dataset
stringclasses 45
values | id
stringlengths 17
64
| messages
listlengths 2
2
|
|---|---|---|
science.pico_ner
|
science.pico_ner.1516
|
[
{
"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:\nMode of ventilation during cardiopulmonary bypass does not affect immediate postbypass oxygenation in pediatric cardiac patients . STUDY OBJECTIVE To investigate the impact of different modes of ventilation during cardiopulmonary bypass ( CPB ) on immediate postbypass oxygenation in pediatric cardiac surgery . DESIGN Prospective , randomized clinical trial . SETTING University hospital . PATIENTS 50 pediatric patients ( 18 girls , 32 boys ) , aged 4 months to 15 years , undergoing elective repair of congenital heart disease . INTERVENTIONS Patients were randomized to receive one of 5 modes of ventilation during bypass . Groups 1 and 2 received high-frequency/low-volume ventilation with 100 % ( group 1 ) or 21 % oxygen ( group 2 ) . Groups 3 and 4 received continuous positive airway pressure of 5 cm H ( 2 ) O with 100 % ( group 3 ) or 21 % oxygen ( group 4 ) ; and in group 5 , each patient 's airway was disconnected from the ventilator ( passive deflation ) . MEASUREMENTS Blood gas analysis and spirometry data were recorded 5 minutes before chest opening , 5 minutes before inducing bypass , 5 minutes after weaning from bypass , and 5 minutes after chest closure . MAIN RESULTS There were no differences in Pao ( 2 ) values among the 5 groups studied and at the different time points . Lung compliance was higher 5 minutes before bypass in group 1 versus group 5 ( 34 +/- 13 mL/cm H ( 2 ) O vs 20 +/- 9 mL/cm H ( 2 ) O ; P = 0.048 ) . CONCLUSIONS Mode of ventilation during CPB did not affect immediate postbypass oxygenation .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"each patient \\u0027s airway was disconnected from the ventilator ( passive deflation )\", \"cardiopulmonary bypass ( CPB )\", \"21 % oxygen\", \"cardiopulmonary bypass\", \"modes of ventilation during\", \"Mode of\", \"ventilation\", \"one of 5 modes of ventilation during\", \"bypass\", \"high-frequency/low-volume ventilation with 100 %\", \"Mode of ventilation during\", \"continuous positive airway pressure of 5 cm H ( 2 ) O with 100 %\"], \"Outcome\": [\"Lung compliance\", \"Pao ( 2 ) values\", \"Blood gas analysis and spirometry data\"], \"Participant\": [\"pediatric cardiac patients .\"]}",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.15852
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nThe inference of network topologies from relational data is an important problem in data analysis. Exemplary applications include the reconstruction of social ties from data on human interactions, the inference of gene co-expression networks from DNA microarray data, or the learning of semantic relationships based on co-occurrences of words in documents. Solving these problems requires techniques to infer significant links in noisy relational data. In this short paper, we propose a new statistical modeling framework to address this challenge. The framework builds on generalized hypergeometric ensembles, a class of generative stochastic models that give rise to analytically tractable probability spaces of directed, multi-edge graphs. We show how this framework can be used to assess the significance of links in noisy relational data. We illustrate our method in two data sets capturing spatio-temporal proximity relations between actors in a social system. The results show that our analytical framework provides a new approach to infer significant links from relational data, with interesting perspectives for the mining of data on social systems.\n\nCited Abstract(s):\n[1]: The ubiquity of mobile devices and the popularity of location-based-services have generated, for the first time, rich datasets of people's location information at a very high fidelity. These location datasets can be used to study people's behavior - for example, social studies have shown that people, who are seen together frequently at the same place and at the same time, are most probably socially related. In this paper, we are interested in inferring these social connections by analyzing people's location information, which is useful in a variety of application domains from sales and marketing to intelligence analysis. In particular, we propose an entropy-based model (EBM) that not only infers social connections but also estimates the strength of social connections by analyzing people's co-occurrences in space and time. We examine two independent ways: diversity and weighted frequency, through which co-occurrences contribute to social strength. In addition, we take the characteristics of each location into consideration in order to compensate for cases where only limited location information is available. We conducted extensive sets of experiments with real-world datasets including both people's location data and their social connections, where we used the latter as the ground-truth to verify the results of applying our approach to the former. We show that our approach outperforms the competitors.\n\n[2]: This paper examines the location traces of 489 users of a location sharing social network for relationships between the users' mobility patterns and structural properties of their underlying social network. We introduce a novel set of location-based features for analyzing the social context of a geographic region, including location entropy, which measures the diversity of unique visitors of a location. Using these features, we provide a model for predicting friendship between two users by analyzing their location trails. Our model achieves significant gains over simpler models based only on direct properties of the co-location histories, such as the number of co-locations. We also show a positive relationship between the entropy of the locations the user visits and the number of social ties that user has in the network. We discuss how the offline mobility of users can have implications for both researchers and designers of online social networks.\n\n[3]: Data collected from mobile phones have the potential to provide insight into the relational dynamics of individuals. This paper compares observational data from mobile phones with standard self-report survey data. We find that the information from these two data sources is overlapping but distinct. For example, self-reports of physical proximity deviate from mobile phone records depending on the recency and salience of the interactions. We also demonstrate that it is possible to accurately infer 95 of friendships based on the observational data alone, where friend dyads demonstrate distinctive temporal and spatial patterns in their physical proximity and calling patterns. These behavioral patterns, in turn, allow the prediction of individual-level outcomes such as job satisfaction.",
"role": "user"
},
{
"content": "Using the special characteristics of time-stamped social interactions or geographical co-occurrences, a second line of works has additionally accounted for . Studying data on time-stamped proximities of students at MIT campus, the authors of [3] show that the temporal and spatial distribution of proximity events allows to infer social ties with high accuracy. In [2] , a model that captures location diversity, regularity, intensity and duration is used to predict social ties based on co-location events. An entropy-based approach taking into account the diversity of interactions' locations has been used in [1] .",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_plos_single_doc_summ
|
science.scientific_lay_summarisation_plos_single_doc_summ.18738
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Fine-Tuning of the Kaposi’s Sarcoma-Associated Herpesvirus Life Cycle in Neighboring Cells through the RTA-JAG1-Notch Pathway\nArticle:\nAbstract:\nKaposi’s sarcoma( KS)-associated herpesvirus( KSHV) is an oncogenic pathogen that displays latent and lytic life cycles. In KS lesions, infiltrated immune cells, secreted viral and/or cellular cytokines, and hypoxia orchestrate a chronic pro-lytic microenvironment that can promote KSHV reactivation. However, only a small subset of viruses spontaneously undergoes lytic replication in this pro-lytic microenvironment while the majority remains in latency. Here, we show that the expression of the Notch ligand JAG1 is induced by KSHV-encoded replication and transcription activator( RTA) during reactivation. JAG1 up-regulation activates Notch signaling in neighboring cells and prevents viral lytic replication. The suppression of JAG1 and Notch1 with inhibitors or small interfering RNA promotes lytic replication in the presence of RTA induction or under conditions of hypoxia. The underlying mechanism involves the Notch downstream effector hairy and enhancer of split 1( Hes1), which directly binds lytic gene promoters and attenuates viral lytic gene expression. RTA interacts with lymphoid enhancer-binding factor 1( LEF1), disrupts LEF1/Groucho/TLE suppressive complexes and releases LEF1 to activate JAG1 expression. Taken together, our results suggest that cells with viral lytic replication can inhibit KSHV reactivation in neighboring cells through an RTA-JAG1-Notch pathway. These data provide insight into the mechanism by which the virus maintains the balance between lytic and latent infection in the pro-lytic tumor microenvironment.\nIntroduction:\nKaposi’s sarcoma( KS)-associated herpesvirus( KSHV) is a large double-stranded DNA virus with a biphasic life cycle[1]. In KS lesions, KSHV latently infects most tumor cells to maintain viral DNA[2, 3], evade host immunosurveillance[4], and promote cellular proliferation[5]. The viruses in a small subset of infected cells spontaneously switch into the lytic replication cycle from latency, expressing viral lytic products such as replication and transcription activator( RTA), open reading frame K8( K-bZIP), human herpesvirus 8 interleukin-6( vIL6), open reading frame 45( ORF45) and open reading frame 59( ORF59)[6–9]. The lytic viruses may benefit KS pathogenesis by re-infecting the neighboring cells[10] and releasing pro-inflammatory or angiogenic cytokines in a paracrine manner[9]. Previous studies suggest that extrinsic factors such as hypoxia[11–14], oxidative stress[15, 16], and inflammation[17, 18], can trigger the change from latency to lytic replication in viruses. Furthermore, KS tissues perfuse with slit-like vessels and a large number of infiltrated inflammatory cells exhibit a pro-lytic milieu that potentially promotes KSHV to be reactivated from latency[19]. The latently infected cells are likely to become stressed, and the virus can be stimulated to undergo lytic replication associated with tumor progression. However, reactivation is a rare event in KS tissues, with approximately 1–3% of spindle cells displaying lytic replicative markers[19]. In this regard, the controlled lytic replication observed in KS tissues suggests its pathological importance for disease development. However, the mechanism by which KSHV regulates this process remains unclear. The Notch signaling pathway is critical for KS development. The Notch ligands JAG1 and Dll4, and the Notch receptors Notch1–4 are highly expressed in KS tumor cells[20]. Notch signaling is evolutionarily conserved in most multicellular organisms. It enables short-range communication between the cells of metazoans through physical contact[21] and regulates many cellular functions including proliferation, death, and differentiation[21–24]. It is unique for its ability to specify the fate of the adjacent cells within an equivalence group into different( sometimes opposite) directions by cell-to-cell communication and subsequently altered gene expression, known as lateral inhibition[25–27]. Aberrant gain or loss of Notch function is linked to a wide range of human disorders, including developmental disorders and cancers[28, 29]. Based on these data, we hypothesized that Notch may specify the fate of viruses in infected cells. In the present study, we found that KSHV RTA up-regulates the Notch ligand JAG1 by interacting with LEF1 and triggers Notch activation in neighboring cells. The activated Notch inhibits KSHV reactivation in those neighboring cells. We found that the inhibitory effect of Notch on KSHV reactivation largely relies on the HES/HEY family, which could directly bind and inhibit a number of major KSHV lytic gene promoters. Our study describes a novel regulatory process by which KSHV specifies latency and reactivation in virus-infected cells. Our findings provide insight into the mechanism by which a minority of viruses undergoes reactivation, while the majority maintains a persistent latent infection in KS tissues.\nDiscussion:\nKSHV mainly displays latency in spindle cells; however, in a small subset of infected cells, viruses spontaneously switch into the lytic phase. The latency program plays a primary role in KSHV associated tumorigenesis, whereas lytic replication allows the virus to spread throughout the host and induces an inflammatory environment during pathogenesis[19, 53]. Many factors contribute to form a pro-lytic microenvironment during disease progression. To our knowledge, all KS lesions contain significant numbers of cells like B cells, plasma cells, CD4+ T cells, CD8+ T cells, monocytes, and high levels of IFN-gamma[19, 54], which forms a tumor microenvironment likely to induce KSHV reactivation. Aside from the inflammatory conditions, hypoxia is another common factor that arises in tumor, which reactivates KSHV from latency[11–14, 55]. Clinical observation also proved that KS tumors often occur on body parts with low oxygen supply such as feet, mouth and arms[19]. Reactive oxygen species( ROS) is another KSHV reactivation inducer[15, 16]. The higher amount of ROS is a common factor generated by tumor metabolic alteration[56]. Similar with other tumors, KS displays Warburg-like effect which leads global metabolic changes[57–60] and stresses the cells via ROS production, thereby reactivates KSHV from latency. KS is a common cancer in AIDS patients and organ transplant patients with immunosuppression. HIV-1 infection has been demonstrated to trigger KSHV reactivation in PEL cells, probably by activating RTA promoter[61, 62]. Moreover, HIV-1 Tat protein might be an important factor potentially to initiate lytic cycle of KSHV[63]. With immunosuppression, a lot of other pathogens took this opportunity to infect patients. Studies showed that super-infection with other pathogens like HSV-1, HHV-6, cytomegalovirus( CMV) causes KSHV reactivation[64–66]. These factors are common in KS lesions, although reactivation is a rare event in tissue with 1 to 3% of spindle cells displaying lytic replicative markers[6–9, 19, 67]. This indicates the presence of specific intrinsic regulatory strategies that allow KSHV to fine-tune the balance between latency and reactivation in virus infected cells. Our study provides a novel regulation mode for this phenomenon( Fig 8). Previously, we showed TLE2 was a novel RTA binding protein which independently inhibited the ability of RTA to auto-activate its own promoter[52]. Grouch/TLE co-repressors did not bind DNA directly; instead, they recruited a diverse profile of transcription factors, including Hes, LEF1/TCF and c-Myc etc. to elicit its functions[68]. The repressive complex formed by Grouch/TLE and TCF/LEF could be broken down by β-catenin induced by Wnt activation[46]. JAG1 promoter contains several LEF1 binding motifs and can be activated via interaction with LEF1[46]. As RTA dramatically up-regulated JAG1 expression( Fig 1A–1D) and RTA co-precipitated with LEF1( Fig 7G), RTA therefore released LEF1 from TLE/LEF1 suppressive complex, which subsequently recruited other co-activators to drive JAG1 expression( Fig 7D, 7E and 7K). Membrane-bound JAG1 activated Notch signaling in trans by binding with Notch receptors in neighboring cells( Fig 2B–2D). Hes1, as downstream effectors of Notch signaling, was a potent transcriptional repressor which bound directly with DNA. Hes1 binding motifs could be found in the promoters of various lytic gene promoters including RTA. Thus Hes1 induced by activated Notch broadly suppressed KSHV lytic reactivation in neighboring cells signaled by RTA expressing cells( Fig 8). This provides a possible explanation for the fact that lytic replication of KSHV occurs only in a small portion of cells within a relatively consistent tumor microenvironment. Aberrant Notch activation was previously reported in KSHV-infected cells and KS tumor samples[20, 69–74]. The Notch ligands JAG1 and Dll4 and the Notch receptors Notch1–4 are functionally overexpressed in KS tumor cells[20]. KSHV-encoded viral FLICE-inhibitory protein( vFLIP) induces JAG1 expression in NF-κB dependent manner, and vGPCR up-regulates Dll4 by activating ERK in LEC cells[69]. Other KSHV ORFs( LANA, RTA, and v-IL6) also regulate Notch components[70]. The activated Notch plays a pivotal role in KSHV induced pathogenesis. In LEC, KSHV-induced Notch activation down-regulates prospero homeobox protein 1( PROX1), a master regulator of lymphatic development, through Hey1 and drives LECs to reprogram into BECs[71]. JAG1 and Dll4 up-regulated by vFLIP and vGPCR induce membrane-type-1 matrix metalloproteinase( MT1-MMP)-dependent endothelial-to-mesenchymal transition( EndMT), facilitating the invasion of surrounding connective tissues by the infected cells[72]. The up-regulated JAG1 and Dll4 also lead to cellular quiescence in neighboring cells[69, 72]. In previous work, we showed that LANA stabilizes intracellular activated Notch( ICN) by competing with ICN for binding with Sel10( a negative regulator of Notch) and maintains the enhanced proliferation and angiogenesis of KSHV-infected cells[73, 74]. In addition to its involvement in the pathogenesis of diseases, Notch signaling plays a critical role in asymmetric cell division and fate determination, which is reflected by distinct gene expression among cells. In signal receiving cells, Notch is activated by the binding of Notch receptors to membrane-anchored Notch ligands on neighboring cells( signal donor cells) where Notch signaling is inhibited by the ligand intracellular domain and other regulatory factors[27, 75], which is known as lateral inhibition. Our results suggest that asymmetric gene expression induced by lateral inhibition affects the behavior of KSHV in infected cells. Notch distinguishes the lytic phase of KSHV in “RTA already expressing” cells and “RTA ready to express” cells, as evidenced by the co-culture assay showing that cells stably expressing RTA inhibit lytic gene activation in cells induced to express RTA at a later time. KSHV usurps this pathway to strategically control the amounts of free-floating viruses and the apoptosis of infected cells, thus evading the host defense mechanisms. The results of the present study suggest a novel role of Notch signaling in virus fate determination. Our results showed the cell-to-cell connection in the monolayer 2D adherent cell culture. In the paper published by Ojala group[72], Cheng and coauthors established a 3D culturing system that better mimics cell-to-cell interactions occurring in vivo. KSHV infection in 3D environment induced a dramatic outgrowth of capillary sprouts and mesenchymal phenotype transition( EndMT). The EndMT sprouting process was Notch dependent as Notch inhibitors suppressed sprouting of KSHV infected LEC( K-LEC) spheroids. Interestingly, the majority of K-LEC spheroids displayed higher numbers of nuclear punctate LANA signal and increased viral DNA levels of the cells while lytic genes could also be detected in the cells, in agreement with KSHV infection in vivo. Thus, in 3D environment or in vivo conditions, activated Notch not only facilitates the interaction of cells but also improves maintenance of viral episomes, probably achieved by in trans reactivation inhibition. In summary, Notch is implicated in KSHV-associated malignancy and contributes to KS development in multiple phases. On one hand, activated Notch promotes key events in tumor progression, such as sustained proliferation, angiogenesis, and EndMT-mediated cell invasion[72–74]; on the other hand, the fine-tuned Notch signaling stringently controls viral reactivation, enabling long-term persistence of KSHV in host cells. Our work not only provides a molecular mechanism to explain how the balance between viral lytic replication and latency is maintained in infected cells, but also suggests that this fine-tuned regulation is an important evolutionary strategy utilized by KSHV to survive in the host.",
"role": "user"
},
{
"content": "KSHV infected cells display significant heterogeneity in viral lytic replication within the universal pro-lytic inflammatory milieu , suggesting that the balance between latency and reactivation is carefully regulated . This fine-tuned regulatory mechanism is essential for KSHV to persist in the host and drive cells to malignancy . In the present study , we show that KSHV can usurp the Notch signaling pathway to inhibit the viral lytic life cycle in neighboring cells . Notch signaling in surrounding cells can be activated through an RTA-JAG1-Notch pathway initiated by cells in which KSHV is reactivated . Activated Notch inhibits KSHV reactivation through its downstream effector Hes1 . These findings suggest that the ability of Notch to determine the fate of adjacent cells is hijacked by KSHV to maintain its life cycle , providing a mechanistic explanation for the phenomenon by which only a small fraction of viruses enters lytic replication in the common pro-lytic microenvironment .",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.19695
|
[
{
"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\nMuch is being learned about clinical outcomes for adult COVID-19 patients with underlying chronic conditions; however, there is less coverage on how the COVID-19 pandemic impacts the management of chronic medical conditions, such as asthma, in children and youth. Asthma is a common chronic medical condition in children that is uniquely susceptible to changes brought on by COVID-19. Sudden dramatic changes in the environment, medical practice, and medication use have altered the asthma management landscape with potential impacts on asthma outcomes. In this paper, we review how changes in transportation and travel patterns, school attendance, physical activity, and time spent indoors, along with changes in health care delivery since the start of the pandemic, all play a contributing role in asthma control in children. We review potentially important influences of asthma control in children during the COVID-19 pandemic worthy of further study.",
"role": "user"
},
{
"content": "[\"Prevention\"]",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_plos_single_doc_summ
|
science.scientific_lay_summarisation_plos_single_doc_summ.12450
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Congenital Heart Disease–Causing Gata4 Mutation Displays Functional Deficits In Vivo\nArticle:\nAbstract:\nDefects of atrial and ventricular septation are the most frequent form of congenital heart disease, accounting for almost 50% of all cases. We previously reported that a heterozygous G296S missense mutation of GATA4 caused atrial and ventricular septal defects and pulmonary valve stenosis in humans. GATA4 encodes a cardiac transcription factor, and when deleted in mice it results in cardiac bifida and lethality by embryonic day( E) 9. 5. In vitro, the mutant GATA4 protein has a reduced DNA binding affinity and transcriptional activity and abolishes a physical interaction with TBX5, a transcription factor critical for normal heart formation. To characterize the mutation in vivo, we generated mice harboring the same mutation, Gata4 G295S. Mice homozygous for the Gata4 G295S mutant allele have normal ventral body patterning and heart looping, but have a thin ventricular myocardium, single ventricular chamber, and lethality by E11. 5. While heterozygous Gata4 G295S mutant mice are viable, a subset of these mice have semilunar valve stenosis and small defects of the atrial septum. Gene expression studies of homozygous mutant mice suggest the G295S protein can sufficiently activate downstream targets of Gata4 in the endoderm but not in the developing heart. Cardiomyocyte proliferation deficits and decreased cardiac expression of CCND2, a member of the cyclin family and a direct target of Gata4, were found in embryos both homozygous and heterozygous for the Gata4 G295S allele. To further define functions of the Gata4 G295S mutation in vivo, compound mutant mice were generated in which specific cell lineages harbored both the Gata4 G295S mutant and Gata4 null alleles. Examination of these mice demonstrated that the Gata4 G295S protein has functional deficits in early myocardial development. In summary, the Gata4 G295S mutation functions as a hypomorph in vivo and leads to defects in cardiomyocyte proliferation during embryogenesis, which may contribute to the development of congenital heart defects in humans.\nIntroduction:\nCongenital heart defects( CHD) are the most prevalent of all human birth defects with an estimated incidence of 6–8 per 1, 000 live births[1],. Defects of cardiac septation, which encompass atrial and ventricular septal defects, may occur as an isolated defect or in combination with other cardiac malformations. Defects of atrial and ventricular septation are the most common type of CHD and account for 50% of all cases of CHD. If unrepaired, these defects result in ventricular dilation and heart failure, pulmonary overcirculation leading to pulmonary vascular disease, atrial enlargement predisposing to atrial arrhythmias and ultimately a decreased life expectancy. The etiology for atrial and ventricular septal defects is multifactorial with genetic and environmental factors playing important roles[3],[4]. Monogenic etiologies for atrial and ventricular septal defects have been primarily discovered by studying large families with autosomal dominant forms of septal defects using traditional linkage approaches[5],[6]. The first genetic etiology for atrial septal defects was the disovery that mutations in the transcription factor, TBX5, are a cause of septation defects in the setting of Holt-Oram syndrome, which is characterized by cardiac and upper limb malformations[7]. Tbx5 haploinsufficiency in mice accurately mimics the phenotype found in patients with Holt-Oram syndrome[8]. Mutations in the cardiac transcription factor, NKX2-5, were identified in families who primarily exhibited non-syndromic atrial septal defects and atrioventricular conduction abnormalities[9]. While targeted deletion of Nkx2-5 in mice causes developmental arrest during heart tube looping, haploinsufficiency of Nkx2-5 results in only subtle defects of atrial septation[10],[11]. Similarly, mutations in the cardiac transcription factor, GATA4, have also been linked to atrial and ventricular septal defects[12],[13],[14],[15],[16]. Gata4 is necessary for normal cardiac development as mice with targeted deletion of Gata4 display embryonic lethality and defects in ventral morphogenesis associated with failure to form a single ventral heart tube[17],[18]. Subsequent studies have demonstrated that Tbx5, Nkx2-5, and Gata4 interact to regulate distinct developmental processes during heart development[19],[20],[21]. While many of the human mutations are predicted to result in haploinsufficiency, little is understood about the underlying mechanism by which reduced transcription factor dosage causes defects in cardiac septation. We reported a large pedigree with autosomal dominant congenital heart disease that was associated with a mutation of a highly conserved glycine residue to a serine at codon 296( G296S)[12]. The affected family members had a spectrum of cardiac phenotypes, primarily atrial and ventricular septal defects and pulmonary valve stenosis[12]. In vitro experiments demonstrated that the mutant Gata4 protein had a greatly reduced affinity for its binding element with an associated decrease in transcriptional activity and disrupted a novel interaction between Gata4 and Tbx5[12]. Subsequently, two other families have been reported with a GATA4 G296S mutation, and affected members display a similar phenotype of atrial septal defects and incompletely penetrant pulmonary valve stenosis[22]. While Gata4 has been shown to be important for several critical processes during heart development[23],[24],[25],[26], the pathogenesis of heart malformations in humans with the G296S missense mutation in GATA4 is not as well understood. To identify the functional deficits of the GATA4 G296S mutation in vivo, we generated and characterized transgenic mice that contain the orthologous G295S mutation in the Gata4 murine locus. Here, we show that homozygous Gata4 G295S knock-in( ki) mice( Gata4 G295Ski/ki) display normal ventral morphogenesis but early embryonic lethality after the linear heart tube stage. Histologic analysis demonstrates a thin ventricular myocardium in the Gata4 G295Ski/ki embryos, which is associated with a cardiomyocyte proliferation defect. Molecular characterization of these mutant embryos demonstrates that expression of Gata4 target genes is decreased in the heart. Echocardiographic examination of heterozygote( Gata4 G295Ski/wt) mice found subtle atrial septal defects and semilunar valve stenosis. Embryonic cardiomyocytes from heterozygote mice display cardiac proliferation deficits. Consistent with functional deficits for the Gata4 G295S mutation, compound heterozygote mice harboring only a single Gata4 G295S mutant allele in the early myocardium recapitulated the phenotype seen in Gata4 G295Ski/ki embryos. These studies demonstrate the generation of a mouse model for human cardiac malformations and suggest that abnormal cardiomyocyte proliferation may contribute to human atrial and ventricular septal defects caused by mutations in GATA4.\nDiscussion:\nThe GATA4 G296S mutation has been associated with atrial septal defects and pulmonary valve stenosis in multiple human families[12],[22]. In vitro studies suggested that GATA4 G296S mutant protein resulted in specific functional deficits including diminished DNA binding affinity, reduced transcriptional activity and loss of a protein-protein interaction with TBX5. Here, we have generated a knock-in mouse harboring the corresponding G295S mutation in Gata4. Phenotypic characterization of these mice demonstrate that the Gata4 G295S mutation functions as a hypomorph in vivo as evidenced by the Gata4 G295Ski/ki embryos displaying prolonged survival as compared to Gata4-null embryos and decreased expression of Gata4 transcriptional target genes. Consistent with the cardiac phenotype seen in humans with GATA4 mutations, Gata4 G295Ski/wt mice also display cardiac abnormalities. In addition, we found that the G295S mutation of Gata4 results in defects of embryonic cardiomyocyte proliferation both in vitro and in vivo. These findings suggest a potential role for abnormal cardiomyocyte proliferation in the development of atrial and ventricular septal defects caused by mutations in GATA4. The G295S mutation in Gata4 may result in multiple functional deficits in the embryonic heart. Mice homozygous for the Gata4 G295S mutation suffer embryonic lethality before E10. 5, which limited our analysis to early myocardial development and precluded analysis of potential functional deficits at later stages of heart development. Conditional deletion of Gata4 in the endocardium results in defective endocardial-mesenchymal transition( EMT) and hypoplastic endocardial cushions[26]. In addition, we have previously shown the G295S mutation in Gata4 inhibits an interaction with Tbx5 and Gata4-Tbx5 compound heterozygotes display atrioventricular septal defects[12],[21]. It remains unclear if the GATA4 G296S mutation has a role in formation of the endocardial cushions but one family member with the G296S mutation did have an atrioventricular septal defect[12] and other non-related individuals with GATA4 mutations have atrioventricular septal defects[13]. In our analysis of potential cell lineage deficits for the Gata4 G295S protein, we did find that enGata4G295S mice, where the endocardium/endothelium expresses only the mutant protein, have somewhat hypocellular endocardial cushions and display partial lethality by post-natal day 10. This finding suggests that the Gata4 G295S mutation may have functional deficits in the endocardium, potentially by disrupting EMT but additional study is required( Figure 7). A role for Gata4 and Tbx5 in the endocardium for formation of the atrial septum by regulation of endothelial nitric oxide synthase( Nos3) has been proposed, but the early lethality of the Gata4 G295Ski/ki embryos did not allow for analysis of this pathway[42]. While this early lethality precluded examination of the development of the cardiac outflow tract and semilunar valves in the Gata4 G295Ski/ki embryos, the Gata4 G295Ski/wt heterozygotes did develop stenosis of the semilunar valves. This phenotype along with recent publications demonstrating bicuspid aortic valve and aortic valve stenosis in Gata5-null and Gata4;Gata5 compound heterozygote mice suggest that endocardial specific deficits of the G296S protein may contribute to the aortic and pulmonary valve stenosis[43],[44]. The phenotypic analysis of Gata4 G295Ski/ki mice demonstrates that the Gata4 G295 mutant allele is not a loss of function allele. Initial human genetic studies demonstrated that haploinsufficiency of GATA4 resulted in cardiac malformations and there was a possibility that the Gata4 G295 was a null allele[45]. Our data demonstrate that the G295S mutation in Gata4 results in a selective loss of some Gata4 functions. Specifically, the Gata4 G295S protein is able to activate downstream target genes in the developing endoderm but not in the cardiac mesoderm. Potential mechanisms for this difference may lie in the inability of Gata4 G295S protein to interact with Tbx5 in the mesoderm to activate downstream targets or that Gata4 may function as a transcriptional co-activator in the endoderm and DNA binding is not necessary. The findings from the conditional deletion crosses, as discussed above, also support that the G295S mutant protein has defined functional deficits in different cell lineages. Additional investigation is needed to identify all the potential functions of Gata4 and then determine which are loss with the Gata4 G295S mutation. Cardiomyocyte proliferation is critical for normal cardiac development, and our findings provide evidence that the Gata4 G295S mutation results in myocardial hypoplasia due to diminished cardiac proliferation. This phenotype is at least partially mediated by reduced expression of cyclin D2, a member of the D-cyclin family of cell cycle regulators. Mice lacking any single D-cyclin are viable and do not display obvious cardiac defects[46]. However, compound mutation of all three D-cyclin genes results in embryonic lethality due to cellular proliferation defects, including reduced cardiomyocyte cell division[47]. Our data demonstrate that both homozygote and heterozygote Gata4 G295Ski mice display cardiomyocyte proliferation deficits and suggest that this is a possible mechanism for the atrial septal defects seen in these mice. The generation of the Gata4 G295Ski mice provides a mouse model to study human congenital heart defects. This mouse model will be of significant value to study genetic and environment modifiers for cardiac malformations along with allowing for a more mechanistic understanding of the embryologic basis of septation and valvular defects. While the dosage sensitivity of cardiac transcription factors for normal cardiac morphogenesis is generally well accepted, this mouse model demonstrates that specific mutations may have limited functional deficits. The Gata4 G295Ski mice which encodes a partially functional mutant protein, offers us a tool to define these abnormalities in vivo.",
"role": "user"
},
{
"content": "Cardiac malformations occur due to abnormal heart development and are the most prevalent human birth defect . Defects of atrial and ventricular septation are the most common type of congenital heart defect and are the result of incomplete closure of the atrial and ventricular septa , a process required for formation of a four-chambered heart . The molecular mechanisms that underlie atrial and ventricular septal defects are unknown . We previously published a highly penetrant autosomal dominant mutation ( G296S ) in GATA4 , which was associated with atrial and ventricular septal defects in a large kindred . The disease-causing mutation has a spectrum of biochemical deficits affecting both DNA binding and protein–protein interactions . Here , we report the generation and phenotypic characterization of mice harboring the orthologous mutation in Gata4 ( G295S ) . While homozygous mutant mice display embryonic lethality and cardiac defects , the phenotype is less severe than Gata4-null mice . A subset of Gata4 G295S heterozygote mice display a persistent interatrial communication ( patent foramen ovale ) and stenosis of the semilunar valves . Molecular characterization of the mutant mice suggests that the Gata4 G295S mutant protein results in diminished expression of Gata4 target genes in the heart and functional deficits in cardiomyocyte proliferation . Thus , cardiomyocyte proliferation defects may contribute to defects of cardiac septation found in humans with GATA4 mutations .",
"role": "assistant"
}
] |
science.chemdner_ner
|
science.chemdner_ner.1341
|
[
{
"content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nNovel diaryl ureas with efficacy in a mouse model of malaria. Exploration of triclosan analogs has led to novel diaryl ureas with significant potency against in vitro cultures of drug-resistant and drug-sensitive strains of the human malaria parasite Plasmodium falciparum. Compound 18 demonstrated EC(50) values of 37 and 55 nM versus in vitro cultured parasite strains and promising in vivo efficacy in a Plasmodium berghei antimalarial mouse model, with >50% survival at day 31 post-treatment when administered subcutaneously at 256 mg/kg. This series of compounds provides a chemical scaffold of novel architecture, as validated by cheminformatics analysis, to pursue antimalarial drug discovery efforts.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"diaryl ureas\"]}",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.5434
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nHigher inductive types are inductive types that include nontrivial higher-dimensional structure, represented as identifications that are not reflexivity. While work proceeds on type theories with a computational interpretation of univalence and higher inductive types, it is convenient to encode these structures in more traditional type theories with mature implementations. However, these encodings involve a great deal of error-prone additional syntax. We present a library that uses Agda’s metaprogramming facilities to automate this process, allowing higher inductive types to be specified with minimal additional syntax.\n\nCited Abstract(s):\n[1]: This paper presents a type theory in which it is possible to directly manipulate @math -dimensional cubes (points, lines, squares, cubes, etc.) based on an interpretation of dependent type theory in a cubical set model. This enables new ways to reason about identity types, for instance, function extensionality is directly provable in the system. Further, Voevodsky's univalence axiom is provable in this system. We also explain an extension with some higher inductive types like the circle and propositional truncation. Finally we provide semantics for this cubical type theory in a constructive meta-theory.\n\n[2]: Cubical type theory provides a constructive justification to certain aspects of homotopy type theory such as Voevodsky's univalence axiom. This makes many extensionality principles, like function and propositional extensionality, directly provable in the theory. This paper describes a constructive semantics, expressed in a presheaf topos with suitable structure inspired by cubical sets, of some higher inductive types. It also extends cubical type theory by a syntax for the higher inductive types of spheres, torus, suspensions, truncations, and pushouts. All of these types are justified by the semantics and have judgmental computation rules for all constructors, including the higher dimensional ones, and the universes are closed under these type formers.\n\n[3]:",
"role": "user"
},
{
"content": "Ongoing work on cubical type theories [1] [3] [2] provides a computational interpretation of univalence and HITs. We strenuously hope that these systems quickly reach maturity, rendering our code generator obsolete. In the meantime, however, these systems are not yet as mature as Agda.",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.1723
|
[
{
"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 immunogenicity of a cluster specific immunotherapy in children with bronchial asthma and mite allergy . BACKGROUND Cluster specific immunotherapy ( SIT ) is a modern form of allergen immunotherapy allowing safe administration of high allergen doses in a short time interval compared to classic SIT . In the current study , we investigated the safety profile and immunological effect of cluster SIT in children with allergic asthma due to house dust mite allergy . METHODS A total of 34 children ( 6-18 years ) with allergic asthma were assigned to cluster ( n = 22 ) or classic SIT ( n = 12 ) . To achieve a maintenance dose of allergen extract , cluster patients received 14 injections of house dust mite allergen within 6 weeks , whereas the classic SIT group received 14 injections within 14 weeks . Safety was monitored by recording adverse events . Immunogenicity was measured by specific IgG ( Mite ) and IgG4 ( Mite ) , by antibody-blocking properties on basophil activation , and by the T cell subset transcription factors Foxp3 , T-bet , and GATA-3 . RESULTS There were no significant differences in local and systemic side effects between the two groups . In the cluster group , serum levels of specific IgG ( Mite ) ( p < 0.001 ) and specific IgG4 ( Mite ) ( p < 0.001 ) significantly increased after 8 weeks , while it took 12 weeks in the classic SIT group . These data were confirmed by blocking CD63 expression as well as release of cysteinyl leukotrienes after in vitro basophil stimulation . No differences in transcription factor expression were found in the two groups . CONCLUSION Cluster SIT is safe in children . Additionally , our data demonstrated an even more rapid induction of specific immune tolerance . Cluster SIT is an attractive alternative to conventional up-dosing schedules with fewer consultations for the patients .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"Cluster specific immunotherapy ( SIT )\", \"classic SIT group received 14 injections\", \"14 injections of house dust mite allergen within 6 weeks\", \"cluster specific immunotherapy\"], \"Outcome\": [\"and immunogenicity\", \"serum levels of specific IgG ( Mite )\", \"safety profile and immunological effect\", \"Immunogenicity\", \"CD63 expression\", \"transcription factor expression\", \"specific IgG4 ( Mite )\", \"local and systemic side effects\", \"Safety\", \"induction of specific immune tolerance\"], \"Participant\": [\"classic SIT ( n = 12 ) .\"]}",
"role": "assistant"
}
] |
science.acl_arc_intent_classification
|
science.acl_arc_intent_classification.262
|
[
{
"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:\nNone\n\nContext before:\nIn addition, we consider several types of lexical features (LexF) inspired by previous work on agreement and disagreement (Galley et al., 2004; Misra and Walker, 2013). The MI approach discovers the words that are highly associated with Agree/Disagree categories and these words turn to be useful features for classification. Compared to the all unigrams baseline, the MI-based unigrams improve the F1 by 4% (Agree) and 2% (Disagree) (Table 6).\n\nCitation:\nIn addition , we consider several types of lexical features ( LexF ) inspired by previous work on agreement and disagreement ( Galley et al. , 2004 ; Misra and Walker , 2013 ) .\n\nContext after:\n⢠Sentiment Lexicon (SL): Two features are designed using a sentiment lexicon (Hu and Liu, 2004) where the first feature represents the number of times the Callout and the Target contain a positive emotional word and the second feature represents the number of the negative emotional words. ⢠Initial unigrams in Callout (IU): Instead of using all unigrams in the Callout and Target, we only select the first words from the Callout (maximum ten). The assumption is that the stance is generally expressed at the beginning of a Callout. We used the same MI-based technique to filter any sparse words.",
"role": "user"
},
{
"content": "Motivation",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_pubmed
|
science.scientific_papers_summarization_single_doc_pubmed.48430
|
[
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\nthe respiratory tract is the site most commonly infected with opportunistic organisms in aids patients , and respiratory failure is the leading cause of death in these cases . in the 1980s , the vast majority of cases of respiratory failure were determined to have been the result of pneumocystis carinii pneumonia ( pcp ) .\nhowever , aids patients now commonly receive antibiotic prophylaxis against pcp , and thus acute respiratory failure is attributed to pcp in only two - thirds of current cases . however , the incidence of acute respiratory failure induced by infection with other organisms is being increasingly encountered1 ) .\ninitial clinical symptoms and radiographic evidence of cryptococcal pneumonia in aids patients may be initially similar to those of pcp , but the mortality associated with cryptococcal pneumonia is much higher than that associated with pcp . therefore , the rapid diagnosis of cryptococcal pneumonia , particularly in immunocompromised hosts , including aids and cancer patients , is crucial2 , 3 ) . here , we present a case of disseminated cryptococcal infection , including acute respiratory distress syndrome associated with cryptococcal pneumonia , cryptococcemia , and cryptococcal meningitis , in an aids patient\na 36-year - old man was admitted to our hospital , with a 30-day history of fever and headache .\nthe patient , a homosexual mexican , had entered korea 4 months prior to admission .\none year prior to admission , the patient had experienced a mild fever , diarrhea , and 20 kg of weight loss . on admission ,\nthis patient 's body temperature was 38.5 , and his blood pressure was 130/80 mmhg .\nthe patient 's breath sounds were clear , and his heart sounds were regular , with no murmur .\nthe patient 's white blood cell count was 1,580/l , total protein was 26 mg / dl , sugar was 17 mg / dl , and intracranial pressure was 23 cmh2o .\nthe patient was diagnosed with hiv ( human immunodeficiency virus ) infection via serum western blotting assay . the total number of cd4 + t lymphocytes and cd8 + t lymphocytes were 7 and 60/l .\ncryptococcus neoformans was isolated on cultures of blood and cerebrospinal fluid . on the day of admission , an initial chest roentgenogram revealed no specific abnormal findings , and the patient was treated with intravenous amphotericin b and ceftriaxone as empirical therapy for possible bacterial and fungal infection . on the patient 's 4th day in our hospital , a chest roentgenogram revealed diffuse interstitial infiltrations in both lung field , and computerized tomography revealed diffuse reticulonodular infiltration and a ground - glass appearance in both perihilar areas , suggesting pcp or cryptococcal pneumonia ( figure 1 ) . on the patient 's 6th day in our hospital ,\nbronchoalveolar lavage and transbronchial lung biopsy were conducted via bronchoscopy , and antiretroviral therapy ( didanosine , lamivudine , nelfinavir ) was initiated .\nresults of methenamine silver staining of the bronchoalveolar lavage fluid revealed no specific abnormal findings . after the patient 's 6th day in our hospital , the patient 's breathing difficulties and arterial hypoxemia worsened . on the patient 's 9th day in the hospital , his arterial oxygen pressure and saturation level were measured at 32.7 mmhg and 61.6% , and mechanical ventilation was initiated .\ncultures of the patient 's blood and csf samples , obtained at the time of admission , revealed cryptococcus neoformans . pathological findings and the special stain results of lung biopsy specimens , obtained at the time of bronchoscopy , also revealed cryptococcal pneumonia ( figures 2 , 3 ) .\nthis patient died on his 14th day in our hospital , as the result of acute respiratory failure , associated with cryptococcal pneumonia and disseminated cryptococcosis .\nacute respiratory failure with cryptococcal pneumonia in aids patients is associated with disseminated disease and a high level of mortality .\nhowever , the diagnosis of cryptococcal pneumonia in its early periods is rather difficult , as the initial clinical symptoms and radiographic signs of cryptococcal pneumonia in aids patients are practically indistinguishable from those of pneumocystis carinii ( p. carinii ) pneumonia , which is the most commonly encountered cause of acute respiratory failure in aids patients2 - 4 ) .\ncryptococcus neoformans ( c. neoformans ) is the fourth most commonly recognized life - threatening infection - causing organism in aids patients , after cytomegalovirus ( cmv ) , p. carinii , and mycobacterium avium intracellulare ( mai)5 ) .\np. carinii , cmv , and mai are known to induce diffuse interstitial pneumonias in aids patients . c. neoformans is also known to induce diffuse interstitial pneumonia in aids patients .\nthe initial clinical manifestations of cryptococcal pneumonia in aids patients are similar to those seen in cases of p. carinii pneumonia , but the mortality associated with cryptococcal pneumonia is much higher .\ncryptococcal pneumonia - induced acute respiratory failure is associated with a mortality rate of nearly 100% , and most of those patients progress to disseminated cryptococcosis . due to the rapidity with which cryptococcal pneumonia progresses to acute respiratory failure in aids patients ,\nit is also quite difficult to distinguish cryptococcal pneumonia from p. carinii pneumonia , bacterial pneumonia , and miliary tuberculosis , as cryptococcal pneumonia is characterized by a variety of radiological findings , including interstitial infiltrations , alveolar consolidation , a ground - glass appearance , miliary nodules , lymphadenopathy , and pleural effusion6 , 7 ) . when an aids patient contracts pneumonia and the results of an induced sputum examination are negative , the accepted course of action is to administer an early check - up , including a bronchoscopy with bronchoalveolar lavage , in order to detect a possible mycotic infection which may prove fatal8 ) .\nthe possibility of mycotic infections , such as cryptococcal pneumonia , must also be investigated in cases in which steroid therapy is administered for the treatment of p. carinii pneumonia9 , 10 ) .\nthe above case represents an example of disseminated cryptococcosis which , in its early stages , manifested the classic symptoms of encephalomeningitis , in a patient in whom cryptococcus neoformans was cultured in cerebrospinal fluid and blood cultures .\nour patient died as the result of galloping pneumonia with acute respiratory insufficiency , although he was being treated with a course of intravenous amphotericin b. this patient exhibited disseminated cyptococcosis , but the diagnosis presented difficulties , as the radiological findings revealed perihilar density and a ground - glass appearance , both of which are also classic characteristics of p. carinii pneumonia . in this patient\nan aids patient suffering from cryptococcus neoformans , like this one in this study , often exhibits the same early clinical patterns and radiological findings observed in patients suffering from p. carinii pneumonia .\nhowever , early diagnosis and treatment are crucial , particularly due to the much higher fatality rate associated with cryptococcus neoformans1 - 3 , 11 ) .",
"role": "user"
},
{
"content": "a 36-year - old homosexual mexican man was admitted to our hospital , with a 30-day history of fever and headache . upon cerebrospinal fluid examination , \n the patient 's white blood cell count was 1,580/l , total protein was 26 mg / dl , sugar was 17 mg / dl , and his intracranial pressure was 23 cmh2o . \n the patient was diagnosed with hiv ( human immunodeficiency virus ) infection by serum western blotting . \n cryptococcus neoformans was isolated in cultures of the patient 's blood and cerebrospinal fluids . \n chest computerized tomography revealed diffuse reticulonodular infiltration and a ground - glass appearance in both perihilar regions , suggestive of either pneumocystis carinii pneumonia or cryptococcal pneumonia . on the patient 's 6th day in our hospital , \n bronchoalveolar lavage and transbronchial lung biopsy were conducted via bronchoscopy , and a pathologic examination of lung biopsy specimens revealed signs of cryptococcal pneumonia.this patient died on his 14th day in our hospital , as the result of acute respiratory failure , associated with cryptococcal pneumonia and disseminated cryptococcosis .",
"role": "assistant"
}
] |
science.chemsum_single_document_summarization
|
science.chemsum_single_document_summarization.83515
|
[
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nCoumarin triazabutadienes for fluorescent labeling of proteins\n\nPaper sections:\n\n<p>Fluorescence imaging is a crucial tool for measuring complex systems in biology, from surfaces, to cells, to whole organisms. While fluorescent proteins are boon to this area, the ability to covalently modify proteins with small molecules remains essential for many modern imaging experiments.[1] At the outset, a goal of this work was to develop a fluorophore that would have a minimal impact on both the size and structure of the target protein. The attachment of the fluorophore using an aryl diazonium ion to tyrosine (Scheme 1a) was seen as potentially useful because: 1) the amino acid side chain would become part of the fluorophore, and, 2) the resulting modification would be charge neutral. In assessing these criteria, coumarin-based fluorophores garnered attention due to their small size, and proven utility for imaging.</p><p>The modification of tyrosine with aryl diazonium ions via electrophilic aromatic substitution is one of the oldest selective bioconjugation strategies, and one that is still used in modern applications.[2, 3] An early concern was that azobenzenes are often found in fluorescent quencher motifs,[4] but upon investigation there are examples of azobenzene-coumarin compounds that have fluorescent properties.[5, 6] One example in particular that offered encouragement was a reported coumarin-derived aryl diazonium ion that acted as a covalent inhibitor of acetyl choline esterase which became fluorescent upon modification of tyrosine in the enzymatic pocket.[5] Moreover, there are marked difference observed in fluorescence between solution-phase and solid immobilized azo dyes.[7] While promising for the desired application, challenges of storage and delivery exist with aryl diazonium ions, often requiring in situ generation. Our recent work masking aryl diazonium ions as triazabutadienes led us to investigate their usage as a convenient source of this fluorophore-generating moiety.[8] Herein, we report the synthesis and utility of several coumarin triazabutadienes that can be environmentally, or photochemically triggered to release aryl diazonium ions to fluorescently label proteins.</p><p>Our previous work with triazabutadienes, a functional group that can release aryl diazonium ions in protic environments, led us to hypothesize that a fluorophorogenic diazonium ion could be protected and liberated as desired. Prior to the synthesis of the triazabutadiene coumarin compound, we sought to test the reactivity of the diazonium ion that would be released. Diazonium salt, 1 (Scheme 1b), was synthetized from its respective amino coumarin precursor following standard diazotization conditions. We confirmed fluorescence of the adduct by making the p-cresol derivative (shown Scheme 1b). While the quantum yield was low (Φ = 0.025), we moved forward to evaluate if there was sufficient fluorescence to be of use in labeling proteins. Using bovine serum albumin (BSA) as a model protein, we examined the pH dependence of the reaction between freshly made 1 and the protein (Scheme 1a). Consistent with previous reports on diazonium ion chemistry on proteins, we observed increased labeling as pH increased.[3] Optimal labeling occurred at pH 8, but even at pH 5, substantial labeling was present (Figure S1 and S2).</p><p>Confident that a coumarin-derived fluorophore could be conjugated onto proteins and visualized, we synthesized a bis-mesityl variant of the triazabutadiene scaffold (Figure 1a). We hypothesized that it would have a good combination of synthetic ease, reactivity, and long-term stability. Triazabutadiene 2 was synthesized from the corresponding azido coumarin (3), and N-heterocyclic carbene precursor 4 in good yield (Figure 1a). To confirm that 2 could release 1 and label proteins, BSA was treated with 2 at various pH. We observed substantial labeling only occurring at pH lower than 6, with intensity increasing as pH decreases (Figure 1b). These findings are consistent with the hypothesis that 1 is released only under acidic conditions. Rate data from NMR studies suggested that 2 is more stable to presence of acid than the simple benzene-substituted triazabutadiene (Figure S3). While the resulting electron deficient aryl diazonium ion is not fluorescent, the triazabutadiene does have mild fluorescence, with an observed quantum yield of 0.004. We attribute this fluorescence to the electron-donating nature of the carbene-derived half. These observations are consistent with this class of fluorophores where electron-donation at the 7 position is essential for robust fluorescence. The labeling of proteins with 2 is not fluorogenic, but we were encouraged by the level of labeling and tested general applicability of the probe. As a result of the mild fluorescence of 2, extra caution was taken to ensure that labeling was the result of diazonium ion release, and not simply non-specific binding.</p><p>Recognizing that low pH is not appropriate for all protein labeling studies and lacks applicability in typical biological environments, we employed an alternative approach for release of the coumarin aryl diazonium at neutral pH. To accomplish this, we explored the use of photochemistry of the triazabutadiene scaffold to release the diazonium ion. This had previously been reported by both our group and others to facilitate release of aryl diazonium for protein labeling via increasing the basicity of the compound.[9] We were relieved to find that the presence of a fluorophore in conjugation with the triazabutadiene did not prevent the photochemistry. Once more we utilized BSA as a model protein to show labeling could be attained at pH 7 by irradiation at 350 nm (Figure 1c). Labeling was evident following as little as 5 minutes of irradiation. Not surprisingly, we also showed that the presence of excess resorcinol attenuated labeling of BSA. These data are consistent with our understanding that this chemistry is primarily operating through diazonium ion chemistry and not other photochemically generated species (such as nitrenes or aryl radicals). This result is consistent with previous work on using light to release aryl diazonium ions from triazabutadienes.[9]</p><p>To ensure fluorescence of the BSA could be attributed to covalent modification several experiments were performed. First, the labeling in the presence or absence of urea showed similar levels of labeling (Figure S4). Additionally, mass spectral data supported covalent modification, and was consistent with the extent of BSA modification reported by others.[3] BSA was treated with 2 and irradiated for 25 min. After prolonged incubation, the sample was analyzed by MALDI mass spectrometry and overall mass shifts indicated that just under two modifications per BSA on average were made in a reagent and light-dependent manner (Figure S5).</p><p>To move beyond BSA and illustrate general utility we analyzed the labeling of egg yolk proteins. In several experiments, analogous to those run with BSA, egg yolk proteins were labeled by 2 in a pH-dependent manner (Figure S6). Furthermore, we treated proteins from egg yolk extracts with 2 at pH 8 in the presence or absence of light (Figure S7). The fluorescence of several proteins in the irradiated samples confirmed that 2 could label a variety of proteins in a light-dependent manner. The lack of fluorescence in several protein bands suggests that protein labeling by 2 is contained to proteins with accessible tyrosine. This is of consequence for future applications, where the environment of tyrosine will dictate the efficiency and extent of labeling. Also of note is that there is a wide range of non-specific binding observed for 2, from proteins that have no observable background binding, to those that appear equivalent to covalent binding.</p><p>Prompted to further broaden applicability, we synthesized, and tested a series of coumarin triazabutadienes (Figure 2a). We had previously established that structures lacking mesityl substituents were more reactive in the presence of low pH than those containing them, and we hypothesized that removal of the trifluoromethyl would also increase release rates.[10] Each of the four triazabutadienes was evaluated for labeling via liberation by both pH and irradiation at 350 nm. Interestingly, treatment of BSA by each triazabutadiene at pH 5 provided similar levels of fluorescence for all four compounds (Figure 2b). While it is possible that we would have seen a difference in labeling at a different pH, a noteworthy trend emerged upon diazonium ion liberation via irradiation. The bis-methyl substituted compounds, 5 and 7, showed nearly zero response to the light, but the bis-mesityl compounds both showed significant amounts of labeling in a light-dependent manner (Figure 2c).[11] The UV/vis absorption peaks for 2 and 6 are broader than those for 5 and 7, but none of the four compounds absorb well at 350 nm. As such, we hypothesize that the mesityl portions of the molecule are potentially forcing 2 and 6 to be ideally positioned to absorb the energy and isomerize. The underlying reason for this phenomenon is unknown at this time, but warrants further investigation. Given the strong increase in fluorescence observed when using 6 under photochemical conditions, we challenged the probe with a complex Escherichia coli (E. coli) lysate.[12] To our delight we observed robust labeling of the sample with minimal background fluorescence (Figure 2d).</p><p>In conclusion, we have reported the synthesis and general utility of new class of fluorophore-embedded triazabutadienes as delivery tool for aryl diazonium salts to fluorescently label proteins of interest. In the process, we have shown multiple strategies for eliciting environmentally triggered modification of proteins, including the use of low pH and irradiation at 350 nm, which afford these compounds the versatility to be used in a wide range of pH and biologically relevant environments. Taken together, our series of masked coumarin diazonium ions provide bench stable, environmentally triggered fluorophores that pose potential for imaging applications. A current limitation of these molecules is that their absorbance and emission spectra will not allow for imaging of tissue; but more broadly, this strategy should be extendable to other classes of fluorophores.</p>",
