recognised by the autophagy machinery . Salmonella inhibits this response through the action of a translocated enzyme , SseL , which deubiquitinates the aggregates and thereby decreases the recruitment of autophagy markers . We show that SseL alone can deubiquitinate known substrates that are degraded by autophagy , that it reduces autophagy in infected cells and that its activity can increase intracellular Salmonella replication . This is a new example of how a bacterium counteracts a cellular defence pathway through the action of a translocated virulence protein .",
"role": "assistant"
}
]
|
science.chemdner_ner | science.chemdner_ner.3214 | [
{
"content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nOptimization of a 1,5-dihydrobenzo[b][1,4]diazepine-2,4-dione series of HIV capsid assembly inhibitors 2: Structure-activity relationships (SAR) of the C3-phenyl moiety. Detailed structure-activity relationships of the C3-phenyl moiety that allow for the optimization of antiviral potency of a series of 1,5-dihydrobenzo[b][1,4]diazepine-2,4-dione inhibitors of HIV capsid (CA) assembly are described. Combination of favorable substitutions gave additive SAR and allowed for the identification of the most potent compound in the series, analog 27. Productive SAR also transferred to the benzotriazepine and spirobenzodiazepine scaffolds, providing a solution to the labile stereocenter at the C3 position. The molecular basis of how compound 27 inhibits mature CA assembly is rationalized using high-resolution structural information. Our understanding of how compound 27 may inhibit immature Gag assembly is also discussed.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"1,5-dihydrobenzo[b][1,4]diazepine-2,4-dione\", \"spirobenzodiazepine\", \"benzotriazepine\", \"phenyl\"]}",
"role": "assistant"
}
]
|
science.scitldr_aic | science.scitldr_aic.1616 | [
{
"content": "Summarize the paper:\n\nPaper text:\n\nPlain recurrent networks greatly suffer from the vanishing gradient problem while Gated Neural Networks (GNNs) such as Long-short Term Memory (LSTM) and Gated Recurrent Unit (GRU) deliver promising results in many sequence learning tasks through sophisticated network designs.\nThis paper shows how we can address this problem in a plain recurrent network by analyzing the gating mechanisms in GNNs.\nWe propose a novel network called the Recurrent Identity Network (RIN) which allows a plain recurrent network to overcome the vanishing gradient problem while training very deep models without the use of gates.\nWe compare this model with IRNNs and LSTMs on multiple sequence modeling benchmarks.\nThe RINs demonstrate competitive performance and converge faster in all tasks.\nNotably, small RIN models produce 12%–67% higher accuracy on the Sequential and Permuted MNIST datasets and reach state-of-the-art performance on the bAbI question answering dataset.\nNumerous methods have been proposed for mitigating the vanishing gradient problem including the use of second-order optimization methods (e.g., Hessian-free optimization BID15 ), specific training schedules (e.g., Greedy Layer-wise training BID20 BID7 BID24 ), and special weight initialization methods when training on both plain FFNs and RNNs BID3 BID16 BID13 BID10 BID26 BID11 .Gated\nNeural Networks (GNNs) also help to mitigate this problem by introducing \"gates\" to control information flow through the network over layers or sequences. Notable\nexamples include recurrent networks such as Long-short Term Memory (LSTM) BID8 , Gated Recurrent Unit (GRU) BID1 , and feedforward networks such as Highway Networks (HNs) BID21 , and Residual Networks (ResNets) BID5 . One can\nsuccessfully train very deep models by employing these models, e.g., ResNets can be trained with over 1,000 layers. It has\nbeen demonstrated that removing (lesioning) or reordering (re-shuffling) random layers in deep feedforward GNNs does not noticeable affect the performance of the network BID23 Noticeably, one interpretation for this effect as given by BID4 is that the functional blocks in HNs or ResNets engage in an Unrolled Iterative Estimate (UIE) of representations and that layers in this block of HNs or ResNets iteratively refine a single set of representations.In this paper, we investigate if the view of Iterative Estimation (IE) can also be applied towards recurrent GNNs (Section 2.1). We present\na formal analysis for GNNs by examining a dual gate design common in LSTM and GRU (Section 2.2). The analysis\nsuggests that the use of gates in GNNs encourages the network to learn an identity mapping which can be beneficial in training deep architectures BID6 BID4 .We propose a\nnew formulation of a plain RNN, called a Recurrent Identity Network (RIN) , that is encouraged to learn an identity mapping without the use of gates (Section 2). This network\nuses ReLU as the activation function and contains a set of non-trainable parameters. This simple\nyet effective method helps the plain recurrent network to overcome the vanishing gradient problem while it is still able to model long-range dependencies. This network\nis compared against two competing networks, the IRNN (Le et al., 2015) and LSTM, on several long sequence modeling tasks including the adding problem (Section 3.1), Sequential and Permuted MNIST classification tasks (Section 3.2), and bAbI question answering tasks (Section 3.3). RINs show faster\nconvergence than IRNNs and LSTMs in the early stage of the training phase and reach competitive performance in all benchmarks. Note that the use\nof ReLU in RNNs usually leads to training instability, and therefore the network is sensitive to training hyperparameters. Our proposed RIN\nnetwork demonstrates that a plain RNN does not suffer from this problem even with the use of ReLUs as shown in Section 3. We discuss further\nimplications of this network and related work in Section 4.\nIn this paper, we discussed the iterative representation refinement in RNNs and how this viewpoint could help in learning identity mapping.\nUnder this observation, we demonstrated that the contribution of each recurrent step a GNN can be jointly determined by the representation that is formed up to the current step, and the openness of the carry gate in later recurrent updates.\nNote in Eq. 9, the element-wise multiplication of C t s selects the encoded representation that could arrive at the output of the layer.\nThus, it is possible to embed a special function in C t s so that they are sensitive to certain pattern of interests.\nFor example, in Phased LSTM, the time gate is inherently interested in temporal frequency selection BID17 .Motivated\nby the analysis presented in Section 2, we propose a novel plain recurrent network variant, the Recurrent Identity Network (RIN), that can model long-range dependencies without the use of gates. Compared\nto the conventional formulation of plain RNNs, the formulation of RINs only adds a set of non-trainable weights to represent a \"surrogate memory\" component so that the learned representation can be maintained across two recurrent steps.Experimental results in Section 3 show that RINs are competitive against other network models such as IRNNs and LSTMs. Particularly\n, small RINs produce 12%-67% higher accuracy in the Sequential and Permuted MNIST. Furthermore\n, RINs demonstrated much faster convergence speed in early phase of training, which is a desirable advantage for platforms with limited computing resources. RINs work\nwell without advanced methods of weight initializations and are relatively insensitive to hyperparameters such as learning rate, batch size, and selection of optimizer. This property\ncan be very helpful when the time available for choosing hyperparameters is limited. Note that we\ndo not claim that RINs outperform LSTMs in general because LSTMs may achieve comparable performance with finely-tuned hyperparameters.The use of ReLU in RNNs might be counterintuitive at first sight because the repeated application of this activation is more likely causing gradient explosion than conventional choices of activation function, such as hyperbolic tangent (tanh) function or sigmoid function. Although the\nproposed IRNN BID13 reduces the problem by the identity initialization, in our experiments, we usually found that IRNN is more sensitive to training parameters and more unstable than RINs and LSTMs. On the contrary\n, feedforward models that use ReLU usually produce better results and converge faster than FFNs that use the tanh or sigmoid activation function. In this paper,\nwe provide a promising method of using ReLU in RNNs so that the network is less sensitive to the training conditions. The experimental\nresults also support the argument that the use of ReLU significantly speeds up the convergence.During the development of this paper, a recent independent work BID27 presented a similar network formulation with a focus on training of deep plain FFNs without skip connections. DiracNet uses the\nidea of ResNets where it assumes that the identity initialization can replace the role of the skip-connection in ResNets. DiracNet employed\na particular kind of activation function -negative concatenated ReLU (NCReLU), and this activation function allows the layer output to approximate the layer input when the expectation of the weights are close to zero. In this paper, we\nshowed that an RNN can be trained without the use of gates or special activation functions, which complements the findings and provides theoretical basis in BID27 .We hope to see more\nempirical and theoretical insights that explains the effectiveness of the RIN by simply embedding a non-trainable identity matrix. In future, we will\ninvestigate the reasons for the faster convergence speed of the RIN during training. Furthermore, we will\ninvestigate why RIN can be trained stably with the repeated application of ReLU and why it is less sensitive to training parameters than the two other models.A ALGEBRA OF EQS. 8-9Popular GNNs such\nas LSTM, GRU; and recent variants such as the Phased-LSTM BID17 , and Intersection RNN BID2 , share the same dual gate design described as follows: DISPLAYFORM0 where t ∈ [1, T ], H t = σ(x t , h t−1 ) represents the hidden transformation, T t = τ (x t , h t−1 ) is the transform gate, and C t = φ(x t , h t−1 ) is the carry gate. σ, τ and φ are recurrent\nlayers that have their trainable parameters and activation functions. represents element-wise\nproduct operator. Note that h t may not be\nthe output activation at the recurrent step t. For example in LSTM, h t\nrepresents the memory cell state. Typically, the elements\nof transform gate T t,k and carry gate C t,k are between 0 (close) and 1 (open), the value indicates the openness of the gate at the kth neuron. Hence, a plain recurrent\nnetwork is a subcase of Eq. 14 when T t = 1 and C t = 0.Note that conventionally, the initial hidden activation h 0 is 0 to represent a \"void state\" at the start of computation. For h 0 to fit into Eq.\n4's framework, we define an auxiliary state h −1 as the previous state of h 0 , and T 0 = 1, C 0 = 0. We also define another\nauxiliary state h T +1 = h T , T T +1 = 0, and C T +1 = 1 as the succeeding state of h T .Based on the recursive\ndefinition in Eq. 4, we can write the final layer output h T as follows: DISPLAYFORM1 where we use to represent element-wise multiplication over a series of terms.According to Eq. 3, and supposing that Eq. 5 fulfills the Eq. 1, we can use a zero-mean residual t for describing the difference between the outputs of recurrent steps: DISPLAYFORM2 Then we can rewrite Eq. 16 as: DISPLAYFORM3 Substituting Eq. 18 into Eq. 15: DISPLAYFORM4 We can rearrange Eqn. 20 to DISPLAYFORM5 The\nterm λ in Eq. 23 can be reorganized to, DISPLAYFORM6 B DETAILS IN THE ADDING PROBLEM EXPERIMENTS Average Estimation Error RIN 2-100 1st IRNN 2-100 1st LSTM 2-100 1st 0 100 200 300 400 500 600 700 800 layer 2 step index RIN 2-100 2nd IRNN 2-100 2nd LSTM 2-100 2nd DISPLAYFORM7 DISPLAYFORM8",
"role": "user"
},
{
"content": "We propose a novel network called the Recurrent Identity Network (RIN) which allows a plain recurrent network to overcome the vanishing gradient problem while training very deep models without the use of gates.",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.28491 | [
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nAlmost all of the current process scheduling algorithms which are used in modern operating systems (OS) have their roots in the classical scheduling paradigms which were developed during the 1970's. But modern computers have different types of software loads and user demands. We think it is important to run what the user wants at the current moment. A user can be a human, sitting in front of a desktop machine, or it can be another machine sending a request to a server through a network connection. We think that OS should become intelligent to distinguish between different processes and allocate resources, including CPU, to those processes which need them most. In this work, as a first step to make the OS aware of the current state of the system, we consider process dependencies and interprocess communications. We are developing a model, which considers the need to satisfy interactive users and other possible remote users or customers, by making scheduling decisions based on process dependencies and interprocess communications. Our simple proof of concept implementation and experiments show the effectiveness of this approach in the real world applications. Our implementation does not require any change in the software applications nor any special kind of configuration in the system, Moreover, it does not require any additional information about CPU needs of applications nor other resource requirements. Our experiments show significant performance improvement for real world applications. For example, almost constant average response time for Mysql data base server and constant frame rate for mplayer under different simulated load values.\n\nCited Abstract(s):\n[1]: Desktop operating systems such as Windows and Linux base scheduling decisions on CPU consumption; processes that consume fewer CPU cycles are prioritized, assuming that interactive processes gain from this since they spend most of their time waiting for user input. However, this doesn't work for modern multimedia applications which require significant CPU resources. We therefore suggest a new metric to identify interactive processes by explicitly measuring interactions with the user, and we use it to design and implement a process scheduler. Measurements using a variety of applications indicate that this scheduler is very effective in distinguishing between competing interactive and noninteractive processes.",
"role": "user"
},
{
"content": "[1] use process display output production as a means of detecting interactive and multimedia applications. They schedule processes based on their display output production in a way that all processes have a chance to produce display output at the same rate. That might be usefull for multimedia applications where, for example, all video applications play at the same frame rate regardless of their window size. This approach only addresses desktop applications as any network user has no display access. Also, it might be possible that a compute intensive job creates a huge amount of disply output and receives an increase in its priority while it actually is not an interactive application.",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_plos_single_doc_summ | science.scientific_lay_summarisation_plos_single_doc_summ.23296 | [
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Transcriptomic Analysis of Host Immune and Cell Death Responses Associated with the Influenza A Virus PB1-F2 Protein\nArticle:\nAbstract:\nAirway inflammation plays a major role in the pathogenesis of influenza viruses and can lead to a fatal outcome. One of the challenging objectives in the field of influenza research is the identification of the molecular bases associated to the immunopathological disorders developed during infection. While its precise function in the virus cycle is still unclear, the viral protein PB1-F2 is proposed to exert a deleterious activity within the infected host. Using an engineered recombinant virus unable to express PB1-F2 and its wild-type homolog, we analyzed and compared the pathogenicity and host response developed by the two viruses in a mouse model. We confirmed that the deletion of PB1-F2 renders the virus less virulent. The global transcriptomic analyses of the infected lungs revealed a potent impact of PB1-F2 on the response developed by the host. Thus, after two days post-infection, PB1-F2 invalidation severely decreased the number of genes activated by the host. PB1-F2 expression induced an increase in the number and level of expression of activated genes linked to cell death, inflammatory response and neutrophil chemotaxis. When generating interactive gene networks specific to PB1-F2, we identified IFN-γ as a central regulator of PB1-F2-regulated genes. The enhanced cell death of airway-recruited leukocytes was evidenced using an apoptosis assay, confirming the pro-apoptotic properties of PB1-F2. Using a NF-kB luciferase adenoviral vector, we were able to quantify in vivo the implication of NF-kB in the inflammation mediated by the influenza virus infection; we found that PB1-F2 expression intensifies the NF-kB activity. Finally, we quantified the neutrophil recruitment within the airways, and showed that this type of leukocyte is more abundant during the infection of the wild-type virus. Collectively, these data demonstrate that PB1-F2 strongly influences the early host response during IAV infection and provides new insights into the mechanisms by which PB1-F2 mediates virulence.\nIntroduction:\nInfluenza A virus( IAV) commonly causes acute respiratory infection and is one of the most important human pathogens, causing between 250, 000 and 500, 000 deaths every year around the world[1]. IAV are enveloped viruses belonging to the Orthomyxoviridae family. Their negative strand RNA genome is composed of 8 segments encoding up to 12 proteins. PB1-F2 is a virulence factor first described 10 years ago[2]. This 75–90 amino acid long accessory protein is encoded by an alternative +1 reading frame on segment 2 which also encodes the RNA polymerase basic protein 1( PB1) and N40, an N-terminally truncated version of PB1 lacking transcriptase function[2],[3]. PB1-F2 is expressed by most IAV strains and has been shown to be associated with immunopathological processes observed during infection[4],[5],[6]. During IAV infection, production of pro-inflammatory cytokines generally results in an innate host response that controls the virus propagation until it is eliminated by the adaptive immune system. However, in some cases, excessive host inflammatory response contributes to disease severity, especially with highly pathogenic strains such as avian H5N1 or the 1918 pandemic H1N1 strain( “Spanish flu”)[7],[8]. PB1-F2 is suspected to contribute to this disproportional response which frequently leads to vital respiratory tissue damage and death of the infected person[5]. Several in vivo studies allowed determining the pathophysiological consequences of PB1-F2 expression during IAV infection. Using an attenuated model of mouse infection, Zamarin et al. demonstrated that wild type( wt) IAV displays a higher pathogenicity than its PB1-F2 knockout counterpart[9]. A single N66S mutation present in the PB1-F2 of the 1918 pandemic strain is sufficient to transform a strain of moderate virulence into a highly pathogenic virus in mice[10]. More recently, a study analyzing the effects of PB1-F2 in the IAV-induced pathogenesis of avian hosts also revealed that amino acid changes within the PB1-F2 reading frame of a highly pathogenic avian IAV decrease lethality in ducks[11]. PB1-F2 was also described as facilitating secondary infection with Streptococcus pneumoniae[12]. In contrast, when introducing a functional PB1-F2 in the 2009 pandemic H1N1 IAV that does not encode this accessory protein, only minimal immune response modulation was observed, underlying the complex contribution of PB1-F2 in virulence[13]. We recently showed that PB1-F2 exacerbates IFN-β production through the activation of the NF-κB pathway during IAV infection of the human respiratory epithelial cell line A549, but not during infection of immune cells[6]. Despite its apoptotic functions, pathways related to cell death were not activated differently in wt and PB1-F2 knockout virus-infected A549 cells. In the present study, we analyzed the global transcriptional response of the mouse respiratory tract associated to PB1-F2 during IAV infection. We report that PB1-F2 expression during IAV infection increases the inflammatory response of the host. PB1-F2 plays a major role in NF-κB pathway activation, chemotaxis of granulocyte and apoptosis of recruited immune cells. Furthermore, we determined that IFN-γ expression is enhanced when PB1-F2 is expressed, and appears to have a central position in the gene network responsible for the respiratory disease provoked by IAV.\nDiscussion:\nInnate immune response is considered as an essential process required for efficient pathogen clearance. However, deregulation of this response can lead to severe damage for the host. The regulation of host defenses to IAV infections is particularly complex and leukocyte recruitment to the inflammatory lung, which is beneficial for clearing the virus, can become deleterious to the host tissues if the reaction is excessive[16]. In fact, although inflammation is essential for IAV clearance, it is becoming increasingly evident that a tight regulation of this process is necessary to avoid development of IAV-related immunopathological sequelae[8],[17]. It illustrates the ambiguity of the host response to infections. The strength of the response has to be proportionate to the pathogen attack in order to eliminate it. If the response is too weak, the pathogen will proliferate, leading to infection. If the host response is too strong, uncontrolled inflammatory reaction will lead to tissue destruction. The present study demonstrates that PB1-F2 is endowed with pro-inflammatory activity and plays a role in the immunopathological consequences observed in severe impairment of influenza-infected lung function. By the use of reverse genetics, we obtained a mutant virus unable to express PB1-F2 and showed that this mutant was less lethal and virulent than the wt virus, consistent with a previous study[9]. These differences cannot be explained by reduced replication efficiency of the ΔF2 virus since no replication variation was observed between the two viruses. Besides, the use of mutants deleted for N40 or PB1-F2 exclude a potential role of N40 in this process. Our previous study identified IFN-β gene as a PB1-F2-mediated exacerbated gene during IAV infection of a human respiratory epithelial cell line[6]. Based on these previous results, we hypothesized that PB1-F2 expression may stimulate in vivo the host immune response, and as a consequence, be a key element that could explain the higher virulence of a virus expressing PB1-F2. IFN-β measurement within infected-mice lungs confirmed our preliminary in vitro observation. To further study whether PB1-F2 could cause immunopathology, we compared the global gene expression patterns of wt- and ΔF2-infected mouse lungs. Our data demonstrate that expression of PB1-F2 during IAV infection enhances the host defense responses by strongly increasing the transcriptional profile of genes involved in inflammation, granulocyte migration and apoptotic pathways. No apoptotic pathways were identified when these two viruses were used to infect human pulmonary epithelial cells in vitro[6]. This may reflect the cell-specific behavior of PB1-F2 that only induces apoptotic process within immune cells and not in epithelial cells[2]. Thus, the use of the wt/ΔF2 virus couple showed the ability of PB1-F2 to modulate the host response, contributing to virulence in vivo. This is supported by a recent work by McAuley et al. characterizing the immunomodulatory properties of several variants of the PB1-F2 protein[5]. Using IPA software, we were able to analyze the functional relationships between the genes differentially regulated when PB1-F2 was expressed or not during infection. The analysis revealed the central role of IFN-γ, which could act as a relay between PB1-F2 and the genes implicated in respiratory disease, inflammatory response, immune cell trafficking, tissue remodeling and apoptosis induction. The PB1-F2-specific increase of IFN-γ expression was confirmed at the protein level in BAL fluids of infected mice. IFN-γ is a member of the type II interferon family and is a potent activator of macrophages and neutrophils. It is worth noting that in the IAV-infected pulmonary environment, IFN-γ represses the innate immunity developed by alveolar macrophages to enhance their adaptive antiviral response through increased MHC gene expression[18]. Consequently, the scavenger receptor MARCO is down-regulated, and innate defense against secondary bacterial infections is suppressed. The link that we identified between PB1-F2 and IFN-γ over-expression appears of first importance since PB1-F2 has been previously described as facilitating the development of opportunistic pneumococcal and staphylococcal infections[12],[19]. Collectively, our data provide a rationale to understand how PB1-F2 exacerbate secondary bacterial infections and post-influenza pneumonia: PB1-F2 induces an apoptosis increase of recruited leucocytes together with a switch of their activation state from innate immunity to adaptive antiviral response through an exacerbation of the IFN-γ expression in the lung. The mechanism by which PB1-F2 mediates inflammatory increase by itself is still unknown. However, NF-κB pathway exacerbation is involved in this process as shown by the dramatic decrease of NF-κB activity in lungs of mice infected by the ΔF2 virus when compared to the wt infection( Fig. 6). The targeting of PB1-F2 to mitochondria could explain the NF-κB pathway exacerbation through a membrane destabilization of this organelle and activation of the RIG-I/MAVS signaling pathway. However PB1-F2 mitochondrial localization is a matter of debate since several studies described differential localization depending on the strain of the virus and the sequence polymorphism of the protein[20],[21]. The capability of PB1-F2 to perforate or target other cellular membranes could also explain its inflammatory and apoptotic activities[14],[22],[23]. Considering the membrane affinity of PB1-F2, it could form protein pores in endoplasmic reticulum and subsequently induce the release of Ca2+ within the cytosol. Such increase in concentration of Ca2+ in the cytosol is described to activate the NF-κB pathway and to play a pivotal role in inducing proinflammatory gene transcription in airway epithelial cells[24]. Another important characteristic of PB1-F2 is its propensity to form or promote the formation of amyloïdic fibers in infected monocytes[14]. These fibrillar aggregates are believed to associate to the membrane, disrupt its integrity and lead to perturbation of the cellular compartmentalization. This suggests that PB1-F2 could contribute to the pulmonary dysfunctions observed throughout IAV infections by several pathways. A striking feature of the inflammation exacerbated by PB1-F2 expression is the enhanced neutrophil recruitment within infected airways. There is evidence, based on their function, that neutrophils play an important role in mediating acute injury characteristic of highly pathogenic IAV infections. Circulating neutrophils migrate to the site of infection and participate in the destruction of pathogens. However this process has to be tightly regulated since the beneficial effect for eliminating microbes can become deleterious to host tissues through the development of lesions. Indeed neutrophils have the potential to damage airspaces by releasing serine proteases and by generating reactive oxygen species[25]. Neutrophil recruitment within lung tissue also increases protein permeability across the endothelial and epithelial barriers of the lung. This leads to the flooding of alveoli by plasma liquid and proteins and is characteristic of early lung injury[26]. However, depletion of neutrophils prior to influenza infection increased viral load and mortality compared to non-treated mice[27], confirming the importance of this type of leucocyte during IAV infection, and underlying the complexity of the host-IAV interactions. A fine balance between inflammation and immunity is necessary to eliminate IAV. Our study shows that PB1-F2 is implicated in the dysfunction of this balance and that it induces a massive recruitment of neutrophils within airspaces through deregulation of the innate host defense. In summary, the present study demonstrated that PB1-F2 expression significantly increases the expression of genes associated with inflammation in the airways of IAV-infected mice. We identified IFN-γ as a pivotal host component implicated in this process, orchestrating immune cell apoptosis induction, granulocyte recruitment and tissue remodeling observed in infected lungs. The PB1-F2 specific NF-κB pathway exacerbation that we revealed is probably involved in this IFN-γ expression increase. Further studies are required to correlate PB1-F2 sequence variability and IAV virulence to help in the prediction of the pathogenicity of emerging virus strains in the human population.",
"role": "user"
},
{
"content": "Influenza A viruses may cause severe respiratory disease . PB1-F2 , a viral protein identified in 2001 is suspected to play a role in influenza-related pneumonia . In order to understand the impact of PB1-F2 in the pathogenesis underlying Influenza A virus infection , we engineered a mutant virus unable to express PB1-F2 . By the use of high-throughput gene expression assays , we compared the host responses of the wild-type-infected and the PB1-F2 mutant-infected mice . We identified that PB1-F2 expression enhances the immune cell death and inflammatory responses of mice . The inflammatory response mediated by the PB1-F2 expression leads to a massive recruitment of leukocytes within the air spaces , a feature that characterizes the influenza-mediated immunopathology . Our results suggest that PB1-F2 is a virulence factor implicated in the deregulation of the inflammatory response observed in acute influenza virus pneumonia . These data underlie the complexities of virus-host interactions and help us understand by which mechanisms Influenza viruses mediate severe respiratory diseases .",
"role": "assistant"
}
]
|
science.qasa_abstractive_qa | science.qasa_abstractive_qa.445 | [
{
"content": "Read this passage from a research paper and answer the question.\n\nContext: creases with the position of the layer in the network. Hence a given input image (cid:126)x is encoded in each layer of the CNN by the filter responses to that image. A layer with N l distinct filters has N l feature maps each of size M l , where M l is the height times the width of the feature map. So the responses in a layer l can be stored in a matrix F l ∈ R N l × M l where F lij is the activation of the i th filter at position j in layer l . To visualise the image information that is encoded at different layers of the hierarchy (Fig 1, content reconstructions) we perform gradient descent on a white noise image to find another image that matches the feature responses of the original image. So let (cid:126)p and (cid:126)x be the original image and the image that is generated and P l and F l their respective feature representation in layer l . We then define the squared-error loss between the two feature representations To generate a texture that matches the style of a given image (Fig 1, style reconstructions), we use gradient descent from a white noise image to find another image that matches the style representation of the original image. This is done by minimising the mean-squared distance between the entries of the Gram matrix from the original image and the Gram matrix of the image to be generated. So let (cid:126)a and (cid:126)x be the original image and the image that is generated and A l and G l their respective style representations in layer l . The contribution of that layer to the total loss is then The gradients of E l with respect to the activations in lower layers of the network can be readily computed using standard error back-propagation. The five style reconstructions in Fig 1 were generated by matching the style representations on layer ‘conv1 1’ (a), ‘conv1 1’ and ‘conv2 1’ (b), ‘conv1 1’, ‘conv2 1’ and ‘conv3 1’ (c), ‘conv1 1’, ‘conv2 1’, ‘conv3 1’ and ‘conv4 1’ (d), ‘conv1 1’, ‘conv2 1’, ‘conv3 1’, ‘conv4 1’ and ‘conv5 1’ (e). To generate the images that mix the content of a photograph with the style of a painting (Fig 2) we jointly minimise the distance of a white noise image from the content representation 11\n\nQuestion: Why did the authors particularly use \"Gradient Descent\" instead of any other optimization algorithm?",
"role": "user"
},
{
"content": "The work uses gradient descent to transform the white noise image to match the stylistic and content representations of an artwork and a photograph respectively. However, they do not discuss the reasons behind choosing gradient descent over other methods and do not provide alternatives.",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.1189 | [
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nDecompressive craniectomy in traumatic brain injury : the randomized multicenter RESCUEicp study ( www.RESCUEicp.com ) . The RESCUEicp ( Randomized Evaluation of Surgery with Craniectomy for Uncontrollable Elevation of intracranial pressure ) study has been established to determine whether decompressive craniectomy has a role in the management of patients with traumatic brain injury and raised intracranial pressure that does not respond to initial treatment measures . We describe the concept of decompressive craniectomy in traumatic brain injury and the rationale and protocol of the RESCUEicp study .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"Decompressive craniectomy\", \"decompressive craniectomy\"], \"Outcome\": [], \"Participant\": []}",
