dataset
stringclasses 45
values | id
stringlengths 17
63
| messages
listlengths 2
2
|
|---|---|---|
science.chemsum_single_document_summarization | science.chemsum_single_document_summarization.12046 | [
{
"content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nTuning the Magnetic Properties of Two-Dimensional MXenes by Chemical Etching\n\nContent Extracts:\nINTRODUCTION\n<p>Since the first reported synthesis of single-layer graphene by the mechanical exfoliation of graphite in 2004, there has been tremendous research interest in the chemical, electronic, physical properties of two-dimensional (2D) materials. 1 In 2011, it was first reported that 2D nanosheets of Ti3C2 could be obtained by chemically etching the aluminum layer from Ti3AlC2 MAX-phase materials with hydrofluoric acid. 2 These materials were referred to as MXenes due to their similar electronic properties to graphene. MXenes have a general formula of Mn+1Xn, where M represents an early transition metal, X is carbon and/or nitrogen, and n = 1, 2, or 3. The etching process may occur via a direct hydrofluoric acid treatment (harsh) or an in situ generation of hydrofluoric acid through the protonation of an aqueous fluoride-containing salt in hydrochloric acid solution (mild), which result in surface terminations (Tx) of fluoride, oxide, hydroxide, and chloride on the metal surface. Thus, the MXene general formula may be denoted as Mn+1XnTx. To date, approximately 20 single-transition metal MXenes and 15 ordered double-transition metal MXenes have reportedly been experimentally synthesized and up to 100 different MXene compositions have been theoretically predicted to be stable. 3 The high elastic mechanical strength 4 , electronic conductivity 5,6 , chemical stability [7][8][9] , and hydrophilicity 10,11 of MXenes have opened broad prospects for their applications in a variety of industrial and technological areas including energy storage, optoelectronics, spintronics, catalysis, and sensing. [12][13][14][15][16][17][18][19][20][21][22][23] Although there is significant research effort in the optical 24,25 and electronic 11,26,27 properties of MXenes, the magnetic properties of these materials for spintronic application is relatively unexplored. 28 The intrinsic properties of MXenes are mainly determined by the transition metal in the MAX phase. Therefore, most of the reported magnetic MXenes are based on magnetic transition metal elements such as Cr, V, Mn, MO, Fe, Co and Ni. 25,27,[29][30][31][32][33][34][35][36][37] However, MXenes based on nonmagnetic transition metals are also predicted to be magnetic and their optical, electronic, and magnetic properties can be influenced by different surface terminating groups and synthetic procedures. [38][39][40][41] It has also been experimentally confirmed that the presence of atomic defects in layers can alter the magnetic properties of MXenes. 42 In this work, we report the synthesis of Ti3C2TX MXenes, which are robust to oxidation 8 , using a milder LiF/HCl solution and investigated the magnetic properties. There have been relatively few reports on the magnetic characteristics of these materials. 40,41,43 The extent of aluminum removal was controlled by performing two separate syntheses, one at ambient temperature and another at an elevated temperature for a longer reaction time. The magnetic property of the resulting Ti3C2TX MXene was analyzed using a superconducting quantum interference device (SQUID) and the extent of etching was determined by using X-ray diffraction (XRD). We observed a paramagneticantiferromagnetic (PM-AFM) phase transition in samples generated by both synthesis techniques that occurs at different Néel temperatures, indicating that the aluminum content mediates the magnetic transition.</p>\n\nSample preparation\n<p>A sample (20 g) of commercially-available MAX phase Ti3AlC2 powder (>98%, 200 mesh, Forman, China) was further milled in a planetary mill (SPEX 8000 M Mixer/Mill) using a zirconia jar (45 cm 3 ) and two zirconia balls (12.7 mm diameter). A milling energy of 1/3 hp was used at a milling rate of 1725 rpm for 45 minutes.</p><p>BATCH 1 Ti3C2Tx was prepared by etching Al from the milled Ti3AlC2 powder in a solution containing 1.33 g LiF (>97% Alfa Aesar) dissolved in 100 mL of 6 M HCl solution. First, 2.00 g Ti3AlC2 powders were slowly added into the 100 mL LiF/HCl solution and magnetically stirred at 400 rpm for 24 h at room temperature (21 °C). The mol ratio of LiF and Ti3AlC2 in this mixture was 5:1. The crude Ti3C2Tx product was collected and centrifuged at 4,500 rpm for 10 minute and further washed first with 6 M HCl for 3 cycles and then with DI water repeatedly; the resultant samples were centrifuged for 15 minutes until the resulting supernatant reached a pH > 6. The supernatant contained a green coloration indicating that delamination of the Ti3C2Tx nanosheets was occurring (Figure S1a). The Ti3C2Tx product was vacuum filtered and air dried at room temperature for 24 h before storage (Figure S1b). The mass of the obtained product was 1.57 g.</p>\n\nBATCH 2\n<p>T3C2Tx was prepared in a solution containing 1.93 g LiF (>97% Alfa Aesar) dissolved 100 mL of 6 M HCl solution. First, 2.90 g Ti3AlC2 powders were slowly added into the 100 mL LiF/HCl solution and magnetically stirred at 400 rpm for 166 h at 35 °C. The mol ratio of LiF and Ti3AlC2 in this mixture was also 5:1. The crude product was washed using the same procedure as Batch 1 and then allowed to air dry at room temperature for 24 hr, followed by heating at 125°C for 45 minutes. The mass of the obtained purified product was 2.00 g.</p>\n\nCharacterization\n<p>The XRD measurements were conducted on a Rigaku Miniflex 600 X-ray diffractometer. The instrument was operated at 20 kV voltage and 2 mA current. The XRD pattern of Ti3AlC2 MAX phase and Ti3C2Tx MXene powder samples were taken over the scan range from 5° to 90° at a scan rate of 0.075° /min. The magnetic behavior of the Ti3AlC2 powders and the etched Ti3C2Tx MXene samples were measured in a Quantum Design SQUID vibrating sample magnetometer (VSM) over the temperature range 2-400K with applied magnetic fields from 0-2T. For these measurements, samples were mounted on a quartz holder with GE 7031 varnish; we confirmed that there is no magnetic contribution from the holder and varnish prior to these measurements. Morphological data were collected using a JEOL JSM-6510LV scanning electron microscope (SEM) and topographic images were taken using a Keysight 5500 AFM/SPM system (Keysight Technologies, Inc., CO, USA).</p>\n\nRESULTS AND DISUSSION\n<p>The X-ray diffraction (XRD) measurements were conducted to determine the crystal structure of materials before and after LiF/HCl etching. Figure 1 shows the XRD patterns of the Ti3AlC2 and Ti3C2Tx samples in the scan range 5-90° where Tx denotes the surface terminations (O 2− , OH − , and F − ) on the MXene sheet. The typical peaks of both of Ti3AlC2 and Ti3C2Tx samples are within this range and are consistent with the previously published results. [44][45][46] The lowest Bragg peak for the (002) reflection of the Ti3AlC2 powder occurs at 9.70° with its second order reflection at ~19° and several other allowed indicating the presence of some unreacted MAX phase in the bulk after the etching process. 44 A very contrasting XRD pattern is obtained when Ti3AlC2 was etched at 35 °C for 166 hours (batch 2). The (002) reflection is shifted to 8.30° and is much broader compared to Ti3AlC2. The peak shift to the smaller angle and hence the increase in the c-lattice parameter suggests that the surface functional groups and micro-molecules such as water molecules appear between the MXene nanosheets. 48 In addition, the (004) reflection at 17.6° and the (006) at 26.5° are also broadened.</p><p>Furthermore, the (104) peak at 39° is vanishingly small as compared to Ti3AlC2 and Ti3C2Tx Batch 1 samples. These observations indicate that Ti3AlC2 is transformed to Ti3C2Tx MXene 44,49 with less unreacted MAX phase in Batch 2 compared to Batch 1. It is worth noting here that the vanishingly small 39° peak was previously reported using direct HF etching 46 but this is the first observation with the milder LiF/HCl etching method.</p><p>The surface roughness of MXene flakes was characterized by atomic force microcopy (AFM) in a tapping mode. The topographic image (Figure S2) shows clear sheet structures with an average height of 16 nm, mean area 1005 nm 2 and mean roughness 2.98 nm. The minimum thickness of the MXene sheets is around 2-3 nm which corresponds to few layers of two dimensional MXene flake nanostructures. 47,48,50 Scanning electron microscopy (SEM) image</p><p>shows that the synthesized Ti3C2Tx MXene exhibits the discrete layered/sheet structure with well crystallized feature (Figure S3) confirming the observation from the AFM measurement.</p><p>To investigate how the extent of etching affected the magnetic properties, a SQUID VSM was used to measure the magnetic moment as a function of applied magnetic field and temperature in an applied magnetic field of 1 kOe. Consistent with the M vs H data (Figure 2), the M vs T behavior of Ti3AlC2 shown in Figure 3(a) indicates that it is ferromagnetic in nature. It has been reported that MAX phases exhibit Pauli paramagnetism. 40,41,51 complex PM-AFM behavior in Ti3C2Tx. This explanation is consistent with the recently reported AFM behavior of La 3+ doped Ti3C2Tx where La 3+ ions are adsorbed onto the MXene surface. 43</p>\n\nCONCLUSION\n<p>In conclusion, we examined the magnetic properties of Ti3AlC2 MAX phase and two batches of Ti3C2Tx MXene to understand the impact of etching on the magnetic behavior. We found that Ti3AlC2 is ferromagnetic whereas a complex PM-AFM behavior is observed in MXenes. The FM-AFM transition temperature depends on the extent of etching of Ti3AlC2. In fact, the results show a direct quantitative correlation between the extent of Al etching (obtained through XRD) and the PM-AFM transition temperature. Our findings provide an improved understanding of the factors that control the magnetic behavior in titanium carbide MXenes.</p><p>ASSOCIATED CONTENT Supporting Information. Additional experimental results \"This material is available free of charge via the Internet at http://pubs.acs.org.\"</p>\n\nAUTHOR INFORMATION\n<p>Corresponding Author [email protected]</p>\n\nNotes\n<p>The authors declare no competing financial interests.</p>",
"role": "user"
},
{
"content": "Two-dimensional materials based on transition metal carbides have been intensively studied due to their unique properties including metallic conductivity, hydrophilicity, and structural diversity and have shown great potential in several applications. While MXenes based on magnetic transition elements show interesting magnetic properties, not much is known about the magnetic properties of titanium-based MXenes. Here, we measured magnetic properties of Ti3C2Tx MXenes synthesized by different chemical etching conditions. Our measurements indicate that there is a paramagnetic-antiferromagnetic (PM-AFM) phase transition, and the transition temperature depends on the synthesis procedure of MXenes. Our observation indicates that the magnetic properties of these MXenes can be tuned by the extent of chemical etching which can be beneficial for the design of MXene-based spintronic devices.",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.2912 | [
{
"content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nConsistentwiththealteredearlyendosomemarker(EEA1)signalobservedbyimmunostaining(Fig.3),fluid-phaseendocytosiswasalsoalteredinhomozygousCbCln3Deltaex7/8cells,asmeasuredbydextran-FITCuptake(Fig.7).",
"role": "user"
},
{
"content": "[\"FITC\"]",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.859 | [
{
"content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nLifecycle models for research data are often abstract and simple. This comes at the danger of oversimplifying the complex concepts of research data management. The analysis of 90 different lifecycle models lead to two approaches to assess the quality of these models. While terminological issues make direct comparisons of models hard, an empirical evaluation seems possible.\n\nCited Works Summary:\n[1]: A huge amount of data is constantly being produced in the world. Data coming from the IoT, from scientific simulations, or from any other field of the eScience, are accumulated over historical data sets and set up the seed for future Big Data processing, with the final goal to generate added value and discover knowledge. In such computing processes, data are the main resource, however, organizing and managing data during their entire life cycle becomes a complex research topic. As part of this, Data LifeCycle (DLC) models have been proposed to efficiently organize large and complex data sets, from creation to consumption, in any field, and any scale, for an effective data usage and big data exploitation. 2. Several DLC frameworks can be found in the literature, each one defined for specific environments and scenarios. However, we realized that there is no global and comprehensive DLC model to be easily adapted to different scientific areas. For this reason, in this paper we describe the Comprehensive Scenario Agnostic Data LifeCycle (COSA-DLC) model, a DLC model which: i) is proved to be comprehensive as it addresses the 6Vs challenges (namely Value, Volume, Variety, Velocity, Variability and Veracity, and ii), it can be easily adapted to any particular scenario and, therefore, fit the requirements of a specific scientific field. In this paper we also include two use cases to illustrate the ease of the adaptation in different scenarios. We conclude that the comprehensive scenario agnostic DLC model provides several advantages, such as facilitating global data management, organization and integration, easing the adaptation to any kind of scenario, guaranteeing good data quality levels and, therefore, saving design time and efforts for the scientific and industrial communities.\n\n[2]: \n\n[3]: As science becomes more data-intensive and collaborative, researchers increasingly use larger and more complex data to answer research questions. The capacity of storage infrastructure, the increased sophistication and deployment of sensors, the ubiquitous availability of computer clusters, the development of new analysis techniques, and larger collaborations allow researchers to address grand societ al challenges in a way that is unprecedented. In parallel, research data repositories have been built to host research data in response to the requirements of sponsors that research data be publicly available. Libraries are re-inventing themselves to respond to a growing demand to manage, store, curate and preserve the data produced in the course of publicly funded research. As librarians and data managers are developing the tools and knowledge they need to meet these new expectations, they inevitably encounter conversations around Big Data. This paper explores definitions of Big Data that have coalesced in the last decade around four commonly mentioned characteristics: volume, variety, velocity, and veracity. We highlight the issues associated with each characteristic, particularly their impact on data management and curation. We use the methodological framework of the data life cycle model, assessing two models developed in the context of Big Data projects and find them lacking. We propose a Big Data life cycle model that includes activities focused on Big Data and more closely integrates curation with the research life cycle. These activities include planning, acquiring, preparing, analyzing, preserving, and discovering, with describing the data and assuring quality being an integral part of each activity. We discuss the relationship between institutional data curation repositories and new long-term data resources associated with high performance computing centers, and reproducibility in computational science. We apply this model by mapping the four characteristics of Big Data outlined above to each of the activities in the model. This mapping produces a set of questions that practitioners should be asking in a Big Data project\n\n[4]: The Semantic Web, especially in the light of the current focus on its nature as a Web of Data, is a data-centric system, and arguably the largest such system in existence. Data is being created, published, exported, imported, used, transformed and re-used, by different parties and for different purposes. Together, these actions form a lifecycle of data on the Semantic Web. Understanding this lifecycle will help to better understand the nature of data on the SW, to explain paradigm shifts, to compare the functionality of different platforms, to aid the integration of previously disparate implementation efforts or to position various actors on the SW and relate them to each other. However, while conceptualisations of many aspects of the SW exist, no exhaustive data lifecycle has been proposed. This paper proposes a data lifecycle model for the Semantic Web by first looking outward, and performing an extensive survey of lifecycle models in other data-centric domains, such as digital libraries, multimedia, eLearning, knowledge and Web content management or ontology development. For each domain, an extensive list of models is taken from the literature, and then described and analysed in terms of its different phases, actor roles and other characteristics. By contrasting and comparing the existing models, a meta vocabulary of lifecycle models for data-centric systems — the Abstract Data Lifecycle Model, or ADLM — is developed. In particular, a common set of lifecycle phases, lifecycle features and lifecycle roles is established, as well as additional actor features and generic features of data and metadata. This vocabulary now provides a tool to describe each individual model, relate them to each other, determine similarities and overlaps and eventually establish a new such model for the Semantic Web.",
"role": "user"
},
{
"content": "[1]0 , [1] and [3] are alike to [4] in the approach to review existing models and deriving an own lifecycle model based on a gap analysis. None of the three publications offer generic and empirical evaluation criteria or a metamodel for the existing models. Their lifecycle model is designed to supersede the existing approaches for a specific context.",
"role": "assistant"
}
]
|
science.bc7_litcovid_topic_classification | science.bc7_litcovid_topic_classification.3743 | [
{
"content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nAs recovery of congenital heart surgery programs begins during this COVID-19 pandemic, we review key considerations such as screening, protection of patients and health care workers (HCWs), case prioritization, barriers to reactivation, redesign of patient care teams, contribution of telemedicine, modification of trainees' experiences, preparation for potential resurgence, and strategies to maintain HCW wellness. COVID-19 has tested the resolve and grit of our specialty and we have an opportunity to emerge more refined.",
"role": "user"
},
{
"content": "[\"Prevention\"]",
"role": "assistant"
}
]
|
science.acl_arc_intent_classification | science.acl_arc_intent_classification.130 | [
{