"role": "user"
},
{
"content": "The use of small-molecule fluorophores to label proteins with minimal perturbation in response to an external stimulus is a powerful tool to probe chemical and biochemical environments. Herein we describe first the use of a coumarin modified triazabutadiene that can deliver aryl diazonium ions to fluorescently label proteins via tyrosine selective modification. The labeling can be triggered by low pH induced liberation of the diazonium species, making the fluorophore specifically useful in labeling biochemical surroundings such as those found within the late endosome. Additionally, we show that a variety of coumarin triazabutadienes may also be prone to releasing their diazonium cargo via irradiation with UV light.",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.159
|
[
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: I want to complete 3D shapes.\n\nKeyphrases: 3d shape completion\n\nDataset descriptions:\n3D Shapes Dataset: 3dshapes is a dataset of 3D shapes procedurally generated from 6 ground truth independent latent factors. These factors are floor colour, wall colour, object colour, scale, shape and orientation.\nShapeNet: ShapeNet is a large scale repository for 3D CAD models developed by researchers from Stanford University, Princeton University and the Toyota Technological Institute at Chicago, USA. The repository contains over 300M models with 220,000 classified into 3,135 classes arranged using WordNet hypernym-hyponym relationships.\n3D-FUTURE: 3D-FUTURE (3D FUrniture shape with TextURE) is a 3D dataset that contains 20,240 photo-realistic synthetic images captured in 5,000 diverse scenes, and 9,992 involved unique industrial 3D CAD shapes of furniture with high-resolution informative textures developed by professional designers.\nIntrA: IntrA is an open-access 3D intracranial aneurysm dataset that makes the application of points-based and mesh-based classification and segmentation models available. This dataset can be used to diagnose intracranial aneurysms and to extract the neck for a clipping operation in medicine and other areas of deep learning, such as normal estimation and surface reconstruction.\n\nOptions: A: 3D Shapes Dataset B: ShapeNet C: 3D-FUTURE D: IntrA",
"role": "user"
},
{
"content": "ShapeNet",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_pubmed
|
science.scientific_papers_summarization_single_doc_pubmed.82690
|
[
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\ncongenital stationary night blindness ( csnb ; csnb1a , omim # 310500 , csnb1b , omim # 257270 , csnb1c , omim # 613216 and csnb2a , omim # 3000071 , csnb 2b , omim # 610427 ) ( online mendelian inheritance in men ) is a clinically heterogeneous group of nonprogressive retinal disorders characterized by impaired night vision , decreased visual acuity , nystagmus , myopia , and strabismus.1 a negative - type electroretinogram ( erg ) recording , with a normal a - wave ( initial negative deflection ) and significantly reduced b - wave ( positive deflection ) amplitude , is recorded in the bright flash , mixed rod and cone erg in csnb .\ncomplete csnb ( csnb1 ) is characterized by reduced rod b - wave response due to a complete defect of the metabotropic ( on)-bipolar cell - mediated signal transduction , whereas incomplete csnb ( csnb2 ) is characterized by both a reduced rod b - wave and substantially reduced flicker cone responses due to the dysfunction of both on and ionotropic ( off ) bipolar cell - mediated signal transduction .\ncomplete csnb patients have normal fundi ; they have malfunction in neurotransmission from rods to bipolar cells.1,2 the hereditary mode of complete csnb is either autosomal recessive or x - linked recessive .\ncomplete csnb is caused by mutations in the genes nyx , grm6 , and trpm1.3,4 typical clinical features of complete csnb consist of night blindness from early childhood and normal to mildly reduced best - corrected visual acuities and high or moderate myopia with astigmatism . in recent research , it is reported that none of the csnb1 patients had severe abnormal color defects , but 14% had mild color defects.5 signals from the blue cones are mainly transferred through the on - bipolar pathway , but csnb1 patients have no function in this pathway.1,6 the reason why csnb1 patients usually do not show color vision abnormalities is unclear . in the current report , we document the clinical characteristics of a patient with complete csnb who was asymptomatic and referred for the investigation of the cause of a color vision defects .\na 17-year - old male who was in a technical school of the transportation industry showed abnormalities in the color perception test for employment , and was referred to our hospital for a detailed examination . while he was in the elementary school\nhe had no family history of color vision deficiency , and had no other symptoms . during the initial examination ,\nhis best - corrected visual acuity was 1.2 , with no refractive error in either eye .\ntesting with ishihara pseudoisochromatic plates , the patient could read only the first plate , and was diagnosed to have a color vision defect .\nthe patient s color vision defect was mild , with no definite axis of error according to the 100-hue test performed at the referral hospital , and he showed normal match with an anomaloscope color blindness test .\nthe referring doctor also performed standard pseudoisochromatic plates , part 2 to assess the type of color defect .\nthe patient made two mistakes for blue yellow differentiation and five mistakes for red green differentiation in the right eye ; and two mistakes for blue yellow differentiation and four mistakes for red green differentiation in the left eye , suggesting that the color vision defect had no definite axis . during the initial examination ,\nhis fundus showed no abnormalities except for a somewhat yellowish reflex in the fovea of both eyes .\nfundus autofluorescence , optical coherence tomography , and multifocal erg were normal ( figure 1 ) .\ncolor vision deficiency with no apparent retinal abnormalities is sometimes associated with retinal diseases.7 thus , these findings prompted us to obtain an erg .\nboth the cone erg and 30 hz flicker erg ( recorded by international society for clinical electrophysiology vision [ iscev ] standard protocol erg [ using tomei le3000 , tomei , tokyo , japan ] ) showed a good response ; however , the cone erg showed wide a - wave trough.7 bright flash , mixed rod and cone erg showed a negative type with a reduced b - wave and a disappearance of oscillatory potential .\nobservation was recommended ; he has been monitored for 5 years , and remains asymptomatic with no changes in visual acuity and fundus appearance since the first visit .\nit has been recognized that complete and incomplete csnb are different diseases , with different erg findings and different gene mutations.1,2 complete csnb patients show a negative type with reduced b - wave amplitude in the mixed rod and cone erg and the disappearance of rod response in the scotopic erg , whereas incomplete csnb patients have residual rod function but cone dysfunction . in complete csnb , the bright flash cone response presents a characteristic wide a - wave trough and moderate reduction of the b - wave amplitude.8 complete csnb is either autosomal recessive or x - linked recessive , whereas incomplete csnb is usually x - linked recessive.2 most of the causative gene products in complete csnb ( ie , nyx , grm6 and trpm1 , and gpr179 ) are localized at the dendritic terminals of on bipolar cells and contribute the cell activity.3,5 there are also differences in other clinical findings ; patients complain of low visual acuity in both types , but complete csnb patients present with moderate or high myopia , whereas incomplete csnb patients present with either myopia or hyperopia.1 sometimes strabismus and nystagmus are also found . in a previous report , 20% to 40% of patients with csnb were found to present with nystagmus.9 there is little complaint of night blindness in incomplete csnb , which is in contrast to patients with complete csnb , who usually complain of night blindness.5 in the recent literature , all patients with complete csnb or csnb1 reported night vision problems .\nmoreover , the clinical features of patients with complete csnb are reported to be similar , though the causative gene is different.3,5 this is in contrast with incomplete csnb , which is reported to show considerable variability in the clinical expression .\nalthough csnb is characterized by impaired night vision and/or decreased visual acuity , myopia , and nystagmus , the patient had neither congenital color blindness nor other symptoms ; he merely happened to present a color vision anomaly in screening tests .\nalthough the results of the color vision defect were moderate and nonspecific , they led us to suspect retinal disorder .\nthe ophthalmological examination revealed atypical findings ; however , the patient has been diagnosed with complete csnb by the characteristic findings of the erg .\nthis case underscores the importance of careful patient examination and erg in order to diagnose the cause of a color vision anomaly .\nclinicians should be more aware of retinal disease with normal fundus and normal visual acuity.5 as a recent study reports , patients with good visual acuity may not always be recognized as having a retinal disorder.5 the yellowish reflex of the fovea in the current case is likely to reflect the increased macular xanthophylls , however , the association of the foveal xanthophylls and complete csnb remains to be clarified in future studies .",
"role": "user"
},
{
"content": "patients with the complete form of congenital stationary night blindness ( csnb ) often have reduced visual acuity , myopia , impaired night vision , and sometimes nystagmus and strabismus , however , they seldom complain of color vision abnormality . a 17-year - old male who was at technical school showed abnormalities in the color perception test for employment , and was referred to our hospital for a detailed examination . \n he had no family history of color vision deficiency and no other symptoms . during the initial examination , \n his best - corrected visual acuity was 1.2 in both eyes . \n his fundus showed no abnormalities except for somewhat yellowish reflex in the fovea of both eyes . \n electroretinogram ( erg ) showed a good response in cone erg and 30 hz flicker erg , however , the bright flash , mixed rod and cone erg showed a negative type with a reduced b - wave ( positive deflection ) . \n there was no response in the rod erg , either . from the findings of the typical erg , \n the patient was diagnosed with complete congenital stationary night blindness . \n this case underscores the importance of erg in order to diagnose the cause of a color vision anomaly .",
"role": "assistant"
}
] |
science.acl_arc_intent_classification
|
science.acl_arc_intent_classification.1054
|
[
{
"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:\nNone\n\nContext before:\nMost DOP models, such as in Bod (1993), Goodman (1996), Bonnema et al. (1997), Sima'an (2000) and Collins & Duffy (2002), use a likelihood criterion in defining the best parse tree: they take (some notion of) the most likely (i.e. most probable) tree as a candidate for the best tree of a sentence.\n\nCitation:\nMost DOP models , such as in Bod ( 1993 ) , Goodman ( 1996 ) , Bonnema et al. ( 1997 ) , Sima'an ( 2000 ) and Collins & Duffy ( 2002 ) , use a likelihood criterion in defining the best parse tree : they take ( some notion of ) the most likely ( i.e. most probable ) tree as a candidate for the best tree of a sentence .\n\nContext after:\nWe will refer to these models as Likelihood-DOP models, but in this paper we will specifically mean by "Likelihood-DOP" the PCFG-reduction of Bod (2001) given in Section 2.2. In Bod (2000b), an alternative notion for the best parse tree was proposed based on a simplicity criterion: instead of producing the most probable tree, this model produced the tree generated by the shortest derivation with the fewest training subtrees. We will refer to this model as Simplicity-DOP. In case the shortest derivation is not unique, Bod (2000b) proposes to back off to a frequency ordering of the subtrees.",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.80230
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Towards Privacy and Security of Deep Learning Systems: A Survey \nChapter Title: Finding 1. \n1. Abstract of Cited Paper (BIB001): Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model, even if the two models have different architectures or were trained on different training sets, so long as both models were trained to perform the same task. An attacker may therefore train their own substitute model, craft adversarial examples against the substitute, and transfer them to a victim model, with very little information about the victim. Recent work has further developed a technique that uses the victim model as an oracle to label a synthetic training set for the substitute, so the attacker need not even collect a training set to mount the attack. We extend these recent techniques using reservoir sampling to greatly enhance the efficiency of the training procedure for the substitute model. We introduce new transferability attacks between previously unexplored (substitute, victim) pairs of machine learning model classes, most notably SVMs and decision trees. We demonstrate our attacks on two commercial machine learning classification systems from Amazon (96.19% misclassification rate) and Google (88.94%) using only 800 queries of the victim model, thereby showing that existing machine learning approaches are in general vulnerable to systematic black-box attacks regardless of their structure. \n2. Abstract of Cited Paper (BIB002): Hyperparameters are critical in machine learning, as different hyperparameters often result in models with significantly different performance. Hyperparameters may be deemed confidential because of their commercial value and the confidentiality of the proprietary algorithms that the learner uses to learn them. In this work, we propose attacks on stealing the hyperparameters that are learned by a learner. We call our attacks hyperparameter stealing attacks. Our attacks are applicable to a variety of popular machine learning algorithms such as ridge regression, logistic regression, support vector machine, and neural network. We evaluate the effectiveness of our attacks both theoretically and empirically. For instance, we evaluate our attacks on Amazon Machine Learning. Our results demonstrate that our attacks can accurately steal hyperparameters. We also study countermeasures. Our results highlight the need for new defenses against our hyperparameter stealing attacks for certain machine learning algorithms. \n3. Abstract of Cited Paper (BIB003): Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality of ML models becomes paramount for two reasons: (a) a model can be a business advantage to its owner, and (b) an adversary may use a stolen model to find transferable adversarial examples that can evade classification by the original model. Access to the model can be restricted to be only via well-defined prediction APIs. Nevertheless, prediction APIs still provide enough information to allow an adversary to mount model extraction attacks by sending repeated queries via the prediction API. In this paper, we describe new model extraction attacks using novel approaches for generating synthetic queries, and optimizing training hyperparameters. Our attacks outperform state-of-the-art model extraction in terms of transferability of both targeted and non-targeted adversarial examples (up to +29-44 percentage points, pp), and prediction accuracy (up to +46 pp) on two datasets. We provide take-aways on how to perform effective model extraction attacks. We then propose PRADA, the first step towards generic and effective detection of DNN model extraction attacks. It analyzes the distribution of consecutive API queries and raises an alarm when this distribution deviates from benign behavior. We show that PRADA can detect all prior model extraction attacks with no false positives.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Training substitute model is by no doubt the dominant method in model extraction attacks with manifold advantages. Equation solving is deemed as an efficient way to recover parameters BIB001 or hyperparameters BIB003 in linear algorithms, since it has an upper bound for sufficient queries. As claimed in BIB001 , d-dimensional weights can be cracked with only d + 1 queries. However, this approach is hardly applicable to the non-linear deep learning algorithms. So researchers turn to the compelling training-based approach. For instance, trains a classifier, dubbed as metamodel, over the target model so as to predict architectural information which is categorical or limited real values. This approach cannot cope with complex model attributes such as decision boundary and functionality. That drives the prevalence of substitute model as it serves as an incarnation of the target model which behaves quite similarly. As such, the substitute model has approximated attributes and prediction results. Additionally, it can be further used to steal model's training data BIB004 and generating adversarial examples BIB002 .",
"role": "assistant"
}
] |
science.craftchem_ner
|
science.craftchem_ner.2696
|
[
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Lawrenceforhistology;Dr.S.",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
] |
science.qasa_abstractive_qa
|
science.qasa_abstractive_qa.589
|
[
{
"content": "Read this passage from a research paper and answer the question.\n\nContext: SeLa Asano et al. (2020) and SwAV Caron et al. (2020) formulate their pseudo-labeling process into optimization problems, i.e., optimal transport (OT) problem, and solve it iteratively with Sinkhorn-Knopp (SK) algorithm Cuturi (2013).To avoid collapse and apply the SK algorithm, they assume the equipartition of data into clusters.Mathematically, the difference to MIRA is in how to deal with the marginal entropy.SeLa and SwAV constrain the marginal entropy to maximum value–equipartition while MIRA decides it by MI regularization333Adding the equipartition constraint into Eq. 4, our problem converts to the OT problem of SwAV Caron et al. (2020)..Asano et al. (2020) argue that their pseudo-labels with the OT problem maximize the MI between labels and data indices under the equipartition constraint.However, it more resembles assuming MI maximization and then finding the cluster assignments that are optimal transport to the model prediction.In contrast, MIRA directly maximizes the MI by regularization without artificial constraints.While SwAV performs better than SeLa in most self-supervised benchmarks, we verify that MIRA improves over SwAV in various downstream tasks.\n\nQuestion: What is the optimal transport used in SwaV?",
"role": "user"
},
{
"content": "Adding equipartition constraint to the objective induces the optimal transport method used in SwaV\n\ncomposition: False",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.22635
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nThe millimeter wave (mmWave) band, a prime candidate for 5G cellular networks, seems attractive for wireless energy harvesting since it will feature large antenna arrays and extremely dense base station (BS) deployments. The viability of mmWave for energy harvesting though is unclear, due to the differences in propagation characteristics, such as extreme sensitivity to building blockages. This paper considers a scenario where low-power devices extract energy and or information from the mmWave signals. Using stochastic geometry, analytical expressions are derived for the energy coverage probability, the average harvested power, and the overall (energy-and-information) coverage probability at a typical wireless-powered device in terms of the BS density, the antenna geometry parameters, and the channel parameters. Numerical results reveal several network and device level design insights. At the BSs, optimizing the antenna geometry parameters, such as beamwidth, can maximize the network-wide energy coverage for a given user population. At the device level, the performance can be substantially improved by optimally splitting the received signal for energy and information extraction, and by deploying multi-antenna arrays. For the latter, an efficient low-power multi-antenna mmWave receiver architecture is proposed for simultaneous energy and information transfer. Overall, simulation results suggest that mmWave energy harvesting generally outperforms lower frequency solutions.\n\nCited Abstract(s):\n[1]: Energy harvesting (EH) from ambient radio-frequency (RF) electromagnetic waves is an efficient solution for fully autonomous and sustainable communication networks. Most of the related works presented in the literature are based on specific (and small-scale) network structures, which although give useful insights on the potential benefits of the RF-EH technology, cannot characterize the performance of general networks. In this paper, we adopt a large-scale approach of the RF-EH technology and we characterize the performance of a network with random number of transmitter-receiver pairs by using stochastic-geometry tools. Specifically, we analyze the outage probability performance and the average harvested energy, when receivers employ power splitting (PS) technique for \"simultaneous\" information and energy transfer. A non-cooperative scheme, where information energy are conveyed only via direct links, is firstly considered and the outage performance of the system as well as the average harvested energy are derived in closed form in function of the power splitting. For this protocol, an interesting optimization problem which minimizes the transmitted power under outage probability and harvesting constraints, is formulated and solved in closed form. In addition, we study a cooperative protocol where sources' transmissions are supported by a random number of potential relays that are randomly distributed into the network. In this case, information energy can be received at each destination via two independent and orthogonal paths (in case of relaying). We characterize both performance metrics, when a selection combining scheme is applied at the receivers and a single relay is randomly selected for cooperative diversity.\n\n[2]: Ambient radio frequency (RF) energy harvesting technique has recently been proposed as a potential solution for providing proactive energy replenishment for wireless devices. This paper aims to analyze the performance of a battery-free wireless sensor powered by ambient RF energy harvesting using a stochastic geometry approach. Specifically, we consider the point-to-point uplink transmission of a wireless sensor in a stochastic geometry network, where ambient RF sources, such as mobile transmit devices, access points and base stations, are distributed as a Ginibre @math -determinantal point process (DPP). The DPP is able to capture repulsion among points, and hence, it is more general than the Poisson point process (PPP). We analyze two common receiver architectures: separated receiver and time-switching architectures. For each architecture, we consider the scenarios with and without co-channel interference for information transmission. We derive the expectation of the RF energy harvesting rate in closed form and also compute its variance. Moreover, we perform a worst-case study which derives the upper bound of both power and transmission outage probabilities. Additionally, we provide guidelines on the setting of optimal time-switching coefficient in the case of the time-switching architecture. Numerical results verify the correctness of the analysis and show various tradeoffs between parameter setting. Lastly, we prove that the RF-powered sensor performs better when the distribution of the ambient sources exhibits stronger repulsion.\n\n[3]: Microwave power transfer (MPT) delivers energy wirelessly from stations called power beacons (PBs) to mobile devices by microwave radiation. This provides mobiles practically infinite battery lives and eliminates the need of power cords and chargers. To enable MPT for mobile recharging, this paper proposes a new network architecture that overlays an uplink cellular network with randomly deployed PBs for powering mobiles, called a hybrid network. The deployment of the hybrid network under an outage constraint on data links is investigated based on a stochastic-geometry model where single-antenna base stations (BSs) and PBs form independent homogeneous Poisson point processes (PPPs) with densities λb and λp, respectively, and single-antenna mobiles are uniformly distributed in Voronoi cells generated by BSs. In this model, mobiles and PBs fix their transmission power at p and q, respectively; a PB either radiates isotropically, called isotropic MPT, or directs energy towards target mobiles by beamforming, called directed MPT. The model is used to derive the tradeoffs between the network parameters (p, λb, q, λp) under the outage constraint. First, consider the deployment of the cellular network. It is proved that the outage constraint is satisfied so long as the product pλbα 2 is above a given threshold where α is the path-loss exponent. Next, consider the deployment of the hybrid network assuming infinite energy storage at mobiles. It is shown that for isotropic MPT, the product qλpλbα 2 has to be above a given threshold so that PBs are sufficiently dense; for directed MPT, zmqλpλbα 2 with zm denoting the array gain should exceed a different threshold to ensure short distances between PBs and their target mobiles. Furthermore, similar results are derived for the case of mobiles having small energy storage.\n\n[4]: Far-field microwave power transfer (MPT) will free wireless sensors and other mobile devices from the constraints imposed by finite battery capacities. Integrating MPT with wireless communications to support simultaneous wireless information and power transfer (SWIPT) allows the same spectrum to be used for dual purposes without compromising the quality of service. A novel approach is presented in this paper for realizing SWIPT in a broadband system where orthogonal frequency division multiplexing and transmit beamforming are deployed to create a set of parallel sub-channels for SWIPT, which simplifies resource allocation. Based on a proposed reconfigurable mobile architecture, different system configurations are considered by combining single-user multi-user systems, downlink uplink information transfer, and variable fixed coding rates. Optimizing the power control for these configurations results in a new class of multi-user power-control problems featuring the circuit-power constraints, specifying that the transferred power must be sufficiently large to support the operation of the receiver circuitry. Solving these problems gives a set of power-control algorithms that exploit channel diversity in frequency for simultaneously enhancing the throughput and the MPT efficiency. For the system configurations with variable coding rates, the algorithms are variants of water-filling that account for the circuit-power constraints. The optimal algorithms for those configurations with fixed coding rates are shown to sequentially allocate mobiles their required power for decoding in ascending order until the entire budgeted power is spent. The required power for a mobile is derived as simple functions of the minimum signal-to-noise ratio for correct decoding, the circuit power and sub-channel gains.\n\n[5]: Wireless networks can be self-sustaining by harvesting energy from ambient radio-frequency (RF) signals. Recently, researchers have made progress on designing efficient circuits and devices for RF energy harvesting suitable for low-power wireless applications. Motivated by this and building upon the classic cognitive radio (CR) network model, this paper proposes a novel method for wireless networks coexisting where low-power mobiles in a secondary network, called secondary transmitters (STs), harvest ambient RF energy from transmissions by nearby active transmitters in a primary network, called primary transmitters (PTs), while opportunistically accessing the spectrum licensed to the primary network. We consider a stochastic-geometry model in which PTs and STs are distributed as independent homogeneous Poisson point processes (HPPPs) and communicate with their intended receivers at fixed distances. Each PT is associated with a guard zone to protect its intended receiver from ST's interference, and at the same time delivers RF energy to STs located in its harvesting zone. Based on the proposed model, we analyze the transmission probability of STs and the resulting spatial throughput of the secondary network. The optimal transmission power and density of STs are derived for maximizing the secondary network throughput under the given outage-probability constraints in the two coexisting networks, which reveal key insights to the optimal network design. Finally, we show that our analytical result can be generally applied to a non-CR setup, where distributed wireless power chargers are deployed to power coexisting wireless transmitters in a sensor network.\n\n[6]: While cognitive radio enables spectrum-efficient wireless communication, radio frequency (RF) energy harvesting from ambient interference is an enabler for energy-efficient wireless communication. In this paper, we model and analyze cognitive and energy harvesting-based device-to-device (D2D) communication in cellular networks. The cognitive D2D transmitters harvest energy from ambient interference and use one of the channels allocated to cellular users (in uplink or downlink), which is referred to as the D2D channel, to communicate with the corresponding receivers. We investigate two spectrum access policies for cellular communication in the uplink or downlink, namely, random spectrum access (RSA) policy and prioritized spectrum access (PSA) policy. In RSA, any of the available channels including the channel used by the D2D transmitters can be selected randomly for cellular communication, while in PSA the D2D channel is used only when all of the other channels are occupied. A D2D transmitter can communicate successfully with its receiver only when it harvests enough energy to perform channel inversion toward the receiver, the D2D channel is free, and the signal-to-interference-plus-noise ratio @math at the receiver is above the required threshold; otherwise, an outage occurs for the D2D communication. We use tools from stochastic geometry to evaluate the performance of the proposed communication system model with general path-loss exponent in terms of outage probability for D2D and cellular users. We show that energy harvesting can be a reliable alternative to power cognitive D2D transmitters while achieving acceptable performance. Under the same @math outage requirements as for the non-cognitive case, cognitive channel access improves the outage probability for D2D users for both the spectrum access policies. When compared with the RSA policy, the PSA policy provides a better performance to the D2D users. Also, using an uplink channel provides improved performance to the D2D users in dense networks when compared to a downlink channel. For cellular users, the PSA policy provides almost the same outage performance as the RSA policy.",
"role": "user"
},
{
"content": "Wireless energy and or information transfer in large-scale networks has also been investigated [2] [5] [6] [3] [4] [1] . In [2] , the performance of ambient RF energy harvesting was characterized using tools from stochastic geometry. Using a repulsive point process to model RF transmitters, it was shown that more repulsion helps improve the performance at an energy harvester for a given transmitter density. In [5] [6] , cognitive radio networks were considered, and opportunistic wireless energy harvesting was proposed and analyzed. In [3] , a hybrid cellular network architecture was proposed to enable wireless power transfer for mobiles. In particular, an uplink cellular network was overlaid with power beacons and trade-offs between the transmit power and deployment densities were investigated under an outage constraint on the data links. A broadband wireless network with transmit beamforming was considered in [4] , where optimal power control algorithms were devised for improving the throughput and power transfer efficiency. Simultaneous information and energy transfer in a relay-aided network was considered in [1] . Under a random relay selection strategy, the network-level performance was characterized in terms of the relay density and the relay selection area.",
"role": "assistant"
}
] |
science.healthver_entailment
|
science.healthver_entailment.1130
|
[
{
"content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Cytokine Storms May Be Fueling Some COVID Deaths\n\nAbstract:\nCytokine storm is an excessive immune response to external stimuli.\nThe pathogenesis of the cytokine storm is complex.\nThe disease progresses rapidly, and the mortality is high.\nCertain evidence shows that, during the coronavirus disease 2019 (COVID-19) epidemic, the severe deterioration of some patients has been closely related to the cytokine storm in their bodies.\nThis article reviews the occurrence mechanism and treatment strategies of the COVID-19 virus-induced inflammatory storm in attempt to provide valuable medication guidance for clinical treatment.",
"role": "user"
},
{
"content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"The disease progresses rapidly, and the mortality is high.\", \"Certain evidence shows that, during the coronavirus disease 2019 (COVID-19) epidemic, the severe deterioration of some patients has been closely related to the cytokine storm in their bodies.\"]}",
"role": "assistant"
}
] |
science.covid_deepset_qa
|
science.covid_deepset_qa.337
|
[
{
"content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: METHODOLOGY/SIGNIFICANT FINDINGS: In this study, we evaluated the HIV-1 RT-LAMP assay using portable, non-instrumented nucleic acid amplification (NINA) heating devices that generate heat from the exothermic reaction of calcium oxide and water. The NINA heating devices exhibited stable temperatures throughout the amplification reaction and consistent amplification results between three separate devices and a thermalcycler. The performance of the NINA heaters was validated using whole blood specimens from HIV-1 infected patients. CONCLUSION: The RT-LAMP isothermal amplification method used in conjunction with a chemical heating device provides a portable, rapid and robust NAAT platform that has the potential to facilitate HIV-1 testing in resource-limited settings and POC. Text: HIV-1 diagnostic tests are held to a high standard of performance, as diagnosis has a direct impact on patient care and reduction of transmission. Despite technological advances in the field of HIV diagnostics and the high sensitivity and specificity associated with most HIV diagnostic tests that are currently available, it is estimated that approximately 20% of HIV-infected individuals living in the United States remain undiagnosed [1] . Furthermore, testing sites have reported as many as 35 to 50% of individuals with an initial positive test result will not return for a confirmatory diagnosis if follow-up laboratory testing is required [2] . Rapid HIV antibodybased tests, which can be performed with minimal training and typically provide results in under 30 minutes [3] , have facilitated HIV testing at the point-of-care and subsequently increased the numbers of individuals aware of their serostatus [4] . Rapid tests are currently a key component of HIV screening at the point-of-care (POC), significantly expanding the diagnostic capabilities of testing sites in developed countries, as well as resource-limited settings. Despite the advances made by the widespread availability of rapid tests, all antibody-based tests for the detection of HIV exhibit some limitations. HIV-specific antibody typically begins to appear around three weeks post-infection, allowing for detection by most antibody-based assays within 3-6 weeks [3, 5] . The window of time prior to or during early seroconversion may lead to false-negative test results in recently infected individuals. Additionally, accurate diagnosis of infants born to HIV-infected mothers can be challenging if based solely on antibody positivity, since vertically transferred maternal antibodies may persist for 12-18 months after birth [6, 7] . For confirmatory diagnosis of early HIV infection or infant diagnosis, nucleic acid amplification tests (NAAT) are preferred, as HIV-1 RNA can be detected as early as 10-12 days post infection and HIV-1 DNA and/or RNA are definitive indicators of active infection [5] . In their current form, however, NAAT's are not feasible for POC testing, because they are timeconsuming, expensive, and technically complicated. To date, the Aptima HIV-1 RNA assay (Gen-Probe, Inc., http://www.fda.gov/ BiologicsBloodVaccines/BloodBloodProducts/ApprovedProducts/ LicensedProductsBLAs/BloodDonorScreening/InfectiousDisease/ UCM080466) is the only FDA-approved NAAT for the diagnosis or confirmation of HIV-1 infection and it is only suitable for laboratory testing. To meet the needs of HIV-1 diagnosis at the POC, a rapid NAAT that can be performed with minimal training, limited equipment, and a relatively short turnaround time (,1 hour)is desirable [8] . The development of a rapid NAAT has proven to be especially challenging since the technology involved in simplifying the test procedure often equates to increased equipment and material costs [8] . Additionally, the reduction in technical complexity should not compromise test sensitivity and specificity. For increased applicability at the POC, an increasing number of novel isothermal amplification techniques have been developed [9] . Isothermal amplification is an attractive alternative to traditional PCR or RT-PCR since thermalcycling is not required, allowing for greater versatility in terms of heating or amplification devices. One such amplification method, termed Loop-Mediated Isothermal Amplification (LAMP) [10] , has been optimized for the detection of DNA and/or RNA (RT-LAMP) from a wide range of bacterial and viral pathogens [11, 12, 13, 14, 15, 16, 17, 18, 19] , including HIV [20, 21] . LAMP or RT-LAMP exhibits several characteristics that are ideal for integration into a rapid nucleic-acid based diagnostic test. The amplification reaction requires six primers specific for eight separate regions within the target sequence, contributing to the high specificity of the amplification method. Amplified material can typically be detected within 15-60 minutes when incubated at a constant reaction temperature of 60-65uC [22] . LAMP has also proven to be less sensitive to biological inhibitors than PCR [23, 24] , which enables direct amplification from clinical specimens, thereby eliminating the need for an additional nucleic acid extraction step. Direct amplification from plasma, whole blood, and oral fluid has previously been demonstrated for HIV-1 [20, 21, 25] . Lastly, immediate visual detection of amplified products is facilitated by the large amount of DNA that is generated by each reaction. Several groups have incorporated fluorescent detection methods into the LAMP assay for real-time or immediate naked-eye detection [15, 17, 21, 22, 26] . The simplicity and isothermal nature of the LAMP procedure opens the door for the evaluation of low-tech integrated devices or novel heating elements, which are appropriate for low-resource settings, where costly equipment and electricity cannot be obtained. In this study, the was evaluated using portable, non-instrumented nucleic acid amplification (NINA) devices that generate heat from the exothermic reaction of calcium oxide and water [27, 28] . We demonstrated the temperature stability of the NINA heating devices and feasibility for POC testing of whole blood specimens from HIV-1 infected individuals. Prototype NINA heaters were designed and provided by Program for Appropriate Technology in Health (PATH, Seattle, WA), as described [27, 28] . Briefly, an amplification temperature of approximately 60uC was provided by the exothermic reaction of calcium oxide (CaO; Sigma-Aldrich, St. Louis, MO) and water. The heating devices, containing the chemical reaction, were designed using thermally insulated, stainless-steel canisters with plastic screw-top lids (Fig. 1) . The lids were modified to contain three sample wells that fit standard 200 ml PCR tubes and were filled with a proprietary phase-change material (PCM) that was used to buffer the heat derived from the exothermic reaction, thereby providing a constant temperature. Lastly, plastic caps containing foam insulation were designed to fit on the top of the canister lids. The thermal profiles of the sample wells were measured and recorded using a digital thermometer (DaqPRO 5300 Data recorder; OMEGA Engineering, Inc., Stamford, CT). DNA and RNA linearity panels were prepared to determine the sensitivity of the HIV-specific RT-LAMP assay. A DNA panel was generated from DNA extracted from the human monocytic cell line OM-10.1 [29] , using a QIAamp DNA blood mini kit (QIAGEN, Valencia, CA). Cell count was used to quantify the input DNA copy number, as a single integrated provirus is contained in each cell [29] . The extracted DNA was diluted tenfold in RNase-free water to create a linearity panel, ranging from 10 5 copies/ml to 10 3 copies/ml. An RNA linearity panel was obtained commercially (PRD801; SeraCare Life Sciences, Mil- ford, MA) and ranged from 2.9610 6 copies/ml to 8 copies/ml, as determined by Roche AMPLICOR HIV MONITOR TM v 1.5, Bayer VERSANT HIV-1 RNA bDNA 3.0 Assay, bioMerieux NucliSensH HIV-1 QT, and Abbott Real Time HIV-1 m2000 TM . RNA was extracted from the panel members using a Viral RNA mini kit (QIAGEN). Negative controls included DNA extracted from PBMC infected with HIV-2 SLRHC [30] and RNA extracted from HIV-2 NIH-Z purified virus (Advanced Biotechnologies Inc., Columbia, MD). Whole blood from HIV-1 infected individuals was collected as part of a separate, IRB-approved study [31] , or obtained commercially (SeraCare Life Sciences). All HIV-positive samples were confirmed using the following tests: Genetic Systems HIV-1/ HIV-2 plus O EIA (Bio-Rad Laboratories, Redmond, WA), GS HIV-1 Western blot (Bio-Rad Laboratories), Aptima HIV-1 RNA assay (Gen-Probe, Inc., San Diego, CA), and Amplicor HIV-1 DNA assay (Roche Diagnostics, Branchburg, NJ ). Viral and proviral loads are unknown, since the samples were tested with qualitative, nucleic acid-based assays. All clinical specimens evaluated in this study were obtained from individuals infected with subtype B HIV-1 virus. As a negative control, HIV-1 seronegative blood samples (SeraCare Life Sciences) were included in every experiment involving whole blood. A positive control included HIV-1 seronegative blood spiked with 5610 6 virus particles/ml of HIV-1 BaL (Advanced Biotechnologies Inc.). HIV-1-specific RT-LAMP primers were designed to recognize a conserved sequence within the reverse transcriptase (RT) gene. The six primers required for the RT-LAMP reaction, forward outer (F3), backward outer (B3), forward inner (FIP), backward inner (BIP), and the loop primers (LoopF and LoopB), were designed using the PrimerExplorer V4 software (Eiken Chemical Co. Ltd.; http:// primerexplorer.jp/e/). The LAMP primers and amplification cycle have been described in detail by Nagamine et al. [32] . Additional modifications included a linker sequence of four thymidines inserted between the F2 and F1c sequences of the FIP primer, as described [20] , and the addition of the fluorescent molecule HEX to the 59 end of the LoopF primer. The labeled primer, along with a quencher probe, allowed for immediate visual detection of amplified products [21] . The quencher probe consisted of the complementary sequence of the LoopF primer with Black Hole Quencher-1 (BHQ-1) added to the 39 end. The HIV-1 HXB2 sequence (GenBank accession number AF033819) was used as the reference for generating the RT-LAMP primers. The sequences of the HIV-1 RT-specific primers and quencher are listed in Table 1 . The RT-LAMP reaction was performed using the following reaction mix: 0.2 mM (final concentration) of each F3 and B3 primers, 1.6 mM of each FIP and BIP primers, 0.8 mM of each LoopF and HEX-LoopB primers, 0.8 M betaine (Sigma-Aldrich), 10 mM MgSO 4 , 1.4 mM dNTPs, 16 ThermoPol reaction buffer (New England Biolabs, Ipswich, MA), 16 U Bst DNA polymerase (New England Biolabs) and 2 U AMV reverse transcriptase (Invitrogen, Carlsbad, CA). The reaction was carried out in a total volume of 25 ml for amplification of extracted nucleic acid, 10 ml of which constituted the sample. For amplification of whole blood specimens, a 100 ml reaction volume was used to facilitate visual detection of amplified products. Whole blood was added directly into the reaction at a total volume of 40 ml, following a 1:4 dilution with red blood cell lysis buffer (2.5 mM KHCO 3 , 37.5 mM NH 4 Cl, and 0.025 mM EDTA), as previously described [21] . The reaction mixture was incubated at 60uC for 60 minutes, using a GeneAmpH PCR System (Applied Biosystems, Foster City, CA) or the NINA heaters. For reactions amplified in the thermalcylcer, an additional two minute heating step of 80uC was added at the end of the amplification cycle to terminate the reaction. The reaction tubes were evaluated for the presence of amplification, following addition of the quencher probe at a 2:1 ratio of quencher to labeled-primer, as previously described [21] . Amplification was determined visually by observing fluorescence in the reaction tubes, using the UV lamp from a ChemiDoc XRS system (Bio-Rad Laboratories, Hercules, CA). Amplification was confirmed by electrophoresis using a 1.2% agarose gel containing SYBRH Safe gel stain (Invitrogen), which was subsequently visualized using the ChemiDoc XRS system. To compare temperature and amplification consistency, three NINA heaters were tested in parallel. The heating reaction was initiated by adding 18 g of CaO to each NINA canister, followed by 6 ml of water. The lid of each canister was then sealed to contain the exothermic reaction. After adding 200 ml of water to each of the sample wells, temperature recording was initiated. Reaction tubes were added to the sample wells once each reaction chamber reached a temperature of 58.5uC. For all samples incubated in the NINA heater, 15 ml of mineral oil was added to the reaction tube during the reaction mix preparation. The samples were incubated in the heaters for a total of 60 minutes. All reactions were carried out in a temperature-controlled laboratory with an ambient temperature of 28uC, unless otherwise stated. Following the amplification reaction, the samples were incubated for two minutes in a heat block set to 80uC. After each amplification cycle, the temperature profile of each device was analyzed by calculating the temperature mean, standard deviation, median, minimum, and maximum from the data provided by the DaqPRO 5300. The stability of the NINA heaters at extreme low and high temperatures was evaluated by placing the canisters in a refrigerator set to 4uC or a 37uC incubator during the length of the amplification reaction. The temperature profiles were recorded and compared to those of reactions that occurred at the laboratory room temperature of 28uC. To determine the sensitivity of RT-LAMP reaction using RTspecific primers, DNA and RNA linearity panels were tested in a thermalcycler. The limit of detection for HIV-1 DNA was 10 copies/reaction. For the RNA linearity panel, the sample containing 1700 copies/reaction was detected in all of the three replicates, while the sample containing 140 copies/reaction was detected in three out of five replicates (60%). For both DNA and RNA linearity panels, the two samples nearest the limit of detection were chosen to further evaluate the performance consistency between the thermalcycler and NINA heaters. In terms of positivity, the amplification results were consistent between all three heaters and the thermalcycler ( Table 2) .\nQuestion: What screening method was evaluated in this study?",
"role": "user"
},
{
"content": "HIV-1 RT-LAMP assay",
"role": "assistant"
}
] |
science.qasa_abstractive_qa
|
science.qasa_abstractive_qa.78
|
[
{
"content": "Read this passage from a research paper and answer the question.\n\nContext: The low-dimensional dense representations for query and passage are computed by PLMs based retrievers from the dual-encoder architecture. Afterward, the candidate passage set could be retrieved efficiently via approximate nearest neighbor algorithms.Existing studies could be categorized into two parts:(1) By optimizing the matching stage: DPR (Karpukhin et al., 2020) is the first study to leverage PLM to empower the retriever by a single vector. Other researches, such asRepBERT (Zhanet al., 2020), ColBERT (Khattab andZaharia, 2020), COIL (Gaoet al., 2021) and Interactor (Yeet al., 2022), obtain multiple vectors for query and passage for matching.(2) By optimizing the representation learning module: RocketQAv1 (Qu et al., 2021) and RocketQAv2 (Ren et al., 2021) boost the representation learning of retriever by leveraging the power of cross-encoder in a cascade or joint manner. Other studies boost the representation learning by designed IR-oriented pre-training tasks.ICT (Leeet al., 2019) treats sentences as pseudo-queries and matched them to the passage they originate from. Condenser (Gao and Callan, 2021) utilizes a novel pre-training task, which can produces an information-rich representation to condense an input sequence. We use the traditional sparse retriever BM25 (Yanget al., 2017) as our first stage method. All experiments are conducted under the same BM25 setting with 1000 retrieved candidates. We conduct experiments with the deep learning framework PaddlePaddle (Maet al., 2019) on up to 4 NVIDIA Tesla A100 GPUs (with 40G RAM). For the GMN module, we use Paddle Graph Learning (PGL) 222https://github.com/PaddlePaddle/PGL, an efficient and flexible graph learning framework based on PaddlePaddle. For training, we used the Adam optimizer (Kingma and Ba, 2014) with a learning rate of 1e-5 for text encoder and 1e-4 for knowledge injector. The model is trained up to 5 epochs with a batch size of 640 and 240 for base and large models respectively.In our experiments, the PLM small, base and large models have 6, 12 and 24 Transformer layers respectively.The text encoder has 9 layers and 21 layers for base and large model respectively, and the knowledge injector both has 3 layers in our experiment. The dropout rates are set to 0.1. The ratio of the positive to the hard negative is set to 1:19.All transformer layers in KERM’s backbone are initialized from ERNIE-2.0 base (Sunet al., 2020b), which is a BERT-like model pre-trained with a continual pre-training framework on multiple tasks. We perform Knowledge-enhanced pre-training on MARCO passage collection to warm up the parameters in knowledge injector, which has 60,000 iterations under the batch size of 256.For a fair comparison, the same pre-training without knowledge enhancement is also conducted on \\textrm{ERNIE}_{\\textrm{base}} re-ranker and all models in ablation studies. Given a query q, passage re-ranking aims at ordering a set of 𝜘 passages, i.e., P = p𝜅 \t𝜘 𝜅=1 , which is usually retrieved from a large-scale passage collection by a retriever, e.g. BM25 [48], DPR [16] etc. In particular, a passage is a sequence of words p = {𝑤𝑝 } |p| 𝑝=1 , where |p| is the length of passage p. Similarly, a query is a sequence of words q = {𝑤𝑞 } |q| 𝑞=1 . Note that a passage p consists of 𝑇 sentences p = {s𝜏 } 𝑇 𝜏=1.\n\nQuestion: How is DPR retriever different from BM25?",
"role": "user"
},
{
"content": "BM25 and DPR are both examples of retrievers used in large-scale passage collection. BM25 is described as a traditional sparse retriever and DPR leverages PLM to empower the retriever by a single vector. How both BM25 and DPR function is not described in detail in this paper and thus their differences cannot be answered in this paper.",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_plos_single_doc_summ
|
science.scientific_lay_summarisation_plos_single_doc_summ.8320
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Analysis of Surface Protein Expression Reveals the Growth Pattern of the Gram-Negative Outer Membrane\nArticle:\nAbstract:\nThe outer membrane( OM) of Gram-negative bacteria is a complex bilayer composed of proteins, phospholipids, lipoproteins, and lipopolysaccharides. Despite recent advances revealing the molecular pathways underlying protein and lipopolysaccharide incorporation into the OM, the spatial distribution and dynamic regulation of these processes remain poorly understood. Here, we used sequence-specific fluorescent labeling to map the incorporation patterns of an OM-porin protein, LamB, by labeling proteins only after epitope exposure on the cell surface. Newly synthesized LamB appeared in discrete puncta, rather than evenly distributed over the cell surface. Further growth of bacteria after labeling resulted in divergence of labeled LamB puncta, consistent with a spatial pattern of OM growth in which new, unlabeled material was also inserted in patches. At the poles, puncta remained relatively stationary through several rounds of division, a salient characteristic of the OM protein population as a whole. We propose a biophysical model of growth in which patches of new OM material are added in discrete bursts that evolve in time according to Stokes flow and are randomly distributed over the cell surface. Simulations based on this model demonstrate that our experimental observations are consistent with a bursty insertion pattern without spatial bias across the cylindrical cell surface, with approximately one burst of ∼10−2 µm2 of OM material per two minutes per µm2. Growth by insertion of discrete patches suggests that stochasticity plays a major role in patterning and material organization in the OM.\nIntroduction:\nThe Gram-negative outer membrane( OM) is a complex[1], non-uniform[2], largely immobile[3] collection of lipids, lipopolysaccharides( LPS), and membrane proteins. This asymmetric organelle is composed of phospholipids and lipoproteins in the inner leaflet, OM proteins spanning the membrane, and LPS in the outer leaflet. Proteins make up approximately two-thirds of the mass of the OM[4], and several OM proteins exhibit distinct subcellular localizations on the bacterial surface( polar, septal, or uniform)[5]. While there is a growing appreciation for the large diversity of outer membrane protein localization patterns[5],[6], insertion patterns have been elucidated only in a few special cases, such as the polar secretion of IcsA in Shigella flexneri[7],[8]; a general understanding of insertion patterning remains lacking. Although the spatiotemporal dynamics of OM protein insertion patterns have typically not been quantitatively measured, electron microscopy studies have shown that newly inserted porins in Salmonella typhimurium appear as discrete clusters[3], and also that LPS arrives in localized patches[9],[10], indicating that growth is the product of discrete events in which many molecules are inserted in bursts. In Gram-negative bacteria, lipids, proteins, and LPS must traverse the inner membrane and the periplasmic space before insertion into the OM, and each step could potentially be spatially localized and/or occur in bursts. Many components of the molecular machinery implicated in OM protein and LPS transport have only recently been identified[11]–[20]. Secreted proteins are synthesized in the cytoplasm and tagged with an N-terminal signal peptide that targets them for transport across the inner membrane via either the Sec or Tat pathways[21], both of which are widely conserved among bacteria. The Sec apparatus is uniformly distributed in the inner membrane, while the Tat pathway is concentrated at the poles; nevertheless, some polar-targeted proteins such as IcsA[22] are transported through the Sec apparatus. Finally, translocation across the cell wall and insertion of folded proteins into the outer membrane is mediated by the BAM( β-barrel assembly machinery) complex[21],[23]. After delivery, the dynamic behavior of OM proteins varies according to subcellular position. Label-and-chase experiments, in which cells are imaged immediately after fluorescent labeling of OM proteins and again during growth without further labeling, show cells that initially have uniformly bright peripheries( indicating that OM proteins are distributed reasonably uniformly across the surface at high density) but transition over several generations to non-uniform fluorescence distributions, ultimately with only originally labeled “old\" poles( poles of progenitor bacteria, versus new poles synthesized during subsequent rounds of bacterial division) remaining bright[24]. While general labeling of all outer membrane proteins using amine-reactive( succinimidyl ester-linked) fluorescent dyes revealed that a subset was freely diffusible, the non-uniform pattern after label-and-chase indicated that other proteins were far less mobile[25]. Similarly, lectin-labeled LPS molecules were virtually immobile on the time scale of growth[25], although crosslinking by the multivalent lectin might have limited LPS mobility in this experiment. Since time intervals on the order of one cell cycle are required to produce a shift in cellular fluorescence distribution, growth itself may be intimately coupled to the localization of older OM proteins. The simplest interpretation of polar retention is that new OM material is inserted along the cylindrical portion of the cell but not at the poles. Thus, material at poles tends to remain at the poles, while older material in the cylindrical portion of the cell is spread out by the insertion of new material that results in growth. To elucidate the role of growth in OM organization, we examined the spatial pattern of initial secretion and subsequent redistribution of the abundant OM protein LamB( maltoporin) in live Escherichia coli cells. LamB is responsible for the uptake of maltose or maltodextrins, which are important carbon sources and the primary breakdown products of starches in the human intestine[26]. This channel protein also transports other carbohydrates including glucose, lactose, and glycerol[27],[28], and is the receptor for bacteriophage λ[29],[30]. In this work, we study the underlying growth pattern of the E. coli OM on generational time scales by adding a single, small, covalently bound fluorophore to LamB. We found that LamB is secreted in discrete punctate spots that diverge from one another during cell elongation, but are virtually immobile in the absence of cellular growth. LamB puncta that are positioned at the poles during septal growth and subsequent division are retained at the poles, consistent with the polar retention characteristic of the OM population as a whole. We used computational modeling of OM growth to demonstrate that the motion of these puncta, including the dilution of older OM components in the cylindrical portion of the cell, may result from discrete insertion events that are temporally stochastic and randomly distributed over the cylindrical cell surface.\nDiscussion:\nOur observations and simulations support a model in which OM growth occurs in discrete insertion events that are uniformly distributed over the cylindrical cell surface, forming an inhomogeneous mixture of newer and older OM on a length scale set by the size of the insertion events. The appearance of fluorescent puncta can be attributed to a large average area per insertion event( Fig. 4A), and simulations based on our fluid dynamics model indicate that the observed growth patterns do not require spatial organization of insertion events, mechanical stresses, or biochemical interactions between molecules. Similarly, the pattern of newly inserted porins in S. typhimurium observed using electron microscopy consists of patches with dimensions of 50–100 nm that increase in number over time but do not increase in size[3]. We observed this patchy insertion directly in our induction time-course experiments, in which longer induction times produced more puncta that were more densely packed on the cylindrical cell surface( Fig. 1), and indirectly in our growth experiments, in which new unlabeled material dispersed the older, labeled OM into punctate spots( Fig. 2). Additionally, other direct and indirect measurements indicate that active translocation events occur at discrete sites on the cylindrical cell surface[40]. While the cylindrical section of the cell undergoes patchy growth, at the division septum, OM material that was once part of the actively growing cylindrical portion of the cell becomes trapped in the inert polar region. Our experiments showed that at short induction times, where new insertion events resulted in new fluorescent puncta, LamB puncta appeared more often in the cylindrical portion of the cell than at the poles( Fig. 1B), indicating that the rate of insertion was indeed lower at the poles. This observation is consistent with our bulk label-and-chase experiments that showed faster dilution of the fluorescence distribution in the cylindrical region, and, after a few generations, the emergence of relatively bright “old\" poles that resulted from the lack of growth in the polar region after the initial labeling( Figs. 2C and 3). While our data cannot be used to rule out the possibility that groups of molecules much smaller than the diffraction limit are occasionally being inserted, when combined with the mechanistic insights from our model, our data suggests that the formation, evolution, and movement of fluorescent OM puncta is well explained by fairly large( ∼10−2 μm2) discrete insertion events that are uniformly distributed over the cylindrical cell surface, with an exponentially distributed duration that has a single, fixed time constant. Within the production and transport pathway of proteins bound for the OM, several possible molecular mechanisms could produce the punctate growth pattern observed here. First, nearly all OM proteins( with the known exception of PulD[41],[42]) are transported from the periplasm, through the rigid cell wall, and inserted into the OM by BAM complexes, and hence one possible interpretation of our data is that the appearance of fluorescent LamB puncta reflects the location of active BAM complexes and OM protein insertion in general. A second, independent possibility is that the uniformly distributed Sec apparatuses[22], responsible for translocating proteins from the cytoplasm to the periplasm where BAM complexes then effect OM insertion, are only active at specific locations, and hence determine the pattern of protein insertion in the OM. A third interpretation arises from the recent discovery that chromosomally expressed mRNAs remain localized to their transcription sites and form diffraction-limited spots, with mRNA diffusion coefficients orders of magnitude lower than expected for free diffusion[43]. While this observation has not been replicated for plasmid-expressed mRNAs, several multicopy plasmids have been shown to localize to a handful of foci in E. coli[44]. The mean duration of an OM insertion event( 2 to 30 sec) is considerably shorter than the half-life of E. coli mRNA( ∼400 sec)[45], thus bursts of cell growth are likely not due to transient mRNA production. However, we speculate that the combination of plasmid localization and mRNA localization to a few foci per cell could give rise to localization of secreted LamB. This list is by no means exhaustive; as data on the lifetimes of candidate molecular complexes( e. g. BAM and Sec) become available, the regions of parameter space we have identified through screening of computational results( Fig. 5) could provide a useful means of distinguishing among possible mechanisms producing the patchy patterns of OM protein insertion. Our observations suggest that bacterial cell surface organization is strongly influenced by growth patterning. Calculations based on ferritin labeling of newly translocated LPS in Salmonella predict that an LPS molecule would diffuse less than 300 nm[9],[10], or approximately one twelfth of the cylindrical circumference, on the time scale of bacterial cell division. These ferritin-labeled LPS molecules initially appear in clusters assumed to be membrane translocation sites. Electron micrographs taken at regular intervals after labeling revealed that these clusters gradually disperse from each other across the surface of Salmonella, beyond the 300 nm diffusion limit. In comparison to the doubling of OM area that occurs on this time scale, it is reasonable to expect that the motion of OM proteins is dominated by patterns of OM incorporation, not diffusion. The spatial pattern of protein expression dictates not only the distribution of proteins within a single cell, but also the distribution of OM proteins in a population. The unequal partitioning of proteins into daughter cells can produce heterogeneity among isogenic bacterial populations, and in a growing bacterial population, the fraction of cells harboring ‘old poles’ shrinks exponentially. If an OM protein is expressed and subsequently repressed early in the growth curve, polar retention will cause it to be concentrated at these few old poles. In this manner, OM protein inheritance could generate heterogeneity based on generational age that has important phenotypic consequences for differential permeability to essential nutrients, drug concentration, or phage infection. The agreement between our simple model and the observed motion of LamB puncta suggests that heterogeneity may be a general outcome in any bacterium in which the OM grows in discrete bursts.",