"role": "assistant"
}
]
|
science.scitldr_aic | science.scitldr_aic.1121 | [
{
"content": "Summarize the paper:\n\nPaper text:\n\nKnowledge bases (KB) are often represented as a collection of facts in the form (HEAD, PREDICATE, TAIL), where HEAD and TAIL are entities while PREDICATE is a binary relationship that links the two.\nIt is a well-known fact that knowledge bases are far from complete, and hence the plethora of research on KB completion methods, specifically on link prediction.\nHowever, though frequently ignored, these repositories also contain numerical facts.\nNumerical facts link entities to numerical values via numerical predicates; e.g., (PARIS, LATITUDE, 48.8).\nLikewise, numerical facts also suffer from the incompleteness problem.\nTo address this issue, we introduce the numerical attribute prediction problem.\nThis problem involves a new type of query where the relationship is a numerical predicate.\nConsequently, and contrary to link prediction, the answer to this query is a numerical value.\nWe argue that the numerical values associated with entities explain, to some extent, the relational structure of the knowledge base.\nTherefore, we leverage knowledge base embedding methods to learn representations that are useful predictors for the numerical attributes.\nAn extensive set of experiments on benchmark versions of FREEBASE and YAGO show that our approaches largely outperform sensible baselines.\nWe make the datasets available under a permissive BSD-3 license.\nKnowledge Bases (KBs) are playing an increasingly important role in a number of AI applications.\nKBs can be seen as a collection of facts or triples of the form (head, predicate, tail) , denoted as (h, p, t) , where head and tail correspond to entities and predicate corresponds to a relationship that holds between these two entities.\nThis structured information is easily accessible by AI systems to enhance their performance.\nA variety of AI applications such as recommender systems, natural language chatbots or question answering models, have benefited from the rich structural information archived in these repositories.\nThis is because much of human knowledge can be expressed with one or more conjunctions of knowledge facts.However, KBs' capabilities are limited due to their incompleteness 1 .\nConsequently there has been a flurry of research on knowledge base completion methods in recent years.\nRelationship extraction BID27 (i.e., classification of semantic relationship mentions), knowledge graph matching BID32 BID12 (i.e., alignment and integration of entities and predicates across KBs), or search-based question-answering BID36 (i.e., queries issued to a web search engine) are a few different ways to address the incompleteness problem.\nHowever, the literature on the so-called link prediction methods BID22 has received more attention in the last few years in comparison to the aforementioned approaches.\nContrary to other solutions, link prediction methods aim to find missing links between entities exclusively based on the existing information contained in the KB.\nThis is achieved by ranking entities that are answer candidates for the query.\nThe queries these methods typically address are of the form (USA, /location/contains, ?), or (Madrid, /location/capitalOf, ?), whereas the missing element -represented by a question mark-is an entity contained in the KB.Many link prediction methods only harness feature types learned from the rich relational information contained in the KB to infer new links, and only very recently Niepert, 2018, Pezeshkpour et al., 2018] numerical attributes have been integrated along with other feature types to improve link prediction performance.\nSimilarly, numerical information is also represented as facts such as (Berlin, /location/latitude, 52.31) or (Albert Einstein, /person/birth year, 1879).\nHowever, as shown in BID5 ] the application of numerical attributes is limited because of the same incompleteness problem: Many entities are missing numerical attribute values they are expected to possess.\nFor example, entities that represent locations should have numerical information regarding latitude, longitude or area, among others; whereas for entities representing people, numerical predicates such as the birth year, weight or height would be more appropriate.\nIn this work we focus on the problem of completing queries where the relationship is a numerical predicate.\nConsequently, the answer to this new type of query is a numerical value.\nThis is contrary to the link prediction problem, wherein the answer to a query is always an element of a closed vocabulary.\nExamples of queries addressed in this paper are (Apple Inc., revenue, ?) or (California, average salary, ?).\nWhile one can interpret link prediction as a classification/ranking problem, this is rather a regression problem.The main contributions of this paper are:• We introduce the problem of predicting the value of entities' numerical attributes in KBs.\nFor the sake of simplicity we term this as 'numerical attribute prediction problem'.\nTo our knowledge, this is the first time this problem is addressed in the literature.•\nWe create benchmark datasets for this problem. We\nuse well-known subsets of Freebase and Yago as the blueprints for creating these benchmarks. We\nalso create versions of these datasets for different percentages of sparsity by artificially removing facts that involve numerical predicates. All\nthese benchmark datasets will be made publicly available.• We\npropose two meaningful baselines for this problem. These\nbaselines are inspired by previous work done in the node classification and the imputation literature.• We propose\nsupervised and semi-supervised approaches to this problem. The semisupervised\napproaches significantly outperform the baselines in all datasets and conditions.The paper is organized as follows: We discuss the related work in Section 2. Afterwards we formalize\nthe problem of predicting numerical values for entities' numerical attributes in KBs in Section 3. We describe our approaches\nto this problem, as well as the two baselines. Section 4 reports the experimental\nsetting followed by an extensive set of experiments on different datasets with different degrees of sparsity in Section 5. Finally, we summarize the conclusions\nof our study in Section 6.\nWe introduce a novel problem, namely numerical attribute prediction in knowledge bases.\nContrary to link prediction, the answer to this new query type is a numerical value, and not an element from a (small) closed vocabulary.\nOur premise to this problem is that the relational structure of a KB can be partially explained by the numerical attribute values associated with entities.\nThis allows for leveraging KB embedding methods to learn representations that are useful predictors of numerical attributes.\nAn extensive set of experiments validates our premise.\nFurthermore, we also show that learning KB representations enriched with numerical attribute information are helpful for addressing this task.\nFinally, we believe that this new problem introduced in the paper will spur interest and deeper investigation from the research community.5.\nNote that it is non-negative and is row normalized.\n6. For all practical purposes he is deemed a philosopher in FB15K-237.\n7. Julius Caesar belongs to profession Politician in FB15K-237",
"role": "user"
},
{
"content": "Prediction of numerical attribute values associated with entities in knowledge bases.",
"role": "assistant"
}
]
|
science.ddi_ner | science.ddi_ner.359 | [
{
"content": "Extract entities of these types from the text: [\"Drug\", \"Brand\", \"DrugGroup\", \"UnapprovedDrug\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nThe administration of local anesthetic solutions containing epinephrine or norepinephrine to patients receiving monoamine oxidase inhibitors or tricyclic antidepressants may produce severe, prolonged hypertension. Phenothiazines and butyrophenones may reduce or reverse the pressor effect of epinephrine. Concurrent use of these agents should generally be avoided. In situations when concurrent therapy is necessary, careful patient monitoring is essential. Concurrent administration of vasopressor drugs (for the treatment of hypotension related to obstetric blocks) and ergot-type oxytocic drugs may cause severe, persistent hypertension or cerebrovascular accidents.",
"role": "user"
},
{
"content": "{\"Brand\": [], \"Drug\": [\"epinephrine\", \"norepinephrine\"], \"DrugGroup\": [\"vasopressor drugs\", \"anesthetic solutions\", \"monoamine oxidase inhibitors\", \"tricyclic antidepressants\", \"Phenothiazines\", \"butyrophenones\", \"ergot-type oxytocic drugs\"], \"UnapprovedDrug\": []}",
"role": "assistant"
}
]
|
science.scitldr_aic | science.scitldr_aic.462 | [
{
"content": "Summarize the paper:\n\nPaper text:\n\nProgram verification offers a framework for ensuring program correctness and therefore systematically eliminating different classes of bugs.\nInferring loop invariants is one of the main challenges behind automated verification of real-world programs which often contain many loops.\nIn this paper, we present Continuous Logic Network (CLN), a novel neural architecture for automatically learning loop invariants directly from program execution traces.\nUnlike existing neural networks, CLNs can learn precise and explicit representations of formulas in Satisfiability Modulo Theories (SMT) for loop invariants from program execution traces.\nWe develop a new sound and complete semantic mapping for assigning SMT formulas to continuous truth values that allows CLNs to be trained efficiently.\nWe use CLNs to implement a new inference system for loop invariants, CLN2INV, that significantly outperforms existing approaches on the popular Code2Inv dataset.\nCLN2INV is the first tool to solve all 124 theoretically solvable problems in the Code2Inv dataset.\nMoreover, CLN2INV takes only 1.1 second on average for each problem, which is 40 times faster than existing approaches.\nWe further demonstrate that CLN2INV can even learn 12 significantly more complex loop invariants than the ones required for the Code2Inv dataset.\nProgram verification offers a principled approach for systematically eliminating different classes of bugs and proving the correctness of programs.\nHowever, as programs have become increasingly complex, real-world program verification often requires prohibitively expensive manual effort (Wilcox et al., 2015; Gu et al., 2016; Chajed et al., 2019) .\nRecent efforts have focused on automating the program verification process, but automated verification of general programs with unbounded loops remains an open problem (Nelson et al., 2017; .\nVerifying programs with loops requires determining loop invariants, which captures the effect of the loop on the program state irrespective of the actual number of loop iterations.\nAutomatically inferring correct loop invariants is a challenging problem that is undecidable in general and difficult to solve in practice (Blass & Gurevich, 2001; Furia et al., 2014) .\nExisting approaches use stochastic search (Sharma & Aiken, 2016) , heurstics-based search (Galeotti et al., 2015) , PAC learning based on counter examples (Padhi & Millstein, 2017) , or reinforcement learning (Si et al., 2018) .\nHowever, these approaches often struggle to learn complex, real-world loop invariants.\nIn this paper, we introduce a new approach to learning loop invariants by modeling the loop behavior from program execution traces using a new type of neural architecture.\nWe note that inferring loop invariants can be posed as learning formulas in Satisfiability Modulo Theories (SMT) (Biere et al., 2009 ) over program variables collected from program execution traces (Nguyen et al., 2017) .\nIn principle, Neural networks seem well suited to this task because they can act as universal function approximators and have been successfully applied in various domains that require modeling of arbitrary functions (Hornik et al., 1989; Goodfellow et al., 2016) .\nHowever, loop invariants must be represented as explicit SMT formulas to be usable for program verification.\nUnfortunately, existing methods for extracting logical rules from general neural architectures lack sufficient precision (Augasta & Kathirvalavakumar, 2012) , while inductive logic learning lacks sufficient expressiveness for use in verification (Evans & Grefenstette, 2018) .\nWe address this issue by developing a novel neural architecture, Continuous Logic Network (CLN), which is able to efficiently learn explicit and precise representations of SMT formulas by using continuous truth values.\nUnlike existing neural architectures, CLNs can represent a learned SMT formula explicitly in its structure and thus allow us to precisely extract the exact formula from a trained model.\nIn order to train CLNs, we introduce a new semantic mapping for SMT formulas to continuous truth values.\nOur semantic mapping builds on BL, or basic fuzzy logic (Hájek, 2013) , to support general SMT formulas in a continuous logic setting.\nWe further prove that our semantic model is sound (i.e., truth assignments for the formulas are consistent with their discrete counterparts) and complete (i.e., all formulas can be represented) with regard to the discrete SMT formula space.\nThese properties allow CLNs to represent any quantifier-free SMT formula operating on mixed integer-real arithmetic as an end-to-end differentiable series of operations.\nWe use CLNs to implement a new inference system for loop invariants, CLN2INV, that significantly outperforms state-of-the-art tools on the Code2Inv dataset by solving all 124 theoretically solvable problems in the dataset.\nThis is 20 problems more than LoopInvGen, the winner of the SyGus 2018 competition loop invariant track (Padhi & Millstein, 2017) .\nMoreover, CLN2INV finds invariants for each program in 1.1 second on average, more than 40 times faster than LoopInvGen.\nWe also demonstrate that CLN2INV is able to learn complex, real-world loop invariants with combinations of conjunctions and disjunctions of multivariable constraints.\nOur main contributions are:\n• We introduce a new semantic mapping for assigning continuous truth values to SMT formulas that is theoretically grounded and enables learning formulas through backpropagation.\nWe further prove that our semantic model is sound and complete.\n• We develop a novel neural architecture, Continuous Logic Networks (CLNs), that to the best of our knowledge is the first to efficiently learn precise and explicit SMT formulas by construction.\n• We use CLNs to implement a new loop invariant inference system, CLN2INV, that is the first to solve all 124 theoretically solvable problems in the Code2Inv dataset, 20 more than the existing methods.\nCLN2INV is able to find invariants for each problem in 1.1 second on average, 40× faster than existing systems.\n• We further show CLN2INV is able to learn 12 more complex loop invariants than the ones present in the Code2Inv dataset with combinations of multivariable constraints.\nRelated Work.\nTraditionally, loop invariant learning relies on stochastic or heuristics-guided search (Sharma & Aiken, 2016; Galeotti et al., 2015) .\nOther approaches like NumInv analyze traces and discover conjunctions of equalities by solving a system of linear equations (Sharma et al., 2013; Nguyen et al., 2017) .\nLoopInvGen uses PAC learning of CNF using counter-examples (Padhi et al., 2016; Padhi & Millstein, 2017) .\nBy contrast, Code2Inv learns to guess loop invariants using reinforcement learning with recurrent and graph neural networks (Si et al., 2018) .\nHowever, these approaches struggle to learn complex invariants.\nUnlike these works, CLN2INV efficiently learns complex invariants directly from execution traces.\nThere is a extensive work on PAC learning of boolean formulas, but learning precise formulas require a prohibitively large number of samples (Kearns et al., 1994) .\nSeveral recent works use differentiable logic to learn boolean logic formulas from noisy data (Kimmig et al., 2012; Evans & Grefenstette, 2018; Payani & Fekri, 2019) or improving adversarial robustness by applying logical rules to training (Fischer et al., 2019) .\nBy contrast, our work learns precise SMT formulas directly by construction, allowing us to learn richer predicates with compact representation in a noiseless setting.\nA variety of numerical relaxations have been applied to SAT and SMT solving.\nApplication-specific approximations using methods such as interval overapproximation and slack variables have been developed for different classes of SMT (Eggers et al., 2008; Nuzzo et al., 2010) .\nMore recent work has applied recurrent and graph neural networks to Circuit SAT problems and unsat core detection (Amizadeh et al., 2019; Selsam et al., 2019; Selsam & Bjørner, 2019) .\nFastSMT uses embeddings from natural language processing like skip-gram and bag-of-words to represent formulas for search strategy optimization (Balunovic et al., 2018) .\nUnlike these approaches, we relax the SMT semantics directly to generate a differentiable representation of SMT.\nWe develop a novel neural architecture that explicitly and precisely learns SMT formulas by construction.\nWe achieve this by introducing a new sound and complete semantic mapping for SMT that enables learning formulas through backpropagation.\nWe use CLNs to implement a loop invariant inference system, CLN2INV, that is the first to solve all theoretically solvable problems in the Code2Inv benchmark and takes only 1.1 second on average.\nWe believe that the CLN architecture will also be beneficial for other domains that require learning SMT formulas.\nA CONTINUOUS PREDICATES Figure 5 shows examples of shifted sigmoids for S(>), S(≥), and S(=).\nCombing these results, we have\nFor any t-norm, we have 0 ⊗ 1 = 0, 1 ⊗ 1 = 1, and 1 ⊗ 0 = 0.\nPut it altogether, we have\n(f (t, u; B, ) ⊗ g(t, u; B, )) = 1 t = u 0 t = u which concludes the proof.",
"role": "user"
},
{
"content": "We introduce the Continuous Logic Network (CLN), a novel neural architecture for automatically learning loop invariants and general SMT formulas.",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_plos_single_doc_summ | science.scientific_lay_summarisation_plos_single_doc_summ.21264 | [
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Functional Assessment of Disease-Associated Regulatory Variants In Vivo Using a Versatile Dual Colour Transgenesis Strategy in Zebrafish\nArticle:\nAbstract:\nDisruption of gene regulation by sequence variation in non-coding regions of the genome is now recognised as a significant cause of human disease and disease susceptibility. Sequence variants in cis-regulatory elements( CREs), the primary determinants of spatio-temporal gene regulation, can alter transcription factor binding sites. While technological advances have led to easy identification of disease-associated CRE variants, robust methods for discerning functional CRE variants from background variation are lacking. Here we describe an efficient dual-colour reporter transgenesis approach in zebrafish, simultaneously allowing detailed in vivo comparison of spatio-temporal differences in regulatory activity between putative CRE variants and assessment of altered transcription factor binding potential of the variant. We validate the method on known disease-associated elements regulating SHH, PAX6 and IRF6 and subsequently characterise novel, ultra-long-range SOX9 enhancers implicated in the craniofacial abnormality Pierre Robin Sequence. The method provides a highly cost-effective, fast and robust approach for simultaneously unravelling in a single assay whether, where and when in embryonic development a disease-associated CRE-variant is affecting its regulatory function.\nIntroduction:\nCis-regulatory elements( CREs) such as enhancers are vital functional regions of the genome which determine where, when and at what levels their target genes will be expressed[1]. In keeping with their crucial role in the control of gene expression, CRE aberrations have been implicated as the cause of a variety of human diseases, genetic trait differences and predisposition to common diseases[2–3]. Modern approaches, such as next generation sequencing, now allow rapid determination of genetic variation between individuals to single nucleotide resolution. In contrast to the advancement offered by these high throughput methods for identification of sequence polymorphisms, progress towards an understanding of their precise role in disease etiology is hampered by a shortage of efficient methods for the functional characterization of observed variants. Identifying exactly which of the non-coding SNPs in a haplotype block have a regulatory function, and in what physiological context, has been complicated by some of the characteristic features of CREs: They can be located at very large distances( in some cases over a mega base) from their target genes; they can reside in gene deserts, or within the introns of- or even beyond- neighboring genes, making the prediction of their target genes difficult. Unlike coding mutations, the effect of non-coding sequence variation is difficult to predict. Moreover, CRE activities are often tissue- and stage-specific and highly dependent on the precise combination and stoichiometry of tissue-specific transcription factors[4]. The in vivo relevance, at the level of the whole organism, of approaches that utilize conventional assays in cell lines to test the effect of a disease-associated CRE variant is therefore highly questionable. The lack of efficient high-throughput and physiologically relevant assays for functional validation of tissue- and developmental-stage-specific CREs and identification of their target genes thus poses a real bottleneck in translating human non-coding variation into better understanding of disease mechanisms. In our search for an efficient approach for characterizing regulatory variation in a vertebrate model system, we developed a versatile, streamlined assay pipeline using zebrafish( Danio rerio). Zebrafish embryos are transparent and develop rapidly and outside the mother, making it feasible to visualize specific tagged cell types in the living animal. They are well suited for transgenic manipulation since it is relatively easy to collect and inject large numbers of fertilized eggs[5]. These features make transgenic zebrafish a useful model for the characterisation of putative tissue-specific CREs in particular over the time-course of vertebrate development but also in adult tissues[6]. The use of multiple fluorescent reporters enables direct comparison between different cis-elements or different variants of the same element in the same cells of the same animal. To determine the performance of the system, we tested a set of known disease-associated CREs in dual colour zebrafish reporter transgenics and demonstrate that the method is effective in revealing differences in functional output between variants in agreement with previously reported in mouse studies of these elements. We then applied the method to investigate a set of novel putative CREs with potential disease-associated variants in the genomic region of the SOX9 gene. These variant elements, located at very long distances from SOX9, in the large gene desert between SOX9 and KCNJ2, were identified based on their potential involvement in the congenital craniofacial malformation Pierre Robin Sequence( PRS)[7]. Consistent with their possible role in PRS aetiology, we show that these elements drive specific expression patterns in the craniofacial region of zebrafish and we reveal that the variant enhancer alleles found in the PRS patients have a variety of functional effects including: complete loss of activity; partial, tissue-specific loss of enhancer activity; and failure to maintain enhancer activity through development.\nDiscussion:\nThe importance of intact gene regulation for correct development and homeostasis has become increasingly recognised. As a result, research groups interested in understanding the aetiology and causative mechanisms of human disorders or disease susceptibility are now routinely looking for possible mutations or variations in CREs in patient cohorts, especially in cases where convincing causative mutations could not be found in the coding regions of genes. However, the lack of efficient and physiologically relevant assays to functionally validate the consequence of these sequence changes and to distinguish disease-linked changes from background sequence variation is hampering the translation of knowledge about human genetic variation into an understanding of disease mechanisms. CRE activity is highly dependent on the availability of the right combination and stoichiometry of specific transcription factors. Consequently, high-throughput assays for assessing the potential effects of disease-associated SNPs in cultured cells are largely uninformative as they often lack the relevant and necessary biological context for tissue or cell-type specific CRE function. In future, cell lines reflecting more closely the cell phenotypes of developing tissues may become available through emerging stem cell differentiation protocols[20]. A few high-throughput in vivo assays, such as hydrodynamic tail-vein injection and retina explant assays[21–23] have also recently been developed but their application is restricted to CREs functional only in liver or retina respectively. Therefore there is a pressing need for robust, widely applicable, relatively high-throughput, cost effective and animal-number efficient in vivo assays that enable the unambiguous comparison of putative mutant and wild-type alleles of CREs for spatial and temporal differences in activity. Such screens are vital for differentiating between common, background sequence variation and functionally active, disease-associated mutations in CREs, and will enable rapid prioritization of candidates for functional follow-up studies. The novel dual-colour zebrafish reporter transgenic assay pipeline that we have developed for investigating the functional consequences of disease- and disease-risk associated CRE mutations is designed to incorporate many of the above described merits, and thus will be a valuable tool for analysing effects of CRE mutations identified in patient cohorts and GWAS studies. While we cannot control for the number and position of transgene insertion sites in our assay, multiple independent transgenic lines bearing both the Wt and Mut version of the element driving distinct fluorescent reporters in the same animal can rapidly be constructed and tested, creating a clear consensus activity pattern and minimising the chance of bias in the analysis introduced by position effects due to site of integration of the transgenes. Other methods aimed towards targeted integration of transgenes in pre-defined docking sites in the zebrafish[24–27] or medaka[28] genomes are being developed, but the use of these techniques is more cumbersome and requires the maintenance of specialized fish stocks. Moreover, while targeted integration offers the advantage of avoiding bias from position effects, the use of dual-colour transgenesis is currently not established in these assays, complicating the possibility of simultaneous visualisation of CRE activity in the same animal, and precluding truly detailed assessment of differences in CRE activity. A comprehensive comparison of the merits and limitations of our assay with other available reporter transgenic assays for testing enhancer function is provided in S3 Table. We anticipate that it will become possible to combine advantages of the different methods in future assay designs. Characterisation of detailed expression patterns driven by particular elements allows selection of the most likely candidate sequences by virtue of their expression in the relevant anatomical structures. In combination with information on the expression patterns of the genes located within the relevant genomic region this can also help to find the likely target gene of an enhancer. This can otherwise be problematic as target genes of enhancers are often not simply the nearest one in the genome, but can be found hundreds or even thousands of kb away in either direction, beyond intervening non-target genes, and may reside within the introns of other non-target genes[29, 30]. Most importantly our method enables the characterisation of wild-type and mutant variants of the same enhancer in the same individual animal. This is an important benefit for assessment of more subtle spatio-temporal differences as it allows a direct comparison without the need for extrapolation between separate individuals. Disruption of cis-regulatory control of gene expression can occur via a number of distinct mechanisms[31]. These range from gross changes such as CRE deletion or translocations that separate the target gene from the influence of the CRE, to single nucleotide change in CREs that abrogate TF binding, or create novel binding sites. Although our method is suitable for a rapid screening of candidate regulatory sequences located in any small- to medium-sized region of interest that has been defined by deletion or translocation breakpoint mapping, the power of our analysis pipeline lies mostly in the characterisation of single nucleotide enhancer variants. We have therefore focussed on the latter mechanism, and our results indicate that it can be further subdivided based on the functional consequences of the basepair change. We observe at least four different types of effect on enhancer activity by patient mutant alleles. The first is the change in activity in the spatial dimension; this can manifest as complete loss of expression in a specific tissue( PAX6-SIMO, SOX9-hocCNEA), reduction in the extent of the expression domain( the SHH-SBE2 element), or an increase in expression domain( the SHH-ZRS). In the case of the SBE2 enhancer it had been shown that the reduction in expression domain size is caused by disruption of a SIX3 binding site in the element[9] and we replicated this effect by morpholino knock-down of Six3. This experiment demonstrates the modular nature of CREs: Six3 is not essential for all of the activity of SBE2 as expression in the caudal part of the hypothalamus remains, but Six3 is essential for the expression in the rostral hypothalamus. The second mechanism we identify is a partial loss of activity in the temporal dimension, as exemplified by the p300-pk17 element in patient PRS026 which loses expression in the oral cavity only at later developmental stage. This indicates that the element functions normally when it first becomes activated, but fails to maintain its activity subsequently. The third example is the complete loss of functional activity of the element in our assay. This suggests the mutation disrupts the binding of an essential factor potentially affecting the effective formation of a TF complex, or enhanceosome[32] at the enhancer. The fourth type of outcome is an apparent lack of change, whereby the tissue-specific activity of the enhancer in the appropriate tissue is unaffected by the sequence variant. The causal connection to the disease phenotype in such cases is not obvious. The mutation could affect the precise level of transcriptional output from the element, which is not readily measured in the current fluorescent reporter assay, or it could disrupt some other function of the element not assayed here, for instance in organisation of chromatin conformation of the locus[33]. Even though not guaranteed to work for all enhancers, our results show that the dual reporter transgenic zebrafish assay is a suitable model system to test enhancer activity of many human disease-associated elements even when the element is not obviously conserved in zebrafish itself. Evolution is characterised by variable loss and gain of cis-regulatory sequences[34]. Teleost fish in particular appear to have been subject to an enhanced rate of evolutionary divergence due to the additional whole genome duplication( 3R) that occurred at the base of the teleost lineage[35, 36], and consequently the zebrafish genome lacks many of the CNEs identifiable in other vertebrate species. However, it is likely that this increased divergence has occurred primarily at the level of the cis-regulatory sequences themselves, while the transcriptional machinery involved in the reading of the elements remains largely conserved due to selection against the wide-ranging effects of changes in the pleiotropic functions of transcription factors. Our results indicate that human regulatory elements implicated in disease can be tested in zebrafish with confidence. It is remarkable that single nucleotide changes at such large genomic distance from their target gene can have such profound phenotypic effects. Most of the currently known examples of distal cis-elements involved in genetic disease act as enhancers for genes sensitive to haplo-insufficiency[31]. Our demonstration that single basepair mutations in multiple long-range cis-elements, with subtly different expression patterns, can lead to PRS highlights the sensitivity of craniofacial development to correct expression levels of SOX9. The same is true for the other genes, SHH and IRF6, for which enhancers were tested in this report. Several of the enhancer variants described here are either inherited or even occur as rare SNPs in the wider population. Nevertheless we present strong evidence that these variants affect the function of the regulatory element in which they occur. Mutations in enhancers may not always lead to clear, fully penetrant phenotypes, but rather could contribute partly to a phenotype in specific individuals, depending on the presence of other modifier alleles. Incomplete penetrance may be observed for a number of reasons including variation in expressivity from the enhancer, or redundancy or buffering among multiple enhancers. The mufti-faceted assay we have described here allows for the functional characterisation of disease-associated enhancer variants at the highest throughput that can currently be achieved using an in vivo animal model system. We anticipate that our strategy will facilitate the analysis of non-coding variants in genome-wide association study( GWAS) hits, and can also be used in studying the mechanistic basis for enhancer activity, the engineering of enhancers with desired properties, or to drive highly spatio-temporally specific expression of genetic tools.",