"content": "Examine the given text from a research paper in the field of NLP. Your task is to identify the role of the citation within the context provided. Focus on understanding the intent behind the citation and classify it accordingly.\n\nSection Title:\nNone\n\nText Before Citation:\nfθ on demand (Mohri et al., 1998) can pay off here, since only part of fθ may be needed subsequently.) 10Traditionally log(strength) values are called weights, but this paper uses âweightâ to mean something else. \u0000\u0000\u0000\u0000 In the extreme, if each input string is fully observed (not the case if the input is bound by composition to the output of a one-to-many FST), one can succeed by restricting g to each input string in turn; this amounts to manually dividing f(x, y) by g(x). \u0000\u0000\u0000\n\nCitation Text:\nfθ on demand ( Mohri et al. , 1998 ) can pay off here , since only part of fθ may be needed subsequently . )\n\nText After Citation:\nAs training data we are given a set of observed (input, output) pairs, (xi, yi). These are assumed to be independent random samples from a joint distribution of the form fe(x, y); the goal is to recover the true Ë0. Samples need not be fully observed (partly supervised training): thus xi C E*, yi C A* may be given as regular sets in which input and output were observed to fall. For example, in ordinary HMM training, xi = E* and represents a completely hidden state sequence (cfXXX Ristad (1998), who allows any regular set), while yi is a single string representing a completely observed emission sequence.11 What to optimize?",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
]
|
science.scientific_papers_summarization_single_doc_pubmed | science.scientific_papers_summarization_single_doc_pubmed.7407 | [
{
"content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nthe 20 century witnessed a myriad of advances in technology , which have found several applications in the field of medicine .\nvideo technology was one of the most important factors that enhanced the ability of surgeons to perform complex laparoscopic surgeries .\nthe advantages of laparoscopy were realized in adult surgeries long before its acceptance in pediatric surgery .\nthe reasons for initial non - acceptance included lack of suitable equipment for the pediatric patient , uncommon need for cholecystectomy and perhaps the traditionally smaller incisions in pediatric patients making the cosmetic benefit of laparoscopy less evident .\ncurrently , laparoscopy can now be performed in infants weighing less than 1.5 kg without significant mortality or morbidity .\nthe advent of minimal access technique of laparoscopy marked a new dawn in surgical care of patients .\nvideo - laparoscopy allows surgical assistants ; anesthesiologists and nurses to view what the surgeon is doing and to actively participate in the procedure in their respective roles .\nthe other benefits of laparoscopy include less post - operative pain , post - operative morbidity , early recovery and return to normal activity with shorter hospital stay .\nthe cosmetic advantage has played a major role in the acceptance of this type of surgery amongst patients .\na developing country like nigeria with a lean health budget and an unresolved primary communicable disease challenge has been slow in joining the trend .\nthere is still a palpable skepticism even among surgeons of the feasibility and relevance of laparoscopy in our environment .\nalbeit pioneering efforts are documented from some parts of the country highlighting the feasibility of this minimal access practice despite immense challenges with a clarion emphasis on local adaptations . to the best of our knowledge ,\nthis is the first documented study from the niger delta region to evaluate laparoscopy as a useful tool for management of common surgical abdominal conditions in a developing country .\nthis is a prospective outcome study of all consecutive surgical patients who had laparoscopic procedures in general and pediatric surgery units of our institution - a regional tertiary health facility , from august 2011 to december 2012 .\npatients were selected after clinical , laboratory and radiological evaluation to exclude significant co - morbidities .\nan american society of anesthesiology class not greater than 2 was an inclusion criterion . in cases of adhesive small bowel obstruction ,\na non - dedicated theatre suite was used with a combination of privately - sourced and hospital equipment . in the absence of a trained endoscopy nurse or technician ,\nresident doctors in the unit were trained by the operating surgeon on equipment handling and disinfection of laparoscopy instruments .\nthere was non - invasive monitoring of temperature , spo2 , blood pressure , respiration , pulse rate and urinary output .\nthere was manual ventilation and no functional capnography . based on surgeon 's preference and presence of previous abdominal scar a closed or open technique\nvisibility was achieved with a 30 10 mm laparoscope mounted on a karl storz ( germany ) or hawk ( china ) single - chip camera unit connected to a video monitor .\nthe light source was from either a karl storz 175w xenon cold light or hawk halogen light sources .\ntwo or three ports were used in the diagnostic laparoscopies and conventional 3-ports ( 10 mm optical and two 5 mm working ports ) were used for laparoscopic appendicectomy .\nthere was random lateralization or centralization of the optical port i.e. 5 mm working ports at either left iliac and supra - pubic or right lumbar and left iliac fossa respectively to compare ergonomic advantage .\ntissue retrieval was routinely carried out using the cannula method and scarcely with an endo - bag .\nthe age range was from 2 to 65 years ( mean : 32.27 17.86 years ) .\nthe surgeries included : six laparoscopic appendicectomies , five diagnostic laparoscopies biopsy , one laparoscopic - assisted orchidopexy , two laparoscopic adhesiolysis for adhesive small bowel obstruction and one trans - abdominal pre - peritoneal hernia repair for adult bilateral inguinal herniorrhaphy [ figure 1 ] .\nthe patients for laparoscopic appendicectomy had an even sex distribution ( male : female 1:1 ) .\nall were successfully completed irrespective of the position of the optical port [ table 1 ] .\nlaparoscopic surgery during study period laparoscopic appendicectomies performed a case of chronic abdominal pains had no pathology observed during diagnostic laparoscopy .\nthe positive findings during the other diagnostic laparoscopies performed are as shown in table 2 .\noperating time was from 40 to 300 min and challenges encountered included power outages , equipment failures and technical difficulties .\noral sips of water was commenced within 24 h and patients discharged by 2 day post - operation except for a case of conversion for an intra - abdominal tumor ( soft - tissue sarcoma ) from uncontrollable bleeding .\nsurgical complications encountered were grade i and ii of the clavien - dindo classification : one wound dehiscence of a 5 mm port site ; two post - operative pyrexia ; one neuropraxia of superficial peroneal nerve and leg edema from pressure effect of stirrup in lithotomy position during evaluation of the pelvis prior to an appendicectomy .\na two - center study from the south - eastern part of the country also had laparoscopic appendicectomy as the most performed procedure .\nthis is probably due to the fact that acute appendicitis is a common abdominal pathology and laparoscopic appendicectomy requires basic laparoscopic skills to execute .\nthe lateralization or centralization of the optical port was observed not to have a significant effect on the outcome of laparoscopic appendectomy in the early career of a laparoscopic surgeon since all cases were successfully completed .\nthere was no laparoscopic cholecystectomy due to a low incidence of gall stone disease in our center .\nthe open hasson port technique is favored by many surgeons in view of less likelihood of visceral and vascular injury , however , the closed access method using the veress needle is safe , fast and efficacious even in children of all ages .\nwe routinely used the closed access method in the absence of previous abdominal surgery ; however following access the working ports were inserted under direct vision .\na two - port laparoscopic and single port laparoscopic appendicectomy are feasible but these have limitations in conditions of extensive adhesion and gangrenous appendix .\nthere was no perforation of viscus , blood vessel injury nor hemodynamic instability resulting from capnoperitoneum peri - operatively .\nthis conversion rate of 6.7% ( n = 1 ) is similar to 4.1% ( n = 1 ) recorded from 24 laparoscopic surgeries performed in a tertiary health facility in nigeria .\ncomparatively , another nigerian study of 145 laparoscopic surgeries recorded a conversion rate of 0.027% ( n = 4 ) .\nsome other challenges encountered during were power outages and lack of trained support staff ( endoscopy nurses and technicians ) .\nthe onus is on the laparoscopic surgeon to acquire an in - depth knowledge of all aspects of the practice from a certified oversea or on - site training to effectively train his support team .\nit is important to note that the operational cost for laparoscopy is not huge after initial set - up i.e. , training of personnel , acquisition of equipment and relevant infrastructure .\ncost reducing measures adopted included : use of reusable instruments , cannula method for tissue retrieval and the choice of extracorporeal knot placement for ligation . these measures though cheap and effective prolong set - up and operating time . in the face of competing theatre usage\nthe practice of laparoscopic surgery in our environment is feasible and safe despite the numerous , but surmountable challenges .\nan institutional will to achieve a routine laparoscopy in a resource - poor setting is achievable with adequately trained surgeons , support staff and necessary infrastructure .",
"role": "user"
},
{
"content": "background : video - laparoscopic surgery has long been practiced in western countries ; however documented practice of this minimal access surgical technique are recently emanating from nigeria . to the best of our knowledge , \n this is the first documented study on laparoscopic surgery from the niger delta region.aim:to evaluate the feasibility of laparoscopy as a useful tool for management of common surgical abdominal conditions in our environment.patients and methods : this was a prospective outcome study of all consecutive surgical patients who had laparoscopic procedures in general and pediatric surgery units of our institution from august 2011 to december 2012 . \n data on patient 's age , gender , indication for surgery , duration of hospital stay and outcome of surgery were collected and analyzed.results:a total of 15 laparoscopic procedures were performed during this study period with age range of 2 - 65 years ; mean : 32.27 17.86 years . \n there were 11 males and four females . \n six laparoscopic appendicectomies , one laparoscopy - assisted orchidopexy , five diagnostic laparoscopy biopsy , one laparoscopic trans - abdominal pre - peritoneal herniorrhaphy for bilateral indirect inguinal hernia and two laparoscopic adhesiolysis for small bowel obstruction were performed . \n all were successfully completed except one conversion ( 6.7% ) for uncontrollable bleeding in an intra - abdominal tumor.conclusion:the practice of laparoscopic surgery in our environment is feasible and safe despite the numerous , but surmountable challenges . \n there is the need for adequate training of the support staff and a dedicated theatre suite .",
"role": "assistant"
}
]
|
science.data_reco_mcq_sc | science.data_reco_mcq_sc.2829 | [
{
"content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: We propose an unsupervised deep hashing method for image retrieval. Different from previous works, our deep hashing method is\n\nKeywords: image retrieval images paragraph-level\n\nDataset Information:\nOxford5k: Oxford5K is the Oxford Buildings Dataset, which contains 5062 images collected from Flickr. It offers a set of 55 queries for 11 landmark buildings, five for each landmark.\nMNIST-8M: MNIST8M is derived from the MNIST dataset by applying random deformations and translations to the dataset.\nCIFAR-10: The CIFAR-10 dataset (Canadian Institute for Advanced Research, 10 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The images are labelled with one of 10 mutually exclusive classes: airplane, automobile (but not truck or pickup truck), bird, cat, deer, dog, frog, horse, ship, and truck (but not pickup truck).\nMVTecAD: MVTec AD is a dataset for benchmarking anomaly detection methods with a focus on industrial inspection. It contains over 5000 high-resolution images divided into fifteen different object and texture categories.\n\nAvailable Datasets: A: Oxford5k B: MNIST-8M C: CIFAR-10 D: MVTecAD",
"role": "user"
},
{
"content": "CIFAR-10",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.4357 | [
{
"content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\n*p<0.05comparedtocorrespondingPGC-1alpha+/+values.",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.mslr2022_cochrane_multidoc_summarization | science.mslr2022_cochrane_multidoc_summarization.2770 | [
{
"content": "Review the provided collection of medical RCT summaries. Your objective is to distill the essential insights into a brief conclusion. Focus solely on the synthesis of findings without additional commentary. The RCT summaries are as follows:\n\n\n\nReport Title 1:\nEffects of exercise on mental and physical health parameters of persons with schizophrenia.\nReport Abstract 1:\nAlthough the benefits of exercise are well documented, few published research studies have examined exercise in persons with schizophrenia. This pilot examined a 16-week walking program for outpatients diagnosed with schizophrenia (N = 10). Six-minute walking distance, body mass index, percent body fat and severity of psychiatric symptoms were measured. Experimental participants in the walking group experienced significant reductions in body fat (p = 0.03) compared to a control group not participating in the exercises during the same time period. Experimental participants also had greater aerobic fitness, lower body mass indexes, and fewer psychiatric symptoms than controls at the conclusion of the program. Research is needed to identify effective exercise interventions and feasible delivery modalities for persons with schizophrenia in community settings.\n\n\nReport Title 2:\nYoga therapy as an add-on treatment in the management of patients with schizophrenia--a randomized controlled trial.\nReport Abstract 2:\nTreatment of schizophrenia has remained unsatisfactory despite the availability of antipsychotics. This study examined the efficacy of yoga therapy (YT) as an add-on treatment to the ongoing antipsychotic treatment.\n Sixty-one moderately ill schizophrenia patients were randomly assigned to YT (n = 31) and physical exercise therapy (PT; n = 30) for 4 months. They were assessed at baseline and 4 months after the start of intervention, by a rater who was blind to their group status.\n Forty-one subjects (YT = 21; PT = 20) were available at the end of 4 months for assessment. Subjects in the YT group had significantly less psychopathology than those in the PT group at the end of 4 months. They also had significantly greater social and occupational functioning and quality of life.\n Both non-pharmacological interventions contribute to reduction in symptoms, with YT having better efficacy.",
"role": "user"
},
{
"content": "Results of this Cochrane review are similar to existing reviews that have examined the health benefits of exercise in this population. Although studies included in this review are small and used various measures of physical and mental health, results indicated that regular exercise programmes are possible in this population, and that they can have healthful effects on both the physical and mental health and well-being of individuals with schizophrenia. Larger randomised studies are required before any definitive conclusions can be drawn.",
"role": "assistant"
}
]
|
science.acl_arc_intent_classification | science.acl_arc_intent_classification.959 | [
{
"content": "Examine the given text from a research paper in the field of NLP. Your task is to identify the role of the citation within the context provided. Focus on understanding the intent behind the citation and classify it accordingly.\n\nSection Title:\nexperiments\n\nText Before Citation:\nThe OntoNotes-5.0 dataset, which is released for the CoNLL-2012 Shared Task (Pradhan et al., 2012), contains 3,145 annotated documents. We use a standard split of 268 training documents, 68 development documents, and 106 testing documents (Culotta et al., 2007; Bengtson and Roth, 2008). Datasets The ACE-2004 dataset contains 443 documents.\n\nCitation Text:\nThe OntoNotes-5 .0 dataset , which is released for the CoNLL-2012 Shared Task ( Pradhan et al. , 2012 ) , contains 3,145 annotated documents .\n\nText After Citation:\nThese documents come from a wide range of sources which include newswire, bible, transcripts, magazines, and web blogs. We report results on the test documents for both datasets. The ACE-2004 dataset is annotated with both mention and mention heads, while the OntoNotes5.0 dataset only has mention annotations. Therefore, we preprocess Ontonote-5.0 to derive mention heads using Collins head rules (Collins, 1999) with gold constituency parsing information and gold named entity information.",
"role": "user"
},
{
"content": "Uses",
"role": "assistant"
}
]
|
science.healthver_entailment | science.healthver_entailment.2673 | [
{
"content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: Smokers seem less likely than non-smokers to fall ill with coronavirus\n\nResearch Abstract:\nObjectives: To investigate whether there is a causal effect of cardiometabolic traits on risk of sepsis and severe covid-19.\nDesign: Mendelian randomisation analysis.\nSetting: UK Biobank and HUNT study population-based cohorts for risk of sepsis, and genome-wide association study summary data for risk of severe covid-19 with respiratory failure.\nParticipants: 12,455 sepsis cases (519,885 controls) and 1,610 severe covid-19 with respiratory failure cases (2,205 controls).\nExposure: Genetic variants that proxy body mass index (BMI), lipid traits, systolic blood pressure, lifetime smoking score, and type 2 diabetes liability - derived from studies considering between 188,577 to 898,130 participants.\nMain outcome measures: Risk of sepsis and severe covid-19 with respiratory failure.\nResults: Higher genetically proxied BMI and lifetime smoking score were associated with increased risk of sepsis in both UK Biobank (BMI: odds ratio 1.38 per standard deviation increase, 95% confidence interval [CI] 1.27 to 1.51; smoking: odds ratio 2.81 per standard deviation increase, 95% CI 2.09-3.79) and HUNT (BMI: 1.41, 95% CI 1.18 to 1.69; smoking: 1.93, 95% CI 1.02-3.64).\nHigher genetically proxied BMI and lifetime smoking score were also associated with increased risk of severe covid-19, although with wider confidence intervals (BMI: 1.75, 95% CI 1.20 to 2.57; smoking: 3.94, 95% CI 1.13 to 13.75).\nThere was limited evidence to support associations of genetically proxied lipid traits, systolic blood pressure or type 2 diabetes liability with risk of sepsis or severe covid-19.\nSimilar findings were generally obtained when using Mendelian randomization methods that are more robust to the inclusion of pleiotropic variants, although the precision of estimates was reduced.\nConclusions: Our findings support a causal effect of elevated BMI and smoking on risk of sepsis and severe covid-19.\nClinical and public health interventions targeting obesity and smoking are likely to reduce sepsis and covid-19 related morbidity, along with the plethora of other health-related outcomes that these traits adversely affect.",
"role": "user"
},
{
"content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"Results: Higher genetically proxied BMI and lifetime smoking score were associated with increased risk of sepsis in both UK Biobank (BMI: odds ratio 1.38 per standard deviation increase, 95% confidence interval [CI] 1.27 to 1.51; smoking: odds ratio 2.81 per standard deviation increase, 95% CI 2.09-3.79) and HUNT (BMI: 1.41, 95% CI 1.18 to 1.69; smoking: 1.93, 95% CI 1.02-3.64).\", \"Conclusions: Our findings support a causal effect of elevated BMI and smoking on risk of sepsis and severe covid-19.\"]}",
"role": "assistant"
}
]
|
science.qasper_extractive_qa | science.qasper_extractive_qa.412.1 | [
{