"role": "user"
},
{
"content": "All Gram-negative bacteria share common structural features , including an inner membrane , a stiff cell wall , and an outer membrane . Balancing growth in all three of these layers is critical for bacterial proliferation and survival , and malfunctions in growth often lead to cellular deformations and/or cell death . However , relatively little is known about how the incorporation of new material into the outer membrane is regulated in space and time . This work combines time-lapse microscopy with biophysical modeling and simulations to examine potential mechanisms by which new material is added to the outer membrane of the rod-shaped Gram-negative bacterium Escherichia coli . Our results indicate that the outer membrane grows in discrete bursts randomly distributed over the cylindrical cell surface . Each insertion event adds a random amount of new material , pushing old material into new locations and thus expanding the cell membrane . Using our biophysical model , we generated simulated fluorescence images and directly compared analyses of our experimental and computational results to constrain the rate and size of bursts of growth . Together , this indicates that growth of the outer membrane does not require spatial regulation , and the stochastic nature of insertion may contribute to the establishment of cellular patterning and asymmetry .",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.9273
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nThe evaluation of interactive machine learning systems remains a difficult task. These systems learn from and adapt to the human, but at the same time, the human receives feedback and adapts to the system. Getting a clear understanding of these subtle mechanisms of co-operation and co-adaptation is challenging. In this chapter, we report on our experience in designing and evaluating various interactive machine learning applications from different domains. We argue for coupling two types of validation: algorithm-centered analysis, to study the computational behaviour of the system; and human-centered evaluation, to observe the utility and effectiveness of the application for end-users. We use a visual analytics application for guided search, built using an interactive evolutionary approach, as an exemplar of our work. Our observation is that human-centered design and evaluation complement algorithmic analysis, and can play an important role in addressing the \"black-box\" effect of machine learning. Finally, we discuss research opportunities that require human-computer interaction methodologies, in order to support both the visible and hidden roles that humans play in interactive machine learning.\n\nCited Abstract(s):\n[1]: We present ReGroup, a novel end-user interactive machine learning system for helping people create custom, on demand groups in online social networks. As a person adds members to a group, ReGroup iteratively learns a probabilistic model of group membership specific to that group. ReGroup then uses its currently learned model to suggest additional members and group characteristics for filtering. Our evaluation shows that ReGroup is effective for helping people create large and varied groups, whereas traditional methods (searching by name or selecting from an alphabetical list) are better suited for small groups whose members can be easily recalled by name. By facilitating on demand group creation, ReGroup can enable in-context sharing and potentially encourage better online privacy practices. In addition, applying interactive machine learning to social network group creation introduces several challenges for designing effective end-user interaction with machine learning. We identify these challenges and discuss how we address them in ReGroup.\n\n[2]: Color enhancement is a very important aspect of photo editing. Even when photographers have tens of or hundreds of photographs, they must enhance each photo one by one by manually tweaking sliders in software such as brightness and contrast, because automatic color enhancement is not always satisfactory for them. To support this repetitive manual task, we present self-reinforcing color enhancement, where the system implicitly and progressively learns the user's preferences by training on their photo editing history. The more photos the user enhances, the more effectively the system supports the user. We present a working prototype system called SelPh, and then describe the algorithms used to perform the self-reinforcement. We conduct a user study to investigate how photographers would use a self-reinforcing system to enhance a collection of photos. The results indicate that the participants were satisfied with the proposed system and strongly agreed that the self-reinforcing approach is preferable to the traditional workflow.",
"role": "user"
},
{
"content": "Other evaluations looked at human behavioural variations with regards to different iML interfaces. [1] compared two interfaces for adding people to online social networks, with and without the interactive component of iML. They looked at behavioural discrepancies in terms of how people used the different interfaces and how they felt. They found that participants were frustrated when model learning was not accurate. [2] compared their adaptive photo enhancement system with the same tool stripped of advanced capabilities, namely the visual system feedback, the optimisation slider functions, and the ordering of search results in terms of similarity. Because photo enhancement quality can be subjective, performance of the iML system was rated by the study participants. In this case, they were satisfied with the iML system and preferred it over more traditional workflows.",
"role": "assistant"
}
] |
science.healthver_entailment
|
science.healthver_entailment.4996
|
[
{
"content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: the drugs do not increase the risk that hospitalized patients with COVID-19 will develop severe complications or die. \n\nAbstract:\nINTRODUCTION The present research aimed to determine the relation between the use of angiotensin-converting enzyme inhibitors (ACE inh) and angiotensinogen receptor blockers (ARBs) and in-hospital mortality of hypertensive patients diagnosed with Covid-19 pneumonia.\nMATERIAL AND METHOD In this retrospective study, we included 113 consecutive hypertensive patients admitted due to Covid-19 infection.\nIn all patients, Covid-19 infection was confirmed with using reverse-transcription polymerase chain reaction.\nAll patients were on ACE inh/ARBs or other antihypertensive therapy unless no contraindication was present.\nThe primary outcome of the study was the in-hospital all-cause mortality.\nRESULTS In total, 113 hypertensive Covid-19 patients were included, of them 74 patients were using ACE inh/ARBs.\nDuring in-hospital follow up, 30.9% [n = 35 patients] of patients died.\nThe frequency of admission to the ICU and endotracheal intubation were significantly higher in patients using ACE inh/ARBs.\nIn a multivariable analysis, the use of ACE inh/ARBs was an independent predictor of in-hospital mortality (OR: 3.66; 95%CI: 1.11-18.18; p= .032).\nKaplan-Meir curve analysis displayed that patients on ACE inh/ARBs therapy had higher incidence of in-hospital death than those who were not.\nCONCLUSION The present study has found that the use of ACE inh/ARBs therapy might be associated with an increased in-hospital mortality in patients who were diagnosed with Covid-19 pneumonia.\nIt is likely that ACE inh/ARBs therapy might not be beneficial in the subgroup of hypertensive Covid-19 patients despite the fact that there might be the possibility of some unmeasured residual confounders to affect the results of the study.",
"role": "user"
},
{
"content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"CONCLUSION The present study has found that the use of ACE inh/ARBs therapy might be associated with an increased in-hospital mortality in patients who were diagnosed with Covid-19 pneumonia.\"]}",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.16997
|
[
{
"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\nSARS-CoV-2 is a new RNA virus which causes coronavirus disease 2019 (COVID-19), declared a pandemic by the World Health Organization (WHO). It triggers an atypical pneumonia that can progress to multiorgan failure. COVID-19 can cause dysregulation of the immune system, triggering an inflammatory response, and simulate haemophagocytic lymphohistiocytosis. Several studies have proposed that anti-IL-6 receptor antibodies, such as tocilizumab, play an important role in the treatment of severe acute respiratory infection associated with SARS-CoV-2. However, the role of anti-IL-1 receptor antibodies, such as anakinra, in the treatment of COVID-19 has not been established. We present a case report of a 51-year-old man diagnosed with severe respiratory infection associated with SARS-CoV-2 that was refractory to antiviral and anti-IL-6 treatment, with a favourable clinical outcome and analytical improvement after treatment with anti-IL-1 (anakinra).",
"role": "user"
},
{
"content": "[\"Case Report\"]",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.66209
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Review of Modern Computational Algorithms for Bayesian Optimal Design \nChapter Title: Contribution and Outline \n1. Abstract of Cited Paper (BIB001): We provide a generic Monte Carlo method to find the alternative of maximum expected utility in a decision analysis. We define an artificial distribution on the product space of alternatives and states, and show that the optimal alternative is the mode of the implied marginal distribution on the alternatives. After drawing a sample from the artificial distribution, we may use exploratory data analysis tools to approximately identify the optimal alternative. We illustrate our method for some important types of influence diagrams. \n2. Abstract of Cited Paper (BIB002): We propose a simulation-based approach to decision theoretic Bayesian optimal design. The underlying probability model is a population pharmacokinetic model which allows for correlated responses (drug concentrations) and patient-to-patient heterogeneity. We consider the problem of choosing sampling times for the anticancer agent paclitaxel, using criteria related to the total area under the curve, the time above a critical threshold and the sampling cost. \n3. Abstract of Cited Paper (BIB003): We review simulation based approaches to optimal design, with an emphasis on problems that cast optimal design as formal decision problems. Under this perspective we approach optimal design problems as expected utility maximization, characterized by an action space, a probability model and a utility function. We first discuss the use of independent Monte Carlo simulation to evaluate expected utility. A variation of such approaches replaces the maximization in the design problem by a simulation problem. This is achieved by augmenting the original probability model on data and parameters to a probability model on data, parameters and actions in such a way that the marginal distribution on the actions is proportional to expected utility. Using power transformations lets us replace the typically flat expected utility function by a more peaked target function, without changing the solution of the optimization. This leads to simulated annealing type algorithms. A interesting class of decision problems are sequential design problems. We discuss simulation based approaches to solve these typically computation intensive decision problems. Another interesting set of decision problems are found in massive multiple comparisons. We discuss the use of posterior simulation to solve such problems. Finally, we show some examples of important alternative, nondecision theoretic approaches. \n4. Abstract of Cited Paper (BIB004): We propose a new stochastic algorithm for Bayesian-optimal design in nonlinear and high-dimensional contexts. Following Peter Muller, we solve an optimization problem by exploring the expected utility surface through Markov chain Monte Carlo simulations. The optimal design is the mode of this surface considered a probability distribution. Our algorithm relies on a “particle” method to efficiently explore high-dimensional multimodal surfaces, with simulated annealing to concentrate the samples near the modes. We first test the method on an optimal allocation problem for which the explicit solution is available, to compare its efficiency with a simpler algorithm. We then apply our method to a challenging medical case study in which an optimal protocol treatment needs to be determined. For this case, we propose a formalization of the problem in the framework of Bayesian decision theory, taking into account physicians' knowledge and motivations. We also briefly review further improvements and alternatives. \n5. Abstract of Cited Paper (BIB005): We describe the use of a successful combination of Bayesian inference and decision theory in a clinical trial design. The trial involves three important decisions, adaptive dose allocation, optimal stopping of the trial, and the optimal terminal decision upon stopping. For all three decisions we use a formal Bayesian decision-theoretic approach. The application demonstrates how Bayesian posterior inference and decision-theoretic approaches combine to provide a coherent solution in a complex application. The main challenges are the need for a flexible probability model for the unknown dose-response curve, a delayed response, the sequential nature of the stopping decision, and the complex considerations involved in the terminal decision. The main methodological features of the proposed solution are the use of decision theory to achieve optimal learning about the unknown dose-response curve, an innovative grid-based approximation method to implement backward induction for the sequential stopping decision, and a utility function for the terminal decision that is based on a posterior predictive description of a future confirmatory trial. \n6. Abstract of Cited Paper (BIB006): Discriminating among competing statistical models is a pressing issue for many experimentalists in the field of cognitive science. Resolving this issue begins with designing maximally informative experiments. To this end, the problem to be solved in adaptive design optimization is identifying experimental designs under which one can infer the underlying model in the fewest possible steps. When the models under consideration are nonlinear, as is often the case in cognitive science, this problem can be impossible to solve analytically without simplifying assumptions. However, as we show in this letter, a full solution can be found numerically with the help of a Bayesian computational trick derived from the statistics literature, which recasts the problem as a probability density simulation in which the optimal design is the mode of the density. We use a utility function based on mutual information and give three intuitive interpretations of the utility function in terms of Bayesian posterior estimates. As a proof of concept, we offer a simple example application to an experiment on memory retention.\n\nLiterature Review:",
"role": "user"
},
{
"content": "A broad range of literature exists on Bayesian optimal experimental design (e.g., , BIB001 , , BIB004 , BIB005 ). This article aims to review those papers which reflect the computational advancements which have allowed solutions to fully Bayesian experimental design problems to be found. Simulation-based design methods have frequently been used in the past two decades (e.g., , BIB002 , BIB004 , BIB003 , BIB005 , BIB006 , Cook et al. [2008], BIB007 ) in which Markov chain Monte Carlo and sequential Monte Carlo algorithms are utilised to solve complex optimal Bayesian design problems (e.g., designing for nonlinear models). Sequential, or adaptive designs, have become increasingly popular in the Bayesian design literature as they provide flexible and efficient designs. Rather than using the same design throughout the experimental process, as in static design problems, the design which maximises the expected utility is chosen at each stage of experimentation, based on the outcomes of previous experiments. Recent developments in static and sequential designs will be discussed further in Sections 4 and 5. There are already several notable review papers on Bayesian experimental design. DasGupta (1995) presents a review of both classical and Bayesian experimental design, with a focus on designing for linear models. Atkinson (1996) reviews classical and pseudo-Bayesian optimal design for linear and nonlinear models. Verdinelli (1992) and present a comprehensive review on Bayesian experimental design, for both linear and nonlinear models. BIB004 provides an overview of simulation-based methods in optimal design. Clyde (2001) presents a broad review on several of the key concepts involved in Bayesian experimental design, such as, choice of utility functions; prior elicitation; and methods for calculating the expected utility. There has been a lack in review papers on fully Bayesian experimental design since the early 2000s. These earlier review papers have often been written from a rather mathematical view point, and have often focused on defining Bayesian design criteria and their relationship to classical design criteria. In the past two decades there has been a substantial increase in computational power and, along with it, the use of Bayesian methodologies for optimal design. At the present time, we have been unable to find any recent review articles which discuss the various algorithms that are used in the Bayesian design literature to solve optimal design problems. Designs for complex models have also received little attention in Bayesian experimental design literature reviews. This article is concerned with reviewing the computational methods that have been used to find fully Bayesian experimental designs and aims to address the aspects of Bayesian experimental design which have received little or no emphasis in previous review papers. This article is aimed at readers with some understanding of Bayesian methods, but not necessarily with knowledge of experimental design. In Section 2 we discuss methods for posterior distribution approximation for use in Bayesian utility functions. In Section 3 we discuss some of the more commonly-used Bayesian utility functions, along with the methods that have been used for their estimation. Sections 4 and 5 provide an overview of the optimisation algorithms that have been used to search for static and sequential Bayesian experimental designs, respectively. We discuss future directions of Bayesian experimental design in Section 6 and provide a conclusion in Section 7.",
"role": "assistant"
}
] |
science.chemprot_ner
|
science.chemprot_ner.962
|
[
{
"content": "Extract entities of these types from the text: [\"Chemical\", \"Protein\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values.\n\nText:\nMitochondrial arginase II modulates nitric-oxide synthesis through nonfreely exchangeable L-arginine pools in human endothelial cells.\nReduced synthesis of nitric oxide (NO) contributes to the endothelial dysfunction and may be related to limited availability of L-arginine, the common substrate of constitutive nitric-oxide synthase (NOS) and cytosolic arginase I and mitochondrial arginase II. To determine whether arginases modulate the endothelial NO synthesis, we investigated the effects of the competitive arginase inhibitor N(omega)-hydroxy-nor-L-arginine (Nor-NOHA) on the activity of NOS, arginases, and L-arginine transporter and on NO release at surface of human umbilical vein endothelial cells (HUVECs). In unstimulated cells, Nor-NOHA dose-dependently reduced the arginase activity with maximal inhibition at 20 microM. When HUVECs were stimulated by thrombin without extracellular L-arginine, Nor-NOHA dose-dependently increased the NOS activity and the NO release with maximal effects at 20 microM. Extracellular L-arginine also dose-dependently increased NO release and arginase activity. When HUVECs were stimulated by thrombin in the presence of 100 microM L-arginine, NOS activity and NO release were similar in untreated and Nor-NOHA-treated cells. However, despite activation of L-arginine uptake, the inhibition of arginase activity by Nor-NOHA was still significant. The depletion of freely exchangeable L-arginine pools with extracellular L-lysine did not prevent Nor-NOHA from increasing the NO release. This indicates the presence of pools, which are accessible to NOS and arginase, but not exchangeable. Interestingly, the mitochondrial arginase II was constitutively expressed, whereas the cytosolic arginase I was barely detectable in HUVECs. These data suggest that endothelial NO synthesis depends on the activity of arginase II in mitochondria and l-arginine carriers in cell membrane.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"N(omega)-hydroxy-nor-L-arginine\", \"Nor-NOHA\", \"l-arginine\", \"L-arginine\", \"nitric-oxide\", \"NO\", \"L-lysine\", \"nitric oxide\"], \"Protein\": [\"arginase I\", \"arginases\", \"mitochondrial arginase II\", \"thrombin\", \"Mitochondrial arginase II\", \"constitutive nitric-oxide synthase\", \"NOS\", \"arginase II\", \"L-arginine transporter\", \"arginase\"]}",
"role": "assistant"
}
] |
science.genia_ner
|
science.genia_ner.625
|
[
{
"content": "Extract all unique entities of these types from the biomedical abstract: [\"CellLine\", \"DNA\", \"Protein\", \"CellType\", \"RNA\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities found for a type, use [].\n\nAbstract:\n\nExpression of either the TCL1 oncogene, or transcripts from its homologue MTCP1 / c6. 1B, in leukaemic and non-leukaemic T cells from ataxia telangiectasia patients. Patients with the recessively inherited disorder ataxia telangiectasia (A-T) have a high level of specific chromosome translocations which can be easily observed in peripheral T cells and show a greatly increased predisposition to leukaemia / lymphoma, mainly of T cell origin. Some translocation cells proliferate into a large clone and may develop into T cell prolymphocytic leukaemia (T-PLL). By the time of diagnosis of T-PLL, the clone contains many more genetic changes in the form of additional translocations. T-PLL is also seen in non-A-T individuals where expression of either TCL1 (at 14q32) or the c6. 1B / MTCP1 A1 transcript (at-Xq28) has been demonstrated in just a few instances. We show here, that expression of TCL1 occurs in leukaemic T cells from A-T patients with chromosome 14 rearrangements. Expression of TCL1 also occurs in the preleukaemic clone cells of A-T patients containing the primary translocation alone. Some expression of TCL1 could also be detected in randomly selected A-T patients without large cytogenetic clones and without any evidence of leukaemic change. We also show that expression of the B1 transcript from a second gene, MTCP1, occurred at a relatively high level only in two T-PLL tumours from A-T patients with t (X;14) translocations whereas the MTCP1 / A1 transcript is much more widely expressed in both tumour and non tumour cells of A-T and non-A-T individuals.",
"role": "user"
},
{
"content": "{\"CellLine\": [], \"CellType\": [\"non - leukaemic T cells\", \"preleukaemic clone cells\", \"leukaemic T cells\", \"tumour and non tumour cells\", \"peripheral T cells\", \"translocation cells\", \"T cell\"], \"DNA\": [\"TCL1 oncogene\", \"MTCP1\", \"MTCP1 / c6 . 1B\", \"at - Xq28\", \"chromosome 14\", \"chromosome translocations\", \"14q32\"], \"Protein\": [\"c6 . 1B / MTCP1 A1 transcript\", \"TCL1\"], \"RNA\": [\"MTCP1 / A1 transcript\", \"B1 transcript\"]}",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_arxiv
|
science.scientific_papers_summarization_single_doc_arxiv.7083
|
[
{
"content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\ntwo non - orthogonal quantum states can not be discriminated with certainty , while the discrimination error can be made smaller as their copies are provided .\nthis leads to one of the well - known no - go theorems , that quantum states can not be copied with certainty @xcite , although approximate quantum cloning is possible with the use of quantum operations and ancillary quantum systems @xcite .\ninterestingly , the impossibility of perfect quantum cloning can be connected to the no - signalling principle in physics , which dictates that information can not be sent faster than light . as a consequence , quantum communication that makes use of ( non - local ) quantum correlations\ncan not be performed faster than light .\nin fact , the relation between the no - cloning theorem and the no - signalling constraint has been established in both qualitative and quantitative terms .\nfor instance , it has been shown in ref .\n@xcite that any no - signalling theory predicting non - locality , i.e. violation of bell inequalities , has a no - cloning theorem .\nthis implies that quantum theory necessarily has the no - cloning theorem .\nin addition , the optimal fidelity of approximate quantum cloning has been derived by applying the no - signalling condition to the cloning process of quantum states @xcite , provided that corresponding quantum operations are positive @xcite . on the other hand , the impossibility of perfect state discrimination can also be connected to the no - signalling condition in a qualitative way , at least through the existing relation that the no - cloning theorem is implied by the no - signalling constraint .\nnow the question naturally arises whether there is a quantitative connection as well .\nin fact , recent progress along this line has shown that the no - signalling condition would imply the optimality of state discrimination , constrained to those figures of merit such as minimum - error discrimination @xcite , unambiguous state discrimination @xcite , and maximum confidence measurement @xcite .\nit is remarkable that the optimality of state discrimination in different figures of merit can be derived from the single condition , no - signalling constraint , despite the fact that quantum theory is not a maximally non - local theory @xcite . in this work ,\nwe relate the no - signalling condition to minimum - error state discrimination of ensembles of quantum states i.e. mixed states .\nthe novelty of this work is that two quantum states to be discriminated between are not purely quantum but mixtures of pure quantum states .\nwe shall derive the minimum error for discriminating between two ensembles of quantum states from the no - signalling constraint . the proof is built on a communication scenario between two parties , alice and bob .\nbefore starting the main proof , for clarity we first fix notations to be used in the communication scenario and then briefly review some known facts about quantum states , minimum - error discrimination and ensemble decompositions .\nwe also restrict our consideration to qubit states , so one can make use of the representation in which a single qubit state is fully characterised by its bloch vector @xmath0 : @xmath1 where @xmath2 .\npure states have unit bloch vectors @xmath3 .\nthe communication scenario to be considered assumes that , sharing entangled states with bob , alice measures her qubits to prepare the ensemble decomposition of bob s state , either one of two ensembles , @xmath4 and @xmath5 , as follows , _\nb^(0 ) & = & p_0 + ( 1-p)|| , + _\nb^(1 ) & = & p_1 + ( 1-p)|--| , [ bobs ] where @xmath6 and @xmath7 are two qubit states for which we are to derive the discrimination bound using the no - signalling constraint , and @xmath8 are two orthogonal quantum states such that it holds @xmath9 , see fig [ fig ] .\nit is convenient to express those quantum states in ( [ bobs ] ) in terms of bloch vectors as follows , _\nb^(i ) = _ b^(i ) ( _ b^(i ) ) , _ i = _ i ( _ i ) , || = ( _ ) , [ parameter ] where @xmath10 .\nthen , the relation between quantum states in ( [ bobs ] ) can be translated to the following relations between bloch vectors _\nb^(0 ) & = & p _ 0 + ( 1-p ) _ , + _\nb^(1 ) & = & p _ 1 + ( 1-p ) _ - . [ vec ]\nrecall that @xmath11 and @xmath12 in ( [ bobs ] ) are two quantum states that we wish to discriminate between .\nthe minimum - error discrimination between two quantum states has been completely analyzed in ref .\n@xcite optimizing over all possible measurement bases .\nthe minimum error , known as the helstrom bound , is p_e= - _ 0 - _\n1,[hel ] assuming that the _ a priori _ probability that the quantum state @xmath13 occurs is equally @xmath14 . here\nthe trace norm for an operator @xmath15 , denoted by @xmath16 , is defined as @xmath17 $ ] . as is shown in ( [ hel ] ) ,\nthe optimal discrimination between two quantum states only depends on their ( trace - norm ) distance separation , and in particular it does not depend on the dimensions of the states . , and\nhere we restrict to two decompositions that can be seen in a cross - section of the bloch sphere spanned by @xmath18 and @xmath19 or @xmath20 . as is shown in ( [ vec ] )\n, @xmath21 can be a mixture of @xmath22 and @xmath23 , or @xmath24 and @xmath25 , both of which point to the same point in the bloch sphere , meaning that they have the same ensemble average.,scaledwidth=32.0% ] we now review properties of _ ensembles _ of quantum states , known as mixed states .\nthese are classical mixtures of some pure quantum states .\nfor instance , each mixed state @xmath26 ( for @xmath10 ) in ( [ parameter ] ) can be expressed as a convex combination of some other pure states @xmath27 , i.e. _ i = _ j _ j |v_j^i v_j^i| .\n[ pure ] note that such a decomposition is not unique @xcite .\nthis means that , in reality , once an ensemble of quantum states is given , its actual decomposition can not be known without knowing how the state was prepared .\none can only deduce ensemble - averaged properties of the state , which does not depend on any particular decomposition . now let us assume that two quantum states in ( [ bobs ] ) are the same . using the expression in ( [ vec ] ) , one can see that the vector of each ensemble of quantum states points to the same point in the bloch sphere , see fig .\nthat is , the two quantum states have different decompositions but have the same ensemble average .\nin addition , each @xmath13 , @xmath28 , is again a mixture of pure quantum states , so finally quantum states of bob in @xmath29 can be expressed as an ensemble of pure quantum states .\nrecall that for any mixed state , there exists higher - dimensional pure quantum state such that partial reduction of the pure state would be the mixed state itself . in this case ,\ntwo - dimensional ancillary systems suffice to purify those quantum states in ( [ bobs ] ) . for two different decompositions of the same state in ( [ bobs ] ) ,\nthe corresponding purifications are equivalent up to local unitary transformations .\nthis simply depends on choice of the measurement basis on the ancillary systems .\nif we assume that alice holds the purification , her measurement will decide the decomposition of bob s quantum state .\nhowever , unless alice announces what basis her measurement was made in , bob will never know which decomposition he has .\nperforming quantum state tomography will only allow bob to understand his quantum state as an ensemble average of other quantum states .\nthis is in fact what prevents the two parties communicating faster than light .\nwe are ready to prove that the no - signalling constraint implies that the helstrom bound in ( [ hel ] ) is optimal .\nconsider that alice and bob are separated in space so that local actions performed by one can not affect the other .\nsuppose that they share copies of entangled states of @xmath30 |_ab = _\nj|a_j_a |b_j_b,[ab ] which is not written in orthonormal basis of alice and bob , so @xmath31 may exceed the rank of systems belonging to two parties . as we have mentioned above , alice chooses measurement basis so that after the measurement on her particle , the ensemble decomposition of bob s state is determined\n. in other words , alice performs a measurement @xmath32 or @xmath33(which are general positive - operator - valued - measures ) , after which decomposition of bob s state will be either @xmath4 or @xmath5 in ( [ bobs ] ) respectively .\nalice actually can make use of the measurement @xmath32 and @xmath33 as an encoding such that a value @xmath31 is encoded by applying @xmath34 .\nbob then decodes the value by discriminating between two ensembles @xmath4 and @xmath5 .\ntwo ensembles are the same , i.e. _\nb^(0 ) = _ b^(1 ) and so their bloch vectors are also the same , i.e. @xmath35 from ( [ vec ] ) , and therefore the value @xmath36 in ( [ vec ] ) is uniquely determined , p=. [ p ] let us now consider a detector that bob applies , that works as follows .\nonce a qubit in a state @xmath37 being measured , the detector gives an outcome @xmath38 with some probability @xmath39 where @xmath10 , i.e. the detector can be thought of being in a black box from which we only know the input / output list .\ntherefore , it fulfills that @xmath40 note that we do not know all the properties of the detector , e.g. the internal structure , etc . , but the probabilities @xmath39 for @xmath10 . for two states @xmath6 and @xmath7\n, we can assume that in general @xmath41 , by which it also follows that @xmath42 .\nwhile alice not announcing which measurement is applied , bob can make guess of it by designing his detector to discriminate the two states @xmath43 of @xmath4 and @xmath44 of @xmath5 .\nif the detector discriminates between @xmath6 and @xmath7 and gives an output @xmath38 ( either @xmath45 or @xmath46 ) , bob will then conclude that the ensemble is @xmath47 .\nnote that alice applies measurement @xmath48 or @xmath49 with equal probabilities , and then the error rate is @xmath50/2.\\ ] ] two ensembles in ( [ bobs ] ) consist of not only @xmath26 but also @xmath51 .\nalthough the detector being designed to discriminate between the two states @xmath43 and @xmath44 in the ensemble , the detector produces some outcomes for @xmath52 and @xmath53 with some probabilities @xmath54 and @xmath55 respectively .\nassume first that alice applies the measurement @xmath32 so that @xmath56 is prepared on the bob s side .\nbob is then with the state @xmath43 with probability @xmath36 , from which the value @xmath45 is found with probability @xmath57 .\nbob is also with the state @xmath53 with probability @xmath58 , from which he can guess the value @xmath45 with probability @xmath59 , a non - negative number .\nfinally , the overall probability that detector s output says the value @xmath45 when alice prepares the ensemble @xmath4 , denoted by @xmath60 denote the probability that the detector says @xmath38 when alice prepares @xmath61 for @xmath10 and @xmath28 . ] and @xmath62 , is greater than or equal to @xmath63 , i.e. , @xmath64 we also have @xmath65 , the overall probability that detector s output says the value @xmath46 when the same ensemble @xmath4 is prepared .\nclearly it holds that @xmath66 next , assume that alice applies the measurement @xmath33 so that @xmath5 is prepared . in the same way we have done for the ensemble @xmath4 , the overall probability that the detector says the value @xmath46 , denoted by @xmath67 , is greater than or equal to @xmath68 , i.e. , @xmath69 it holds again that @xmath70 however , if the following holds @xmath71 bob can discriminate the two ensembles since equations in ( [ b ] ) , ( [ d ] ) , and ( [ e ] ) tell that @xmath72 the above ( [ f ] ) means that , once @xmath34 is applied so that @xmath61 is prepared , the measurement data show more frequency on the value @xmath31 than @xmath73 , through which the two ensemble can be discriminated .\nthis implies that the no - signalling principle excludes ( [ e ] ) and therefore the following holds , @xmath74 combining ( [ a ] ) , ( [ c ] ) , and ( [ g ] ) , we have @xmath75 as well , from ( [ y]),([z ] ) , and ( [ h ] ) we obtain @xmath76 finally from ( [ p ] ) and ( [ i ] ) , the following is the discrimination error limited by the non - signalling principle @xmath77 which is already saturated by the helstrom bound in ( [ hel ] ) .\nin conclusion , we relate two no - go theorems - the no - perfect state discrimination and the no - signalling - by showing that the optimal discrimination between two quantum states is derived from the no - signalling condition .\nit can thus be said that the impossibility of perfect state discrimination is a consequence of the no - signalling condition , not only qualitatively , but also quantitatively as is the case with the no - cloning theorem @xcite .\nfurthermore , it was shown in ref .\n@xcite that the fidelity of optimal quantum cloning converges asymptotically to the fidelity obtained through optimal state estimation .\ntherefore , the quantitative relationship between three no - go theorems- no - signalling , no - cloning , and no - perfect state estimation- has been established at the most basic level i.e. two non - orthogonal quantum states\n. it would be interesting to investigate whether optimal values of all figures of merit in state discrimination , more generally state estimation , of quantum states could be derived solely from the no - signalling condition .\nrecently , it is shown that the optimal measurement for the maximum confidence is also implied by the no - signalling condition @xcite .\nwe thank j. hur , d. song , and h. nha for discussions . this work is supported by the it r@xmath78d program of mke / iita ( 2008-f-035 - 01 ) , the korean government ( moehrd ) ( krf-2005 - 003-c00047 ) , and the korea science and engineering foundation ( r01 - 2006 - 000 - 10354 - 0 ) .",
"role": "user"
},
{
"content": "in this work we relate the well - known no - go theorem that two non - orthogonal ( mixed ) quantum states can not be perfectly discriminated , to the general principle in physics , the no - signalling condition . \n in fact , the minimum error in discrimination between two quantum states is derived from the no - signalling condition .",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.2009
|
[
{
"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:\nParacetamol reduces postoperative pain and rescue analgesic demand after robot-assisted endoscopic thyroidectomy by the transaxillary approach . BACKGROUND Postoperative pain following endoscopic thyroidectomy , although less severe than after open methods , is still a source of marked discomfort and surgical stress . This clinical trial was conducted to determine if repeated intravenous paracetamol could decrease postoperative pain and rescue analgesic requirements after robot-assisted endoscopic thyroidectomy via the transaxillary approach . MATERIALS AND METHODS This prospective , randomized , double-blinded , and placebo-controlled study enrolled 124 women 21-60 years of age who were scheduled for elective gasless robot-assisted endoscopic thyroidectomy via the transaxillary approach . The patients were given placebo or 1 g of paracetamol as a 100 ml solution infused over 15 min 1 h before the induction of anesthesia , and then at 6-h intervals for the following 24 h. RESULTS Postoperative pain scores were significantly lower at 1 , 3 , 6 , and 24 h after surgery in the paracetamol group than in the placebo group . Significantly fewer patients in the paracetamol group received rescue analgesics compared to the placebo group ( 9.5 % vs. 65.6 % , respectively ) . First analgesic time was similar in the two groups . Postoperative nausea ( 44.3 % vs. 22.2 % ) and vomiting ( 21.3 % vs. 6.3 % ) were more frequent in the placebo group than in the paracetamol group . Other postoperative side effects , including sedation , confusion , and pruritus , were similar in the two groups . CONCLUSIONS We concluded that repeated administration of 1 g of intravenous paracetamol over 24 h is easy , effective , safe , and well tolerated for pain management in patients with moderate to severe postoperative pain after gasless robot-assisted endoscopic thyroidectomy performed via the transaxillary approach .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"intravenous paracetamol\", \"analgesic\", \"gasless robot-assisted endoscopic thyroidectomy\", \"robot-assisted endoscopic thyroidectomy by the transaxillary approach\", \"transaxillary approach\", \"Paracetamol\", \"rescue analgesic\", \"endoscopic thyroidectomy\", \"rescue analgesics\", \"elective gasless robot-assisted endoscopic thyroidectomy\", \"anesthesia\", \"placebo-controlled\", \"robot-assisted endoscopic thyroidectomy\", \"placebo\", \"paracetamol\"], \"Outcome\": [\"pain and rescue analgesic demand\", \"sedation , confusion , and pruritus\", \"Postoperative pain scores\", \"analgesic time\", \"Postoperative nausea\", \"vomiting\"], \"Participant\": [\"moderate to severe postoperative pain\", \"124 women\", \"Postoperative pain following endoscopic thyroidectomy\"]}",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.9514
|
[
{
"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\nSince the SARS-CoV-2 pandemic outbreak, growing evidence suggests that patients suffering from COVID-19 are at increased risk of thrombotic events. The sepsis-related activation of the coagulation combined with a high prevalence of common thrombotic risk factors could contribute to this prothrombotic state. Coagulation biomarkers could help in the identification of patients at risk of complications and mortality. The incidence of venous thromboembolic events appears to be increased, especially in severe COVID-19 patients. Based on that knowledge, several societies have provided recommendation on the prevention of venous thromboembolism. In this narrative review, we summarize available epidemiologic data on venous thromboembolism and recommendations on thromboprophylaxis in COVID-19.",
"role": "user"
},
{
"content": "[\"Diagnosis\", \"Treatment\"]",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.4538
|
[
{
"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:\nDoxymycine-cyanoacrylate treatment of recurrent aphthous ulcers . OBJECTIVE This study addressed the efficacy of singularly applied topical doxymycine in the pain relief treatment of recurrent aphthous stomatitis . STUDY DESIGN Thirty-one patients with recurrent aphthous lesions were examined and divided randomly in two groups . Experimental group ( n = 15 ) received a topical application of doxymycine and controls ( n = 16 ) received calcii gluconase in the same manner . Medications were covered by isobutyl cyanoacrylate ( Iso-Dent ) . Application was made only once during the recurrent aphthous ulcer episode . RESULTS Patients recorded their pain level on a visual analog scale for 10 days during healing . Pain decreased more rapidly in the experimental group , and a statistically significant difference ( p < 0.05 ) in the pain intensity was found from the second to the seventh day after application of doxymycine . CONCLUSIONS In recurrent aphthous ulcers , singular treatment of topical doxymycine-cyanoacrylate relieves the pain intensity remarkably for 6 days after a 1 day latency period . Topical doxymycine treatment further exerts potential to directly prevent tissue destruction and to indirectly suppress host inflammatory reaction .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"Doxymycine-cyanoacrylate\", \"doxymycine\", \"isobutyl cyanoacrylate\", \"doxymycine-cyanoacrylate\", \"topical application of doxymycine\", \"controls\"], \"Outcome\": [\"pain level\", \"pain intensity\", \"pain relief\", \"Pain\"], \"Participant\": [\"Thirty-one\", \"aphthous lesions\"]}",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.40248
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Name Lookup in Named Data Networking: A Review \nChapter Title: Hybrid Schemes \n1. Abstract of Cited Paper (BIB001): Complex name constitution plus huge-sized name routing table makes wire speed name lookup a challenging task in Named Data Networking. To overcome this challenge, we propose two techniques to significantly speed up the lookup process. First, we look up name prefixes in an order based on the distribution of prefix length in the forwarding table, which can find the longest match much faster than the linear search of current prototype CCNx. The search order can be dynamically adjusted as the forwarding table changes. Second, we propose a new near-perfect hash table data structure that combines many small sparse perfect hash tables into a larger dense one while keeping the worst-case access time of O(1) and supporting fast update. Also the hash table stores the signature of a key instead of the key itself, which further improves lookup speed and reduces memory use. \n2. Abstract of Cited Paper (BIB002): Abstract A hardware implementation of the pending interest table (PIT) for named data networking (NDN) is presented. One of the major challenges in this research is the per-packet update requirement in NDN packet processing. In general, the data structure of the lookup table is optimized in order to minimize the implementation cost and maximize the lookup performance. However, more computation steps are required to update the highly optimized data structure. Thus, the design of the hardware lookup table needs to tradeoff between the implementation cost, lookup performance and update cost. We employ an on-chip Bloom Filter and an off-chip linear-chained hash table in our design. The lookup operation for an interest/data packet and the associated update operation are integrated into one task. This can effectively reduce the overall processing time and the I/O communications with the software control unit. Our design also incorporates a name ID table ( nidT ) to store all distinct name IDs ( nid ) in the PIT. If the content name in an interest packet can be found in the nidT , then the router needs not look up the forwarding information base (FIB) to determine how to forward the interest packet. This can reduce the workload of the FIB significantly. For proof-of-concept, the proposed hardware architecture is implemented on a FPGA and the overall packet processing rate is about 56 to 60 million packets per second.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Most hybrid solutions exploit the HT either with a BF or trie. Combining the BF and HT creates a few drawbacks. Aggregation is still required and the memory for the HT is large for a fast memory chip. The fast BF concentrates on reducing the times of memory accesses on the slow HT. Nevertheless, this method is currently not a good solution for the aggregated table in the FIB because the BF could damage the hierarchical structure of the name prefix. However, such an approach can be used for the PIT and CS tables because they perform exact matching BIB001 . A hybrid trie and BF method achieves only 1 MLPS for the FIB packet lookup BIB003 . Implementing a solution with specific hardware like the GPU or FPGA is suitable for NDN routers and could reach 60 MLPS. However, such technique suffers from several limitations. Given the per-packet update constraint, low memory density, large power consumption, and high cost, such hardware solutions are unlikely to be implemented in an NDN router BIB002 . Nowadays, the throughput of CPUs has increased because of developments such as CPU caching, high memory bus and bandwidth, and short execution pipelines. The increased demand of virtualized systems requires an elastic infrastructure with less hardware. In addition, some software approaches achieve high performance with less per-packet delay [6].",
"role": "assistant"
}
] |
science.chemsum_single_document_summarization
|
science.chemsum_single_document_summarization.70108
|
[
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nChemical Assistance in Refolding of Bacterial Inclusion Bodies\n\nPaper sections:\n1. Introduction\n<p>The expression of recombinant products is an essential method for producing target proteins and one of the most important unit processes for production of therapeutic protein and structural study [1–6]. There are different expression systems for producing recombinant protein in biotechnology industry. Expression in mammalian cells produces active recombinant proteins that have posttranslation modification but expression by this system is time consuming and expensive. Although bacteria still represent a convenient production system, most of recombinant polypeptides produced in prokaryotic hosts undergo misfolding or incomplete folding processes that usually result in their accumulation as insoluble aggregates, which called inclusion bodies [7–9]. All these studies of recombinant protein expression in Escherichia coli showed that inclusion body formation is the rule rather than the exception.</p><p>In vitro refolding is required for obtaining active protein from inclusion body aggregates which consist of four main steps: inclusion body isolation, solubilization, refolding, and purification. Because of high density of IBs, they separated easily by centrifuge. After isolation of the IBs, the proteins contained in the inclusion bodies need to be solubilized, usually by high concentration of denaturing agents such as urea or guanidinium chloride (Gn-HCl). Then, solubilized IBs are subjected for refolding in specified conditions. Refolding of proteins from inclusion bodies is influenced by different factors including solubilization method, removal of the denaturant, and assistance of refolding by co-solute or additives. The refolding condition is critical in order to obtain acceptable amounts of active protein. It has been known that additives, especially low molecular weight compounds, may significantly enhance the yield of the refolding process. In many cases, inclusion body protein can only be successfully refolded by making use of these effects.</p>\n\n2. Cosolute Assistance\n<p>Low molecular weight additives are usually added to refolding buffer to promote the refolding process. In the case of refolding by dilution, there is a residual concentration of Guanidine HCl or urea in refolding buffer. This low concentration of denaturants holds aggregate prone structures of target protein in soluble and flexible state; thus refolding yield efficiency improves. Due to this reason, additional to residual concentration of denaturants, additives should be added to refolding buffer to decrease the degree of aggregates and misfolds. Co-solute may be classified into two groups: folding enhancer and aggregation suppressor. In principle, folding enhancer enhances protein-protein interaction, while aggregation suppressor reduces side chain interactions [4, 17].</p><p>The folding enhancers facilitate interaction between proteins and thus increase the stability of proteins whereas aggregation suppressor reduces side chain interaction of folding intermediates without interfering with refolding process [4]. Common additives used in refolding of recombinant proteins are shown in Table 1.</p>\n\n3. Arginine (Arg)\n<p>Arginine is one of the useful reagents that are effective in assisting refolding of recombinant proteins from inclusion bodies. It is an aggregation suppressor that improves refolding yield; however, the mechanism of arginine action during refolding is still unclear. ARGININE was first used in refolding of human tissue type plasminogen activator [18, 19]. Since then, it has been used for refolding of a variety of proteins including casein kinase II, [20], Fab antibody fragments [18, 21], growth hormone [22], human gamma interferon, [23], human matrix metalloproteinase-7 human neurotrophins [24] human p53 tumor suppressor protein [25], interleukin-21 [26], interleukin-6 receptor [27], lysozyme [28], single-chain Fv fragments [29], and single-chain immunotoxins [18, 30]. However, arginine may act as a protein-denaturant, which limits the expansion of its applications. Yancey et al. [31] showed that the activity and stability of certain enzymes were perturbed by arginine and concluded that arginine is a protein-destabilizer. Xia et al. [32] have made a similar observation and showed that fluorescence properties of aminoacylase are perturbed by arginine. They interpreted the observed effects of arginine in terms of denaturing property of the guanidinium group, which makes guanidine hydrochloride (Gn-HCl) a strong denaturant. But arginine differs from Gn-HCl in the mode of interactions with proteins.</p>\n\n4. Cyclodextrins (CDs)\n<p>Cyclodextrins have been reported to suppress aggregate formation during the refolding of recombinant proteins. These cyclic glucose macromolecules have hydrophobic cavities and functional groups that can interact with polypeptide chains by weak forces similar to those involved in protein folding. CDs may interact with proteins via hydrophobic forces, hydrogen bonding, and Van der Waals interactions. Charged chemically modified CDs can also bind to the folding polypeptide chain via electrostatic interactions. CDs have been investigated in both dilution additive and artificial chaperone-assisted modes. CDs have been used as stripping agents for removal of detergents in proteins refolded with surfactants [33, 34]. CDs have been used for refolding of recombinant-human growth hormone [35] and α amylase [36].</p>\n\n5. Polyethylene Glycol (PEG)\n<p>Polyethylene glycol is one of the water-soluble polymers that are used for refolding of recombinant proteins [37]. PEG, a polyhydric alcohol, like other polyols is known to stabilize protein conformations as well as to increase the rate of in vitro protein refolding [38, 39].</p><p>It enhances the recovery of active protein by preventing aggregation during refolding [40]. PEG improves in vitro structure formation, which can block aggregation by combining with a molten globule folding intermediate. It stabilizes proteins by chemical modification [41, 42]. PEG binds an intermediate in the folding pathway of carbonic anhydrase, therefore prevents self-association and promotes correct refolding [43–45]. PEG interacts with the hydrophobic side chains exposed upon unfolding at high temperatures [46]. PEG has been successfully used for refolding of interferon [47], xylanase [48], and insulin-like growth factor (IGF-1) [49] from inclusion bodies.</p>\n\n6. Proline (Pro)\n<p>The role of proline was studied for the first time in in vitro refolding of bovine carbonic anhydrase. Proline inhibited bovine carbonic anhydrase aggregation and enabled the protein to return to its native structure. It was proposed that proline acts as a protein-folding chaperone due to the formation of an ordered, amphipathic supramolecular assembly [50]. Later, proline was found to prevent aggregation during hen egg-white lysozyme refolding. Also proline has been used during refolding of arginine kinase [32] and aminoacylase [51]. Proline inhibits protein aggregation by binding to folding intermediates. Proline (1 M) was also found to act as a creatin kinase (CK) folding aid [52]. Results further indicate that proline possibly binds to and stabilizes folding intermediates and reduces the hydrophobic surface of CK, thus inhibiting protein aggregation and improving the final yield of CK. The unusual properties of proline may be due to hydrophobic stacking in aqueous solution and intermolecular self-association [53]. The hydrophobic nature of proline covers hydrophobic region of the proteins, through which this amino acid effectively suppresses protein aggregation [54].</p>\n\n7. Ammonium Sulfate ((NH4)2SO4)\n<p>Salts can stabilize proteins through nonspecific electrostatic interactions at low concentration, dependent on the ionic strength of the medium [55]. At high concentrations, salts exert specific effects on proteins depending on the type and concentration of the salts, resulting in either the stabilization or destabilization of proteins, or even denaturation [56]. Salts usually increase interfacial tension between the protein surface and solvent [57], which leads to increase the solubility of proteins and aggregates, although the stabilizing effect of salts on protein structure is closely correlated to the salting-out effect of salts.</p><p>Ammonium sulfate is widely used as a precipitant for protein purification and for crystallization, as this salt can prevent aggregation. Ammonium salts have been reported to prevent heat-induced aggregation of lysozyme [58]. Also magnesium chloride is another example of salts that has been used in refolding of recombinant proteins [59].</p>\n\n8. Polyols\n<p>Polyols vary in length of carbon chain and number of hydroxyl groups. Polyols used as additives for enhancing refolding yield and stabilize protein structure. The structure-stabilizing polyols are supposed to lead to compact folded state. Bolen and Baskakov demonstrated that the addition of certain osmolytes results in the compaction of RNase A [60]. Polyols have been shown to stabilize the acid-unfolded molten globule state of cytochrome c by enhancing hydrophobic interactions that overcome electrostatic repulsion at low pH between charged residues [61].</p><p>Glycerol has long been known as a protein stabilizer, and its stabilization mechanism has been shown by Timasheff [62]. Glycerol leads to the enhancement of hydrophobic interactions as a consequence of an increase in the solvent ordering around proteins. Comparing with the other polyols, glycerol is a mild stabilizer of protein conformation. Unlike other polyols, Glycerol has unusual properties that decreases the surface tension of water but increases its viscosity [63, 64]. Increasing glycerol concentrations are known to increase the stability of proteins at all concentrations [62, 65] although it decreases refolding at high concentrations due to its ability to considerably slow down the kinetics of refolding, which could result in off-pathway aggregation. An optimum glycerol concentration seems to be critical for striking a balance between its stabilizing effect governed by thermodynamic principles and its effect on the kinetics of folding glycerol successfully used in refolding of lysozyme [66].</p><p>Sorbitol is another polyol that has been shown to reduce aggregation of nucleocapsid protein of rhabdovirus after its expression in Escherichia coli [67]. Sorbitol is likely to exert its effect on folding by altering the structure and properties of water around the folding protein molecule.</p><p>Erythritol is also a protein structure stabilizer and studies showed that it stabilizes proteins to lesser extents compared with sorbitol [64]. The study on citrate synthase aggregation kinetics during refolding in erythritol and other polyols showed the ability of the polyols to stabilize proteins depending on the number of hydroxyl groups in them [68].</p>\n\n9. Stimuli-Responsive Polymers\n<p>Recently it has been shown that smart polymers can act as a pseudochaperonins and precipitation of the protein from its denatured solution by such polymers can yield refolded active protein [69, 70]. Such polymers exist in soluble state in aqueous buffers and can be made insoluble by application of a stimulus. The latter can be a pH change, temperature change, or a change in the concentration of chemical species. This process is reversible. Table 2 represents the smart polymers which are used in refolding of recombinant proteins.</p>\n\n10. Conclusion\n<p>Obtaining a good amount of active protein at low cost is the main objective in in vitro refolding of recombinant protein from bacterial inclusion bodies but there is no single refolding technique or method that satisfies all protein refolding processes. With providing a good condition for in vitro refolding of inclusion body, bacterial system could be an excellent alternative to the mammalian expression system or other expression systems that can directly generate active proteins with a complex disulfide bond structure. In this process, the solubilized target protein is subjected to refolding using different methods. Increasing protein concentrations during the refolding process improves protein refolding and the final refolding yield. Refolding aiding chemicals are helpful agents for increasing protein concentration especially in dilution method. Therefore, application and optimization of additives concentration is a main step in protein refolding and should be done for each protein individually.</p>\n\n\n<p>Examples of buffer additives which may be used to facilitate protein refolding (see text references).</p><p>Lists of smart polymers which are used in refolding procequres.</p>",