"role": "user"
},
{
"content": "Cis-regulatory elements ( CREs ) play a vital role in gene regulation by providing spatial and temporal specificity to the expression of their target genes . Understanding how these regions of the genome work is of vital importance for human health as it has been demonstrated that genetic changes in these regions can result in incorrect gene expression , leading to a variety of human diseases . Functional characterization of putative CREs and the effects of mutations on their activity is currently a major bottleneck in many studies towards understanding the causes and mechanisms of disease and disease susceptibility . We describe a robust in-vivo approach using dual-colour reporter transgenesis in zebrafish for unambiguous assessment of the effects of disease-associated CRE mutations on CRE activity during the entire time-course of embryonic development . The highly efficient , cost-effective and modular design of the assay allows rapid analysis of several CRE-variants in parallel . We illustrate the robustness of our approach using examples of CRE-variants associated with a broad spectrum of genetic diseases including brain , limb , eye and jaw disorders . In a single assay the method can address where and when in development the CRE variant affects its activity , what potential target genes are misregulated by the change and what upstream trans-acting factors are likely to mediate this effect .",
"role": "assistant"
}
]
|
science.qasa_abstractive_qa | science.qasa_abstractive_qa.1169 | [
{
"content": "Read this passage from a research paper and answer the question.\n\nContext: SQuAD is a machine comprehension dataset on a large set of Wikipedia articles, with more than 100,000 questions. The answer to each question is always a span in the context.The model is given a credit if its answer matches one of the human written answers.Two metrics are used to evaluate models: Exact Match (EM) and a softer metric, F1 score, which measures the weighted average of the precision and recall rate at character level.The dataset consists of 90k/10k train/dev question-context tuples with a large hidden test set.It is one of the largest available MC datasets with human-written questions and serves as a great test bed for our model.\n\nQuestion: What are the metrics used to evaluate the model performance in question answering experiments?",
"role": "user"
},
{
"content": "Exact Match and F1 score",
"role": "assistant"
}
]
|
science.data_reco_mcq_mc | science.data_reco_mcq_mc.368 | [
{
"content": "Based on the dataset descriptions below, which datasets would be suitable for the following research question? Your response should be a JSON array.\n\nQuestion: Domain agnostic normalization unlocks the benefits of normalization layers for unsupervised adversarial domain adaptation\n\nKeywords: semantic scene segmentation video\n\nDataset descriptions:\nImageCLEF-DA: The ImageCLEF-DA dataset is a benchmark dataset for ImageCLEF 2014 domain adaptation challenge, which contains three domains: Caltech-256 (C), ImageNet ILSVRC 2012 (I) and Pascal VOC 2012 (P). For each domain, there are 12 categories and 50 images in each category.\nUSPS: USPS is a digit dataset automatically scanned from envelopes by the U.S. Postal Service containing a total of 9,298 16×16 pixel grayscale samples; the images are centered, normalized and show a broad range of font styles.\nGTA5: The GTA5 dataset contains 24966 synthetic images with pixel level semantic annotation. The images have been rendered using the open-world video game Grand Theft Auto 5 and are all from the car perspective in the streets of American-style virtual cities.\nVisDA-2017: VisDA-2017 is a simulation-to-real dataset for domain adaptation with over 280,000 images across 12 categories in the training, validation and testing domains. The training images are generated from the same object under different circumstances, while the validation images are collected from MSCOCO..\nCityscapes: Cityscapes is a large-scale database which focuses on semantic understanding of urban street scenes. It provides semantic, instance-wise, and dense pixel annotations for 30 classes grouped into 8 categories (flat surfaces, humans, vehicles, constructions, objects, nature, sky, and void).\nEMNIST: EMNIST (extended MNIST) has 4 times more data than MNIST. It is a set of handwritten digits with a 28 x 28 format.\n\nOptions: A: ImageCLEF-DA B: USPS C: GTA5 D: VisDA-2017 E: Cityscapes F: EMNIST",
"role": "user"
},
{
"content": "[\"GTA5\", \"Cityscapes\"]",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.10541 | [
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Heterozygoteswerenormalinallrespects,buthomozygoteswerepresentat~2/3theexpectedratiofromintercrossesbetweenheterozygotes(91Trip13+/+,183Trip13Gt/+,and61Trip13Gt/Gt).",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.45759 | [
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Human Activity Recognition Using Inertial Sensors in a Smartphone: An Overview \nChapter Title: 2. \n1. Abstract of Cited Paper (BIB001): This is a critical design paper offering a possible scenario of use intended to provoke reflection about values and politics of design in persuasive computing. We describe the design of a system - Fit4Life - that encourages individuals to address the larger goal of reducing obesity in society by promoting individual healthy behaviors. Using the Persuasive Systems Design Model [26], this paper outlines the Fit4Life persuasion context, the technology, its use of persuasive messages, and an experimental design to test the system's efficacy. We also contribute a novel discussion of the ethical and sociocultural considerations involved in our design, an issue that has remained largely unaddressed in the existing persuasive technologies literature [29]. \n2. Abstract of Cited Paper (BIB002): Mobile devices are becoming increasingly sophisticated and the latest generation of smart cell phones now incorporates many diverse and powerful sensors. These sensors include GPS sensors, vision sensors (i.e., cameras), audio sensors (i.e., microphones), light sensors, temperature sensors, direction sensors (i.e., magnetic compasses), and acceleration sensors (i.e., accelerometers). The availability of these sensors in mass-marketed communication devices creates exciting new opportunities for data mining and data mining applications. In this paper we describe and evaluate a system that uses phone-based accelerometers to perform activity recognition, a task which involves identifying the physical activity a user is performing. To implement our system we collected labeled accelerometer data from twenty-nine users as they performed daily activities such as walking, jogging, climbing stairs, sitting, and standing, and then aggregated this time series data into examples that summarize the user activity over 10- second intervals. We then used the resulting training data to induce a predictive model for activity recognition. This work is significant because the activity recognition model permits us to gain useful knowledge about the habits of millions of users passively---just by having them carry cell phones in their pockets. Our work has a wide range of applications, including automatic customization of the mobile device's behavior based upon a user's activity (e.g., sending calls directly to voicemail if a user is jogging) and generating a daily/weekly activity profile to determine if a user (perhaps an obese child) is performing a healthy amount of exercise. \n3. Abstract of Cited Paper (BIB003): This paper investigates two major issues in using a tri-axial accelerometer-embedded mobile phone for continuous activity monitoring, i.e. the difference in orientations and locations of the device. Two experiments with a total of ten test subjects performed six daily activities were conducted in this study: one with a device fixed on the waist in sixteen different orientations and another with three different device locations (i.e., shirt-pocket, trouser-pocket and waist) in two different device orientations. For handling with varying device orientations, a projection-based method for device coordinate system estimation has been proposed. Based on the dataset with sixteen different device orientations, the experimental results have illustrated that the proposed method is efficient for rectifying the acceleration signals into the same coordinate system, yielding significantly improved activity recognition accuracy. After signal transformation, the recognition results of signals acquired from different device locations are compared. The experimental results show that when the sensor is placed on different rigid body, different models are required for certain activities. \n4. Abstract of Cited Paper (BIB004): Automated methods of real-time, unobtrusive, human ambulation, activity, and wellness monitoring and data analysis using various algorithmic techniques have been subjects of intense research. The general aim is to devise effective means of addressing the demands of assisted living, rehabilitation, and clinical observation and assessment through sensor-based monitoring. The research studies have resulted in a large amount of literature. This paper presents a holistic articulation of the research studies and offers comprehensive insights along four main axes: distribution of existing studies; monitoring device framework and sensor types; data collection, processing and analysis; and applications, limitations and challenges. The aim is to present a systematic and most complete study of literature in the area in order to identify research gaps and prioritize future research directions. \n5. Abstract of Cited Paper (BIB005): Motion sensor embedded smartphones have provided a new platform for activity inference. These sensors, initially used for cell phone feature enhancement, are now being used for a variety of applications. Providing cell phone users information about their own physical activity in an understandable format can enable users to make more informed and healthier lifestyle choices. In this work, we built a smartphone application which tracks users' physical activities and provide feedback requiring no user input during routine operation. The application reports estimates of the calories burned, broken up by physical activities. Detectable physical activities include walking, running, climbing stairs, descending stairs, driving, cycling and being inactive. We evaluated a number of classification algorithms from the area of Machine Learning, including Naive Bayes, Decision Tree, K-Nearest Neighbor and Support Vector Machine classifiers. For training and verification of classifiers, we collected a dataset of 510 activity traces using cell phone sensors. We developed a smartphone app that performs activity recognition that does not require any user intervention. The classifier implemented in the Android app performs at an average true positives rate of greater than 95%, false positives rate of less than 1.5% and an ROC area of greater than 98%. \n6. Abstract of Cited Paper (BIB006): Physical activity recognition using embedded sensors has enabled many context-aware applications in different areas, such as healthcare. Initially, one or more dedicated wearable sensors were used for such applications. However, recently, many researchers started using mobile phones for this purpose, since these ubiquitous devices are equipped with various sensors, ranging from accelerometers to magnetic field sensors. In most of the current studies, sensor data collected for activity recognition are analyzed offline using machine learning tools. However, there is now a trend towards implementing activity recognition systems on these devices in an online manner, since modern mobile phones have become more powerful in terms of available resources, such as CPU, memory and battery. The research on offline activity recognition has been reviewed in several earlier studies in detail. However, work done on online activity recognition is still in its infancy and is yet to be reviewed. In this paper, we review the studies done so far that implement activity recognition systems on mobile phones and use only their on-board sensors. We discuss various aspects of these studies. Moreover, we discuss their limitations and present various recommendations for future research.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Semi-natural: Users perform their daily activities normally, but the user is required to perform the activities from the experiments at least once, that is, the user must ensure that all activities related to the study have been performed. 3. Laboratory: Users perform activities systematically in a controlled environment with previously defined steps. The literature shows that data collection performed in laboratories tends to generate more accurate classification models because the activities in this type of data collection are previously defined. However, the models generated with these kinds of datasets lose accuracy when applied in real contexts due to the diversity of users' behavior. On the other hand, models generated with natural datasets tend to be more generic and can be applied to groups of people with similar behaviors. Table 1 presents some works divided by the type of data collection. The frequency rate of data collection is also an important factor that should be considered during data collection since the frequency rate contains relevant information about the movement of the human body BIB007 . Theoretically, the frequency rate represents the amount of sample data collected every second (Hertz). In the literature, the frequencies used in the extraction of cellular sensor data vary from 1 Hz to 200 Hz for the inertial sensors. To find out the ideal frequency, Khusainov et al. BIB005 proved through experiments that the frequency of 20 Hz contains enough information about human physical movements. Table 2 shows a list of papers that have conducted studies on several frequency bands. The position of the smartphone on the user's body is another factor that greatly influences the quality of the data collected and the accuracy of the classification models. For example, data collected with the smartphone positioned at a user's waist produces different signal patterns from a smartphone placed in a user's hand BIB002 BIB003 . Table 3 shows a list of works separated by smartphone positions on the user's body. Backpack BIB001 BIB006 Generating generic models for the activities' recognition using smartphones located at different positions on the user's body is still a challenge to be overcome. Studies performed with the smartphone at different positions show that the waist is the best position to recognize physical activities since human body movements originate from this region BIB004 . Moreover, some works described in BIB007 have employed solutions that are independent from the position of the smartphone on the human body. In brief, these solutions have focused on data extraction with the smartphone located in all relevant positions on the user's body. The orientation of the smartphone (e.g., portrait and landscape) is also another factor that influences the accuracy of the classification models. What makes the classification models dependent or independent of orientation are the types of features used in the training phase. For example, the features signal magnitude is considered an independent orientation feature, since their values do not change with device orientation changes. Table 4 presents a list of works that observed the orientation of smartphones to generate classification models and Section 5.4 presents details about these features. Finally, the diversity of the data allows for greater generalization of classification models. The literature review shows that the number of individuals did not exceed 49, as shown in the datasets presented in Section 8. This occurs because of the difficulty in persuading users to provide their personal information. To diversify the scenarios, it is necessary to obtain data from people of different ages and groups, and with different levels of health and locomotion, among other factors. Personal or specific: Models are trained with data from only one user and tested with the same user. 3. Mixed: models are trained using the entire database without distinction between users. In addition, classification models can be generated based on three strategies: 1. Cross-validation: the database is randomly divided into 10 equal parts, where the models are generated with 9 parts and tested with the remaining part. This is repeated until all parts are individually used as training. The final accuracy consists of the average of the 10 classification models generated in 10 training rounds. Leave-one-subject-out: This strategy is similar to cross-validation, but instead of being randomly divided into equal parts, the data is divided by the user. The data of each user is used as a test. 3. Leave-30%-out: This strategy consists of dividing the data into 70% for training and 30% for testing. In general, previous studies have sought to develop impersonal models with high accuracy rates; however, generating recognizers of human activities that consider factors such as age and health of the user is still a challenge. One solution to this problem would be to generate classification models for each user profile, such as children, adults, people with locomotion difficulties, among others. The shallow machine learning algorithms commonly used to recognize users' physical activities are represented by Naïve Bayes, Support Vector Machine (SVM), neural networks, KNN, and the decision tree family algorithms, for example. These algorithms use the time and frequency domains feature in the training process of the classification models. Table 9 presents a list of papers that use these methods. This article does not attempt to provide theoretical information about how each of these algorithms work, more details about each of them can be found in . Table 9 . List of works separated by shallow machine learning algorithms.",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_plos_single_doc_summ | science.scientific_lay_summarisation_plos_single_doc_summ.6309 | [
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Systemic Bud Induction and Retinoic Acid Signaling Underlie Whole Body Regeneration in the Urochordate Botrylloides leachi\nArticle:\nAbstract:\nRegeneration in adult chordates is confined to a few model cases and terminates in restoration of restricted tissues and organs. Here, we study the unique phenomenon of whole body regeneration( WBR) in the colonial urochordate Botrylloides leachi in which an entire adult zooid is restored from a miniscule blood vessel fragment. In contrast to all other documented cases, regeneration is induced systemically in blood vessels. Multiple buds appear simultaneously in newly established regeneration niches within vasculature fragments, stemming from composites of pluripotent blood cells and terminating in one functional zooid. We found that retinoic acid( RA) regulates diverse developmental aspects in WBR. The homologue of the RA receptor and a retinaldehyde dehydrogenase-related gene were expressed specifically in blood cells within regeneration niches and throughout bud development. The addition of RA inhibitors as well as RNA interference knockdown experiments resulted in WBR arrest and bud malformations. The administration of all-trans RA to blood vessel fragments resulted in doubly accelerated regeneration and multibud formation, leading to restored colonies with multiple zooids. The Botrylloides system differs from known regeneration model systems by several fundamental criteria, including epimorphosis without the formation of blastema and the induction of a “multifocal regeneration niche” system. This is also to our knowledge the first documented case of WBR from circulating blood cells that restores not only the soma, but also the germ line. This unique Botrylloides WBR process could serve as a new in vivo model system for regeneration, suggesting that RA signaling may have had ancestral roles in body restoration events.\nIntroduction:\nSome of the most fundamental issues in developmental biology concern the ability of metazoans to regenerate. In most multicellular organisms, adult stem cells maintain organs' homeostasis throughout life and facilitate tissue repair after injury or disease[1]. Several organisms are capable of regrowing amputated organs and body parts, for example, amphibian limbs, lens, and retina[2–4]. Phylogenetic perspectives reveal a decrease in regenerative abilities concomitant with an increase in animal body complexity[5]. Thus, only a few adult animals manifest massive regeneration events, and these events occur mostly in less complex multicellular organisms such as sponges[6], cnidarians[7], and flat worms[8]. An exception is the phenomenon of whole body regeneration( WBR) in the highly evolved urochordates subfamily, Botryllinae. In this group of sedentary colonial organisms, which are the closest living relatives of vertebrates[9], a fully functional adult can regenerate within 10–14 d from any isolated minute fragment( 0. 1 mm) of a blood vessel containing a limited number( n = 100–300) of blood cells[10, 11]. The filter-feeding Atlantic urochordate B. leachi( Figure 1A) is a common encrusting colonial sea squirt, probably a Mediterranean species that has spread ubiquitously[12]. Animals are found in very shallow waters, under stones, on algae, pilings, floats, and other substrata. Each colony is composed of several to thousands of genetically identical modules( zooids)( Figure 1A, arrowheads), each 2–3 mm long, embedded within a gelatinous matrix called the tunic. Zooids are arranged in systems of two parallel elongated and often serpentine rows. A network of blood vessels connects all zooids within a colony, from which pear-shaped vascular termini( ampullae) extend toward the colony margins( Figure 1A, arrows). Once the planktonic larva metamorphoses into the founder individual( called the oozooid), a colony of zooids develops by a weekly budding process. This process is comprised of four successive phases( A–D)[13], during which new zooids bud from the thoracic body wall of the oozooid and the subsequent zooids, a phenomenon called palleal budding[14] or blastogenesis[15–17]. Each blastogenic cycle ends in a massive apoptotic event( Phase IV—the takeover phase) in which parental zooids are resorbed concurrently with the maturation of buds into adult, functional zooids. A unique WBR event, in which buds develop at the bases of vascular ampullae, was observed in congener botryllid species under adverse environmental conditions[18, 19], a regeneration phenomenon that had also been induced experimentally[10, 11], providing a unique model system for WBR. Retinoic acid( RA) is a low molecular weight biologically active metabolite of Vitamin A, which plays diverse functional roles in a wide variety of tissues and organs[20–22]. It plays a conserved role in controlling positional information and cellular differentiation during embryonic development. RA action is mediated at the metabolism and signaling levels. RA-synthesizing enzymes, such as retinaldehyde dehydrogenase( Raldh), together with degrading enzymes( Cyp26) create the spatiotemporal distribution of RA during development and refine it[23]. Signaling is mediated through RA binding to two nuclear receptors, retinoic acid receptor( RAR) and retinoic X receptor, through which it acts as a ligand-dependent transcription factor[24, 25], subsequently inducing gene transcription. RA has also been recorded as being involved in restricted regeneration of tissues and organs in adult vertebrates[26]. In urodele amphibians, administering RA into amputated limbs resulted in regeneration of extra limb tissue[27–29]. In adult rat lung, RA induces alveolar regeneration, and systemic RA treatment can reverse pathological features of experimental emphysema[30]. In adult rat spinal cord, RAR isoform RARβ2 is able to promote functional regeneration of sensory axons[31]. Despite the identification of RA receptors exclusively in chordates, and the consideration of RA signaling as a chordate innovation[32], remarkably little evidence exists connecting the activation of RA signaling to conserved chordate biological traits of regeneration. A single RA receptor[33] in lower chordates( such as urochordates and cephalochordates) offers an advantage when searching for direct RA-signaling functions. This is not the case in vertebrates where, due to redundancy in RAR genes, RAR localization fails to provide sufficient information on RA-signaling functions. Here, we endeavor to elucidate cellular processes and RA signaling during WBR in the urochordate B. leachi in order to reveal traits and evolutionary routes of regeneration similar to those recorded in its vertebrate counterparts[33].\nDiscussion:\nWhereas most animals share the ability to repair damaged tissue, the phenomenon of massive body restoration is a rare event in highly complex animals[5]. Here, we studied the unique whole body regeneration phenomenon in a colonial urochordate, revealing the capability of rebuilding the entire zooid body from minute vasculature fragments. We defined three consecutive developmental phases, shedding light on a unique regeneration process that differs from known regeneration model systems in several fundamental criteria( Table 3). In other epimorphic regenerations, restoration starts with the formation of a transient structure termed blastema[38]. However, in the Botrylloides WBR, instead of blastema, regeneration niches are structured de novo inside vasculature. Furthermore, while a single restoration center is induced in all other model systems studied[5], a “multifocal regeneration niche” system is generated in the Botrylloides WBR. A possible explanation for this regeneration strategy in Botrylloides is the presence of a systemic inductive regeneration cue. Regeneration in Animalia is regularly induced by inductive signals[39, 40]. In model systems, such as regeneration of limb in salamander or fin in zebrafish[41, 42] it is regulated by locally induced signals. We suggest that in B. leachi, WBR, in contrast to other cases, signals might be propelled throughout circulation( cellular and humoral elements), leading to many regeneration foci in any single regeneration entity. The Botrylloides system is also the first documented case, to our knowledge, of WBR originating from circulating blood cells( Table 3) and reveals the capability of restoring not only the soma, but also the germ line[10, 11]. As previously reported[10, 11, 19], Botrylloides WBR initiates through aggregates of haemocytes within newly formed vasculature niches; each housing up to 100 small round cells. Any haphazardly isolated peripheral ampulla( out of hundreds of ampullae fringing in a single colony), containing only 100–300 circulating cells[10, 11], is capable of successful WBR. What is the cellular source of the regenerating bud? Their small cell size, cellular morphology, and strong ubiquitous hematoxylin staining suggest primitive stem cell origin[19]; however, direct proof should be addressed in further controlled studies. In Botrylloides WBR, as in embryonic development[43], the transformation of the initial state of aggregated cells into complete animal structures reveals a fundamental attribute of animal development. Both processes have very different starting points( a fertilized egg versus pluripotent blood cells); yet both converge at a common endpoint of adult morphology through the establishment of body axes, self-assembly, and differentiation of tissues and organs[44, 45]. We can draw close morphological similarities between the initial developmental stages in Botrylloides WBR( cell aggregates, development of blastula-like structures, and invaginations of epithelial layers) and fundamental embryonic developmental stages( morula, blastula, and gastrula). A similar resemblance transpires when comparing Hydra WBR from dissociated cells[46] to embryonic development, implying a basic evolutionary root underlying whole body restoration events[47, 48]. The conserved signaling pathways governing the development of tissues and organs are one of the major objects in developmental biology. Redeployment of these embryonic signaling pathways at different biological contexts enables quicker responses by multicellular organisms to adverse environmental conditions, such as RA signaling in the regeneration of specific tissues and organs in various vertebrate model systems[26, 49, 50]. A functional example of redeployment of a developmental mechanism comes from the mammalian central nervous system. Embryonic central nervous system undergoes regeneration through RARβ2-stimulated RA signaling, unlike adult central nervous system, which does not express RARβ2. Redeployment of RA signaling through overexpression of RARβ2 indeed promotes functional regeneration of adult central nervous system[31]. It had already been shown that RAR is expressed in mesenchymal cells of developing buds in the colonial tunicate P. misakiensis, where it regulates developmental aspects in normal budding processes, including the induction of a secondary axis in developing buds[51–53]. Following the evaluation of the biological redeployment strategy, this study reveals, for the first time to our knowledge, the important roles of RA in botryllid ascidian WBR. We show that RAR is expressed during WBR, specifically in haemocytes within the vasculature. In contrast to tissue- and organ-specific expression patterns of RA receptors in vertebrates, RAR expression in botryllid regeneration does not follow developmental processes expressed in normal blastogenesis of tissue and organ structuring, but is expressed ubiquitously throughout the entire body. This observation suggests that in addition to its role in early stages of regeneration, RAR expression also represents other RA activities, such as maintenance or other yet unknown proceedings. We further show that the entire body of developing zooids is susceptible to RA signaling. The use of both DEAB, Citral, BMS-493, and RNAi-mediated knockdown of Bl-RAR to disrupt RA synthesis and RA receptor function, collectively result in WBR arrest and bud malformation. The administration of all-trans RA into fragments of blood vessels results in accelerated regeneration and the unusual development of multibuds, leading to restored colonies with multiple functional zooids. This observation could indicate that in regular Botrylloides WBR, the systemic developmental inhibition of all buds but one, could be achieved by controlling the levels of RA transcriptional cascade. We found, during early stages of WBR, that highly Aldedh-positive macrophages form foci of expression that correspond to foci of multiple initiations of regeneration, strengthening the notion that RA is required for the early stages of this process[54, 55]. Regeneration as a central discipline in biology holds great promise not only for the understanding of species-specific developmental issues, but also for deduction of its evolutionary roots and for medical applications[56]. In the past few years, ascidians have become model organisms for the study of a wide variety of biological phenomena, including developmental processes, embryogenesis, stem cell biology, and immunology[57–60]. This group of organisms demonstrates basic mechanisms of biological phenomena, similar to those observed in vertebrates. In light of the unique regenerative power of botryllid ascidians, WBR in B. leachi may serve as a model system for studying the evolutionary roots of organ regeneration, lost in most vertebrate taxa.",
"role": "user"
},
{
"content": "Whole body regeneration ( WBR ) in Animalia is rare , confined to morphologically less complex taxa such as sponges , cnidarians , and flatworms . In the chordate phylum , only colonial ascidians ( invertebrate chordates also known as sea squirts ) have the documented ability to wholly regenerate . Once separated from the colony , any minute fragment of peripheral blood vessel ( about 1 mm in length , containing 100–300 blood cells ) of the colonial ascidian Botrylloides leachi regenerates an entire functional adult within one to three weeks . By following cellular and molecular events in Botrylloides WBR , we revealed that this system proceeds differently from regeneration events in other model organisms by several fundamental criteria . This is , for example , to our knowledge the first documented case of WBR initiating from circulating blood cells that restore not only the body tissue , but also the germ line . We found that retinoic acid ( RA ) signaling , previously reported in the regeneration of specific vertebrate tissues and organs , plays a major role in WBR via RA receptor expression throughout the entire regenerating animal . This suggests that RA signaling may have had ancestral roles in body restoration events . Elucidating the processes involved in this WBR system will improve our understanding of the nature of regeneration and the reduced regeneration capabilities represented in so many vertebrates .",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.54637 | [