"content": "Analyze the given research paper excerpts and address the question provided. Extract the necessary information directly from the text. Your answer should be formatted as a JSON object with the following structure:\n\n\"answer\": A list of text segments from the paper that directly respond to the question.\n\"evidence\": A list of text segments from the paper where the answer can be found.\n\nIf the question cannot be answered with the given text, return \"null\".\n\nDocument: Effectiveness of Data-Driven Induction of Semantic Spaces and Traditional Classifiers for Sarcasm Detection\n\nIrony and sarcasm are two complex linguistic phenomena that are widely used in everyday language and especially over the social media, but they represent two serious issues for automated text understanding. Many labelled corpora have been extracted from several sources to accomplish this task, and it seems that sarcasm is conveyed in different ways for different domains. Nonetheless, very little work has been done for comparing different methods among the available corpora. Furthermore, usually, each author collects and uses its own dataset to evaluate his own method. In this paper, we show that sarcasm detection can be tackled by applying classical machine learning algorithms to input texts sub-symbolically represented in a Latent Semantic space. The main consequence is that our studies establish both reference datasets and baselines for the sarcasm detection problem that could serve to the scientific community to test newly proposed methods.\n\nIntroduction\nAffective computing has raised a great deal of interest in the last years. Picard picard1995affective introduced it as a computing paradigm that relates to, arises from, or influences emotions, letting computers be both more effective in assisting humans and successful in making decisions.\nLanguage, as a conceptual process, plays a key role in the perception of verbal irony and sarcasm, two well-known forms of figurative language (FL) BIBREF0 Traditionally, irony as a figure of speech can be intended as “saying something while meaning something else” BIBREF1 . A comprehensive overview of different theories of irony has been illustrated in Attardo attardo07. Understanding if irony and sarcasm are the same linguistic phenomenon or not is still an unresolved question in literature BIBREF2 . Some authors consider irony a more general form of sarcasm, while others tend to consider it a separate linguistic issue BIBREF3 , BIBREF4 . According to the theory of sarcastic irony, sarcasm and irony are very similar, but sarcasm has a specific victim who is the object of the sarcastic statement, while irony does not have such a target BIBREF5 . More commonly, the noun “sarcasm” is understood as “saying the opposite of what one is thinking”, usually with a negative intention. Henceforth, due to the different nuances of irony and sarcasm, and the multiple interpretations of these two concepts, we do not differentiate between them, and, like many researchers, e.g., BIBREF6 , we will use the term “sarcasm” to refer to both verbal irony and sarcasm.\nA sarcastic sentence may include features that characterize a positive sentiment, but that insinuates a negative sentiment BIBREF7 , BIBREF8 . It is clear that sarcastic sentences are more difficult to process by an algorithm than non-sarcastic assertions; as a matter of fact, both the situation and the mental state of the speaker are factors that can determine a sarcastic content in a sentence.\nA system capable of detecting sarcasm correctly would greatly improve the performance of sentiment analysis systems BIBREF9 , BIBREF10 , BIBREF6 , BIBREF11 , especially considering the big data available nowadays due to the exponential growth of social platforms. Unfortunately, sarcasm detection in written texts is a difficult task even for humans BIBREF12 .\nMoreover, some people usually do not understand sarcasm, and there are sentences meant as being sarcastic by the author that are not recognized as such by the readers.\nWe focus our attention on the possibility of detecting sarcastic sentences automatically from written text only, and from the reader's point of view. Managing this task without any knowledge of relevant contextual features, like prosody, is very hard.\nThe problem of sarcasm detection has been tackled with machine learning approaches, made possible by the availability of several annotated corpora. In the literature we can find two main categories of such corpora: automatically annotated and manually annotated.\nThe automatically annotated corpora are usually collected from the microblogging platform Twitter BIBREF13 , BIBREF14 by exploiting the final hashtag of tweets. For instance, a tweet is labeled as sarcastic only if it ends with a hashtag such as #sarcasm or #irony. The same cue is used in Davidov, Tsur and Rappoport davidov2010semi to produce a silver standard for evaluating their model.\nManually annotated corpora are collected from a more diversified range of social media, such as Amazon reviews BIBREF15 , Reddit (Wallace et al. 2014) or online forums BIBREF16 , BIBREF17 , and then labeled by hiring people in the Amazon Mechanical Turk portal. When using crowdsourcing, the annotation procedures are complex and involve, among others, a stage for ensuring that the workers understood the task and they are performing correctly, and a quality assurance stage for removing texts for which a high discrepancy between the annotators arises.\nIn this work we have tackled the problem of sarcasm detection by trying to use an entirely data-driven approach, exploiting a distributional semantics representation by inducing a semantic space and then applying a set of classifiers to classify the texts as being sarcastic or not sarcastic. With “fully data-driven” we mean approaches that are capable of finding connections between input text and class labels without using any a priori knowledge about the features that characterize a sarcastic statement.\nIn particular, we do not define “irony” or “sarcasm”, neither use any definition. We simply rely on sets of sentences binary labeled for sarcasm detection taking for granted that the labels correctly identify a sarcastic sentence.\nIt is worthwhile to point out that in this work we do not create any dataset: we simply exploit the labels of datasets that have already been produced by others, trying to give a baseline for the sarcasm detection task.\nThe contribution of this work can be summed up in three key points:\nTo reach these goals, we exploit a Distributional Semantics approach, whose aim is to give a representation of words in a continuous vector space BIBREF18 , BIBREF19 , where word similarity is coded in an unsupervised manner. This representation is useful for building models with little, or no, a-priori knowledge about the task BIBREF20 .\nDistributional semantics is a research field that concerns methodologies aimed at determining semantic similarities between linguistic items. The key idea is based on the hypothesis that words co-occurring in similar contexts tend to have similar meaning BIBREF21 , BIBREF22 . Distributional semantics deals with the automatic construction of semantic models induced from large unstructured textual corpora, and it exploits vector space models to represent the meaning of a word BIBREF23 . Many methods can be applied to construct distributional models. They range from the statistical models to machine learning ones BIBREF24 , BIBREF19 , BIBREF25 , BIBREF26 . Among these techniques, Latent Semantic Analysis (LSA) is a methodology for building distributional semantic spaces that extract statistical relations between words which co-occurr in a given context though the use of the Truncated Singular value decomposition (T-SVD). In this work we explored and studied the possibility of building a data-driven model in the field of sarcasm detection exploiting the well-known Latent Semantic Analysis (LSA) paradigm both in its traditional formulation given by Landauer, Foltz and Laham landauer1998introduction and by using the Truncated Singular Value Decomposition (T-SVD) as a statistical estimator as illustrated in Pilato and Vassallo pilato2015tsvd.\nBoth approaches have been used to create data-driven semantic spaces where documents and, generally, text chunks can be mapped.\nThe theory behind LSA states that the “psychological similarity between any two words is reflected in the way they co-occur in small sub-samples of language” (Landauer et al. 1998).\nWe have chosen to exploit the LSA paradigm since it is a well-known distributional semantics paradigm capable of modeling many human cognitive abilities; furthermore, it has many potential practical applications BIBREF27 , BIBREF18 , BIBREF28 , BIBREF29 . Moreover, it has been demonstrated in Pilato and Vassallo pilato2015tsvd that Truncated Singular Value Decomposition (T-SVD), as used in LSA, can be interpreted as a statistical estimator, giving a robust theoretical interpretation to the Latent Semantic Analysis paradigm. Many researchers have successfully applied this technique for typical Semantic Computing applications, such as natural language understanding, cognitive modeling, speech recognition, smart indexing, anti-spam filters, dialogue systems, and other Statistical Natural Language processing problems BIBREF30 , BIBREF31 , BIBREF32 . Moreover, Latent Semantic Analysis has been successfully used for inducing data-driven “conceptual” spaces BIBREF33 . For the aforementioned reasons, we have chosen this approach as a baseline for the detection of sarcasm in texts.\nFurthermore, our study makes use of four machine learning methods that have been used on four manually annotated, publicly available corpora.\nThe experimental results show that our data-driven approach consisting of LSA followed by a classifier can establish models that outperform the published results on two of the corpora; additionally, it produces competitive results for the other corpora that we used for our evaluation.\nThe next section describes the state of the art in the field, Section SECREF3 describes the Semantic Representation and the Machine Learning methods used in the study. Section SECREF4 introduces the datasets used for the experiments. Section SECREF5 summarizes the experimental results, Section SECREF6 is for the final conclusions and remarks.\nThe code and the datasets used for the experiments are available on github.\n\nExperimental setup\nWe ran three groups of experiments, to assess both the effectiveness of our approach when compared with the approaches we found in literature and its capability of extracting features that are relevant for sarcasm in a cross-domain scenario. In both cases, we denote with the word model one of the possible combinations of classic/statistical LSA and a classifier. The used classifiers are Support Vector Machine (SVM), Logistic regression (Log.Reg), Random Forest (RF) and gradient boosting (XGB).\nFor the first group of experiments, we evaluated the performance of each of our models in every corpus. We use 10-fold cross-validation and report the mean values of INLINEFORM0 -score, precision, and recall among all the folds. The proportion of the two classes in each fold is equal to the proportion in the whole corpus. Where applicable, we compare our results with existing results in the literature. Besides, we compare with the method presented in Poira et al. cambria2016.\nThe second group of experiments has been performed on the Semeval 2018 Task 3 dataset (Van Hee et al. 2018). We first find the best LSA dimensionality by 10-fold cross-validation in the training set. Then, we trained again the models in the whole dataset and evaluated them in the test set for comparison with the participants to the shared task.\nThe third group of experiments is inter-corpora. For each experiment, we have chosen one corpus as a training set and another one as a test set. This process is performed for all the models and all the corpora pairs. We aim to find whether sarcasm detection is domain-dependent.\nFinally, in the fourth group of experiments (union experiments) we perform another 10-fold in which all the corpora are concatenated. Each fold contains samples from every corpus proportionally to the size of that corpus. The goal of this experiment is to understand whether simply adding more data, but from different domains, improves the classification performance.\nThe hyperparameters of the classifiers have been chosen by grid search on SarcasmCorpus with LSA dimensionality 40, and then used for all the reported experiments. We use SVM with Gaussian kernel, C value of 100, INLINEFORM0 logistic regression with penalty L1 and C=10 and decision tree with entropy loss. SVM and logistic regression both have balanced class weights to cope with unbalanced datasets.\n\nUnion Experiments\nThe last group of experiments we ran has the goal of understanding whether the combination of data coming from different sources can influence positively the final score. For this purpose, as anticipated in Section SECREF51 , we computed 10-folds of each of the four corpora used for the first group of experiments, and used as a training set the concatenation of 9 folds of every corpus, and as a validation set the remaining single folds of each corpus.\nFrom Tables TABREF64 , TABREF65 we can observe that these results are not higher overall with respect to the inter-corpora results. The only exceptions are SarcasmCorpus, where the results are almost 20 F-score points higher than those obtained in the inter-corpora; and IAC-v2, where the gradient boosting (XGB) obtains 2 F-score points more than the top score in the inter-corpora results.\nThe results on SarcasmCorpus are still lower than the in-corpus results, and the scores of random forest and gradient boosting are much lower than the other two methods. This is further evidence that adding diverse data is not helpful, or is actually harmful, for classifying SarcasmCorpus.\nThe general trend of this block of experiments is that our classifiers are not able to leverage data from different domains in order to improve global results. In-domain data represent the best choice even if the data amount is lower.\n\nConclusions\nIn this work, we have tackled the problem of automatic sarcasm detection from a data-driven point of view. More in details, we have used a set of labeled dataset and applied distributional semantics followed by some machine learning approaches in order to give a baseline for the literature in managing such a problem. We do not differentiate between sarcasm and irony because they are not so easily distinguishable even for human experts. Experiments have been carried out on four different corpora containing texts from online reviews or forums, and the corpus used for the shared task on irony detection on Twitter proposed in SemEval 2018. We have shown experimentally that some basic methods can outperform in all the datasets other methods based on bag of words and linguistic features, thus representing a solid baseline. With our experiments that train the models with one corpus and test them by using the other corpora, we have confirmed experimentally that also the annotators tend to not distinguish the distinction between irony and sarcasm. By contrast, major differences can be found according to the text domains, i.e., review vs. political forum. The domain difference can also prevent the method from taking benefits from more data when they are too diverse from the test data. As a future work, we will try to improve distributional semantics approaches with linguistic features in order to perform more fair comparisons with more recent and advanced methods. Furthermore, we will exploit more classical AI methodologies (e.g., by using ontologies, reasoners, common-sense reasoning techniques, etc.) to deduce the context, understanding the concepts expressed in a sentence, exploiting also features like hashtags and emojis to improve the overall performance of the approach.\n\nFig. 1. Accuracy and F-score values of all the considered classifiers for different LSA size in the case of Sarcasm Corpus\n\nFig. 5. Accuracy and F-score values of all the considered classifiers for different LSA size in the case of IAC-Sarcastic-v2-HYP Corpus\n\nInquiry: What are the different methods used for different corpora?",
"role": "user"
},
{
"content": "{\"answer\": [\"Support Vector Machine (SVM), Logistic regression (Log.Reg), Random Forest (RF) and gradient boosting (XGB)\"], \"evidence\": [\"We ran three groups of experiments, to assess both the effectiveness of our approach when compared with the approaches we found in literature and its capability of extracting features that are relevant for sarcasm in a cross-domain scenario. In both cases, we denote with the word model one of the possible combinations of classic/statistical LSA and a classifier. The used classifiers are Support Vector Machine (SVM), Logistic regression (Log.Reg), Random Forest (RF) and gradient boosting (XGB).\", \"For the first group of experiments, we evaluated the performance of each of our models in every corpus. We use 10-fold cross-validation and report the mean values of INLINEFORM0 -score, precision, and recall among all the folds. The proportion of the two classes in each fold is equal to the proportion in the whole corpus. Where applicable, we compare our results with existing results in the literature. Besides, we compare with the method presented in Poira et al. cambria2016.\"]}",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_elife_single_doc_summ | science.scientific_lay_summarisation_elife_single_doc_summ.1197 | [
{