"role": "user"
},
{
"content": "Escherichia coli is one of the most widely used hosts for the production of recombinant proteins but insoluble expression of heterologous proteins is a major bottleneck in production of recombinant proteins in E. coli. In vitro refolding of inclusion body into proteins with native conformations is a solution for this problem but there is a need for optimization of condition for each protein specifically. Several approaches have been described for in vitro refolding; most of them involve the use of additives for assisting correct folding. Cosolutes play a major role in refolding process and can be classified according to their function as aggregation suppressors and folding enhancers. This paper presents a review of additives that are used in refolding process of insoluble recombinant proteins in small scale and industrial processes.",
"role": "assistant"
}
] |
science.craftchem_ner
|
science.craftchem_ner.10004
|
[
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: GenesrelatedtothesexualregulatorDoublesexofDrosophilahavebeenfoundtocontrolsexualdevelopmentinawidevarietyofanimals,rangingfromroundwormstomammals.",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_arxiv
|
science.scientific_papers_summarization_single_doc_arxiv.106772
|
[
{
"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:\ncompact stars with strong magnetic fields are rewarding objects to study .\nthey offer the opportunity to probe atoms under the influence of strong magnetic fields not available in laboratory experiments .\nfurthermore , magnetic wds should give information on the origin and evolution of stellar magnetic fields from the main sequence ( e.g. ap stars ) to the final evolutionary stages .\nfor reviews of the subject , cf . angel ( 1978 ) , koester & chanmugam ( 1990 ) , chanmugam ( 1992 ) , schmidt ( 1995 ) , and jordan ( 1997 ) .\njordan lists 50 magnetic wds , but only 15 with extemely high field strengths ( @xmath3 mg ) .\nnearly all magnetic wds have pure hydrogen spectra , while , surprisingly , magnetic dbs have been missing so far . until very recently , the only known magnetic wd with unambiguously identified lines was feige 7 , which shows strong , magnetically split hydrogen _ and _ lines ( achilleos et al .\n1992 ) . however , among the high magnetic field wds there were two stars with strong unidentified features , namely and .\nthe latter has a broad absorption feature at 5500 , and in addition a ly@xmath4 component at 1340 and a stationary h@xmath5 component at @xmath6 , suggesting a high field strength of 670 mg ( liebert et al . 1993 ; glenn at al .\nit was suggested that since the strong features in and can not be hydrogen , the next likely atmospheric constituent , namely he , is responsible for the broad features .\nvery recently jordan et al . ( 1998 ) indeed have succeeded in identifying most of the features as due to in fields between 300 and 700 mg .\nthe hamburg / eso survey for bright qsos has turned out to be a rich source of magnetic wds ( reimers et al .\n1994 , 1996 ) . due to the high spectral resolution ( @xmath7 fwhm ) of the he s objective prism plates taken with the eso schmidt - telescope , the stellar component with identifiable features ( h , he ,\n, ) can be removed from the qso candidate sample ( wisotzki et al .\n1996 ; cf .\nreimers & wisotzki , 1997 , for further references ) .\nthe fraction of non - qsos within the sample of quasar candidates for which follow - up spectroscopy is finally performed therefore contains considerable numbers of peculiar blue stars ; in particular magnetic wds , cvs , and binaries .\nin addition to the stars already published we have roughly 20 further magnetic wd candidates , most of them with hydrogen spectra . in this letter\nwe announce the discovery of seven new peculiar white dwarfs ; four of them are magnetic dbs with detectable zeeman lines .\ncoordinates and magnitudes of the seven objects are given in table [ coordsmag ] .\nthe coordinates are accurate to @xmath8 .\nno finding charts are given since the objects can be localized unambiguously using the _ digital sky survey_. details of the spectroscopic follow - up observations are presented in table [ observations ] .\nspectra are shown in fig .\n[ magdbs ] and fig .\n[ unidwds ] , together with a spectrum of from schmidt et al .\n. lllll object & type & r.a .\n( 2000.0 ) & decl . & @xmath9 ' '' '' + & mag .\ndb & 03:40:36.8 & @xmath1038:43:43 & 16.7 ' '' '' + & mag .\ndb & 01:10:13.2 & @xmath1001:42:03 & 16.4 + & mag .\ndb & 00:29:26.1 & @xmath1021:33:42 & 16.6 + & mag .\ndb & 00:05:39.2 & @xmath1056:44:41 & 15.8 + & unid . & 10:46:09.8 & @xmath1005:18:17 & 17.0 + & unid . & 02:38:41.2 & @xmath1026:43:24 & 16.7 + & unid . & 03:33:20.2 & @xmath1100:07:20 & 16.8 + lllr object & date & u.t . & ' '' '' + & 02/11/95 & 6:31 & 20min ' '' '' + & 23/10/97 & 5:52 & 8min + & 23/10/97 & 1:52 & 10min + & 05/10/96 & 1:40 & 5min + & 05/02/97 & 5:20 & 20min + & 06/12/97 & 4:12 & 5min + & 04/12/97 & 4:57 & 5min + it should be emphasized that all spectra have been taken in the course of quasar candidate follow - up spectroscopy and that typically the spectrophotometry of these snapshot spectra is not sufficiently accurate for determining temperatures of the stars .\nwe notice , however , that the apparent temperature sequence with and as being the hottest stars while and are the coolest among the seven stars is confirmed by the colours estimated from the digitized objective prism spectra .\nfour of the new wds have remarkably similar spectra ( fig . [ magdbs ] ) . in two of them ( and ) the features can be identified with lines split under magnetic fields of roughly 20 mg . as in case of feige 7 ( achilleos et al .\n1992 ) the central @xmath0 component of 5876 as well as the @xmath1 and @xmath2 components are clearly detected .\nthe broad feature between 5000 and 5200 consists of the five @xmath0 components of 4929 .\nthe corresponding blue shifted @xmath2 components are unresolved and are visible as broad absorption at @xmath12 , while the two @xmath1 components are seen at roughly 5270 and 5340 , respectively .\ncomparison with the tables of kemic ( 1974 ) , and also fig .\n3 in achilleos et al .\n( 1992 ) , hints at field strengths in the range of 20 to 25 mg .\nthe additional features between roughly 6200 and 7300 are probably due to the zeeman - triplets of 6678 and 7065 . according to the new computations of schmelcher ( priv\n, the two triplets cover the range longward of 6200 at field strengths of 20 mg .\nthese features are visible as a broad , shallow absorption trough with evidence for individual lines , e.g. at 7200 ( fig .\n[ magdbs ] ) . at 6200\nthere is a blending with the @xmath1 component of 5876 . at higher spectral resolution and @xmath13 the individual triplett components ( 6 lines )\ncan probably identified .\nthe features in the blue part of the spectra can also be attributed to he lines at similar field strengths ; partly to 4471 .\nso far , there is no evidence for hydrogen lines .\nthe other two stars have quite similar spectra , although the features are weaker ( ) , or the spectrum is too noisy to show narrow , weak features ( ) .\nhowever , the gross appearance of the stronger features is rather similar : the shifted @xmath0 components of 5876 and in particular of 4929 at 5100 are detected .\nboth stars apparently have spectra split by magnetic fields in the range of 10 to 30 mg .\nhas an additional strong , sharp h@xmath5 emission line and is probably a binary . besides the magnetic dbs we have found three further stars with peculiar spectra ( fig .\n[ unidwds ] ) , probably also magnetic non - das . has a strong feature at 4430 similar to the 4300 trough in .\nfurther features can be seen roughly at 3400 and 4000 .\nin addition , there is an extremely broad , shallow trough between 5000 and 5800 . although the spectra of and look similar at first glance , jordan et al .\n( 1998 ) on the one hand have _ succeeded _ in identifying most of the features of as stationary transitions in a field between 300 and 700 mg , while on the other hand there is _ no _ possible match of the features in the spectrum of with in magnetic fields of up to @xmath14 mg ( becken & schmelcher , priv comm .\njordan et al . 1998 ) .\nhowever , even in the case of gd229 the strongest features at @xmath15 and at about @xmath16 can only be attributed to two line transitions ( @xmath17 , @xmath18 ) , while other and weaker ones are produced by a superposition of several stationary components .\ntherefore , jordan et al . (\n1998 ) speculated that additional stationary line components must be present which were not included in the current data sets for in a strong magnetic field .\nall available data are restricted to transitions with magnetic quantum numbers @xmath19 .\nwe have also no identification of the shallow features in the spectra of ( at 4650 and 5800 ) and ( at 3900 , 4650 , and 6650 ) . in the former\n, the broad absorption troughs could be molecular bands according to their form , but we do not have an identification . apart from missing identifications , the apparently low temperature of these two objects argues against the presence of lines . we tentatively conclude that neither hydrogen nor helium give a plausible identification of the features .\ngiven the fact that except there is no db in the sample of 50 magnetic wds known today ( jordan 1997 ) , our discovery of four magnetic dbs appears surprising .\nthe question is : why have no magnetic dbs been discovered in the course of proper motion surveys or the pg survey , with exception of ?\nthe probable reason is the rareness of the phenomenon . with respect to the detection of peculiar blue stars ,\nthe he s should be complete to @xmath20 .\nthe he s follow - up observations of candidates from 280 eso / src fields , corresponding to an effective area of @xmath21 square degrees , have revealed 4 magnetic dbs . only is significantly brighter than the pg magnitude limit ( @xmath22 ) . on the same area\nroughly three dozens dbs have been found by the he s ( unpublished ) .\nalthough we are aware of the fact that this is still small number statistics , we tentatively conclude that the incidence of magnetism is not lower in dbs than in das .\n_ acknowledgements .\n_ this work has been supported by grants from the deutsche forschungsgemeinschaft under re 353/391 , re 353/401 and ko 738/71 .\nwe are particulary grateful to p. schmelcher , heidelberg , for the communication of his unpublished calculations .\nachilleos n. , wickramasinghe d.t .\n, liebert j. , saffer r.a . , grauer a.d . , 1992 ,\napj 396 , 273 angel j.r.p . , 1978 , araa 16 , 487 chanmugam g. , 1992 , araa 30 , 143 glenn j. , liebert j. , schmidt g.d . , 1994 , pasp 106 , 722 jordan s. , 1993 , in : burstow m.a .\n( ed . ) , white dwarfs : advances in observation and theory , nato asi series , kluwer , dordrecht jordan s. , 1997 , in : isern i. , hernanz m. , garca - berro e. ( eds . ) , white dwarfs , p. 397\n, kluwer , dordrecht jordan s. , schmelcher p. , becken w. , schweizer w. , 1998 , a&a 336 , l33 kemic s.b .\n, 1974 , jila rep .\n113 koester d. , chanmugam g. , 1990 , rep .\n53 , 837 latter w.b . ,\nschmidt g.d .\n, green r.f .\n1987 , apj 320 , 308 liebert j. , bergeron p. , schmidt g.d . , saffer r.a . , 1993 ,\napj 418 , 426 reimers d. , wisotzki l. , 1997 , the messenger 88 , 14 reimers d. , jordan s. , khler t. , wisotzki l. , 1994 , a&a 285 , 995 reimers d. , jordan s. , koester d. , bade n , khler t. , wisotzki l. , 1996 , a&a 311 , 572 schmidt g.d . , 1995 , rev .\nastr . 8 , 147 schmidt g.d . ,\nallen r.g . ,\nsmith p.s . , liebert j. , 1996 , apj 463 , 320 wickramasinghe d.t . ,\ncropper m. 1988 , mnras 235 , 1451 wickramasinghe d.t . , ferrario l. , 1988 , apj 327 , 222 wisotzki l. , khler t. , groote d. , reimers d. , 1996 , a&as 115 , 227",
"role": "user"
},
{
"content": "we report on seven peculiar faint blue stars found in the course of the hamburg / eso survey ( he s ) which appear to be magnetic white dwarfs ( wds ) with non - hydrogen spectra . \n we show in particular that four of them ( , , , and ) have lines split by magnetic fields of roughly 20 mg , since the @xmath0 components of 5876 and 4929 can be identified unambiguously in their spectra , and the @xmath1 , @xmath2 components can be identified in the spectra of two of these stars ( and ) . besides , these are the first magnetic db white dwarfs discovered so far . in addition , three further wds with broad , \n unidentifiable features have been found : , , and . \n we argue that in all three of these stars can not be responsible for the broad features , and most probably not for the features in and , while it still remains possible that the broad features of are due to .",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_plos_single_doc_summ
|
science.scientific_lay_summarisation_plos_single_doc_summ.3915
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Leadership in Moving Human Groups\nArticle:\nAbstract:\nHow is movement of individuals coordinated as a group? This is a fundamental question of social behaviour, encompassing phenomena such as bird flocking, fish schooling, and the innumerable activities in human groups that require people to synchronise their actions. We have developed an experimental paradigm, the HoneyComb computer-based multi-client game, to empirically investigate human movement coordination and leadership. Using economic games as a model, we set monetary incentives to motivate players on a virtual playfield to reach goals via players' movements. We asked whether( I) humans coordinate their movements when information is limited to an individual group member's observation of adjacent group member motion,( II) whether an informed group minority can lead an uninformed group majority to the minority's goal, and if so,( III) how this minority exerts its influence. We showed that in a human group – on the basis of movement alone – a minority can successfully lead a majority. Minorities lead successfully when( a) their members choose similar initial steps towards their goal field and( b) they are among the first in the whole group to make a move. Using our approach, we empirically demonstrate that the rules of swarming behaviour apply to humans. Even complex human behaviour, such as leadership and directed group movement, follow simple rules that are based on visual perception of local movement.\nIntroduction:\nSchools of fish and flocks of birds move collectively towards a spatial goal[1],[2] despite their large local group sizes and therefore reduced capacity for global or inter-individual communication across the group[3],[4]. Behavioural modelling[5]–[7] and empirical research[8]–[10] have shown that in diverse species, including humans[11],[12], local individual rules are adequate to generate complex collective behaviour at the group level[13]–[15]. There is increasing evidence[9],[16],[17] that not only large swarms but also small heterogeneous groups may be coordinated by local interaction rules. To explain this “swarming” phenomenon in animals and humans, Couzin et al.[18] created a model in which group locomotion emerges from individuals steering their motion based on the moves of local neighbours. Their model comprises three fundamental parameters described by Aoki[19] and Reynolds[20], stating that members of a swarm( a) become attracted to neighbours' positions within a local range( cohesion);( b) align with neighbours' direction and speed within this range( alignment) and c) avoid neighbours within a predefined radius( collision avoidance). In order to incorporate the influence of those individuals with information about a preferred goal, a weighted direction vector was added[18] to investigate the dilemma of informed individuals pursuing their preferred goal while trying to remain with the group[21]. In their computer simulation model, Couzin et al.[18] deduced that a proportionally small number of directionally informed individuals can channel the naïve( uninformed) members of the swarm to the target of the directionally informed. Neither the informed nor the naïve need to recognise each other, be aware of the informational gap, or practise active signalling. Assumptions about inherent personal distinctions( e. g. personality traits or social cues) need not to be present in order to explain effective movement leadership. The purpose of the present study was to test whether such “swarm-like” human movement and leadership behaviour empirically holds for a small group of humans restricted to ‘reading/transmitting’ only movement behaviour. To do so, we developed the computer-based HoneyComb multi-client game as our investigative platform. The elements of this virtual game were designed to eliminate all sensory/communication channels except the perception of player-assigned avatar movements on the playfield. To create experimental factors of individual motivation towards the two swarming behaviours – “cohesion” and “alignment” – without experimenter's direct behavioural instructions, we implemented within-group graded monetary incentives, an informed minority of players with a higher-rewarded target, and an uninformed majority of players with lower but equal reward targets. This experimental paradigm differs substantially from the approach taken in three other studies on human movement and leadership by Dyer et al.[11],[22] and Faria et al.[23], where the minority leadership prediction of the Couzin et al. model[18] was investigated in a face-to-face group situation. All three studies conducted live experiments of humans walking in a circular arena with a landmark randomly assigned as a target to the informed individuals. This naturalistic approach has benefits in terms of ecological validity. But these studies fall short in discretising the spectrum of human communication: defining where communication among humans begins in the phenomenon of leading human group movement. Firstly, face-to-face procedures, despite instructions not to communicate, could not preclude the transmission of non-verbal cues between participants( e. g. eye contact, facial expressions, shared/non-shared social categories of age and gender). These cues likely functioned to signal intention towards the goal or to unite participants to “flock” based on the perceived affiliation to the same social category, almost certainly confounding results. Second, instruction methodology in these studies was direct, which is incongruent with the above-mentioned swarming conditions as “local” rules. In the three studies' standard set of instructions, the model[18] parameter “group cohesion” was directly translated into the investigator's explicit instruction to participants to “remain as a group of eight( ten resp.) ”. “Collision avoidance” was implemented by the instruction “to stay within an arm's length of another individual”[11]. Our platform ensures internal validity because the study design of humans moving their avatars on a virtual playfield eliminates all sensory/communication channels between the human participants other than observed directional movement. By using monetary incentives we introduce a motivational factor for group movement but avoid any direct instruction; therefore, any potential leadership influence of movement remains with the transmitting/reading of participants' movements rather than external or internal socio-cognitive sources. The goals of our study are to address three fundamental questions regarding basic human coordination mechanisms and the emergence of patterns of group leadership in the complete absence of communication mechanisms and pre-knowledge of information differentiation other than the perceived movement of others:( I) Can humans coordinate their avatars' movement under such extremely restricted communication conditions?( IIa) Can the informed minority lead the uninformed majority to their goal field,( IIb) even with the additional restriction for each group member to perceive only local movement relative to his/her proximity?( III) Which movement behaviour of the minority is the best predictor for the success of leading the majority to a target?\nDiscussion:\nWe confirmed that even in humans, self-organised patterns of collective movement emerge without assuming global information, strategic or other cognitive complex considerations, or any other sort of communication besides transmitting/reading one's own and other participants' movement behaviour. We could predict the most effective locomotive behaviour of an informed minority to pull an uninformed majority's avatar movements to a specific goal field( i. e. invoking effective leadership) when all channels of communication were reduced to pure movement on a virtual playfield, even when perception radius limited transmitting/reading movement information to/from local neighbours[3],[4],[34]. The successful locomotive pattern of the informed minority players was achieved by moving their avatars analogously into the same direction, and – when perception radius was restricted to only neighbouring fields – making use of an initial mover's effect[28]. The results show that the immediacy of the very first move of the informed minority players and consistency of their initial move – compared to their overall locomotive pattern, path similarity, path length, movement latency, and starting order – are the most effective behaviours for influencing the majority to follow. Personality traits and computer literacy of informed minority players were not crucial to their success in pulling the uninformed majority's avatars to their preferred goal field. Our results corroborate one of the core assumptions of Couzin et al. 's[18] modelling of the synoptic process of individuals coordinating via movement as a channel of information transfer. This empirical evidence that the ability exists to coordinate behaviour via the transmitting/reading of movement alone might have high adaptive value in situations where human groups experience restricted communication and therefore are forced to lead solely via movement trends of immediacy and consistency. Applied to emergency, rescue, and sport scenarios where face-to-face communication is hindered but movement is still possible, the group success rate towards a desired goal could be maximised via movement initiation that is decisive: i. e. consistent, immediate and therefore consequent. For instance, leadership personnel of such groups could be trained accordingly in using simple behavioural mechanisms for leading masses of uninformed people to emergency exits or secure areas. But the question here is whether our results – obtained in a virtual environment where movement was performed by representations of the group participants as black dots on a virtual playfield – are applicable to these actual( vs. avatar) human movement scenarios. It can be argued that the representation of the human participants in the rather abstract avatars of black dots in a virtual environment exacerbated the lack of sense of connection between the participants[35]. Because our avatars were designed to reduce social meanings and social roles to a minimum, coupled with the work by others showing avatars mediate the body in virtual settings[36] and that anthropomorphic as well as polymorphic representations in a virtual environment facilitate feelings of embodiment[37], we felt confident that human behavioural association would not be diminished by not transmitting influences of body shape, gender, age and other hierarchical standings[38] by our HoneyComb avatars. Also, the physical presence of their co-players sitting at tables besides them – although behind partitions and with earplugs – likely confirmed feelings of human embodiment. Although we did not ask participants whether they felt sufficiently represented by their avatar and also perceived their co-players as humans moving on a field in this study, the high percentage of participants reporting high levels of embodiment in a subsequent, yet to be published study might hold as an additional argument. The use of movement as a basic signal to maintain group cohesion and indicate direction appears to be an innate behaviour that does not require complex cognition[39],[40]. As in models describing collective pedestrian behaviour as “spatiotemporal patterns” emergent “through the nonlinear interactions of pedestrians”[12, p. 368], we could empirically show that collective group movement and leadership – in other words non-random behaviour – emerged empirically from implementing the assumed parameters of the swarm behaviour models[18]–[20] into incentives within our HoneyComb virtual movement game. Unlike studies on pedestrian behaviour[16],[17],[41], we did not base our approach on the sociological concept of a group allowing social interaction and social ties between individuals. Nevertheless, fundamental human mechanisms of collective movement as trails, unidirectional lanes or a basic principle of least effort[7] identified by these researchers are likely to underlie the movement patterns identified in our study. To explain such complex collective phenomena in humans, we needed neither to assume humans communicating with each other, nor to apply other higher order cognitive and/or social competence nor mutual acknowledging of intentional behaviour in leading( and being led) as none of the players knew that there was any informational difference in the group. Methodologically, this means that functional behavioural complexity at the group level does not necessarily equate with an underlying cognitive complexity at the individual level, but can also be explained by distributed embodied cognition[39], local heuristics[42] or even the principle of least effort[7]. Due to the physical restrictions of our study setup, as compared to the Dyer et al. experiment setting[11],[22],[23], it is highly unlikely that players were able to signal each other their intention, cognitive or motivational state. The rationale behind our study's strident physical restrictions was to focus on mere movement behaviour as a type of inadvertent social cue or – even less – the possibility that the players do not apply mutual responsiveness but in the simplest case practise spatial pattern recognition[39], suggesting the most reductionist explanation possible for effective leadership behaviour in human groups. Methodologically, this study's application of the HoneyComb paradigm makes heuristic use of existing formal models of swarming behaviour[18]–[20] in order to( a) implement the model parameters into experimentally set behavioural incentives to participants,( b) test whether their empirical behaviour fits specific model predictions in this study of leadership of a minority over a majority, and( c) describe patterns of this observed behaviour. With step( c) we reach beyond the existing formal models we built upon. The next investigations will likely entail additional applications of the HoneyComb computer-based multi-client game approach to analyse the process patterns on a more sophisticated level, i. e. Markov chains and topological models, and design and execute further experiments in order to identify additional influencing factors of leadership( e. g. initial positioning, visual appearance, communication, and the identifiability of informed minorities). Along the lines of the experimental studies on schooling fish by Couzin et al.[43] and Tunstrøm et al.[44], we could gain deeper insights into the mutual dependence of leadership and followership by manipulating size as well as informational status of the subpopulations of a group and of the size of the group as a whole. We have already run further HoneyComb paradigm based experiments where we manipulated the colours of the avatars in order to investigate how the distinction of “minimal groups”[45] of similar individuals can influence their flocking behaviour and their mutual perception as well as their identification with “their” group. Another application of the paradigm has been to install two minorities with opposing goal fields to investigate how leadership and group fission and fusion work under these conditions. In sum, our approach and the results of this study provide a new paradigm on boundaries of communication in the influence of coordinated human movement that could readily be extended to additional questions regarding consensus and leadership dynamics.",
"role": "user"
},
{
"content": "Our article gives empirical evidence of group coordination mechanisms and basic rules of leadership that assist in leading a human group . Using a computer-based multi-client game that blocks explicit signals or other typical human information transfer , we offer a model of human group movement patterns applicable to group scenarios such as emergency , rescue , and sports where inter-individual communication is hindered but the reading of movement is still possible . Results show that even in these communication-restricted situations , movement of an informed minority that is efficient and consistent can effectively pull the majority towards a target goal .",
"role": "assistant"
}
] |
science.covidfact_entailment
|
science.covidfact_entailment.805
|
[
{
"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: Using experimental data from bnei brak, israel, to estimate the relative susceptibility and infectivity of children\n\nText:\nOne of the significant unanswered questions about COVID-19 epidemiology relates to the role of children in transmission.\nThis study uses data on infections within households in order to estimate the susceptibility and infectivity of children compared to those of adults.\nThe data were collected from households in the city of Bnei Brak, Israel, in which all household members were tested for COVID-19 using PCR (637 households, average household size of 5.3).\nIn addition, serological tests were performed on a subset of the individuals in the study.\nInspection of the PCR data shows that children are less likely to be tested positive compared to adults (25% of children positive over all households, 44% of adults positive over all households, excluding index cases), and the chance of being positive increases with age.\nAnalysis of joint PCR/serological data shows that there is under-detection of infections in the PCR testing, which is more substantial in children.\nHowever, the differences in detection rates are not sufficient to account for the differences in PCR positive rates in the two age groups.\nTo estimate relative transmission parameters, we employ a discrete stochastic model of the spread of infection within a household, allowing for susceptibility and infectivity parameters to differ among children and adults.\nThe model is fitted to the household data using a simulated maximum likelihood approach.\nTo adjust parameter estimates for under-detection of infections in the PCR results, we employ a multiple imputation procedure using estimates of under-detection in children and adults, based on the available serological data.\nWe estimate that the susceptibility of children (under 20 years old) is 43% (95% CI: [31%, 55%]) of the susceptibility of adults.\nThe infectivity of children was estimated to be 63% (95% CI: [37%, 88%]) relative to that of adults.",
"role": "user"
},
{
"content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"This study uses data on infections within households in order to estimate the susceptibility and infectivity of children compared to those of adults.\", \"To estimate relative transmission parameters, we employ a discrete stochastic model of the spread of infection within a household, allowing for susceptibility and infectivity parameters to differ among children and adults.\"]}",
"role": "assistant"
}
] |
science.acl_arc_intent_classification
|
science.acl_arc_intent_classification.1426
|
[
{
"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:\nintroduction\n\nContext before:\nBut their importance has grown far beyond machine translation: for instance, transferring annotations between languages (Yarowsky and Ngai 2001; Hwa et al. 2005; Ganchev, Gillenwater, and Taskar 2009); discovery of paraphrases (Bannard and Callison-Burch 2005); and joint unsupervised POS and parser induction across languages (Snyder and Barzilay 2008). MT system combination (Matusov, Ueffing, and Ney 2006). Word alignments are used primarily for extracting minimal translation units for machine translation (MT) (e.g., phrases [Koehn, Och, and Marcu 2003] and rules [Galley et al. 2004; Chiang et al. 2005]) as well as for \u0000\u0000\u0000\u0000\u0000\u0000\n\nCitation:\nBut their importance has grown far beyond machine translation : for instance , transferring annotations between languages ( Yarowsky and Ngai 2001 ; Hwa et al. 2005 ; Ganchev , Gillenwater , and Taskar 2009 ) ; discovery of paraphrases ( Bannard and Callison-Burch 2005 ) ; and joint unsupervised POS and parser induction across languages ( Snyder and Barzilay 2008 ) .\n\nContext after:\nIBM Models 1 and 2 and the HMM are simple and tractable probabilistic models, which produce the target sentence one target word at a time by choosing a source word and generating its translation. IBM Models 3, 4, and 5 attempt to capture fertility (the tendency of each source word to generate several target words), resulting in probabilistically deficient, intractable models that require local heuristic search and are difficult to implement and extend. Many researchers use the GIZA++ software package (Och and Ney 2003) as a black box, selecting IBM Model 4 as a compromise between alignment quality and efficiency. All of the models are asymmetric (switching target and source languages produces drastically different results) and the simpler models (IBM Models 1, 2, and HMM) do not enforce bijectivity (the majority of words translating as a single word).",
"role": "user"
},
{
"content": "Motivation",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.51814
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Statistical Modeling of Polarimetric SAR Data: A Survey and Challenges \nChapter Title: G and G 0 Distributions \n1. Abstract of Cited Paper (BIB001): Remote sensing data, and radar data in particular, have become an essential tool for environmental studies. Many airborne polarimetric sensors are currently operational, and many more will be available in the near future including spaceborne platforms. The signal-to-noise ratio of this kind of imagery is lower than that of optical information, thus requiring a careful statistical modelling. This modelling may lead to useful or useless techniques for image processing and analysis, according to the agreement between the data and their assumed properties. Several distributions have been used to describe synthetic aperture radar (SAR) data. Many of these univariate laws arise by assuming the multiplicative model, such as Rayleigh, square root of gamma, exponential, gamma, and the class of K I distributions. The adequacy of these distributions depends on the detection (amplitude, intensity, complex, etc.), the number of looks, and the homogeneity of the data. In Frery et al. (1997), another class of univariate distributions, called G, was proposed to model extremely heterogeneous clutter, such as urban areas, as well as other types of clutter. This article extends the univariate G family to the multivariate multi-look polarimetric situation: the G p law. The new family has the classical polarimetric multi-look K p distribution as a particular case, but another special case is shown to be more flexible and tractable, while having the same number of parameters and fully retaining their interpretability: the G 0 p law. The main properties of this new multivariate distribution are shown. Some results of modelling polarimetric data using the G 0 p distribution are presented for two airborne polarimetric systems and a variety of targets, showing its expressiveness beyond classical models. \n2. Abstract of Cited Paper (BIB002): In this paper we demonstrate that simple yet exible modelling of multilook polarimetric synthetic aperture radar (PolSAR) data can be obtained through a relaxation of the Wishart model. The degrees of freedom of the complex Wishart distribution is treated as a spatially nonstationary parameter, which is allowed to vary between thematic classes and segments of the PolSAR scene. \n3. Abstract of Cited Paper (BIB003): Several characterizations of the Generalized Inverse Gaussian (GIG) distribution on the positive real line have been proposed in the literature, especially over the past two decades. These characterization theorems are surveyed, and two new characterizations are established, one based on maximum likelihood estimation and the other is a Stein characterization. \n4. Abstract of Cited Paper (BIB004): The K distribution can arguably be regarded as one of the most successful and widely used models for radar data. However, in the last two decades, we have seen tremendous growth in even more accurate modeling of radar statistics. In this regard, the relatively recent G0 distribution has filled some deficiencies that were left unaccounted for by the K model. The G0 model, in fact, resulted as a special case of a more general model, the G distribution, which also has the K model as its special form. Single-look and multilook complex polarimetric extensions of these models (and many others) have also been proposed in this prolific era. Unfortunately, statistical analysis using the polarimetric G distribution remained limited, primarily because of more complicated parameter estimation. In this paper, the authors have analyzed the G model for its parameter estimation using state-of-the-art univariate and matrix-variate Mellin-kind statistics (MKS). The outcome is a class of estimators based on the method of log cumulants and the method of matrix log cumulants. These estimators show superior performance characteristics for product model distributions such as the G model. Diverse regions in TerraSAR-X polarimetric synthetic aperture radar data have also been statistically analyzed using the G model with its new and old estimators. Formal goodness-of-fit testing, based on the MKS theory, has been used to assess the fitting accuracy between different estimators and also between the G, K, G0, and Kummer- U models.\n\nLiterature Review:",
"role": "user"
},
{
"content": "It is shown that the G distribution and the G 0 distribution have a good representation of extremely heterogeneous regions such as urban areas BIB002 . Especially, the G 0 distribution has the same number of parameters as the K distribution, but without complex special functions like the Bessel function which requires intensive computations BIB001 BIB002 . The G distribution assumes that the texture parameter obeys the Generalized Inverse Gaussian (GIG) law which is characterized by the PDF BIB001 BIB004 p(x; a, b, p) = 1 where a > 0, b > 0 and p is a real parameter. The mean value of this distribution is µ = b a which can be further rewritten as follows by replacing √ ab with ω to reduce the number of parameters Substituting (51) into (39) and (40), and calculating the integral using (A1) leads to and where η = . The above expressions are the PDFs of the scattering vector and the sample covariance matrix following G distributions BIB001 BIB005 . The G 0 distribution can be obtained from the G distribution by letting a → 0. Representing the modified Bessel function K v (z) using (A6), Equation (49) becomes If a → 0, p = −λ, b = 2β, then after calculating the integral via (A7), the PDF of the GIG distribution is reduced to Equation (55) is known as the inverse gamma distribution, or the reciprocal of the gamma distribution, with mean value µ = β λ−1 . Let τ = x µ to ensure the mean value of the texture τ is equal to 1, the PDF becomes The PDFs of the scattering vector and the sample covariance matrix of the G 0 distribution can be obtained by plugging the texture distribution into BIB003 and (40) respectively, and calculating the integral by (A9), giving and Another extreme case of the GIG distribution is the gamma distribution when b → 0, which leads to the K distribution BIB001 .",
"role": "assistant"
}
] |
science.bioasq_factoid_qa
|
science.bioasq_factoid_qa.674
|
[
{
"content": "Answer the following biomedical question based on the given context. Provide only the answer without additional explanation.\n\nQuestion: Glecaprevir and Pibrentasvir are used for tratment of which disease?\n\nContext: Glecaprevir and pibrentasvir for 12 weeks for hepatitis C virus genotype 1 infection and prior direct-acting antiviral treatment.\nThis phase 2, open-label study (MAGELLAN-1) evaluated the efficacy and safety of glecaprevir (GLE) + pibrentasvir (PIB) ± ribavirin (RBV) in HCV genotype 1-infected patients with prior virologic failure to HCV DAA-containing therapy.\nCONCLUSION: The combination of GLE and PIB was highly efficacious and well tolerated in patients with HCV genotype 1 infection and prior failure of DAA-containing therapy; RBV coadministration did not improve efficacy.\nGlecaprevir and pibrentasvir yield high response rates in patients with HCV genotype 1-6 without cirrhosis.\nThe efficacy and safety of 8- and 12-week treatments with glecaprevir (ABT-493; NS3/4A protease inhibitor) and pibrentasvir (ABT-530; NS5A inhibitor) were evaluated in non-cirrhotic patients with chronic HCV genotype 1-6 infection.\nCONCLUSIONS: Glecaprevir plus pibrentasvir was well tolerated and achieved high sustained virologic response rates in HCV genotypes 1-6-infected patients without cirrhosis following 8- or 12-week treatment durations.LAY SUMMARY: The combination of direct-acting antivirals glecaprevir and pibrentasvir comprise a once-daily, all-oral, pangenotypic treatment for HCV genotype 1-6 infection.\nGlecaprevir and pibrentasvir are direct-acting antiviral agents being developed as combination therapy for the treatment of chronic hepatitis C virus infection.\nThe combination of glecaprevir (formerly ABT-493), a nonstructural protein 3/4A (NS3/4A) protease inhibitor, and pibrentasvir (formerly ABT-530), an NS5A protein inhibitor, is being developed as treatment for HCV genotype 1 to 6 infection.\n<b>BACKGROUND AND OBJECTIVE</b>: Glecaprevir and pibrentasvir are pangenotypic direct-acting antiviral agents for the treatment of chronic hepatitis C virus infection.\nGlecaprevir and pibrentasvir are direct-acting antiviral agents being developed as combination therapy for the treatment of chronic hepatitis C virus infection.\nBACKGROUND AND OBJECTIVE: Glecaprevir and pibrentasvir are pangenotypic direct-acting antiviral agents for the treatment of chronic hepatitis C virus infection.\nThe combination of glecaprevir (formerly ABT-493), a nonstructural protein 3/4A (NS3/4A) protease inhibitor, and pibrentasvir (formerly ABT-530), an NS5A protein inhibitor, is being developed as treatment for HCV genotype 1 to 6 infection.\nThis article summarizes the milestones in the development of glecaprevir/pibrentasvir leading to its first global approval in the EU and subsequent approval in the USA for chronic HCV infection.\nThe efficacy and safety of 8- and 12-week treatments with glecaprevir (ABT-493; NS3/4A protease inhibitor) and pibrentasvir (ABT-530; NS5A inhibitor) were evaluated in non-cirrhotic patients with chronic HCV genotype 1-6 infection.\nFour patients discontinued the trial treatment prematurely because of adverse events; three of these patients had a sustained virologic response.<br><b>CONCLUSIONS</b>: Treatment with glecaprevir and pibrentasvir for 12 weeks resulted in a high rate of sustained virologic response in patients with stage 4 or 5 chronic kidney disease and HCV infection.\nThis article summarizes the milestones in the development of glecaprevir/pibrentasvir leading to its first global approval in the EU and subsequent approval in the USA for chronic HCV infection.<br>\nWe evaluated the safety and efficacy of 8 and 12 weeks' treatment with glecaprevir/pibrentasvir in patients with HCV genotype 2, 4, 5, or 6 infection without cirrhosis in 3 separate phase 3 trials.<br><b>METHODS</b>: We performed 2 open label, single-arm studies (SURVEYOR-II, Part 4 and ENDURANCE-4) and a randomized, double-blind, placebo-controlled study (ENDURANCE-2).\nAmong patients receiving glecaprevir/pibrentasvir for 12 weeks, rates of SVR12 were 99.5% (95% CI, 98.5-100) in those infected with HCV genotype 2 and 99% (95% CI, 97.6-100) in those infected with HCV genotype 4, 5, or 6.\nTreatment with glecaprevir and pibrentasvir for 12 weeks resulted in a high rate of sustained virologic response in patients with stage 4 or 5 chronic kidney disease and HCV infection.\nCoadministration of glecaprevir 400 mg increased pibrentasvir 120 and 40 mg steady-state C and AUC values to 2.9-6.3-fold, and coadministration of glecaprevir 700 mg increased pibrentasvir 160 mg steady-state C and AUC values to up to sevenfold of the values when pibrentasvir was administered alone.\nWe conducted a multicenter, open-label, phase 3 trial to evaluate the efficacy and safety of treatment with the combination of the NS3/4A protease inhibitor glecaprevir and the NS5A inhibitor pibrentasvir for 12 weeks in adults who had HCV genotype 1, 2, 3, 4, 5, or 6 infection and also had compensated liver disease (with or without cirrhosis) with severe renal impairment, dependence on dialysis, or both.",
"role": "user"
},
{
"content": "Hepatitis C virus infection",
"role": "assistant"
}
] |
science.genia_ner
|
science.genia_ner.182
|
[
{
"content": "Extract all unique entities of these types from the biomedical abstract: [\"CellLine\", \"DNA\", \"Protein\", \"CellType\", \"RNA\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities found for a type, use [].\n\nAbstract:\n\nAn intricate arrangement of binding sites for the Ets family of transcription factors regulates activity of the alpha 4 integrin gene promoter. alpha 4 integrins mediate cell-cell and cell-extracellular matrix interactions that are critical for maturation and function of the immune system as well as differentiation of skeletal muscle. Here we examine molecular mechanisms controlling the pattern of alpha 4 expression. The activity of constructs containing 5' deletion mutants of the alpha 4 gene promoter was compared in transfection assays into cell lines that express alpha 4 and cell lines that do not. The sequence between position-42 and-76 base pairs (bp) was required for efficient transcription in cells that express alpha 4, but it showed no activity in HeLa cells, which do not express alpha 4. Three binding sites for the Ets family of transcription factors are found in this region: two adjacent sites at positions-50 and-54 bp and a more 5' site at position-67 bp. Using a series of constructs containing deletions and mutations in this region, we found that the 3'-most site alone was sufficient for binding GA-binding protein alpha (GABP alpha) / GABP beta and for a low level of transcriptional activation. When all three sites were present, a second complex \" a \" was detected, which contains an unknown member of the Ets family. Formation of complex a was cell-type specific and correlated with a high level of transcription. Deletion of the 5'-most Ets site had no effect on binding to GABP alpha / GABP beta, but it eliminated a. Concomitant with this loss of a, a new Ets-1-containing complex \" c \" appeared. Complex c substituted efficiently for complex a in transcriptional activation. We conclude that although neither of the two 5'-most Ets sites alone binds nuclear protein, they appear to act as modulators which control the pattern of Ets proteins that bind the alpha 4 gene promoter. This arrangement of Ets sites, coupled with the tissue-and developmental-specific expression of Ets members, likely play a key role in defining the pattern of alpha 4 integrin.",
"role": "user"
},
{
"content": "{\"CellLine\": [\"cell lines\", \"HeLa cells\"], \"CellType\": [], \"DNA\": [\"alpha 4 gene promoter\", \"- 50 and - 54 bp\", \"- 67 bp\", \"5\\u0027 deletion mutants\", \"binding sites\", \"5\\u0027 site\", \"3\\u0027 - most site\", \"5\\u0027 - most Ets site\", \"alpha 4 integrin gene promoter\", \"5\\u0027 - most Ets sites\", \"Ets sites\", \"- 42 and - 76 base pairs\"], \"Protein\": [\"Ets proteins\", \"GA - binding protein alpha\", \"GABP alpha) / GABP beta\", \"Ets members\", \"alpha 4 integrins\", \"Ets family\", \"GABP alpha\", \"c\", \"alpha 4\", \"transcription factors\", \"nuclear protein\", \"GABP alpha / GABP beta\", \"alpha 4 integrin\", \"GABP beta\", \"new Ets - 1 - containing complex\"], \"RNA\": []}",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.21486
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nIn image deconvolution problems, the diagonalization of the underlying operators by means of the fast Fourier transform (FFT) usually yields very large speedups. When there are incomplete observations (e.g., in the case of unknown boundaries), standard deconvolution techniques normally involve non-diagonalizable operators, resulting in rather slow methods or, otherwise, use inexact convolution models, resulting in the occurrence of artifacts in the enhanced images. In this paper, we propose a new deconvolution framework for images with incomplete observations that allows us to work with diagonalized convolution operators, and therefore is very fast. We iteratively alternate the estimation of the unknown pixels and of the deconvolved image, using, e.g., an FFT-based deconvolution method. This framework is an efficient, high-quality alternative to existing methods of dealing with the image boundaries, such as edge tapering. It can be used with any fast deconvolution method. We give an example in which a state-of-the-art method that assumes periodic boundary conditions is extended, using this framework, to unknown boundary conditions. Furthermore, we propose a specific implementation of this framework, based on the alternating direction method of multipliers (ADMM). We provide a proof of convergence for the resulting algorithm, which can be seen as a “partial” ADMM, in which not all variables are dualized. We report experimental comparisons with other primal–dual methods, where the proposed one performed at the level of the state of the art. Four different kinds of applications were tested in the experiments: deconvolution, deconvolution with inpainting, superresolution, and demosaicing, all with unknown boundaries.\n\nCited Abstract(s):\n[1]: We propose a new first-order splitting algorithm for solving jointly the primal and dual formulations of large-scale convex minimization problems involving the sum of a smooth function with Lipschitzian gradient, a nonsmooth proximable function, and linear composite functions. This is a full splitting approach, in the sense that the gradient and the linear operators involved are applied explicitly without any inversion, while the nonsmooth functions are processed individually via their proximity operators. This work brings together and notably extends several classical splitting schemes, like the forward–backward and Douglas–Rachford methods, as well as the recent primal–dual method of Chambolle and Pock designed for problems with linear composite terms.\n\n[2]: A wide array of image recovery problems can be abstracted into the problem of minimizing a sum of composite convex functions in a Hilbert space. To solve such problems, primal-dual proximal approaches have been developed which provide efficient solutions to large-scale optimization problems. The objective of this paper is to show that a number of existing algorithms can be derived from a general form of the forward-backward algorithm applied in a suitable product space. Our approach also allows us to develop useful extensions of existing algorithms by introducing a variable metric. An illustration to image restoration is provided.\n\n[3]: We present primal-dual decomposition algorithms for convex optimization problems with cost functions @math , where @math and @math have inexpensive proximal operators and @math can be decomposed as a sum of two structured matrices. The methods are based on the Douglas--Rachford splitting algorithm applied to various splittings of the primal-dual optimality conditions. We discuss applications to image deblurring problems with nonquadratic data fidelity terms, different types of convex regularization, and simple convex constraints. In these applications, the primal-dual splitting approach allows us to handle general boundary conditions for the blurring operator. Numerical results indicate that the primal-dual splitting methods compare favorably with the alternating direction method of multipliers, the Douglas--Rachford algorithm applied to a reformulated primal problem, and the Chambolle--Pock primal-dual algorithm.",
"role": "user"
},
{
"content": "The works [1] and [2] propose primal-dual methods that do not involve the inversion of large BTTB matrices. In , we experimentally test one of these methods [1] , and find it to be rather slow. Another primal-dual method that considers non-periodic boundaries was proposed in [3] . It needs the structure of the boundaries to be known , which normally is not the case in real-life situations. The use of an artificially chosen structure results, once again, in the occurrence of artifacts.",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_pubmed
|
science.scientific_papers_summarization_single_doc_pubmed.100031
|
[
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\na stroke is a central nervous system disease that has a serious impact on individuals \n lives1 .\ndepending on the lesion area , \n strokes cause diverse and complex functional disabilities , including decreased motor \n function , sensory loss , and impaired balance ability2 , \n 3 .\nstroke patients also experience \n restricted performance of the functional motions necessary for ordinary life , and reduced \n gait ability4 , 5 . to support the many body postures needed in everyday life , maintenance of appropriate trunk \n muscle strength and endurance are very important6 .\nthe abdominal and trunk muscles maintain the stability of the lower \n trunk , and they are important for trunk movement and motor control7 .\ndickstein et al.8 demonstrated the significance of trunk muscles by verifying a \n decrease in anticipatory postural adjustments in hemiplegic patients compared to healthy \n subjects , based on a comparison of left and right trunk muscle onset time through movement \n of the upper and lower extremities .\ntherefore , to improve the abilities of chronic stroke \n patients , it is important to ensure functioning postural stability during movement training . \n\nthis requires activation of the trunk muscles . a representative technique for achieving this \n is the bracing method .\nbracing involves stabilizing the trunk by increasing internal \n abdominal pressure through the action activation of 29 pairs of deep and superficial \n muscles9 . accordingly , this study \n examined the effects of upper extremity task training with the bracing method applied on \n trunk adjustment ability and balance in stroke patients .\nas subjects , this study selected 46 non - traumatic hemiplegic stroke patients in at r , h , \n and b hospitals whose onset of stroke had occurred at least six months earlier .\nall \n demonstrated an understanding of the experimental process before they agreed to participate \n in the experiment .\n( all scored at least 24 on the korean version of the mini - mental state \n examination . )\nthey were able to sit unassisted for five minutes or longer without special \n equipment .\nthe subjects were able to understand and follow the therapist s directions and \n had no other neurological problems ( vision , hearing , other senses ) or orthopedic damage \n ( table 1table 1.general characteristics of the subjectsexperimental group ( n=23)control group ( n=23)age ( yrs)60.4 10.558.1 10.7height ( cm)164.0 8.6164.4 8.2weight ( kg)65.8 10.563.5 9.8gendermale13 ( 56.5)14 ( 60.9)female10 ( 43.5)9 ( 39.1)affected sideleft7 ( 30.0)10 ( 43.5)right16 ( 69.6)13 ( 56.5)time since stroke ( months)17.7 10.416.5 11.2mean standard deviation ; n ( % ) ) .\nall protocols were approved by the university of daejeon . before \n participation , the procedures , risks , and benefits\nmean standard deviation ; n ( % ) the subjects of the experimental group ( upper extremity task - training group with symmetric \n abdominal muscle contraction ) received upper extremity task training while maintaining \n symmetric abdominal muscle contraction ( referred to here as bracing ) .\nsounds while they concurrently contracted left and right and forward and backward trunk \n muscles isometrically for five seconds as if force was given to the abdomen reflexively , and \n while maintaining hallow respiration .\nthe control group ( general upper extremity task - training group ) received upper extremity \n task training . during the training , each subject sat on a chair with the back .\nthey flexed \n the hip , knee , and ankle joints of both lower extremities by 90 degrees and placed both feet \n on the floor .\nthey were instructed to utilize only the paretic upper extremity and were \n assisted in the movement so that they did not exert compensatory strategies .\nsix numbered \n tasks were performed in sequence for five to six minutes . the order and duration of the \n tasks\nfor example , subjects who showed \n good function in one task were asked to stop and move on to the next task .\nif they were not \n able to perform the next task due to poor function , they performed the previous task for an \n extended amount of time .\nthe postural assessment scale for stroke ( pass ) and trunk impairment scale ( tis ) were \n utilized to evaluate subjects postures and assess balance .\nthe balance performance monitor \n ( bpm ) was employed and biorescue software ( ap 1153 rm ingenierie , rodez , france ) was \n utilized to evaluate static balance ability and limit of stability ( los ) .\npasw statistics 18.0 for windows ( ibm / spss inc , chicago , il , usa ) was used for all \n statistical analyses performed in this study .\nthe general characteristics of each group were \n analyzed using a test and an independent t - test . to compare differences in \n pre- and post - training results between the two groups over time , an independent samples \n t - test was utilized . to determine the statistical significance of data over time within each \n group , a paired t - test was employed .\ntable 2table 2.a comparison of postural assessment scale for stroke , trunk impairment scale \n scoresexperimental group ( n=23)control group ( n=23)pass ( score)pre - test21.7 7.421.0 7.0post - test22.4 7.021.5 6.7tis ( score)pre - test13.0 4.312.5 4.6post - test14.4 4.313.1 4.4mean standard deviation . * significant difference within group ( pre - test vs. post - test ) .\nsignificant difference between groups ( experimental group vs. control \n group ) shows the results of posture comparisons between the experimental group and \n the control group before and after intervention .\nthe experimental group s tis scores \n significantly increased after the intervention ( p<0.05 ) , whereas the control group did \n not see any significant difference .\ntable \n 3table 3.a comparison of center of pressure and limit of stabilityexperimental group ( n=23)control group ( n=23)cop ( cm)pre - test5.39 2.825.65 3.13post - test3.98 \n2.314.80 2.93*los ( mm)pre - test8,443.4 1,545.78,440.4 1,573.3post - test8,866.0 1,611.08,651.0 1,610.7*mean standard deviation . *\nsignificant difference between groups ( experimental group vs. control \n group ) displays the results of a comparison of pre- and post - intervention balance \n evaluations between the groups .\nthere was significant improvement in balance after the \n intervention in both the experimental group and the control group .\naccording to the \n between - group comparisons , the improvements in the experimental group were significantly \n greater in the control group ( p<0.05 ) , except in the postural assessment scale ( pass ) \n ( p>0.05 ) .\nsignificant difference between groups ( experimental group vs. control \n group ) mean standard deviation .\nthis study applied upper extremity task training with symmetric abdominal muscle \n contraction as a method of improving postural adjustment in adult hemiplegic patients and \n examined its effect on postural adjustment .\nthe pre- and post - exercise values of tis scores \n were significantly different in both groups , and a significant difference was seen between \n the two groups .\na study by allison et al.10 featuring bracing - assisted trunk stabilization exercises showed \n heightened activity of the trunk muscles and improved trunk function , which is consistent \n with the results of the present study .\nthe stroke postural evaluation scores of both groups \n increased , but no significant difference was seen between them .\nthis is consistent with a \n study of sub - acute state patients by benaim et al.11 , which showed that a short intervention period of six weeks \n resulted in no significant difference . in the static balance test\n, significant differences \n were seen within both groups in pre- and post - exercise results , as well as in the scores \n between the two groups .\nthis is consistent with the results of research by brown et al.12 , which show that short muscle contraction \n initiation times enabled anticipatory postural adjustments , and that postural adjustment \n affected balance . in the los test , both groups saw significant differences in pre- and \n post - exercise results ; a significant difference was also seen between the results of the two \n groups after the exercise .\nhodge and richardson13 report that intervention in the deep abdominal muscles through \n trunk stabilization exercises was more effective than other forms of exercise in achieving \n improved movement of the four limbs and postural adjustment ability ; this is consistent with \n the present study s results .\nthe limitations of this study were the short intervention \n period of six weeks and the small number of experimental participants satisfying selection \n criteria .\nbased on the results of this study , upper limb task training with symmetric \n abdominal muscle contraction , applied as part of trunk stabilization exercises in adult \n hemiplegic patients , may be applied to diverse hemiplegic patients in the clinical field and \n be implemented as an exercise program for them after discharge from hospital .",