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: LSM-based Storage Techniques: A Survey \nChapter Title: \n1. Abstract of Cited Paper (BIB001): AsterixDB is a new, full-function BDMS (Big Data Management System) with a feature set that distinguishes it from other platforms in today's open source Big Data ecosystem. Its features make it well-suited to applications like web data warehousing, social data storage and analysis, and other use cases related to Big Data. AsterixDB has a flexible NoSQL style data model; a query language that supports a wide range of queries; a scalable runtime; partitioned, LSM-based data storage and indexing (including B+-tree, R-tree, and text indexes); support for external as well as natively stored data; a rich set of built-in types; support for fuzzy, spatial, and temporal types and queries; a built-in notion of data feeds for ingestion of data; and transaction support akin to that of a NoSQL store. ::: ::: Development of AsterixDB began in 2009 and led to a mid-2013 initial open source release. This paper is the first complete description of the resulting open source AsterixDB system. Covered herein are the system's data model, its query language, and its software architecture. Also included are a summary of the current status of the project and a first glimpse into how AsterixDB performs when compared to alternative technologies, including a parallel relational DBMS, a popular NoSQL store, and a popular Hadoop-based SQL data analytics platform, for things that both technologies can do. Also included is a brief description of some initial trials that the system has undergone and the lessons learned (and plans laid) based on those early \"customer\" engagements. \n2. Abstract of Cited Paper (BIB002): Realtime data processing powers many use cases at Facebook, including realtime reporting of the aggregated, anonymized voice of Facebook users, analytics for mobile applications, and insights for Facebook page administrators. Many companies have developed their own systems; we have a realtime data processing ecosystem at Facebook that handles hundreds of Gigabytes per second across hundreds of data pipelines. Many decisions must be made while designing a realtime stream processing system. In this paper, we identify five important design decisions that affect their ease of use, performance, fault tolerance, scalability, and correctness. We compare the alternative choices for each decision and contrast what we built at Facebook to other published systems. Our main decision was targeting seconds of latency, not milliseconds. Seconds is fast enough for all of the use cases we support and it allows us to use a persistent message bus for data transport. This data transport mechanism then paved the way for fault tolerance, scalability, and multiple options for correctness in our stream processing systems Puma, Swift, and Stylus. We then illustrate how our decisions and systems satisfy our requirements for multiple use cases at Facebook. Finally, we reflect on the lessons we learned as we built and operated these systems.\n\nLiterature Review:",
"role": "user"
},
{
"content": "and simplification of concurrency control and recovery. For example, its high space utilization, due to the fact that ondisk data can be stored fully compacted, was the main motivation for Facebook to widely adopt LSM-based storage . LSM-based storage engines have greatly improved SSD utilization, thus lowering the storage cost, compared to traditional B-tree-based storage engines where leaf pages are typically just 2/3 full on average BIB001 . A key advantage of the LSM-tree is that it is a highly tunable structure. Its inherent merge operations continuously reorganize data to improve storage and query efficiency, with theoretical bounds on write performance, query performance, and space utilization. This versatility enables the LSM-tree to serve a large variety of workloads. As reported by Facebook , RocksDB, an LSM-based key-value store engine, has been used for real-time data processing BIB003 , graph processing [2], stream processing BIB003 , and OLTP workloads [5] . Due to the popularity of LSM-trees among today's data stores, a large number of proposed LSM improvements have come from the research community; these have come from both the database and operating systems communities. In this paper, we survey these recent LSM improvements, ranging from key-value store settings with a single LSM-tree to more general database settings with secondary indexes. This paper aims to serve as a guide to the state of the art in LSM-based storage techniques for researchers, practitioners, and users. We first provide a general taxonomy to classify the existing LSM improvements based on the specific aspects that they attempt to optimize. We then present the various improvements in detail and discuss their strengths and trade-offs. To reflect how LSM-trees are being used in real systems, we further survey five representative LSMbased NoSQL open-source systems, including LevelDB [4] , RocksDB [6] , HBase [3] , Cassandra , and AsterixDB BIB002 . Finally, we also identify several interesting future research directions through categorizing and reviewing the existing LSM improvements, The reminder of this paper is organized as follows. Section 2 briefly reviews the history of LSM-trees and presents the basics of today's LSM-tree implementations. Section 3 presents a taxonomy of the proposed LSM improvements and surveys the existing work using that framework. Section 4 surveys some representative LSM-based NoSQL systems, focusing on their storage layers. Section 5 reflects on the results of this survey, identifying several outages and opportunities for future work on LSM-based storage systems. Finally, Section 6 concludes the paper.",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_elife_single_doc_summ | science.scientific_lay_summarisation_elife_single_doc_summ.3460 | [
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Viruses are a dominant driver of protein adaptation in mammals\nArticle:\nAbstract:\nViruses interact with hundreds to thousands of proteins in mammals, yet adaptation against viruses has only been studied in a few proteins specialized in antiviral defense. Whether adaptation to viruses typically involves only specialized antiviral proteins or affects a broad array of virus-interacting proteins is unknown. Here, we analyze adaptation in ~1300 virus-interacting proteins manually curated from a set of 9900 proteins conserved in all sequenced mammalian genomes. We show that viruses( i) use the more evolutionarily constrained proteins within the cellular functions they interact with and that( ii) despite this high constraint, virus-interacting proteins account for a high proportion of all protein adaptation in humans and other mammals. Adaptation is elevated in virus-interacting proteins across all functional categories, including both immune and non-immune functions. We conservatively estimate that viruses have driven close to 30% of all adaptive amino acid changes in the part of the human proteome conserved within mammals. Our results suggest that viruses are one of the most dominant drivers of evolutionary change across mammalian and human proteomes.\nIntroduction:\nA number of proteins with a specialized role in antiviral defense have been shown to have exceptionally high rates of adaptation( Cagliani et al., 2011; Cagliani et al., 2012; Elde et al., 2009; Fumagalli et al., 2010; Kerns et al., 2008; Liu et al., 2005; Sawyer et al., 2004; Sawyer et al., 2005; Sawyer et al., 2007; Sironi et al., 2012; Vasseur et al., 2011). One example is protein kinase R( PKR), which recognizes viral double-stranded RNA upon infection, halts translation, and as a result blocks viral replication( Elde et al., 2009). PKR is one of the fastest adaptively evolving proteins in mammals. Specific amino acid changes in PKR have been shown to be associated with an arms race against viral decoys for the control of translation( Elde et al., 2009). However, PKR and other fast-evolving antiviral defense proteins may not be representative of the hundreds or even thousands of other proteins that interact physically with viruses( virus-interacting proteins or VIPs in the rest of this manuscript). Most VIPs are not specialized in antiviral defense and do not have known roles in immunity. Many of these VIPs play instead key functions in basic cellular processes, some of which might be essential for viral replication. In principle some VIPs without specific antiretroviral functions might nonetheless evolve to limit viral replication or alleviate deleterious effects of viruses despite the need to balance this evolutionary response with the maintenance of the key cellular functions they play. There are reasons to believe that such an evolutionary response to viruses might be limited, however. First, most VIPs evolve unusually slowly rather than unusually fast both in animals( Davis et al., 2015; Jäger et al., 2011) and in plants( Mukhtar et al., 2011; Weßling et al., 2014). Second, VIPs tend to interact with proteins that are functionally important hubs in the protein-protein interaction network of the host possibly limiting their ability to adapt( Dyer et al., 2008; Halehalli and Nagarajaram, 2015). Finally, very few cases of adaptation to viruses are known outside of fast evolving, specialized antiviral proteins( Demogines et al., 2012; Meyerson et al., 2014; Meyerson and Sawyer, 2011; Meyerson et al., 2015; Ng et al., 2015; Ortiz et al., 2009; Schaller et al., 2011). Transferrin receptor or TFRC is the most notable exception, and serves as a striking example of a non-immune, housekeeping protein used by viruses( Demogines et al., 2013; Kaelber et al., 2012). TFRC is responsible for iron uptake in many different cell types and is used as a cell surface receptor by diverse viruses in rodents and carnivores. TFRC has repeatedly evaded binding by viruses through recurrent adaptive amino acid changes. As such, TFRC is the only clear-cut example of a host protein not involved in antiviral response that is known to adapt in response to viruses. Here we analyze patterns of evolutionary constraint and adaptation in a high quality set of ~1300 VIPs that we manually curated from virology literature. These 1300 VIPs come from a set of ~10000 proteins conserved across 24 well-sequenced mammalian genomes( Materials and methods). As expected, the vast majority of these VIPs( ~80%) have no known antiviral or any other more broadly defined immune activity. We confirm that VIPs do tend to evolve slowly and demonstrate that this is because VIPs experience much stronger evolutionary constraint than other proteins within the same functional categories. However, despite this greater evolutionary constraint, VIPs display higher rates of adaptation compared to other proteins. This excess of adaptation is visible in VIPs across biological functions, on multiple time scales, in multiple taxa, and across multiple studied viruses. Finally, we showcase the power of our global scan for adaptation in VIPs by studying the case of aminopeptidase N, a well-known multifunctional enzyme( Mina-Osorio, 2008) used by coronaviruses as a receptor( Delmas et al., 1992; Yeager et al., 1992). Using our approach we reach an amino-acid level understanding of parallel adaptive evolution in aminopeptidase N in response to coronaviruses in a wide range of mammals.\nDiscussion:\nHere, we have shown that viruses have been a major selective pressure in the evolution of the mammalian proteome. Indeed viruses appear to drive ~30% of all adaptive amino acid changes in the conserved part of the human proteome, as evidenced by the MK test. Furthermore, the footprints of the arms race with viruses are visible in a large number of VIPs, and in a broad range of mammals. Importantly, we find a substantial enrichment in strong signals of adaptation in VIPs with no known antiviral or other immune functions( Figures 4B and 5A). Instead adaptation to viruses is visible in VIPs with a very diverse range of functions including such core functions as transcription or signal transduction( Figures 4B, 5C and Supplementary file 1C). This very diverse range of functions strongly argues in favor of a pervasive, external selective pressure –in our case viruses– as the cause for the observed signals. Our results thus draw a broader picture where adaptation against viruses involves not only the specialized antiviral response, but also the entire population of host proteins that come into contact with viruses. The best-known case of a housekeeping protein having adapted in response to viruses, the transferrin receptor, may thus represent the rule more than an exception( Demogines et al., 2013). In line with this, a new non-antiviral protein, NPC1, has very recently been shown to adapt against its use as a receptor by filoviruses in bats( Ng et al., 2015). Although we find a strong signal of increased adaptation, the amount of adaptive evolution that can be attributed to viruses is probably underestimated by our analysis. First, there likely to be many undiscovered VIPs. There is no sign that the pace of discovery of new VIPs is slowing down( Figure 2). This means that a substantial number of proteins classified as non-VIPs in this analysis are in fact VIPs, making non-VIPs a conservative control. Second, adaptation in response to viruses is most likely not restricted to proteins that physically interact with viruses. For example, adaptation to viruses might happen in proteins that act downstream of VIPs in signaling cascades, or in non-coding sequences that regulate the expression of VIPs. Third, not all of the 1256 VIPs we use here have been consistently interacting with viruses during evolution. Most VIPs in the dataset( 95%) were discovered in humans, and how frequently these VIPs have also been interacting with viruses in other mammals is currently unknown. Some VIPs like PKR have probably been in very frequent contact with diverse viruses. Conversely, other VIPs may have been in contact with viruses for a very limited evolutionary time in mammals, and only in a limited range of lineages. This would apply to VIPs that interact with viruses with a limited host range and few other phylogenetically closely related viruses, as is the case with HCV( Figure 5B). In addition, we could only work with VIPs active in current human populations reflecting the set of viruses infecting humans at present. This means that a potentially large number of proteins classified as non-VIPs in our study were actually VIPs during past human evolution or during the evolution of other mammalian lineages. Altogether, the bias of our sample towards present human VIPs thus makes our results conservative. We speculate that our results might explain a puzzling observation that rates of protein adaptation appear relatively invariant across different biological functions assessed using GO analysis( Bierne and Eyre-Walker, 2004). Because viruses( and likely other pathogens) interact with diverse proteins across most GO functions, they elevate the rate of adaptation across the whole proteome in a way that appears independent of specific functions in the GO analysis. We argue that grouping genes together based on the way they interact with diverse pathogens or other environmental stimuli might be a profitable way for discerning the nature of selective pressures that have molded animal genomes. In conclusion, our analysis suggests that viruses have exerted a very powerful selective pressure across the breadth of the mammalian proteome, and suggests the possibility that pathogens in general are the key driver of protein adaptation in mammals and likely other lineages and might have driven many pleiotropic effects on diverse biological functions.",
"role": "user"
},
{
"content": "When an environmental change occurs , species are able to adapt in response due to mutations in their DNA . Although these mutations occur randomly , by chance some of them make the organism better suited to their new environment . These are known as adaptive mutations . In the past ten years , evolutionary biologists have discovered a large number of adaptive mutations in a wide variety of locations in the genome – the complete set of DNA – of humans and other mammals . The fact that adaptive mutations are so pervasive is puzzling . What kind of environmental pressure could possibly drive so much adaptation in so many parts of the genome ? Viruses are ideal suspects since they are always present , ever-changing and interact with many different locations of the genome . However , only a few mammalian genes had been studied to see whether they adapt to the presence of viruses . By studying thousands of proteins whose genetic sequence is conserved in all mammalian species , Enard et al . now suggest that viruses explain a substantial part of the total adaptation observed in the genomes of humans and other mammals . For instance , as much as one third of the adaptive mutations that affect human proteins seem to have occurred in response to viruses . So far , Enard et al . have only studied old adaptations that occurred millions of years ago in humans and other mammals . Further studies will investigate how much of the recent adaptation in the human genome can also be explained by the arms race against viruses .",
"role": "assistant"
}
]
|
science.chemsum_single_document_summarization | science.chemsum_single_document_summarization.113891 | [
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nDrFLINC Contextualizes Super-resolution Activity Imaging\n\nPaper sections:\n\n<p>Super-resolution fluorescence imaging has become a powerful mode for investigating the cellular organization of molecular machineries1–2. We previously discovered a phenomenon called Fluorescence fLuctuation INcrease by Contact (FLINC)3, where the reversibly switchable fluorescent protein (RSFP) Dronpa4 can specifically and quantitatively enhance the fluorescence fluctuations of TagRFP-T5 when the two proteins are in molecular proximity. By coupling such a FLINC pair with kinase activity-dependent molecular switches from our FRET-based kinase activity reporters (KARs), we developed FLINC-based kinase activity reporters that achieved super-resolution activity imaging. As FLINC-AKAR revealed protein kinase A (PKA) activity microdomains on the plasma membrane and laid a foundation for mapping biochemical activity architecture in living cells6–7, the need quickly emerged to identify at a comparable resolution the regulatory or effector components that influenced or inherited the spatial organization of PKA signaling architecture.</p><p>Photochromic stochastic optical fluctuation imaging (pcSOFI)8 is an imaging modality that achieves sub-diffraction-limit resolution using correlated fluctuations3, 9. Its advantages include technical simplicity, compatibility with living cells, and a temporal resolution suited to signaling dissection. Theoretically, using pcSOFI in distinct colors to highlight both protein location and biochemistry with sub-diffraction resolution, we can reveal the context surrounding the activity of interest8. Yet despite recent development of new variants10–12, the number of spectrally distinct genetically encoded fluorescent labels exhibiting robust fluctuations remain limited. A suitable dual-color scheme that achieves synchronized live-cell imaging of both dynamic biochemical activities with associated regulators and effectors at super-resolution remains out of reach.</p><p>We reason that a new generation of FLINC probe can address both challenges. We previously showed that FLINC is mediated by external residues on Dronpa, not by internal residues or the Dronpa chromophore itself3. Thus, we surmised that FLINC can be maintained while removing Dronpa fluorescence (Figure 1A). We identified several residues important for Dronpa fluorescence13: Cys62-Tyr63-Gly64 (CYG) autocatalytically form the chromophore; His193 forms π-π stacking with the p-hydroxyphenyl ring of the ON-state; Ser142 is stabilized by a hydrogen bond to the hydroxyl group of the p-hydroxyphenyl ring in the ON-state. Thus, we hypothesized that introducing three types of mutations: a) CYG to GGG to abolish the chromophore, b) S142D for large steric/charge perturbation, or c) H193T to remove π-π stacking stabilization, will disable Dronpa fluorescence but not affect FLINC. To test this idea, we fused TagRFP-T with wildtype or mutant Dronpa through an 8-amino-acid linker, termed DpTT, DpH193TTT, DpGGGTT and DpS142DTT, and characterized the resulting plasma membrane-targeted14 tandem constructs using pcSOFI. Compared to DpTT, all three mutant pairs show robust, pcSOFI-compatible single-molecule fluctuations with 561-nm excitation, with minimal green fluorescence under 488-nm excitation (Figure 1B and Figure S1). We chose DpH193TTT, hereafter designated μDpTT, as the Dronpa-chromophore-removed FLINC (DrFLINC) pair for all subsequent experiments (Figure S1C). Single-pixel fluctuation profiling showed that both DpTT and μDpTT exhibit higher dynamic-range fluctuations than TagRFP-T alone (Figure 1C). Illumination at 561 nm generated red fluorescence fluctuations in a laser-power-dependent manner (Figure S2), and μDpTT outperformed TagRFP-T over a range of laser powers, especially in the low-intensity range. As shown in Figure 1D, quantification of fluctuations by normalized pcSOFI values indicated enhanced performance by DpTT and μDpTT compared with TagRFP-T (Figure 1D). These results indicate that the proximity of mutant Dronpa without a functional fluorophore still significantly increases the fluorescence fluctuations of TagRFP-T and permits high-contrast imaging using pcSOFI.</p><p>Since μDpTT can generate robust single molecule fluctuations in living cells, we next tested its utility as a reversibly photoswitchable red-fluorescent label for super-resolution imaging and co-imaging. We chose to focus on imaging PKA RIIα, a regulatory subunit of PKA that is expressed in most tissues and is anchored by various A-kinase anchor proteins (AKAPs) to different intracellular compartments15. Comparing μDpTT to Dronpa and rsTagRFP10, the most commonly used RSFPs in pcSOFI, we found that RIIα-Dronpa and RIIα-μDpTT generated sub-diffraction images that clearly illustrated the plasma membrane localization of RIIα, while RIIα-rsTagRFP yielded blurry, low-contrast images (Figure S3A/B), partly due to the low switching contrast and the poor photostability of rsTagRFP (Figure S3C). We next tested fusion of μDpTT for targeting to different subcellular compartments using TIRF, HILO16 or epifluorescence microscopy (Figure 2A and Figure S4). 2nd and 3rd order pcSOFI analyses showed that μDpTT could generate super-resolution images of filamentous actin, microtubules, nucleus, endoplasmic reticulum (ER), and mitochondria when fused to Lifeact, tau, Histone 2B (H2B), and CYP450- and DAKAP1-derived targeting motifs, respectively. We could also observe the plasma membrane localization of β−2 adrenergic receptor (B2AR) at super-resolution. Fourier ring correlation (FRC) estimation of the mean resolution revealed 127 nm, 124 nm and 132 nm for the 2nd order pcSOFI calculated by ImageJ or Localizer with or without deconvolution (Figure S5), which are consistent with previous report8. Furthermore, we examined the influence of target expression level on the performance of μDpTT and found that clear super-resolution images of microtubules were obtained across a wide range of tau-μDpTT expression (Figure S6); although we note that imaging targets at low endogenous expression levels could be challenging when the labeling density is too low. These results suggest that μDpTT is an advantageous red label in live-cell pcSOFI.</p><p>The improved imaging of RIIα localization using μDpTT further revealed cytoskeleton-like structures in MIN6 β cells. To determine the nature of these structures and demonstrate the suitability of μDpTT in multi-color pcSOFI, we next co-imaged PKA RIIα-μDpTT with Dronpa-fused subcellular markers tau, Lifeact, CAAX for microtubules, actin, and plasma membrane, respectively. Dual-color imaging indicated that fibrous RIIα structures co-localized with microtubules, but not actin or plasma membrane (Figure 2B–C). Furthermore, Nocodazole treatment led to 54% dissociation of fibrous RIIα structures, concurrent with microtubule depolymerization (Figure S7), conforming that RIIα localizes on microtubules in MIN6 β cells.</p><p>We next examined whether the new DrFLINC pair in μDpTT, namely DronpaH193T and TagRFP-T, could also be used to develop a next-generation super-resolution kinase activity biosensor. Introducing the H193T mutation into Dronpa on FLINC-AKAR1, we constructed a new biosensor where the molecular switch consisting of a PKA-specific substrate and phospho-amino-acid binding FHA1 domain17 joined by an EV linker18 is sandwiched between DronpaH193T and TagRFP-T. Named DrFLINC-AKAR, this sensor reported PKA activity via an increase in red fluorescence fluctuations, which can be quantified by pcSOFI (Figure 3A). Plasma membrane-targeted DrFLINC-AKAR generated a super-resolution map of PKA activity (FRC estimation: 106 nm) with clearly visible high-activity microdomains, consistent with previous findings3. DrFLINC-AKAR showed similar responses to FLINC-AKAR1 under the current microscopy setting (Supplementary information), clearly outperforming a variant containing DpGGG (Figure S8). The average normalized pcSOFI value showed a 13% increase upon forskolin (Fsk) and 3-isobutyl-1-methylxanthine (IBMX) treatment to activate adenylyl cyclase and inhibit phosphodiesterases, respectively (Figure 3B/C). Addition of the selective PKA inhibitor H89 gradually decreased the normalized pcSOFI value, demonstrating the reversibility of DrFLINC-AKAR. The negative-control biosensor that cannot be phosphorylated (Figure 3B/C) demonstrated that the response was dependent on phosphorylation of the biosensor. Activation of PKA induced a two-fold increase in microdomain coverage over the basal membrane, and the PKA activity puncta were clearly resolved on the plasma membrane (Figure 3D), similar to what was observed with the original FLINC-AKAR13.</p><p>Anchoring proteins like AKAPs can host kinases, phosphodiesterases, phosphatases, channels, and adenylyl cyclases within the signaling microdomain. Identifying the localization of both upstream and downstream signaling components at super-resolution and relating them to PKA activity is therefore important in understanding the effective functions of distinct PKA microdomains. Conveniently, the above Dronpa-removal allows co-imaging with another Dronpa fusion at super-resolution. Thus, we can now resolve the context of live-cell PKA activity at super-resolution via dual-color pcSOFI. We first examined the colocalization of stimulated PKA activity microdomains with plasma membrane AKAP79, which we previously showed via STORM imaging to be co-clustered3. We co-expressed plasma membrane-targeted DrFLINC-AKAR and AKAP79-Dronpa in HeLa cells and performed sequential pcSOFI under TIRF conditions. Nanoclusters of AKAP79 molecules were observed on the plasma membrane, a majority of which were colocalized with PKA activity microdomains (Figure 4A/D and Figure S9A), confirming the presence of AKAP-mediated PKA activity architecture in living cells. AKAP nano-clustering likely plays a critical role in organizing this activity architecture, not only by increasing the effective concentration of PKA regulatory subunits to enable micro-compartmentalized PKA activity3 but also by recruiting and concentrating adenylyl cyclases19.</p><p>Next, we examined the spatial interplay between stimulated PKA activity microdomains and potential effectors. AKAPs have been shown to link actin and PKA through β-catenin20. We performed two-color pcSOFI with DrFLINC-AKAR and Lifeact-Dronpa in HeLa cells and found that with the exception of filopodia, the majority of PKA activity microdomains did not colocalize with actin (Figure 4B/E). These data suggest that PKA activity microdomains are not generally organized along actin networks, but instead more specifically targeted to sub-regions that are involved in migration and mechano-sensing21–22.</p><p>PKA plays a critical role in the complex, tissue-specific regulation of the voltage-dependent L-type calcium channel Cav1.223, which is itself a PKA substrate. Previous experiments examined the colocalization of Cav1.2 and PKA24, but co-imaging of PKA activity microdomains and Cav1.2 was not possible in a live-cell context. Employing DrFLINC-AKAR and Cav1.2-Dronpa, we observed the formation of Cav1.2 nanoclusters on the plasma membrane of living cells, whereupon β-adrenergic stimulation increased the number of Cav1.2 nanoclusters that colocalized with PKA activity microdomains (Figure 4C/F and Figure S9B and S10). Consistent with previous findings24, we found that PKA activity microdomains colocalize with only a subset of Cav1.2 nanoclusters. Thus, micro-compartmentalization of PKA signaling is maintained and re-shaped from the signaling enzyme to specific downstream substrates. These data suggest that DrFLINC-AKAR can be applied in multiplexed imaging to investigate the context of PKA activity at the super-resolution level in living cells.</p><p>In this study, we introduced DrFLINC as both a red fluctuating fluorescent label and a super-resolution activity reporter unit amenable to dual-color imaging. Since μDpTT uses two fluorescent protein domains, we expect the typical caveats associated with using larger fusion tags such as tdTomato25. We envision that with the modular design of fluorescent biosensors26 and general applicability of pcSOFI27–28, DrFLINC-based biosensors and dual-color super-resolution imaging should help reveal the complex activity architectures of the cell6–7.</p>",
"role": "user"
},
{
"content": "Super-resolution activity imaging maps the biochemical architecture of living cells, yet currently overlooks the locations of collaborating regulators/effectors. Building on the fluorescence fluctuation increase by contact (FLINC) principle, here we devise Dronpa-chromophore-removed FLINC (DrFLINC), where the nonfluorescent Dronpa can nevertheless enhance TagRFP-T fluorescence fluctuations. Exploiting DrFLINC, we develop a superior red label and a next-generation activity sensor for context-rich super-resolution biosensing.",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.58457 | [
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: What to account for when accounting for algorithms: a systematic literature review on algorithmic accountability \nChapter Title: ON ACCOUNTABILITY AND \n1. Abstract of Cited Paper (BIB001): This article responds to recent debates in critical algorithm studies about the significance of the term “algorithm.” Where some have suggested that critical scholars should align their use of the term with its common definition in professional computer science, I argue that we should instead approach algorithms as “multiples”—unstable objects that are enacted through the varied practices that people use to engage with them, including the practices of “outsider” researchers. This approach builds on the work of Laura Devendorf, Elizabeth Goodman, and Annemarie Mol. Different ways of enacting algorithms foreground certain issues while occluding others: computer scientists enact algorithms as conceptual objects indifferent to implementation details, while calls for accountability enact algorithms as closed boxes to be opened. I propose that critical researchers might seek to enact algorithms ethnographically, seeing them as heterogeneous and diffuse sociotechnical systems, rather than rigidly constrained and... \n2. Abstract of Cited Paper (BIB002): At the dawn of the fourth industrial revolution, we are witnessing a fast and widespread adoption of artificial intelligence (AI) in our daily life, which contributes to accelerating the shift towards a more algorithmic society. However, even with such unprecedented advancements, a key impediment to the use of AI-based systems is that they often lack transparency. Indeed, the black-box nature of these systems allows powerful predictions, but it cannot be directly explained. This issue has triggered a new debate on explainable AI (XAI). A research field holds substantial promise for improving trust and transparency of AI-based systems. It is recognized as the sine qua non for AI to continue making steady progress without disruption. This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI. Through the lens of the literature, we review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.\n\nLiterature Review:",
"role": "user"
},
{
"content": "ALGORITHMIC SYSTEMS 2.0.1 Defining accountability. Making governmental conduct transparent is now viewed as 'good governance'. As such, accountability efforts can often be said to have a virtuous nature BIB001 . However, a side effect to such accountability efforts is the 'sunlight is the best disinfectant; electric light the most efficient policeman' logic. In having to be transparent about one's work, one starts to behave better: here we see accountability used as a mechanism to facilitate better behavior BIB001 . Both logics can co-exist. Accountability as a term can be used in a broad and narrow sense. Typically, though, the term refers to what Bovens [24, p. 447 ] describes as: a relationship between an actor and a forum, in which the actor has an obligation to explain and to justify his or her conduct, the forum can pose questions and pass judgement, and the actor may face consequences. BIB003 Thus an 'actor' (be they an individual, a group, or an organization) is required to explain their actions before a particular audience, the 'forum'. This account is bound to particular criteria. The audience can then ask for clarifications, and additional explanations, and subsequently decides if the actor has displayed proper conduct, from which repercussions may or may not follow. What is denoted with algorithmic accountability is this kind of accountability relationship where the topic of explanation and/or justification is an algorithmic system. So what, then, is an algorithmic system? 2.0.2 Defining algorithmic systems. As noted above, algorithms are basically instructions fed to a computer [70, p. 16] , They are technical constructs that are simultaneously deeply social and cultural BIB002 . Appreciating this 'entanglement' of various perspectives and enactments BIB002 of algorithms, this contribution sees algorithms not as solely technical objects, but rather as socio-technical systems, which are embedded in culture(s) and can be viewed, used, and approached from different perspectives (e.g. legal, technological, cultural, social). This rich set of algorithmic 'multiples' [107, cited in 125] can enhance accountability rather than limit it. The interdisciplinary systematic literature review presented in the remainder of this contribution bundles knowledge and insight from a broad range of disciplines and appreciates the entanglements and multiples that are invariably a characteristic of algorithmic system interaction.",