"content": "Transform the provided sections of a biomedical research paper into a digestible summary for a general audience. Focus on simplifying complex ideas while retaining key scientific insights.\n\nResearch Title: Rapamycin rejuvenates oral health in aging mice\nContent Overview:\nAbstract:\nPeriodontal disease is an age-associated disorder clinically defined by periodontal bone loss, inflammation of the specialized tissues that surround and support the tooth, and microbiome dysbiosis. Currently, there is no therapy for reversing periodontal disease, and treatment is generally restricted to preventive measures or tooth extraction. The FDA-approved drug rapamycin slows aging and extends lifespan in multiple organisms, including mice. Here, we demonstrate that short-term treatment with rapamycin rejuvenates the aged oral cavity of elderly mice, including regeneration of periodontal bone, attenuation of gingival and periodontal bone inflammation, and revertive shift of the oral microbiome toward a more youthful composition. This provides a geroscience strategy to potentially rejuvenate oral health and reverse periodontal disease in the elderly.\nIntroduction:\nOld age is associated with failure to maintain homeostasis resulting in degradation of cellular maintenance and repair processes( López-Otín et al., 2013) and is the single greatest risk factor for many human diseases including cardiovascular disorders, dementias, diabetes, and most cancers( Kennedy et al., 2014). Interventions that target specific aging hallmarks have been shown to delay or prevent age-related disorders and extend lifespan in model organisms( Kaeberlein et al., 2015). Rapamycin, an FDA-approved drug, which directly inhibits the mechanistic target of rapamycin complex I( mTORC1), is one such intervention that extends lifespan and ameliorates a variety of age-related phenotypes( Johnson et al., 2013). In mice, rapamycin extends lifespan when administered beginning at 9 or 20 months of age( Harrison et al., 2009), and short-term treatments ranging from 6 to 12 weeks during adulthood have been shown to increase lifespan( Bitto et al., 2016), improve cardiac function( Flynn et al., 2013; Dai et al., 2014) and restore immune function as measured by vaccine response( Chen et al., 2009). Initial indications suggest that mTORC1 inhibition may also reverse declines in age-related heart function in companion dogs( Urfer et al., 2017a; Urfer et al., 2017b), and age-related immune function( Mannick et al., 2014; Mannick et al., 2018) and skin aging( Chung et al., 2019) in humans. Periodontal disease is clinically defined by inflammation of the periodontium, the specialized tissue surrounding and supporting the tooth structure, resulting in clinical attachment loss, alveolar( periodontal) bone loss and periodontal pocketing, and pathogenic changes in the oral microbiome( Könönen et al., 2019; Lang and Bartold, 2018). Most recent epidemiologic data in the U. S. population suggests that more than 60% of adults aged 65 years and older have periodontitis( Eke et al., 2012; Eke et al., 2015), and diagnosis with periodontal disease is associated with increased risk for other age-related conditions including heart disease, diabetes, and Alzheimer’s disease( Gil-Montoya et al., 2015; Kim and Amar, 2006; Razak et al., 2014). Given that periodontal disease shows a similar age-related risk profile as other age-associated diseases( An et al., 2018), we predicted that interventions which target biological aging could be effective at treating periodontal disease. Consistent with that hypothesis, aged mice treated with rapamycin have greater levels of periodontal bone than control animals( An et al., 2017). In order to further test this idea and to understand potential mechanisms by which mTOR activity influences oral health during aging, we carried out a longitudinal study in which we asked whether transient rapamycin treatment during middle age can impact three clinically defining features of periodontal disease: loss of periodontal bone, inflammation of periodontal tissues, and pathogenic changes to the microbiome. Here we report that 8 weeks of treatment with rapamycin in aged mice is sufficient to regrow periodontal bone, reduce inflammation in both gingival tissue and periodontal bone, and revert the composition of the oral microbiome back toward a more youthful state.\nDiscussion:\nTaken together, our data demonstrate that a short-term treatment with rapamycin in aged mice is sufficient to reverse three clinically defining features of periodontal disease: periodontal bone loss, periodontal inflammation, and pathogenic changes to the oral microbiome. This adds further support for the Geroscience Hypothesis, which posits that any intervention which targets the biological aging process will simultaneously delay multiple age-related diseases and functional declines( Kaeberlein, 2017; Sierra and Kohanski, 2017). To the best of our knowledge, this is the first report of rejuvenation in the aged oral cavity. This work suggests several interesting questions that it will be important to evaluate in future studies. One such question is whether the effects of rapamycin on the aged periodontium will persist after the treatment period or will rapidly revert back to the aged state. Improvements in age-related cardiac function associated with a similar rapamycin treatment regimen have been found to persist for at least eight weeks following cessation of treatment( Quarles et al., 2020), and it will be of interest to determine whether similar outcomes are observed for improvements in oral health. It will also be important in future studies to determine whether these effects are mediated through local inhibition of mTORC1 in the gingiva and periodontal bone or through systemic effects on immune function or other tissues. Likewise, it will be of interest to understand whether additional features of oral health that are known to decline with age, such as salivary function, are improved by rapamycin treatment. Finally, these results suggest the intriguing likelihood that additional geroscience interventions, such clearance of senescent cells, may phenocopy the effects of rapamycin in this context. Such interventions could pave the way for the first effective treatments to reverse periodontal disease and improve oral health in the elderly.",
"role": "user"
},
{
"content": "Age is the single greatest risk factor for many human diseases , including cancer , heart disease , and dementia . This is because , as the body ages , it becomes less able to repair itself . One way to prevent age-related disease and extend lifespan , at least in laboratory animals , is to use a drug called rapamycin . Mice treated with rapamycin live longer , have stronger hearts , and respond better to vaccination . But , despite these promising observations , the use of rapamycin as an anti-aging treatment is still under investigation . One open question is what age-related diseases rapamycin can help to prevent or treat . In the United States , more than 60% of adults over the age of 65 have gum disease . These people are also more likely to have other age-related diseases , like heart disease or Alzheimer's . This association between gum problems and other age-related diseases prompted An et al . to ask whether it might be possible to treat gum disease by targeting aging . To find out whether rapamycin could improve gum health , An et al . performed three-dimensional CT scans on mice as they aged to measure the bone around the teeth . Some of mice were treated with rapamycin , while the rest received a placebo . The mice that received the placebo started to show signs of gum disease as they aged , including inflammation and loss of bone around the teeth . The types of bacteria in their mouths also changed as they aged . Treating mice with rapamycin not only delayed the onset of these symptoms , but actually reversed them . After eight-weeks of the drug , the older mice had lost less bone and showed fewer signs of inflammation . There was also a shift in their mouth bacteria , restoring the balance of species back to those found in younger mice . Rapamycin is already approved for use in people , so a clinical trial could reveal whether it has the same effects on gum health in humans as it does in mice . But there are still unanswered questions about how rapamycin affects the mouth as it ages . These include how the drug works at a molecular level , and how long the changes to gum health persist after treatment stops .",
"role": "assistant"
}
]
|
science.scientific_papers_summarization_single_doc_pubmed | science.scientific_papers_summarization_single_doc_pubmed.3588 | [
{
"content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nduring january august 2013 , we collected rodents and shrews in jiaonan county , shandong province , china ( 1193012030e , 35353608 n ) .\nthe animals were trapped once a month by using mouse traps baited with peanuts ; a different trap site was used each month .\nthe traps were set before sunset outside human dwellings in rural areas and collected the next morning .\nwe classified the rodents and shrews according to appearance ( hair color ) and body structures ( i.e. , shape of mouth , teeth , tail , ratio of tail length to body length , cheek pouch ) .\nafter the animals were euthanized , we collected blood samples from their hearts onto absorbent paper strips ( 10 mm 30 mm ) .\nanimal use and sample collection protocols were approved by the bioethics committee of the school of public health , shandong university . before testing the serum samples for the presence of sftsv\n, we evaluated the sensitivity and specificity of a double - antigen sandwich elisa kit ( wuxi xinlianxin biotech co , wuxi city , china ) for detecting sftsv in rodent serum . to do this\n, we used an indirect immunofluorescence assay ( ifa ) as a standard to test rodent serum samples for sftsv and compared the results with those from the elisa .\na total of 68 kunming albino mice ( shandong university experimental animal center , jinan , china ) were used for the tests : 36 were injected with sftsv , and 32 ( controls ) were injected intraperitoneally with saline solution . on days 7 , 12 , 17 , and 21 after injection , 9 infected and 8 control mice were euthanized , and serum samples from the mice were tested for sftsv antibody by ifa and elisa .\nof the 36 serum samples from the sftsv - inoculated mice , 33 were positive for sftsv by ifa and elisa and 3 were positive by ifa only .\nall 32 serum samples from the control mice were negative for sftsv by ifa and elisa .\nthus , under these laboratory conditions and compared with the ifa , the elisa had a sensitivity of 91.7% and specificity of 100% , suggesting that the elisa could be used to test serum samples from the field - collected rodents .\nkits for shrews were not commercially available in china , so we were unable to test the sensitivity and specificity of the elisa for detecting sftsv in serum from shrews .\nwe collected 89 asian house shrews ( suncus murinus ) and 666 rodents in the field during january \nthe rodents included 186 striped field mice ( apodemus agrarius ) , 182 house mice ( mus musculus ) , 156 brown rats ( rattus norvegicus ) , 125 greater long - tailed hamsters ( cricetulus tyiton ) , and 17 chinese hamsters ( cricetulus barabensis ) .\nserum samples from the rodents and shrews were tested for igg and igm to sftsv by using the elisa as described previously ( 810 ) .\nserum samples on absorbent paper were each reconstituted by adding 150 l of phosphate - buffered saline , and 75 l of each sample was added to a well of the elisa plate .\nelisa results showed that sftsv seroprevalence was higher among asian house shrews ( 4.5% , 4/89 ) than among rodents ( 0.9% , 6/666 ) ( p = 0.014 ) . among the rodents , sftsv seropositivity was higher in house mice ( 1.1% , 2/182 ) and striped field mice ( 1.1% , 2/186 ) than in other rodent species ( table ) .\nhowever , the seropositivity rate was not significantly different among the rodent species ( p = 0.691 ) .\nin addition , the seropositivity rate did not differ significantly by month ( p = 0.411 ) .\ntotal rna was extracted from homogenized animal spleens by using the rneasy mini kit ( qiagen , hilden , germany ) , which was used as a template for sftsv amplification performed by using the access rt - pcr system ( promega , madison , wi , usa ) .\nprimers for reverse transcription pcr ( rt - pcr ) were designed from the m segments of the sftsv genome .\noutside pcr primers were 5-tctgcagttcagactcaggga-3 and 5-gacgtgtattgctgttttccc-3 ; nested pcr primers were 5-tgttgcttgtcagcctatgac-3 and 5-caaccaatgatcctgagtgga-3. the pcr products ( 674 bp ) were cloned and sequenced for both strands at least 3 times .\namplification results showed that the sftsv positivity rate was higher among shrews ( 2.6% , 2/77 ) than among rodents ( 0.7% , 3/440 ) , but the difference was not significant ( p = 0.162 ) ( table ) .\nthe pcr positivity rate differed by month : the rate was 4.7% ( 4/86 ) for animals trapped in march , 1.6% ( 1/62 ) for animals trapped in june , and 0 for animals collected during the other 6 months ( p = 0.043 ) .\nphylogenetic analysis indicated that the sftsv sequences from the rodents and shrews were closely related to each other ( 98.5% 99.7% homology ) and highly homologous ( 95.3% to 99.7% ) to the corresponding sequences of sftsv from a human ( genbank accession no .\njf267784 ) , and ticks ( genbank accession nos . kc473541 and jq684872 ) ( figure ) .\nphylogenetic analysis of severe fever with thrombocytopenia syndrome virus ( sftsv ) amplified from the spleens of asian house shrew and rodents .\nthe neighbor - joining phylogenetic tree was constructed by using mega 5.2 software(http://www.megasoftware.net/).genbank accession numbers precede isolate names on the right side of the figure .\ntwo previous studies demonstrated that rodents in china were seronegative for sftsv ( 7,12 ) .\nhowever , negative results might have been caused by small sample sizes or by using rodents that were collected from sites where sftsv was not endemic .\nthe serologic and rt - pcr results in our study show that rodents and shrews in eastern china are seropositive for sftsv .\nwe also attempted to amplify s segments of the genomes of sftsv isolates , but results were positive for only 1 animal .\nit is possible that in our study , the primer for the s segment was not as sensitive as that for the m segment .\nmost animal species that have been investigated for the presence of sftsv have been positive for the virus , including rodents , shrews , goats , cattle , dogs , and chickens ( 5,810 ) .\ngoats have usually shown high seroprevalence to sftsv but very low virus loads and short periods of sftsv viremia ( 9 ) .\nrodents experimentally infected with sftsv usually have long periods of viremia and high virus loads in the blood ( 13,14 ) .\ncross - sectional analysis indicated that the sftsv infection rate among rodents and shrews did not differ substantially by month during the 8-month study period , but the pcr positivity rate was highest for animals collected during march .\nthe variation between months can probably be explained by the fact that the animals were collected from different sites each month ; the rates of infection among animals at the different sites may have differed . in conclusion ,\nour findings show that the asian house shrew and different varieties of rodents are potential animal hosts of sftsv .\nfurther studies are needed to determine which of the many animal hosts of sftsv can most effectively transmit the virus to ticks , the probable vector of sftsv transmission to humans .",
"role": "user"
},
{
"content": "to evaluate the role of small mammals as hosts of severe fever with thrombocytopenia syndrome virus ( sftsv ) , we tested serum samples from rodents and shrews in china , collected in 2013 . \n sftsv antibodies and rna were detected , suggesting that rodents and shrews might be hosts for sftsv .",
"role": "assistant"
}
]
|
science.bioasq_yesno_qa | science.bioasq_yesno_qa.1090 | [
{
"content": "Examine the provided biomedical text and determine the answer to the question. Your response should be either \"yes\" or \"no\" based on the information given.\n\nQuestion: Is MIS-C or Multisystem Inflammatory syndrome in children a complication of Covid-19?\n\nText: Much remains unknown about the risk factors, pathogenesis, prognosis, and specific therapy for this emerging manifestation of COVID-19 known as Multisystem Inflammatory Syndrome in Children (MIS-C).\nMultisystem Inflammatory Syndrome in Children During the Coronavirus 2019 Pandemic: A Case Series\nCOVID-19 and Multisystem Inflammatory Syndrome in Latin American Children\nThis study aims to assess COVID-19 and Multisystem Inflammatory Syndrome (MIS-C) in Latin American children,\nA complication is the rare multisystem inflammatory syndrome in children (MIS-C) associated with COVID-19, presenting 4-6 weeks after infection as high fever, organ dysfunction, and strongly elevated markers of inflammation.\nWe apply systems-level analyses of blood immune cells, cytokines, and autoantibodies in healthy children, children with Kawasaki disease enrolled prior to COVID-19, children infected with SARS-CoV-2, and children presenting with MIS-C. We find that the inflammatory response in MIS-C differs from the cytokine storm of severe acute COVID-19, shares several features with Kawasaki disease, but also differs from this condition with respect to T cell subsets, interleukin (IL)-17A, and biomarkers associated with arterial damage.\nOBJECTIVE: Multisystem inflammatory syndrome in children (MIS-C) associated with coronavirus disease (COVID-19) is a rare and challenging diagnosis requiring early treatment.\nThis syndrome is now known as either \"Pediatric Inflammatory Multisystem Syndrome temporally related with COVID-19\" (PIMS-TS) (1), or Multisystem Inflammatory Syndrome in Children (MIS-C) (2) and is currently considered a rare post-COVID-19 complication which, in a minority of cases, can lead to death.\nMultisystem Inflammatory Syndrome in Children (MIS-C) associated with Coronavirus Disease 2019 (COVID-19) is a newly recognized condition in which children with recent SARS-CoV-2 infection present with a constellation of symptoms including hypotension, multiorgan involvement, and elevated inflammatory markers. Thes\nBackground: Kawasaki-like syndrome occurring in children during the COVID-19 pandemic has been labelled multisystem inflammatory syndrome in children (MIS-C) by the CDC and paediatric inflammatory multisystem syndrome temporally associated with SARS-CoV-2 infection (PIMS-TS) by\nem inflammatory syndrome in children (MIS-C), a possible complication of COVID-19, has been described as a hyperinflammatory condition with multiorgan involvement similar to that in Kawasaki disease or toxic shock syndrome in children with evidence of SARS-CoV-2 infection. This revie\nBACKGROUND: A small subset of pediatric patients develop a rare syndrome associated with Coronavirus Disease 2019 (COVID-19) infection called multisystem inflammatory syndrome in childr\nadults. However, the newly described multisystem inflammatory syndrome in children (MIS-C) associated with coronavirus disease 2019 (COVID-19) has been associated with cardiac complicat\nBACKGROUND: Multisystem inflammatory syndrome temporally associated with COVID-19 (MIS-C) has been described as a novel and often severe presentation of SARS-CoV-2 infection i\nOBJECTIVE: Multisystem inflammatory syndrome in children (MIS-C) associated with coronavirus disease (COVID-19) is a rare and challenging diagnosis requiring early tr\nBackground: Multisystem inflammatory syndrome in children (MIS-C), also known as pediatric inflammatory multisystem syndrome, is a new dangerous childhood disease that is temporally associated with coronavirus disease 2019 (\nRecent COVID-19 publications describe a variety of clinical presentations including an asymptomatic state, pneumonia, a hemophagocytic lymphohistiocytosis like syndrome, Multisystem Inflammatory Syndrome in Children (MIS-C) but, also called Pediatric Inflammatory Multisystem Syndrome-Toxic Shock (PIMS-TS), Kawasaki Disease, and myocarditis.\nWe analyzed peripheral blood immune responses in hospitalized SARS-CoV-2 infected pediatric patients (pediatric COVID-19) and patients with MIS-C. MIS-C patients had patterns of T cell-biased lymphopenia and T cell activation similar to severely ill adults, and all patients with MIS-C had SARS-CoV-2 spike-specific antibodies at admission.\nMultisystem inflammatory syndrome in children (MIS-C), a possible complication of COVID-19, has been described as a hyperinflammatory condition with multiorgan involvement similar to that in Kawasaki disease or toxic shock syndrome in children with evidence of SARS-CoV-2 infection.\nIt includes a discussion of multisystem inflammatory syndrome in children (MIS-C) associated with COVID-19, as well as other aspects of the COVID-19 pandemic that are affecting children and families, such as poisonings, childhood immunizations, mental health, nonaccidental trauma, and neglect.\nImportance: To date, no study has characterized the mucocutaneous features seen in hospitalized children with multisystem inflammatory syndrome in children (MIS-C) or the temporal association of these findings with the onset of systemic symptoms.Objective: To describe the mucocutaneous findings seen in children with MIS-C during the height of the coronavirus disease 2019 (COVID-19) pandemic in New York City in 2020.Design, Setting, and Participants: A retrospective case series was conducted of 35 children admitted to 2 hospitals in New York City between April 1 and July 14, 2020, who met Centers for Disease Control and Prevention and/or epidemiologic criteria for MIS-C.Main Outcomes and Measures: Laboratory and clinical characteristics, with emphasis on mucocutaneous findings, of children who met criteria for MIS-C.\nThis condition, since defined as the multisystem inflammatory syndrome in children (MIS-C), is assumed to be a delayed immune response to coronavirus disease 2019 (COVID-19), and there are frequently cardiac manifestations of ventricular dysfunction and/or coronary artery dilation.Methods: We surveyed the inpatient MIS-C management approaches of the members of the International Kawasaki Disease Registry across 38 institutions and 11 countries.Results: Among the respondents, 56% reported using immunomodulatory treatment for all MIS-C patients, regardless of presentation.