"role": "user"
},
{
"content": "[ purpose ] the purpose of this study is to examine the effects of upper extremity task \n training employing the bracing method on the trunk control and balance of stroke patients . \n \n [ subjects and methods ] the subjects were 46 stroke patients whose strokes had occurred six \n months or more prior to the study . \n the subjects were divided into two groups . \n one group \n underwent upper extremity task training with symmetric abdominal muscle contraction \n ( bracing ) applied . \n the other group simply underwent upper extremity task training , without \n bracing . \n [ results ] the experimental group s trunk impairment scale ( tis ) significantly \n increased after the intervention , whereas the control group did not see any significant \n difference . \n there was significant improvement in balance after the intervention in both \n the experimental group and the control group . \n according to the between - group comparisons , \n the improvements in the experimental group were significantly greater in the control \n group , except in the postural assessment scale ( pass ) . \n [ conclusion ] based on the results \n of this study , upper extremity task exercises with symmetric abdominal muscle contraction , \n conducted as part of adult hemiplegic patients trunk stabilization exercises , can be \n applied to a diverse range of hemiplegic patients and implemented as an exercise program \n after discharge from hospital .",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.11569
|
[
{
"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\nThe individual infectiousness of coronavirus disease 2019 (COVID-19), quantified by the number of secondary cases of a typical index case, is conventionally modelled by a negative-binomial (NB) distribution. Based on patient data of 9120 confirmed cases in China, we calculated the variation of the individual infectiousness, i.e., the dispersion parameter k of the NB distribution, at 0.70 (95% confidence interval: 0.59, 0.98). This suggests that the dispersion in the individual infectiousness is probably low, thus COVID-19 infection is relatively easy to sustain in the population and more challenging to control. Instead of focusing on the much fewer super spreading events, we also need to focus on almost every case to effectively reduce transmission.",
"role": "user"
},
{
"content": "[\"Prevention\", \"Transmission\"]",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.3925
|
[
{
"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\nBackground: The COVID-19 infection which emerged in December 2019, is caused by the virus SARS-CoV-2. Infection with this virus can lead to severe respiratory illness, however, myocarditis has also been reported. The purpose of this study is to identify the clinical features of myocarditis in COVID-19 patients. Methods: A systematic review was conducted to investigate characteristics of myocarditis in patients infected with COVID-19 using the search term \"Coronavirus\" or \"COVID\" and \"myocarditis,\" \"heart,\" or \"retrospective.\" Case reports and retrospective studies were gathered by searching Medline/Pubmed, Google Scholar, CINAHL, Cochrane CENTRAL, and Web of Science databases. 11 articles were selected for review. Results: COVID-19 myocarditis affected patients over the age of 50 and incidences among both genders were equally reported. Patients presented with dyspnea, cough, fever with hypotension and chest pain. Laboratory tests revealed leukocytosis with increased C-reactive protein, while arterial blood gas analysis demonstrated respiratory acidosis. All cardiac markers were elevated. Radiographic imaging of the chest showed bilateral ground glass opacities or bilateral infiltrates, while cardiac magnetic resonance imaging produced late gadolinium enhancements. Electrocardiography demonstrated ST-segment elevation or inverted T waves, while echocardiography revealed reduced left ventricular ejection fraction with cardiomegaly or increased wall thickness. Management with corticosteroids was favored in most cases, followed by antiviral medication. The majority of studies reported either recovery or no further clinical deterioration. Conclusion: Current available data on COVID-19 myocarditis is limited. Further research is needed to advance our understanding of COVID-19 myocarditis.",
"role": "user"
},
{
"content": "[\"Diagnosis\", \"Treatment\"]",
"role": "assistant"
}
] |
science.mslr2022_ms2_multidoc_summarization
|
science.mslr2022_ms2_multidoc_summarization.12769
|
[
{
"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:\nConcentrations of amoxicillin and clindamycin in teeth following a single dose of oral medication\nAbstract 1:\nObjectives The main purpose of this study is the detection of amoxicillin and clindamycin concentrations in teeth . Material s and methods Eleven patients received 2 g of amoxicillin , and 11 patients received 600 mg of clindamycin in a single dose of oral medication at least 60 min prior to tooth extraction due to systemic diseases . The concentrations were determined in crowns and roots separately using liquid chromatography – t and em mass spectrometry ( LC-MS-MS ) . Results Amoxicillin ( 13 sample s ) and clindamycin ( 12 sample s ) were detected in the sample s of the root and crown preparations of the extracted teeth . The mean concentration of amoxicillin was 0.502 μg/g in the roots and 0.171 μg/g in the crowns . The mean concentration of clindamycin was 0.270 μg/g in the roots and 0.064 μg/g in the crowns . Conclusions A single dose of oral amoxicillin and clindamycin leads to concentrations of both antibiotics in teeth which exceed the minimal inhibition concentration of some oral bacteria . Clinical relevance The proof of antibacterial activity in dental hard tissue after oral single-dose application is new . The antimicrobial effect of amoxicillin and clindamycin concentrations in roots of teeth may be of clinical relevance to bacterial reinfection from dentinal tubules\n\n\nTitle 2:\nEarly dental implant failure: risk factors.\nAbstract 2:\nThe objective of this prospect i ve study was to estimate the incidence of early loss of dental implants and the potential risk factors . The predictive variables were classified as being patient , implant , anatomical , or operation-specific . The outcome variable was early failure of the implant . The significance of differences was assessed using bivariate analyses , and then a multivariate logistic regression model to identify independent predictors for early loss of implants . A total of 169 patients , 116 women and 53 men , mean age 47 ( range 16 - 80 ) years , had 399 implants inserted . Fifteen implants were lost in 14 patients ( 8 % ) . The early loss of dental implants was significantly associated with width of keratinised gingiva ( p=0.008 ) , the use polyglactin sutures ( p=0.048 ) , and the use of narrow implants ( p=0.035 ) . Multivariate logistic regression analysis established the significance of narrow keratinised gingiva ( OR=4.7 , p=0.005 ) and the use of polyglactin sutures ( OR=3.8 , p=0.042 ) , which we conclude are probably the strongest predictors of early failure of implants\n\n\nTitle 3:\nEfficacy of two antibiotic regimens in the reduction of early dental implant failure: a pilot study.\nAbstract 3:\nThe purpose of this study was to compare the efficacy of two antibiotic regimens in reducing early dental implant failure . A preoperative single-dose regimen and a 3-day antibiotic course were compared . Eighty subjects needing dental implant placement were r and omly allocated to one of the two antibiotic prophylaxis regimen groups . In the first group , dental implants were placed after the administration of a single preoperative dose of antibiotic ( 1 g of amoxicillin ) ; no postoperative antibiotics were given . In the second group , dental implants were inserted in patients who received the same preoperative dose of antibiotic as the first group , but the antibiotic was then continued postoperatively for 3 days . Patients returned for postoperative evaluation at 3 days , 7 days , and 12 weeks . The surgical sites were assessed for pain , swelling , wound dehiscence , and pus formation . No statistically significant difference was observed between the two groups , probably because of the limited number of patients . Although minor complications were seen in a few patients , all implants were successfully osseointegrated . Until a study with a larger population rules definitively on the role of antibiotics in implant surgery , a single dose of antibiotic before implant placement may be sufficient\n\n\nTitle 4:\nSingle preoperative dose versus long-term prophylactic antibiotic regimens in dental implant surgery.\nAbstract 4:\nPURPOSE The purpose of this prospect i ve study was to compare the efficacy of prophylactic antibiotic regimens commonly used in dental implant surgery . Preoperative single-dose and long-term prophylactic antibiotic regimens were compared . MATERIAL S AND METHODS This was a 2-center prospect i ve study in which 215 patients underwent ambulatory endosseous implant placement . In the first group , 445 dental implants were placed in 125 patients after the administration of a single preoperative dose of prophylactic antibiotic with no postoperative antibiotics . In the second group , 302 dental implants were placed in 90 patients who received a preoperative dose of antibiotics and were instructed to take antibiotics postoperatively for 7 days . In both groups , 0.12 % chlorhexidine pre- and postoperative mouth rinses were used . Patients returned for postoperative evaluation at 1 week , 2 weeks , and just prior to surgical uncovering . The surgical sites were assessed for pain , swelling , erythema , and purulence . RESULTS In the first group , 3 patients developed wound dehiscence at 5 implant sites and 1 developed a minor inflammatory response . None of the patients in this group received further antibiotics . In the second group , 3 patients developed wound dehiscence , 2 developed an inflammatory response , and 1 was diagnosed with infection , for which another course of antibiotics was required . There was no statistical difference between the 2 groups according to the Fisher 2 x 4 exact test ( P = .56 ) . DISCUSSION Indiscriminate use of antibiotics is unacceptable in clinical practice today . Surgeons must adhere to basic principles to gain the most benefit from the use of prophylactic antibiotics . CONCLUSION Long-term prophylactic antibiotic use in implant surgery was of no advantage or benefit over a single-dose preoperative antibiotic regimen in this patient population\n\n\nTitle 5:\nBacterial profiles and proteolytic activity in peri-implantitis versus healthy sites.\nAbstract 5:\nPeri-implantitis is a biofilm-induced destructive inflammatory process that , over time , results in loss of supporting bone around an osseointegrated dental implant . Biofilms at peri-implantitis sites have been reported to be dominated by Gram-negative anaerobic rods with a proteolytic metabolism such as , Fusobacterium , Porphyromonas , Prevotella and Tannerella , as well as anaerobic Gram-positive cocci . In this study , we hypothesized that protease activity is instrumental in driving bone destruction and we therefore compared the microbial composition and level of protease activity in sample s of peri-implant biofluid ( PIBF ) from 25 healthy subjects ( H group ) and 25 subjects with peri-implantitis ( PI group ) . Microbial composition was investigated using culture techniques and protease activity was determined using a FITC-labelled casein substrate . The microbial composition was highly variable in subjects both in the H and PI groups but one prominent difference was the prevalence of Porphyromonas/Prevotella and anaerobic Gram positive cocci which was significantly higher in the PI than in the H group . A subgroup of subjects with peri-implantitis displayed a high level of protease activity in the PIBF compared to healthy subjects . However , this activity could not be related to the presence of specific bacterial species . We propose that a high level of protease activity may be a predictive factor for disease progression in peri-implantitis . Further longitudinal studies are however required to determine whether assessment of protease activity could serve as a useful method to identify patients at risk for progressive tissue destruction\n\n\nTitle 6:\nA pilot study to determine the effectiveness of different amoxicillin regimens in implant surgery.\nAbstract 6:\nThe aim of this study was to attempt to determine the minimum effective regimen of amoxicillin antibiotic prophylaxis for dental implant surgery . One hundred patients were r and omly allocated to 4 different antibiotic prophylactic treatment groups . At second-stage surgery , only 2 implants failed in the nonantibiotic group . No statistically significant differences were found in the 4 groups , probably because of the limited number of the sample s. Until a study with a larger population may definitely rule on the role of antibiotics in oral implant surgery , in may be prudent for the practitioner to adopt the single preoperative antibiotic dose as the minimal effective regimen\n\n\nTitle 7:\nAdjunctive Systemic and Local Antimicrobial Therapy in the Surgical Treatment of Peri-implantitis\nAbstract 7:\nThe aim of the present r and omized controlled clinical trial was to investigate the adjunctive effect of systemic antibiotics and the local use of chlorhexidine for implant surface decontamination in the surgical treatment of peri-implantitis . One hundred patients with severe peri-implantitis were recruited . Surgical therapy was performed with or without adjunctive systemic antibiotics or the local use of chlorhexidine for implant surface decontamination . Treatment outcomes were evaluated at 1 y. A binary logistic regression analysis was used to identify factors influencing the probability of treatment success , that is , probing pocket depth ≤5 mm , absence of bleeding/suppuration on probing , and no additional bone loss . Treatment success was obtained in 45 % of all implants but was higher in implants with a nonmodified surface ( 79 % ) than those with a modified surface ( 34 % ) . The local use of chlorhexidine had no overall effect on treatment outcomes . While adjunctive systemic antibiotics had no impact on treatment success at implants with a nonmodified surface , a positive effect on treatment success was observed at implants with a modified surface . The likelihood for treatment success using adjunctive systemic antibiotics in patients with implants with a modified surface , however , was low . As the effect of adjunctive systemic antibiotics depended on implant surface characteristics , recommendations for their use in the surgical treatment of peri-implantitis should be based on careful assessment s of the targeted implant ( Clinical Trials.gov NCT01857804 )",
"role": "user"
},
{
"content": "These findings demonstrate that plasma concentrations of a prophylactic dose of amoxicillin are higher than the minimum inhibitory concentration needed to prevent the common dental bacteria involved in peri-implantitis and periodontal diseases",
"role": "assistant"
}
] |
science.chia_ner
|
science.chia_ner.1397
|
[
{
"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\nKidney transplant recipients at Washington University/Barnes-Jewish Hospital\nExperiencing GI toxicity from MPA as determined by the treating physician within 12 months post-renal transplant\nOn standard immunosuppression with tacrolimus and prednisone",
"role": "user"
},
{
"content": "{\"Condition\": [], \"Device\": [], \"Drug\": [\"tacrolimus\", \"MPA\", \"prednison\"], \"Measurement\": [], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [], \"Procedure\": [\"Kidney transplant\", \"standard immunosuppression\", \"GI toxicity\"], \"Qualifier\": [], \"ReferencePoint\": [], \"Scope\": [\"tacrolimus and prednison\"], \"Temporal\": [], \"Value\": [], \"Visit\": [\"Washington University/Barnes-Jewish Hospital\"]}",
"role": "assistant"
}
] |
science.craftchem_ner
|
science.craftchem_ner.7230
|
[
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Whitecircleindicatesmature-formofADAM11proteinandblackcircleshowsimmature-form,whichwasnotprocessed.",
"role": "user"
},
{
"content": "[\"protein\"]",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.830
|
[
{
"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:\nHuman achaete-scute homologue ( hASH1 ) mRNA level as a diagnostic marker to distinguish esthesioneuroblastoma from poorly differentiated tumors arising in the sinonasal tract . Distinction of high-grade esthesioneuroblastomas from other poorly differentiated tumors arising in the nasal cavity is an important diagnostic challenge because it determines patient management and prognosis . The human achaete-scute homologue ( hASH1 ) gene is critical in olfactory neuronal differentiation and is expressed in immature olfactory cells ; therefore , it could have potential use as a diagnostic marker The aim of the present study was to determine the value of hASH1 messenger RNA ( mRNA ) levels in differentiating esthesioneuroblastoma from other poorly differentiated tumors . A real-time polymerase chain reaction assay was developed , permitting the comparative determination of hASH1 mRNA levels in triplicate in a double-blind pilot study including 24 frozen cases of esthesioneuroblastoma and poorly differentiated tumors . All 4 positive cases were esthesioneuroblastomas , and all 19 poorly differentiated tumors were negative . In addition , there was an inverse association between the grade of esthesioneuroblastomas and hASH1 mRNA levels . The hASH1 mRNA level might represent a useful tool for distinguishing esthesioneuroblastoma from poorly differentiated tumors of the sinonasal region .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"real-time polymerase chain reaction assay\"], \"Outcome\": [\"grade of esthesioneuroblastomas\", \"hASH1 mRNA levels\", \"esthesioneuroblastomas\"], \"Participant\": [\"24\", \"esthesioneuroblastomas\", \"esthesioneuroblastoma\", \"tumors\", \"other poorly differentiated tumors arising in the nasal cavity\"]}",
"role": "assistant"
}
] |
science.qasper_extractive_qa
|
science.qasper_extractive_qa.176.0
|
[
{
"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: Aspect Term Extraction with History Attention and Selective Transformation\n\nAspect Term Extraction (ATE), a key sub-task in Aspect-Based Sentiment Analysis, aims to extract explicit aspect expressions from online user reviews. We present a new framework for tackling ATE. It can exploit two useful clues, namely opinion summary and aspect detection history. Opinion summary is distilled from the whole input sentence, conditioned on each current token for aspect prediction, and thus the tailor-made summary can help aspect prediction on this token. Another clue is the information of aspect detection history, and it is distilled from the previous aspect predictions so as to leverage the coordinate structure and tagging schema constraints to upgrade the aspect prediction. Experimental results over four benchmark datasets clearly demonstrate that our framework can outperform all state-of-the-art methods.\n\nIntroduction\nAspect-Based Sentiment Analysis (ABSA) involves detecting opinion targets and locating opinion indicators in sentences in product review texts BIBREF0 . The first sub-task, called Aspect Term Extraction (ATE), is to identify the phrases targeted by opinion indicators in review sentences. For example, in the sentence “I love the operating system and preloaded software”, the words “operating system” and “preloaded software” should be extracted as aspect terms, and the sentiment on them is conveyed by the opinion word “love”. According to the task definition, for a term/phrase being regarded as an aspect, it should co-occur with some “opinion words” that indicate a sentiment polarity on it BIBREF1 .\nMany researchers formulated ATE as a sequence labeling problem or a token-level classification problem. Traditional sequence models such as Conditional Random Fields (CRFs) BIBREF2 , BIBREF3 , BIBREF4 , BIBREF5 , Long Short-Term Memory Networks (LSTMs) BIBREF6 and classification models such as Support Vector Machine (SVM) BIBREF7 have been applied to tackle the ATE task, and achieved reasonable performance. One drawback of these existing works is that they do not exploit the fact that, according to the task definition, aspect terms should co-occur with opinion-indicating words. Thus, the above methods tend to output false positives on those frequently used aspect terms in non-opinionated sentences, e.g., the word “restaurant” in “the restaurant was packed at first, so we waited for 20 minutes”, which should not be extracted because the sentence does not convey any opinion on it.\nThere are a few works that consider opinion terms when tackling the ATE task. BIBREF8 proposed Recursive Neural Conditional Random Fields (RNCRF) to explicitly extract aspects and opinions in a single framework. Aspect-opinion relation is modeled via joint extraction and dependency-based representation learning. One assumption of RNCRF is that dependency parsing will capture the relation between aspect terms and opinion words in the same sentence so that the joint extraction can benefit. Such assumption is usually valid for simple sentences, but rather fragile for some complicated structures, such as clauses and parenthesis. Moreover, RNCRF suffers from errors of dependency parsing because its network construction hinges on the dependency tree of inputs. CMLA BIBREF9 models aspect-opinion relation without using syntactic information. Instead, it enables the two tasks to share information via attention mechanism. For example, it exploits the global opinion information by directly computing the association score between the aspect prototype and individual opinion hidden representations and then performing weighted aggregation. However, such aggregation may introduce noise. To some extent, this drawback is inherited from the attention mechanism, as also observed in machine translation BIBREF10 and image captioning BIBREF11 .\nTo make better use of opinion information to assist aspect term extraction, we distill the opinion information of the whole input sentence into opinion summary, and such distillation is conditioned on a particular current token for aspect prediction. Then, the opinion summary is employed as part of features for the current aspect prediction. Taking the sentence “the restaurant is cute but not upscale” as an example, when our model performs the prediction for the word “restaurant”, it first generates an opinion summary of the entire sentence conditioned on “restaurant”. Due to the strong correlation between “restaurant' and “upscale” (an opinion word), the opinion summary will convey more information of “upscale” so that it will help predict “restaurant” as an aspect with high probability. Note that the opinion summary is built on the initial opinion features coming from an auxiliary opinion detection task, and such initial features already distinguish opinion words to some extent. Moreover, we propose a novel transformation network that helps strengthen the favorable correlations, e.g. between “restaurant' and “upscale”, so that the produced opinion summary involves less noise.\nBesides the opinion summary, another useful clue we explore is the aspect prediction history due to the inspiration of two observations: (1) In sequential labeling, the predictions at the previous time steps are useful clues for reducing the error space of the current prediction. For example, in the B-I-O tagging (refer to Section SECREF4 ), if the previous prediction is “O”, then the current prediction cannot be “I”; (2) It is observed that some sentences contain multiple aspect terms. For example, “Apple is unmatched in product quality, aesthetics, craftmanship, and customer service” has a coordinate structure of aspects. Under this structure, the previously predicted commonly-used aspect terms (e.g., “product quality”) can guide the model to find the infrequent aspect terms (e.g., “craftmanship”). To capture the above clues, our model distills the information of the previous aspect detection for making a better prediction on the current state.\nConcretely, we propose a framework for more accurate aspect term extraction by exploiting the opinion summary and the aspect detection history. Firstly, we employ two standard Long-Short Term Memory Networks (LSTMs) for building the initial aspect and opinion representations recording the sequential information. To encode the historical information into the initial aspect representations at each time step, we propose truncated history attention to distill useful features from the most recent aspect predictions and generate the history-aware aspect representations. We also design a selective transformation network to obtain the opinion summary at each time step. Specifically, we apply the aspect information to transform the initial opinion representations and apply attention over the transformed representations to generate the opinion summary. Experimental results show that our framework can outperform state-of-the-art methods.\n\nThe ATE Task\nGiven a sequence INLINEFORM0 of INLINEFORM1 words, the ATE task can be formulated as a token/word level sequence labeling problem to predict an aspect label sequence INLINEFORM2 , where each INLINEFORM3 comes from a finite label set INLINEFORM4 which describes the possible aspect labels. As shown in the example below:\n \n INLINEFORM0 , INLINEFORM1 , and INLINEFORM2 denote beginning of, inside and outside of the aspect span respectively. Note that in commonly-used datasets such as BIBREF12 , the gold standard opinions are usually not annotated.\n\nModel Description\nAs shown in Figure FIGREF3 , our model contains two key components, namely Truncated History-Attention (THA) and Selective Transformation Network (STN), for capturing aspect detection history and opinion summary respectively. THA and STN are built on two LSTMs that generate the initial word representations for the primary ATE task and the auxiliary opinion detection task respectively. THA is designed to integrate the information of aspect detection history into the current aspect feature to generate a new history-aware aspect representation. STN first calculates a new opinion representation conditioned on the current aspect candidate. Then, we employ a bi-linear attention network to calculate the opinion summary as the weighted sum of the new opinion representations, according to their associations with the current aspect representation. Finally, the history-aware aspect representation and the opinion summary are concatenated as features for aspect prediction of the current time step.\nAs Recurrent Neural Networks can record the sequential information BIBREF13 , we employ two vanilla LSTMs to build the initial token-level contextualized representations for sequence labeling of the ATE task and the auxiliary opinion word detection task respectively. For simplicity, let INLINEFORM0 denote an LSTM unit where INLINEFORM1 is the task indicator. In the following sections, without specification, the symbols with superscript INLINEFORM2 and INLINEFORM3 are the notations used in the ATE task and the opinion detection task respectively. We use Bi-Directional LSTM to generate the initial token-level representations INLINEFORM4 ( INLINEFORM5 is the dimension of hidden states): DISPLAYFORM0 \nIn principle, RNN can memorize the entire history of the predictions BIBREF13 , but there is no mechanism to exploit the relation between previous predictions and the current prediction. As discussed above, such relation could be useful because of two reasons: (1) reducing the model's error space in predicting the current label by considering the definition of B-I-O schema, (2) improving the prediction accuracy for multiple aspects in one coordinate structure.\nWe propose a Truncated History-Attention (THA) component (the THA block in Figure FIGREF3 ) to explicitly model the aspect-aspect relation. Specifically, THA caches the most recent INLINEFORM0 hidden states. At the current prediction time step INLINEFORM1 , THA calculates the normalized importance score INLINEFORM2 of each cached state INLINEFORM3 ( INLINEFORM4 ) as follows: DISPLAYFORM0 \n DISPLAYFORM0 \n INLINEFORM0 denotes the previous history-aware aspect representation (refer to Eq. EQREF12 ). INLINEFORM1 can be learned during training. INLINEFORM2 are parameters associated with previous aspect representations, current aspect representation and previous history-aware aspect representations respectively. Then, the aspect history INLINEFORM3 is obtained as follows: DISPLAYFORM0 \nTo benefit from the previous aspect detection, we consolidate the hidden aspect representation with the distilled aspect history to generate features for the current prediction. Specifically, we adopt a way similar to the residual block BIBREF14 , which is shown to be useful in refining word-level features in Machine Translation BIBREF15 and Part-Of-Speech tagging BIBREF16 , to calculate the history-aware aspect representations INLINEFORM0 at the time step INLINEFORM1 : DISPLAYFORM0 \nwhere ReLU is the relu activation function.\nPrevious works show that modeling aspect-opinion association is helpful to improve the accuracy of ATE, as exemplified in employing attention mechanism for calculating the opinion information BIBREF9 , BIBREF17 . MIN BIBREF17 focuses on a few surrounding opinion representations and computes their importance scores according to the proximity and the opinion salience derived from a given opinion lexicon. However, it is unable to capture the long-range association between aspects and opinions. Besides, the association is not strong because only the distance information is modeled. Although CMLA BIBREF9 can exploit global opinion information for aspect extraction, it may suffer from the noise brought in by attention-based feature aggregation. Taking the aspect term “fish” in “Furthermore, while the fish is unquestionably fresh, rolls tend to be inexplicably bland.” as an example, it might be enough to tell “fish” is an aspect given the appearance of the strongly related opinion “fresh”. However, CMLA employs conventional attention and does not have a mechanism to suppress the noise caused by other terms such as “rolls”. Dependency parsing seems to be a good solution for finding the most related opinion and indeed it was utilized in BIBREF8 , but the parser is prone to generating mistakes when processing the informal online reviews, as discussed in BIBREF17 .\nTo make use of opinion information and suppress the possible noise, we propose a novel Selective Transformation Network (STN) (the STN block in Figure FIGREF3 ), and insert it before attending to global opinion features so that more important features with respect to a given aspect candidate will be highlighted. Specifically, STN first calculates a new opinion representation INLINEFORM0 given the current aspect feature INLINEFORM1 as follows: DISPLAYFORM0 \nwhere INLINEFORM0 and INLINEFORM1 are parameters for history-aware aspect representations and opinion representations respectively. They map INLINEFORM2 and INLINEFORM3 to the same subspace. Here the aspect feature INLINEFORM4 acts as a “filter” to keep more important opinion features. Equation EQREF14 also introduces a residual block to obtain a better opinion representation INLINEFORM5 , which is conditioned on the current aspect feature INLINEFORM6 .\nFor distilling the global opinion summary, we introduce a bi-linear term to calculate the association score between INLINEFORM0 and each INLINEFORM1 : DISPLAYFORM0 \nwhere INLINEFORM0 and INLINEFORM1 are parameters of the Bi-Linear Attention layer. The improved opinion summary INLINEFORM2 at the time INLINEFORM3 is obtained via the weighted sum of the opinion representations: DISPLAYFORM0 \nFinally, we concatenate the opinion summary INLINEFORM0 and the history-aware aspect representation INLINEFORM1 and feed it into the top-most fully-connected (FC) layer for aspect prediction: DISPLAYFORM0 DISPLAYFORM1 \nNote that our framework actually performs a multi-task learning, i.e. predicting both aspects and opinions. We regard the initial token-level representations INLINEFORM0 as the features for opinion prediction: DISPLAYFORM0 \n INLINEFORM0 and INLINEFORM1 are parameters of the FC layers.\n\nJoint Training\nAll the components in the proposed framework are differentiable. Thus, our framework can be efficiently trained with gradient methods. We use the token-level cross-entropy error between the predicted distribution INLINEFORM0 ( INLINEFORM1 ) and the gold distribution INLINEFORM2 as the loss function: DISPLAYFORM0 \nThen, the losses from both tasks are combined to form the training objective of the entire model: DISPLAYFORM0 \nwhere INLINEFORM0 and INLINEFORM1 represent the loss functions for aspect and opinion extractions respectively.\n\nConcluding Discussions\nFor more accurate aspect term extraction, we explored two important types of information, namely aspect detection history, and opinion summary. We design two components, i.e. truncated history attention, and selective transformation network. Experimental results show that our model dominates those joint extraction works such as RNCRF and CMLA on the performance of ATE. It suggests that the joint extraction sacrifices the accuracy of aspect prediction, although the ground-truth opinion words were annotated by these authors. Moreover, one should notice that those joint extraction methods do not care about the correspondence between the extracted aspect terms and opinion words. Therefore, the necessity of such joint extraction should be obelized, given the experimental findings in this paper.\n\nFigure 1: Framework architecture. The callouts on both sides describe how THA and STN work at each time step. Color printing is preferred.\n\nTable 1: Statistics of datasets.\n\nTable 2: Experimental results (F1 score, %). The first four methods are implemented by us, and other results without markers are copied from their papers. The results with ‘*’ are reproduced by us with the released code by the authors. For RNCRF, the result with ‘\\’ is copied from the paper of CMLA (they have the same authors). ‘-’ indicates the results were not available in their papers.\n\nQuestion: How do they determine the opinion summary?",
"role": "user"
},
{
"content": "{\"answer\": [\"the weighted sum of the new opinion representations, according to their associations with the current aspect representation\"], \"evidence\": [\"As shown in Figure FIGREF3 , our model contains two key components, namely Truncated History-Attention (THA) and Selective Transformation Network (STN), for capturing aspect detection history and opinion summary respectively. THA and STN are built on two LSTMs that generate the initial word representations for the primary ATE task and the auxiliary opinion detection task respectively. THA is designed to integrate the information of aspect detection history into the current aspect feature to generate a new history-aware aspect representation. STN first calculates a new opinion representation conditioned on the current aspect candidate. Then, we employ a bi-linear attention network to calculate the opinion summary as the weighted sum of the new opinion representations, according to their associations with the current aspect representation. Finally, the history-aware aspect representation and the opinion summary are concatenated as features for aspect prediction of the current time step.\"]}",
"role": "assistant"
}
] |
science.chemdner_ner
|
science.chemdner_ner.2124
|
[
{
"content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nRNAi in Clinical Studies. RNA interference (RNAi) is an efficient process of posttranscriptional gene silencing. In recent years it has been developed into a new technology in biopharmaceutical fields of science. RNAi products include short interference RNA (siRNA) but also short hairpin RNA (shRNA), bifunctional short hairpin RNA (bi-shRNA) and microRNA (miRNA). They combine with homologous fragments of the mRNA and cause its degradation. It results in inhibition of protein synthesis, or in mutation in the gene encoding it. RNAi has been used in analysis of genomes and creation of new animal models to test drugs. From the pharmaceutical point of view, what is the most important is its therapeutic application. So far the basic and clinical research has been focused on the following targets: macular degeneration, cancer and antiviral therapy. But there are also reports on clinical trials in asthma, hypercholesterolemia and genetic diseases such as inherited skin disorders and amyloidosis. Among over 20 therapeutics that reached clinical trials, only few are still investigated. Another few are clinical candidates. The review focuses on RNAi products under clinical evaluation and their most promising new applications.",
"role": "user"
},
{
"content": "{\"Chemical\": []}",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.3098
|
[
{
"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\nAIMS: This study assessed factors contributing to glycemic control among diabetes mellitus patients complying with home quarantine during the epidemic of coronavirus disease 2019 (COVID-19). METHODS: We conducted an analytical cross-sectional study by telephone with 1159 patients with type 2 diabetes mellitus (T2DM) and 96 patients with type 1 diabetes mellitus (T1DM) who were discharged from the endocrinology department of a hospital from January 1, 2019, to January 24, 2020. According to their fasting blood glucose (FBG) and 2-h postprandial BG (2hPBG) values, the patients were divided into the well-controlled BG group and the poorly controlled BG group. The main evaluation indicators included sociodemographic variables, health risk variables and adherence to self-management behaviors. RESULTS: In total, 74.46% of the T2DM patients and 64.89% of the T1DM patients had poor glycemic control. T2DM patients with poor glycemic control were more likely to be older (odds ratio (OR): 1.017 [95% confidence interval (CI) 1.003-1.030]; P = 0.013), have fewer than 12 years of education (OR: 1.646 [95% CI 1.202-2.255]; P = 0.002), lack a BG meter at home (OR: 2.728 [95% CI 1.205-6.179]; P = 0.016), have a lower degree of medicationcompliance (OR: 1.627 [95% CI 1.076-2.460]; P = 0.021), and engage in less self-monitoring of BG (SMBG) per week (OR: 10.884 [95% CI 5.883-20.139]; P < 0.001). Fewer than 12 years of education (OR: 3.031 [95% CI 1.112-8.263]; P = 0.030) was a risk factor for glycemic control in T1DM. CONCLUSIONS: Glycemic control among patients with T1DM and T2DM during home quarantine amid the COVID-19 pandemic is poor. Our results showed that more eduction, a higher frequency of SMBG, and improved medication compliance may contribute to glycemic control. Therefore, diabetic patients should be advised to increase the frequency of blood glucose measurements during home quarantine and be re-educated regarding the importance of medication compliance.",
"role": "user"
},
{
"content": "[\"Prevention\"]",
"role": "assistant"
}
] |
science.scicite_classification
|
science.scicite_classification.839
|
[
{
"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: All katanin derivatives were PCR amplified from the human p60 (McNally and Thomas, 1998) or human p80 (Hartman et al., 1998) cDNAs previously described.\np80 derivatives The WD40 domain of p80 (WD) consisted of amino acids 1-304, WDpro consisted of residues 1-484, pro-con80 consisted of residues…",
"role": "user"
},
{
"content": "Method",
"role": "assistant"
}
] |
science.craftchem_ner
|
science.craftchem_ner.2915
|
[
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Figure7",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_plos_single_doc_summ
|
science.scientific_lay_summarisation_plos_single_doc_summ.11858
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Let-7 Represses Carcinogenesis and a Stem Cell Phenotype in the Intestine via Regulation of Hmga2\nArticle:\nAbstract:\nLet-7 miRNAs comprise one of the largest and most highly expressed family of miRNAs among vertebrates, and is critical for promoting differentiation, regulating metabolism, inhibiting cellular proliferation, and repressing carcinogenesis in a variety of tissues. The large size of the Let-7 family of miRNAs has complicated the development of mutant animal models. Here we describe the comprehensive repression of all Let-7 miRNAs in the intestinal epithelium via low-level tissue-specific expression of the Lin28b RNA-binding protein and a conditional knockout of the MirLet7c-2/Mirlet7b locus. This ablation of Let-7 triggers the development of intestinal adenocarcinomas concomitant with reduced survival. Analysis of both mouse and human intestinal cancer specimens reveals that stem cell markers were significantly associated with loss of Let-7 miRNA expression, and that a number of Let-7 targets were elevated, including Hmga1 and Hmga2. Functional studies in 3-D enteroids revealed that Hmga2 is necessary and sufficient to mediate many characteristics of Let-7 depletion, namely accelerating cell cycle progression and enhancing a stem cell phenotype. In addition, inactivation of a single Hmga2 allele in the mouse intestine epithelium significantly represses tumorigenesis driven by Lin28b. In aggregate, we conclude that Let-7 depletion drives a stem cell phenotype and the development of intestinal cancer, primarily via Hmga2.\nIntroduction:\nMicro-RNAs( miRNAs) are critical for tumor suppression, which is most notably revealed following genetic manipulation of Dicer1, an enzyme needed for miRNA processing, in which haplo-insufficiency of Dicer1 and global reduction of miRNA levels significantly accelerates tumorigenesis[1, 2]. Let-7 miRNAs comprise one of the largest and most highly expressed families of miRNAs, possessing potent anti-carcinogenic properties in a variety of tissues[3]. This activity is likely mediated via Let-7 repression of a multitude of onco-fetal mRNAs and other pro-proliferative and/or pro-metastatic targets, such as HMGA2, IGF2BP1, IGF2BP2, and NR6A1[4–6]. Let-7 biogenesis is tightly regulated, revealed by the discovery of several proteins that regulate processing by DGCR8/DROSHA in the nucleus, and by DICER1 cleavage in the cytoplasm. Most notable are LIN28A and LIN28B, which are RNA-binding proteins that directly bind to and block the processing of Let-7 mRNAs[7, 8]. LIN28A works in concert with TRIM25 and TUT4 to mediate terminal uridylation and subsequent degradation of immature precursor-Let-7( pre-Let-7) miRNA molecules[9–11]. LIN28B appears to act by sequestering primary-Let-7( pri-Let-7) miRNAs within the nucleolus to prohibit processing by DGCR8 and DROSHA[9]. The critical nature of maintaining sufficient levels of mature Let-7 miRNAs is reflected in the large number of studies that have found LIN28A or LIN28B up-regulated in human cancers, with expression often associated with an aggressive disease phenotype and/or predictive of poor outcomes[12–15]. LIN28B appears somewhat more frequently up-regulated than LIN28A in cancer, and may reflect the greater expression potential of LIN28B in adult tissues: LIN28B exhibits a later temporal pattern of expression in adult tissues such as the intestine, plays a greater role in post-natal growth, and can be re-activated by inflammation and NF-kappa-B[16–19]. In efforts of The Cancer Genome Atlas( TCGA) research consortia to define miRNA-mRNA associations across multiple different cancers( i. e. the pan-cancer initiative), the LIN28B:Let-7b interaction was identified as one of the most significant relationships discovered across nine different human malignancies[20]. The tight functional interplay between LIN28 proteins and Let-7 is delineated clearly, on biochemical and biological levels. However, Let-7 action appears dependent on the particular mRNA targets affected, although Let-7 represses de-differentiation in multiple contexts. For example, Let-7 regulates insulin-PI3K-mTOR signaling in muscle by inhibiting expression of INSR, IGF1R, and IRS2[21], yet can also inhibit mTORC1 without affecting insulin-PI3K signaling[22], whereas we have observed no effects on insulin-PI3K-mTOR signaling following depletion of Let-7 miRNAs in the small intestine[18]. Micro-RNAs have many targets, including both coding and non-coding mRNAs, and to address the functional impact of these miRNAs, one must dissect the cascade of integrated signals that ensue following alterations of a miRNA. Many studies have focused on RAS and MYC as cancer-relevant Let-7 targets, although recent high-throughput sequencing( mRNA-seq, miRNA-seq, and CLIP-seq) and meta-analyses indicate that these mRNA targets are not frequently regulated by Let-7, especially in the context of cancer[5, 6, 20, 23]. Onco-fetal Let-7 targets such as HMGA2 and IGF2BP1-3 appear to be more frequently up-regulated in multiple contexts, across multiple tissues, and in association with somatic stem cell potential[4, 5, 20, 24–29]. We have demonstrated that LIN28B is a potent driver of colorectal cancer( CRC) progression, cellular invasion, and in mouse models, a regulator of intestinal growth and tumorigenesis[15, 18, 30]. The exploration of Let-7-dependence through genetic manipulation in mouse models is currently untenable due to the large number of miRNA clusters, with 12 Let-7 genes located at 8 separate clusters on 7 different chromosomes. To circumvent this obstacle and elucidate the mechanistic roles of Let-7 miRNAs in intestinal tumorigenesis in a genetic mouse model we have combined a Vil-Lin28bLow( Lin28bLo) transgene with intestinal deletion of the MirLet7c-2/Mirlet7b bi-cistronic cluster( Let-7IEC-KO) to achieve robust repression of all Let-7 miRNAs expressed in the intestinal epithelium. Concurrent deletion of the MirLet7c-2/Mirlet7b bi-cistronic cluster is necessary as Lin28b is unable to effectively target and inhibit processing of these specific Let-7 miRNAs[18]. These Lin28bLo/Let-7IEC-KO mice develop intestinal polyps with 100% penetrance and develop adenocarcinomas in the majority of animals, coincident with reduced survival. Examination of Let-7 targets in these tumors and in tumoroid cultures suggest that HMGA2 is likely playing a major role in driving carcinogenesis following Let-7 depletion, a novel in vivo finding. Furthermore, we find that tumorigenesis and a stem cell signature are driven by Let-7 depletion in mouse and human intestinal tumors, in which HMGA2 appears to play a functional role in reinforcing.\nDiscussion:\nWe have achieved comprehensive depletion of all Let-7 miRNAs in the intestinal epithelium and demonstrated the critical nature of their cumulative tumor-suppressive properties. These effects appear to be due to Let-7, although LIN28B can bind mRNAs and modulate protein levels of targets in the intestinal epithelium[18]. However, this appears unlikely in Lin28bLo/Let7IEC-KO mice since LIN28B did not have any effect on RNA or protein levels of targets in the context of low-level expression in Vil-Lin28bLo mice[18]. While tumors from Lin28bLo/Let7IEC-KO mice appear to be more advanced than those from Vil-Lin28bMed mice[18], surprisingly there is not a significant difference in tumor multiplicity. Nascent tumorigenesis beginning with aberrant crypt foci and/or microadenomas may occur spontaneously in our mouse model of Let-7 depletion, likely due to sporadic deregulation of Wnt signaling or potential spontaneous loss of other tumor suppressive mechanisms. Therefore, Let-7 may not have the “gatekeeper” function that is characteristic of tumor suppressors such as APC. Despite this, there is a link between LIN28B expression in human colon cancer samples and aggressive disease in early stages, which may reflect a role for LIN28B in early neoplastic growth[15]. Supporting this hypothesis is the documentation that LIN28 proteins and Let-7 miRNAs do indeed affect proliferation, migration, and invasion in cell culture models and xenografts of various malignancies[16, 17, 46–49]. However, the differences between Let-7 target mRNAs in each of these models can be quite disparate; e. g. KRAS has a larger effect on tumorigenesis than does HMGA2 in a non-small cell lung cancer model[49], whereas HMGA2 appears to have a much larger role in other cancer models[28, 50–53], likely as a modifier of chromatin structure and gene expression[54–57]. As documented in developmental programs in C. elegans and in human cancers, Let-7 miRNAs repress a stem cell phenotype and tumor-initiating phenotype[3], an association we observe here as well. The connection between HMGA2 and a stem cell phenotype in the intestinal epithelium is also intriguing. HMGA2 promotes somatic stem cell specification, with such roles in neural stem cells and hematopoietic stem cells[25–27]. In some contexts, HMGA2 can enhance Wnt signaling, a known driver of the crypt-base-columnar( CBC) intestinal epithelial stem cell phenotype[34, 58, 59]. This was observed in a mouse model of prostatic intraepithelial neoplasia, where overexpression of Hmga2 in cancer-associated fibroblasts enhances expression of the Wnt ligands Wnt2, Wnt4, and Wnt9b, concomitant with enhanced Wnt signaling and nuclear β-catenin in adjacent neoplastic epithelium[60]. Wnt signaling is required for the enhanced prostatic intraepithelial tumorigenesis induced by Hmga2 in this model[60]. However, we do not observe any effects on Wnt target genes or β-catenin localization in non-malignant Lin28bLo/Let7IEC-KO intestine tissue, suggesting that Wnt deregulation may be an independent event. A recent study that largely replicated our earlier work found that tumors triggered by transgenic LIN28B expression in the mouse small intestine frequently have mutations in Ctnnb1( β-catenin), but not Apc[61]. Although the level of induced LIN28B expression in this study is likely much higher than in Lin28bLo/Let7IEC-KO mice, and therefore different, we suspect that derangements of the Wnt pathway, e. g. in Ctnnb1, are also occurring in tumors in Lin28bLo/Let7IEC-KO mice, as evidenced by frequent nuclear β-catenin. Alternatively, the co-localization of nuclear β-catenin with intense Hmga2 staining in mouse tumors( Fig 6K–6N) could reflect Wnt signaling enhancement of Hmga2 expression, a phenomenon observed in triple-negative breast cancer, a subtype that also tends to express high LIN28B levels[9, 62]. Curiously, in our genetic manipulations of enteroids, exogenous Hmga2 does not affect expression of stem cell markers( such as those assayed in Fig 6I) in transduced intestinal enteroids( S4 Fig). Alternatively, increased Hmga2 expression may enhance survival of stem cells or facilitate the recruitment of a facultative population( such as the quiescent “+4” secretory progenitor stem cell) and entry into the cell cycle. Or, Hmga2 may synergize with deregulated Wnt signaling in the promotion of a stem cell phenotype, which could account for the dramatic up-regulation of stem cell markers we see in tumors from Lin28bLo/Let7IEC-KO mice. Others have also reported that HMGA2 expression is predictive of aggressive disease and poor outcomes in CRC[63], as similarly found in other cancers[50]. While HMGA2 is playing a key role, it is likely that the effects of Let-7 on an intestinal stem cell phenotype and epithelial tumorigenesis are dependent on the collective and/or cooperative role of multiple Let-7 targets. Not uncommonly, additive roles of target genes are uncovered in the genetic dissection of a single pathway, such as that seen for PDGF-receptor signaling and the collective biological contribution of multiple target genes dependent on Pdgfra and Pdgfrb[64]. However, it is challenging to dissect the combinatorial relationships among a dozen candidate targets, especially in mouse models. An oncogenic function of HMGA1 and IGF2BP1 has been reported in other cancers, including colon cancer, with evidence that both factors enhance tumorigenesis[65, 66]. Dissecting the interaction and possible cooperation of Let-7 target mRNAs is critical for designing strategies to ameliorate the loss of Let-7 in human cancers via combinatorial targeted therapies against multiple oncogenes.",
"role": "user"
},
{
"content": "Cancer develops following multiple genetic mutations ( i . e . in tumor suppressors and oncogenes ) , and mutations that cooperate or synergize are often advantageous to cancer cell growth . To study how multiple genes might cooperate , it is usually informative to generate candidate mutations in cells or in mice . Large gene families , such as the Let-7 family , are difficult to silence or mutate because of the large amount of redundancy that exists between similar copies of the same gene; the mutation of one will often be masked or compensated by the continued function of others . In the mouse intestine we have achieved comprehensive depletion of all Let-7 miRNAs in this large multi-genic family through use of an inhibitory protein , called LIN28B , that specifically represses Let-7 , and genetic inactivation of another gene cluster called MirLet7c-2/Mirlet7b . Mice with this comprehensive depletion of Let-7 develop intestinal cancers that resemble human colon cancers . Our further analysis identified another gene , HMGA2 , downstream of this pathway that is critical to this outcome .",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.957
|
[
{
"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\nThe rapid growth of the coronavirus disease 2019 (COVID-19) pandemic, limited availability of personal protective equipment, and uncertainties regarding transmission modes of severe acute respiratory syndrome coronavirus-2 have heightened concerns for the safety of healthcare workers (HCWs). Systematic studies of occupational risks for COVID-19 in the context of community risks are difficult and have only recently started to be reported. Ongoing quality improvement studies in various locales and within many affected healthcare institutions are needed. A template design for small-scale quality improvement surveys is proposed. Such surveys have the potential for rapid implementation and completion, are cost-effective, impose little administrative or workforce burden, can reveal occupational risks while taking community risks into account, and can be repeated easily with short time intervals between repetitions. This article describes a template design and proposes a survey instrument that is easily modifiable to fit the particular needs of various healthcare institutions in the hope of beginning a collaborative effort to refine the design and instrument. These methods, along with data management and analytic techniques, can be widely useful and shared globally. The authors' goal is to facilitate quality improvement surveys aimed at reducing the risk of occupational infection of HCWs during the COVID-19 pandemic.",
"role": "user"
},
{
"content": "[\"Prevention\"]",
"role": "assistant"
}
] |
science.craftchem_ner
|
science.craftchem_ner.7132
|
[
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: ThesestudiesmightclarifywhetherADAM11playsanimportantsignallingorstructuralroleatthesynapticlevelandwhetheritparticipatesinsynapticregulation.",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
] |
science.data_reco_mcq_mc
|
science.data_reco_mcq_mc.1097
|
[
{
"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: I want to train a supervised model for person re-identification from images.\n\nKeywords: person re-identification images\n\nDataset descriptions:\nMarket-1501: Market-1501 is a large-scale public benchmark dataset for person re-identification. It contains 1501 identities which are captured by six different cameras, and 32,668 pedestrian image bounding-boxes obtained using the Deformable Part Models pedestrian detector.\nCUHK02: CUHK02 is a dataset for person re-identification. It contains 1,816 identities from two disjoint camera views.\nSYSU-MM01: The SYSU-MM01 is a dataset collected for the Visible-Infrared Re-identification problem. The images in the dataset were obtained from 491 different persons by recording them using 4 RGB and 2 infrared cameras.\nCUHK03: The CUHK03 consists of 14,097 images of 1,467 different identities, where 6 campus cameras were deployed for image collection and each identity is captured by 2 campus cameras. This dataset provides two types of annotations, one by manually labelled bounding boxes and the other by bounding boxes produced by an automatic detector.\nP-DESTRE: Provides consistent ID annotations across multiple days, making it suitable for the extremely challenging problem of person search, i.e., where no clothing information can be reliably used. Apart this feature, the P-DESTRE annotations enable the research on UAV-based pedestrian detection, tracking, re-identification and soft biometric solutions.\n\nOptions: A: Market-1501 B: CUHK02 C: SYSU-MM01 D: CUHK03 E: P-DESTRE",
"role": "user"
},
{
"content": "[\"Market-1501\", \"CUHK03\"]",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.2304
|
[
{
"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:\nVascular pedicle width in acute lung injury : correlation with intravascular pressures and ability to discriminate fluid status . INTRODUCTION Conservative fluid management in patients with acute lung injury ( ALI ) increases time alive and free from mechanical ventilation . Vascular pedicle width ( VPW ) is a non-invasive measurement of intravascular volume status . The VPW was studied in ALI patients to determine the correlation between VPW and intravascular pressure measurements and whether VPW could predict fluid status . METHODS This retrospective cohort study involved 152 patients with ALI enrolled in the Fluid and Catheter Treatment Trial ( FACTT ) from five NHLBI ARDS ( Acute Respiratory Distress Syndrome ) Network sites . VPW and central venous pressure ( CVP ) or pulmonary artery occlusion pressure ( PAOP ) from the first four study days were correlated . The relationships between VPW , positive end-expiratory pressure ( PEEP ) , cumulative fluid balance , and PAOP were also evaluated . Receiver operator characteristic ( ROC ) curves were used to determine the ability of VPW to detect PAOP < 8 mmHg and PAOP ≥ 18 mm Hg . RESULTS A total of 71 and 152 patients provided 118 and 276 paired VPW/PAOP and VPW/CVP measurements , respectively . VPW correlated with PAOP ( r = 0.41 ; P < 0.001 ) and less well with CVP ( r = 0.21 ; P = 0.001 ) . In linear regression , VPW correlated with PAOP 1.5-fold better than cumulative fluid balance and 2.5-fold better than PEEP . VPW discriminated achievement of PAOP < 8 mm Hg ( AUC = 0.73 ; P = 0.04 ) with VPW ≤67 mm demonstrating 71 % sensitivity ( 95 % CI 30 to 95 % ) and 68 % specificity ( 95 % CI 59 to 75 % ) . For discriminating a hydrostatic component of the edema ( that is , PAOP ≥ 18 mm Hg ) , VPW ≥ 72 mm demonstrated 61.4 % sensitivity ( 95 % CI 47 to 74 % ) and 61 % specificity ( 49 to 71 % ) ( area under the curve ( AUC ) 0.69 ; P = 0.001 ) . CONCLUSIONS VPW correlates with PAOP better than CVP in patients with ALI . Due to its only moderate sensitivity and specificity , the ability of VPW to discriminate fluid status in patients with acute lung injury is limited and should only be considered when intravascular pressures are unavailable .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"mechanical ventilation\", \"Vascular pedicle width ( VPW )\", \"Conservative fluid management\"], \"Outcome\": [\"VPW\", \"Vascular pedicle width ( VPW )\", \"relationships between VPW , positive end-expiratory pressure ( PEEP ) , cumulative fluid balance , and PAOP\", \"VPW and central venous pressure ( CVP ) or pulmonary artery occlusion pressure ( PAOP )\"], \"Participant\": []}",
"role": "assistant"
}
] |
science.craftchem_ner
|
science.craftchem_ner.10069
|
[
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Testissectionsfrom6-wk-oldmalestainedwithantibodiestoDMRT7(red)andSUMO-1(green).",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
] |
science.mslr2022_cochrane_multidoc_summarization
|
science.mslr2022_cochrane_multidoc_summarization.381
|
[
{