"role": "assistant"
}
]
|
science.chemsum_single_document_summarization | science.chemsum_single_document_summarization.67283 | [
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nOne-Pot Hydrothermal Synthesis of Benzalkonium-Templated Mesostructured Silica Antibacterial Agents\n\nPaper sections:\n\n<p>Over the past several decades, mesoporous silica nanoparticles (MSNs) have attracted a great deal of interest in fields such as catalysis, drug delivery systems (DDS), sensing, environmental remediation, and nanoelectronics due to their unique structures and properties.1–8 Since the first report of drug delivery systems based on MSNs, research on biomedical applications of MSNs has increased exponentially each year.2,9 MSNs demonstrated significant advantages over traditional nano-based formulations for potential treatment of diabetes, inflammation, and especially cancer.10–14 However, significant effort is still warranted to overcome the key challenges involved with developing effective DDSs that can attain: 1) sufficient drug loading capacity, 2) controlled or activated release, 3) targeted delivery of drug, and 4) biocompatibility.</p><p>MSNs are typically synthesized with \"inert\" structure directing agents (SDAs), commonly referred to as soft templates, with their subsequent removal to yield nanoporous structures suitable for surface modification and drug loading. On the other hand, several previous reports have described the use of different active molecules (e.g., a corrosion inhibitor, an antitumor drug, etc.) as templates for the synthesis of various porous silica materials.15–17 Although numerous advantages of one-step fabrication of DDSs have been realized through these works, there have been only a few reports involving those with antimicrobial applications, and the efficacy of the fabricated materials is often not evaluated beyond the scope of drug release kinetics.</p><p>The bactericidal drug benzalkonium chloride (BAC) (Figure 1) forms micelles in aqueous solution above a critical micelle concentration of ca. 0.5 mM.18 BAC is a ubiquitous ingredient in food, pharmaceutical, and industrial formulations due to its broad spectrum of bactericidal activity. In small concentrations, it affects the membrane permeability to cause cytolytic leakage of cytoplasmic materials (Figure 1); however, at high concentrations, it targets carboxylic groups to cause coagulation in the bacterial cytoplasm.19 Herein, we report the development of novel BAC-templated mesoporous silica microparticles, dubbed BAC-SiO2, for antimicrobial drug delivery by using BAC as the template during a one-step hydrothermal synthesis. The material demonstrates a relatively high payload of BAC, a sustained and prolonged release of BAC in physiologically-relevant pH ranges (4-8), an extremely high surface area framework upon removal of BAC, and a time-dependent bactericidal activity.</p><p>Synchrotron-based small-angle X-ray scattering (SAXS) and static light scattering (SLS) measurements of aqueous BAC/NH4OH solution prior to TEOS addition revealed the presence of nano-sized BAC micelle aggregates. SAXS profile (Figure S1 in Supporting Information, SI) exhibits diffraction peaks within the range of ca. 20-70 Å. SLS measurements (Figure S2), in decent agreement of SAXS, revealed size distribution between ca. 10-50 Å. The FTIR spectra of both BAC and BAC-SiO2 (Figure 2a) exhibited C-H stretching bands (2854 cm−1 and 2924 cm−1) and C-H bending vibration band (1457 cm−1), due to alkylammonium groups.12–14 Asymmetric (1044 cm−1) and symmetric (809 cm−1) bands associated with Si-O-Si were observed in the spectra of BAC-SiO2 before and after calcination.20–21</p><p>Quantification of BAC within the framework of BAC-SiO2 was conducted using TGA (Figures 2b). Consistent with previous reports of quaternary ammonium surfactants, TGA data of freeze-dried BAC showed a 95 % weight loss in the range of 170-300 °C due to its thermal degradation (Figure 2b).20, 22 On the other hand, the TGA curve of BAC-SiO2 exhibited four distinct weight loss ranges: 1) the loss of water, and maybe residual ammonia from the synthesis, at < 170 °C; 2) first step of BAC degradation in the range of 170-300 °C; 3) second step of BAC degradation in the range of 300-340 °C; and 4) loss of water due to condensation of silanol groups. The weight loss between 170-340 °C was ca. 36% (0.56 g per 1 g SiO2), which corresponds to the amount of BAC within the BAC-SiO2. The thermal properties of the materials were analyzed by DSC (see Figure S3).</p><p>TEM micrograph of the calcined material (Figure 2c) showed seemingly disordered mesopores structures with pore widths on the order of 30-50 Å. The small-angle X-ray diffraction (SAXRD) pattern (Figure 2d) was characteristic of an isotropic material that forms layers by virtue of consistent size rather than by extended 1D or 2D periodic arrangements of molecules. (The TEM image and SAXRD pattern of the corresponding BAC-SiO2 material, before calcination, are shown in Figures S4–S6). Thus, there was no diffraction pattern from self-assembly of molecular species. There was only random packing of nearest neighbor pores that gave rise to a consistent, but isotropic, scattering vector near 32 Å, which is the approximate distance between rows of pores. If the pattern was cubic, then the pore-to-pore centroids are what were measured. However, information gathered from TEM micrographs and expected packing arrangements of random spheres appeared to favor an hcp motif, making the observed value to be 3∕2 times the average core-to-core distance. Thus, the average core-to-core distance was about 37 Å. By incorporating the Scherrer equation, the domain spacing was determined to be ca. 11 nm, which is consistent with three repeats of the 37 Å spacing (i.e., on average there are triplets of pores that scatter).23–24</p><p>The N2 sorption results revealed a type IV isotherm, with a capillary condensation step and type H4 hysteresis loop (Figure S6), which is characteristic of mesoporous materials. The Brunauer-Emmett-Teller (BET) surface area, the Barrett-Joyner-Halenda (BJH) average pore width, and the pore volume were found to be 1579 m2g−1, 18.4 Å, and 0.56 cm3 g−1, respectively (see details in SI).25,26 However, the Kruk-Jaroniec-Sayari (KJS) corrections on the data with cylindrical pore assumptions27 yielded a pore width closer to 30 Å. The hysteresis loop also suggested the presence of larger mesopores (−100-500 Å) due to inter-particle gaps.</p><p>A kinetic study of BAC release from BAC-SiO2 into an aqueous solution in static conditions indicates that the release rate strongly depends on the solution's pH (Figures S7–S12). Controlled release of drugs in physiological conditions is of particular interest since the pH of many healthy human tissues is between 6.2-74, but decreases to a value of ca. 5 or lower in presence of inflammation, around tumor sites, or at specific areas of the body.28</p><p>In solutions with pH 7.4, only 2.5 % of the encapsulated BAC was released from BAC-SiO2 within 2-3 days (Figure 3a). Upon decreasing pH to 4.0, a larger portion of BAC (8.0 %) was released within the same time frame. These findings agree with the drug release kinetics data for MSNs reported in literature.9,29,30 The increase in BAC release in acidic solution can be largely attributed to the replacement of cationic benzalkonium with H+ ions at the Si-O− sites. Drug release profiles at pH values of 4.0, 5.0, 6.5, and 7.4 (Figure 3a) suggest that the amount of BAC released is pH dependent in a range of 4.0-7.4. It is important to note that although the majority (ca. 93 %) of the BAC remained within the particles, a second release profile (not shown) indicated an additional 4.5 % of BAC was released upon placing the particles in a fresh solution with pH 4.0. This and additional experiment (Figure S12) suggested that the BAC could be continuously released from BAC-SiO2 in physiologically-relevant dynamic conditions.</p><p>In order to investigate the mechanism of BAC release, the in vitro drug release data was analyzed using the power law (Korsmeyer-Peppas) model (Eqn. 1).21,31 This model, based on Fick's second law of diffusion, depicts drug release with the assumption that the diffusion coefficient is concentration independent and the drug is homogeneously distributed throughout the drug delivery system. The general form is:\nEqn. 1MtM∞=ktn\nwhere Mt and M∞ are the cumulative amounts of released BAC at time t and infinity, respectively; n is the release exponent that characterizes the desorption mechanism; and k is the kinetic constant which correlates directly with the diffusion coefficient, D, if a constant thickness of the diffusion path is assumed.32–33 Although the values of n are geometry dependent, the same BAC-SiO2 material was used for the release experiments, eliminating the geometry variable. A plot of log(Mt/M∞) as a function of log(t), with t ≤ 62 h in solutions with pH 4.0 and 7.4, (see Supporting Information or SI) yielded n values shown in Table S1.</p><p>Comparison of n values indicated that there were at least two processes that could govern the release of BAC from the silica particles. In phosphate-buffered saline (PBS) pH 7.4, n = 0.72, which is indicative of non-Fickian diffusion with a superposition of framework swelling or erosion.21 However, in PBS solutions acidified with HCl to pH 4.0, 5.0, and 6.5, n values ranged between 0.13–0.18 which suggests non-Fickian diffusion from disordered pores with respect to shape, length, and size.17,21 It is noteworthy that the dependence of n values to the release should, in reality, comprise several superimposed processes. For example, penetration of water into the particles is present in both release media, but it is more profound in PBS without HCl.</p><p>Kinetic modeling of the release data (see SI) demonstrated that the release mechanism in a solution with pH 7.4 versus that with pH 4.0 was different. The proposition of different mechanisms responsible for BAC release in the aforementioned media was reasonable due to the vast differences in the release environment. At pH 7.4, an environment representative of extracellular healthy tissues and blood, there is an excess of OH− relative to H3O+ ions. Thus, the excess OH− ions have the capacity to deprotonate some of the silanol (-Si-OH) groups and even hydrolyze some of the siloxanes. Many studies report that the pKa of silanol groups is ca. 4-5.34–35 On the other hand, at pH 4.0 the environment is moderately acidic, and thus, the electrostatically-bound BAC templates can be liberated by ion exchange with another cation (e.g., H+). Additionally, acid-catalyzed condensation of two silanol groups, which reduces silanol groups, occurs concomitantly with the release of the cationic BAC surfactants.</p><p>Since surfactant-extracted MSNs have proven to exhibit a remarkably faster degradation rate in simulated body fluid,36 it is proposed that the materials synthesized herein will continue to release drug. Additionally, as the material is not calcined, the density of surface silanols is conserved, which can be further modified. Indeed, BAC-SiO2 exposure resulted in a time- and concentration-dependent killing of the Gram-positive S. aureus and the Gram-negative S. enterica human bacterial pathogens (Figure 3b). Similar findings have been reported for BAC.37,38 Importantly, SiO2 had no effect on bacterial viability while BAC-SiO2 displayed much more killing than pure BAC, when the amount of BAC present in and released from the BAC-SiO2 was taken into consideration (40 wt.% BAC in BAC-SiO2 that released <10% BAC in 2.5 days) (Figures 3a and 3c). Besides, any possible residual NH4OH in the material had no contribution to BAC-SiO2's bactericidal activity (Figures S13 and S14 and discussions therein). These results, as a whole, suggest that BAC-SiO2 is inherently quite effective at killing microbes.</p><p>In summary, we have developed a mesostructured silica drug delivery vehicle that releases BAC slowly over 2-3 days using pH changes as a trigger in static conditions. The material exhibits a high drug loading capacity and very good antibacterial properties. The synthetic approach can be extended to a variety of drugs to realize advanced functional biomaterials.</p>",
"role": "user"
},
{
"content": "Novel mesostructured silica microparticles are synthesized, characterized and investigated as a drug delivery system (DDS) for antimicrobial applications. The materials exhibit relatively high density (0.56 g per 1 g SiO2) of BAC, pore channels of 18 \\xc3\\x85 in width, and high surface area (1500 m2/g). Comparison of SAXRD pattern with BJH pore size distribution data suggests that the 18 \\xc3\\x85 pores exhibit short range ordering and a wall thickness of ca. 12 \\xc3\\x85. Drug release studies demonstrate pH-responsive controlled release of BAC without additional surface modification of the materials. Prolonged drug release data was analyzed using a power law (Korsmeyer-Peppas) model and indicates substantial differences in release mechanism in acidic (pH 4.0, 5.0, 6.5) versus neutral (pH 7.4) solutions. Microbiological assays demonstrate a significant time-dependent reduction in Staphylococcus aureus and Salmonella enterica viability above 10 and 130 mg L\\xe2\\x88\\x921 of the synthesized materials, respectively. The viability of cells is reduced over time compared to control samples. The findings will help in widening the use of BAC as a disinfectant and bactericidal agent, especially in pharmaceutical and food industries where Gram-positive and Gram-negative bacterial contamination is common.",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_elife_single_doc_summ | science.scientific_lay_summarisation_elife_single_doc_summ.250 | [
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Distinct insulin granule subpopulations implicated in the secretory pathology of diabetes types 1 and 2\nArticle:\nAbstract:\nInsulin secretion from β-cells is reduced at the onset of type-1 and during type-2 diabetes. Although inflammation and metabolic dysfunction of β-cells elicit secretory defects associated with type-1 or type-2 diabetes, accompanying changes to insulin granules have not been established. To address this, we performed detailed functional analyses of insulin granules purified from cells subjected to model treatments that mimic type-1 and type-2 diabetic conditions and discovered striking shifts in calcium affinities and fusion characteristics. We show that this behavior is correlated with two subpopulations of insulin granules whose relative abundance is differentially shifted depending on diabetic model condition. The two types of granules have different release characteristics, distinct lipid and protein compositions, and package different secretory contents alongside insulin. This complexity of β-cell secretory physiology establishes a direct link between granule subpopulation and type of diabetes and leads to a revised model of secretory changes in the diabetogenic process.\nIntroduction:\nBlood glucose levels are maintained in a narrow range by secretion of the hormone insulin from pancreatic β-cells. Insufficient insulin secretion leads to elevated levels of blood glucose resulting in diabetes( Rorsman and Ashcroft, 2018). Type 1 diabetes( T1D) results primarily from immune-mediated killing of pancreatic β-cells. In contrast, type 2 diabetes( T2D) arises when peripheral resistance to insulin signaling causes persistent demand for insulin secretion and eventual β-cell exhaustion( Guthrie and Guthrie, 2004; Rorsman and Ashcroft, 2018). Understanding molecular deficiencies of the secretory pathway in diabetes is essential for identifying the underlying causes of the disease. Secretory defects have been observed in diabetic human islet cells. Treatments that mimic these defects have been identified and used to model diabetes in healthy human cells, rodent islets, and immortalized cell lines( Aslamy et al., 2018a; Aslamy et al., 2018b; Gandasi and Barg, 2014; Hoppa et al., 2009; Olofsson et al., 2007). Onset of T1D is modeled by treatment of insulin-secreting cells with proinflammatory cytokines TNF-α, INF-γ, and IL-1β, which leads to decreased insulin release and a loss of Doc2B, an established biomarker for the disease( Aslamy et al., 2018a; Aslamy et al., 2018b). T2D is associated with extended exposure to elevated free fatty acids( FFA) caused by high fat diets( Grill and Qvigstad, 2000). The lipotoxicity component of T2D is frequently modeled by sustained treatment of insulin-secreting cells with palmitate, resulting in reduced glucose-stimulated insulin secretion( Hoppa et al., 2009; Sako and Grill, 1990). Stimulated secretion of insulin normally occurs in two sequential phases, an acute first phase and a sustained second phase, which are differently affected in the T1D and T2D models. Modeling the inflammation of T1D by cytokine treatment causes a defect in insulin secretion attributed to the loss of Doc2B( Aslamy et al., 2018a; Aslamy et al., 2018b), which primarily suppresses the second phase of secretion( Ramalingam et al., 2012). Conversely, modeling T2D by palmitate treatment strongly decreases the first phase( Rorsman and Ashcroft, 2018). These observations show distinct insulin secretion profiles in the two diseases, and understanding the molecular and cellular mechanisms of how these different outcomes arise would provide a fundamentally new molecular view on the pathology of diabetes. Although the secretory defects leading to T1D and T2D are well established, the cell and molecular biology that underlies the phenotypes of T1D and T2D model treatments is not known. To address this fundamental gap in knowledge, we performed large-scale purification of secretory granules on either untreated, palmitate-treated, or cytokine-treated insulin-secreting cells. These granules were characterized comparatively for SNARE-mediated fusion properties in single particle fusion assays with SNARE-containing reconstituted target membranes. This novel cellular dissection and reconstitution approach, which was corroborated in intact insulin-secreting cells undergoing the same treatments, revealed a previously unknown heterogeneity among insulin granules with different subpopulations of secretory vesicles being lost following one or the other of the two diabetes-mimicking treatments. Further study showed remarkable differences in size, composition, and fusion characteristics of these subpopulations. As a result, we were able to identify a strong correlation between the distinct contents of the two subpopulations and known changes in β-cell output of signaling molecules by pancreatic islets during the onset of each type of diabetes. Taken together, these studies lead to a revised model about how the organization and regulation of two insulin secretory pathways potentially impact physiological intra-islet communication and pathological changes that accompany the diabetogenic process.\nDiscussion:\nOur results reveal that insulin-secreting cells harbor distinct subpopulations of insulin granules that are selectively activated for secretion to release different secretory molecules. Therefore, insulin granules can no longer be considered generic storage units for releasing the full range of secretory molecules without regard to timing and signal strength. Regulated exocytosis provides a complex network of β-cell derived signals that serve as autocrine and paracrine governors of the secretion of insulin and other islet-derived hormones. The current work shows that these secretory regulators are parsed out selectively among the two insulin granule subpopulations that we have characterized in great molecular detail. The biphasic secretory pattern of insulin release in response to glucose has been previously described by its correlation to electrical activity in stimulated islet β-cells( Rorsman and Ashcroft, 2018). Because the granule subpopulations with secretory cargo compositions have different calcium affinities furnished by different synaptotagmin isoforms( Figure 3), we propose that these phases can be interpreted as a staged release of selected peptides and transmitters over time and levels of intracellular calcium. The detailed characteristics of the granule subpopulations and their correlations to T1D and T2D are summarized in Table 1. In our new model linking the progression of T1D and T2D to different subpopulations of insulin secretory granules in the same cells, we posit that the syt9 granules release their content primarily in the first phase of secretion during the initial spike in intracellular calcium supported by their close proximity to calcium channels( Hoppa et al., 2009). Granules harboring the high-affinity calcium sensor syt7 would release their content during both phases. Indeed, both first- and second-phase secretion are decreased in human β-cells upon syt7 knockout( Dolai et al., 2016) and upon Doc2b knockout in mice( Ramalingam et al., 2012), while treatment of human β-cells with free fatty acids inhibits the peak during the initial release phase( Hoppa et al., 2009). It will be interesting to see if physiologic responses can be correlated to time-dependent release of selected cargoes that have local and systemic regulatory roles and if there is further heterogeneity within the discovered subpopulations. Our studies further illustrate the very important contribution of granule membrane protein and lipid composition in supporting the complex signaling capability of β-cell exocytosis. The striking difference in lipid composition between the two granule subpopulations, especially with regard to sphingomyelin and cholesterol content( Figure 4), almost certainly contributes to the specific sorting of the fusion regulatory proteins and transporters( Figure 5). These sorting events enable granule subpopulations to be mobilized according to signaling strength and thereby export different regulatory signals during different phases of T1D and T2D development. Going forward, it will be interesting to define these sorting processes in more detail, determine how they interface with other post-Golgi pathways, and thereby contribute to the pathology of diabetes. A central and striking new finding of the present study is the discovery that the two markedly different insulin granule subpopulations are each selectively sensitive to T1D and T2D model treatments. This brings new insight to the differing secretory pathologies that arise in β-cells during the two types of diabetes. Further, the differential loss of specific granule subpopulations can explain previously observed changes in insulin release characteristics such as more restricted fusion pores after palmitate treatment( Hoppa et al., 2009), which would be consistent with slower content release that we observed after this treatment. Because the levels of neither syt7 nor syt9 are decreased in lysates of cells following diabetic model treatments( Figure 3B), it appears that shifts in granule subpopulations induced by the treatments are not explainable solely by amplified autophagic degradation of a particular type of granule, although the process of granule turnover by crinophagy in β-cells( Marsh et al., 2007) may be membrane-conservative and thus not lead to synaptotagmin degradation. In the case of palmitate treatment, however, it will be necessary to evaluate this deduction in relation to the recently reported crinophagy of newly formed insulin granules under experimental conditions that differ from ours( Pasquier et al., 2019). Follow-up studies may also be needed to examine whether diabetogenic signaling is targeted to granule formation where a role for CAPS has already been defined( Speidel et al., 2008) or to enhanced stimulated secretion( Olofsson et al., 2007). As well, it will be interesting to learn whether perturbed clustering of L-type calcium channels by palmitate( Gandasi and Barg, 2014) and perturbed function of syntaxin-4 caused by proinflammatory cytokines( Oh et al., 2012; Wiseman et al., 2011) interface with the signaling that is targeted to the insulin granule subpopulations. Regardless, the loss of a whole granule subpopulation and with it the loss of a variety of signaling molecules during the onset of T1D or throughout T2D likely explains multiple previously unknown effects on the progression of the disease. For example, losing granules secreting ATP and MIF( Figure 6A) during the onset of T1D might compromise both local signaling and islet protection from immune cells( Stojanovic et al., 2012; Weitz et al., 2018). Although there were prior hints that high and low sensitivity calcium pools co-exist in insulin secreting cells( Wan et al., 2004; Yang and Gillis, 2004), the identities of different granule subpopulations have not been previously described and mapping of the complex arrays of secretory products within these subpopulations has not been achieved. Also, the discovery that these subpopulations and their secretory products are linked to distinct diabetic states of insulin producing cells is novel and provides new mechanistic insight to established defects in diabetic( T1D and T2D) secretory signals. Our granule purification and functional reconstitution approach was ideally suited to characterize heterogeneity of granules subpopulations in extensive detail, which has not been previously achieved using traditional cellular approaches. A recent study demonstrates that the described granule heterogeneity likely extends to human and rodent pancreatic β-cells with differential modulation of calcium sensitivity of exocytosis conferred by synaptotagmin isoforms during pancreatic development and maturation( Huang et al., 2018). Therefore, our current work provides a road map for examining changes of secretory signals within diabetes in authentic islets. The new insights gained here will likely inform the design of future studies to explore granule heterogeneity in human and other mammalian islet secretion of specific products stimulated by appropriate signals under different diabetic states. The presence of functionally and compositionally distinct secretory vesicles revealed here for insulin secreting cells( Table 1) is not unique to pancreatic β-cells and derivatives, but is likely a general property of a variety of regulated secretory cells. Secretory vesicle heterogeneity has been shown to have consequences on synaptic secretion and likely affects secretion from most endocrine cell types as well as from immune cells functioning in host defense. In neurons, the partitioning of VGAT and VGLUT between different vesicles has been observed( Farsi et al., 2016) but no mechanism of how a cell facilitates sorting of these transporters into distinct synaptic vesicles has been explored. The tools developed and presented in this work should open new avenues for future studies of the characteristics and mechanisms of sorting processes in these other cell types and thus help with a better molecular understanding of the diseases that are associated with them.",
"role": "user"
},
{
"content": "Diabetes is a disease that occurs when sugar levels in the blood can no longer be controlled by a hormone called insulin . People with type 1 diabetes lose the ability to produce insulin after their immune system attacks the β-cells in their pancreas that make this hormone . People with type 2 diabetes develop the disease when β-cells become exhausted from increased insulin demand and stop producing insulin . β-cells store insulin in small compartments called granules . When blood sugar levels rise , these granules fuse with the cell membrane allowing β-cells to release large quantities of insulin at once . This fusion is disrupted early in type 1 diabetes , but later in type 2: the underlying causes of these disruptions are unclear . In the laboratory , signals that trigger inflammation and molecules called fatty acids can mimic type 1 or type 2 diabetes respectively when applied to insulin-producing cells . Kreutzberger , Kiessling et al . wanted to know whether pro-inflammatory molecules and fatty acids affect insulin granules differently at the molecular level . To do this , insulin-producing cells were grown in the lab and treated with either fatty acids or pro-inflammatory molecules . The insulin granules of these cells were then isolated . Next , the composition of the granules and how they fused to lab-made membranes that mimic the cell membrane was examined . The experiments revealed that healthy β-cells have two types of granules , each with a different version of a protein called synaptotagmin . Cells treated with molecules mimicking type 1 diabetes lost granules with synaptotagmin-7 , while granules with synaptotagmin-9 were lost in cells treated with fatty acids to imitate type 2 diabetes . Each type of granule responded differently to calcium levels in the cell and secreted different molecules , indicating that each elicits a different diabetic response in the body . These findings suggest that understanding how insulin granules are formed and regulated may help find treatments for type 1 and 2 diabetes , possibly leading to therapies that reverse the loss of different types of granules . Additionally , the molecules of these granules may also be used as markers to determine the stage of diabetes . More broadly , these results show how understanding how molecule release changes with disease in different cell types may help diagnose or stage a disease .",
"role": "assistant"
}
]
|
science.scientific_papers_summarization_single_doc_arxiv | science.scientific_papers_summarization_single_doc_arxiv.59605 | [
{