\nDESIGN: Children ages 0-22 years with suspected severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection presenting to urgent care clinics or being hospitalized for confirmed/suspected SARS-CoV-2 infection or multisystem inflammatory syndrome in children (MIS-C) at Massachusetts General Hospital were offered enrollment in the Massachusetts General Hospital Pediatric COVID-19 Biorepository.\nWe recently discovered a superantigen-like motif, similar to Staphylococcal enterotoxin B (SEB), near the S1/S2 cleavage site of SARS-CoV-2 Spike protein, which might explain the multisystem-inflammatory syndrome (MIS-C) observed in children and cytokine storm in severe COVID-19 patients.\nMETHODS: An extensive search strategy was conducted by combining the terms multisystem inflammatory syndrome in children and coronavirus infection or using the term multisystem inflammatory syndrome in children in bibliographic electronic databases (PubMed, EMBASE, and CINAHL) and in preprint servers (BioRxiv.org and MedRxiv.org) following the Preferred Reporting Items for Systematic Reviews and Metaanalyses guidelines to retrieve all articles published from January 1, 2020, to July 31, 2020.\nHere, we show that pediatric patients with multisystem inflammatory syndrome in children (MIS-C) possess higher SARS-CoV-2 spike IgG titers compared to those with severe coronavirus disease 2019 (COVID-19), likely reflecting a longer time since onset of infection in MIS-C patients.\nHere, we show that pediatric patients with multisystem inflammatory syndrome in children (MIS-C) possess higher SARS-CoV-2 spike IgG titers compared to those with severe coronavirus disease 2019 (COVID-19), likely reflecting a longer time since onset of infection in MIS-C patients.\nMultisystem inflammatory syndrome in children (MIS-C) is a life-threatening post-infectious complication occurring unpredictably weeks after mild or asymptomatic SARS-CoV2 infection in otherwise healthy children.\nData on multisystem inflammatory syndrome in children (MIS-C) related to coronavirus disease-19 (COVID-19) is increasing in the current COVID-19 pandemic.\nIntroduction Multisystem inflammatory syndrome in children (MIS-C) is a unique clinical complication of SARS-CoV-2 infection observed in pediatric patients.\nNew onset diabetes with diabetic ketoacidosis in a child with multisystem inflammatory syndrome due to COVID-19.\nCase presentation An eight-year-old female presented with hyperglycemia, ketosis and metabolic acidosis consistent with diabetic ketoacidosis (DKA) in the setting of fever, rash, respiratory distress, hemodynamic instability, reduced systolic function with dilation of the left anterior descending artery, and positive SARS-CoV-2 antibodies suggestive of MIS-C.\nHowever, the newly described multisystem inflammatory syndrome in children (MIS-C) associated with coronavirus disease 2019 (COVID-19) has been associated with cardiac complications.M\nToxic shock-like syndrome and COVID-19: Multisystem inflammatory syndrome in children (MIS-C).\nMany of these cases feature a toxic shock-like syndrome or Kawasaki-like syndrome in the setting of SARS-CoV-2 positive diagnostic testing and the CDC has termed this presentation Multisystem Inflammatory Syndrome (MIS-C).\nWe describe a case of MIS-C in a child who presented to our Emergency Department (ED) twice and on the second visit was found to have signs of distributive shock, multi-organ injury and systemic inflammation associated with COVID-19.\nPURPOSE OF REVIEW: Here we summarize current knowledge about multisystem inflammatory syndrome in children (MIS-C), a presumed postinfectious inflammatory condition that has emerged as an important COVID-19-associated complication, to help clinicians identify and manage cases.RECENT FINDINGS: Clinical presentation of MIS-C is do\nMIS-C is a rare yet severe and highly critical complication of COVID-19 infection in pediatrics, leading to serious and life-threatening illnesses.\nBACKGROUND: A multisystem inflammatory syndrome in children associated with COVID-19 (MIS-C) has recently been described.OBJECTIVE: To evaluate imaging findings of MIS-C associated with COVID-19.SUBJECTS AND METHODS: Imaging studies and medical records of sixteen patients (0-20 years) admit\nBACKGROUND: Recently, cases of multisystem inflammatory syndrome in children (MIS-C) associated with COVID-19 have been reporte\nRecent reports have described a secondary Multisystem Inflammatory Syndrome in Children (MIS-C) after a prior COVID-19 infection that often has features of Kawasaki disease (KD).\ndischarged home (length of hospital stay 3-20 days). There were no mortalities.CONCLUSION: MIS-C associated with COVID-19 is characterized predominantly by cardiovascular abnormalities, though also solid visceral organ, gallbladder, and bowel abnormalities as well as ascites, reflecting a multisystemic inflammatory process.CLINICAL IMPACT: The constellation of imaging findings in the setting of COVID-19 may alert pediatr\nMultisystem Inflammatory Syndrome in Children Temporally Related to COVID-19: A Case Report From Saudi Arabia.\nBACKGROUND: Multisystem inflammatory syndrome temporally associated with COVID-19 (MIS-C) has been described as a novel and often severe presentation of SARS-CoV-2 infection\nric patients. An association between COVID-19 and a Kawasaki-like inflammatory syndrome has recently presented in pediatric patients.CASE REPORT: We report a unique case of multisystem inflammatory syndrome in children presenting with characteristic findings in a child who later developed cardiogenic shock requiring venoarterial extracorporeal membrane oxygenation.CONCLUSION: Recognition of these early signs and symptoms facilitates screening and risk stratification of pediatric COVID-19 cas\nSevere cardiac dysfunction in a patient with multisystem inflammatory syndrome in children associated with COVID-19: Retrospective diagnosis of a puzzling presentation. A case report.",
"role": "user"
},
{
"content": "yes",
"role": "assistant"
}
]
|
science.chemdner_ner | science.chemdner_ner.794 | [
{
"content": "Analyze the given text to identify specific entities. Focus on extracting relevant data.\n\nProvide your findings in JSON format. Each category should list the entities found.\n\nText:\n\nThe ATPase domain of ISWI is an autonomous nucleosome remodeling machine. ISWI slides nucleosomes along DNA, enabling the structural changes of chromatin required for the regulated use of eukaryotic genomes. Prominent mechanistic models imply cooperation of the ISWI ATPase domain with a C-terminal DNA-binding function residing in the HAND-SANT-SLIDE (HSS) domain. Contrary to these models, we show by quantitative biochemical means that all fundamental aspects of nucleosome remodeling are contained within the compact ATPase module of Drosophila ISWI. This domain can independently associate with DNA and nucleosomes, which in turn activate ATP turnover by inducing a conformational change in the enzyme, and it can autonomously reposition nucleosomes. The role of the HSS domain is to increase the affinity and specificity for nucleosomes. Nucleosome-remodeling enzymes may thus have evolved directly from ancestral helicase-type motors, and peripheral domains have furnished regulatory capabilities that bias the remodeling reaction toward different structural outcomes.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"C\", \"ATP\"]}",
"role": "assistant"
}
]
|
science.chemprot_ner | science.chemprot_ner.892 | [
{
"content": "Analyze the following text to identify specific entities. Focus on the categories provided: [\"Chemical\", \"Protein\"].\n\nDeliver your findings as a JSON structure: {\"Chemical\": [\"ExampleChemical\", ...], \"Protein\": [\"ExampleProtein\", ...]}. Each key represents an entity type, and the associated list contains the entities found. \n\nEnsure the response is strictly the JSON format without any extra text.\n\nSource:\n\nNovel analgesic/anti-inflammatory agents: 1,5-diarylpyrrole nitrooxyalkyl ethers and related compounds as cyclooxygenase-2 inhibiting nitric oxide donors.\nA series of 3-substituted 1,5-diarylpyrroles bearing a nitrooxyalkyl side chain linked to different spacers were designed. New classes of pyrrole-derived nitrooxyalkyl inverse esters, carbonates, and ethers (7-10) as COX-2 selective inhibitors and NO donors were synthesized and are herein reported. By taking into account the metabolic conversion of nitrooxyalkyl ethers (9, 10) into corresponding alcohols, derivatives 17 and 18 were also studied. Nitrooxy derivatives showed NO-dependent vasorelaxing properties, while most of the compounds proved to be very potent and selective COX-2 inhibitors in in vitro experimental models. Further in vivo studies on compounds 9a,c and 17a highlighted good anti-inflammatory and antinociceptive activities. Compound 9c was able to inhibit glycosaminoglycan (GAG) release induced by interleukin-1β (IL-1β), showing cartilage protective properties. Finally, molecular modeling and (1)H- and (13)C-NMR studies performed on compounds 6c,d, 9c, and 10b allowed the right conformation of nitrooxyalkyl ester and ether side chain of these molecules within the COX-2 active site to be assessed.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"nitric oxide\", \"3-substituted 1,5-diarylpyrroles\", \"alcohols\", \"1,5-diarylpyrrole nitrooxyalkyl ethers\", \"carbonates\", \"ethers\", \"nitrooxyalkyl ester and ether\", \"nitrooxyalkyl ethers\", \"nitrooxyalkyl\", \"Nitrooxy\", \"(13)C\", \"esters\", \"(1)H\", \"NO\", \"pyrrole\"], \"Protein\": [\"COX-2\", \"cyclooxygenase-2\", \"IL-1\\u03b2\", \"interleukin-1\\u03b2\"]}",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_elife_single_doc_summ | science.scientific_lay_summarisation_elife_single_doc_summ.3607 | [
{
"content": "Transform the provided sections of a biomedical research paper into a digestible summary for a general audience. Focus on simplifying complex ideas while retaining key scientific insights.\n\nResearch Title: FGF14 modulates resurgent sodium current in mouse cerebellar Purkinje neurons\nContent Overview:\nAbstract:\nRapid firing of cerebellar Purkinje neurons is facilitated in part by a voltage-gated Na+( NaV) ‘resurgent’ current, which allows renewed Na+ influx during membrane repolarization. Resurgent current results from unbinding of a blocking particle that competes with normal channel inactivation. The underlying molecular components contributing to resurgent current have not been fully identified. In this study, we show that the NaV channel auxiliary subunit FGF14 ‘b’ isoform, a locus for inherited spinocerebellar ataxias, controls resurgent current and repetitive firing in Purkinje neurons. FGF14 knockdown biased NaV channels towards the inactivated state by decreasing channel availability, diminishing the ‘late’ NaV current, and accelerating channel inactivation rate, thereby reducing resurgent current and repetitive spiking. Critical for these effects was both the alternatively spliced FGF14b N-terminus and direct interaction between FGF14b and the NaV C-terminus. Together, these data suggest that the FGF14b N-terminus is a potent regulator of resurgent NaV current in cerebellar Purkinje neurons.\nIntroduction:\nCerebellar Purkinje neurons, which provide the sole output from the cerebellar cortex, display a repetitive firing behavior driven by voltage-gated Na+ channels( NaV channels). Fast repetitive firing in Purkinje neurons is promoted by unusual characteristics associated with NaV channel inactivation, whereby channels recover unusually rapidly from inactivation and in doing so pass a ‘resurgent’ sodium current, which helps drive the cell to fire a subsequent action potential. The molecular components underlying the peculiar properties of NaV channels in Purkinje neurons have not been definitively identified. Several features of NaV currents in cerebellar Purkinje neurons, however, set them apart from NaV currents recorded in other neurons. First, more than half of the NaV current in Purkinje neurons is carried by NaV1. 6, an isoform for which inactivation is less complete compared to other NaV channels( Raman et al., 1997). Examination of NaV currents in cerebellar Purkinje neurons from Scn8a−/− mice showed that, compared to the other resident NaV channels, the Scn8a-encoded NaV1. 6 channels have a relatively large ‘late’( non-inactivating) component and NaV1. 6 channels have increased availability( depolarized V1/2 for steady-state inactivation). Second, NaV channels in cerebellar Purkinje neurons display an unusual transient re-opening during repolarization, which is identified as ‘resurgent’ NaV current( Raman and Bean, 1997). This resurgent current derives from an unblocking of open channels by a peptide moiety that can be eliminated by the intracellular application of trypsin or chymotrypsin proteases into the cytoplasm( Grieco et al., 2005). The blocking particle acts only on open channels and competes with the inactivation process to prevent channels from entering an absorbed, inactivated state. During action potential repolarization, unblocking of these channels then allows Na+ influx that can initiate a subsequent action potential( Khaliq et al., 2003). Since the NaV current in Purkinje neurons carried by NaV1. 6 is relatively resistant to inactivation, it is particularly susceptible to open block by the peptide moiety. Why NaV1. 6 channels in cerebellar Purkinje neurons are relatively resistant to inactivation, however, is unknown. Here, we focused on the role of the ion channel regulator FGF14, which is enriched in cerebellar granule and Purkinje neurons( Wang et al., 2002). FGF14 is one of four fibroblast growth factor homologous factors( FHFs), members of the fibroblast growth factor( FGF) superfamily sharing a FGF-like core but having extended N- and C-termini not found in other FGFs. Individual FHFs undergo alternative splicing that generates distinct N-termini, none of which contain a signal sequence( Smallwood et al., 1996; Munoz-Sanjuan et al., 2000). Thus, unlike other FGFs they are not secreted and do not function as growth factors( Smallwood et al., 1996). Instead, FHFs remain intracellular and modulate various ion channels. FHFs can bind directly to the cytoplasmic C-terminal domains( CTDs) of NaV channels( Liu et al., 2001) and regulate NaV channel function( Lou et al., 2005). Further, FGF14 is a potent regulator of both NaV1. 1 and NaV1. 6( Lou et al., 2005; Laezza et al., 2009), the two dominant NaV channels in cerebellar Purkinje neurons( Raman et al., 1997; Kalume et al., 2007). FHFs also regulate voltage-gated Ca2+ channels through a mechanism that does not appear to involve a direct interaction( Hennessey et al., 2013; Yan et al., 2013). An ataxia phenotype in Fgf14−/− mice highlights the role of FGF14 in cerebellar physiology and the development of spinocerebellar ataxia type 27( SCA27) in patients with either FGF14 haploinsufficiency or a dominant negative FGF14 mutation( Wang et al., 2002; van Swieten et al., 2003; Dalski et al., 2005) underscores the role of FGF14 in disease. Using shRNA knockdown of endogenous FGF14 in cultured cerebellar Purkinje neurons and replacement with informative mutants that blocked binding of FGF14 to NaV CTDs and eliminated the FGF14 extended N-terminus, we found that FGF14, and especially the N-terminus of the FGF14b isoform exerts specific kinetic effects on cerebellar NaV channels that support repetitive firing and therefore provides new information on the pathophysiology of SCA27.\nDiscussion:\nAlthough FGF14 haploinsufficiency is associated with spinocerebellar ataxia( Dalski et al., 2005) and intrinsic excitability of cerebellar Purkinje neurons is reduced in Fgf14−/− mice( Shakkottai et al., 2009), the detailed multifactorial molecular mechanisms by which FGF14 affects neuronal excitability were not previously known. We had found that FGF14 knockdown in cerebellar granule neurons reduced presynaptic voltage-gated Ca2+ currents and thereby affected neurotransmission at the cerebellar granule neuron to Purkinje neuron synapse( Yan et al., 2013). Here, we found that FGF14b in cerebellar Purkinje neurons affects multiple kinetic parameters of NaV channels, thereby reducing the resurgent NaV current that underlies repetitive firing. Together, the accelerated inactivation, reduced channel availability, and decreased late current observed after FGF14 knockdown bias NaV channels to the inactivated state. Thus, the blocking particle that competes with the inactivation gate for open NaV channels is disadvantaged. Consequently, the resurgent current, and the resulting ability to support repetitive firing in Purkinje neurons, is reduced as we observed. Thus, our data show that an essential regulatory feature of FGF14 in cerebellar Purkinje neurons is to slow NaV channel inactivation in order to foster resurgent current. Resurgent current results from the actions on NaV1. 6 of a putative blocking particle, which is thought to be the cytoplasmic C-terminal peptide of the NaV auxiliary NaVβ4 subunit( Grieco et al., 2005). Nevertheless, the actions of NaVβ4 are not sufficient to generate resurgent NaV current( Chen et al., 2008; Aman et al., 2009), suggesting that other components of the NaV channel complex may be necessary for proper regulation of resurgent NaV current in cerebellar Purkinje neurons. Here, our knockdown experiments and expression of the dominant negative FGF14bΔNT show that FGF14b, and specifically its N-terminus, strongly influence resurgent NaV current. FGF14 knockdown caused a ∼60% reduction. Expression of FGF14ΔNT was even more efficient, resulting in a ∼85% reduction, perhaps because overexpression of FGF14ΔNT was more efficient in replacing endogenous FGF14b than shRNA knockdown was in eliminating endogenous FGF14b. Thus, FGF14 may cooperate with NaVβ4 to generate resurgent current, perhaps by biasing NaV1. 6 channels towards inactivation and thereby disadvantaging the blocking particle. Our results examining effects on total NaV current must be assessed in the context of FGF14 effects not only on NaV1. 6 channels but also on NaV1. 1 channel, the other major source of NaV currents in cerebellar Purkinje neurons( Kalume et al., 2007). Those NaV channels are also influence by FGF14( Lou et al., 2005). Thus, the effects on resurgent current that we attribute to FGF14 may result from FGF14's overall influence of NaV channel kinetics within Purkinje neurons. Our results may also provide some insight into the more variable phenotypes and decreased penetrance in spinocerebellar ataxia patients with FGF14 haploinsufficiency( Dalski et al., 2005; Coebergh et al., 2013) vs patients with a FGF14 mutation( FGF14bF150S) found in a large Dutch spinocerebellar ataxia kindred( van Swieten et al., 2003). Studies in hippocampal neurons suggest that the FGF14bF150S mutant exerts a dominant negative mechanism in which the axon initial segment is depleted of NaV channels and NaV current density is reduced( Laezza et al., 2007). Here, we found no effect on NaV current density in cerebellar Purkinje neurons after FGF14 knockdown. A reduction in NaV current density( with the FGF14bF150S mutation) compared to an effect solely on NaV channel kinetics( with FGF14 haploinsufficiency) may explain the higher penetrance and decreased phenotypic variability in patients with the FGF14bF150S mutation. An important aspect of this study examining effects on NaV channel kinetics was that our analyses were performed in Purkinje neurons. Studying FHFs in their native cellular context appears to be crucial for defining their specific roles. Previous investigations of FGF14-dependent regulation of neuronal NaV channels in heterologous expression systems led to different conclusions from experiments in neurons. For example, expression of NaV1. 6 and FGF14bWT in ND7/23 cells almost eliminated NaV current density( Laezza et al., 2009) while overexpression of FGF14bWT in hippocampal neurons increased NaV current density( Laezza et al., 2007). Similarly, expression of FGF14ΔNT in ND7/23 cells increased current density, while here we observed that FGF14ΔNT expression in cerebellar Purkinje neurons exerted dominant-negative effects upon NaV channel kinetics, but no consequences for NaV current density. While the etiology of the different results in neurons compared to heterologous expression systems is not known, we speculate that additional regulatory factors present in neurons are necessary for physiologic regulation of NaV channels by FHFs. Indeed, we have observed similarly disparate results for the related FGF13 and the cardiac NaV1. 5 channel. In HEK293 cells, FGF13 co-expression reduces NaV1. 5 current density( not shown), but we showed that the role FGF13 in cardiomyocytes is to increase NaV current density( Wang et al., 2011; Hennessey et al., 2013). Finally, our data also provide information about possible consequences of FGF14 overexpression, hypothesized as pathologic in rare cases. Some patients with spinocerebellar ataxia, but not controls, harbor synonymous variants in FGF14. These variants encode a more frequently used codon than the wild type sequence, leading to the hypothesis that patients with these variants would overexpress FGF14 as a cause of disease( Dalski et al., 2005). We found, however, that overexpression of FGF14bWT did not affect current density or any of the measured NaV kinetic properties( Figure 3 and Table 1). Thus, if these variants identified in spinocerebellar ataxia patients are truly associated with disease, our data suggest mechanisms other than FGF14 overexpression. In summary, these data add to a growing appreciation of physiologic and pathophysiologic roles for FHFs in neurons. In the case of spinocerebellar ataxia, our data suggest that FGF14 is a critical regulator of the ability of cerebellar Purkinje neuron NaV channels to support resurgent NaV current and thereby allow Purkinje neurons to fire repetitively. Thus, we provide a molecular understanding for the observation that FGF14 regulates Purkinje neuron intrinsic excitability( Shakkottai et al., 2009). In combination with our data showing that FGF14 also regulates presynaptic voltage-gated Ca2+ channels at the cerebellar granule cell to Purkinje cell synapse, these data pinpoint several specific mechanisms by which mutations in FGF14 underlie spinocerebellar ataxia.",