"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:\nDiazepam to improve acute stroke outcome: results of the early GABA-Ergic activation study in stroke trial. a randomized double-blind placebo-controlled trial.\nAbstract 1:\nWe tested whether diazepam, a GABA-ergic drug that also inhibits brain nitric monoxide formation, improves acute stroke prognosis.\n 880 patients, randomized within 12 h of acute stroke, received diazepam 10 mg or placebo by rectiole, as soon as possible, followed by 10-mg tablets twice daily for 3 days. Primary outcome was independence (Rankin score <3) at 3 months; secondary outcome was complete recovery (Barthel index >or=95 or Rankin score <or=1).\n Intention-to-treat analyses on all 849 patients with full follow-up (50.4% on diazepam): odds ratio (OR) 1.14, 95% CI 0.87-1.49 for primary endpoint, and an OR of 1.26 (0.90-1.76) for complete recovery, both favoring diazepam. Adjusted analyses for all stroke patients (843): OR 1.20 (0.87-1.65), and 1.25 (0.89-1.74), respectively, and for all infarct patients (748): OR 1.31 (0.93-1.85), and 1.46 (1.02-2.09; p=0.037), respectively. Analyses restricted to cardioembolic infarct patients (200) showed treatment benefit for the primary outcome: OR 2.26, 95% CI 1.07-4.76, p=0.032, and complete recovery: OR 2.65, 95% CI 1.06-6.59, p=0.037. About one third of ischemic stroke patients had 'any adverse event', without any difference between treatment groups. In 95 intracerebral hemorrhage patients, frequency of pneumonia and death were higher in the diazepam group than in the placebo group: 35 and 10%, 22 and 12%, respectively.\n Although point estimates favored diazepam treatment in various analyses, our data did not confirm our primary hypothesis. Diazepam treatment seems beneficial in cardioembolic infarct patients, is safe in acute ischemic stroke, but may better be avoided in intracerebral hemorrhage.\n Copyright (c) 2006 S. Karger AG, Basel.\n\n\nTitle 2:\nThe Clomethiazole Acute Stroke Study in tissue-type plasminogen activator-treated stroke (CLASS-T): final results.\nAbstract 2:\nTo assess the safety of tissue-type plasminogen activator (t-PA) plus clomethiazole in patients with acute ischemic stroke and determine the feasibility of combination stroke therapy.\n Clomethiazole is a neuroprotectant that appeared to improve outcome in patients with clinical deficits of a major stroke (total anterior circulation syndrome [TACS]) in a previous study, the Clomethiazole Acute Stroke Study (CLASS). Combining a neuroprotectant such as clomethiazole with thrombolysis may augment the beneficial effects of the two agents. CLASS-t-PA (CLASS-T) was a pilot study to explore the safety of the combination and the feasibility of performing combination treatment in the setting of acute ischemic stroke.\n In a randomized, double-blind design (stratified for age, severity at admission, and time since onset of stroke), all patients received 0.9 mg/kg t-PA beginning within 3 hours of stroke onset and then either 68 mg/kg clomethiazole (n = 97) IV over 24 hours or placebo (n = 93) beginning within 12 hours of stroke onset. Patients were followed for 90 days. The main measures of safety were mortality and serious adverse events, and the main measure of functional outcome was the Barthel Index.\n The number of serious adverse event reports was 47 in the clomethiazole group and 48 in the placebo group. Death during the 90 days after treatment occurred in 15 clomethiazole and nine placebo patients (p = 0.26). Sedation was reported as an adverse event during therapy in 42% of clomethiazole patients vs 13% of placebo patients. The proportion of patients with TACS was 53% in the clomethiazole group and 41% in the placebo group. In the TACS subgroup, 52.9% of the clomethiazole patients scored a Barthel Index greater than 60 vs 44.7% of placebo patients (odds ratio 1.39; 95% CI 0.60 to 3.23).\n In this pilot study, there were no safety concerns related to the combination of t-PA and clomethiazole. The combination paradigm proved feasible, although many patients received clomethiazole several hours after thrombolysis; future studies must require prompt administration of the neuroprotectant either before or during administration of the thrombolytic. Patients with major strokes (TACS) may have the potential to benefit from the combination of t-PA and clomethiazole.\n\n\nTitle 3:\nClomethiazole acute stroke study (CLASS): results of a randomized, controlled trial of clomethiazole versus placebo in 1360 acute stroke patients.\nAbstract 3:\nThe efficacy and safety of the neuroprotective drug clomethiazole was tested in a double blind placebo controlled trial in patients with a clinical diagnosis of acute hemispheric stroke.\n Patients with symptom onset of </=12 hours before the start of treatment were included in the study. Clomethiazole (75 mg/kg) or placebo was given as an intravenous infusion over a 24-hour period. Patients were followed up for 90 days. The primary efficacy variable was the proportion of patients reaching relative functional independence (>/=60 points on the Barthel Index) at 90 days.\n A total of 1360 patients were included. In the main efficacy analysis (n=1353), 56.1% of patients taking clomethiazole and 54.8% of placebo patients reached relative functional independence. The difference was not statistically significant. An analysis of the effect of time since onset of symptoms showed no difference between the treatment groups. Clomethiazole was generally well tolerated and appeared safe in the population studied. Sedation was the most common adverse event, leading to treatment withdrawal that occurred in 15.6% of clomethiazole-treated patients compared with 4.2% of placebo-treated patients. In a subgroup classified before randomization as having total anterior circulation syndrome (TACS) (n=545, or 40% of all randomized patients), the percentage of those reaching relative functional independence was 40.8% on clomethiazole and 29.8% on placebo, a difference of approximately 11 percentage units. TACS patients have clinical symptoms suggesting a \"large\" stroke.\n Clomethiazole had no adverse or beneficial effect on long-term outcome for all patients but produced sedation. The hypothesis that clomethiazole is effective in patients with large strokes will be tested in a further study.\n\n\nTitle 4:\nClomethiazole Acute Stroke Study in ischemic stroke (CLASS-I): final results.\nAbstract 4:\nA previous trial (the Clomethiazole Acute Stroke Study) generated the hypothesis that clomethiazole is effective in patients with a major ischemic stroke (total anterior circulation syndrome), and this was tested in the present study.\n A total of 1198 patients with major ischemic stroke and a combination of limb weakness, higher cortical dysfunction, and visual field deficits were randomly assigned to clomethiazole (68 mg/kg IV over 24 hours) or placebo. The study drug was initiated within 12 hours of symptom onset. Functional outcome and neurological recovery were assessed at days 7, 30, and 90, with the proportion of patients with a Barthel Index > or =60 at last follow-up as the primary outcome measure.\n The patients were randomly assigned equally, and the two treatment groups were well matched for baseline characteristics, including stroke severity (mean National Institutes of Health Stroke Scale score 16.9+/-5.2). Ninety-six percent were classified as total anterior circulation syndrome. The proportion of patients reaching a Barthel Index score of > or =60 was 42% in the clomethiazole-treated group and 46% in the placebo-treated group (odds ratio, 0.81; 95% CI, 0.62 to 1.05; P=0.11). There was no evidence of efficacy on any secondary outcome variables (modified Rankin Score, National Institutes of Health Stroke Scale, Scandinavian Stroke Scale, and 30-day CT infarct volumes) compared with placebo. Subgroup analysis showed a similar lack of treatment effect in patients treated early (<6 hours) and in those treated later (6 to 12 hours). Somnolence was an expected pharmacological effect of clomethiazole, and this occurred during treatment as an adverse event in half of the patients randomly assigned to study drug.\n The target population was selected, and sufficient drug was given to produce the expected pharmacological effect in the brain. Clomethiazole does not improve outcome in patients with major ischemic stroke.",
"role": "user"
},
{
"content": "This review does not provide the evidence to support the use of GABA receptor agonists (chlormethiazole or diazepam) for the treatment of patients with acute ischemic or hemorrhagic stroke. Chlormethiazole appeared to be beneficial in improving functional independence in patients with TACS according to the subgroup analysis, but this result must be interpreted with great caution. More well-designed RCTs with large samples of TACS would be required for further confirmation. However, somnolence and rhinitis are frequent adverse events related to chlormethiazole.",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_arxiv
|
science.scientific_papers_summarization_single_doc_arxiv.117064
|
[
{
"content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nthe determination of the ages of pulsars is of crucial importance to neutron star astrophysics .\nneutron star population synthesis , birthrate , supernova remnant associations , and even cooling timescales ( which serve as probes of the neutron star equation of state ) , all depend on accurate determinations of pulsar ages . in general , a pulsar s age is estimated by assuming a spin - down evolution of the form @xmath4 where @xmath5 is known as the _ braking index_. it can be determined observationally by measuring @xmath6 , since , as is easily shown , @xmath7 . integrating equation [ eq : spindown ] over the lifetime of the pulsar , assuming a constant braking index , results in the following estimate of the pulsar s age : @xmath8 , \\label{eq : age}\\ ] ] where @xmath9 is the spin period of the pulsar at birth .\nit is conventional to assume @xmath10 , appropriate for spin - down due to magnetic dipole radiation , and @xmath11 to derive the characteristic age @xmath12 . timing noise , stochastic variations in the pulse spin - down ( see e.g. * ?\n* ) , make accurate determinations of the braking index impossible for the large majority of the over 1300 radio pulsars currently known .\nthe five reliably measured radio pulsar braking indices are in the range @xmath13 @xcite .\nthis clearly signals a significant difference between pulsar electrodynamics and a simple dipole spinning down _ in vaccuo_. this is of major interest to modelers of pulsar magnetospheres ( e.g. * ? ? ?\nbut it is also very important for neutron star astrophysics in general : if the braking indices of all pulsars are @xmath14 , then the characteristic age systematically underestimates the true age . on the other hand , initial spin periods @xmath9\nthat are a non - negligible fraction of the current spin period @xmath15 lead to a systematic over estimation of the true age .\nthe distribution of initial spin periods is also of intrinsic scientific interest , since it gives clues to the physics of the formation of neutron stars as well as such possibilities as early epochs of rapid spin - down due to gravitational radiation or interactions with fossil disks .\nhowever , to infer the initial spin period from equation [ eq : age ] requires an independent determination of the true age , such as an associated historical event or a well determined age from an associated supernova remnant .\nthis situation is very rare .\nthe best , and until recently only , example is the crab pulsar , whose measured braking index and known age results in an inferred @xmath16 ms .\nthere are very few other historical supernovae that might be used .\nof course an isolated pulsar s current spin period is an upper limit on the initial spin period , so , for example , @xmath17 ms can be trivially inferred for psr j0537@xmath186910 in the lmc @xcite .\ng11.20.3 is a young supernova remnant plausibly associated with the historical `` guest star '' witnessed by chinese astronomers in the year 386 a.d .\n@xcite . radio and x - ray estimates of its age @xcite , assuming a type ii supernova , support the historical association .\na young 65-ms pulsar with spin - down energy @xmath19 erg s@xmath20 was discovered in x - rays by _ asca _ within [email protected] @xcite .\nrecent _ chandra _ observations place the pulsar at the precise center of the remnant @xcite , making the association of the two unambiguous . surprisingly , the @xmath21 , determined from one observation in 1994 and three observations in 1998 , implies a characteristic spin - down age of @xmath22 yr @xcite , 15 times that inferred from the historical association , the remnant radio surface brightness , and the remnant x - ray spectrum . for this large discrepancy to be resolved , either the braking index @xmath23 , or the initial spin period @xmath24 ms is very near the current spin period .\nvery recently , a similar @xmath9 was inferred for the newly discovered pulsar in 3c58/sn1181 @xcite , suggesting that such long initial spin periods may be common .\nunfortunately , the number of systems where the initial spin period can be estimated is likely to remain small .\ntherefore , it is crucial that all alternative explanations for the age discrepancy observed in g11.20.3 be fully explored .\nthe results presented here were obtained using the proportional counter array ( pca ) on board the _ rossi x - ray timing explorer _ ( _ rxte _ ) .\nour observations consist primarily of @xmath25 ks observations taken on a monthly basis .\ndeep radio searches have been unable to detect the pulsar @xcite , and so x - ray monitoring of the source is the only option for timing .\nthe spin - down rate @xmath26 of psr j18111925 was first made by @xcite using _ asca _ , essentially on the basis of periods at just two widely spaced epochs .\nhere we present a phase - coherent timing solution for the the pulsar using regular _ rxte _ observations .\n.spin parameters for psr j18111925 derived from phase coherent timing of this source for @xmath27 months.[ta : spin ] [ cols=\"<,^\",options=\"header \" , ] in order to obtain a high signal - to - noise pulsed spectrum for psr j18111925 , data from each observing epoch were folded at the expected pulse period as was done for the timing analysis .\nhowever , here , 8 phase bins were used across the pulse . for each phase bin\n, we maintained a spectral resolution of 128 bins over the pca range .\none off - pulse phase bin was used as a background estimator .\nthe pulse profiles were then phase aligned , so that the same off - pulse bin was used for background in every case .\nthe remaining phase bins were summed , and their spectral bins regrouped into groups of 4 using the ` ftool ` ` grppha ` .\nenergies below 2 kev and above 70 kev were ignored , leaving 23 spectral channels for fitting .\nthe regrouped , phase - summed data set , along with the background measurement , were used as input to the x - ray spectral fitting software package ` xspec ` .\nresponse matrices were created using the ` ftool`s ` xtefilt ` and ` pcarsp ` .\nwe fit the data using a simple photoelectrically absorbed power law , holding only @xmath28 fixed at the value found by @xcite ( see table [ ta : spectra ] ) .\nuncertainties were measured using the ` xspec ` command ` steppar ` .\nthe photon index @xmath29 we obtained is consistent within the uncertainties with the value ( @xmath30 ) found by @xcite using _ chandra _ observations .\n, scaledwidth=45.0% ]\nthe ratio of the pulsed x - ray luminosity in the 210 kev band to @xmath31 gives an efficiency , @xmath32 assuming isotropic emission . comparing the efficiencies calculated by @xcite for the 41 known rotation - powered x - ray pulsars ,\npsr j18111925 is the third most efficient , with psr j18460258 @xcite being the first , and psr b150958 @xcite the second .\nnote that the efficiencies calculated by @xcite often included unpulsed contributions resulting from pulsar wind nebular emission , therefore their efficiencies can only be considered upper limits to the pulsed efficiencies .\nit is interesting to note the similarities among the three most x - ray efficient rotation - powered pulsars : ( i ) they all have long duty - cycles , with profiles that remain broad even to high energies ( @xmath33 kev ) ( ii ) they have very hard spectra with photon indices @xmath34 ( iii ) they are all very young ( @xmath35 yrs ) pulsars in the centers of supernova remnants ( iv ) they all have pulsar wind nebulae .\nfurthermore , none of these pulsars have been detected in high energy @xmath36-rays ( @xmath37 mev ) .\nthis is in contrast to pulsars such as the crab , vela , and psr b170644 @xcite , which have very narrow x - ray pulse profiles , relatively low x - ray efficiencies , but are all detected in high energy @xmath36-rays .\nthe spectrum and pulse morphology can give us a clue to the emission mechanism at work in psr j18111925 .\nhigh - energy emission mechanism models generally fall into two classes : polar cap models ( e.g. * ? ? ?\n* ) and outer gap models ( e.g. * ? ? ?\nthe two harder components of the four component x - ray profile ( in the _ rxte _ band ) of the vela pulsar , which are as hard or harder that psr j18111925 are due to particle curvature emission according to the polar cap model ( see * ? ? ?\nthese two components are very narrow and phase aligned with the double peaked @xmath36-ray pulse . for psr j18111925 , the broad profile and the absence of @xmath36-ray pulsations make a similar mechanism unlikely . in the outer gap model ,\nthe broad , hard profile of psr j18111925 would be from the tail of the synchrotron component . according to @xcite , the peak of the synchrotron spectrum for psr j18111925 would occur at @xmath38 mev ,\nthis could be verified with @xmath36-ray observatories such as _ glast _ and _\nthis work was supported in part by a nasa ltsa grant , an nserc research grant .\nvmk is a canada research chair .\nthis research has made use of data obtained through the high energy astrophysics science archive research center online service , provided by the nasa / goddard space flight center .",
"role": "user"
},
{
"content": "the x - ray pulsar psr j18111925 in the historic supernova remnant g11.20.3 has a characteristic age over 10 times the age of the remnant . \n this likely implies that its current spin period , @xmath0 ms , is close to its birth spin period . \n alternatively , the pulsar may have an unusually high braking index . \n we report here on regular _ rossi x - ray timing explorer_/ proportional counting array ( _ rxte_/pca ) timing observations of the pulsar that were designed to measure its braking index . \n we provide a preliminary phase - coherent timing solution which includes a significant @xmath1 . \n the braking index we measure is @xmath2 , likely a result of conventional timing noise . \n we also report on a preliminary analysis of the pulsar s unusually hard spectrum : we determine a photon index of @xmath3 , for the pulsed component of the spectra , consistent within the uncertainties with previous _ \n asca _ and _ chandra _ observations . \n the pulsed emission of psr j18111925 is seen beyond 30 kev , and the pulsations remain sinusoidal up to and beyond this energy .",
"role": "assistant"
}
] |
science.mslr2022_ms2_multidoc_summarization
|
science.mslr2022_ms2_multidoc_summarization.2705
|
[
{
"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:\nHelicobacterpylori in Dental Plaque (A Comparison of Different PCR Primer Sets)\nAbstract 1:\nThis study was design ed to compare differentprimer sets for PCR analysis of H. pylori in the sameseries of 40 dental plaque sample s. Three pairs ofprimers , HPU1/HPU2 , HP1/HP2 , and EHC-U/EHC-L , directed to the urease A gene , 16S rRNA gene , or 860-bpDNA of H. pylori , respectively , were used . Our results demonstrate that EHC-L/EHC-U were moRespecific and sensitive for H. pylori added to saliva or dental plaque than HPU1/HPU2 and HP1/HP2 . Thedetection rates for H. pylori DNA in dental plaque sample s from r and omly selected adult patients from theDental Clinic of the University of Ulm were 26.5 % ( 9/34 ) for HPU1/HPU2 , 78.9 % ( 30/38 ) for HP1/HP2 , and 100 % ( 40/40 ) for EHC-U/EHC-L ( P < 0.001 ) . Nested PCRusing primers directed to the 860-bp DNA of H. pylorifurThe r confirmed the presence of H. pylori DNA ( 40/40 ) in all these sample s. Our results indicate that primers EHC-U/EHC-L are to be recommendedfor PCR detection of H. pylori in the oralcavity\n\n\nTitle 2:\nHelicobacter pylori in the dental plaque of healthy Saudis.\nAbstract 2:\nThe objective of this study is to determine the presence of Helicobacter pylori in the dental plaque of healthy Saudis and its relation to dental care . One hundred r and omly selected healthy Saudis attending the dental clinic were assessed for oral hygiene and periodontal disease by dental examination . Information about the use of toothpaste , chewing stick , smoking and dentures was obtained . Sample s of dental plaque were collected after scoring it according to the plaque index . Presence of H. pylori in the plaque was sought by a commercially available rapid urease test with a sensitivity of 94 % and a specificity of 100 % . The presence of H. pylori was indicated by a positive rapid urease test in 81 % . There was significant correlation of heavy dental plaque ( plaque index score 3 ) with presence of H. pylori ( p=0.03 ) . We conclude that H. pylori is present in the dental plaque of most Saudis and this is due to poor oral hygiene\n\n\nTitle 3:\nOral health status and oral hygiene practices of patients with peptic ulcer and how these affect Helicobacter pylori eradication from the stomach.\nAbstract 3:\nBACKGROUND Helicobacter pylori eradication from the oral cavity is more difficult than from the stomach . Thus , if the bacterium survives the antibacterial therapy in the oral cavity , it would be able to re-infect the stomach within a few weeks . Since oral health status could correspond to oral infection with H. pylori , the aim of the study was to determine whether oral health and oral hygiene practice s affect the efficacy of H. pylori eradication from the stomach . MATERIAL AND METHODS The study was performed in 137 patients with peptic ulcer who had undergone a 7-day course of eradication treatment with one of two sets of drugs : 1 , omeprazole , amoxicillin , and tinidazole or 2 , omeprazole , clarithromycin , and tinidazole . The efficacy of H. pylori eradication from the stomach was evaluated at the second gastroscopy 4 weeks after cessation of eradication therapy by means of two methods : rapid urease test and histology . The examination of natural dentition and prosthetic restorations as well as the assessment of hygienic procedures referring to natural dentition and dentures accompanied the second gastroscopy . RESULTS No association was found between the efficacy of H. pylori eradication from the stomach and the number of natural teeth , decayed teeth , use of dentures , debris index , or periodontal index . However , an association between eradication success and some oral hygiene procedures were noted . Unexpectedly , in patients treated with omeprazole , amoxicillin and tinidazole , the removal of dental prosthesis for the night and brushing the natural teeth twice a day or more reduced the efficacy of H. pylori eradication from the stomach . CONCLUSIONS Oral health and oral hygiene practice s seem unlikely to increase the efficacy of H. pylori eradication from the stomach",
"role": "user"
},
{
"content": "Based on the systematic review of the available literature on H. pylori infection and its presence in the oral cavity , it can be concluded that dental plaque can act as a reservoir , and proper oral hygiene maintenance is essential to prevent reinfection .",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.8507
|
[
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: This paper demonstrates that a combination of both visual and social features can predict popularity of images accurately.\n\nKeyphrases: popularity prediction images\n\nDataset descriptions:\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.\nMSD: The Million Song Dataset is a freely-available collection of audio features and metadata for a million contemporary popular music tracks. The core of the dataset is the feature analysis and metadata for one million songs, provided by The Echo Nest.\nImageNet: The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection.\nLocalized Narratives: We propose Localized Narratives, a new form of multimodal image annotations connecting vision and language. We ask annotators to describe an image with their voice while simultaneously hovering their mouse over the region they are describing.\n\nOptions: A: GuessWhat?! B: MSD C: ImageNet D: Localized Narratives",
"role": "user"
},
{
"content": "ImageNet",
"role": "assistant"
}
] |
science.bioasq_general_qa
|
science.bioasq_general_qa.385
|
[
{
"content": "Answer the following question using the provided context. Only provide the answer without any additional text.\n\nQuestion: Under which conditions does AMPK phosphorylate TSC2?\nContext: The AMP-activated serine/threonine protein kinase (AMPK) is a sensor of cellular energy status found in all eukaryotes that is activated under conditions of low intracellular ATP following stresses such as nutrient deprivation or hypoxia.\nAMPK directly phosphorylates at least two proteins to induce rapid suppression of mTORC1 activity, the TSC2 tumour suppressor and the critical mTORC1 binding subunit raptor.\nAMPK is a highly conserved sensor of cellular energy status that is activated under conditions of low intracellular ATP. AMPK responds to energy stress by suppressing cell growth and biosynthetic processes, in part through its inhibition of the rapamycin-sensitive mTOR (mTORC1) pathway. AMPK phosphorylation of the TSC2 tumor suppressor contributes to suppression of mTORC1\nTSC2 is regulated by cellular energy levels and plays an essential role in the cellular energy response pathway. Under energy starvation conditions, the AMP-activated protein kinase (AMPK) phosphorylates TSC2 and enhances its activity.\nConversely, energy depletion reduces Rheb-GTP charging through the ability of the adenosine monophosphate-activated protein kinase to phosphorylate TSC2 and stimulate its Rheb-GTPase activating function, as well as by HIFalpha-mediated transcriptional responses that act upstream of the TSC1/2 complex.\nUnder energy starvation conditions, the AMP-activated protein kinase (AMPK) phosphorylates TSC2 and enhances its activity.\nHere, we report that LKB1 is required for repression of mTOR under low ATP conditions in cultured cells in an AMPK- and TSC2-dependent manner, and that Lkb1 null MEFs and the hamartomatous gastrointestinal polyps from Lkb1 mutant mice show elevated signaling downstream of mTOR.\nHypoxia results in energy starvation and activation of the AMPK/TSC2/Rheb/mTOR pathway.\nAMPK phosphorylation of the TSC2 tumor suppressor contributes to suppression of mTORC1; however, TSC2-deficient cells remain responsive to energy stress.\nUnder energy starvation conditions, the AMP-activated protein kinase (AMPK) phosphorylates TSC2 and enhances its activity.\nAMPK phosphorylation of the TSC2 tumor suppressor contributes to suppression of mTORC1; however, TSC2-deficient cells remain responsive to energy stress.\nUnder energy starvation conditions, the AMP-activated protein kinase (AMPK) phosphorylates TSC2 and enhances its activity. Phosphorylation of TSC2 by AMPK is required for translation regulation and cell size control in response to energy deprivation.\nHere, we describe that TSC2 is regulated by cellular energy levels and plays an essential role in the cellular energy response pathway. Under energy starvation conditions, the AMP-activated protein kinase (AMPK) phosphorylates TSC2 and enhances its activity.\nOnce activated under the various metabolic stress conditions, AMPK regulates a multitude of metabolic pathways to balance cellular energy. In addition, AMPK also induces cell cycle arrest or apoptosis through several tumor suppressors including LKB1, TSC2, and p53.",
"role": "user"
},
{
"content": "The AMP-activated serine/threonine protein kinase (AMPK) is a sensor of cellular energy status found in all eukaryotes, and it is activated under conditions of low intracellular ATP following stresses such as nutrient deprivation or hypoxia.",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_arxiv
|
science.scientific_papers_summarization_single_doc_arxiv.13212
|
[
{
"content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nwe present a measurement of the hadronic photon structure function at a higher value of the average momentum transfer squared , , than has ever previously been reported .\nthe measurement of is interesting because of its potential to test perturbative qcd @xcite . in the high-\ndomain the perturbatively calculable point - like contribution to , which rises logarithmically with , dominates over the non - perturbative hadron - like part .\nthe structure function has been measured at of 706 using a sample of single - tagged two - photon events recorded by the opal detector between 1997 and 1999 .\nthese events ( also referred to as events ) can be regarded as deep inelastic scattering of an electron on a quasi - real photon , and the flux of quasi - real photons can be calculated using the equivalent photon approximation @xcite . to study the distribution of events in @xmath0 and\nis needed .\nthese variables are related to experimentally measurable quantities by @xmath1 and @xmath2 where is the energy of the beam electron , and are the energy and polar angle of the deeply inelastically scattered electron , @xmath3 is the invariant mass squared of the hadronic final state and @xmath4 , where @xmath5 is the four - momentum of the quasi real target photon .\nthe requirement that the associated electron is not visible in the detector ensures that @xmath6 , so can be neglected when calculating @xmath0 from equation [ eqn : xcalc ] .\nthis analysis uses data from the 1997 to 1999 lep runs , with centre - of - mass energies ranging from 183 to 202 .\nthe total integrated luminosity is @xmath7 .\ncandidate @xmath8 events are required to satisfy the following selection criteria , in addition to several technical cuts to ensure good detector status and track quality . 1 . a tagged electron is required ; that is , a cluster in the opal electromagnetic endcap calorimeter with an energy of at least @xmath9 and a polar angle @xmath10 in the range 230500 mrad with respect to either beam direction .\nthe energy of the most energetic electromagnetic cluster in the hemisphere opposite to that which contains the tagged electron must be less than @xmath11 .\n3 . the number of tracks originating from the hadronic final state must be at least 3 .\nthe visible invariant mass of the hadronic system is required to be in the range @xmath12 .\nthe number of objects ( tracks plus unassociated clusters ) , belonging to the hadronic final state must be at least 9 .\nthe energy deposited in a cone of 200 mrad half - angle about the direction of the tag , excluding the tag itself , must not be more than 2 .\ncuts 14 select a sample of candidate single - tag hadronic two - photon events , with double - tag events excluded by cut 2 .\nevents with leptonic final states are rejected by cuts 3 and 5 .\nthe invariant mass cuts have two functions .\nthe lower limit removes the low-@xmath13 region which is dominated by resonance production and is very difficult to model accurately .\nthe upper limit rejects background events from hadronic decays of bosons , as does cut 6 .\na total of 348 events pass these cuts , with the data covering the range @xmath14 .\nthere is a two sigma difference between the number of events selected in the 1997/8 data and that recorded in 1999 , with the 1999 data lying below the monte carlo expectation , particularly at low .\nno explanation has been found for this .\nthe larger samples of events with the electron tagged in subdetectors at lower polar angles are consistent between the two periods , suggesting that the observed difference could well be purely statistical .\nhowever , as a precaution , the difference is included in the systematic error in this preliminary analysis .\nthe opal lep1 analysis of using tags in the same subdetector @xcite found the trigger efficiency to be 100% .\nthe present analysis uses a tighter set of cuts , thus no inefficiency is to be expected , and a trigger efficiency of 100% is assumed .\nmonte carlo programs are used to simulate events and to provide background estimates .\nthe monte carlo generator used to simulate signal multiperipheral events is herwig 5.9+(dyn ) @xcite .\nthe grv lo @xcite parameterisation of was used as the input structure function .\nthe dominant background comes from the reaction @xmath15 .\nalso significant are non - multiperipheral four - fermion processes with final states and the qed process .\nless severe sources of background are estimated to account for around 1% of the data sample .\nfigure [ datadists ] shows comparisons between data and monte carlo distributions .\nfigure [ datadists](b ) shows the polar angle of the tagged electron .\nit can be seen that the monte carlo is somewhat higher than the data in the polar range 260350 mrad . turning to variables describing the hadronic final state\n, it can be seen that the number of charged tracks is reasonably well described , figure [ datadists](c ) , but that the monte carlo lies above the data at low in figure [ datadists](d ) - which correlates with high @xmath0 .\nthe perennial problem in measurements of is that , because the centre - of - mass system does not coincide with the laboratory system , the hadronic final state , which must be measured to determine @xmath13 , is only partially observed in the detector .\nthis leads to a dependence of the measurement on the monte carlo modelling , which is needed for the unfolding process used to relate the visible distributions to the underlying @xmath0 distribution . in the high- measurement presented here , however , the situation is not as serious as at lower values of . because of the larger tagging angle\n, the hadronic final state has much more transverse momentum and as a consequence is better contained in the detector .\nfigure [ wrec ] shows the correlation between the measured invariant mass and the generated @xmath13 as given by herwig 5.9+(dyn ) .\nit can be seen that the correlation is maintained throughout .\nthis is in contrast with the situation observed in the lower analysis @xcite where the correlation deteriorates at high w. as a consequence of this the result can be expected to have a smaller dependence on the monte carlo modelling of the hadronic final state .\nafter subtraction of background , the data are unfolded on a linear scale in @xmath0 in the range @xmath16 using the guru program @xcite .\neach data point is corrected for radiative effects and bin - centre corrections are applied . in figure\n[ result ] the data are compared to several theoretical calculations .\nthe leading order parameterisations of from grv , sas1d @xcite and whit1 @xcite , which all include a contribution from massive charm quarks , are described in detail in reference @xcite .\nthe naive quark - parton model ( qpm ) simulates only the point - like component of , and is calculated for four active flavours with masses of 0.325 for light quarks and 1.5 for charm quarks .\nit can be seen that in this high- regime the differences between the models are relatively small , particularly in the central @xmath0-region .\nthe differences between the qpm and the other models are much smaller than at lower , where the photon has been shown to have a significant hadron - like component @xcite .\nall the predictions are compatible with the data in three of the @xmath0 bins , but overshoot the data in one bin .\nthe photon structure function has been measured using deep inelastic electron - photon scattering events recorded by the opal detector during the years 19971999 .\nthe value of 706 represents the highest measured thus far .\nhas now been measured by opal at values ranging from 1.9706 .\ne. witten , nucl .\nb120 * ( 1977 ) 189 ; + a. cordier and p.m. zerwas , in ecfa workshop on lep200 , vol .\n1 , cern 87 - 08 , ecfa 87/108 , edited by a. bhm and w. hoogland , p. 242 .\nr. nisius , phys . rep .\n* 332 * ( 2000 ) 165 , hep - ex/0006032 .\nvon weizscker , z. phys .\n* 88 * ( 1934 ) 612 ; + e.j .\nwilliams , phys .\n* 45 * ( 1934 ) 729 ; + v.m .\nbudnev , phys . rep . * 15 * ( 1975 ) 181 .\nopal collaboration , k. ackerstaff , z. phys .\n* c74 * ( 1997 ) 33 .\ng. marchesini , comp .\n* 79 * ( 1992 ) 465 .\n+ the lep working group for two - photon physics , aleph , l3 and opal collaborations , _ comparison of deep inelastic electron - photon scattering data with the herwig and phojet monte carlo models _ , cern - ep/2000 - 109 , submitted to eur .\nj. * c*. m. glck , e. reya and a. vogt , phys . rev . *\nd45 * ( 1992 ) 3986 ; + m. glck , e. reya and a. vogt , phys . rev .\n* d46 * ( 1992 ) 1973 .\nclay , these proceedings ; + opal collaboration , g. abbiendi , _ measurement of the low-@xmath0 behaviour of the photon structure function _ , cern - ep/2000 - 082 , hep - ex/0007018 , accepted by eur .\nj. * c*. a. hcker , v. kartvelishvili , nucl . instr . and meth .\n* a372 * ( 1996 ) 469 , hep - ph/9509307 .\ng.a . schuler and t. sjstrand , z. phys . *\nc68 * ( 1995 ) 607 , hep - ph/9503384 .\nk. hagiwara , phys .\n* d51 * ( 1995 ) 3197 , hep - ph/9406252 .",
"role": "user"
},
{
"content": "the photon structure function has been measured at of 706 using a sample of two - photon events with a scattered electron observed in the opal electromagnetic endcap calorimeter . \n the data were taken during the years 1997 - 1999 , when lep operated at centre - of - mass energies ranging from 183 to 202 , and correspond to an integrated luminosity of 424 . \n this analysis represents the highest measurement of made to date . \n ucl / hep 2000 - 08 + opal cr444 +",
"role": "assistant"
}
] |
science.genia_ner
|
science.genia_ner.1364
|
[
{
"content": "Extract all unique entities of these types from the biomedical abstract: [\"CellLine\", \"DNA\", \"Protein\", \"CellType\", \"RNA\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities found for a type, use [].\n\nAbstract:\n\nThe PEBP2betaMYH11 fusion created by Inv (16) (p13;q22) in myeloid leukemia impairs neutrophil maturation and contributes to granulocytic dysplasia. Chromosomal translocations involving the genes encoding the alpha and beta subunits of the Pebp2 / Cbf transcription factor have been associated with human acute myeloid leukemia and the preleukemic condition, myelodysplasia. Inv (16) (p13;q22) fuses the gene encoding the beta subunit of Pebp2 to the MYH11 gene encoding a smooth muscle myosin heavy chain (Smmhc). To examine the effect of the inv (16) (p13;q22) on myelopoiesis, we used the hMRP8 promoter element to generate transgenic mice expressing the Pebp2beta Smmhc chimeric fusion protein in myeloid cells. Neutrophil maturation was impaired in PEBP2betaMYH11 transgenic mice. Although the transgenic mice had normal numbers of circulating neutrophils, their bone marrow contained increased numbers of immature neutrophilic cells, which exhibited abnormal characteristics. In addition, PEBP2betaMYH11 inhibited neutrophilic differentiation in colonies derived from hematopoietic progenitors. Coexpression of both PEBP2betaMYH11 and activated NRAS induced a more severe phenotype characterized by abnormal nuclear morphology indicative of granulocytic dysplasia. These results show that PEBP2betaMYH11 can impair neutrophil development and provide evidence that alterations of Pebp2 can contribute to the genesis of myelodysplasia.",
"role": "user"
},
{
"content": "{\"CellLine\": [], \"CellType\": [\"circulating neutrophils\", \"myeloid cells\", \"hematopoietic progenitors\", \"immature neutrophilic cells\"], \"DNA\": [\"Inv (16) (p13;q22)\", \"MYH11 gene\", \"inv (16) (p13;q22)\", \"hMRP8 promoter element\"], \"Protein\": [\"Smmhc\", \"Pebp2beta\", \"PEBP2betaMYH11\", \"Pebp2\", \"Smmhc chimeric fusion protein\", \"beta subunit\", \"Pebp2 / Cbf transcription factor\", \"alpha and beta subunits\", \"smooth muscle myosin heavy chain\", \"activated NRAS\"], \"RNA\": []}",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.4196
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nWe present structured domain randomization (SDR), a variant of domain randomization (DR) that takes into account the structure of the scene in order to add context to the generated data. In contrast to DR, which places objects and distractors randomly according to a uniform probability distribution, SDR places objects and distractors randomly according to probability distributions that arise from the specific problem at hand. In this manner, SDR-generated imagery enables the neural network to take the context around an object into consideration during detection. We demonstrate the power of SDR for the problem of 2D bounding box car detection, achieving competitive results on real data after training only on synthetic data. On the KITTI easy, moderate, and hard tasks, we show that SDR outperforms other approaches to generating synthetic data (VKITTI, Sim 200k, or DR), as well as real data collected in a different domain (BDD100K). Moreover, synthetic SDR data combined with real KITTI data outperforms real KITTI data alone.11Video is at http: youtu.be 1WdjWJYx9AY\n\nCited Abstract(s):\n[1]: \n\n[2]: We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the simulator-such as lighting, pose, object textures, etc.-are randomized in non-realistic ways to force the neural network to learn the essential features of the object of interest. We explore the importance of these parameters, showing that it is possible to produce a network with compelling performance using only non-artistically-generated synthetic data. With additional fine-tuning on real data, the network yields better performance than using real data alone. This result opens up the possibility of using inexpensive synthetic data for training neural networks while avoiding the need to collect large amounts of hand-annotated real-world data or to generate high-fidelity synthetic worlds-both of which remain bottlenecks for many applications. The approach is evaluated on bounding box detection of cars on the KITTI dataset.\n\n[3]: In this paper, we propose an approach that exploits object segmentation in order to improve the accuracy of object detection. We frame the problem as inference in a Markov Random Field, in which each detection hypothesis scores object appearance as well as contextual information using Convolutional Neural Networks, and allows the hypothesis to choose and score a segment out of a large pool of accurate object segmentation proposals. This enables the detector to incorporate additional evidence when it is available and thus results in more accurate detections. Our experiments show an improvement of 4.1 in mAP over the R-CNN baseline on PASCAL VOC 2010, and 3.4 over the current state-of-the-art, demonstrating the power of our approach.",
"role": "user"
},
{
"content": "Our previous work in [2] used DR to train an object detector for cars, which was tested on KITTI, similar to the work presented here. In that research, we learned that DR requires a large amount of data to train given the amount of variation, often the network finds it hard to learn the correct features, and the lack of context prevents DR from detecting small vehicles. The research described in this paper aims to address these limitations. Other researchers [3] have also found context to be important. Georgakis al [1] create training data for indoor robotics by locating planes in background images and pasting foreground objects onto them, an acknowledgment of the importance of context.",
"role": "assistant"
}
] |
science.chemsum_single_document_summarization
|
science.chemsum_single_document_summarization.112419
|
[
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nI2-SDS-H2O System: A highly Efficient Dual Catalytic Green System for Deprotection of Imines and in Situ Preparation of Bis(indolyl)alkanes from Indoles in Water\n\nPaper sections:\n1. Introduction\n<p>Using water as solvent in the organic reactions is one of the most important targets to organic chemists because of the easy availability, nontoxicity, and ecofriendly nature of the water [1–7]. In this endeavour, a number of chemical reactions such as Diels Alder, hetero Diels-Alder, 1,3-dipolar cycloaddition, oxidations, reductions, and others are performed successfully in water [1–3]. Also, it is reported that in few cases addition of the water increases the rate and the yield of a reaction and also enhances the enantioselectivity in a chiral synthesis [8]. But the main problems associated with water as a solvent is its poor ability to solubilise organic reactants and incapability to create anhydrous condition for moisture sensitive organic compounds and catalysts. To overcome the solubility problem, generally a surfactant is introduced to the reaction mixture. The surfactant, due to its hydrophobic and hydrophilic nature, forms micelles with water insoluble organic compounds and promote the desired reactions to occur inside the hydrophobic ambience of the micelle core [9, 10].</p><p>Cleavage of the C=N bonds is a very important transformation in organic synthesis as the C=N functionality is widely used to protect both the carbonyl and amines. There are a number of methods used for the cleavage of C=N bonds which include acidic reagents [11–13], oxidizing agents [14], metallic salts [15, 16], (PhSeO)2O [17], NaHSO3 [18], and others. Most of these methodologies suffer from serious drawbacks like involvement of strong Lewis and Bronsted acids, use of toxic and costly transition metals (i.e., Cr, Pd, Co), low temperature, longer reaction time, low yield, and difficulties in isolating the products. Therefore, development of efficient, mild and environment friendly reagents are always necessary. On the other hand, bisindoles are recently emerging as extremely important class of compounds because of their novel antibacterial and anticancer activities [19–21]. That is why a number of methodologies have also been postulated for the synthesis of bisindoles [22–29].</p><p>In our previous communications, we reported that surfactant- (SDS-) mediated cleavage of C=N bonds could be achieved with acetic anhydride [30] and surfactant-I2-water can be used for the deprotection of imines to carbonyls [31]. We have also shown that bis- and tris (indolyl)alkanes can be synthesized in presence of Bronsted acid in water [32]. In continuation of our research in hydrated media, herein, we wish to disclose the dual catalytic activity of the system I2-SDS-H2O which behaves as a Lewis acid [33] for the cleavage of 2,3-diaza-1,3-butadiene, 1-aza-1,3-butadienes, and oximes to produce carbonyls and amines, and the resulting reaction mixture reacts with indoles to produce bis (indolyl)alkanes in situ at room temperature under neutral conditions.</p>\n\n2. Results and Discussion\n<p>For an initial study, molecular iodine was added to a mixture of 1,4-diphenyl-2,3-diaza-1,3-butadiene (1a) (1 mmol) and indole (2a) (2 mmol) in water. It was presumed that the activated imine should produce carbonyl compound in the reaction mixture which might be trapped with indole. But only a trace amount of 3,3′-bis(indolyl)phenylmethane (3a) was found to be formed in the reaction. We envisioned that the poor yield of the product may be due to the insolubility of organic substrates in water. Accordingly, we added a surfactant (SDS) to the reaction flask. To our delight, the reaction produced isolable amount of 3a as a brown solid but half of the 1,4-diphenyl-2,3-diaza-1,3-butadiene (1a) left unreacted in the reaction mixture. So amount of indole (2a) was doubled (4 mmol) and the same reaction condition successfully produced quantitative amount of 3a. The product was filtered out and the filtrate was treated with freshly distilled benzaldehyde (0.05 mmol) in ethanol which furnished 1a (m.p. 91°C; lit [34] m.p. 92-93°C). This infers the simultaneous involvement of two C=N bonds of bis-anils, leaving behind hydrazine in the reaction mixture. Also, no self-reaction of individual starting materials leading to indole dimer [35] (4) or pyrrole formation [36] (5) were observed under the same reaction conditions (Scheme 1). Optimization of the reaction conditions was undertaken by employing different catalyst loadings under various surfactant conditions. The results are summarized in Table 1. It was found that the best result was obtained by the application of 15 mol% of I2 containing sodium dodecyl sulphate (SDS) and water at room temperature (entry 1, Table 1). In absence of the catalyst no formation of 3a was observed even after stirring for 24 hours (entry 5, Table 1).</p><p>To study the scope and limitations of the reaction, I2-SDS-H2O system was applied to the reaction of indole (2) and 2,3-diaza-1,3-butadiene derivatives (Table 2, entries a–f). The bisindoles were formed in excellent yields under the reaction condition. It was observed that the reaction was relatively faster when an electron withdrawing substituent, for example, NO2, was present in the phenyl ring of the 2,3-diaza-1,3-butadienes (Table 2, entry e) in comparison to the electron donating groups, for example, OMe and OH (Table 2, entries b and f). Identical results were obtained when 2-methylindole (2a) was used in place of indole (2) (Table 2, entries g and h). All the products were characterized by their IR, 1H NMR, 13C NMR, and mass spectral data and also by comparison with the literature report (Scheme 2) [24, 25].</p><p>In order to further explore the efficiency of the I2-SDS-H2O system the reaction of the oximes 6 and indoles 2 was studied. When oximes (1 mmol) and indole (2 mmol) were allowed to react under the same reaction condition described earlier, bis-indolylalkanes formed (Table 3). The product was filtered off and the filtrate was treated with benzaldehyde in ethanol. The resulted product was Benzaldoxime, which proved the liberation of hydroxylamine during the reaction. It was found that no Michael addition product [37] was formed and only a trace amount of indole dimer 5 [35] could be identified. The system was also applied to the reaction of 1-aza-1,3-butadienes 7 with indole (2) which produced bis (indolyl)alkanes 8 in very good yield eliminating aryl amine in the reaction mixture (Table 4). All the products were well characterized by comparison of their spectral and mass data with that of the reported value [24, 25].</p>\n\n3. Conclusions\n<p>In conclusion, we have shown the dual catalytic activity of I2-SDS-H2O system which deprotects the azadienes, oximes, and azabutadienes and produces bis (alkyl)indoles in situ when indole is present in the reaction medium. The two-step reaction can be carried out without using acid, transition metals, and organic solvents. Besides, the reaction condition is mild and can be done in water under neutral condition which contributes to the criteria of green chemistry.</p>\n\n4. Experimental\n<p>Melting points were measured using Buchi B-540 apparatus and are uncorrected. 1H NMR spectra were recorded on Avance DPX 300 MHz FT-NMR spectrometer. Chemical shifts are expressed in δ units relative to tetramethylsilane (TMS) signal as internal reference. IR spectra were recorded on FT-IR-system-2000 Perkin Elmer spectrometer on KBr pellets or in CHCl3. Mass spectra were recorded on ESQUIRE 3000 Mass Spectrometer. All reagents were obtained from commercial sources and used without further purification. The solvents for chromatography were distilled before use.</p>\n\n4.1. General Procedure for the Synthesis of 3,3′-Bis(indolyl)alkanes\n<p>In a 50 mL round bottom flask, 15 mol% of I2 was first dissolved in water (10 mL). 2,3-Diaza-1,3-butadiene (1 mmol) and indole (4 mmol) were added and stirred in the presence of sodium dodecyl sulphate (SDS) (0.02 g) for the stipulated time. The progress of the reaction was monitored by TLC. The product formed was filtered off and washed with water, dried, and recrystallized from ethanol.</p><p>Identical reaction condition was followed when 1-aza-1,3-butadienes and oximes were used as reactants. In this case, 2 mmol of indoles were used to react with 1 mmol of imines.</p>\n\n4.2. 3,3′-Bis(indolyl)phenylmethane (3a) [24]\n<p>Colorless solid; mp: 150–152°C; FTIR (KBr): ν 3418, 3058, 1623, 1611, 1445, 1093 cm−1; 1H NMR (300 MHz, CDCl3): δ 5.95 (s, 1H, Ar–CH), 6.73(s, 2H), 7.06 (t, 2H, J = 6.8 Hz), 7.18–7.27 (m, 3H), 7.31–7.36 (m, 2H), 7.36–7.42 (m, 6H), 7.98 (br, s, 2H, NH); 13C NMR (75 MHz, CDCl3): 40.7, 111.2, 119.1, 119.5, 120.4, 122.1, 123.8, 126.9, 126.9, 128.2, 129.1, 136.8, 144.8; HRMS calcd for C23H18N2 (M+): 322.2851, found 322.2832; Anal.calcd.: C, 85.70; H, 5.59; N, 8.69; found C, 85.75; H, 5.56; N, 8.56.</p>\n\n4.3. 3,3′-Bis(indolyl)-4-chlorophenylmethane (3d) [24]\n<p>Pink solid; mp: 76-77°C; FTIR (KBr): ν 3415, 3060, 1491, 1465, 1095 cm−1; 1H NMR (300 MHz, CDCl3): δ 5.91 (s, 1H, Ar–CH), 6.76 (s, 2H), 7.08 (t, 2H, J = 8.3 Hz), 7.22 (t, 2H, J = 7.9 Hz), 7.28–7.42 (m, 8H), 8.01 (br, s, 2H, NH); 13C NMR (75 MHz, CDCl3): 39.8, 111.5, 122.6, 123.8, 127.1,128.4, 129.8, 130.1, 130.9, 131.0, 131.6, 137.2, 143.5; HRMS calcd for C23H17N2Cl (M+): 356.7371; found 356.7324; Anal.calcd.: C, 77.52; H, 4.77; N, 7.86; found C, 77.48; H, 4.72; N, 7.80.</p>\n\n4.4. 3,3΄-Bis(indolyl)furylmethane (3j) [24]\n<p>Brown solid; mp: 323–325°C; FTIR (KBr): ν 3420, 1720, 1455, 1258 cm−1; 1H NMR (300 MHz, CDCl3): δ 5.98 (s, 1H, Ar-CH), 6.85 (s, 2H), 7.10–7.55 (m, 11H), 8.05 (br, s, 2H, NH), 13C NMR (75 MHz, CDCl3): 34.8, 107.0, 110.0, 111.5, 117.8, 119.9, 120.0, 122.5, 124.8, 127.1, 136.8, 142.2; HRMS calcd for C21H16N2O2 (M+): 312.2621; found 312.2611; Anal.calcd. C, 80.84; H, 5.12; N, 8.97; found C, 84.05; H, 5.15; N, 8.94.</p><p>All the products were fully characterized by 1H and 13C NMR and MS analyses. The spectral data of the compounds are available in the Supplementary Material available online at doi: 105402/2012/635835.</p>\n\n\n<p>The supplementary material contains all the characterization data (Melting point, IR, 1H NMR, 13C NMR, HRMS, and CHN analysis) of the compounds 3a-3g, 3j, and 8.</p><p>Click here for additional data file.</p>",
"role": "user"
},
{
"content": "A novel catalytic system consisting of I2-SDS-H2O has been developed which cleaves 2,3-diaza-1,3-butadiene, 1-aza-1,3-butadienes, oximes and in presence of indoles in the medium uses the corresponding aldehyde products to produce bis(indolyl)alkanes in situ. This one pot simple and mild dual catalytic system works in water at room temperature under neutral conditions.",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.11135
|
[
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: Using constellations to encode spatial and semantic information of objects in a scene.\n\nKeyphrases: place recognition images\n\nDataset descriptions:\nSUN3D: SUN3D contains a large-scale RGB-D video database, with 8 annotated sequences. Each frame has a semantic segmentation of the objects in the scene and information about the camera pose.\nFreiburg Spatial Relations: The Freiburg Spatial Relations dataset features 546 scenes each containing two out of 25 household objects. The depicted spatial relations can roughly be described as on top, on top on the corner, inside, inside and inclined, next to, and inclined.\nMLRSNet: MLRSNet is a a multi-label high spatial resolution remote sensing dataset for semantic scene understanding. It provides different perspectives of the world captured from satellites.\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.\n\nOptions: A: SUN3D B: Freiburg Spatial Relations C: MLRSNet D: COCO",
"role": "user"
},
{
"content": "COCO",
"role": "assistant"
}
] |
science.annotated_materials_syntheses_events
|
science.annotated_materials_syntheses_events.87
|
[
{
"content": "Extract all synthesis operations from this materials science abstract into JSON format. Your output should be a JSON array where each entry describes a synthesis operation with these fields:\n\n- \"trigger\": The action verb indicating a synthesis operation, quoted directly from the abstract\n- \"arguments\": An array of [<text>, <type>] pairs, where text is quoted from the abstract and type is one of: [\"Solvent_Material\", \"Recipe_Precursor\", \"Recipe_Target\", \"Participant_Material\", \"Atmospheric_Material\"]\n\nReturn only the JSON output.\n\nAbstract:\n10.1016/j.electacta.2016.11.160\nA simple method to synthesize V 2 O 5 nanostructures with controllable morphology for high performance Li-ion batteries\nV2O5 nanomaterials were synthesized using solid-state chemical reaction methods. All the reagents were analytically pure from commercial sources and used without further purification. Typical synthesis for V2O5 nanostructures was as follows. Solid ammonium metavanadate (NH4VO3, AR, >99%) and tartaric acid (C4H6O6, AR, >99%) with a molar ratio of 1:2, and polyethylene glycol 4000 (PEG-4000, AR, >99%) were apart weighed and ground in an agate mortar for about 5 min to ensure the evenness of starting materials, then mixed. Then the reactants were mixed, and the color of mixture changed from white to yellow. After grind for 30 min at room temperature, the color of mixture changed from yellow to grey. The obtained sample was washed with absolute ethanol, and then dried at 60 degC for 10 h. Finally pure grey precursor (NH4)2[(VO)(C4H4O6)2] was got. Then the precursor was placed in muffle furnace at different calcination temperature of 400 degC, 500 degC, 600 degC for 4 h (1 degC min-1) to obtain final products.",
"role": "user"
},
{
"content": "[{\"arguments\": [[\"V2O5\", \"Recipe_Target\"]], \"trigger\": \"synthesized\"}, {\"arguments\": [[\"reagents\", \"Participant_Material\"]], \"trigger\": \"used\"}, {\"arguments\": [[\"V2O5\", \"Recipe_Target\"]], \"trigger\": \"synthesis\"}, {\"arguments\": [[\"tartaric acid\", \"Recipe_Precursor\"], [\"ammonium metavanadate\", \"Recipe_Precursor\"], [\"polyethylene glycol 4000\", \"Recipe_Precursor\"]], \"trigger\": \"weighed\"}, {\"arguments\": [[\"reactants\", \"Participant_Material\"]], \"trigger\": \"mixed\"}, {\"arguments\": [[\"mixture\", \"Participant_Material\"]], \"trigger\": \"changed\"}, {\"arguments\": [[\"mixture\", \"Participant_Material\"]], \"trigger\": \"changed\"}, {\"arguments\": [[\"sample\", \"Participant_Material\"], [\"ethanol\", \"Solvent_Material\"]], \"trigger\": \"washed\"}, {\"arguments\": [[\"(NH4)2[(VO)(C4H4O6)2]\", \"Recipe_Precursor\"]], \"trigger\": \"got\"}, {\"arguments\": [[\"precursor\", \"Participant_Material\"]], \"trigger\": \"placed\"}, {\"arguments\": [[\"final products\", \"Participant_Material\"]], \"trigger\": \"obtain\"}]",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.75828
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Research Overview of Mobile Projected User Interfaces \nChapter Title: Environment-aware Handheld Projection Interfaces. \n1. Abstract of Cited Paper (BIB001): We evaluate an approach for mobile smart objects to cooperate with projector-camera systems to achieve interactive projected displays on their surfaces without changing their appearance or function. Smart objects describe their appearance directly to the projector-camera system, enabling vision-based detection based on their natural appearance. This detection is a significant challenge, as objects differ in appearance and appear at varying distances and orientations with respect to a tracking camera. We investigate four detection approaches representing different appearance cues and contribute three experimental studies analysing the impact on detection performance, firstly of scale and rotation, secondly the combination of multiple appearance cues and thirdly the use of context information from the smart object. We find that the training of appearance descriptions must coincide with the scale and orientations providing the best detection performance, that multiple cues provide a clear performance gain over a single cue and that context sensing masks distractions and clutter, further improving detection performance. \n2. Abstract of Cited Paper (BIB002): The Projected Interfaces architecture enables bi-directional user interaction with smart tangible objects. Smart objects function as both input and output devices simultaneously by cooperating with projector-camera systems to achieve a projected display on their surfaces. Tangible manipulation of the object and camera-based tracking allow interaction directly with the projected display. Such hybrid interfaces benefit both from the flexibility offered by the GUI and the intuitiveness of TUI. In this paper we present the theory behind how to consider interaction for projected interfaces with an architecture design and a proof of concept implementation using an augmented photograph album. \n3. Abstract of Cited Paper (BIB003): This paper presents two novel handheld projector systems for indoor pervasive computing spaces. These projection-based devices are \"aware\" of their environment in ways not demonstrated previously. They offer both spatial awareness, where the system infers location and orientation of the device in 3D space, and geometry awareness, where the system constructs the 3D structure of the world around it, which can encompass the user as well as other physical objects, such as furniture and walls. Previous work in this area has predominantly focused on infrastructure-based spatial-aware handheld projection and interaction. Our prototypes offer greater levels of environment awareness, but achieve this using two opposing approaches; the first infrastructure-based and the other infrastructure-less sensing. We highlight a series of interactions including direct touch, as well as in-air gestures, which leverage the shadow of the user for interaction. We describe the technical challenges in realizing these novel systems; and compare them directly by quantifying their location tracking and input sensing capabilities. \n4. Abstract of Cited Paper (BIB004): Sensors, processors, and radios can be integrated invisibly into objects to make them smart and sensitive to user interaction, but feedback is often limited to beeps, blinks, or buzzes. We propose to redress this input-output imbalance by augmentation of smart objects with projected displays, that—unlike physical displays—allow seamless integration with the natural appearance of an object. In this article, we investigate how, in a ubiquitous computing world, smart objects can acquire and control a projection. We consider that projectors and cameras are ubiquitous in the environment, and we develop a novel conception and system that enables smart objects to spontaneously associate with projector-camera systems for cooperative augmentation. Projector-camera systems are conceived as generic, supporting standard computer vision methods for different appearance cues, and smart objects provide a model of their appearance for method selection at runtime, as well as sensor observations to constrain the visual detection process. Cooperative detection results in accurate location and pose of the object, which is then tracked for visual augmentation in response to display requests by the smart object. In this article, we define the conceptual framework underlying our approach; report on computer vision experiments that give original insight into natural appearance-based detection of everyday objects; show how object sensing can be used to increase speed and robustness of visual detection; describe and evaluate a fully implemented system; and describe two smart object applications to illustrate the system's cooperative augmentation process and the embodied interactions it enables with smart objects.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Various interfaces focus on making handheld projections environment-aware: the projector reveals information depending on where the projector is situated in physical space and what parts of the environment, for example physical objects, are actually targeted by the projection ray. Early examples are projects by Raskar et al., iLamps and RFIG Lamps BIB001 . The overarching goal for both projects was to develop technology for projecting onto nonplanar surfaces and therefore augmenting arbitrary objects with additional information. The idea of environment-aware projection interfaces has been developed further by Molyneaux et al. BIB005 BIB002 BIB003 in so-called smart objects. They investigated how physical objects can be turned into interactive projected displays. The main focus of the work was on orchestrating a technical infrastructure, allowing for reliable and robust object detection through model-based approaches. More recently, Molyneaux et al. BIB004 have presented two camera-projector systems, which support direct touch and mid-air interaction. The systems leverage on an ad-hoc generated model of the physical space. The model is obtained by scanning the environment using depth-sensing cameras. The projected interfaces can then be precisely situated in physical space. In particular, the 3D shape can impact the behavior of projected imagery, for example a rolling ball projected onto a table would bounce off its edge. However, once the model has been obtained, objects must remain at a fixed location. A slightly different notion of environmentawareness is explored in PicoPet (see Fig. 4 ). The basic idea is that the user projects a virtual pet into the physical space using a handheld projector. Behavior and evolvement of the pet depend on where it is projected. Hence, colors, textures, objects, and the presence of other virtual pets in the physical environment impact one's own pet. These features are recognized using a camera that is mounted on top of the projector.",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_arxiv