"content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nthe jets of radio - loud agn carry energy and matter out from the nucleus to cluster - sized lobes , over distances of hundreds of kpc .\nwhile found in only @xmath2 of agn , jets can have a power output ( including both luminosity and kinetic energy flux ) comparable to that of the host galaxy and agn @xcite , and can profoundly influence the evolution of their host galaxy and nearby neighbors .\nagn jets are completely ionized flows , and the radiation we see from them is non - thermal in nature . that the radio emission arise from synchrotron radiation is supported by strong linear polarization and power - law spectra seen in both lower- and higher - power jets . however , at higher energies\n, the nature of the emission from higher - power large - scale jets is less clear . in low - power fr\ni radio galaxies , the optical and x - ray fluxes fit on extrapolations of the radio spectra ( e.g. , @xcite ) , and high polarizations are seen in the optical ( typically @xmath3 , @xcite ) suggesting synchrotron emission .\nthese jets exhibit a wide variety of polarization properties @xcite , often correlated with x - ray emission .\nfor example , in the jet of m87 @xcite , a strong anti - correlation between x - ray emission and optical polarization was found in the knots , accompanied by changes in the magnetic field direction , suggesting a strong link between the jet s dynamical structure and high - energy processes in the jet interior , where shocks compress the magnetic field and accelerate particles in situ . for the more powerful fr ii and quasar jets , the nature of both the optical and x - ray emission is under active debate .\nin many fr ii jets , the optical emission can lie well below an interpolation between the radio and x - rays ( e.g. , @xcite ) , sometimes by decades ( e.g. , pks 0637@xmath1752 , @xcite ) , resulting in a characteristic double - humped shape of spectral energy distribution . in some jets the optical emission appears linked to the x - ray emission by a common component .\nthis is the case in both 3c 273 and pks 1136@xmath1135 , where deep hst , chandra and spitzer imaging @xcite has shown that a second component , distinct from the lower - energy synchrotron emission , arises in the near - ir / optical and dominates the jet emission at optical and higher energies , at least up to 10 kev .\ncompeting mechanisms have been proposed : either synchrotron radiation from very high - energy particles or inverse - comptonization ( see @xcite ) , however , the nature of this component can not be constrained by multi - waveband spectra alone @xcite .\npolarimetry is a powerful diagnostic for jets because synchrotron emission is naturally polarized , with the inferred direction of the magnetic field vector indicating the weighted direction of the magnetic field in the radiating volume . in fr\niis , where the radio - optical spectrum can not be neatly extrapolated to the x - rays , high - energy synchrotron emission requires a second electron population .\nthe existence of such a component would drastically alter our picture of fr ii jets , which until recently were not believed to accelerate electrons to @xmath4 .\nthis would require highly efficient particle acceleration mechanisms that can operate well outside the host galaxy ( e.g. , in pks 1136@xmath1135 the x - ray emitting knots are at projected distances of @xmath5 kpc from the agn ) .\nif the optical and x - ray emission is synchrotron radiation , the optical polarization will be high , comparable to that seen in the radio , but with characteristics that may be linked to acceleration processes .\nthe second possibility is inverse - comptonization of cosmic microwave background photons ( ic - cmb ) , @xcite .\nthis requires a jet that remains highly relativistic out to distances of hundreds of kpc @xcite , viewed within a few degrees of the line of sight .\nany optical ic - cmb would be linked to nearly cold electrons , with @xmath6 , a population of particles that has never been tracked before .\nif the emitter is moving at relativistic bulk speeds , @xmath7 , then the forward - bunching effect will make the cmb photons essentially unidirectional in the jet frame\n. the ic scattering on the unidirectional and unpolarized photon beam by high - energy electrons having large lorentz factors ( @xmath8 ) should be unpolarized . on the other hand , the scattered radiation by cold electrons ( @xmath9\n; so - called bulk comptonization ) in the jet is expected to be highly polarized @xcite .\nwe have carried out calculations covering the intermediate regime with @xmath10 few , making use of the general expression for the intensity and polarization of singly - scattered comptonized radiation presented by @xcite .\nwe found that , for a power - law energy distribution of electrons with a cutoff at @xmath11 , the polarization degree can be as large as @xmath12 with the direction of the electric field vector perpendicular to the jet axis ( see also @xcite ) .\na second comptonization process is also possible .\nthis is synchrotron self - compton ( ssc ) radiation , in which the seed photons come from the jet s low - frequency radio emission . while ssc is unavoidable , it is unlikely to dominate the x - ray emission of the jet knots because in order to fit the observed x - ray emission , one requires a jet that is massively out of equipartition ( by factors of @xmath13 ) .\nhowever , ssc is the leading scenario for x - ray emission from the terminal hotspots of powerful jets @xcite .\nssc predicts optical polarization properties similar to that of the lowest - frequency radio emission .\npolarization observations have now been done with hst for the jet of pks 1136@xmath1135 . in figure 1\n, we show the stokes i image from those observations . in table 1 , we give polarization properties for the jet components in apertures shown in figure 1 .\nwe will discuss the details of the observations and data reduction procedures in a future paper .\nknot a is shown to be highly polarized , with fractional polarization @xmath14 , and an inferred magnetic field vector close to that seen in the radio .\nknot b , however , is weakly polarized , with @xmath15 at @xmath16 and only in the central region of the knot . moreover ,\nthe magnetic field vector in knot b is perpendicular to the direction seen in radio .\nthis indicates that different emission mechanisms dominate in these two regions in the optical as well as x - rays .\nknot a is clearly dominated by synchrotron emission up to energies of @xmath17 .\nthis is the first time high - energy synchrotron emission has been proven for any quasar jet at distances of kiloparsecs from the agn .\nknot b , however , is consistent with the ic - cmb mechanism dominating .\nfor the first time we also detect knots @xmath18 , c , and d in optical . knot @xmath18 , like knot b , is weakly polarized with the direction of the magnetic field vector perpendicular to the one seen in radio , while knots c and d are highly polarized ( @xmath19 ) with magnetic field position angle ( mfpa ) similar to the one in radio in agreement with the synchrotron radiation being the primarily emission mechanism in these knots in optical .",
"role": "user"
},
{
"content": "the emission mechanisms in extragalactic jets include synchrotron and various inverse - compton processes . at low ( radio through infrared ) energies \n , it is widely agreed that synchrotron emission dominates in both low - power ( fr i ) and high - power ( fr ii and quasar ) jets , because of the power - law nature of the spectra observed and high polarizations . \n however , at higher energies , the emission mechanism for high - power jets at @xmath0 scales is hotly debated . \n two mechanisms have been proposed : either inverse - compton of cosmic microwave background photons or synchrotron emission from a second , high - energy population of electrons . \n here we discuss optical polarimetry as a method for diagnosing the mechanism for the high - energy emission in quasar jets , as well as revealing the jet s three - dimensional energetic and magnetic field structure . \n we then discuss high - energy emission mechanisms for powerful jets in the light of the hst polarimetry of pks 1136@xmath1135 . \n address = department of physics & space sci . \n , florida institute of technology , melbourne , fl 32901 , usa address = department of physics & space sci . , florida institute of technology , melbourne , fl 32901 , usa address = slac national accelerator laboratory , menlo park , ca 94025 , usa address = max planck institute for astronomy , 69117 heidelberg , germany address = joint center for astrophysics , university of maryland , baltimore , md 21250 , usa address = nasa goddard space flight center , greenbelt , md 20771 , usa address = nasa goddard space flight center , greenbelt , md 20771 , usa address = space telescope science institute , baltimore , md 21218 , usa address = space telescope science institute , baltimore , md 21218 , usa address = cis and department of physics , rochester institute of technology , rochester , ny 14623 , usa address = cis and department of physics , rochester institute of technology , rochester , ny 14623 , usa address = cis and department of physics , rochester institute of technology , rochester , ny 14623 , usa address = joint institute for laboratory astrophysics , university of colorado , boulder , co \n 80309 , usa address = department of physics , university of bristol , bristol bs8 1tl , uk address = department of physics , university of bristol , bristol bs8 1tl , uk address = department of physics , yale university , new haven , ct 06520 - 8121 , usa address = department of astronomy , yale university , new haven , ct 06520 - 8101 , usa address = kipac , stanford university , stanford , ca 94305 , usa",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.42 | [
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: StrainnameCBA/CaHN-Btkxid/JisabbreviatedtoCBA/CaHN.",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.scitldr_aic | science.scitldr_aic.1047 | [
{
"content": "Summarize the paper:\n\nPaper text:\n\nDeep neural networks require extensive computing resources, and can not be efficiently applied to embedded devices such as mobile phones, which seriously limits their applicability.\nTo address this problem, we propose a novel encoding scheme by using {-1,+1} to decompose quantized neural networks (QNNs) into multi-branch binary networks, which can be efficiently implemented by bitwise operations (xnor and bitcount) to achieve model compression, computational acceleration and resource saving.\nOur method can achieve at most ~59 speedup and ~32 memory saving over its full-precision counterparts.\nTherefore, users can easily achieve different encoding precisions arbitrarily according to their requirements and hardware resources.\nOur mechanism is very suitable for the use of FPGA and ASIC in terms of data storage and computation, which provides a feasible idea for smart chips.\nWe validate the effectiveness of our method on both large-scale image classification (e.g., ImageNet) and object detection tasks.",
"role": "user"
},
{
"content": "A novel encoding scheme of using {-1, +1} to decompose QNNs into multi-branch binary networks, in which we used bitwise operations (xnor and bitcount) to achieve model compression, computational acceleration and resource saving.",
"role": "assistant"
}
]
|
science.mslr2022_ms2_multidoc_summarization | science.mslr2022_ms2_multidoc_summarization.3551 | [
{
"content": "Based on the RCT reports below, write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article.\n\n\n\nTitle 1:\nBevacizumab in association with de Gramont 5‐fluorouracil/folinic acid in patients with oxaliplatin‐, irinotecan‐, and cetuximab‐refractory colorectal cancer\nAbstract 1:\nThe aim of the current study was the investigation of the value of bevacizumab + 5‐fluorouracil(5–FU)/folinic acid in patients with advanced colorectal cancers who have exhausted st and ard chemotherapy options\n\n\nTitle 2:\nTreatment of Colorectal Cancer with and without Bevacizumab: A Phase III Study\nAbstract 2:\nObjective : The objective of this phase III trial was to compare chemotherapy combined with bevacizumab versus chemotherapy alone in the treatment of patients with advanced colorectal cancer . Methods : From September 2004 till September 2008 , 222 treatment-naive patients were enrolled and divided into 2 arms : 114 arm A patients were treated with leucovorin , 5-fluorouracil plus irinotecan in combination with bevacizumab , and 108 arm B patients were treated as above without bevacizumab . All patients were stage IV with histologically confirmed adenocarcinoma . Results : The median overall survival of arm A patients was 22.0 months ( 95 % CI : 18.1–25.9 ) and 25.0 months ( CI : 18.1–31.9 ) for arm B patients . There was no statistically significant difference between the 2 arms ( p = 0.1391 ) . No statistically significant difference between the 2 arms regarding the response ratewas observed : partial response , 42 patients ( 36.8 % ) and 38 patients ( 35.2 % ) for arms A and B , respectively . Hematologic toxicity did not differ in the comparison of the 2 arms . Nonhematologic toxicity in arm A involved hypertension in 23 ( 20.2 % ) of the patients and proteinuria in 7 ( 6.1 % ) ; 3 patients experienced hemorrhage and 1 patient intestinal perforation . None of these side effects was observed in arm B patients . Conclusion : No statistically significant difference in median overall survival in patients with advanced colorectal cancer treated with bevacizumab plus a combination therapy ( arm A ) and those treated with the combination only , without bevacizumab ( arm B ) , was observed\n\n\nTitle 3:\nWhy observational studies should be among the tools used in comparative effectiveness research.\nAbstract 3:\nDoctors , patients , and other decision makers need access to the best available clinical evidence , which can come from systematic review s , experimental trials , and observational research . Despite method ological challenges , high- quality observational studies have an important role in comparative effectiveness research because they can address issues that are otherwise difficult or impossible to study . In addition , many clinical and policy decisions do not require the very high levels of certainty provided by large , rigorous r and omized trials . This paper provides insights and a framework to guide good decision making that involves the full range of high- quality comparative effectiveness research techniques , including observational research\n\n\nTitle 4:\nQuality of Life of Patients with Type 1 Diabetes Mellitus Using Insulin Analog Glargine Compared with NPH Insulin: A Systematic Review and Policy Implications\nAbstract 4:\nIntroduction Insulin analog glargine ( GLA ) has been available as one of the therapeutic options for patients with type 1 diabetes mellitus to enhance glycemic control . Studies have shown that a decrease in the frequency of hypoglycemic episodes improves the quality of life ( QoL ) of diabetic patients . However , there are appreciable acquisition cost differences between different insulins . Consequently , there is a need to assess their impact on QoL to provide future guidance to health authorities . Method A systematic review of multiple data bases including Medline , LILACS , Cochrane , and EMBASE data bases with several combinations of agreed terms involving r and omized controlled trials and cohorts , as well as manual search es and gray literature , was undertaken . The primary outcome measure was a change in QoL. The quality of the studies and the risk of bias was also assessed . Results Eight studies were eventually included in the systematic review out of 634 publications . Eight different QoL instruments were used ( two generic , two mixed , and four specific ) , in which the Diabetes Treatment Satisfaction Question naire ( DTSQ ) was the most used . The systematic review did not consistently show any significant difference overall in QoL scores , whether as part of subsets or combined into a single score , with the use of GLA versus neutral protamine Hagedorn ( NPH ) insulin . Only in patient satisfaction measured by DTSQ was a better result consistently seen with GLA versus NPH insulin , but not using the Well-being Inquiry for Diabetics ( WED ) scale . However , none of the cohort studies scored a maximum on the Newcastle – Ottawa scale for quality , and they generally were of moderate quality with bias in the studies . Conclusion There was no consistent difference in QoL or patient-reported outcomes when the findings from the eight studies were collated . In view of this , we believe the current price differential between GLA and NPH insulin in Brazil can not be justified by these findings\n\n\nTitle 5:\nPatients' expectations about effects of chemotherapy for advanced cancer.\nAbstract 5:\nBACKGROUND Chemotherapy for metastatic lung or colorectal cancer can prolong life by weeks or months and may provide palliation , but it is not curative . METHODS We studied 1193 patients participating in the Cancer Care Outcomes Research and Surveillance ( CanCORS ) study ( a national , prospect i ve , observational cohort study ) who were alive 4 months after diagnosis and received chemotherapy for newly diagnosed metastatic ( stage IV ) lung or colorectal cancer . We sought to characterize the prevalence of the expectation that chemotherapy might be curative and to identify the clinical , sociodemographic , and health-system factors associated with this expectation . Data were obtained from a patient survey by professional interviewers in addition to a comprehensive review of medical records . RESULTS Overall , 69 % of patients with lung cancer and 81 % of those with colorectal cancer did not report underst and ing that chemotherapy was not at all likely to cure their cancer . In multivariable logistic regression , the risk of reporting inaccurate beliefs about chemotherapy was higher among patients with colorectal cancer , as compared with those with lung cancer ( odds ratio , 1.75 ; 95 % confidence interval [ CI ] , 1.29 to 2.37 ) ; among nonwhite and Hispanic patients , as compared with non-Hispanic white patients ( odds ratio for Hispanic patients , 2.82 ; 95 % CI , 1.51 to 5.27 ; odds ratio for black patients , 2.93 ; 95 % CI , 1.80 to 4.78 ) ; and among patients who rated their communication with their physician very favorably , as compared with less favorably ( odds ratio for highest third vs. lowest third , 1.90 ; 95 % CI , 1.33 to 2.72 ) . Educational level , functional status , and the patient 's role in decision making were not associated with such inaccurate beliefs about chemotherapy . CONCLUSIONS Many patients receiving chemotherapy for incurable cancers may not underst and that chemotherapy is unlikely to be curative , which could compromise their ability to make informed treatment decisions that are consonant with their preferences . Physicians may be able to improve patients ' underst and ing , but this may come at the cost of patients ' satisfaction with them . ( Funded by the National Cancer Institute and others . )\n\n\nTitle 6:\nLeucovorin and fluorouracil with or without oxaliplatin as first-line treatment in advanced colorectal cancer.\nAbstract 6:\nPURPOSE In a previous study of treatment for advanced colorectal cancer , the LV5FU2 regimen , comprising leucovorin ( LV ) plus bolus and infusional fluorouracil ( 5FU ) every 2 weeks , was superior to the st and ard North Central Cancer Treatment Group/Mayo Clinic 5-day bolus 5FU/LV regimen . This phase III study investigated the effect of combining oxaliplatin with LV5FU2 , with progression-free survival as the primary end point . PATIENTS AND METHODS Four hundred twenty previously untreated patients with measurable disease were r and omized to receive a 2-hour infusion of LV ( 200 mg/m(2)/d ) followed by a 5FU bolus ( 400 mg/m(2)/d ) and 22-hour infusion ( 600 mg/m(2)/d ) for 2 consecutive days every 2 weeks , either alone or together with oxaliplatin 85 mg/m(2 ) as a 2-hour infusion on day 1 . RESULTS Patients allocated to oxaliplatin plus LV5FU2 had significantly longer progression-free survival ( median , 9.0 v 6.2 months ; P = .0003 ) and better response rate ( 50.7 % v 22.3 % ; P = .0001 ) when compared with the control arm . The improvement in overall survival did not reach significance ( median , 16.2 v 14.7 months ; P = . 12 ) . LV5FU2 plus oxaliplatin gave higher frequencies of National Cancer Institute common toxicity criteria grade 3/4 neutropenia ( 41 . 7 % v 5.3 % of patients ) , grade 3/4 diarrhea ( 11.9 % v 5.3 % ) , and grade 3 neurosensory toxicity ( 18.2 % v 0 % ) , but this did not result in impairment of quality of life ( QoL ) . Survival without disease progression or deterioration in global health status was longer in patients allocated to oxaliplatin treatment ( P = .004 ) . CONCLUSION The LV5FU2-oxaliplatin combination seems beneficial as first-line therapy in advanced colorectal cancer , demonstrating a prolonged progression-free survival with acceptable tolerability and maintenance of\n\n\nTitle 7:\nA Comparison of Response Patterns for Progression-Free Survival and Overall Survival Following Treatment for Cancer With PD-1 Inhibitors\nAbstract 7:\nKey Points Question Does the treatment effect size differ between overall survival and progression-free survival for PD-1 ( programmed cell death 1 ) inhibitors used in patients with advanced solid tumors , and are overall survival and progression-free survival correlated ? Findings This meta- analysis of 12 r and omized clinical trials found no significant correlation between overall survival and progression-free survival in terms of medians and gains in medians , but their hazard ratios were significantly correlated . The protective effects of treatment were greater for overall survival than for progression-free survival . Meaning Progression-free survival can not adequately capture the benefit of PD-1 inhibitors ; thus , overall survival should remain the gold st and ard end point for trials of PD-1 inhibitors",
"role": "user"
},
{
"content": "There were statistically significant and clinical ly relevant benefits in patients treated with bevacizumab versus no bevacizumab mainly around OS , PFS , PPS and the metastasectomy rate , but not for the disease control rates .\nHowever , there was an increase in treatment-related toxicities and concerns with the heterogeneity of the studies .\nConclusion The results pointed to an advantage in favor of bevacizumab for OS , PFS , PPS , and metastasectomy .\nAlthough this advantage may be considered clinical ly modest , bevacizumab represents a hope for increased survival and a chance of metastasectomy for patients with mCRC .",
"role": "assistant"
}
]
|
science.chemsum_single_document_summarization | science.chemsum_single_document_summarization.52696 | [
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nN-Aminopyridinium Reagents as Traceless Activating Groups in the Synthesis of N-Aryl Aziridines\n\nPaper sections:\n\n<p>Aziridines, which are three-membered nitrogen-containing heterocycles, are attractive synthetic intermediates en route to 1,2-aminofunctionalization products and are present in various naturally occurring alkaloids and pharmacologically active compounds. 1 Retrosynthetically, aziridines can be envisioned as arising from the combination of a nitrene equivalent with an olefinic substrate. In practice, aziridination via nitrene transfer is severely limited by the promiscuous reactivity of unstabilized nitrenes: 2 For example, attempts to access Nphenylazidines from phenylnitrene (generated by thermolysis or photolysis of phenyl azide) result in polymeric tars instead of the desired aziridine. 3 Since Evans's report of Cu-catalyzed olefin aziridination, 4 myriad transition metal-catalyzed methods have been developed for nitrene transfer to olefins (Figure 1a). 5 Metal-catalyzed nitrene transfer catalysis typically requires electronwithdrawing groups, such as N-sulfonyl substituents, to activate the nitrogen equivalent for transfer; 6,7 there are limited reports of metal-catalyzed nitrene transfer from aryl azide precursors. 8 The resulting N-protected aziridines can be challenging to utilize in downstream Nfunctionalization chemistry. For example, exposure of N-sulfonyl aziridines to metal-catalyzed cross-coupling conditions typically results in aziridine opening, not N-functionalization. 9 N-H aziridines can be accessed by either deprotection of N-protected aziridines 10 or by direct synthesis of olefinic precursors (Figure 1b). 11 While derivitization of the N-H valence can provide access to some N-functionalization products, arylation of these compounds is not broadly developed. 12,13 N-aminopyridinium reagents represent a burgeoning class of bifunctional reagents 14 which combine a nucleophilic N-amino group with a low-lying pyridinium-centered LUMO that enables access to N-centered radicals via reductive N-N cleavage (LUMO = lowest unoccupied molecular orbital). 15 In the context of amination chemistry, N-sulfonylaminopyridiniums have been utilized in photoredox-promoted olefin difunctionalization 16 and aromatic C-H amination reactions. 17,18 Broad application of N-aminopyridiniums as bifunctional reagents in amination chemistry is stymied by the limited methods currently available to prepare N-functionalized aminopyridiniums, which are accessed by either addition of hydrazines to pyrylium salts or by sulfonylation of Naminopyridiniums. 19 Here, we describe the first example of olefin aziridination with Naminopyridinium reagents (Figure 1c). Inspired by the Ni-catalyzed C-C coupling chemistry of N-alkylpyridinium electrophiles pioneered by Watson 20 and others, 21 we demonstrate that the resulting N-pyridinium aziridines are competent electrophiles for C-N bond-forming crosscoupling with aryl boronic acids to afford N-aryl aziridines. This two-step protocol provides access to the products of formal aryl nitrene transfer to olefinic substrates and stands in contrast to classical methods of aziridine functionalization which are based on N-centered nucleophilicity.</p><p>Initial mechanistic experiments suggest that the cross-coupling proceeds via a non-canonical mechanism involving halide-promoted ring opening, C-N bond-forming cross coupling, and aziridine reclosure. Combination of styrene and N-aminopyridinium triflate in the presence of iodobenzene diacetate (PhI(OAc)2) and MgO resulted in 1-(2-phenylaziridin-1-yl)pyridin-1-ium in 64% yield.</p><p>Aziridination could also be accomplished using N-amino-2,4,6-triphenylpyridinium tetrafluoroborate ( 2) as the nitrogen source under these conditions (42% yield of the corresponding pyridinium aziridine (3a)). During subsequent studies of C-N cross coupling (vide infra), the triphenyl derivative was found to be superior and thus we optimized the aziridination reaction with compound 2 as the pyridinium source. Examination of the impact of various catalysts, solvents, reaction temperatures, and additives (see Supporting Information Section C.1 for details) identified optimized aziridination conditions based on iodide catalysis in the presence of 4Å molecular sieves, which affords aziridine 3a in 71% yield (Figure 2).</p><p>An array of 4-substituted vinyl arenes participate in aziridination with the optimized conditions: hydrocarbyl substituents (3b and 3c), electron-donating alkoxy and Boc-protected amines (3d and 3e), as well as various electron-withdrawing substituents (3f-3k) are all well tolerated. Both meta-and ortho-substituents (3l-3p and 3q-3s, respectively) are compatible with the developed aziridination conditions and 2-vinylbenzothiophene undergoes aziridination to 3t in 60% yield. For electron-neutral and -rich substrates, 5 mol% [TBA]I is utilized; for electron deficient substrates we increased the catalyst loading to 20 mol% to achieve efficient aziridination.</p><p>Consistent with previous reports of iodide-catalyzed aziridination, functionalization of 1,2disubstituted olefins is not stereospecific: Error! Bookmark not defined.a aziridination of trans-bmethylstyrene (trans-1u) affords a 45:55 cis:trans mixture of 3u; aziridination of cis-1u affords a 35:65 cis:trans mixture of 3u. The developed conditions are effective for the aziridination on more complex substrates, including 3v-3z, which are derived from pharmaceutically relevant isatin, estrone, ibuprofen, tufnil, and probenecid. With conditions in hand to efficiently access N-pyridinium aziridines, we turned our attention to engaging these species as electrophiles in C-N coupling reactions. We envisioned a C-N cross coupling of N-pyridinium aziridines would 1) provide access to the products of formal nitrene transfer to olefins, 2) provide a rare example of an aziridine cross-coupling in which the aziridine ring remains intact, and 3) represent the first application of pyridinium electrophiles in C-N crosscoupling chemistry. We initiated our investigations by examining potential Ni-catalyzed cross coupling of N-pyridinium aziridine electrophiles with appropriate organometallic nucleophiles (i.e., Grignard reagents, organolithiums, organostannanes, and boronic acids). We identified that treatment of N-pyridinium aziridine 3a with tolyl boroxine and NiCl2(dme) in MeCN afforded Narylaziridine 5b in 36% yield. The coupling efficiency is extremely sensitive to the Ni(II) counter anion: Under identical conditions, NiCl2 provided 5b in 36% yield while NiBr2 afforded 5b in 60% yield. Ni(OAc)2, Ni(acac)2 and NiSO4 salts were completely ineffective. Optimization of the crosscoupling reaction (see Supporting Information Section C.2 for details) ultimately identified the use of NiBr2(phen) as catalyst in the presence of K3PO4 and 2,4,6-collidine provided N-tolylaziridine 5b in 79% yield (Figure 3). The catalyst loading could be reduced to 10 mol% without significant loss of yield, but further reduction to 5 mol% resulted in substantial reduction in reaction efficiency.</p><p>Figure 3. Ni-catalyzed cross-coupling of N-pyridinium aziridines with aryl boronic acids provides access to Narylaziridines, which are the products of formal transfer of aryl nitrenes to olefins. a For these substrates, K2CO3 was used in place of K3PO4. Yields reported are based on isolated products (based on 1 H NMR integration).</p><p>The developed cross-coupling conditions enable cross-coupling with simple arylboronic acids substituted in the 4-position (5a-5j) and in the 3-position (5k), but substitution in the 2-position (5l) was not tolerated. Notably, electron-neutral and -rich aryl groups can be incorporated in the N-arylaziridine efficiently, which represent specific challenges in direct nitrene transfer strategies.</p><p>Similarly, various substitutions of the pyridinium aziridine coupling partner were also tolerated</p>\n\nMeO\n<p>OMe (5m-5s). The developed aziridination reaction was also compatible with both complex boronic acids, such as those derived from thioflavin T (5t), indomethacin (5u), loratadine (5v), and chloropyramine (5w), and with complex pyridinium aziridine partners, such as those derived from estrone (5x-5y), probenecid (5z), and ibuprofen (5aa-5ab). Finally, fragment coupling reactions in which both complex boronic acids and complex pyridinium aziridine partners could be directly linked via an aziridine ring were efficient (5ac-5ad).</p><p>In addition to direct C-N coupling with boronic acids, the developed N-pyridinium aziridines participate in ring-opening chemistry to access 1,2-difunctionalization products (Figure 4).</p><p>Exposure of N-pyridinium aziridine 3a to halide sources (i.e.</p><p>[TBA]Br, [TBA]Cl, or pyridine×HF)</p><p>or H2O in the presence of BF3•OEt2 resulted in opening of the aziridine to afford haloamine derivatives 6a-6c or hydroxyamine 6d. Attempts to isolate 6a and 6b resulted in low isolated yields due to aziridine reclosure to N-pyridinium aziridine 3a (vide infra). A variety of other oxygen-, nitrogen-, and sulfur-based nucleophiles participate in aziridine opening to afford isolable aminopyridinium derivatives 6e-6j. These ring-opened compounds could be isolated as analytically pure materials and participate in efficient Ni-catalyzed cross coupling to generate 1,2aminofunctionalized compounds 7e-7j (the products of p-tolylboronic acid coupling), respectively. The ring-opened product 6g also participated in cross coupling with more complex boronic acids, as highlighted by the synthesis of 7k and 7l, which are derived from cross-coupling of ring-opened compounds with the boronic acid derived from indomethacin. Metal-catalyzed cross-coupling of aziridine often results in ring opening products. 9 In contrast, we observed Ni-catalyzed C-N coupling to generate N-arylaziridines in which the aziridine ring is conserved in the product. To better understand this unusual reaction outcome, we were interested in evaluating the mechanism of C-N bond-forming chemistry that leaves the three-membered aziridine ring intact. These investigations were guided by 1) a desire to understand the bromidespecific activity noted in our original catalyst optimization studies and 2) the observation that while treatment of 3a with [TBA]Br and BF3•OEt2 resulted in ring opening, attempts to isolate the resulting benzyl bromide 6a resulted in re-isolation of 3a, which suggested that ring-opening with bromide is reversible. This observation suggested the possibility that aziridine opening, followed by cross-coupling of an open-chain aminopyridinium intermediates, and finally aziridine reclosure may be operative (Figure 5a). Consistent with this hypothesis, treatment of aziridine 3a with NiBr2(dme) (with or without added phenanthroline) results in the observation of ring-opened compound 6a by 1 H NMR (Figure 5b). In summary, we report a strategy for the synthesis of N-aryl aziridines, which are the formal products of aryl nitrene addition to olefins. This method overcomes the inherent instability of free nitrene fragments by harnessing N-pyridinium aziridine intermediates that participate in Ni- Chem. Commun. 2019, 55, 11478-11481. (22) Of note, while BF3•OEt2 was required when [TBA]Br was used as the source of bromide, spontaneous ring-opening is observed upon addition of NiBr2, which suggest that under these conditions Ni 2+ is serving as a cooperative Lewis acid activator for aziridine opening.</p>",
"role": "user"
},
{
"content": "N-functionalized aziridines, which are both useful intermediates and are present in important synthetic targets, can be envisioned as arising from the direct addition of nitrenes (i.e., NR fragments) to olefinic substrates. The exceptional reactivity of most nitrenes, in particular with respect to unimolecular decomposition reactions, prevents general application of nitrene-transfer chemistry to the synthesis of N-functionalized aziridines. Here we describe a strategy for the synthesis of N-aryl aziridines based on 1) olefin aziridination with N-aminopyridinium reagents to afford N-pyridinium aziridines followed by 2) Ni-catalyzed C-N cross-coupling of the Npyridinium aziridines with aryl boronic acids. The N-pyridinium aziridine intermediates also participate in ring-opening chemistry with a variety of nucleophiles to afford 1,2aminofunctionalization products. Preliminary mechanistic investigations indicate aziridine crosscoupling proceeds via a noncanonical mechanism involving initial aziridine opening promoted by the bromide counterion of the Ni catalyst, C-N cross-coupling, and finally aziridine reclosure.Together, these results provide new opportunities to achieve selective incorporation of generic aryl nitrene equivalents in organic molecules.",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.2770 | [
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nRandomized trial of early developmental intervention on outcomes in children after birth asphyxia in developing countries . OBJECTIVE To determine if early developmental intervention ( EDI ) improves developmental abilities in resuscitated children . STUDY DESIGN This was a parallel group , randomized controlled trial of infants unresponsive to stimulation who received bag and mask ventilation as part of their resuscitation at birth and infants who did not require any resuscitation born in rural communities in India , Pakistan , and Zambia . Intervention infants received a parent-implemented EDI delivered with home visits by parent trainers every other week for 3 years starting the first month after birth . Parents in both intervention and control groups received health and safety counseling during home visits on the same schedule . The main outcome measure was the Mental Development Index ( MDI ) of the Bayley Scales of Infant Development , 2nd edition , assessed at 36 months by evaluators unaware of treatment group and resuscitation history . RESULTS MDI was higher in the EDI ( 102.6 ± 9.8 ) compared with the control resuscitated children ( 98.0 ± 14.6 , 1-sided P = .0202 ) , but there was no difference between groups in the nonresuscitated children ( 100.1 ± 10.7 vs 97.7 ± 10.4 , P = .1392 ) . The Psychomotor Development Index was higher in the EDI group for both the resuscitated ( P = .0430 ) and nonresuscitated children ( P = .0164 ) . CONCLUSIONS This trial of home-based , parent provided EDI in children resuscitated at birth provides evidence of treatment benefits on cognitive and psychomotor outcomes . MDI and Psychomotor Development Index scores of both nonresuscitated and resuscitated infants were within normal range , independent of early intervention .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"early developmental intervention\", \"health and safety counseling\", \"parent-implemented EDI\", \"bag and mask ventilation\"], \"Outcome\": [\"Mental Development Index ( MDI )\", \"MDI\", \"birth asphyxia\"], \"Participant\": [\"infants\", \"children\", \"birth asphyxia\", \"resuscitated\"]}",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_plos_single_doc_summ | science.scientific_lay_summarisation_plos_single_doc_summ.18155 | [