"role": "user"
},
{
"content": "The cerebellum is a region of the brain that is involved in motor control , and it contains a special type of nerve cells called Purkinje neurons . Messages travel along neurons as electrical signals carried by sodium ions , which have a positive electric charge . Normally , when a neuron is ‘at rest’ , the plasma membrane that surrounds the neuron prevents the sodium ions outside the cell from entering . To send an electrical signal , voltage-sensitive proteins in the membrane called sodium channels open up . This allows the sodium ions to enter the cell by passing through a pore in the channel protein , thereby changing the voltage across the membrane . Once sodium channels open , they rapidly become ‘locked’ in a closed state , which allows the membrane voltage to return to its original value before another signal can be sent . This locked state also prevents sodium channels from reopening quickly . As a consequence most neurons cannot send successive electrical signals rapidly . Purkinje neurons are unusual because they can send many electrical signals in quick succession—known as rapid firing—without having to be reset each time . Rapid firing is possible in Purkinje neurons because the channel proteins can be reopened to allow more Na+ to enter the cell , but it is not clear how this is controlled . Now , based on experiments on Purkinje neurons isolated from mice , Yan et al . have shown that a protein called FGF14 that binds to the sodium channel proteins can help them to reopen quickly in order to allow rapid firing . Spinocerebellar ataxia is a degenerative disease caused by damage to the cerebellum that leads to loss of physical coordination . Some patients suffering from this disease carry mutations in the gene that makes the FGF14 protein . Therefore , understanding the role of FGF14 in the rapid firing of Purkinje neurons may aid the development of new treatments for this disease .",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.164 | [
{
"content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nTotestiftheYchromosomeofstrain129/OlaaltersIOPinrelationtothatofstrainB6,wecomparedtheIOPsofpureB6malesandconsomicB6malesthathadthe129P2/OlaYchromosome(backcrossedfor11generations).",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.genia_ner | science.genia_ner.850 | [
{
"content": "Analyze the provided text excerpt from a scientific document. Identify and extract distinct entities based on predefined categories.\n\nDeliver the results as a JSON structure where each key represents an entity category, and the associated value is a list of identified entities. If no entities are found for a category, return an empty list.\n\nText Excerpt:\n\nImpaired fetal thymocyte development after efficient adenovirus-mediated inhibition of NF-kappa B activation. We introduce a new experimental system combining adenovirus-mediated gene transfer and fetal thymic organ culture (FTOC). This system allowed us to efficiently express in developing thymocytes a mutant form of the NF-kappa B inhibitor I kappa B alpha (mut-I kappa B) and to study the maturation defects occurring when NF-kappa B activation is inhibited during fetal development. Fetal thymocytes infected with adenovirus containing mut-I kappa B were found to develop normally until the CD44-CD25 +, CD4-CD8-double-negative stage, while production of more mature double-positive and single-positive populations was strongly decreased. Proliferation, as measured by the percentage of cells in cycle appeared normal, as did rearrangement and expression of the TCR beta-chain. However, apoptosis was much higher in FTOC infected with adenovirus containing mut-I kappa B than in FTOC infected with a control virus. Taken together, these results suggest that NF-kappa B plays a crucial role in ensuring the differentiation and survival of thymocytes in the early stages of their development.",
"role": "user"
},
{
"content": "{\"CellLine\": [], \"CellType\": [\"fetal thymocyte\", \"Fetal thymocytes\", \"thymocytes\"], \"DNA\": [], \"Protein\": [\"mut - I kappa B\", \"CD44\", \"I kappa B alpha\", \"CD4\", \"CD8\", \"NF - kappa B\", \"TCR beta - chain\"], \"RNA\": []}",
"role": "assistant"
}
]
|
science.bioasq_yesno_qa | science.bioasq_yesno_qa.796 | [
{
"content": "Examine the provided biomedical text and determine the answer to the question. Your response should be either \"yes\" or \"no\" based on the information given.\n\nQuestion: Have machine learning methods been used to predict the severity of major depressive disorder(MDD)?\n\nText: Here, we conduct a meta-review to identify predictors of response to antidepressant therapy in order to select robust input features for machine learning models of treatment response.\nmachine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder (MDD).\nIdentification of risk factors of treatment resistance may be useful to guide treatment selection, avoid inefficient trial-and-error, and improve major depressive disorder (MDD) care. We extended the work in predictive modeling of treatment resistant depression (TRD) via partition of the data from the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) cohort into a training and a testing dataset.\npersistence and severity of major depressive disorder from baseline self-reports\nThese results confirm that clinically useful MDD risk-stratification models can be generated from baseline patient self-reports and that ML methods improve on conventional methods in developing such models\nFurthermore, machine learning weighting factors may reflect an objective biomarker of major depressive disorder illness severity, based on abnormalities of brain structure.\nNotably, while the only information provided for training the classifiers was T(1)-weighted scans plus a categorical label (major depressive disorder versus controls), both relevance vector machine and support vector machine 'weighting factors' (used for making predictions) correlated strongly with subjective ratings of illness severity.\nBACKGROUND Although variation in the long-term course of major depressive disorder (MDD) is not strongly predicted by existing symptom subtype distinctions, recent research suggests that prediction can be improved by using machine learning methods.\nBACKGROUND Although variation in the long-term course of major depressive disorder (MDD) is not strongly predicted by existing symptom subtype distinctions, recent research suggests that prediction can be improved by using machine learning methods.\nBACKGROUND Growing evidence documents the potential of machine learning for developing brain based diagnostic methods for major depressive disorder (MDD).\nOBJECTIVE We aimed to integrate neural data and an advanced machine learning technique to predict individual major depressive disorder (MDD) patient severity.\nFurthermore, machine learning weighting factors may reflect an objective biomarker of major depressive disorder illness severity, based on abnormalities of brain structure.\n<b>BACKGROUND</b>: Although variation in the long-term course of major depressive disorder (MDD) is not strongly predicted by existing symptom subtype distinctions, recent research suggests that prediction can be improved by using machine learning methods.",
"role": "user"
},
{
"content": "yes",
"role": "assistant"
}
]
|
science.bioasq_yesno_qa | science.bioasq_yesno_qa.1132 | [
{
"content": "Examine the provided biomedical text and determine the answer to the question. Your response should be either \"yes\" or \"no\" based on the information given.\n\nQuestion: Has dupilumab been FDA approved for atopic dermatitis?\n\nText: Recent advances and understanding of the pathogenesis of AD have resulted in new therapies that target specific pathways with increased efficacy and the potential for less systemic side effects. New FDA-approved therapies for AD are crisaborole and dupilumab.\nIn March of 2017, the United States Food and Drug Administration (FDA) approved dupilumab for the treatment of moderate-to-severe atopic dermatitis in adults that is uncontrolled with topical medications, becoming the first biologic agent approved to treat this chronic skin condition.\nDupilumab is the first US FDA approved biologic for treatment of atopic dermatitis.\nDupilumab is the first biological treatment approved for moderate-to-severe atopic dermatitis (AD).",
"role": "user"
},
{
"content": "yes",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.3453 | [
{
"content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nInSnail-expressingTgregions,therewasareducedstainingwithanti-E-cadandanti-alpha-catandamorediffusestainingwithanti-Ajuba.",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.mslr2022_ms2_multidoc_summarization | science.mslr2022_ms2_multidoc_summarization.9831 | [
{
"content": "Analyze the following collection of medical RCT summaries. Your goal is to craft a concise synthesis of the findings. Focus on the core insights and present them succinctly. Only include the synthesis in your response. Below are the RCT summaries:\n\n\n\nReport 1:\nTitle: A multicenter comparison of related pharmacologic features of cephalexin and dicloxacillin given for two months to young children with cystic fibrosis.\nSummary: Twenty-one cystic fibrosis patients under 3 years of age were enrolled in an open multicenter study to assess the feasibility of the study design and to compare selected pharmacologic features of cephalexin or dicloxacillin administered orally for 2 months . Patient tolerance and compliance were significantly less for dicloxacillin ( p less than .01 and p less than .001 , respectively ) . Superficial C and ida infections were more common in the cephalexin group ( p = 0.02 ) , however increased stool frequency and nonspecific diaper rashes were more prevalent in patients receiving dicloxacillin ( p less than .05 ) . Staphylococcus aureus was isolated from respiratory secretions after 2 months from two dicloxacillin and no cephalexin patients . Areas under the curve and peak serum concentrations were higher for cephalexin ( p less than .05 and p = .02 ) , but antistaphylococcal activity in serum was higher for dicloxacillin ( p less than .05 ) due to a lower mean MIC compared to cephalexin . Deep pharyngeal plus routine throat culture yielded more pathogens than either method alone . Express mail and central processing of respiratory specimens was efficient for most organisms , however there was some loss of Streptococcus pneumoniae and Haemophilus influenzae . Cephalexin was associated with better patient acceptance and compliance despite higher rates of superficial fungal infections as compared to dicloxacillin . Cephalexin , routine bacteriologic throat swabs processed locally or central ly , mail-in urine compliance assessment and a multicenter design are feasible components for a long-term prospect i ve evaluation of antibiotic prophylaxis in patients with cystic fibrosis\n\n\nReport 2:\nTitle: The Cochrane Collaboration: the role of the UK Cochrane Centre in identifying the evidence.\nSummary: This paper attempts to explain why systematic review s of r and omized controlled trials , based on as high a proportion as possible of the relevant studies , are so important in generating reliable information for evidence -based decision making within health care . The preparation , maintenance and dissemination of such review s is the challenge which has been taken up by the Cochrane Collaboration . The first phase of data collection is the identification of relevant studies . Currently , bibliographic data bases are inadequate for this task . MEDLINE search es identify on average only about half of the relevant studies , and until 1994 there were no suitable indexing terms in EMBASE to identify r and omized controlled trials . Co-operation between the Cochrane Collaboration and both the National Library of Medicine and Elsevier , however , is already transforming this situation . From January 1994 a new indexing term has been added to EMBASE to help identify r and omized controlled trials . From January 1995 a new indexing term will be added to MEDLINE to help identify controlled trials where the method of allocation to treatment or control can not be described with certainty as being r and omized . Also from January 1995 an additional 20,000 reports will be identifiable as r and omized controlled trials in MEDLINE . Progress during the first 2 years of the Cochrane Collaboration has been encouraging , but much remains to be done if users of health services are to benefit from the evidence -based health care which they deserve\n\n\nReport 3:\nTitle: Prognosis in cystic fibrosis treated with continuous flucloxacillin from the neonatal period.\nSummary: All newborn infants in East Anglia are screened for cystic fibrosis by blood immunoreactive trypsin assay at 7 days . Thirty eight infants with cystic fibrosis were r and omised to treatment with either continuous oral flucloxacillin 250 mg/day ( group P , n = 18 ) or with episodic antimicrobials as clinical ly indicated ( group E , n = 20 ) . Their progress was monitored from diagnosis to 24 months by a nurse coordinator who visited all infants regularly , at home and in hospital , to collect anthropometric , dietary , clinical , and microbiological data . Mean ( range ) age of confirmation of diagnosis was 5.7 weeks ( 1 - 14 weeks ) . There was no significant difference in birth weight , genotype , immunoreactive trypsin concentration , neonatal history , symptoms at diagnosis , pancreatic enzyme supplementation , or parental smoking history between the groups . Infants in group E had more frequent cough and a greater number of Staphylococcus aureus isolates than infants in group P. More infants of group E were admitted to hospital , had higher admission rates during the second year ( 19 v 5 ) , for longer periods ( 6.4 v 2.2 days ) , despite receiving more than double the number of courses of antibiotics than group P infants ( in addition to flucloxacillin ) . Continuous prophylactic flucloxacillin from early diagnosis of cystic fibrosis is associated with improved clinical progress during the first two years of life\n\n\nReport 4:\nTitle: Clindamycin therapy of staphylococcal pulmonary infections in patients with cystic fibrosis.\nSummary: [ N PATIENTS with cystic fibrosis , the progression of pulmonary disease following Staphylococcus aureus colonization and the improvement after its eradication suggest that S. aureus may be more important than Pseudomonas aeruginosa and Haemophilus influenzae as primary pathogens . 1'~ The favorable results in CF patients using continuous antistaphylococcal therapy with cloxacillin 3 support this idea . Moreover , S. aureus produces microabscesses of the lung 4 and remains in a CF patient 's sputum despite prolonged administration of antibiotics ? Patients with cystic fibrosis developed precipitating antibodies against S. aureus more frequently than against other sputum pathogens . We therefore studied 29 CF patients receiving prophylactic pulmonary care 6 at the University of Minnesota Hospitals who gave informed consent for treatment of staphylococcal infections with clindamycin",
"role": "user"
},
{
"content": "Sputum clearance of S aureus was more frequently achieved than any other beneficial outcome .\nA beneficial effect on pulmonary function was rarely measured or observed .\nAntistaphylococcal treatment achieves sputum clearance of S aureus in patients with cystic fibrosis .\nProphylactic antistaphylococcal treatment in young children with cystic fibrosis is likely to be of clinical benefit .\nIt remains to be determined whether the use of \" prophylactic \" versus \" intermittent \" antistaphylococcal therapy in cystic fibrosis is associated with improved lung function and /or chest radiographic scores , an increase in bacterial resistance , or earlier acquisition of Pseudomonas aeruginosa .",
"role": "assistant"
}
]
|
science.bioasq_general_qa | science.bioasq_general_qa.627 | [
{
"content": "Review the provided biomedical excerpts and respond to the question concisely. Ensure your answer is derived solely from the given context and avoid adding any extraneous information.\n\nQuestion: What is PARP inhibitor (PARPi) resistance?\n\nExcerpts: PARPi has been designed and tested for many years and became a potential supplement for the conventional chemotherapy. However, increasing evidence indicates the appearance of the resistance to this treatment. Specifically, cancer cells may acquire new mutations or events that overcome the positive effect of these drugs.\nRecent studies have shown that PARP-1 could be either oncogenic or tumor suppressive in different cancers. PARP inhibitor resistance is also a growing concern in the clinical setting. Recently, changes in the levels of PARP-1 activity or expression in cancer patients have provided the basis for consideration of PARP-1 regulatory proteins as potential biomarkers.\nHowever, emerging data have also shown that even BRCA-mutant cells may be resistant to PARPi. The mechanistic basis for these drug resistances is poorly understood.",
"role": "user"
},
{
"content": "PARPi has been designed and tested for many years and became a potential supplement for the conventional chemotherapy. However, increasing evidence indicates the appearance of the resistance to this treatment. Specifically, cancer cells may acquire new mutations or events that overcome the positive effect of these drugs.",
"role": "assistant"
}
]
|
science.mslr2022_cochrane_multidoc_summarization | science.mslr2022_cochrane_multidoc_summarization.1597 | [
{