|
science.scientific_papers_summarization_single_doc_arxiv.37827
|
[
{
"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:\nin a previous paper @xcite we analyzed the exclusive processes of charm pseudoscalar meson @xmath12 photoproduction , @xmath13 , @xmath14 , or @xmath11 .\nwe consider here the exclusive processes of charmed vector meson @xmath15 photoproduction , @xmath16 , on proton and neutron targets .\nno detailed theoretical analysis exists for such processes , and up to now , experimentally , only an indirect evaluation of their cross section has been done . in @xcite\nan attempt has been done to estimate the contribution of the processes @xmath17 to the asymmetry of the collisions of a circularly polarized photon beam with a polarized target in @xmath18 open charm @xmath19 .\nit is well known , that such asymmetry is sensitive to the @xmath20 gluon contribution to the nucleon spin @xcite . in @xcite\nthe d - exchange contribution has been calculated for @xmath21 , in the near threshold region , considering the possible baryon exchange as a background process .\nlet us list some arguments to justify the interest in exclusive charmed vector meson photoproduction : * their contribution to the total cross section is important , especially in the near - threshold region ; * the understanding of the reaction mechanisms require the deconvolution of these channels ; * these reactions naturally explain the particle - antiparticle asymmetry in charmed particles photoproduction , at high energies ; * the polarization phenomena induced by the production of vector meson are new , interesting and measurable ( the @xmath22-meson is a self analyzing particle , through the angular dependence of the decay products in @xmath23 , but this decay does not allow to access the vector @xmath22-meson polarization ) ; * direct experimental data , concerning these reactions , are expected soon , due to the higher luminosity of ongoing experiments , as compass @xcite .\nthere are essential differences beween the processes of exclusive photoproduction of light vector mesons ( @xmath24 , @xmath25 , @xmath26 or @xmath27 ) and heavy @xmath22-production . in the last case ,\nthe diffractive mechanism is absent and the large mass of the @xmath28-quark seems to justify the applicability of perturbative qcd .\nhowever there is no direct relation between the photon - gluon fusion subprocess , @xmath29 and the exclusive @xmath22-photoproduction .\ntherefore , qcd - inspired models , like the effective lagrangian approach ( ela ) , in terms of hadronic degrees of freedom , as charmed baryons and mesons , seem more appropriate .\nin such approach , it is possible to predict the differential cross section and all polarization observables in terms of a finite number of coupling constants , of strong and electromagnetic nature - in any kinematical condition .\nthe same coupling constants enter also in the calculation of other processes of associative charm production in @xmath30 , @xmath31 and @xmath32-collisons .\nthere are experimental data about inclusive @xmath22 photoproduction , @xmath33 or @xmath34 up to hera energies @xcite .\nthe smallest energy , where @xmath22-photoproduction has been observed is @xmath35 gev , at slac @xcite . typically , @xmath22-production is the main channel for @xmath36 charm @xmath19 @xcite , so that the ratio between the vector ( @xmath37 ) and the total @xmath22 contribution to the total cross section is in agreement with the spin quark rule @xmath38 , where @xmath39 is the pseudoscalar contribution .\nthe relative role of the charged and neutral @xmath40-meson photoproduction depends , on one side , on the relative cross sections for the @xmath41 and @xmath42 photoproduction , and , from another side , on the branching ratio for the decays @xmath43 ( for different charge combinations ) .\nwe consider here the exclusive processes @xmath16 , in case of collinear kinematics , where helicity conservation and the p - invariance of electromagnetic interaction allow three amplitudes , only , which are functions of a single kinematical variable , the photon energy @xmath4 .\nnote , in this respect , that generally the processes @xmath16 are characterized by a set of twelve independent amplitudes , which are complex functions of two kinematical variables .\ntherefore the theoretical analysis is largely simplified in collinear kinematics .\nthis paper is organized as follows . in section\nii the spin structure of the collinear matrix element is parametrized in terms of three amplitudes , which allows to develop a general and model independent formalism for the analysis of polarization phenomena .\nthe expressions for the different possible pole contributions , in framework of ela approach , are derived in section iii .\nthe strong and electromagnetic coupling constants as well as the form factors are discussed in section iv .\nnumerical predictions for the differential cross section , the single and double - spin polarization observables , as functions of @xmath4 , are given in section v. concluding remarks are given in section vi .\nthe appendix contains the explicit expressions of the collinear amplitudes .\nwe consider here the processes @xmath16 , @xmath14 , or @xmath11 , @xmath5=@xmath44 or @xmath45 , in collinear regime , i.e. for @xmath46 or @xmath47 , where @xmath48 is the @xmath45-production angle in the reaction cms .\nthe reasons of this choice are the following : * the differential cross section , @xmath49 , as a rule , is maximal in the forward direction ( @xmath50 is the momentum transfer squared ) ; * the total helicity of the interacting particles is conserved , for any reaction mechanisms , which implies that the spin structure of the matrix element and the polarization phenomena are highly simplified . taking into account the p - invariance of the electromagnetic interaction of charmed particles and the helicity conservation ,\none can write the following general parametrization of the matrix element for any process @xmath51 , in collinear kinematics ( which holds for any reaction mechanism ) : @xmath52\\chi_1 , \\label{eq : mat}\\ ] ] with the following notations : * @xmath53 and @xmath54 are the two - component spinors of the initial nucleon and the produced @xmath8-hyperon , * @xmath55 and @xmath56 are the three vector of the photon and of the @xmath5-meson polarizations , with the condition @xmath57 , * @xmath58 is the unit vector along the three - momentum of @xmath59 ; * @xmath60 , @xmath61=1 - 3 , are the collinear amplitudes , which are generally complex functions of a single variable , @xmath4 . using this parametrization\n, one can find for the differential cross section : @xmath62 , \\label{eq : cs1}\\ ] ] where @xmath63 is a normalization factor , @xmath64 @xmath65 is the energy ( mass ) of the produced vector meson : @xmath66 where @xmath67 @xmath68 is the nucleon ( @xmath8-hyperon ) mass , @xmath4 is the photon energy in the laboratory ( lab ) system .\nthe @xmath69-mesons , produced in collinear kinematics , are generally polarized , ( with tensor polarization ) even in collisions of unpolarized particles : @xmath70 with the normalization condition : @xmath71 .\nthe non - diagonal elements for @xmath72 are equal to zero , in collinear regime .\nall the other single - spin polarization observables , such as the @xmath73-asymmetry ( with linearly polarized photons interacting with unpolarized target ) , the analyzing power @xmath74 ( induced by polarized nucleon target ) and the final @xmath8-polarization ( in the collision of unpolarized particles ) , vanish for the considered reactions , for any photon energy and for any reaction mechanism , due to the axial symmetry of collinear kinematics .\nhowever an interesting set of double - spin polarization observables can be measured , for the reactions @xmath16 : * * the asymmetry @xmath7 * in the collision of circularly polarized photon beam , with a polarized nucleon target , in the @xmath58-direction , which we choose as the @xmath75-direction , @xmath76 due to the p - invariance of the electromagnetic interaction , the asymmetry for a linearly polarized photon beam vanish , even in collisions with polarized target . in the same way , the linear photon polarization can not induce any polarization of the emitted @xmath8-hyperon ( for simplicity , we will assume here 100% photon polarization , with helicity @xmath77 ) .\n* in the collision of circularly polarized photons with unpolarized target , the @xmath8-hyperon can be longitudinally polarized , and * the polarization @xmath9 * is : @xmath78 * the nonzero components of * the depolarization tensor , @xmath79 * , describing the dependence of the @xmath80-component of the @xmath8-polarization on the @xmath81-component of the target polarization can be written as : @xmath82 one can see that these observables are not independent , and the following relations hold , at any photon energy and for any reaction mechanism : @xmath83 these formulas show which experiments are necessary to determine the moduli of the collinear amplitudes , @xmath84 : latexmath:[\\ ] ] e. tomasi - gustafsson and m. p. rekalo , arxiv : hep - ph/0310172 .\ng. k. mallot , j. phys .\ng * 25 * , 1539 ( 1999 ) ; + m. ryskin and e. leader , j. phys .\ng * 25 * , 1541 ( 1999 ) .\nl. m. jones and h. w. wyld , phys .\nd * 17 * , 759 ( 1978 ) ; + f. halzen and d. m. scott , phys .\nb * 72 * , 404 ( 1978 ) ; + h. fritzsch and k. h. streng , phys .\nb * 72 * , 385 ( 1978 ) ; + v. a. novikov , m. a. shifman , a. i. vainstein and v. i. zakharov , nucl .\nb * 136 * , 125 ( 1978 ) [ yad .\n* 27 * , 771 ( 1978 ) ] ; + j. babcock , d. w. sivers and s. wolfram , phys .\nd * 18 * , 162 ( 1978 ) .\nm. p. rekalo and e. tomasi - gustafsson , phys .\nd * 65 * , 074023 ( 2002 ) and refs herein\n. g. baum _ et al .\n_ [ compass collaboration ] , cern - spslc-96 - 14 m. derrick _ et al . _\n[ zeus collaboration ] , phys .\nb * 349 * , 225 ( 1995 ) ; + s. aid _ et al . _\n[ h1 collaboration ] , nucl .\nb * 472 * , 32 ( 1996 ) .\nk. abe _ et al .\n_ [ slac hybrid facility photon collaboration ] , phys .\nd * 33 * , 1 ( 1986 ) .\nh. rubinstein and l. stodolsky , phys .\nb * 76 * , 479 ( 1978 ) .\nk. abe _ et al . _\n[ slac hybrid facility photon collaboration ] , phys .\nd * 30 * , 694 ( 1984 ) .\nk. hagiwara _\n_ , phys . rev . *\nd 66 * , 010001 ( 2002 ) .\nm. p. rekalo , ukr .\n22 , 1602 ( 1977 ) .\ns. k. bose and l. p. singh , phys .\nd * 22 * , 773 ( 1980 ) .\ns. n. jena and d. p. rath , phys .\nd * 34 * , 196 ( 1986 ) .\nm. j. savage , phys .\nb 326 , 303 ( 1994 ) . v. m. samsonov , nucl . instrum .\nb * 119 * , 271 ( 1996 ) .",
"role": "user"
},
{
"content": "the spin structure of the matrix element for the reactions @xmath0 , where @xmath1 , @xmath2 are charmed baryons with spin 1/2 , and @xmath3 is the vector charmed meson , can be parametrized , in collinear regime , in terms of three independent scalar amplitudes , which are functions of the photon energy @xmath4 , only . in framework of an effective lagrangian approach generalized to charm photoproduction \n , we calculate the energy dependence of the differential cross section , the density matrix element of @xmath5 , @xmath6 , the asymmetry @xmath7 in the collision of circularly polarized photons with polarized nucleons , and the polarization of the produced @xmath8-hyperon , @xmath9 , in the collision of circularly polarized photons with unpolarized target . \n all these polarization observables either vanish or are large , in absolute value , with a smooth @xmath4-dependence , and differ for @xmath10 and @xmath11 production .",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.6034
|
[
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: I want to train a hybrid representation for image recognition.\n\nKeyphrases: image recognition images\n\nDataset descriptions:\nPASCAL Context: The PASCAL Context dataset is an extension of the PASCAL VOC 2010 detection challenge, and it contains pixel-wise labels for all training images. It contains more than 400 classes (including the original 20 classes plus backgrounds from PASCAL VOC segmentation), divided into three categories (objects, stuff, and hybrids).\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.\nImageNet: The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection.\nConvAI2: The ConvAI2 NeurIPS competition aimed at finding approaches to creating high-quality dialogue agents capable of meaningful open domain conversation. The ConvAI2 dataset for training models is based on the PERSONA-CHAT dataset.\n\nOptions: A: PASCAL Context B: SNIPS C: ImageNet D: ConvAI2",
"role": "user"
},
{
"content": "ImageNet",
"role": "assistant"
}
] |
science.scicite_classification
|
science.scicite_classification.219
|
[
{
"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: COQN-term anti-COQ7(1-37)specific antibodies were derived using the same protocol but starting with antiCOQ7 (Santa Cruz, sc-135040).",
"role": "user"
},
{
"content": "Method",
"role": "assistant"
}
] |
science.chia_ner
|
science.chia_ner.1091
|
[
{
"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\nHIV controlled on therapy for at least 12 weeks\nViral load < 200 copies\nBMI >27 to 45\nDiagnosis of DM type 2 with A1-C >7 to 15\nParticipants must be willing to comply with all study related procedures",
"role": "user"
},
{
"content": "{\"Condition\": [\"HIV\", \"DM type 2\"], \"Device\": [], \"Drug\": [], \"Measurement\": [\"A1-C\", \"Viral load\"], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [\"BMI\"], \"Procedure\": [], \"Qualifier\": [\"controlled\"], \"ReferencePoint\": [], \"Scope\": [], \"Temporal\": [\"at least 12 weeks\"], \"Value\": [\"\\u003c 200 copies\", \"\\u003e27 to 45\", \"\\u003e7 to 15\"], \"Visit\": []}",
"role": "assistant"
}
] |
science.chemsum_single_document_summarization
|
science.chemsum_single_document_summarization.16100
|
[
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nAmide-Directed Catalytic Asymmetric Hydroboration of Trisubstituted Alkenes\n\nPaper sections:\n\n<p>Rhodium-catalyzed hydroboration1 often exhibits interesting chemo-, regio- and diastereoselectivity, at times nicely complementing that obtained via the non-catalyzed reaction. Chiral organoboranes are useful intermediates for a variety of subsequent transformations.2 Some efficient chiral catalysts have been developed for the catalytic asymmetric reaction, but they are largely limited to vinyl arene substrates.3,4 Furthermore, catalyzed hydroboration of trisubstituted alkenes is usually slow or suffers from competing rhodium-catalyzed alkene isomerization.5,6 Thus, the utility of catalytic asymmetric hydroboration is significantly compromised by the present lack of substrate scope.</p><p>Building on the Evans5c,d and Gevorgyan7 reports of carbonyl-directed hydroboration, we found that the amide-directed asymmetric hydroborations of (E)- and (Z)-disubstituted β,γ-unsaturated amides proceed with high regio- and enantioselectivity using (BINOL)PN(Me)Ph in conjunction with Rh(nbd)2BF4.8 However, this catalyst proves somewhat less applicable to similar trisubstituted alkene substrates, for example, (E)- and (Z)-1. Although the level of enantioselectivity obtained is good (89–90% ee), the reaction is slow and the yield rather modest (Table 1, entry 1). The results obtained using (TADDOL)POPh (3a) are more encouraging (entry 2).9</p><p>Seebach showed that adding substituents to the four phenyl groups appended to the TADDOL core (e.g., structures 3a–d) subtly changes the topography defined by this versatile chiral scaffold.10 Screening a series of such ligands reveals that the tert-butyl-substituted derivative 3c affords both a good yield of product and high levels of enantioselectivity of the (E)- and (Z)-isomers of substrate 1 (Table 1, entry 4, 96–98% ee).11,12 Substituting [Rh(cod)Cl]2 as the source of the rhodium catalyst leads to markedly lower reactivity and poor asymmetric induction (entry 7). A trisubstituted alkene lacking the amide directing group, (E)-4, reacts only sluggishly under these conditions (<20% conversion) highlighting the role of the carbonyl directing group and apparent two-point binding of the unsaturated amide substrate to the catalyst.</p><p>Trisubstituted alkenes bearing non-identical alkenyl substituents generate two new stereocenters upon hydroboration, and therefore, syn/anti-diastereoselectivity is also a relevant concern. The rhodium-catalyzed asymmetric hydroboration of (E)-1 using ligand 3c affords the anti-diastereomer of 2 in good yield (79%) after oxidative workup (Figure 1). The level of diastereoselectivity is high; we see none of the corresponding syn-diastereomer which is easily recognized by 1H NMR analysis. The level of enantioselectivity is also excellent; anti-diastereomer (3R,4S)-2 is obtained in 98% ee as determined by chiral HPLC analysis. Using the same chiral ligand (i.e., 3c), (Z)-1 affords the syn-diastereomer (3R,4R)-2, again with high diastereo- and enantioselectivity (80% yield, 96% ee).13</p><p>While the reactions of (E)- and (Z)-1 are quite efficient, it was initially disappointing to find that other trisubstituted substrates gave slightly lower levels of enantioselectivity under similar conditions. Monitoring the course of the reaction of (E)-5 proved insightful. The blue data points in Figure 2 show the yield (squares) and enantiomeric excess (circles) of anti-6 as formed over time. In the initial stages of the reaction, the anti-6 produced is near racemic; only 10–15% ee in the first hour. However, the enantiomeric purity increases dramatically over time, and upon complete consumption of starting materials, anti-6 is obtained in good, but obviously not optimal, enantiopurity (80% yield, 92% ee). The improvement in enantioselectivity over time suggests that a transient rhodium complex is an active but poorly stereoselective catalyst at the early stages of the reaction. Once replaced by the more highly selective catalyst, the reaction proceeds with high levels of asymmetric induction.14</p><p>Switching from Rh(nbd)2BF4 to Rh(cod)2BF4 or increasing the time for complexation with the chiral ligand (in this case, 3b) did not significantly improve the results. Several \"sacrificial\" alkene addends were screened based on the premise that a more reactive alkene might be preferentially consumed by the non-selective catalyst leaving the β,γ-unsaturated amide to react with the later formed selective catalyst. The red data points in Figure 2 show the yield for the formation of anti-6 (squares) and its enantiomeric excess (circles) for the reaction run in the presence of norbornene, a more reactive alkene under the conditions employed. In its presence (10 mole percent with respect to (E)-5), anti-6 is formed in similar yield, but somewhat higher enantiopurity (80%, 95% ee), than the reaction lacking norbornene.15</p><p>While more work is needed to understand the role of the addend, these modified reaction conditions prove useful for a number of substrates (Table 2). For example, both (E)-5 and its stereoisomer (Z)-5 (entries 1–2) undergo hydroboration/oxidation with a high degree of stereocontrol to afford anti-6 and syn-6 respectively, each in 95% ee. It is interesting to note that, while the end results are essentially identical, these stereoisomeric substrates each require a different ligand for optimal results.16 Additionally, (Z)-5 requires a higher catalyst load, 2% versus 1%, to effect complete conversion within 24 h. Other (E)-substrates also give the anti-product with good enantioselectivity (entries 3–4, 93 and 96% ee, respectively). Other (Z)-substrates, including ones bearing somewhat more sterically encumbering branched substituents, afford the syn-product in good yield and high enantioselectivity (entries 5–7, 80–82% yield, 91–95% ee).</p><p>In summary, the rhodium-catalyzed hydroborations of trisubstituted alkenes are generally slow or suffer competing isomerization. In contrast, the trisubstituted alkene moieties contained within the framework of a β,γ-unsaturated amide undergo facile reaction, perhaps facilitated by carbonyl directing effects and two-point binding of the substrate to the rhodium catalyst. The reactions of stereoisomer substrates, for example, (E)- and (Z)-3, cleanly give rise to diastereomeric anti- and syn-products, thus the rhodium-catalyzed reaction is stereospecific. In addition, simple TADDOL-derived phenyl monophosphite ligands in combination with Rh(nbd)2BF4 afford highly enantioselective catalysts. These catalysts provide an alternative methodology to prepare Felkin or anti-Felkin acetate-aldol products and related derivatives that are obtainable from the intermediate organoboranes. Further studies are in progress.</p><p>Selective formation of either Felkin or anti-Felkin acetate-aldol products via stereospecific rhodium-catalyzed asymmetric hydroboration.</p><p>Comparing the yield of anti-6 (indicated by squares) and its enantiomeric excess (indicated by circles) over time with (red data) and without (blue data) added norbornene.</p><p>Catalyzed hydroborations of (E)- and (Z)-1 as a function of ligand 3a–d.a</p><p>Unless otherwise specified, the reaction was run as follows: 1.0% Rh(nbd)2BF4, 2.1% of the indicated ligand, 2.0 PinBH, 40 °C, 12–24 h.</p><p>Uses 1.0% Rh(cod)2BF4.</p><p>Uses 0.5% [Rh(cod)Cl]2.</p><p>Other trisubstituted alkene substrates undergo efficient catalytic asymmetric hydroboration.a</p><p>Unless otherwise specified the reaction conditions are as shown above the table.</p><p>Carried out using 2% Rh(nbd)2BF4, 4.1% ligand 3, and 10% norbornene.</p><p>Carried out in the absence of norbornene using 0.5% Rh(nbd)2BF4, 1.1% 3c, 40 °C.</p>",
"role": "user"
},
{
"content": "Rhodium-catalyzed hydroborations of trisubstituted alkenes are generally slow and often suffer from competing alkene isomerization. In contrast, the trisubstituted alkene moieties contained within the framework of a \\xce\\xb2,\\xce\\xb3-unsaturated amide undergo facile reaction, perhaps facilitated by carbonyl directing effects and two-point binding of the substrate to the rhodium catalyst. Stereoisomeric substrates, for example, (E)- and (Z)-3, cleanly give rise to diastereomeric products and thus the rhodium-catalyzed reaction is stereospecific. In addition, simple TADDOL-derived phenyl monophosphite ligands in combination with Rh(nbd)2BF4 afford highly enantioselective catalysts (seven examples, 91\\xe2\\x80\\x9398% ee). These catalysts provide an alternative methodology to prepare Felkin or anti-Felkin acetate-aldol products and related derivatives that are obtainable from the intermediate chiral organoboranes.",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.2361
|
[
{
"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:\nDo sheltered workshops enhance employment outcomes for adults with autism spectrum disorder ? This study investigated whether sheltered workshops help prepare individuals with autism spectrum disorder ( ASD ) for competitive employment within the community . Two groups of individuals were compared : ( a ) 215 supported employees who were in sheltered workshops prior to entering supported employment and ( b ) 215 supported employees who were not in sheltered workshops . Individuals from both groups were matched based on their primary diagnosis , secondary diagnosis ( if present ) , and gender . Results showed that there were no differences in rates of employment between these two groups . However , individuals who participated in sheltered workshops earned significantly less ( US $ 129.36 versus US $ 191.42 per week ) , and cost significantly more to serve ( US $ 6,065.08 versus US $ 2,440.60 ) , than their non-sheltered workshop peers . Results presented here suggest that individuals with ASD achieve better vocational outcomes if they do not participate in sheltered workshops prior to enrolling in supported employment .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"not in sheltered workshops\", \"sheltered workshops\", \"non-sheltered workshop\"], \"Outcome\": [\"employment outcomes\", \"earned significantly less\", \"competitive employment\", \"better vocational outcomes\", \"cost significantly more\", \"rates of employment\"], \"Participant\": [\"( a ) 215 supported employees who were in sheltered workshops prior to entering supported employment and ( b ) 215 supported employees who were not in sheltered workshops .\", \"adults with autism spectrum disorder\"]}",
"role": "assistant"
}
] |
science.craftchem_ner
|
science.craftchem_ner.727
|
[
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: InparticularthehorizontalcanalreceivesaratherdenseafferentandefferentinnervationinBrn3cnullmutants.",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
] |
science.covidfact_entailment
|
science.covidfact_entailment.277
|
[
{
"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: Reappearance of effector t cells cannots successful recovery from covid-19\n\nText:\nBACKGROUND: Elucidating the role of T cell responses in COVID-19 is of utmost importance to understand the clearance of SARS-CoV-2 infection.\nMETHODS: 30 hospitalized COVID-19 patients and 60 age-and gender-matched healthy controls (HC) participated in this study.\nWe used two comprehensive 11-colour flow cytometric panels conforming to Good Laboratory Practice and approved for clinical diagnostics.\nFINDINGS: Absolute numbers of lymphocyte subsets were differentially decreased in COVID-19 patients according to clinical severity.\nIn severe disease (SD) patients, all lymphocyte subsets were reduced, whilst in mild disease (MD) NK, NKT and γδ T cells were at the level of HC.\nAdditionally, we provide evidence of T cell activation in MD but not SD, when compared to HC.\nFollow up samples revealed a marked increase in effector T cells and memory subsets in convalescing but not in non-convalescing patients.\nINTERPRETATION: Our data suggest that activation and expansion of innate and adaptive lymphocytes play a major role in COVID-19.\nAdditionally, recovery is associated with formation of T cell memory as suggested by the missing formation of effector and central memory T cells in SD but not in MD.\nUnderstanding T cell-responses in the context of clinical severity might serve as foundation to overcome the lack of effective anti-viral immune response in severely affected COVID-19 patients and can offer prognostic value as biomarker for disease outcome and control.\nFUNDING: Funded by State of Lower Saxony grant 14-76,103-184CORONA-11/20 and German Research Foundation, Excellence Strategy-EXC2155\"RESIST\"-Project ID39087428, and DFG-SFB900/3-Project ID158989968, grants SFB900-B3, SFB900-B8.",
"role": "user"
},
{
"content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"Follow up samples revealed a marked increase in effector T cells and memory subsets in convalescing but not in non-convalescing patients.\", \"Understanding T cell-responses in the context of clinical severity might serve as foundation to overcome the lack of effective anti-viral immune response in severely affected COVID-19 patients and can offer prognostic value as biomarker for disease outcome and control.\"]}",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.11258
|
[
{
"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\nThe COVID-19 pandemic has seen a proposal for frailty to be used as a rationing criterion. This commentary suggests circumstances under which that is defensible: in the face of lack of capacity to treat everyone, and as an alternative to age in stratifying risk. How best to stratify risk is likely to evolve and may include information about illness severity and dynamic measures. Current research must focus on mobilizing better, COVID-19-specific prognostic information, with a goal of best discriminating which lives are most and least likely to be saved should scarcity of resources dictate that not everyone can receive critical care.",
"role": "user"
},
{
"content": "[\"Treatment\", \"Prevention\"]",
"role": "assistant"
}
] |
science.medmentions_ner
|
science.medmentions_ner.622
|
[
{
"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: Diagnosing a rare case of desmoplastic small round cell tumour on liver biopsy A 50- year -old male of Indian descent presented with jaundice and right hypochondrium pain. Following a computed tomography (CT) scan of the abdomen, a segment 7 liver lesion was visualized, accompanied by extensive peritoneal tumour deposits. An ultrasound guided liver biopsy was performed and histology showed loose nests and sheets of tumour cells with a small blue round cell morphology. The tumour cells showed patchy strong immunopositivity for cytokeratins (AE1/3, CK7, CK19) and synaptophysin, while showing diffuse strong perinuclear positivity for desmin. Interphase fluorescence in-situ hybridization (FISH) study using EWSR1 breakapart probe was positive for EWSR1 gene rearrangement. Desmoplastic small round cell tumour is a rare but aggressive intra-abdominal mesenchymal tumour. While the primary sites of involvement are usually the peritoneum and omentum, visceral involvement can occur. We wish to highlight the importance of considering this entity when evaluating a liver biopsy especially in a less than classical clinical context.",
"role": "user"
},
{
"content": "{\"AnatomicalStructure\": [\"tumour cells\", \"peritoneum\", \"EWSR1\", \"omentum\"], \"Bacterium\": [], \"BiologicFunction\": [\"gene rearrangement\", \"tumour\", \"desmoplastic small round cell tumour\", \"Desmoplastic small round cell tumour\", \"mesenchymal tumour\"], \"BiomedicalOccupationOrDiscipline\": [\"histology\"], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"desmin\", \"CK19\", \"EWSR1 breakapart probe\", \"AE1/3\", \"CK7\", \"cytokeratins\", \"synaptophysin\"], \"ClinicalAttribute\": [\"small blue round cell morphology\"], \"Eukaryote\": [], \"Finding\": [\"perinuclear positivity\", \"segment 7 liver lesion\", \"positive\", \"immunopositivity\", \"right hypochondrium pain\", \"jaundice\"], \"Food\": [], \"HealthCareActivity\": [\"liver biopsy\", \"computed tomography (CT) scan\", \"ultrasound guided liver biopsy\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [\"Indian descent\"], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"study\", \"FISH\", \"Diagnosing\", \"Interphase fluorescence in-situ hybridization\"], \"SpatialConcept\": [\"abdomen\", \"peritoneal\", \"primary sites\", \"intra-abdominal\", \"sheets\", \"visceral\"], \"Virus\": []}",
"role": "assistant"
}
] |
science.healthver_entailment
|
science.healthver_entailment.780
|
[
{
"content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Can a vaccine from 1921 save lives from Covid-19? No Absolutely not\n\nAbstract:\nBACKGROUND The Coronavirus Disease-19 (COVID-19) is the new form of an acute infectious respiratory disease and has quickly spread over most continents in the world.\nRecently, it has been shown that Bacille Calmette-Guerin (BCG) might protect against COVID-19.\nThis study aims to investigate the possible correlation between BCG vaccination and morbidity/mortality/recovery rate associated with COVID-19 infection.\nMETHODS Data of COVID-19 confirmed cases, deaths, recoveries, and population were obtained from https://www.worldometers.info/coronavirus/ (Accessed on 12 June, 2020).\nTo have meaningful comparisons among countries' mortality and recovery rates, we only choose those countries with COVID-19 infected cases at least 200.\nThe Poisson regression and logistic regression were used to explore the relationship between BCG vaccination and morbidity, mortality and recovery rates.\nRESULTS Among those 158 countries with at least 200 COVID-19 infected cases, there were 141 countries with BCG vaccination information available.\nThe adjusted rates ratio of COVID-19 confirmed cases for Current BCG vaccination vs. non-Current BCG vaccination was 0.339 (with 95% CI= (0.338,0.340)).\nMoreover, the adjusted odds ratio (OR) of death and recovery after coronavirus infected for Current BCG vaccination vs. non-Current BCG vaccination were 0.258 (with 95% CI= (0.254,0.261)) and 2.151 (with 95% CI= (2.140,2.163)), respectively.\nCONCLUSIONS That data in this study show the BCG might provide the protection against COVID-19, with consequent less COVID-19 infection and deaths and more rapid recovery.\nBCG vaccine might bridge the gap before the disease-specific vaccine is developed, but this hypothesis needs to be further tested in rigorous randomized clinical trials.",
"role": "user"
},
{
"content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"Recently, it has been shown that Bacille Calmette-Guerin (BCG) might protect against COVID-19.\", \"The adjusted rates ratio of COVID-19 confirmed cases for Current BCG vaccination vs. non-Current BCG vaccination was 0.339 (with 95% CI= (0.338,0.340)).\", \"Moreover, the adjusted odds ratio (OR) of death and recovery after coronavirus infected for Current BCG vaccination vs. non-Current BCG vaccination were 0.258 (with 95% CI= (0.254,0.261)) and 2.151 (with 95% CI= (2.140,2.163)), respectively.\", \"CONCLUSIONS That data in this study show the BCG might provide the protection against COVID-19, with consequent less COVID-19 infection and deaths and more rapid recovery.\"]}",
"role": "assistant"
}
] |
science.ddi_ner
|
science.ddi_ner.666
|
[
{
"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:\nTheophylline: In three pharmacokinetic studies including 46 normal, healthy subjects, theophylline clearance and concentration were not significantly altered by the addition of lomefloxacin. In clinical studies where patients were on chronic theophylline therapy, lomefloxacin had no measurable effect on the mean distribution of theophylline concentrations or the mean estimates of theophylline clearance. Though individual theophylline levels fluctuated, there were no clinically significant symptoms of drug inter-action. Antacids and sucralfate: Sucralfate and antacids containing magnesium or aluminum, as well as formulations containing divalent and trivalent cations such as Videx (didanosine), chewable/buffered tablets or the pediatric powder for oral solution can form chelation complexes with lomefloxacin and interfere with its bioavailability. Sucralfate administered 2 hours before lomefloxacin resulted in a slower absorption (mean C max decreased by 30% and mean T max increased by 1 hour) and a lesser extent of absorption (mean AUC decreased by approximately 25%). Magnesium- and aluminum-containing antacids, administered concomitantly with lomefloxacin, significantly decreased the bioavailability (48%) of lomefloxacin. Separating the doses of antacid and lomefloxacin minimizes this decrease in bioavailability; therefore, administration of these agents should precede lomefloxacin dosing by 4 hours or follow lomefloxacin dosing by at least 2 hours. Caffeine: Two hundred mg of caffeine (equivalent to 1 to 3 cups of American coffee) was administered to 16 normal, healthy volunteers who had achieved steady-state blood concentrations of lomefloxacin after being dosed at 400 mg qd. This did not result in any statistically or clinically relevant changes in the pharmacokinetic parameters of either caffeine or its major metabolite, paraxanthine. No data are available on potential interactions in individuals who consume greater than 200 mg of caffeine per day or in those, such as the geriatric population, who are generally believed to be more susceptible to the development of drug-induced CNS-related adverse effects. Other quinolones have demonstrated moderate to marked interference with the metabolism of caffeine, resulting in a reduced clearance, a prolongation of plasma half-life, and an increase in symptoms that accompany high levels of caffeine. Cimetidine: Cimetidine has been demonstrated to interfere with the elimination of other quinolones. This interference has resulted in significant increases in half-life and AUC. The interaction between lomefloxacin and cimetidine has not been studied. Cyclosporine: Elevated serum levels of cyclosporine have been reported with concomitant use of cyclosporine with other members of the quinolone class. Interaction between lomefloxacin and cyclosporine has not been studied. Omeprazole: No clinically significant changes in lomefloxacin pharmacokinetics (AUC, C max , or T max ) were observed when a single dose of lomefloxacin 400 mg was given after multiple doses of omeprazole (20 mg qd) in 13 healthy volunteers. Changes in omeprazole pharmacokinetics were not studied. Phenytoin: No significant differences were observed in mean phenytoin AUC, C max , C min or T max (although C max increased by 11%) when extended phenytoin sodium capsules (100 mg tid) were coadministered with lomefloxacin (400 mg qd) for five days in 15 healthy males. Lomefloxacin is unlikely to have a significant effect on phenytoin metabolism. Probenecid: Probenecid slows the renal elimination of lome-floxacin. An increase of 63% in the mean AUC and increases of 50% and 4%, respectively, in the mean T max and mean C max were noted in 1 study of 6 individuals. Terfenadine: No clinically significant changes occurred in heart rate or corrected QT intervals, or in terfenadine metabolite or lomefloxacin pharmacokinetics, during concurrent administration of lomefloxacin and terfenadine at steady-state in 28 healthy males. Warfarin: Quinolones may enhance the effects of the oral anticoagulant, warfarin, or its derivatives. When these products are administered concomitantly, prothrombin or other suitable coagulation tests should be monitored closely. However, no clinically or statistically significant differences in prothrombin time ratio or warfarin enantiomer pharmacokinetics were observed in a small study of 7 healthy males who received both warfarin and lomefloxacin under steady-state conditions.",
"role": "user"
},
{
"content": "{\"Brand\": [\"Videx\"], \"Drug\": [\"Terfenadine\", \"theophylline\", \"phenytoin\", \"omeprazole\", \"Phenytoin\", \"cyclosporine\", \"Warfarin\", \"sucralfate\", \"Lomefloxacin\", \"terfenadine\", \"Caffeine\", \"warfarin\", \"Omeprazole\", \"Cyclosporine\", \"Theophylline\", \"Probenecid\", \"lomefloxacin\", \"caffeine\", \"Cimetidine\", \"didanosine\", \"magnesium\", \"Magnesium\", \"cimetidine\", \"Sucralfate\", \"aluminum\", \"phenytoin sodium\"], \"DrugGroup\": [\"antacids\", \"Antacids\", \"anticoagulant\", \"antacid\", \"quinolone class\", \"quinolones\", \"Quinolones\"], \"UnapprovedDrug\": [\"paraxanthine\"]}",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_pubmed
|
science.scientific_papers_summarization_single_doc_pubmed.39461
|
[
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\nas most spinal cord injuries ( scis ) are incomplete , an important target for promoting neural repair and recovery of lost motor function is to augment and strengthen the connections of spared descending spinal pathways with spinal motor circuits . among the pathways , the corticospinal tract ( cst )\ncst loss , whether at its origin in the motor cortex or in the white matter tracts subcortically and in the spinal cord , leads to movement impairments and paralysis . to restore motor function after injury will , by necessity , require repair of the damaged cst .\nknowledge of the mechanisms of establishment of cst spinal connections during development and cst plasticity induced by partial injury in maturity has informed repair strategies that we have examined ( carmel and martin , 2014 ) .\nwe have shown that development of cst spinal connections depends on the activity of the corticospinal motor system ( martin et al . , 2009 ) .\nactivation of the system during development leads to cst outgrowth , and inactivation promotes withdrawal of its axons and the spinal connections they make .\nimportantly , harnessing activity can repair the injured developing corticospinal system and restore motor functions .\ncst plasticity after sci in maturity may contribute to partial recovery of function ( weidner et al . , 2001 ) , but this recovery is limited . with serious injury ,\nthere are too few spared cst axons to enable effective transmission of control signals ; they must be made stronger . in this review , focus is on cst repair after injury by enabling activity - dependent processes that lead both to axonal outgrowth and to establishment of new connections .\nhuman and cat cst grow into the spinal cord before and near term , respectively , whereas rodent cst develops postnatally .\nirrespective of the time of the start of development , important refinement occurs at the last stages , when connectional specificity is established . in the different species ,\nnormal cst development is characterized by concurrent axonal outgrowth and axon elimination ( i.e. , pruning ) .\na variety of manipulations reveal the importance of activity - dependent synaptic competition in establishment of cst connections during development .\nunilateral motor cortex ( mcx ) inactivation during an early critical period in cats blocks development of a dense and strong contralateral cst ( friel and martin , 2007 ) .\nconcurrently , the active mcx / cst not only develops a dense contralateral cst but also an ipsilateral cst ( friel and martin , 2007 ) .\nthe ipsilateral cst is not a misprojection , as seen in several genetic models of cst miswiring .\nrather , it represents maintenance and further outgrowth of an early ipsilateral cst projection that normally is eliminated early in development .\nthese data suggest that it is not activity per se that is steering cst development , but rather activity - dependent competition .\nelectrical stimulation of mcx maintains ipsilateral cst projections , at least into feline adolescent development ( salimi and martin , 2004 ) , and , interestingly , impedes somewhat development of the contralateral cst projection from the non - stimulated side .\nagain , this is consistent with activity - dependent competition , playing a key role .\nour developmental findings provide a framework for using activity in maturity to promote cst repair and restoration of function after injury ( carmel and martin , 2014 ) .\nspared axons are too sparse and too weak to contribute to restoration of serious impairments . a way to promote spared cst axon outgrowth is to stimulate the axons , to drive up their activity and their capacity to compete for spinal connections .\nin extending our developmental findings to maturity , we used the unilateral pyramidal tract lesion ( ptx ) model ( brus - ramer et al . , 2007 ) .\nthe denervated side of the spinal cord receives sparse ipsilateral cst projections from the intact mcx .\nfor example , if the pyramidal tract on the right side ( red ) is lesioned , then the spinal cord on the left would only receive sparse ipsilateral cst axons from the blue pathway . whereas it is well known\nthat spared ipsilateral axons can sprout in response to ptx , there is no recovery of the skilled locomotion task we study ( horizontal ladder walking ) .\n( a ) schematic of cst organization ; ( b ) sparse spared axons after contusion injury ; ( c ) axonal outgrowth after stimulation ; and ( d ) schematic relationship between spared cst axons in the white matter and cst axon length / connections in the gray matter .\nour studies showed that injury alone produces injury - dependent sprouting of ipsilateral cst axons into the denervated side of the spinal cord , which is neither significant over uninjured controls nor does it lead to significant improvement in the horizontal ladder walking task ( brus - ramer et al .\nimportantly , by stimulating the injured cst ( 6 hours of motor cortex epidural stimulation ; each day for 10 days ) , either directly after injury or beginning 8 weeks later , resulted in significant ventral ipsilateral cst outgrowth and significant improvement in the ladder walking task ( carmel et al . , 2010 , 2014 ) .\nwe have observed that cst outgrowth appears to be several times greater 6 weeks compared with 2 weeks after injury , and motor recovery parallels this time - course of cst outgrowth .\nreversible inactivation of the stimulated hemisphere abolished the recovery produced by stimulation through reinstating the impairment ( carmel et al . , 2014 ) .\nit is important to consider that simulation - induced cst activation can be implemented in animals that have limited behavioral capacity and thus may be useful in humans with serious motor impairment .\nptx is an important model for establishing the presence of cst axonal sprouting and has been essential for our demonstration of the importance of activity - dependent competition and simulation efficacy .\nbut because it is a brain lesion , it is not known if stimulation can provoke outgrowth below a spinal lesion , where there is massive wallerian degeneration and associated tissue reaction that could create an unfavorable environment for activity - dependent outgrowth .\nwe extended our ptx studies to cervical contusion sci , where it has been shown that a moderate injury spares a small number of cst axons bilaterally ( anderson et al . , 2009 ) .\nwith the loss of most cst axons due to the bilateral contusion injury in a rat model ( gray ; loss of most of the dorsal cst bilaterally ) , there are only sparse projections from axons located in the lateral and ventral columns ( figure 1b ) . in translating our stimulation approach , we were initially concerned that the cst sprouting induced by motor cortex stimulation might not be sufficiently robust caudal to a serious sci to promote function .\nfirst , we used intermittent theta burst stimulation ( itbs ) , which is a stimulation protocol that induces strong short - term physiological plasticity ( huang et al . , 2005 ) .\nsecond , we stimulated bilaterally since we wished to repair the damaged cst on each side .\nthird , we augmented spinal activity using trans - spinal direct current stimulation ( tsdcs ) ( song et al . , 2016 ) .\nin intact animals , we conducted a series of studies demonstrating that combined itbs and tsdcs produced larger muscle evoked potentials and disproportionately strong correlations between motor cortex local field potential activity and contralateral forelimb emg than either stimulation alone .\nrecently , we used this combined approach and showed motor recovery and cst outgrowth after ptx , equivalent to our earlier study , but with only 30 minutes of stimulation each day ( song et al . , 2016 ) .\nusing a fourth segment cervical ( c4 ) contusion model , we compared an injury - only group of rats ( n = 13 ) after with animals that received stimulation beginning 1 week after injury ( n = 14 ) .\nas in our recent ptx study ( song et al . , 2016 ) using combined mcx stimulation and tsdcs , we stimulated for 27 minutes each day for 10 days .\nwe used several behavioral assays , but described only the forepaw manipulation task here , the irvine , beattie , and bresnahan test ( irvine et al . , 2014 ) .\nthe cst was traced 6 weeks post - injury , after the behavioral assays were completed .\nour current findings show that the injured + stimulated animals had significantly increased manipulation scores at 6 weeks post - injury compared with the injury - only group .\ninterestingly , between 4 and 6 weeks post - contusion , the injury - only group did not show a significant improvement ( paired t - test ) , whereas the stimulated group did . for the stimulated group , improvement of distal motor skills in this contusion injury\ncompared with the injured - only group , the injured + stimulated group showed an expanded spinal region at c6 where the cst gray matter axons are located and local cst axon density was greater ( shown schematically in figure 1c ) . to quantify cst outgrowth further , we examined the relationship between the number of spared cst axons in the white matter and axon length and presynaptic connections ( assayed as axon varicosities ) within the gray matter .\nwe expected that there would be a longer cst gray matter axon length and more connections for larger numbers of cst axon spared in the white matter , whether or not an animal received treatment ( figure 1d shows this relationship schematically ) . in support of this idea , data analyzed thus far revealed that the slope of the linear regression was shallow in the injury - only group .\nby contrast , the slope of the linear regression line in the stimulated group was greater than that of the injured - only group .\nour initial studies are very encouraging , showing that our stimulation approach , based on the ptx lesion model , can be optimized for the more complex and physically damaging spinal injury .\nfor example , the improvement after sci was observed with only a brief daily therapy session ( 27 minutes ) and for a brief treatment period ( 10 days ) ; longer periods of daily stimulation or a longer treatment period may improve efficacy .\nwe have developed a novel treatment approach for cst repair and motor recovery after cervical sci in rats .\nthis is because stimulation produces cst structural plasticity , axon sprouting and formation of more connections with spinal motor circuits .\nthe theoretical basis for this approach derives from our studies in development , where activity - dependent processes initially help establish strong contralateral cst connections .\nit is well - recognized that activity - dependent processes can be augmented through intensive behavioral approaches .\nhowever , motor functions are limited after serious injuries , reducing the efficacy of behavioral therapies . instead , to augment the activity of the corticospinal system we leverage brain stimulation and neuromodulation approaches that do not depend on the behavioral capabilities of the injured person .",
"role": "user"
},
{
"content": "as most spinal cord injuries ( scis ) are incomplete , an important target for promoting neural repair and recovery of lost motor function is to promote the connections of spared descending spinal pathways with spinal motor circuits . among the pathways , the corticospinal tract ( cst ) \n is most associated with skilled voluntary functions in humans and many animals . \n cst loss , whether at its origin in the motor cortex or in the white matter tracts subcortically and in the spinal cord , leads to movement impairments and paralysis . to restore motor function after injury will require repair of the damaged cst . in this review , \n i discuss how knowledge of activity - dependent development of the cst which establishes connectional specificity through axon pruning , axon outgrowth , and synaptic competition among cst terminals informed a novel activity - based therapy for promoting sprouting of spared cst axons after injur in mature animals . \n this therapy , which comprises motor cortex electrical stimulation with and without concurrent trans - spinal direct current stimulation , leads to an increase in the gray matter axon length of spared cst axons in the rat spinal cord and , after a pyramidal tract lesion , restoration of skilled locomotor movements . \n i discuss how this approach is now being applied to a c4 contusion rat model .",
"role": "assistant"
}
] |
science.mslr2022_ms2_multidoc_summarization
|
science.mslr2022_ms2_multidoc_summarization.9217
|
[
{
"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:\nThe Risk of Acute Radiocontrast-Mediated Kidney Injury Following Endovascular Therapy for Acute Ischemic Stroke Is Low\nAbstract 1:\nBACKGROUND AND PURPOSE : Endovascular therapy is an alternative for the treatment of AIS result ing from large intracranial arterial occlusions that depends on the use of iodinated RCM . The risk of RCM-mediated AKI following endovascular therapy for AIS may be different from that following coronary interventions because patients may not have identical risk factors . MATERIAL S AND METHODS : All consecutive patients with large-vessel AIS undergoing endovascular therapy were prospect ively recorded . We recorded the baseline kidney function , and RCM-AKI was assessed according to the AKIN criteria at 48 hours after RCM administration . We compared the rate of RCM-AKI 48 hours after the procedure and sought to determine whether any preexisting factors increased the risk of RCM-AKI . RESULTS : We identified 99 patients meeting inclusion criteria . The average volume of contrast was 189 ± 71 mL , and the average creatinine change was −4.6 % at 48 hours postangiography . There were 3 patients with RCM-AKI . Although all 3 patients died as a result of their strokes , return to baseline creatinine levels occurred before death . There was a trend toward higher rates of premorbid diabetes mellitus , chronic renal insufficiency , preadmission statin and NSAID use , and a higher serum creatinine level on admission for the RCM-AKI group . The volume of procedural contrast was similar between groups ( those with and those without RCM-AKI ) ( P = .5 ) . CONCLUSIONS : In this small study , the rate of RCM-AKI following endovascular intervention for AIS was very low . A much larger study is required to determine its true incidence\n\n\nTitle 2:\n2015 American Heart Association/American Stroke Association Focused Update of the 2013 Guidelines for the Early Management of Patients With Acute Ischemic Stroke Regarding Endovascular Treatment: A Guideline for Healthcare Professionals From the American Heart Association/American Stroke Association\nAbstract 2:\nPurpose — The aim of this guideline is to provide a focused up date of the current recommendations for the endovascular treatment of acute ischemic stroke . When there is overlap , the recommendations made here supersede those of previous guidelines . Methods — This focused up date analyzes results from 8 r and omized , clinical trials of endovascular treatment and other relevant data published since 2013 . It is not intended to be a complete literature review from the date of the previous guideline publication but rather to include pivotal new evidence that justifies changes in current recommendations . Members of the writing committee were appointed by the American Heart Association/American Stroke Association Stroke Council ’s Scientific Statement Oversight Committee and the American Heart Association/American Stroke Association Manuscript Oversight Committee . Strict adherence to the American Heart Association conflict of interest policy was maintained throughout the consensus process . Recommendations follow the American Heart Association/American Stroke Association methods of classifying the level of certainty of the treatment effect and the class of evidence . Prerelease review of the draft guideline was performed by 6 expert peer review ers and by the members of the Stroke Council Scientific Statement Oversight Committee and Stroke Council Leadership Committee . Results — Evidence -based guidelines are presented for the selection of patients with acute ischemic stroke for endovascular treatment , for the endovascular procedure , and for systems of care to facilitate endovascular treatment . Conclusions — Certain endovascular procedures have been demonstrated to provide clinical benefit in selected patients with acute ischemic stroke . Systems of care should be organized to facilitate the delivery of this care\n\n\nTitle 3:\nReducing the delay in thrombolysis: is it necessary to await the results of renal function tests before computed tomography perfusion and angiography in patients with code stroke?\nAbstract 3:\nOBJECTIVE We sought to determine the percentage of patients presenting with code stroke who would be excluded from computed tomography angiography , computed tomography perfusion , or both based on their emergency department laboratory results ( creatinine and glomerular filtration rate ) and the incidence of contrast-induced nephropathy in patients with code stroke who receive contrast . DESIGN We conducted a retrospective analysis of our prospect i ve code stroke data base . SETTING The study took place in an emergency department at a university medical center . RESULTS A total of 131 consecutive patients with code stroke were identified . Of these , 11 ( 8.4 % ) would not have received contrast based on a creatinine level greater than 1.5 mg/dL on initial evaluation . However , 10 of these 11 patients ( 91 % ) had a history of renal disease . A total of 3 % of patients who received contrast developed contrast-induced nephropathy . CONCLUSIONS Our findings suggest that the use of contrast agents in patients with code stroke before availability of renal function tests appears safe in patients who do not have a known history of renal disease\n\n\nTitle 4:\nNo Increased Risk for Contrast-Induced Nephropathy after Multiple CT Perfusion Studies of the Brain with a Nonionic, Dimeric, Iso-Osmolal Contrast Medium\nAbstract 4:\nBACKGROUND AND PURPOSE : Contrast-induced nephropathy ( CIN ) is one of the most common causes of in-hospital acute renal failure . The aim of this study was to assess the risk for CIN after repeated administration of the nonionic , dimeric , iso-osmolal contrast agent iodixanol regardless of pre-existing renal function . Changes in serum creatinine ( SCr ) levels were compared with those of control subjects who did not receive iodinated contrast media ( CM ) . MATERIAL S AND METHODS : Between January 2005 and March 2007 , a total of 100 consecutive patients were prospect ively included . Patients underwent a CT perfusion ( CTP ) study of the brain from clinical signs of acute cerebral infa rct ion . CTP was performed with an intravenous bolus of 60 mL of iodixanol-270 . Precontrast and postcontrast SCr levels were obtained , and the CTP study was repeated within 32 hours and postcontrast SCR was assessed . The control group consisted of 100 patients scheduled for plain cranial CT examination , who were not exposed to iodinated CM . RESULTS : Mean baseline SCr level was 0.96 ± 0.35 mg/dL in the contrast group and 1.14 ± 0.74 mg/dL in the control group . After repeated administration of CM , a total of 7 patients had a relative increase of greater than or equal to 25 % compared with baseline . In the control group , a relative increase of 25 % or more was seen in 12 patients . The difference in the incidence of the rise in SCr of > 25 % was not significantly different ( P = .094 ) . CONCLUSION : Multiple contrast-enhanced studies with intravenously administered iodixanol are not associated with a higher risk for CIN compared with a control group receiving no CM\n\n\nTitle 5:\nFunctional Contrast-Enhanced CT for Evaluation of Acute Ischemic Stroke Does Not Increase the Risk of Contrast-Induced Nephropathy\nAbstract 5:\nBACKGROUND AND PURPOSE : Concerns have recently grown regarding the safety of iodinated contrast agents used for CTA and CTP imaging . We tested whether the incidence of AN , defined by a ≥25 % increase in the post−contrast scan creatinine level , was higher among patients with ischemic stroke who underwent a functional contrast-enhanced CT protocol compared with those who had no iodinated contrast administration . MATERIAL S AND METHODS : The contrast-exposed group consisted of 575 patients with acute ischemic stroke who underwent CTA ( n = 313 ) , CTA/CTP ( n = 224 ) , or CTA/CTP followed by conventional angiography ( n = 38 ) within 24 hours of stroke onset and were consecutively enrolled in a prospect i ve cohort study . The nonexposed group consisted of 343 patients with ischemic stroke , consecutively admitted to the same institution , who did not receive iodinated contrast material . Patients were stratified by baseline eGFR . In the primary analysis , the Fisher exact test was used to compare the incidence of AN between the contrast-exposed and the nonexposed patients at 24 , 48 , and 72 hours and on a cumulative basis . A secondary analysis compared the incidence of AN in patients who underwent conventional angiography following CTA/CTP versus patients who underwent CTA/CTP only . RESULTS : The incidence of AN was 5 % in the exposed and 10 % in the nonexposed group ( P = .003 ) . Patients who underwent conventional angiography after contrast CT were at no greater risk of AN than patients who underwent CTA/CTP alone ( 26 patients , 5 % ; and 2 patients , 5 % , respectively ; P = .7 ) . CONCLUSIONS : Administration of a contrast-enhanced CT protocol involving CTA/CTP and conventional angiography in selected patients does not appear to increase the incidence of CIN\n\n\nTitle 6:\nRenal Safety of CT Angiography and Perfusion Imaging in the Emergency Evaluation of Acute Stroke\nAbstract 6:\nBACKGROUND AND PURPOSE : Multimodal CT imaging with contrast-enhanced CT angiography ( CTA ) and CT perfusion ( CTP ) is increasingly being used to guide emergency management of acute stroke . However , little has been reported about the safety of intravenous contrast administration associated with these studies in the acute stroke population , including cases in which baseline creatinine values are unknown . We investigated the incidence of contrast-induced nephropathy ( CIN ) , defined as a 25 % or more increase in baseline creatinine levels within 72 hours of contrast administration and chronic kidney disease in patients receiving CTA±CTP at our regional stroke center . MATERIAL S AND METHODS : We analyzed 198 patients who underwent contrast CT studies for evaluation of acute ischemic or hemorrhagic stroke at our center ( 2003–2007 ) . Through retrospective chart abstract ion , we analyzed serial creatinine levels ( baseline to day 3 ) and later values ( ≥day 4 ) where available . The incidences of CIN and /or chronic kidney disease were documented . After power analysis , CIN and non-CIN groups were compared by using the unpaired t test , Wilcoxon rank sum test , or Fisher exact test . RESULTS : None of the 198 patients developed chronic kidney disease or required dialysis . Of 175 patients with serial creatinine measurements between baseline and day 3 , 5 ( 2.9 % ) developed CIN . The incidence of CIN was 2 % in patients who were scanned before a baseline creatinine level was available . CONCLUSION : The incidence of renal sequelae is relatively low in acute stroke patients undergoing emergent multimodal CT scanning . Prompt CTA/CTP imaging of acute stroke , if indicated , need not be delayed in those with no history of renal impairment",