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Phosphatidylthreonine and Lipid-Mediated Control of Parasite Virulence\nArticle:\nAbstract:\nThe major membrane phospholipid classes, described thus far, include phosphatidylcholine( PtdCho), phosphatidylethanolamine( PtdEtn), phosphatidylserine( PtdSer), and phosphatidylinositol( PtdIns). Here, we demonstrate the natural occurrence and genetic origin of an exclusive and rather abundant lipid, phosphatidylthreonine( PtdThr), in a common eukaryotic model parasite, Toxoplasma gondii. The parasite expresses a novel enzyme PtdThr synthase( TgPTS) to produce this lipid in its endoplasmic reticulum. Genetic disruption of TgPTS abrogates de novo synthesis of PtdThr and impairs the lytic cycle and virulence of T. gondii. The observed phenotype is caused by a reduced gliding motility, which blights the parasite egress and ensuing host cell invasion. Notably, the PTS mutant can prevent acute as well as yet-incurable chronic toxoplasmosis in a mouse model, which endorses its potential clinical utility as a metabolically attenuated vaccine. Together, the work also illustrates the functional speciation of two evolutionarily related membrane phospholipids, i. e., PtdThr and PtdSer.\nIntroduction:\nIntracellular protozoan parasites impose a substantial threat to human and animal health. Toxoplasma gondii is one of the most prevalent protozoan parasites, infecting nearly all warm-blooded vertebrates, including humans[1]. Over the last two decades, T. gondii has also become a popular model organism to understand the biology of parasitic and free-living protozoans alike. The parasite causes debilitating opportunistic infections in immunocompromised individuals and neonates. The disease occurs by the multiplication and persistence of its acute and chronic stages, the latter of which is impervious to host immunity and existing drugs. Acute infection, hallmarked by tissue necrosis, is caused by successive rounds of lytic cycles, comprising host cell invasion, intracellular replication, and egression[1]. The entry and exit of T. gondii into and from host cells is dependent on calcium-regulated gliding motility and exocytosis of specialized secretory organelles[2, 3]. Parasites proliferating within their host cells oblige a substantial biogenesis of organelle membranes, which are composed of mainly phospholipids and neutral lipids. The typical and natural phospholipids characterized so far include phosphatidylcholine( PtdCho), phosphatidylethanolamine( PtdEtn), phosphatidylserine( PtdSer), phosphatidylinositol( PtdIns), phosphatidylglycerol, and phosphatidate[4]. Others and we have shown that T. gondii contains common eukaryotic phospholipids as well as the pathways for autonomous synthesis[5–8]. Physiological functions of phospholipids in the parasite are poorly understood however, and most of the underlying enzymes have not been characterized as yet. Moreover, despite a steadily rising interest in roles of lipids in host–pathogen interactions[9], the existence and biogenesis of divergent pathogen-specific lipids remain very much underappreciated.\nDiscussion:\nOur data reveal a natural and fairly abundant expression of PtdThr in a widespread pathogen. We also identified a novel enzyme realizing de novo synthesis of PtdThr in T. gondii. In addition, the work signifies functional speciation of two closely related lipids, i. e., PtdThr and PtdSer. Last but not least, we show a vital physiological role of PTS and PtdThr for the lytic cycle and virulence of T. gondii, which can be exploited to develop a vaccine against acute as well as chronic toxoplasmosis. Besides being the building blocks of biological membranes, phospholipids are involved in many other cellular functions. For example, one of the several roles of PtdSer is to regulate calcium signaling and exocytosis that has been recognized for more than three decades in mammalian cells[21, 22]. PtdSer controls Ca2+-triggered exocytosis by multiple mechanisms, which involve facilitating the binding of membrane-fusion protein machinery, altering the energy for membrane bending, as well as modulation of PLC-mediated IP3-dependent Ca2+ channels in the ER[23–25]. Further, anionic phospholipids, such as PtdSer, can also restrict Ca2+ slippage into the cytosol by sarcolemmal Ca2+-ATPase, which in turn increases the ion capture into the ER[26]. In T. gondii, calcium signaling is well-known to govern the consecutive events of motility, egression, and invasion by regulating exocytosis of specialized parasite organelles, notably micronemes[27, 28]. PtdThr as one of the most abundant anionic lipids regulating Ca2+ homeostasis is therefore quite conceivable. Indeed, chemically-synthesized PtdThr derivatives are much more potent inducers of mast cell secretion than PtdSer, and the presence of defined acyl chains exerts a maximal exocytosis[29]—both of these findings are consistent with the natural and dominant existence of selected PtdThr species in T. gondii. It remains also possible that a lack of PtdThr induces adaptive changes in the parasite ER, which consequently impairs the lytic cycle. The PTS mutant lacking PtdThr showed a balanced increment in PtdSer, which is reversed by genetic complementation. In line, we observed an apparent increase in the level of another major anionic lipid, PtdIns; however, only when PtdSer content was restored to normal in the double mutant deficient in PtdThr( Δtgpts/TgPSS-2HA-DD without Shield1), but not in the Δtgpts strain regardless of Shield1 in cultures( S12B Fig). Such a specific, reversible, and proportionate amplification of two other anionic lipids appears to maintain the net charge and membrane biogenesis but was entirely unable to mend the lytic cycle. It is therefore plausible that parasite has invented or selected PtdThr for realizing the lytic cycle, while satisfying the customary role of lipids in membrane biogenesis. In this context, it is worth stating that the parasite harbors a putative plant-like pathway to make threonine( www. ToxoDB. org), an amino acid otherwise essential for mammalian host cells. Our assays using stable 13C isotope of threonine demonstrated de novo synthesis of PtdThr in replicating T. gondii( S13 Fig). The isotope-labeled lipid accounted for only about 5% of the total PtdThr in the parasite, which implies a rather inefficient import of threonine by intracellular parasites and a dependence on autonomous synthesis to produce this exclusive lipid. A modest labeling of intracellular parasites with 13C-threonine resonates with a rather inefficient incorporation of radioactive precursor by extracellular parasites( not shown). Hence, it appears as though T. gondii has evolved a serine-threonine homeostasis that is quite distinct from its mammalian host. Going forward, it will be important to define biochemical features of PtdThr-deprived and PtdSer-enriched mutant membranes. It will also be critical to characterize the biophysical properties of PtdThr species and perform high-resolution imaging of fluorescent analogs to determine its distribution in the parasite organelles. Likewise, knowing the exact sites of lipid synthesis using the antibodies against endogenous PSS and PTS proteins should help define the trafficking of PtdSer and PtdThr and their relative importance for calcium homeostasis in T. gondii. Most such studies, however, demand pure preparations of PtdThr species, fluorescent lipid derivatives and antibodies, which are not available at this point. Nonetheless, having established the genetic origin and functional relevance of PtdThr in a model pathogen provides a strong basis for future research on mechanism, evolution and therapeutic potential of PTS and PtdThr. Curative importance of a metabolically-attenuated strain has also been exemplified before using an uracil-auxotroph strain[30, 31]. This work should therefore enable prospective vaccination studies using the attenuated PTS-disrupted strain, particularly against the yet-incurable and more prevalent chronic infections. In summary, our research demonstrates the natural and abundant synthesis of an exclusive lipid class, PtdThr, in a widespread protozoan parasite, which is synthesized by a unique enzyme evolved from an otherwise universal protein. We also reveal a lipid-mediated regulation of parasite-specific functions, while illustrating an evolutionary paradigm, i. e., adaptive divergence of the related phospholipids. The physiological need of PTS for the parasite makes it an attractive therapeutic and vaccine target.",
"role": "user"
},
{
"content": "Lipids are essential constituents of biological membranes , and most organisms across the tree of life use a relatively limited repertoire of lipids in their membranes . This work reveals the natural and abundant presence of an exclusive lipid phosphatidylthreonine ( PtdThr ) in Toxoplasma gondii , a ubiquitous protozoan parasite of humans and animals . PtdThr is made by a novel parasite-specific enzyme , PtdThr synthase , which has evolved from the widespread enzyme phosphatidylserine synthase . The study shows that PtdThr is required for asexual reproduction and virulence of the parasite in vivo , and a metabolically attenuated mutant strain of Toxoplasma lacking PtdThr can protect vaccinated mice against acute and currently incurable chronic infection . This discovery demonstrates adaptive “speciation” of PtdThr from an otherwise near-universal membrane lipid phosphatidylserine and reveals de novo PtdThr synthesis in T . gondii as a potential drug target .",
"role": "assistant"
}
]
|
science.scientific_papers_summarization_single_doc_arxiv | science.scientific_papers_summarization_single_doc_arxiv.76335 | [
{
"content": "Given the full text of a scientific research paper, write an abstract section for the paper. Your response should contain only the abstract without any other text.\n\nArticle text:\nthe exploration of the origin of mass and of the mechanism of electro - weak symmetry breaking represents one of the main issues on the physics agenda of future colliders .\nif the higgs mechanism is indeed responsible for providing matter and force particles with their masses , the detailed exploration of the higgs sector will most likely require the combination of data from the lhc and lepton colliders .\ntoday there are compelling indications that new physics is required beyond the standard model ( sm ) . in several sm extensions ,\na second complex scalar higgs doublet is added yielding five physical higgs bosons , two of which charged @xmath3 , instead of just one .\nthis is the case in the minimal supersymmetric sm extension ( mssm ) and also in non - supersymmetric models ( 2hdm ) .\nthe extra higgs doublet introduces an additional fundamental parameter , describing the ratio of the vacuum - expectation values of the two doublets : @xmath4 .\nthe negative results of charged higgs boson searches in the lep-2 and tevatron data and the indirect limits from the rate of the @xmath5 process have set lower bounds on its mass , @xmath6 , but the bulk of the parameter space remains still unexplored . at the lhc , charged higgs bosons can be observed but , according to present studies , only in the limited region of the parameters defined by @xmath7 , depending on its mass and detectable decay modes . in this paper , we discuss the potential of a high energy , high luminosity @xmath8 linear collider ( lc ) in the discovery of the charged higgs boson and in the study of its properties .\nsince @xmath6 is not constrained in the models and can vary from the present 78.5 gev lep-2 limit @xcite up to , and beyond , 1 tev , different collider energies need to be considered .\nwe concentrate on a tev - class lc able to deliver @xmath8 collisions at @xmath9 = 0.8 tev , such as tesla @xcite or an x - band lc @xcite , and a multi - tev lc operating at @xmath9 = 3 tev , such as clic @xcite , and discuss the experimental issues specific to the different lc parameters .\ntwo mass values have been chosen for the charged higgs boson : @xmath6 = 300 gev with moderate @xmath10 , representative of susy scenarios with a relatively light higgs sector , and @xmath6 = 880 gev with @xmath10 = 35 , as point j from a set of susy benchmarks recently proposed @xcite .\nin @xmath8 collisions , charged higgs bosons are pair produced via an intermediate photon or @xmath11 boson . at tree level\n, the production cross section for @xmath12 only depends on @xmath6 and on the centre - of - mass energy @xmath9 : @xmath13 however , in calculating the effective cross sections at high energy @xmath0 collisions , initial state radiation ( isr ) and beam - beam effects must be taken into account . because of the very small transverse dimensions of the beams at the interaction point , the electrons and positrons undergo significant radiation , in the field of the incoming beam , before collision ( beamstrahlung ) .\nthe average energy loss is of the order of 5% for @xmath9=0.8 tev at tesla but reaches 31% for @xmath9=3 tev at clic .\nwhen these effects are taken into account , the tree level cross section is folded with the luminosity spectrum . for the low values of @xmath6 the effective cross section\nis enhanced compared to the tree level cross section , while close to the kinematical threshold only a smaller fraction of the energy spectrum is available and the effective cross section is reduced as exemplified in figure [ fig : crosshh ] .\ncorrections to the @xmath14 production cross section have been computed at one loop and found to become sizeable in some region of the parameter space @xcite .\na precise determination of the cross section can thus provide additional information on model parameters . at @xmath15 ( left ) and at @xmath16 ( right ) .\nopen crosses and dashed lines show the cross section at tree level , while full circles show the effective cross section after including isr and beamstrahlung.,height=264 ] when considering only decays to sm particles , the dominant @xmath17 decay modes are those involving the heaviest quark or lepton pairs accessible , i.e. @xmath18 and @xmath19 , as shown in figure [ hdecay ] for two values of @xmath10 .\nthe dependence of the dominant branching fractions on @xmath10 can be exploited for determining this fundamental parameter of the theory . in this study\nwe consider the fully hadronic @xmath20 channel , which leads to two @xmath21 bosons and four @xmath22 quarks in the final state and provides with a direct reconstruction of @xmath6 . branching fractions for the dominant decay modes as a function of @xmath6 for two values of @xmath10.,width=415,height=340 ]\nthe simdet parametrised detector simulation @xcite has been used to account for the anticipated experimental resolutions of a lc detector .\nthe @xmath22-tagging performance , which is of major importance in this analysis , has been included , assuming an efficiency @xmath23 = 0.90 .\nthe characteristic signal final state , including four @xmath22 jets and the intermediate @xmath21 and @xmath24 mass constraints , guarantees an efficient rejection of most multi - fermion background processes .\nthe cross section of the irreducible @xmath25 background has been estimated using the comphep program @xcite at 0.8 tev and 3 tev and found to be 5.5 fb and 1.5 fb respectively .\nhadronic jets have been reconstructed using the camjet clustering algorithm , for the 0.8 tev analysis , and the lund algorithm for 3 tev , tuning the cut - off to maximise the number of eight jet events for the signal . in order to distinguish the production of charged higgs bosons from the associated background processes and to accurately measure its mass ,\nit is important to obtain a clean mass distribution of the multi - jet final states .\ntherefore only hadronic @xmath21 boson decays have been considered by removing events with significant transverse missing energy or tagged leptons .\nthe mass reconstruction has been performed as follows . in a first step ,\nthe presence of two @xmath21 bosons decaying hadronically has been tested .\nthe assignment of the four non-@xmath22 tagged jets to their correct @xmath26 pair has been done by choosing the combination which minimises the difference between the di - jet masses and the @xmath21 mass . in a second step ,\neach @xmath24 quark has been reconstructed from a @xmath21 candidate paired with one of the four @xmath22 tagged jets , taking the combination giving the invariant mass closest to the top mass .\neach of the charged higgs bosons has then been reconstructed from a @xmath24 candidate paired with one of the two remaining @xmath22 tagged jets and selecting the configuration minimising the mass difference of the two @xmath27 pairs .\nevents with no jet combination compatible with the @xmath21 or @xmath24 masses within the observed resolution have been discarded .\nan event kinematical fit has been finally applied to improve the mass resolution .\nthe fit uses energy and momentum conservation , the @xmath21 and @xmath24 mass constraints and imposes @xmath28 boson equal mass . at @xmath9\n= 0.8 tev , the reconstructed mass peak has a width of 6.2 gev with a natural @xmath3 width of 4.3 gev , for @xmath6 = 300 gev .\nthis corresponds to a mass resolution of 1.5% .\nthe signal reconstruction efficiency has been found to be 0.022 , corresponding to 149 signal with 24 background events , in a signal mass window of @xmath30 around the mass peak .\nthe good mass resolution achieved with the kinematical fit gives a signal significance @xmath31=30 ( see figure [ tesla_mass ] ) .\nthe product @xmath32 can be measured to an accuracy of 8.8% . with @xmath33 = 300 gev .\nthe histogram is normalised to an integrated luminosity of 1 @xmath34 , with a 100% branching ratio in the analysed decay mode .\nthe contribution of the @xmath1 background events is shown by the dark histograms.,height=283 ] the maximum reach in mass for a @xmath35 discovery has been studied by analysing signal samples generated at different higgs mass .\nthe largest observable higgs mass corresponds to about 350 gev , corresponding to the detection of 47 signal events , with the same number from background for 1 ab@xmath36 of data at @xmath9 = 0.8 tev . at moderate @xmath10 values , as well as in scenarios where the couplings to fermions are suppressed ,\nthe @xmath37 decay , leading to the same @xmath38 decay final state , may become sizeable . in order to study this process\n, a similar mass reconstruction procedure can be applied except for the top quark constraint being replaced by the @xmath39 one . by comparing the @xmath40 of the fit for the two hypotheses\n, the @xmath41 and @xmath37 decays can be efficiently distinguished . at a multi - tev collider\nthe decay reconstruction is complicated by the larger beamstrahlung , as mentioned above , and by the @xmath42 background @xcite overlayed to each @xmath8 collision .\nthe reconstruction procedure for the charged higgs boson follows closely that described above , but special care has been taken to make the result robust in presence of the @xmath43 background , while the broader luminosity spectrum affects the kinematic fit , as discussed below .\nthe additional hadrons generated by these @xmath43 collisions , mostly affecting the forward regions , may either be merged into the jets coming from the @xmath3 decay or result in extra jets being reconstructed .\nit is therefore important to minimise the impact from this background source on the event reconstruction . in this analysis\nonly the four leading non-@xmath22 jets have been considered , together with the @xmath22-tagged jets .\nin addition the resulting invariant masses of the intermediate states are biased towards higher values due to the additional hadron contribution .\nthis needs to be taken into account by calibrating the mass response with simulation including the @xmath43 background . due to the significant loss of energy of the colliding @xmath44 and @xmath45\n, energy and momentum conservation constraints can not be applied on the reconstructed system for the nominal @xmath9 .\ninstead the kinematical fit allows for an extra particle to be radiated but imposes its transverse momentum to be zero .\nthe kinematic fit allows to improve , by a factor of two , the resolution on the mass reconstruction for @xmath28 candidates .\nfurthermore , the use of the kinematical fit , allows to correct for the effect of the @xmath46 background resulting in a mass peak of the charged higgs boson at the position of the generated mass ( see figure [ higgs - recplots ] ) .\ninvariant mass after the kinematical fit for an integrated luminosity of 3 ab@xmath36 .\nthe @xmath1 background is shown by the hatched distribution.,height=283 ] the signal event rate has been estimated for @xmath47 , first disentangling the @xmath46 background and then assuming that the detector integrates the background from 15 bunch crossings ( bx ) .\nin the first case with an integrated luminosity is 3 ab@xmath36 and assuming br(@xmath48 ) = 1.0 , the r.m.s . of the mass peak , after the kinematical fit ,\nis 33 gev with a @xmath3 natural width of 21 gev .\n47 @xmath20 signal events are expected to be reconstructed within the @xmath49 signal mass region , corresponding to a signal efficiency of @xmath50 .\nwhen the hadronic background , integrated over 15 bx is included , the peaks of the intermediate @xmath21 and @xmath24 states are shifted towards higher masses and get significantly wider . to account for this effect ,\nthe mass windows for the reconstructed @xmath21 boson and @xmath24 quark need to be shifted and made 50% wider .\nthe fitted signal width becomes 42 gev and there are 51 @xmath51 signal events with a reconstructed mass in the signal window , corresponding to an efficiency comparable to the previous case .\nthe @xmath1 background processes contribute 24 events for 3 ab@xmath36 . by scaling these results , the estimated maximum mass reach for a @xmath35 discovery with 3 ab@xmath36 at 3 tev\nis @xmath21.0 tev . beyond discovery the properties of the charged higgs boson needs to be studied .\nthese include the mass , the production rate and the decay branching fractions .\nthe mass can be measured to an accuracy of 1% for 15 integrated bx and the product @xmath32 can be measured to an accuracy of @xmath2 20% .\nthe full reconstruction of the charged higgs boson @xmath52 multi - jet final states has been studied for two scenarios : @xmath6 = 300 gev at @xmath9 = 800 gev and @xmath6 = 880 gev with @xmath9 = 3 tev .\nthe analyses are based on the reconstruction of hadronic events with eight jets , four of which @xmath22-tagged .\na kinematical fit taking into account the @xmath21 and @xmath24 intermediate mass constraints and energy - momentum conservation has been applied to reject the multi - fermion background and optimise the mass resolution for signal events .\nthe higgs mass can be reconstructed with an accuracy of @xmath53 and the product @xmath54 can be measured to an accuracy of 8.8% for @xmath6 = 300 gev at 0.8 tev and 15% for @xmath6 = 880 gev at 3 tev . for further studies , a more efficient event selection needs to be envisaged .\nan interesting possibility is to tag the @xmath55 event by reconstructing only one @xmath48 decay .\nthis allows to increase the event selection efficiency and to study the @xmath28 decay in the hemisphere opposite to the tagged one in an unbiased way .\nthe research activity of a.f . has been supported by a marie curie fellowship of the european community programme _ improving human research potential and the socio - economic knowledge base _ under contract number hpmf - ct-2000 - 00865 .\nlep higgs wg , _ search for charged higgs bosons : preliminary combined results using lep data collected at energies up to 209 gev _ , contributed paper to the xxxvith rencontres de moriond , les arcs , france , 10 - 17 march 2001 , lhwg internal note 2001 - 1 .",
"role": "user"
},
{
"content": "in this paper , the pair production of charged higgs bosons at possible future @xmath0 linear colliders is studied . \n multi - jet final states are considered and the combinatorial , hadronic and genuine @xmath1 backgrounds are reduced thanks to a kinematical fit . \n tev - class and multi - tev linear colliders are likely to be sensitive to charged higgs bosons with masses up to @xmath2 350 gev and 1.0 tev respectively .",
"role": "assistant"
}
]
|
science.medmentions_ner | science.medmentions_ner.2456 | [
{
"content": "Extract all unique entities from this biomedical abstract. Only choose entities from these types: [\"Virus\", \"MedicalDevice\", \"BodySubstance\", \"SpatialConcept\", \"BiologicFunction\", \"ResearchActivity\", \"AnatomicalStructure\", \"ProfessionalOrOccupationalGroup\", \"HealthCareActivity\", \"BiomedicalOccupationOrDiscipline\", \"Bacterium\", \"Chemical\", \"InjuryOrPoisoning\", \"IntellectualProduct\", \"Finding\", \"ClinicalAttribute\", \"Organization\", \"Eukaryote\", \"Food\", \"BodySystem\", \"PopulationGroup\"].\n\nOutput a JSON object where keys are entity types and values are lists of extracted entities. If no entities found for a type, use empty list [].\n\nAbstract: Simultaneous Bilateral Cataract Surgery in Outreach Surgical Camps The aim of this study was to evaluate the safety and visual outcomes of simultaneous bilateral cataract surgery (SBCS) with intraocular lens implantation performed in outreach surgical eye camps. The medical records of 47 consecutive patients who underwent simultaneous bilateral small-incision cataract surgery between January 2010 and December 2015 in outreach surgical camps in rural Cameroon were reviewed. The measures included postoperative visual outcomes and intraoperative and postoperative complications. Data from 94 eyes of 47 participants (30 men, 17 women; mean age: 60.93 ± 13.58 years, range: 45-80 years) were included in this study. The presented best visual acuity (VA) was less than 3/60 in 100% of the eyes. At the 4- week follow-up, 84.04% of the eyes showed increased VA of 1 line or more (P = .001). Of these, 71 (75.53%) achieved good VA (greater than 6/18). Intraoperative or postoperative complications occurred in 19 (20.21%) eyes. The most serious intraoperative complication was a posterior capsule rupture and vitreous loss (2 patients, 2 eyes). The postoperative complications included a transient elevation in the intraocular pressure (6 eyes), chronic corneal oedema (5 eyes), iris capture (3 eyes), lens decentration (2 eyes), and hyphema (1 eye). No cases of postoperative endophthalmitis were recorded. Under the strict observation of endophthalmitis prophylaxis, SBCS is an option to reduce the cataract blindness backlog in rural areas of developing countries.",
"role": "user"
},
{
"content": "{\"AnatomicalStructure\": [\"eye\", \"eyes\", \"cataract\"], \"Bacterium\": [], \"BiologicFunction\": [\"Intraoperative\", \"corneal oedema\", \"vitreous loss\", \"intraoperative complication\", \"postoperative endophthalmitis\", \"intraoperative\", \"chronic\", \"endophthalmitis\", \"postoperative complications\", \"iris capture\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [\"visual acuity\", \"VA\"], \"Eukaryote\": [], \"Finding\": [\"transient elevation in the intraocular pressure\", \"blindness\"], \"Food\": [], \"HealthCareActivity\": [\"surgical eye camps\", \"small-incision\", \"lens decentration\", \"intraocular lens implantation\", \"surgical camps\", \"SBCS\", \"Cataract Surgery\", \"cataract surgery\", \"Surgical Camps\", \"prophylaxis\", \"follow-up\"], \"InjuryOrPoisoning\": [\"posterior capsule rupture\"], \"IntellectualProduct\": [\"medical records\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [\"men\", \"women\", \"participants\"], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"study\"], \"SpatialConcept\": [\"bilateral\", \"Bilateral\", \"Cameroon\"], \"Virus\": []}",
"role": "assistant"
}
]
|
science.chia_ner | science.chia_ner.1933 | [
{
"content": "Extract all unique entities of these types from the following clinical trial criteria: [\"Negation\", \"Observation\", \"ReferencePoint\", \"Procedure\", \"Drug\", \"Measurement\", \"Value\", \"Person\", \"Multiplier\", \"Device\", \"Qualifier\", \"Mood\", \"Temporal\", \"Condition\", \"Visit\", \"Scope\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities are found for a type, use [].\n\nText:\n\npremenopausal women\nBRCA1 carrier",
"role": "user"
},
{
"content": "{\"Condition\": [\"BRCA1 carrier\", \"premenopausal\"], \"Device\": [], \"Drug\": [], \"Measurement\": [], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [\"women\"], \"Procedure\": [], \"Qualifier\": [], \"ReferencePoint\": [], \"Scope\": [], \"Temporal\": [], \"Value\": [], \"Visit\": []}",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.3728 | [
{
"content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: Specifically, the autonomous vehicle segmentation dataset KITTI (Ros et al. 2015) is used, augmented with 49 additional train images by (Kundu et al.",
"role": "user"
},
{
"content": "Method",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.81348 | [
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Feature Lines for Illustrating Medical Surface Models: Mathematical Background and Survey \nChapter Title: Crease Lines \n1. Abstract of Cited Paper (BIB001): We propose a simple and effective method for detecting view-and scale-independent ridge-valley lines defined via first- and second-order curvature derivatives on shapes approximated by dense triangle meshes. A high-quality estimation of high-order surface derivatives is achieved by combining multi-level implicit surface fitting and finite difference approximations. We demonstrate that the ridges and valleys are geometrically and perceptually salient surface features, and, therefore, can be potentially used for shape recognition, coding, and quality evaluation purposes.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Crease lines are a set of edges where incident triangles change strongly. The dihedral angle, i.e., the angle of the normals of the corresponding incident triangles, along the edges is calculated. The edge belongs to a crease line if the dihedral angle exceeds a user-defined threshold τ. As the change of the normals is an indicator of the magnitude of the curvature, one can state that all points contribute to a feature line if the underlying absolute value of the maximum curvature exceeds a threshold: for adjacent triangles with corresponding normals n i , n j . Afterwards, all adjacent vertices which fulfill the property are connected. These feature lines need to be computed only once, since they are not view-dependent. Furthermore, these lines are only drawn along edges. Summary: Crease lines display edges where the dihedral angle is large. Strong edges are appropriately depicted, but if the object has small features, this method is not able to depict only important edges. This is caused by the local determination of the dihedral angle without concerning a neighborhood. Even smoothing the surface mesh would not deliver proper line drawings. Furthermore, this method is only able to detect features on edges. Ridges and valleys were proposed by Interrante et al. BIB001 and adapted to triangulated surface meshes by Ohtake et al. BIB002 . These feature lines are curvaturebased and not view-dependent. The computation is based on the principle curvature κ 1 as well as the associated principle curvature direction k 1 with |κ 1 | ≥ |κ 2 |. Formally, ridges and valleys are defined as the loci of points at which the principle curvatures assume an extremum in the principle direction:",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_plos_single_doc_summ | science.scientific_lay_summarisation_plos_single_doc_summ.14488 | [