"content": "Review the provided collection of medical RCT summaries. Your objective is to distill the essential insights into a brief conclusion. Focus solely on the synthesis of findings without additional commentary. The RCT summaries are as follows:\n\n\n\nReport Title 1:\nA randomized controlled trial of intervention in fear of childbirth.\nReport Abstract 1:\nTo compare intensive and conventional therapy for severe fear of childbirth.\n In Finland, 176 women who had fear of childbirth were randomly assigned at the 26th gestational week to have either intensive therapy (mean 3.8 +/- 1.0 sessions with obstetrician and one with midwife) or conventional therapy (mean 2.0 +/- 0.6 sessions), with follow-up 3 months postpartum. Pregnancy-related anxiety and concerns, satisfaction with childbirth, and puerperal depression were assessed with specific questionnaires. Power analysis, based on previous studies, showed that 74 women per group were necessary to show a 50% reduction in cesarean rates.\n Birth-related concerns decreased in the intensive therapy group but increased in the conventional therapy group (linear interaction between the group and birth-concerns P =.022). Labor was shorter in the intensive therapy group (mean +/- standard deviation 6.8 +/- 3.8 hours) compared with the conventional group (8.5 +/- 4.8 hours, P =.039). After intervention, 62% of those originally requesting a cesarean (n = 117) chose to deliver vaginally, equally in both groups. Cesarean was more frequent for those who refused to fill in the questionnaires than for those who completed them (57% compared with 27%, P =.001). In the log-linear model, parous women who had conventional therapy and refused to fill in the questionnaires chose a cesarean more often than expected (standardized residual 2.54, P =.011). There were no differences between groups in satisfaction with childbirth or in puerperal depression.\n Both kinds of therapy reduced unnecessary cesareans, more so in nulliparous and well-motivated women. With intensive therapy, pregnancy- and birth-related anxiety and concerns were reduced, and labors were shorter.",
"role": "user"
},
{
"content": "Research has focussed on encouraging women to attempt vaginal delivery. Trials of interventions to encourage women to attempt vaginal birth showed no effect, but shortcomings in study design mean that the evidence is inconclusive.\nFurther research on this topic is urgently needed.",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.4423 | [
{
"content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\n(D)TAGsynthesisratesinisolatedhepatocytes.",
"role": "user"
},
{
"content": "[\"TAG\"]",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.388 | [
{
"content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: Routing Protocols for Unmanned Aerial Vehicle Networks: A Survey \nChapter Title: 4) SINGLE-PATH -GREEDY-BASED NON-DELAY TOLERANT ROUTING a: GEOGRAPHIC LOAD SHARE ROUTING (GLSR) \n1. Abstract of Cited Paper (BIB001): Unmanned Aerial Vehicles (UAVs) play more and more important roles in modern warfare. However, the data routing for communication among UAVs faces several challenges, such as packet loss or routing path failure etc. The main problem of UAVs data routing is caused by the high mobility of UAVs. In this paper, an effective geographic mobility prediction routing protocol is proposed to improve the performance of routing among UAVs. First, a Gaussian distribution of UAVs movement probability density function is deduced to reduce the impact of high mobility. Then, two-hop perimeter forwarding is proposed to reduce the impact of routing void. The experiment results show that the proposed approach can provide effective and reliable data routing with acceptable communication overhead in the highly dynamic environment of Ad Hoc UAV Network.\n\nReview Chapter:",
"role": "user"
},
{
"content": "Geographic load share routing (GLSR) BIB001 is another geographic routing protocol for UAVs, proposed by Medina et al., which can use multiple paths at a time between the source, and the destination. In addition, Mobility predication-based geographic routing (MPGR) BIB002 based on geographic position for inter-UAV networks, proposed by Lin et al., uses the Gaussian distribution function to detect the mobility of UAVs.",
"role": "assistant"
}
]
|
science.ncbi_ner | science.ncbi_ner.429 | [
{
"content": "Examine the text below and extract disease-related entities. Present your findings in a structured JSON format.\n\nYour response should be a JSON object with keys as entity types and values as lists of entities. If no entities are found, return an empty list for that type.\n\nContent:\n\nA 71-kilodalton protein is a major product of the Duchenne muscular dystrophy gene in brain and other nonmuscle tissues. The known Duchenne muscular dystrophy (DMD) gene products, the muscle- and brain-type dystrophin isoforms, are 427-kDa proteins translated from 14-kilobase (kb) mRNAs. Recently we described a 6. 5-kb mRNA that also is transcribed from the DMD gene. Cloning and in vitro transcription and translation of the entire coding region show that the 6. 5-kb mRNA encodes a 70. 8-kDa protein that is a major product of the DMD gene. It contains the C-terminal and the cysteine-rich domains of dystrophin, seven additional amino acids at the N terminus, and some modifications formed by alternative splicing in the C-terminal domain. It lacks the entire large domain of spectrin-like repeats and the actin-binding N-terminal domain of dystrophin. This protein is the major DMD gene product in brain and other nonmuscle tissues but is undetectable in skeletal muscle extracts.",
"role": "user"
},
{
"content": "{\"Disease\": [\"Duchenne muscular dystrophy\", \"DMD\"]}",
"role": "assistant"
}
]
|
science.nlmgene_ner | science.nlmgene_ner.273 | [
{
"content": "Analyze the provided text to identify gene-related entities. \n\nFormat your findings as a JSON object: {\"Gene\": [\"ExampleGene\", ...]}. Use the entity type as the key, and list the entities under it. If no entities are found, use an empty list.\n\nFocus solely on the JSON output.\n\nText:\n\nRBFOX1 cooperates with MBNL1 to control splicing in muscle, including events altered in myotonic dystrophy type 1. With the goal of identifying splicing alterations in myotonic dystrophy 1 (DM1) tissues that may yield insights into targets or mechanisms, we have surveyed mis-splicing events in three systems using a RT-PCR screening and validation platform. First, a transgenic mouse model expressing CUG-repeats identified splicing alterations shared with other mouse models of DM1. Second, using cell cultures from human embryonic muscle, we noted that DM1-associated splicing alterations were significantly enriched in cytoskeleton (e.g. SORBS1, TACC2, TTN, ACTN1 and DMD) and channel (e.g. KCND3 and TRPM4) genes. Third, of the splicing alterations occurring in adult DM1 tissues, one produced a dominant negative variant of the splicing regulator RBFOX1. Notably, half of the splicing events controlled by MBNL1 were co-regulated by RBFOX1, and several events in this category were mis-spliced in DM1 tissues. Our results suggest that reduced RBFOX1 activity in DM1 tissues may amplify several of the splicing alterations caused by the deficiency in MBNL1.",
"role": "user"
},
{
"content": "{\"Gene\": [\"MBNL1\", \"TACC2\", \"TTN\", \"KCND3\", \"RBFOX1\", \"SORBS1\", \"TRPM4\", \"ACTN1\", \"DMD\"]}",
"role": "assistant"
}
]
|
science.medmentions_ner | science.medmentions_ner.342 | [
{
"content": "Analyze the provided paragraph from a scientific document. Your goal is to identify and extract relevant entities.\n\nFormat your findings as a JSON object, where each key represents a category of entities, and the corresponding value is a list of entities identified in that category. If no entities are found for a category, return an empty list.\n\nFocus on precision and ensure that the output is strictly in JSON format.\n\nDocument:\n\nAn efficient approach to identify different chemical markers between fibrous root and rhizome of Anemarrhena asphodeloides by ultra high-performance liquid chromatography quadrupole time-of-flight tandem mass spectrometry with multivariate statistical analysis An ultra high-performance liquid chromatography quadrupole time-of-flight tandem mass spectrometry approach coupled with multivariate statistical analysis was established and applied to rapidly distinguish the chemical differences between fibrous root and rhizome of Anemarrhena asphodeloides. The datasets of tR-m/z pairs, ion intensity and sample code were processed by principal component analysis and orthogonal partial least squares discriminant analysis. Chemical markers could be identified based on their exact mass data, fragmentation characteristics, and retention times. And the new compounds among chemical markers could be isolated rapidly guided by the ultra high-performance liquid chromatography quadrupole time-of-flight tandem mass spectrometry and their definitive structures would be further elucidated by NMR spectra. Using this approach, twenty-four markers were identified on line including nine new saponins and five new steroidal saponins of them were obtained in pure form. The study validated this proposed approach as a suitable method for identification of the chemical differences between various medicinal parts in order to expand medicinal parts and increase the utilization rate of resources.",
"role": "user"
},
{
"content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"saponins\", \"ion\", \"steroidal saponins\"], \"ClinicalAttribute\": [], \"Eukaryote\": [\"medicinal parts\", \"rhizome\", \"Anemarrhena asphodeloides\", \"fibrous root\"], \"Finding\": [], \"Food\": [], \"HealthCareActivity\": [\"NMR spectra\", \"ultra high-performance liquid chromatography quadrupole time-of-flight tandem mass spectrometry\", \"method\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"datasets\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"orthogonal partial least squares discriminant analysis\", \"study\"], \"SpatialConcept\": [\"structures\"], \"Virus\": []}",
"role": "assistant"
}
]
|
science.mslr2022_ms2_multidoc_summarization | science.mslr2022_ms2_multidoc_summarization.48 | [
{
"content": "Analyze the following collection of medical RCT summaries. Your goal is to craft a concise synthesis of the findings. Focus on the core insights and present them succinctly. Only include the synthesis in your response. Below are the RCT summaries:\n\n\n\nReport 1:\nTitle: Subcortical brain volume abnormalities in 2028 individuals with schizophrenia and 2540 healthy controls via the ENIGMA consortium\nSummary: The profile of brain structural abnormalities in schizophrenia is still not fully understood , despite decades of research using brain scans . To vali date a prospect i ve meta- analysis approach to analyzing multicenter neuroimaging data , we analyzed brain MRI scans from 2028 schizophrenia patients and 2540 healthy controls , assessed with st and ardized methods at 15 centers worldwide . We identified subcortical brain volumes that differentiated patients from controls , and ranked them according to their effect sizes . Compared with healthy controls , patients with schizophrenia had smaller hippocampus ( Cohen ’s d=−0.46 ) , amygdala ( d=−0.31 ) , thalamus ( d=−0.31 ) , accumbens ( d=−0.25 ) and intracranial volumes ( d=−0.12 ) , as well as larger pallidum ( d=0.21 ) and lateral ventricle volumes ( d=0.37 ) . Putamen and pallidum volume augmentations were positively associated with duration of illness and hippocampal deficits scaled with the proportion of unmedicated patients . Worldwide cooperative analyses of brain imaging data support a profile of subcortical abnormalities in schizophrenia , which is consistent with that based on traditional meta-analytic approaches . This first ENIGMA Schizophrenia Working Group study vali date s that collaborative data analyses can readily be used across brain phenotypes and disorders and encourages analysis and data sharing efforts to further our underst and ing of severe mental illness\n\n\nReport 2:\nTitle: Neural Correlates of Hate\nSummary: In this work , we address an important but unexplored topic , namely the neural correlates of hate . In a block- design fMRI study , we scanned 17 normal human subjects while they viewed the face of a person they hated and also faces of acquaintances for whom they had neutral feelings . A hate score was obtained for the object of hate for each subject and this was used as a covariate in a between-subject r and om effects analysis . Viewing a hated face result ed in increased activity in the medial frontal gyrus , right putamen , bilaterally in premotor cortex , in the frontal pole and bilaterally in the medial insula . We also found three areas where activation correlated linearly with the declared level of hatred , the right insula , right premotor cortex and the right fronto-medial gyrus . One area of deactivation was found in the right superior frontal gyrus . The study thus shows that there is a unique pattern of activity in the brain in the context of hate . Though distinct from the pattern of activity that correlates with romantic love , this pattern nevertheless shares two areas with the latter , namely the putamen and the insula\n\n\nReport 3:\nTitle: Lower Amygdala Volume in Men is Associated with Childhood Aggression, Early Psychopathic Traits, and Future Violence\nSummary: BACKGROUND Reduced amygdala volume has been implicated in the development of severe and persistent aggression and the development of psychopathic personality . With longitudinal data , the current study examined whether male subjects with lower amygdala volume have a history of aggression and psychopathic features dating back to childhood and are at increased risk for engaging in future aggression/violence . METHODS Participants were selected from a longitudinal study of 503 male subjects initially recruited when they were in the first grade in 1986 - 1987 . At age 26 , a sub sample of 56 men with varying histories of violence was recruited for a neuroimaging sub study . Automated segmentation was used to index individual differences in amygdala volume . Analyses examined the association between amygdala volume and levels of aggression and psychopathic features of participants measured in childhood and adolescence . Analyses also examined whether amygdala volume was associated with violence and psychopathic traits assessed at a 3-year follow-up . RESULTS Men with lower amygdala volume exhibited higher levels of aggression and psychopathic features from childhood to adulthood . Lower amygdala volume was also associated with aggression , violence , and psychopathic traits at a 3-year follow-up , even after controlling for earlier levels of these features . All effects remained after accounting for several potential confounds . CONCLUSIONS This represents the first prospect i ve study to demonstrate that men with lower amygdala volume have a longst and ing history of aggression and psychopathic features and are at increased risk for committing future violence . Studies should further examine whether specific amygdala abnormalities might be a useful biomarker for severe and persistent aggression\n\n\nReport 4:\nTitle: Incidence and clinical correlates of aggression and violence at presentation in patients with first episode psychosis\nSummary: This study aim ed to identify the incidence and clinical correlates of aggression and violence in first episode psychosis . We prospect ively recruited subjects with a first episode of DSM-psychosis presenting from a geographically defined catchment area to a secondary referral psychiatric service over a four-year period ( n = 157 ) . We used the Modified Overt Aggression Scale to retrospectively assess aggression ( a hostile or destructive mental attitude , including verbal aggression , physical aggression and /or violence ) and violence ( the exercise of physical force ) , blind to diagnosis . One in three patients with psychosis was aggressive at the time of presentation . One patient in 14 engaged in violence that caused , or was likely to cause , injury to other people . Aggression was independently associated with drug misuse ( odds ratio ( OR ) 2.80 , 95 % confidence interval 1.12 - 6.99 ) and involuntary admission status ( OR = 3.62 , 95 % CI 1.45 - 9.01 ) . Violence in the week prior to presentation was associated with drug misuse ( OR = 2.75 , CI 1.04 - 7.24 ) and involuntary admission status ( OR = 3.21 , CI 1.21 - 8.50 ) . Violence in the week following presentation was associated with poor insight ( OR 2.97 , CI 1.03 - 8.56 ) and pre-contact violence ( OR 3,82 , CI 1.34 - 10.88 ) . In patients with schizophrenia , violence in the week following presentation was associated with drug misuse ( OR = 7.81 , CI 1.33 - 45.95 ) and high psychopathology scores ( OR = 20.59 , CI 1.66 - 254.96 ) . Overall , despite a high rate of verbal aggression , physical violence towards other people is uncommon in individuals presenting with first episode psychosis\n\n\nReport 5:\nTitle: Brief Psychiatric Rating Scale — Excited Component (BPRS-EC) and neuropsychological dysfunction predict aggression, suicidality, and involuntary treatment in first-episode psychosis\nSummary: OBJECTIVE Aggression , suicidality and involuntary treatment constitute severe clinical problems in first-episode psychosis ( FEP ) . Although there are studies on prevalence and clinical predictors of these conditions , little is known on the influence of psychopathology and neuropsychological dysfunction . METHOD 152 FEP in patients were prospect ively assessed using the Brief Psychiatric Rating Scale ( BPRS ) and a neuropsychological examination covering the domains ' processing speed ' , ' concentration and attention ' , ' executive function ' , ' working memory ' , ' verbal memory ' , ' verbal comprehension ' , ' logical reasoning ' , ' global cognition ' , and ' general intelligence ' . Clinical data were collected retrospectively in a structured file audit trial . RESULTS Patients were aged 24.5±4.9years , and 112 ( 74 % ) were male . At admission , 13 ( 9 % ) patients presented with severe aggression , and 28 ( 18 % ) with severe suicidality . 31 patients ( 20 % ) received involuntary treatment . In multivariate analyses , aggression was predicted by BPRS-Excited Component ( BPRS-EC ; p=.001 ) , suicidality was predicted by BPRS-EC ( p=.013 ) and general intelligence ( p=.016 ) , and predictors for involuntary treatment were BPRS-EC ( p=.001 ) and neuropsychological dysfunction in the domain ' concentration and attention ' ( p=.016 ) . CONCLUSION Psychopathology and neuropsychological functioning independently predict dangerous behavior in FEP patients . Some correlations with neuropsychology ( e.g. , of aggression with concentration/attention ) are absent in multivariate analyses and may thus constitute a proxy of psychopathological features . In addition to clinical data , BPRS-EC can be used as a predictor of dangerous behavior . Patients with severe aggression and suicidality show different patterns of neuropsychological dysfunction , indicating that suicidality should not be conceptualized as subtype of aggressive behavior\n\n\nReport 6:\nTitle: Evidence for an agitated-aggressive syndrome in early-onset psychosis correlated with antisocial personality disorder, forensic history, and substance use disorder\nSummary: OBJECTIVE Agitation , aggression , and violence are increased in psychotic disorders . Additionally , an earlier age at onset may be associated with aggressive behavior . However , the relationship of age at onset , an agitated-aggressive syndrome as measured with the Positive And Negative Syndrome Scale for Schizophrenia - Excited Component ( PANSS-EC ) , and its potential correlates in first-episode psychosis ( FEP ) has not been studied . METHOD This study assessed the association between age at onset , an agitated-aggressive syndrome , and its potential correlates in a prospect i ve sample of 52 FEP patients with early-onset and adult-onset followed up for 12months . RESULTS Twenty-six patients conformed to the criteria of early-onset psychosis . Early age at onset was associated with antisocial personality disorder ( p=0.004 ; φc=0.39 ) , a history of legal involvement ( p=0.005 ; φc=0.39 ) , and higher rates of lifetime substance use disorder ( SUD ; p=0.002 ; φc=0.42 ) . Early-onset patients had significantly higher PANSS-EC scores over the course of observation ( F(1,44.4)=5.39 ; p=0.025 ; d=0.656 ) , but no significant group differences emerged for the remaining PANSS subscores . PANSS-EC scores were correlated positively with antisocial personality disorder and forensic history at 6weeks , 3months , 6months , and 12months , and with lifetime substance use disorder at 3months and 6months . CONCLUSIONS Patients with early onset psychosis may have increased levels of agitation/aggressiveness , and , more likely , antisocial personality disorder , forensic history , and lifetime substance use disorder . These variables were linked to suicidality , aggressiveness , and involuntary treatment",