"role": "user"
},
{
"content": "Conclusions — Nonr and omized evidence suggests that CTA/CTP are not associated with statistically significant increase in risk of AKI in patients with stroke , even those with known chronic kidney disease",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.16703
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nMotivated by emerging vision-based intelligent services, we consider the problem of rate adaptation for high quality and low delay visual information delivery over wireless networks using scalable video coding. Rate adaptation in this setting is inherently challenging due to the interplay between the variability of the wireless channels, the queuing at the network nodes and the frame-based decoding and playback of the video content at the receiver at very short time scales. To address the problem, we propose a low-complexity, model-based rate adaptation algorithm for scalable video streaming systems, building on a novel performance model based on stochastic network calculus. We validate the model using extensive simulations. We show that it allows fast, near optimal rate adaptation for fixed transmission paths, as well as cross-layer optimized routing and video rate adaptation in mesh networks, with less than @math quality degradation compared to the best achievable performance.\n\nCited Abstract(s):\n[1]: \n\n[2]: \n\n[3]: The MIMO wireless channel offers a rich ground for quality of service analysis. In this work, we present a stochastic network calculus analysis of a MIMO system, operating in spatial multiplexing mode, using moment generating functions (MGF). We quantify the spatial multiplexing gain, achieved through multiple antennas, for flow level quality of service (QoS) performance. Specifically we use Gilbert-Elliot model to describe individual spatial paths between the antenna pairs and model the whole channel by an @math -State Markov Chain, where @math depends upon the degrees of freedom available in the MIMO system. We derive probabilistic delay bounds for the system and show the impact of increasing the number of antennas on the delay bounds under various conditions, such as channel burstiness, signal strength and fading speed. Further we present results for multi-hop scenarios under statistical independence.\n\n[4]: The class of Gupta-Kumar results, which predict the throughput capacity in wireless networks, is restricted to asymptotic regimes. This tutorial presents a methodology to address a corresponding non-asymptotic analysis based on the framework of the stochastic network calculus, in a rigorous mathematical manner. In particular, we derive explicit closed-form results on the distribution of the end-to-end capacity and delay, for a fixed source-destination pair, in a network with broad assumptions on its topology and degree of spatial correlations. The results are non-asymptotic in that they hold for finite time scales and network sizes, as well as bursty arrivals. The generality of the results enables the research of several interesting problems, concerning for instance the effects of time scales or randomness in topology on the network capacity.\n\n[5]: Network calculus is an established theory for deterministic quality of service analysis of fixed networks. Due to the failures inherent in fading channels it is, however, not applicable to radio systems. Emerging probabilistic equivalents allow closing this gap. Based on the recent network calculus with moment generating functions we present a methodology for performance analysis of fading channels. We use a service curve representation of radio links which facilitates an efficient analysis of radio networks. We investigate fading channels with memory and our results show that the fading speed impacts service guarantees significantly. Numerical performance bounds are provided for an example taken from cellular radio communications for which the effects of opportunistic scheduling are quantified. Simulation results are shown which confirm the efficiency of the approach.\n\n[6]: Network calculus is a min-plus system theory for performance evaluation of queuing networks. Its elegance steins from intuitive convolution formulas for concatenation of deterministic servers. Recent research dispenses with the worst-case assumptions of network calculus to develop a probabilistic equivalent that benefits from statistical multiplexing. Significant achievements have been made, owing for example to the theory of effective bandwidths; however, the outstanding scalability set up by concatenation of deterministic servers has not been shown. This paper establishes a concise, probabilistic network calculus with moment generating functions. The presented work features closed-form, end-to-end, probabilistic performance bounds that achieve the objective of scaling linearly in the number of servers in series. The consistent application of moment generating functions put forth in this paper utilizes independence beyond the scope of current statistical multiplexing of flows. A relevant additional gain is demonstrated for tandem servers with independent cross-traffic\n\n[7]: In this paper, we develop a method for analyzing time-varying wireless channels in the context of the modern theory of the stochastic network calculus. In particular, our technique is applicable to channels that can be modeled as Markov chains, which is the case of channels subject to Rayleigh fading. Our approach relies on theoretical results on the convergence time of reversible Markov processes and is applicable to chains with an arbitrary number of states. We provide two expressions for the delay tail distribution of traffic transmitted over a fading channel fed by a Markov source. The first expression is tighter and only requires a simple numerical minimization, the second expression is looser, but is in closed form.",
"role": "user"
},
{
"content": "Stochastic network calculus has been extended to capture the randomly varying channel capacity of wireless links, following different methods [4] [5] [3] [7] [2] [3]0 . Most of the existing work builds on an abstracted finite-state Markov channel (FSMC) model of the underlying fading channel, e.g., [5] [3] or uses moment generating function based network calculus [3]0 . However, the complexity of the resulting models limits the applicability of these approaches in multi--hop wireless network analysis with more than a few state FSMC model and more than two hops. In this work, we follow the approach proposed by Al- [1] , where a wireless network calculus based on the dioid algebra was developed. The main premise for this approach is that the channel capacity, and hence the offered service of fading channels is related to the instantaneous received SNR through the logarithmic function as expressed by the Shannon capacity, @math . Hence, an equivalent representation of the channel capacity in an isomorphic transform domain, obtained using the exponential function, would be @math . This simplifies the otherwise cumbersome computations of the end-to-end performance metrics.",
"role": "assistant"
}
] |
science.data_reco_mcq_mc
|
science.data_reco_mcq_mc.352
|
[
{
"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: I want to use a supervised model for pedestrian attribute recognition from images.\n\nKeywords: pedestrian attribute recognition images\n\nDataset descriptions:\nPETA: The PEdesTrian Attribute dataset (PETA) is a dataset fore recognizing pedestrian attributes, such as gender and clothing style, at a far distance. It is of interest in video surveillance scenarios where face and body close-shots and hardly available.\nVisDrone: VisDrone is a large-scale benchmark with carefully annotated ground-truth for various important computer vision tasks, to make vision meet drones. The VisDrone2019 dataset is collected by the AISKYEYE team at Lab of Machine Learning and Data Mining, Tianjin University, China.\nJAAD: JAAD is a dataset for studying joint attention in the context of autonomous driving. The focus is on pedestrian and driver behaviors at the point of crossing and factors that influence them.\nCompCars: The Comprehensive Cars (CompCars) dataset contains data from two scenarios, including images from web-nature and surveillance-nature. The web-nature data contains 163 car makes with 1,716 car models.\nTITAN: TITAN consists of 700 labeled video-clips (with odometry) captured from a moving vehicle on highly interactive urban traffic scenes in Tokyo. The dataset includes 50 labels including vehicle states and actions, pedestrian age groups, and targeted pedestrian action attributes that are organized hierarchically corresponding to atomic, simple/complex-contextual, transportive, and communicative actions.\nRAP: The Richly Annotated Pedestrian (RAP) dataset is a dataset for pedestrian attribute recognition. It contains 41,585 images collected from indoor surveillance cameras.\nPA-100K: PA-100K is a recent-proposed large pedestrian attribute dataset, with 100,000 images in total collected from outdoor surveillance cameras. It is split into 80,000 images for the training set, and 10,000 for the validation set and 10,000 for the test set.\n\nOptions: A: PETA B: VisDrone C: JAAD D: CompCars E: TITAN F: RAP G: PA-100K",
"role": "user"
},
{
"content": "[\"PETA\", \"RAP\"]",
"role": "assistant"
}
] |
science.acl_arc_intent_classification
|
science.acl_arc_intent_classification.1354
|
[
{
"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:\nintroduction\n\nContext before:\nPeople are much more likely to consult such evaluative statements than the actual text of a bill or law under discussion, given the dense nature of legislative language and the fact that (U.S.) bills often reach several hundred pages in length (Smith et al., 2005). Evaluative and persuasive documents, such as a politicianâs speech regarding a bill or a bloggerâs commentary on a legislative proposal, form a particularly interesting type of politically oriented text. Regardless of whether one views such claims as clear-sighted prophecy or mere hype, it is obviously important to help people understand and analyze politically oriented text, given the importance of enabling informed participation in the political process.\n\nCitation:\nPeople are much more likely to consult such evaluative statements than the actual text of a bill or law under discussion , given the dense nature of legislative language and the fact that ( U.S. ) bills often reach several hundred pages in length ( Smith et al. , 2005 ) .\n\nContext after:\nMoreover, political opinions are exsional bills and related data was launched in January 1995, when Mosaic was not quite two years old and Altavista did not yet exist. \u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000 plicitly solicited in the eRulemaking scenario. In the analysis of evaluative language, it is fundamentally necessary to determine whether the author/speaker supports or disapproves of the topic of discussion. In this paper, we investigate the following specific instantiation of this problem: we seek to determine from the transcripts of U.S. Congressional floor debates whether each âspeechâ (continuous single-speaker segment of text) represents support for or opposition to a proposed piece of legislation.",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.18953
|
[
{
"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\nBACKGROUND: Characteristics of critically ill adults with coronavirus disease 2019 (COVID-19) in an academic safety net hospital and the effect of evidence-based practices in these patients are unknown. RESEARCH QUESTION: What are the outcomes of critically ill adults with COVID-19 admitted to a network of hospitals in New Orleans, Louisiana, and what is an evidence-based protocol for care associated with improved outcomes? STUDY DESIGN AND METHODS: In this multi-center, retrospective, observational cohort study of ICUs in four hospitals in New Orleans, Louisiana, we collected data on adults admitted to an ICU and tested for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) between March 9, 2020 and April 14, 2020. The exposure of interest was admission to an ICU that implemented an evidence-based protocol for COVID-19 care. The primary outcome was ventilator-free days. RESULTS: The initial 147 patients admitted to any ICU and tested positive for SARS-CoV-2 constituted the cohort for this study. In the entire network, exposure to an evidence-based protocol was associated with more ventilator-free days (25 days; 0-28) compared with non-protocolized ICUs (0 days; 0-23, P = .005), including in adjusted analyses (P = .02). Twenty patients (37%) admitted to protocolized ICUs died compared with 51 (56%; P = .02) in non-protocolized ICUs. Among 82 patients admitted to the academic safety net hospital's ICUs, the median number of ventilator-free days was 22 (interquartile range, 0-27) and mortality rate was 39%. INTERPRETATION: Care of critically ill COVID-19 patients with an evidence-based protocol is associated with increased time alive and free of invasive mechanical ventilation. In-hospital survival occurred in most critically ill adults with COVID-19 admitted to an academic safety net hospital's ICUs despite a high rate of comorbidities.",
"role": "user"
},
{
"content": "[\"Treatment\", \"Diagnosis\"]",
"role": "assistant"
}
] |
science.scicite_classification
|
science.scicite_classification.3412
|
[
{
"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: Although the lack of true branch lengths may increase Type I error of independent contrast correlations, equal branch lengths are associated with a lower Type I error than other topological approaches when information regarding true branch lengths does not exist (Ackerly 2000).",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
] |
science.acl_arc_intent_classification
|
science.acl_arc_intent_classification.831
|
[
{
"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:\nrelated work\n\nContext before:\nA common computational treatment of lexical rules adopted, for example, in the ALE system (Carpenter and Penn 1994) consists of computing the transitive closure of the base lexical entries under lexical rule application at compile-time.\n\nCitation:\nA common computational treatment of lexical rules adopted , for example , in the ALE system ( Carpenter and Penn 1994 ) consists of computing the transitive closure of the base lexical entries under lexical rule application at compile-time .\n\nContext after:\nWhile this provides a front-end to include lexical rules in the grammars, it has the disadvantage that the generalizations captured by lexical rules are not used for computation. We mentioned in Section 2.2 that eliminating lexical rules in a precompilation step makes it impossible to process lexical rules or lexical entries that impose constraints that can only be properly executed once information from syntactic processing is available. A related problem is that for analyses resulting in infinite lexica, the number of lexical rule applications needs to be limited. In the ALE system, for example, a depth bound can be specified for this purpose.",
"role": "user"
},
{
"content": "CompareOrContrast",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_plos_single_doc_summ
|
science.scientific_lay_summarisation_plos_single_doc_summ.5105
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: The Development of Audio-Visual Integration for Temporal Judgements\nArticle:\nAbstract:\nAdults combine information from different sensory modalities to estimate object properties such as size or location. This process is optimal in that( i) sensory information is weighted according to relative reliability: more reliable estimates have more influence on the combined estimate and( ii) the combined estimate is more reliable than the component uni-modal estimates. Previous studies suggest that optimal sensory integration does not emerge until around 10 years of age. Younger children rely on a single modality or combine information using inappropriate sensory weights. Children aged 4–11 and adults completed a simple audio-visual task in which they reported either the number of beeps or the number of flashes in uni-modal and bi-modal conditions. In bi-modal trials, beeps and flashes differed in number by 0, 1 or 2. Mutual interactions between the sensory signals were evident at all ages: the reported number of flashes was influenced by the number of simultaneously presented beeps and vice versa. Furthermore, for all ages, the relative strength of these interactions was predicted by the relative reliabilities of the two modalities, in other words, all observers weighted the signals appropriately. The degree of cross-modal interaction decreased with age: the youngest observers could not ignore the task-irrelevant modality—they fully combined vision and audition such that they perceived equal numbers of flashes and beeps for bi-modal stimuli. Older observers showed much smaller effects of the task-irrelevant modality. Do these interactions reflect optimal integration? Full or partial cross-modal integration predicts improved reliability in bi-modal conditions. In contrast, switching between modalities reduces reliability. Model comparison suggests that older observers employed partial integration, whereas younger observers( up to around 8 years) did not integrate, but followed a sub-optimal switching strategy, responding according to either visual or auditory information on each trial.\nIntroduction:\nImagine you are at an academic conference. A heated debate turns nasty and one scientist is repeatedly hit before falling to the floor. You are later asked how many punches were thrown. You confidently answer ‘3’; you were able to combine information from audition and vision, having both seen and heard the incident. We often receive information about the same object or event from multiple sensory modalities that we can integrate to improve the precision of our perceptual estimates. As adults, we integrate multisensory information for a variety of spatial and temporal tasks, such as judging the size, location, number or duration of objects or events[1–5]. A key benefit of this integration is that uncertainty, or variance( random noise) in the combined, multisensory estimate is reduced, relative to either of the component uni-sensory estimates, see e. g.[6]. Under standard models of integration, sensory estimates are combined via weighted averaging, according to the estimates’ relative reliabilities, see e. g.[1, 2, 6]. For example, consider the case in which an aspect of the environment is estimated from vision and audition. The visual and auditory estimates, S^V and S^A are not perfectly precise, but contain noise with variance σV2 and σA2. It is commonly assumed that these noise distributions are Gaussian and independent. Under these assumptions, and given that the prior probability distribution over the estimated variable is uniform, then the optimal audio-visual estimate( i. e. that with the lowest possible variance), for a continuous variable is given by: S^VA=wVS^V+wAS^A with the visual and auditory weights, wV and wA defined as: wV=1/σV21/σV2+1/σA2 and wA=1/σA21/σV2+1/σA2. As can be seen from the equations above, sensory weights give the relative influence of each uni-modal sensory estimate in determining responses to bi-modal stimuli. These weights can be estimated from behavioural data corresponding to bi-modal and uni-modal stimulus conditions. For example, in a size estimation task such as[1], subjects might be required to estimate an object’s size from vision alone, from haptics( touch) alone, or from both vision and hatpics. If the visual size is 9cm and the haptic size is 12cm, then given unbiased uni-modal estimates, a mean bi-modal response of 10cm would correspond to visual and haptic weights of 2/3 and 1/3, respectively, i. e. vision has double the influence of haptics. These observed weights would be optimal if the uni-modal visual estimates were twice as reliable as the uni-modal haptic estimates, i. e. σV2/σH2=0. 5. Observing optimal sensory weights is consistent with optimal integration, i. e. the integration behaviour that minimises variance in the multimodal estimates. However, optimal sensory weights might be observed in the absence of integration: as an alternative to integration, an observer may select one of the uni-modal estimates on each trial, rather than computing a weighted average[7, 8]. In the example above, the observer may select the visual estimate on 2/3 of trials, and the haptic estimate on 1/3 of trials. This ‘switching’ behaviour would produce the same mean response in bi-modal conditions as optimal integration, but with higher variance. Standard models predict that variance will be reduced in bi-modal, relative to uni-modal conditions under optimal integration, see, e. g.[1, 2, 6, 9]. For example in the visual-haptic size example, under optimal integration the predicted variance of the visual-haptic estimates, σVH2, is given by σVH2=σV2σH2σV2+σH2. In contrast, switching behaviour will result in variance that is at least as large as the more reliable cue. For this reason, studies of multimodal integration generally determine( i) whether the sensory weights are optimal, given uni-sensory variability, and( ii) whether variability in the bi-modal estimates is reduced, relative to uni-modal estimates. Recently, a number of studies have asked whether children show optimal integration of sensory cues, as indexed by( i) appropriate cue weighting and( ii) a reduction in variance, relative to single cue conditions. Gori and Burr[10] reported that optimal integration of multisensory information doesn’t appear until surprisingly late—at the age of around 10 years. In two visual-haptic tasks, younger children who were asked to judge object size or orientation relied on only one modality, and not necessarily the most reliable one. Other work has confirmed that children as old as 8 years fail to optimally integrate visual cues with movement-based information( proprioceptive and vestibular) for navigation[7], and another study suggests that optimal integration of auditory and haptic information does not occur until after age 11[11]. Interestingly, this developmentally late integration is not limited to situations in which information must be combined from different sensory modalities: Nardini and colleagues reported similarly late integration for cues within a modality—optimal integration of two visual depth cues did not emerge until around age 12[12]. The current study focuses on the developmental trajectory of audio-visual integration, using a straightforward counting task. The age at which optimal integration emerges for vision and audition is not yet clear. One previous audio-visual study with children aged 5–14 years and adults failed to find optimal integration at any age[13]. We employed a simple audio-visual task in which, on each trial, observers were presented with a number of beeps and / or flashes[14]. In separate blocks, they either reported the number of flashes, or the number of beeps. The task had the benefit of reduced memory and decisional demands, relative to previous studies that have used two-alternative forced choice designs. By comparing observers’ responses to different integration models we ask:\nDiscussion:\nA simple task was used to investigate the developmental trajectory of audio-visual integration. Importantly, we evaluated three different models of integration that together provide a good account of sensory integration behaviour at all stages of development. Key findings emerged: Sensory integration has the potential to provide benefits for virtually all of our everyday activities—precision is improved by combining redundant information sources either within or across modalities. An obvious question remains unanswered—why does this ability fail to appear until around 10 years? One proposed explanation is that the lack of integration is beneficial during early childhood, and facilitates recalibration[10, 12]. During this period of growth and sensory development, constant sensory recalibration is required in order to maintain accurate( unbiased) perceptual estimates. Recalibration requires the estimation of inter-sensory conflict—if this were only possible in the absence of integration, i. e. by keeping sensory estimates separate, then the developing sensory system might forego integration in favour of recalibration. The importance of cross-sensory interaction for sensory calibration and development is supported by studies in populations with sensory impairments—congenital visual deficits appear to have a detrimental effect on the precision of haptic estimates and vice versa[25, 26]. Studies with adult observers, however, suggest that integration and recalibration are not mutually exclusive. For example, when glasses distort the relationship between binocular disparity and depth, the perceptual system recalibrates accordingly, whilst continuing to integrate binocular disparity with other depth cues[27]. Moreover, the sensory system adapts relatively quickly( within hours) when sensory statistics change[17, 28–30]. In fact, recalibration and integration both rely on establishing the correspondence between signals—identifying which signals are redundant and only integrating( or recalibrating) when they arise from the same source. It might be that younger children find this correspondence hard to learn[31]. In the current study, observers were told to ignore one modality—adults were able to do this to a large extent, whereas children were sub-optimal in the sense that cross-modal influences were larger, even though vision and audition were discrepant on the majority of trials. A previous study also found that the effect of auditory beeps on the reported number of flashes was larger in children than adults[32]. However, that study did not use a design that allowed optimal integration to be evaluated. One recent study using a visual-proprioceptive reaching task did find some evidence of optimal integration, as evidenced by a reliability benefit, in children as young as 4–6 years[33]. However, this was only for the subset of observers who showed similar reliability for visual and proprioceptive estimates. Sub-optimal behaviour in other observers was attributed to inappropriate weighting. However, because the study did not include cue-conflict conditions, precise estimation of cue weightings was not possible. Our data suggest that, at least for the current task, the lack of integration shown by our observers was not due to a failure to weight the available signals appropriately. In summary, the current work suggests that optimal integration does not emerge until around 10 years. Model comparison suggests that before that age, observers switch between the information provided by the two modalities, but do so in accordance with their relative reliabilities. This behaviour does result in responses centred on optimal values, but variance is larger than under optimal integration. In contrast with previous work, our younger observers did not rely on a single modality—in fact they were less able to ignore task-irrelevant information. Instead, they instead showed stronger, mandatory cross-sensory interactions than older observers.",
"role": "user"
},
{
"content": "To complete everyday activities , such as judging where or when something occurred , we combine information from multiple senses such as vision and audition . In adults , this merging of information is optimal: more reliable sensory estimates have more influence ( higher weight ) in the combined , multisensory estimate . Multisensory integration can result in illusions: if a single visual flash ( e . g . a bright disk appearing briefly on a screen ) occurs at the same time as two beeps , we sometimes perceive two flashes . This is because auditory information is generally more reliable than vision for judging when things happen; it dominates our audio-visual percept for temporal tasks . Previous work suggests that children don’t combine information from different senses in this adult-like way until around 10 years . To investigate this further , we asked children and adults to report the number of visual flashes or auditory beeps when these were presented simultaneously . Surprisingly , all children used appropriate sensory weights: audition—the more reliable signal—tended to dominate perception , with less weight given to vision . However , children didn’t show the adult-like reduction in uncertainty until around 8–10 years . Before that age , they switched between using only auditory or only visual information on each trial .",
"role": "assistant"
}
] |
science.medmentions_ner
|
science.medmentions_ner.2404
|
[
{
"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: Drug release studies from lipid nanoparticles in physiological media by a new DSC method Lipid nanoparticles are an interesting parenteral delivery system for poorly water-soluble drugs. In order to approach physiological conditions when conducting release studies from such systems the release media should preferentially contain lipophilic acceptor compartments such as lipoproteins or other colloidal lipophilic components. In practice, drug release studies under such close to physiological conditions may be complicated by the small size of lipid nanoparticles, which is in the same range as that of the potential acceptor particles. This study describes a novel differential scanning calorimetry (DSC) method for drug release measurements which works without separation of donor and acceptor particles. The technique is based on measuring the crystallization temperature of trimyristin nanoparticles by DSC. The crystallization temperature of the nanoparticles decreases proportionally with the amount of active ingredient incorporated and thus increases as a result of drug release. Liquid trimyristin nanoparticles loaded with fenofibrate, orlistat, tocopherol acetate and ubidecarenone were studied in three different release media with increasing complexity and comparability to physiological conditions: a rapeseed oil nanoemulsion, porcine serum and porcine blood. Using the new method, a correlation between release behavior and drug lipophilicity was observed: the higher the logP value of the drug, the slower the release. The extent of drug release was influenced by partition equilibrium as indicated by increased drug release in the rapeseed oil nanoemulsion compared to porcine serum and blood.",
"role": "user"
},
{
"content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [\"serum\", \"blood\"], \"BodySystem\": [], \"Chemical\": [\"drug\", \"Lipid\", \"fenofibrate\", \"lipoproteins\", \"media\", \"trimyristin\", \"orlistat\", \"lipid\", \"tocopherol acetate\", \"donor\", \"ubidecarenone\", \"acceptor particles\", \"colloidal\", \"water-soluble drugs\"], \"ClinicalAttribute\": [], \"Eukaryote\": [\"porcine\"], \"Finding\": [], \"Food\": [], \"HealthCareActivity\": [\"differential scanning calorimetry\", \"DSC\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"method\", \"new method\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"study\", \"studies\"], \"SpatialConcept\": [], \"Virus\": []}",
"role": "assistant"
}
] |
science.chemdner_ner
|
science.chemdner_ner.1864
|
[
{
"content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nEFFECT OF C60 FULLERENES ON THE ACCUMULATION OF WEATHERED p,p'-DDE BY PLANT AND EARTHWORM SPECIES UNDER SINGLE AND MULTISPECIES CONDITIONS. The use of engineered nanomaterials has increased dramatically in recent years, but an understanding of nanomaterial fate and effects in the environment is lacking. In particular, the interaction of nanomaterials with coexisting organic contaminants and the subsequent implications for sensitive biota is almost completely unknown. Here, the effect of C60 fullerenes on the accumulation of weathered dichlorodiphenyldichloroethylene (p,p'-DDE; DDT metabolite) by Cucurbita pepo (pumpkin) and Eisenia fetida (earthworm) was determined under single and multispecies conditions. The plants, in the presence or absence of earthworms, were grown in soil containing weathered DDE (200 ng/g) and 0 or 1,670 mg/kg C60 fullerenes. Plants and earthworms were added either simultaneously or sequentially (earthworms after plants). Neither DDE nor C60 had an impact on survival or biomass of plants and earthworms, although fullerenes significantly decreased (29.6-39.0%) the relative root mass. Under single or multispecies conditions, C60 had little impact on DDE bioaccumulation by either species. The DDE concentrations in non-fullerene-exposed shoots, roots, and earthworms were 181, 7,400, and 8,230 ng/g, respectively. On fullerene exposure, the DDE content was nonsignificantly lower at 163, 7280, and 7540 ng/g, respectively. In the presence of the earthworms, C60 significantly decreased the shoot DDE content (28.6%), but no impact on root concentrations was observed. Root DDE content was unaffected by the presence of fullerenes and decreased by 21.6 to 37.5% during coexposure with earthworms. Earthworm DDE content was decreased by plant presence. Earthworms added to soils after plant harvest accumulated more DDE but were unaffected by the C60 exposure. Additional work is necessary, but these findings suggest that fullerenes may have minimal impact on the bioaccumulation of weathered cocontaminants in soil. Environ. Toxicol. Chem. 2013;32:1117-1123. © 2013 SETAC.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"FULLERENES\", \"p,p\\u0027-DDE\", \"fullerenes\", \"DDE\", \"fullerene\", \"C60\", \"dichlorodiphenyldichloroethylene\", \"DDT\"]}",
"role": "assistant"
}
] |
science.scitldr_aic
|
science.scitldr_aic.1653
|
[
{
"content": "Summarize the paper:\n\nPaper text:\n\nWe present an adversarial exploration strategy, a simple yet effective imitation learning scheme that incentivizes exploration of an environment without any extrinsic reward or human demonstration.\nOur framework consists of a deep reinforcement learning (DRL) agent and an inverse dynamics model contesting with each other.\nThe former collects training samples for the latter, and its objective is to maximize the error of the latter.\nThe latter is trained with samples collected by the former, and generates rewards for the former when it fails to predict the actual action taken by the former.\nIn such a competitive setting, the DRL agent learns to generate samples that the inverse dynamics model fails to predict correctly, and the inverse dynamics model learns to adapt to the challenging samples.\nWe further propose a reward structure that ensures the DRL agent collects only moderately hard samples and not overly hard ones that prevent the inverse model from imitating effectively.\nWe evaluate the effectiveness of our method on several OpenAI gym robotic arm and hand manipulation tasks against a number of baseline models.\nExperimental results show that our method is comparable to that directly trained with expert demonstrations, and superior to the other baselines even without any human priors.\nOver the past decade, imitation learning (IL) has been successfully applied to a wide range of domains, including robot learning BID7 BID20 , autonomous navigation BID4 BID19 , manipulation tasks BID11 BID17 , and self-driving cars BID5 .\nTraditionally, IL aims to train an imitator to learn a control policy π only from expert demonstrations.\nThe imitator is typically presented with multiple demonstrations during the training phase, with an aim to distill them into π.\nTo learn π effectively and efficiently, a large set of high-quality demonstrations are necessary.\nThis is especially prevalent in current state-of-the-art IL algorithms, such as dataset aggregation (DAgger) BID18 and generative adversarial imitation learning (GAIL) BID9 .\nAlthough these approaches have been the dominant algorithms in IL, a major bottleneck for them is their reliance on high-quality demonstrations, which often require extensive supervision from human experts.\nIn addition, a serious flaw in the learned policy π is its tendency to overfit to demonstration data, preventing it from generalizing to new ones.\nTo overcome the aforementioned challenges in IL, a number of methods have been investigated to enhance the generalizability and data efficiency, or reduce the degree of human supervision.\nInitial efforts in this direction were based on the idea of meta learning BID6 BID8 Yu et al., 2018) , in which the imitator is trained from a meta learner that is able to quickly learn a new task with only a few set of demonstrations.\nHowever, such schemes still require training the meta-learner with tremendous amount of time and demonstration data, leaving much room for improvement.\nThus, a rapidly-growing body of literature based on the concept of using forward/inverse dynamics models to learn π within an environment in a self-supervised fashion BID0 BID11 BID13 has emerged in the past few years.\nOne key advantage of the concept is that it provides an autonomous way for preparing training data, removing the need of human intervention.\nIn this paper, we call it self-supervised IL.Self-supervised IL allows an imitator to collect training data by itself instead of using predefined extrinsic reward functions or expert supervision during training.\nIt only needs demonstration during inference, drastically decreasing the time and effort required from human experts.\nAlthough the core principles of self-supervised IL are straightforward and have been exploited in many fields BID0 BID11 BID12 , recent research efforts have been dedicated to addressing the challenges of multi-modality and multi-step planning.\nFor example, the use of forward consistency loss and forward regularizer have been extensively investigated to enhance the task performance of the imitator BID0 BID13 .\nThis becomes especially essential when the lengths of trajectories grow and demonstration samples are sparse, as multiple paths may co-exist to lead the imitator from its initial observation to the goal observation.\nThe issue of multi-step planning has also drawn a lot of attention from researchers, and is usually tackled by recurrent neural networks (RNNs) and step-by-step demonstrations BID11 BID13 .\nThe above self-supervised IL approaches report promising results, however, most of them are limited in applicability due to several drawbacks.\nFirst, traditional methods of data collection are usually inefficient and time-consuming.\nInefficient data collection results in poor exploration, giving rise to a degradation in robustness to varying environmental conditions (e.g., noise in motor control) and generalizability to difficult tasks.\nSecond, human bias in data sampling range tailored to specific interesting configurations is often employed BID0 BID11 .\nAlthough a more general exploration strategy called curiosity-driven exploration was later proposed in BID12 , it focuses only on exploration in states novel to the forward dynamics model, rather than those directly influential to the inverse dynamics model.\nFurthermore, it does not discuss the applicability to continuous control domains, and fails in high dimensional action spaces according to our experiments in Section 4.\nUnlike the approaches discussed above, we do not propose to deal with multi-modality or multi-step planning.\nInstead, we focus our attention on improving the overall quality of the collected samples in the context of self-supervised IL.\nThis motivates us to equip the model with the necessary knowledge to explore the environment in an efficient and effective fashion.In this paper, we propose a straightforward and efficient self-supervised IL scheme, called adversarial exploration strategy, which motivates exploration of an environment in a self-supervised manner (i.e., without any extrinsic reward or human demonstration).\nInspired by Pinto et al. (2017) ; BID23 ; BID24 , we implement the proposed strategy by jointly training a deep reinforcement learning (DRL) agent and an inverse dynamics model competing with each other.\nThe former explores the environment to collect training data for the latter, and receives rewards from the latter if the data samples are considered difficult.\nThe latter is trained with the training data collected by the former, and only generates rewards when it fails to predict the true actions performed by the former.\nIn such an adversarial setting, the DRL agent is rewarded only for the failure of the inverse dynamics model.\nTherefore, the DRL agent learns to sample hard examples to maximize the chances to fail the inverse dynamics model.\nOn the other hand, the inverse dynamics model learns to be robust to the hard examples collected by the DRL agent by minimizing the probability of failures.\nAs a result, as the inverse dynamics model becomes stronger, the DRL agent is also incentivized to search for harder examples to obtain rewards.\nOverly hard examples, however, may lead to biased exploration and cause instability of the learning process.\nIn order to stabilize the learning curve of the inverse dynamics model, we further propose a reward structure such that the DRL agent is encouraged to explore moderately hard examples for the inverse dynamics model, but refraining from too difficult ones for the latter to learn.\nThe self-regulating feedback structure between the DRL agent and the inverse dynamics model enables them to automatically construct a curriculum for exploration.We perform extensive experiments to validate adversarial exploration strategy on multiple OpenAI gym BID3 robotic arm and hand manipulation task environments simulated by the MuJoCo physics engine (Todorov et al., 2012) , including FetchReach, FetchPush, FetchPickAndPlace, FetchSlide, and HandReach.\nThese environments are intentionally selected by us for evaluating the performance of inverse dynamics model, as each of them allows only a very limited set of chained actions to transition the robotic arms and hands to target observations.\nWe examine the effectiveness of our method by comparing it against a number of self-supervised IL schemes.\nThe experimental results show that our method is more effective and data-efficient than the other self-supervised IL schemes for both low-and high-dimensional observation spaces, as well as in environments with high-dimensional action spaces.\nWe also demonstrate that in most of the cases the performance of the inverse dynamics model trained by our method is comparable to that directly trained with expert demonstrations.\nThe above observations suggest that our method is superior to the other self-supervised IL schemes even in the absence of human priors.\nWe further evaluate our method on environments with action space perturbations, and show that our method is able to achieve satisfactory success rates.\nTo justify each of our design decisions, we provide a comprehensive set of ablative analysis and discuss their implications.\nThe contributions of this work are summarized as follows:• We introduce an adversarial exploration strategy for self-supervised IL.\nIt consists of a DRL agent and an inverse dynamics model developed for efficient exploration and data collection.•\nWe employ a competitive scheme for the DRL agent and the inverse dynamics model, enabling them to automatically construct a curriculum for exploration of observation space.•\nWe introduce a reward structure for the proposed scheme to stabilize the training process.•\nWe demonstrate the proposed method and compare it with a number of baselines for multiple robotic arm and hand manipulation tasks in both low-and high-dimensional state spaces.•\nWe validate that our method is generalizable to tasks with high-dimensional action spaces.The remainder of this paper is organized as follows. Section\n2 introduces background material. Section\n3 describes the proposed adversarial exploration strategy in detail. Section\n4 reports the experimental results, and provides an in-depth ablative analysis of our method. Section\n5 concludes.\nIn this paper, we presented an adversarial exploration strategy, which consists of a DRL agent and an inverse dynamics model competing with each other for self-supervised IL.\nThe former is encouraged to adversarially collect difficult training data for the latter, such that the training efficiency of the latter is significantly enhanced.\nExperimental results demonstrated that our method substantially improved the data collection efficiency in multiple robotic arm and hand manipulation tasks, and boosted the performance of the inverse dynamics model in both low-and high-dimensional observation spaces.\nIn addition, we validated that our method is generalizable to environments with high-dimensional action spaces.\nMoreover, we showed that our method is robust to action space perturbations.\nFinally, we provided a set of ablative analysis to validate the effectiveness for each of our design decisions.",
"role": "user"
},
{
"content": "A simple yet effective imitation learning scheme that incentivizes exploration of an environment without any extrinsic reward or human demonstration.",
"role": "assistant"
}
] |
science.mslr2022_ms2_multidoc_summarization
|
science.mslr2022_ms2_multidoc_summarization.12390
|
[
{
"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:\nEconomic Evaluation of Pediatric Telemedicine Consultations to Rural Emergency Departments\nAbstract 1:\nBackground . Comprehensive economic evaluations have not been conducted on telemedicine consultations to children in rural emergency departments ( EDs ) . Objective . We conducted an economic evaluation to estimate the cost , effectiveness , and return on investment ( ROI ) of telemedicine consultations provided to health care providers of acutely ill and injured children in rural EDs compared with telephone consultations from a health care payer prospect i ve . Methods . We built a decision model with parameters from primary programmatic data , national data , and the literature . We performed a base-case cost-effectiveness analysis ( CEA ) , a probabilistic CEA with Monte Carlo simulation , and ROI estimation when CEA suggested cost-saving . The CEA was based on program effectiveness , derived from transfer decisions following telemedicine and telephone consultations . Results . The average cost for a telemedicine consultation was $ 3641 per child/ED/year in 2013 US dollars . Telemedicine consultations result ed in 31 % fewer patient transfers compared with telephone consultations and a cost reduction of $ 4662 per child/ED/year . Our probabilistic CEA demonstrated telemedicine consultations were less costly than telephone consultations in 57 % of simulation iterations . The ROI was calculated to be 1.28 ( $ 4662/$3641 ) from the base-case analysis and estimated to be 1.96 from the probabilistic analysis , suggesting a $ 1.96 return for each dollar invested in telemedicine . Treating 10 acutely ill and injured children at each rural ED with telemedicine result ed in an annual cost-savings of $ 46,620 per ED . Limitations . Telephone and telemedicine consultations were not r and omly assigned , potentially result ing in biased results . Conclusions . From a health care payer perspective , telemedicine consultations to health care providers of acutely ill and injured children presenting to rural EDs are cost-saving ( base-case and more than half of Monte Carlo simulation iterations ) or cost-effective compared with telephone consultations\n\n\nTitle 2:\nA comparison of real‐time and store‐and‐forward teledermatology: a cost–benefit study\nAbstract 2:\nBackground Increasing use of teledermatology should be based on demonstration of favourable accuracy and cost – benefit analysis for the different methods of use of this technique\n\n\nTitle 3:\nAn empirical chart analysis of the suitability of telemedicine for hospice visits.\nAbstract 3:\nTelehospice ( TH ) utilizes telemedicine technology to provide care at the end of life . A bistate project was launched in 1998 to study the use of home-based telemedicine for routine hospice care . Videophones were deployed for telenursing visits and evaluations by social workers . In order to determine what proportion of home hospice visits could be performed using currently available telemedicine technology , we review ed clinical records retrospectively for hospice nurse home visits . Clinical notes documenting home nursing visits were obtained from two large hospices , one based in Kansas , and the other in Michigan . Records were r and omly selected for patients who received hospice nurse visits during the month of January 2000 . The charts were review ed for patient demographic information , patient assessment s , teaching activities , and interventions . Five hundred ninety-seven nursing notes were analyzed using an 85-item coding instrument . After careful review of the records , the coders also made a subjective observation regarding the suitability of each visit for telemedicine . As part of this analysis , we found that 64.5 % of home hospice nursing visits could be performed by telemedicine . Using TH , it is possible to reduce the number of in-person visits , thereby significantly decreasing the cost of providing hospice care\n\n\nTitle 4:\nHow effective is a virtual consultation process in facilitating multidisciplinary decision-making for malignant epidural spinal cord compression?\nAbstract 4:\nPURPOSE The purpose of this study was to assess the accuracy of a virtual consultation ( VC ) process in determining treatment strategy for patients with malignant epidural spinal cord compression ( MESCC ) . METHODS AND MATERIAL S A prospect i ve clinical data base was maintained for patients with MESCC . A virtual consultation process ( involving exchange of key predetermined clinical information and diagnostic imaging ) facilitated rapid decision-making between oncologists and spinal surgeons . Diagnostic imaging was review ed retrospectively ( by R.R. ) for surgical opinions in all patients . The primary outcome was the accuracy of virtual consultation opinion in predicting the final treatment recommendation . RESULTS After excluding 20 patients who were referred directly to the spinal surgeon , 125 patients were eligible for virtual consultation . Of the 46 patients who had a VC , surgery was recommended in 28 patients and actually given to 23 . A retrospective review revealed that 5/79 patients who did not have a VC would have been considered surgical c and i date s. The overall accuracy of the virtual consultation process was estimated at 92 % . CONCLUSION The VC process for MESCC patients provides a reliable means of arriving at a multidisciplinary opinion while minimizing patient transfer . This can potentially shorten treatment decision time and enhance clinical outcomes\n\n\nTitle 5:\nA randomized controlled trial assessing the health economics of realtime teledermatology compared with conventional care: an urban versus rural perspective\nAbstract 5:\nA r and omized controlled trial was carried out to measure the cost-effectiveness of realtime teledermatology compared with conventional outpatient dermatology care for patients from urban and rural areas . One urban and one rural health centre were linked to a regional hospital in Northern Irel and by ISDN at 128 kbit/s . Over two years , 274 patients required a hospital outpatient dermatology referral - 126 patients ( 46 % ) were r and omized to a telemedicine consultation and 148 ( 54 % ) to a conventional hospital outpatient consultation . Of those seen by telemedicine , 61 % were registered with an urban practice , compared with 71 % of those seen conventionally . The clinical outcomes of the two types of consultation were similar - almost half the patients were managed after a single consultation with the dermatologist . The observed marginal cost per patient of the initial realtime teledermatology consultation was 52.85 for those in urban areas and 59.93 per patient for those from rural areas . The observed marginal cost of the initial conventional consultation was 47.13 for urban patients and 48.77 for rural patients . The total observed costs of teledermatology were higher than the costs of conventional care in both urban and rural areas , mainly because of the fixed equipment costs . Sensitivity analysis using a real-world scenario showed that in urban areas the average costs of the telemedicine and conventional consultations were about equal , while in rural areas the average cost of the telemedicine consultation was less than that of the conventional consultation\n\n\nTitle 6:\nSuccesses and challenges in a field-based, multi-method study of home telehealth\nAbstract 6:\nWe are conducting a three-year study of telehealth in 11 home care offices that serve rural clients in Alberta . Three hundred and twenty palliative home care clients are being recruited to participate in a r and omized controlled trial ( RCT ) to answer three questions about the use of video-phones and their effect on symptom management , quality of life and cost , as well as readiness to use the technology . Both successes and challenges have been identified in three main areas : technology , people/organizational issues and study design . Maintaining study integrity has been the key factor in decision making , as adjustments from the original proposal are made . It is already clear that field-based RCTs are feasible , but require commitment and flexibility on the part of research ers and community partners to work through the study implementation\n\n\nTitle 7:\nUsing videotelephony to support paediatric oncology-related palliative care in the home: from abandoned RCT to acceptability study\nAbstract 7:\nVideotelephony ( real-time audio-visual communication ) has been used successfully in adult palliative home care . This paper describes two attempts to complete an RCT ( both of which were ab and oned following difficulties with family recruitment ) , design ed to investigate the use of videotelephony with families receiving palliative care from a tertiary paediatric oncology service in Brisbane , Australia . To investigate whether providing videotelephone-based support was acceptable to these families , a 12-month non-r and omised acceptability trial was completed . Seventeen palliative care families were offered access to a videotelephone support service in addition to the 24 hours ‘ on-call ’ service already offered . A 92 % participation rate in this study provided some reassurance that the use of videotelephones themselves was not a factor in poor RCT participation rates . The next phase of research is to investigate the integration of videotelephone-based support from the time of diagnosis , through outpatient care and support , and for palliative care rather than for palliative care in isolation . Trial registration ACTRN\n\n\nTitle 8:\nA randomized controlled trial to assess the clinical effectiveness of both realtime and store-and-forward teledermatology compared with conventional care\nAbstract 8:\nThe clinical effectiveness of realtime teledermatology , store- and -forward teledermatology and conventional outpatient dermatological care were evaluated in a r and omized control trial . A total of 204 patients took part – 102 patients were r and omized to the realtime teledermatology consultation , 96 of whose cases were also referred using a store- and -forward technique , and 102 to the conventional outpatient consultation . There were no differences in the reported clinical outcomes of realtime teledermatology and conventional dermatology . Of those r and omized to the realtime teledermatology consultation , 46 % required at least one subsequent hospital appointment compared with 45 % of those r and omized to the conventional outpatient consultation . In contrast , the dermatologist requested a subsequent hospital appointment for 69 % of those seen by store- and -forward teledermatology . An analysis of costs showed that realtime teledermatology was clinical ly feasible but more expensive than conventional care , while the store- and -forward teledermatology consultation was less expensive but its clinical usefulness was limited . Sensitivity analysis indicated that realtime teledermatology was as economical as conventional care when less artificial assumptions were made about equipment utilization , costs and travel distances to hospital",
"role": "user"
},
{
"content": "Studies on teledermatology and teleradiology indicated a favorable level of economic efficiency .\nOverall , telemedicine programs in Japan were indicated to have a favorable level of economic efficiency .",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.29378
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nWe prove the existence and uniqueness, for wave speeds sufficiently large, of monotone traveling wave solutions connecting stable to unstable spatial equilibria for a class of @math -dimensional lattice differential equations with unidirectional coupling. This class of lattice equations includes some spatial discretizations for hyperbolic conservation laws with a source term as well as a subclass of monotone systems. We obtain a variational characterization of the critical wave speed above which monotone traveling wave solutions are guaranteed to exist. We also discuss non-monotone waves, and the coexistence of monotone and non-monotone waves.\n\nCited Abstract(s):\n[1]: Abstract This work proves the existence and multiplicity results of monotonic traveling wave solutions for some lattice differential equations by using the monotone iteration method. Our results include the model of cellular neural networks (CNN). In addition to the monotonic traveling wave solutions, non-monotonic and oscillating traveling wave solutions in the delay type of CNN are also obtained.\n\n[2]: The theory of a novel class of information-processing systems, called cellular neural networks, which are capable of high-speed parallel signal processing, was presented in a previous paper (see ibid., vol.35, no.10, p.1257-72, 1988). A dynamic route approach for analyzing the local dynamics of this class of neural circuits is used to steer the system trajectories into various stable equilibrium configurations which map onto binary patterns to be recognized. Some applications of cellular neural networks to such areas as image processing and pattern recognition are demonstrated, albeit with only a crude circuit. In particular, examples of cellular neural networks which can be designed to recognize the key features of Chinese characters are presented. >",
"role": "user"
},
{
"content": "In [1] Hsu and Lin consider lattice equations of the form (two-dimensional equations, and equations where the coupling is not unidirectional, are also considered in [1] ). The chief motivation for [1] lies in the case that @math is piecewise linear; in this case becomes a so-called (CNN). Cellular neural networks were first introduced in [2] to model the behavior of a large array of coupled electronic components.",
"role": "assistant"
}
] |
science.chemdner_ner
|
science.chemdner_ner.619
|
[
{
"content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nEthanol modulates the neurovascular coupling. Despite some evidence of the underlying molecular mechanisms the neuronal basis of ethanol-induced effects on the neurovascular coupling that forms the BOLD (blood oxygenation level dependent) signal is poorly understood. In a recent fMRI (functional magnetic resonance imaging) study monitoring ethanol-induced changes of the BOLD signal a reduction of the amplitude and a prolongation of the BOLD signal were observed. However, the BOLD signal is assumed to consist of a complex superposition of different underlying signals. To gain insight how ethanol influences stimulus efficacy, oxygen extraction, transit time and vessel-related parameters the fMRI time series from the sensori-motor and the visual cortex were analyzed using the balloon model. The results show a region-dependent decrease of the stimulus efficacy to trigger a post-stimulus neurovascular response as well as a prolongation of the transit time through the venous compartment. Oxygen extraction, feedback mechanisms and other vessel-related parameters were not affected. The results may be interpreted as follows: the overall mechanisms of the neurovascular coupling are still acting well at the moderate ethanol level of about 0.8‰ (in particular the vessel-related parts), but the potency to evoke a neurovascular response is already compromised most obviously in the supplementary motor area responsible for complex synchronizing and planning processes.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"Oxygen\", \"Ethanol\", \"ethanol\", \"oxygen\"]}",
"role": "assistant"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.