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: The Multilayer Connectome of Caenorhabditis elegans\nArticle:\nAbstract:\nConnectomics has focused primarily on the mapping of synaptic links in the brain; yet it is well established that extrasynaptic volume transmission, especially via monoamines and neuropeptides, is also critical to brain function and occurs primarily outside the synaptic connectome. We have mapped the putative monoamine connections, as well as a subset of neuropeptide connections, in C. elegans based on new and published gene expression data. The monoamine and neuropeptide networks exhibit distinct topological properties, with the monoamine network displaying a highly disassortative star-like structure with a rich-club of interconnected broadcasting hubs, and the neuropeptide network showing a more recurrent, highly clustered topology. Despite the low degree of overlap between the extrasynaptic( or wireless) and synaptic( or wired) connectomes, we find highly significant multilink motifs of interaction, pinpointing locations in the network where aminergic and neuropeptide signalling modulate synaptic activity. Thus, the C. elegans connectome can be mapped as a multiplex network with synaptic, gap junction, and neuromodulator layers representing alternative modes of interaction between neurons. This provides a new topological plan for understanding how aminergic and peptidergic modulation of behaviour is achieved by specific motifs and loci of integration between hard-wired synaptic or junctional circuits and extrasynaptic signals wirelessly broadcast from a small number of modulatory neurons.\nIntroduction:\nThe new field of connectomics seeks to understand the brain by comprehensively mapping the anatomical and functional links between all its constituent neurons or larger scale brain regions[1]. The C. elegans nervous system has served as a prototype for analytical studies of connectome networks, since the synaptic connections made by each of its 302 neurons have been completely mapped at the level of electron microscopy[2, 3]. Through this approach, the C. elegans nervous system has been found to share a number of topological features in common with most other real-world networks, from human brain networks through social networks to the internet[1, 4, 5]. One well-known example is the small-world phenomenon, whereby networks are simultaneously highly clustered( nodes that are connected to each other are also likely to have many nearest neighbours in common) and highly efficient( the average path length between a pair of nodes is short)[6, 7]. Another characteristic feature of real-world networks which has attracted much attention is the existence of hubs or high-degree nodes, with many more connections to the rest of the network than expected in a random graph[8]. As in other networks, these topological features of the C. elegans connectome are thought to reflect the functional needs of the system[9, 10]. For example hubs are known to play a privileged role in coordinating functions across a distributed network[11], while the short path lengths( often mediated by the hubs) help increase the efficiency of information transfer across the network[6]. Although connectomics has primarily focused on mapping the synaptic links between neurons, it is well established that chemical synapses are only one of several modes of interaction between neurons. For example, gap junctions, which mediate fast, potentially bidirectional electrical coupling between cells, are widespread in all nervous systems. Likewise, volume transmission and neurohumoral signalling provide means for local or long-range communication between neurons unconnected by synapses. As neuromodulators released through these routes can have profound effects on neural activity and behaviour[12–14], a full understanding of neural connectivity requires a detailed mapping of these extrasynaptic pathways. In C. elegans, as in many animals, one important route of neuromodulation is through monoamine signalling. Monoamines are widespread throughout phyla, with evidence that they are one of the oldest signalling systems, evolving at least 1 billion years ago[15]. In both humans and C. elegans, many neurons expressing aminergic receptors are not post-synaptic to releasing neurons, indicating that a significant amount of monoamine signalling occurs outside the wired connectome[16]. Monoamines are known to be essential for normal brain function, with abnormal signalling being implicated in numerous neurological and psychiatric conditions[17]. In C. elegans, these monoaminergic systems play similarly diverse roles in regulating locomotion, reproduction, feeding states, sensory adaptation, and learning[16]. Clearly, if the goal of connectomics is to understand behaviourally relevant communication within the brain, extrasynaptic monoamine interactions must also be mapped, not just the network of wired chemical synapses and gap junctions. In addition to monoamines, neuropeptides are also widely used as neuromodulators in the C. elegans nervous system. C. elegans contains over 250 known or predicted neuropeptides synthesized from at least 122 precursor genes, and over 100 putative peptide receptors[18, 19]. These include homologues of several well-known vertebrate neuropeptide receptors, including those for oxytocin/vasopressin( NTR-1), neuropeptide Y( NPR-1) and cholecystokinin( CKR-2)[19]. As in other animals, neuropeptide signalling is critical for nervous system function, and frequently involves hormonal or other extrasynaptic mechanisms. This study describes a draft connectome of extrasynaptic monoamine signalling in C. elegans, as well as a partial network of neuropeptide signalling, based on new and published gene expression data. We find that the extrasynaptic connectomes exhibit topological properties distinct from one another as well as from the wired connectome. Overall, the neuronal connectome can be modelled as a multiplex network with structurally distinct synaptic, gap junction, and extrasynaptic( neuromodulatory) layers representing neuronal interactions with different dynamics and polarity, and with critical interaction points allowing communication between layers. This network represents a prototype for understanding how neuromodulators interact with wired circuitry in larger nervous systems and for understanding the organisational principles of multiplex networks.\nDiscussion:\nAlthough monoamine and neuropeptide signalling both occur extrasynaptically and act on similar timescales, the monoamine and neuropeptide networks show distinct topologies, perhaps reflecting differences in biological function. As noted previously, the monoamine network has a star-like architecture that is qualitatively different to the other network layers. This structure is reflected in the network's high disassortativity and in the low number of recurrent connections. In addition, we observed that the monoamine network contains a rich-club of highly interconnected high-degree releasing neurons, whose members are distinct from( though linked to) the rich-club of the wired connectome. Together, this structure is well-suited to the organisation of collective network dynamics, and is a useful feature given the role of monoamines in signalling physiologically important states relevant to the entire organism, such as food availability. Despite enormous differences in scale, the monoamine systems of C. elegans and mammals share a number of common properties suggestive of common network topology. As in C. elegans, mammalian brains contain a relatively small number of monoamine-releasing neurons that project widely to diverse brain regions; for example, in humans serotonin is produced by less than 100, 000 cells in the raphe nuclei, or one millionth of all brain neurons[54]. Moreover, extrasynaptic volume transmission is thought to account for much, if not most, monoamine signalling throughout the mammalian brain[55, 56]. Parallels between monoamine systems in C. elegans and larger nervous systems are not exact; for example, in C. elegans, most if not all aminergic neurons appear capable of long-distance signalling, whereas monoamines in larger nervous systems can be restricted by glial diffusion barriers[57]. Nonetheless, mammalian monoamine-releasing neurons, like their C. elegans counterparts, appear to function as high-degree broadcasting hubs with functionally and spatially diverse targets[54]. Thus, understanding how such hubs act within the context of the completely mapped wired circuitry of C. elegans, may provide useful insights into the currently unknown structures of multilayer neuronal networks in larger animals. Although the neuropeptide network has been only partially characterized, the partial network analysed here suggests it may differ in important ways from the other connectome layers, including the monoamine network. In particular, the neuropeptide layer shows strikingly high clustering, even taking into account its high density of connections, and higher reciprocity than the monoamine network. These properties suggest the neuropeptide networks are important for cohesiveness within the nervous system. Multilink analysis also identified differences between the extrasynaptic monoamine and neuropeptide networks. In both cases, a unidirectional extrasynaptic connection coincident with a reciprocal synaptic connection( motif 10) was overrepresented in the multiplex connectome. This motif is well-suited to provide feedback between linked nodes, and occurs in several microcircuits implicated in learning and memory. For neuropeptides, a second multilink motif, involving reciprocal neuromodulatory and synaptic connections coincident with a gap junction( motif 20) was even more highly overrepresented. This motif occurs in several places in the RMG-centred hub-and-spoke circuit that plays a key role in control of aggregation and arousal. As more neuropeptide systems become characterized, it is reasonable to expect additional examples of this motif will be identified; these may likewise have important computational roles in key neural circuits. While network theory has occasionally provided novel insights in C. elegans biology, more often the C. elegans wired connectome has provided a useful test-bed for validating new network theoretical concepts or their application to larger mammalian brains[10]. In recent years, multilayer complex systems have become an area of intense focus within network science, with a large number of papers dedicated to extending classical network metrics to the multilayer case and to developing new frameworks to understand the dynamical properties of multilayer systems[58]. By definition, multilayer networks contain much more information than simple monoplex networks, leading to significant data-collection challenges. In social networks, for example, large monoplex datasets have been collected describing various types of interactions between people, but these are typically disparate datasets based on different populations. Multiplex datasets combining various edge types into a number of layers are often restricted in size( the number of nodes for which data are collected) or in the choice of edges it is possible to consider( interaction types constrained by data availability)[58]. The multiplex connectome of C. elegans has the potential to emerge as a gold standard in the study of multilayer networks, much like the wired C. elegans connectome has for the study of simple monoplex networks over the last 15 years. The synaptic, gap junction, and monoamine layers already represent a relatively reliable and complete mapping of three distinct connection types. The lack of degree-degree correlation between some of these layers suggests that they are not just different facets of one true underlying network( such that each edge is essentially duplicated across all layers). Rather, it suggests that the wired and wireless layers provide distinct channels of communication with differing functional roles. We therefore expect wired and wireless connections to be coupled in functionally relevant 3-node and 4-node motif structures[59, 60], such as( for example) monoamine-based feedback loops or monoamine-regulated wired interactions. The different time-scales on which each of the layers operates are also likely to allow the emergence of interesting dynamical phenomena. Finally, the large number of distinct extrasynaptic interactions offers the scope for a more refined dataset, each aligned to the same complete set of 302 nodes. How feasible is it to obtain a complete multiplex neuronal connectome? Although the neuropeptide network described here represents only a sample of the total network, the monoamine network already represents a reasonable draft of a complete monoamine connectome. Since expression patterns for amine receptors have been based on reporter coexpression with well-characterized markers, the rate of false positives( i. e. neurons falsely identified as monoamine receptor expressing) is probably very low. In contrast, the false-negative rate( monoamine receptor-expressing cells not included in the network) is almost certainly somewhat higher. In some cases( e. g. dop-4 and dop-3 in ASH[27, 61]), reporter transgenes appear to underreport full functional expression domains; in others( e. g. ser-5) only a subset of cells expressing a particular reporter have been identified[62]. With recently developed marker strains[60, 63], it should be possible to revisit cell identification and fill in at least some of these missing gaps. In addition, other monoamines( e. g. melatonin[64]) might function as neuromodulators in C. elegans, and some of the currently uncharacterized orphan receptors in the worm genome[19] might respond to monoamines. Potentially, some of these receptors might be expressed in postsynaptic targets of aminergic neurons( in particular, those of dopaminergic and octopaminergic neurons, which are not known to express classical neurotransmitters). However, the existence of additional monoamine receptor-expressing cells also means that non-synaptic edges are almost certainly undercounted in the network. Thus, the high degree of monoamine releasing hubs–and their importance for intraneuronal signalling outside the wired connectome–is if anything understated by the current findings. In the future, it should be possible to expand the scope of the multilayer connectome to gain a more complete picture of intraneuronal functional connectivity. Obtaining extrasynaptic connectomes for larger brains, especially those of mammals, will likely be vastly more complicated than for C. elegans, due not only to the increase in size, but also the existence of additional structural and dynamical properties, such as glial barriers, cellular swelling, and arterial pulsations, all of which dynamically alter extracellular diffusion[65, 66]. In contrast, reanalysis of reporters for monoamine receptors using recently developed reference strains[60, 63] could provide a largely complete monoamine signalling network for C. elegans. A greater challenge would be to obtain a complete neuropeptide network; this would require comprehensive de-orphanization of neuropeptide GPCRs as well as expression patterns for hundreds of receptor and peptide genes. Additional layers of neuronal connectivity also remain unmapped, such as extrasynaptic signalling by insulin-like peptides, purines, and classical neurotransmitters such as acetylcholine and GABA[67–69]. Obtaining this information, while difficult, is uniquely feasible in C. elegans given the small size and precise cellular characterisation of its nervous system. Such a comprehensive multilayer connectome could serve as a prototype for understanding how different modes of signalling interact in the context of neuronal circuitry.",
"role": "user"
},
{
"content": "Connectomics represents an effort to map brain structure at the level of individual neurons and their synaptic connections . However , neural circuits also depend on other types of signalling between neurons , such as extrasynaptic modulation by monoamines and peptides . Here we present a draft monoamine connectome , along with a partial neuropeptide connectome , for the nematode C . elegans , based on new and published expression data for biosynthetic genes and receptors . We describe the structural properties of these \"wireless\" networks , including their topological features and modes of interaction with the wired synaptic and gap junction connectomes . This multilayer connectome of C . elegans can serve as a prototype for understanding the multiplex networks comprising larger nervous systems , including the human brain .",
"role": "assistant"
}
]
|
science.chemsum_single_document_summarization | science.chemsum_single_document_summarization.86070 | [
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nUrea–hydrogen peroxide prompted the selective and controlled oxidation of thioglycosides into sulfoxides and sulfones\n\nPaper sections:\nIntroduction\n<p>Organosulfur compounds such as sulfides, sulfoxides and sulfones are useful intermediates for the construction of highly functionalized natural products [1,2]. Sulfur moieties are found in several therapeutically important molecules that possess antibacterial, antifungal, anti-ulcer, anti-atherosclerotic, antihypertensive activities, etc. [3,4]. Sulfur compounds also play an important role in carbohydrate synthesis. Thioglycosides, glycosyl sulfoxides and sulfones have been widely used as glycosyl donors in oligosaccharide synthesis which can be activated under mild reaction conditions [5][6][7][8][9][10]. Glycosyl sulf-oxide donors usually provide excellent anomeric selectivity during the synthesis of various glycosyl linkages not only in solution phase but also in solid-phase oligosaccharide synthesis [6][7][8][9]11]. Glycosyl sulfones were also used as donors in the preparation of various Cand Olinked oligosaccharides and functionalized glycols [8,9,12]. In addition, glycosyl sulfones are known to be potential glycosyltransferase inhibitors [13].</p><p>Glycosyl sulfoxides and sulfones are prepared from the corresponding sulfides using various oxidizing reagents [5][6][7]10]. Al- though a number of oxidation methods were developed for the oxidation of simple organic sulfides to corresponding sulfoxides and sulfones [14][15][16], there are only limited reports available for the preparation of glycosyl sulfoxides and sulfones from corresponding thioglycosides [5][6][7][17][18][19][20][21][22][23]. Moreover, there is no report available where a given oxidant is suitable for controlled oxidation of thioglycosides to glycosyl sulfoxides and sulfones selectively by altering the reaction conditions. It is also observed that thioglycoside oxidation suffers from low yields, poor selectivity (i.e., sulfoxide vs sulfone), use of inconvenient reaction conditions and expensive oxidants, intolerance of other oxidation susceptible functional groups, etc. Thus, developing a mild and efficient method for the controlled oxidation of sulfides to corresponding glycosyl sulfoxides and sulfones, is of great interest.</p><p>The utility of hydrogen peroxide-solid adducts in organic synthesis is well explored [24]. Most of them are found to be stable which can be easily handled and stored. One such solid adduct is urea-hydrogen peroxide (UHP) which is considered to be a safer and efficient alternative to high concentrated aqueous hydrogen peroxide solution [25]. In addition, UHP is also commercially available, inexpensive and nontoxic. The application of UHP as oxidant is well explored in various solution-as well as solid-phase organic syntheses [25][26][27][28]. In fact, we have recently reported the oxidation of arylboronic acids into corresponding phenols by using UHP as a selective oxidizing agent [29]. In continuation to our effort in developing green methodologies [29][30][31][32][33], here we disclose an efficient and practical method for the conversion of glycosyl sulfides into sulfoxides and sulfones in a selective and controlled manner using urea-hydrogen peroxide in acetic acid.</p>\n\nResults and Discussion\n<p>Initially, phenyl-2,3,4,6-tetra-O-acetyl-1-thio-β-D-glucopyranoside (1) was chosen as a substrate for the optimization study and oxidation was performed in various solvents at different temperatures in the presence of urea-hydrogen peroxide (UHP) (Table 1). Polar aprotic solvents such as dichloromethane and acetonitrile gave a negligible amount of corresponding sulfoxide (1a) while no sulfone (1b) was detected at room temperature even after 6 hours (Table 1, entries 1 and 2). However, protic solvents such as methanol, ethanol, tert-butanol and acetic acid were found to be relatively efficient media for the oxidation when compared with dichloromethane and acetonitrile (Table 1, entries 3-6). Among them, acetic acid gave 37% of the glycosyl sulfoxide (1a) after 6 h at room temperature with one equiv of UHP (Table 1, entry 6) while alcoholic solvents gave a low yield. When we increased the amount of UHP to 1.5 equiv, the reaction provides only 64% of the desired sulfoxide at room temperature (Table 1, entry 7). Therefore, the reaction was further investigated at elevated temperatures using 1.5 equiv of UHP (Table 1, entries 8 and 9) in acetic acid. Interestingly, the reaction was driven to completion with the desired sulfoxide (1b) in 92% yield within 2 h at 60 °C (Table 1, entry 9). It is also worth noting that less than 5% of the corresponding sulfone was detected in the crude product by 1 H NMR under these conditions.</p><p>Considering the importance of glycosyl sulfones, we further investigated the suitable conditions for the direct oxidation of sulfide to sulfone using UHP in acetic acid. For this, we have tried the reactions with an increased amount of UHP and elevated temperature (Table 1, entries 10-12). It was observed that with 1.5 to 2.0 equiv of UHP at 80 °C, the reaction yields a mixture of sulfoxide 1a and sulfone 1b (Table 1, entries [10][11] in different ratio. However, by increasing the amount of UHP to 2.5 equiv, sulfide 1 is fully converted to the corresponding sulfone 1b in an excellent yield, i.e., 93% in 10 h at 80 °C (Table 1, entry 12).</p><p>With optimized conditions in hand (Table 1, entries 9 and 12), a controlled oxidation of various glycosyl sulfides to corresponding sulfoxides and sulfones was studied with urea-hydrogen peroxide in acetic acid (Table 2). For this study, a series of αand β-thioglycosides, 1-19 were initially prepared by using literature procedures (see Supporting Information File 1). In addition, structurally diverse aglycone moieties were selected in order to study the breadth and scope of the current methodology. Initially, the oxidation of O-acetylated and benzoylated phenyl and p-tolyl thioglucopyranosides was examined (Table 2, entries 1-4). These aryl sulfides underwent oxidation very efficiently to provide the corresponding sulfoxides 1a-4a in excellent yields, i.e., 85-93% under optimized conditions. Similarly, corresponding glycosyl sulfones 1b-4b were also achieved in 91-94% yield by simply altering the reaction conditions as described in the optimization study.</p><p>We further examined the oxidation of O-acetyl-(Ac) and benzoyl-(Bz) protected benzyl thioglucopyranosides, which showed a good selectivity during the controlled oxidation with UHP and provided >87% and >89% of the desired sulfoxides (5a and 6a) and sulfones (5b and 6b), respectively (Table 2, entries 5 and 6). Similar to phenyl and benzyl sulfides, alkyl sulfides such as ethyl, n-hexyl and cyclohexyl glycosyl sulfides were also successfully oxidized in a controlled and selective manner with equal efficiency (Table 2, entries 7-12).</p><p>Having studied the oxidation of electron deficient thioglucopyranosides, we further investigated the oxidation of O-benzyl protected 4-methylphenyl thioglycoside 13 under optimized conditions (Table 2, entry 13). This substrate was found to be more reactive than O-acetylated and benzoylated thioglycosides and gave the sulfoxide in a good yield within 1.5 h. However, corresponding sulfone was obtained in a moderated yield due to instability which undergoes partial amount of decomposition.</p><p>In general, olefins functional groups are known to undergo epoxidation or dihydroxylation with different oxidizing agents (e.g. m-CPBA, t-BuOOH, oxone, etc.) [34]. Therefore, the scope of this methodology was further investigated with oxidation of allyl group protected thioglycoside 14 (Table 2, entry 14). Remarkably, allyl groups were found to be very stable during the oxidation while sulfide underwent selective oxidation to corresponding sulfoxide and sulfone in 89% and 91%, respectively. Further, we have studied the oxidation of protected glucosamine thioglycoside (Table 2, entry 15) which provided 91% of sulfoxide and 82% of sulfone.</p><p>The scope of the oxidation reaction was subsequently investigated with other monosaccharides such as galacto and mannothioglycosides under optimized conditions (Table 2). Similar to glucopyranosides, galacto and mannothioglycosides 16-19 were successfully oxidized to corresponding sulfoxides and sulfones in good to excellent yields (Table 2, entries [16][17][18][19]. Overall, sulfoxides were achieved within the time period of 1.5-2.5 h while sulfones were obtained in 6-11 h.</p>\n\nConclusion\n<p>In conclusion, we have developed a practical method for the selective and controlled oxidation of thioglycosides to corresponding glycosyl sulfoxides and sulfones using the stable, inexpensive and commercially available oxidant urea-hydrogen peroxide (UHP). Glycosyl sulfoxides were achieved using 1.5 equiv of UHP at 60 °C while sulfones were achieved using 2.5 equiv of UHP at 80 °C. Remarkably, oxidation susceptible olefin functional groups were found to be stable during the sulfide oxidation.</p>",
"role": "user"
},
{
"content": "A practical method for the selective and controlled oxidation of thioglycosides to corresponding glycosyl sulfoxides and sulfones is reported using urea-hydrogen peroxide (UHP). A wide range of glycosyl sulfoxides are selectively achieved using 1.5 equiv of UHP at 60 °C while corresponding sulfones are achieved using 2.5 equiv of UHP at 80 °C in acetic acid. Remarkably, oxidation susceptible olefin functional groups were found to be stable during the oxidation of sulfide.",
"role": "assistant"
}
]
|
science.ncbi_ner | science.ncbi_ner.273 | [
{
"content": "Extract all unique entities of these types from the following abstract: [\"Disease\"]\n\nOutput a JSON object with entity types as keys and lists of entities as values.\n\nAbstract:\nHuman deficiency of the sixth component of complement in a patient with meningococcal meningitis and no haemostasis abnormality. A case of human complete C6 deficiency is reported. The patient, a 31 year old white male, was seen on the occasion of an isolated episode of meningococcal meningitis. Serum complement hemolytic and bactericidal activities were lacking and could be restored to normal by addition of appropriate amounts of purified C6. No hemostatic abnormalities were observed..",
"role": "user"
},
{
"content": "{\"Disease\": [\"hemostatic abnormalities\", \"haemostasis abnormality\", \"deficiency of the sixth component of complement\", \"C6 deficiency\", \"meningococcal meningitis\"]}",
"role": "assistant"
}
]
|
science.bioasq_yesno_qa | science.bioasq_yesno_qa.356 | [
{
"content": "Based on the following biomedical documents, answer the question with either yes or no.\n\nQuestion: Is p100 the precursor protein molecule of the NF-kappaB transcription factor subunit p50?\n\nContext: We previously reported that alymphoplasia (aly/aly) mice, which have a natural loss-of-function mutation in the Nik gene, which encodes a kinase essential for the processing of p100 to p52 in the alternative nuclear factor-κB (NF-κB) pathway, show mild osteopetrosis with an increase in several parameters of bone formation:\nProteolytic processing of the nuclear factor (NF)-kappaB2 precursor protein p100 generates the active NF-kappaB2 subunit p52, which in turn transcriptionally up-regulates p100 expression.\nThe mammalian Rel/NF-kappaB family of transcription factors, including RelA, c-Rel, RelB, NF-kappaB1 (p50 and its precursor p105), and NF-kappaB2 (p52 and its precursor p100), plays a central role in the immune system by regulating several processes ranging from the development and survival of lymphocytes and lymphoid organs to the control of immune responses and malignant transformation.\nNF-kappaB functions as a hetero- or homo-dimer which can be formed from five NF-kappaB subunits, NF-kappaB1 (p50 and its precursor p105), NF-kappaB2 (p52 and its precursor p100), RelA (p65), RelB and c-Rel.\nThe non-canonical pathway based on processing of NF-kappaB2 precursor protein p100 to generate p52 plays a critical role in controlling B cell function and lymphoid organogenesis.\nProcessing of NF-kappaB2 precursor protein p100 to generate p52 is tightly controlled, which is important for proper function of NF-kappaB.\nProcessing of NF-kappa B2 precursor protein p100 to generate p52 is tightly regulated.\nProcessing of the NF-kappaB2 precursor protein p100 to generate p52 is an important step of NF-kappaB regulation.\nTargeted disruption of the Rel/NF-kappaB family members NF-kappaB2, encoding p100/p52, and RelB in mice results in anatomical defects of secondary lymphoid tissues.\nHere, we show that in T cells infected with the human T-cell leukemia virus (HTLV), IKKalpha is targeted to a novel signaling pathway that mediates processing of the nfkappab2 precursor protein p100, resulting in active production of the NF-kappaB subunit, p52.\nnfkb2 encodes two members of the NF-kappa B/Rel family of proteins: p52 and p100. The p100 polypeptide has been proposed to serve as a precursor of p52, which corresponds to the N-terminal half of p100.\nIn most cells, small amounts of p52 are produced relative to the levels of p100, unlike the usually balanced production of nfkb1-derived p50 and p105.\nThe alternative or second pathway proceeded via NF-kappaB-inducing kinase (NIK)-, IKKalpha-, and protein synthesis-dependent processing of the inhibitory NF-kappaB2 p100 precursor protein to the p52 form and resulted in a delayed but sustained activation of primarily RelB-containing NF-kappaB dimers.\nIn one exceptional case, generation of the p50 subunit of the transcriptional regulator NF-kappaB, the precursor protein p105 is processed in a limited manner: the N-terminal domain yields the p50 subunit, whereas the C-terminal domain is degraded\nProteolytic processing of the p105 precursor (NF-kappa B1) generates the p50 subunit of NF-kappa B\np105 (NFKB1) acts in a dual way as a cytoplasmic IkappaB molecule and as the source of the NF-kappaB p50 subunit upon processing\nThe p50 subunit of NF-kappa B is derived from the amino terminus of a 105 kilodalton precursor\nRegulation of the transcription factor NF-kappaB involves proteasome-mediated processing of the NF-kappaB1 p105 precursor protein, which generates the p50 subunit of NF-kappaB\nThis effort identified NF-kappaB1 (p105), an atypical IkappaB molecule and the precursor of NF-kappaB subunit p50\nNF-kappaB functions as a hetero- or homo-dimer which can be formed from five NF-kappaB subunits, NF-kappaB1 (p50 and its precursor p105), NF-kappaB2 (p52 and its precursor p100), RelA (p65), RelB and c-Rel\nThe mammalian Rel/NF-kappaB family of transcription factors, including RelA, c-Rel, RelB, NF-kappaB1 (p50 and its precursor p105), and NF-kappaB2 (p52 and its precursor p100), plays a central role in the immune system by regulating several processes ranging from the development and survival of lymphocytes and lymphoid organs to the control of immune responses and malignant transformation",
"role": "user"
},
{
"content": "no",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.18705 | [
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nThe utilization of social media material in journalistic workflows is increasing, demanding automated methods for the identification of mis- and disinformation. Since textual contradiction across social media posts can be a signal of rumorousness, we seek to model how claims in Twitter posts are being textually contradicted. We identify two different contexts in which contradiction emerges: its broader form can be observed across independently posted tweets and its more specific form in threaded conversations. We define how the two scenarios differ in terms of central elements of argumentation: claims and conversation structure. We design and evaluate models for the two scenarios uniformly as 3-way Recognizing Textual Entailment tasks in order to represent claims and conversation structure implicitly in a generic inference model, while previous studies used explicit or no representation of these properties. To address noisy text, our classifiers use simple similarity features derived from the string and part-of-speech level. Corpus statistics reveal distribution differences for these features in contradictory as opposed to non-contradictory tweet relations, and the classifiers yield state of the art performance.\n\nCited Abstract(s):\n[1]: Understanding entailment and contradiction is fundamental to understanding natural language, and inference about entailment and contradiction is a valuable testing ground for the development of semantic representations. However, machine learning research in this area has been dramatically limited by the lack of large-scale resources. To address this, we introduce the Stanford Natural Language Inference corpus, a new, freely available collection of labeled sentence pairs, written by humans doing a novel grounded task based on image captioning. At 570K pairs, it is two orders of magnitude larger than all other resources of its type. This increase in scale allows lexicalized classifiers to outperform some sophisticated existing entailment models, and it allows a neural network-based model to perform competitively on natural language inference benchmarks for the first time.\n\n[2]: Detecting conflicting statements is a foundational text understanding task with applications in information analysis. We propose an appropriate definition of contradiction for NLP tasks and develop available corpora, from which we construct a typology of contradictions. We demonstrate that a system for contradiction needs to make more fine-grained distinctions than the common systems for entailment. In particular, we argue for the centrality of event coreference and therefore incorporate such a component based on topicality. We present the first detailed breakdown of performance on this task. Detecting some types of contradiction requires deeper inferential paths than our system is capable of, but we achieve good performance on types arising from negation and antonymy.",
"role": "user"
},
{
"content": "The RTE-3 benchmark dataset is the first resource that labels paired text snippets in terms of 3-way RTE judgments [2] , but it is comprised of general newswire texts. Similarly, the new large annotated corpus used for deep models for entailment [1] labeled text pairs as Contradiction are too broadly defined, i.e., expressing generic semantic incoherence rather than semantically motivated polarization and mismatch that we are after, which questions its utility in the rumor verification context.",
"role": "assistant"
}
]
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.