"role": "user"
},
{
"content": "Qualitative analyses showed lower volumes of WB , prefrontal regions , temporal lobe , hippocampus , thalamus and cerebellum , and higher volumes of lateral ventricles , amygdala , and putamen in violent vs. non-violent people with schizophrenia .\nConclusions : We review ed evidence for differences in brain volume correlates of aggression in persons with schizophrenia .\nOur results point toward a reduced whole brain volume in violent as opposed to non-violent persons with schizophrenia .",
"role": "assistant"
}
]
|
science.drug_combo_extraction_re | science.drug_combo_extraction_re.378 | [
{
"content": "Analyze the given paragraph from a biomedical study. Focus on identifying drug pairings within a specified sentence. Your goal is to determine the nature of these pairings.\n\nPresent your findings as a JSON array. Each element should be an array containing the drug names and their interaction type. Use the exact names from the sentence.\n\nOnly consider the specified sentence for your analysis. The paragraph is for context only.\n\nReturn solely the JSON array. If no pairings are found, return an empty array.\n\nContext Paragraph: How do azoles inhibit cytochrome P450 enzymes? A density functional study. To examine how azole inhibitors interact with the heme active site of the cytochrome P450 enzymes, we have performed a series of density functional theory studies on azole binding. These are the first density functional studies on azole interactions with a heme center and give fundamental insight into how azoles inhibit the catalytic function of P450 enzymes. Since azoles come in many varieties, we tested three typical azole motifs representing a broad range of azole and azole-type inhibitors: methylimidazolate, methyltriazolate, and pyridine. These structural motifs represent typical azoles , such as econazole , fluconazole , and metyrapone . The calculations show that azole binding is a stepwise mechanism whereby first the water molecule from the resting state of P450 is released from the sixth binding site of the heme to create a pentacoordinated active site followed by coordination of the azole nitrogen to the heme iron. This process leads to the breaking of a hydrogen bond between the resting state water molecule and the approaching inhibitor molecule. Although, formally, the water molecule is released in the first step of the reaction mechanism and a pentacoordinated heme is created, this does not lead to an observed spin state crossing. Thus, we show that release of a water molecule from the resting state of P450 enzymes to create a pentacoordinated heme will lead to a doublet to quartet spin state crossing at an Fe-OH(2) distance of approximately 3.0 A, while the azole substitution process takes place at shorter distances. Azoles bind heme with significantly stronger binding energies than a water molecule, so that these inhibitors block the catalytic cycle of the enzyme and prevent oxygen binding and the catalysis of substrate oxidation. Perturbations within the active site (e.g., a polarized environment) have little effect on the relative energies of azole binding. Studies with an extra hydrogen-bonded ethanol molecule in the model, mimicking the active site of the CYP121 P450, show that the resting state and azole binding structures are close in energy, which may lead to chemical equilibrium between the two structures, as indeed observed with recent protein structural studies that have demonstrated two distinct azole binding mechanisms to P450 heme.\n\nTarget Sentence: These structural motifs represent typical azoles , such as econazole , fluconazole , and metyrapone .",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.3461 | [
{
"content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nNotch signaling is involved in endothelial angiogenesis and vasculogenesis (Duarte et al., 2004; Lawson et al., 2001).",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.3568 | [
{
"content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nDevore’s polynomials over finite fields[18]; Gao F’s algebraic curves [19]; Amini and Marvasti’s bipolar matrix by BCH code [20] and its generalization [21]; Bourgain’s additive combinatorics[16].",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
]
|
science.chemprot_ner | science.chemprot_ner.701 | [
{
"content": "Analyze the following text to identify specific entities. Focus on the categories provided: [\"Chemical\", \"Protein\"].\n\nDeliver your findings as a JSON structure: {\"Chemical\": [\"ExampleChemical\", ...], \"Protein\": [\"ExampleProtein\", ...]}. Each key represents an entity type, and the associated list contains the entities found. \n\nEnsure the response is strictly the JSON format without any extra text.\n\nSource:\n\nFibrillar Morphology of Derivatives of Poly(3-alkylthiophene)s by Solvent Vapor Annealing: Effects of Conformational Transition and Conjugate Length.\nA fibrillar morphology was obtained, compared to the featherless pristine films, via solvent annealing the films of a series of derivatives of poly(3-alkylthiophene)s (P3ATs): poly(3-dodecylthiophene) (P3DDT), poly(3,3‴-didodecyl-quaterthiophene) (PQT12), and poly(2,5-bis(3-dodecylthiophen-2-yl)thieno[3,2-b]thiophene) (pBTTT12). Among the solvents used, including dichloromethane, chloroform, tetrahydrofuran, and carbon disulfide (CS2), CS2 was the best to induce fibril formation because its solubility parameter is closest to those of the P3AT derivatives. It was found that higher critical CS2 vapor pressures were needed to form crystal nuclei with increasing conjugation length and molecular weight of the P3AT derivatives; i.e., the critical vapor pressures for P3DDT 13.9k and PQT12 15.5k were 59.0% and 80.7%, respectively, and there were no nuclei of fibrils for pBTTT12 15.6k with the highest conjugation length, even at a CS2 vapor pressure of 98.3%. Meanwhile, at the highest vapor pressure, the fibril density decreased with increasing conjugation length and molecular weight of the P3AT derivatives. This is attributed to the rod-like conformation prevailing for polymers with larger conjugation length and higher molecular weight during solvent annealing, making the conformational transition toward coils more difficult and hindering diffusion of molecules. The results presented here are expected to be helpful for the design and processing of conjugated semiconductor polymers.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"dichloromethane\", \"carbon disulfide\", \"P3ATs\", \"Poly(3-alkylthiophene)s\", \"chloroform\", \"CS2\", \"PQT12\", \"poly(2,5-bis(3-dodecylthiophen-2-yl)thieno[3,2-b]thiophene)\", \"poly(3-alkylthiophene)s\", \"P3AT\", \"poly(3,3\\u2034-didodecyl-quaterthiophene)\", \"poly(3-dodecylthiophene)\", \"tetrahydrofuran\", \"P3DDT\", \"pBTTT12\"], \"Protein\": []}",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.4618 | [
{
"content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nRandomised community-based trial of annual single-dose diethylcarbamazine with or without ivermectin against Wuchereria bancrofti infection in human beings and mosquitoes . BACKGROUND WHO has targeted lymphatic filariasis for elimination . Studies of vector-parasite relations of Wuchereria bancrofti suggest that a reduction in the microfilarial reservoir by mass chemotherapy may interrupt transmission and thereby eliminate infection . However , no field data exist on the impact of chemotherapy alone on vector efficiency and transmission intensity of W bancrofti . We compared the impact of an annual community-wide single-dose treatment with diethylcarbamazine alone or with ivermectin on rate and intensity of microfilaraemia , and transmission intensity in an area of Papua New Guinea endemic for intense W bancrofti transmission . METHODS We carried out clinical and parasitological surveys in 14 communities in matched pairs . People aged 5 years or older in seven communities received randomly assigned diethylcarbamazine 6 mg/kg and people in the other seven communities received diethylcarbamazine 6 mg/kg plus ivermectin 400 micrograms/kg . We made physical examinations for hydroceles and leg oedema and investigated microfilarial densities by membrane filtration before and after treatment . We selected five communities for monthly entomological surveys between September , 1993 , and September , 1995 . Mosquitoes were collected in these communities by the all-night landing catch method and were individually dissected to identify rates of infection and infectiveness . FINDINGS 2219 ( 87.6 % ) of 2534 eligible people received treatment . Microfilarial rate and density had decreased 1 year after treatment in all 14 communities ; this decrease was significantly higher in communities given combined therapy than in those given diethylcarbamazine alone ( mean decreases 57.5 % and 30.6 % , respectively ; p = 0.0013 ) . Greater decreases were also seen in community-specific microfilarial intensity with combined therapy ( mean reductions 91.1 % and 69.8 % , respectively ; p = 0.0047 ) . The rate of leg oedema was not altered , but the frequency of advanced hydroceles decreased by 47 % with combined therapy and 56 % with diethylcarbamazine alone . 26,641 Anopheles punctulatus mosquitoes were caught during 499 person-nights of landing catches . Exposure to infective third-stage larvae decreased in all monitored five communities . Annual transmission potential decreased by between 75.7 % and 98.8 % in combined-therapy communities and between 75.6 % and 79.4 % in communities given diethylcarbamazine alone . Transmission was almost interrupted in two communities treated with combined therapy . INTERPRETATION Annual single-dose community-wide treatment with diethylcarbamazine alone or with ivermectin is effective for the control of lymphatic filariasis in highly endemic areas , but combination therapy brings about greater decreases in rates and intensity of microfilaraemia .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"annual community-wide single-dose treatment with diethylcarbamazine alone or with ivermectin\", \"chemotherapy\", \"ivermectin\", \"diethylcarbamazine\"], \"Outcome\": [\"rates and intensity of microfilaraemia .\", \"Exposure to infective third-stage larvae\", \"community-specific microfilarial intensity\", \"rate of leg oedema\", \"Annual transmission potential\", \"effective\", \"Microfilarial rate and density\", \"frequency of advanced hydroceles\"], \"Participant\": [\"Wuchereria bancrofti infection\", \"2219\", \"5\", \"2534\"]}",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.4478 | [
{
"content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nInterest point detection and local feature description are fundamental steps in many computer vision applications. Classical methods for these tasks are based on a detect-then-describe paradigm where separate handcrafted methods are used to first identify repeatable keypoints and then represent them with a local descriptor. Neural networks trained with metric learning losses have recently caught up with these techniques, focusing on learning repeatable saliency maps for keypoint detection and learning descriptors at the detected keypoint locations. In this work, we argue that salient regions are not necessarily discriminative, and therefore can harm the performance of the description. Furthermore, we claim that descriptors should be learned only in regions for which matching can be performed with high confidence. We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness. This allows us to avoid ambiguous areas and leads to reliable keypoint detections and descriptions. Our detection-and-description approach, trained with self-supervision, can simultaneously output sparse, repeatable and reliable keypoints that outperforms state-of-the-art detectors and descriptors on the HPatches dataset. It also establishes a record on the recently released Aachen Day-Night localization dataset.\n\nCited Works Summary:\n[1]: In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions. We propose an approach where a single convolutional neural network plays a dual role: It is simultaneously a dense feature descriptor and a feature detector. By postponing the detection to a later stage, the obtained keypoints are more stable than their traditional counterparts based on early detection of low-level structures. We show that this model can be trained using pixel correspondences extracted from readily available large-scale SfM reconstructions, without any further annotations. The proposed method obtains state-of-the-art performance on both the difficult Aachen Day-Night localization dataset and the InLoc indoor localization benchmark, as well as competitive performance on other benchmarks for image matching and 3D reconstruction.\n\n[2]: We present a novel strategy to learn a local feature pipeline from collections of images with deep networks, without the need for human supervision. To do so we frame the learning problem with a two-branch network. We posit that training both branches with a standard Siamese architecture is not feasible, as solving the correspondence problem jointly with feature learning is too challenging, and does not converge well enough to train from scratch. Instead, we propose to break differentiability on one branch and use ground-truth geometry to remove the burden of solving the correspondence problem while training, while keeping the other fully-differentiable. In order to train this setup with gradient-based methods, we optimize for the differentiable branch while using the parameters from the previous training step for the other, and demonstrate that both converge to a single, optimal solution. Our method can be trained with only the relative camera pose and depth information---furthermore, we show that this ground truth does not need to be perfect and can be easily obtained with off-the-shelf Structure-from-Motion solutions. Our models outperform the state of the art on sparse feature matching on both indoor and outdoor datasets, while running at 60+ fps for QVGA images.",
"role": "user"
},
{
"content": "More recently, D2-Net [1] uses a single CNN for joint detection and description that share all weights; the detection being based on local maxima across the channels and the spatial dimensions of the feature maps. Instead of arbitrarily defining keypoints as local maxima in the descriptor space, our approach explicitly estimates the keypoint reliability and repeatability. Finally, Ono al [2] train a network from pairs of matching images with a complicated asymmetric gradient backpropagation scheme for the detection and a triplet loss for the local descriptor. Compared to these works, for the first time we jointly train a sparse keypoint detector with a deep descriptor enhanced with a reliability confidence value such that ambiguous areas are avoided.",
"role": "assistant"
}
]
|
science.data_reco_mcq_sc | science.data_reco_mcq_sc.5153 | [
{
"content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: I want to learn a pooling function for video action recognition.\n\nKeywords: action recognition video\n\nDataset Information:\nMTL-AQA: A new multitask action quality assessment (AQA) dataset, the largest to date, comprising of more than 1600 diving samples; contains detailed annotations for fine-grained action recognition, commentary generation, and estimating the AQA score. Videos from multiple angles provided wherever available.\nHMDB51: The HMDB51 dataset is a large collection of realistic videos from various sources, including movies and web videos. The dataset is composed of 6,766 video clips from 51 action categories (such as “jump”, “kiss” and “laugh”), with each category containing at least 101 clips.\nDISFA: The Denver Intensity of Spontaneous Facial Action (DISFA) dataset consists of 27 videos of 4844 frames each, with 130,788 images in total. Action unit annotations are on different levels of intensity, which are ignored in the following experiments and action units are either set or unset.\nJHMDB: JHMDB is an action recognition dataset that consists of 960 video sequences belonging to 21 actions. It is a subset of the larger HMDB51 dataset collected from digitized movies and YouTube videos.\n\nAvailable Datasets: A: MTL-AQA B: HMDB51 C: DISFA D: JHMDB",
"role": "user"
},
{
"content": "HMDB51",
"role": "assistant"
}
]
|
science.chemsum_single_document_summarization | science.chemsum_single_document_summarization.5954 | [
{
"content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nLight induced drug release from a folic acid-drug conjugate\n\nContent Extracts:\n\n<p>Targeted therapeutics promise to greatly reduce the adverse side effects associated with current cancer chemotherapeutics.1 Targeted therapies typically act either by interfering with upregulated oncogenic pathways or through enabling cancer cell selective delivery by binding to an overexpressed receptor on the cell membrane of cancer cells.2–5 In the latter approach, a receptor targeting ligand is covalently coupled to a cytotoxic agent, which is then selectively delivered to the tumor cells.</p><p>Folic acid (FA-vitamin B9) is a precursor to tetrahydrofolate, 1-carbon donor which is essential for the synthesis of nucleotide bases. Commonly prescribed as nutritional supplement, FA has high affinity towards folate receptors (FRs), which facilitates its internalization. Two independent and mechanistically different systems mediate cellular uptake of FA in mammalian cells. The Reduced Folate Carrier (RFC) is a low affinity (Kd ~ 10−6 M), high-capacity membrane-spanning anion transport protein that delivers reduced FAs across the plasma membrane in a bidirectional fashion. Folate Receptor (FRα) is a high affinity (Kd ~ 10−10 M), single chain FA-binding protein which internalizes FA through active-receptor mediated endocytosis.6,7 FRα is frequently overexpressed in epithelial tumors, particularly in ovarian cancer where 90% of patients have elevated FRα levels.8,9 For this reason, FR targeting is being pursued for imaging and therapeutic purposes by conjugating FA with imaging or drug molecules.10–13 Folate-containing conjugates bind to FRα and are internalized via endocytosis. Once internalized the cargo needs to be released in order to prevent endosomal entrapment.14</p><p>Endosomal escape can be facilitated through cleavage of the bond between folate and a cell permeable drug, enabling it to pass through the endosomal membrane. A common approach to achieve this involves the use of disulfide bonds, which are cleaved only under reducing conditions inside the endosomes.15</p><p>Another potential modality for drug release is light.16–28 Light has the advantages of being non-invasive, and spatially and temporally controllable for added selectivity. A folate targeted drug release system based on light would also offer an oxygen-independent alternative to photodynamic therapy,29,30 and other light-activated therapeutic strategies.31–34 Here, we describe such a targeted drug release system prepared by attaching doxorubicin to folic acid via a light-cleavable bond. Such a conjugate should selectively bind to and concentrate in tumor cells expressing the folate receptor (Fig. 1). When irradiated with light, the drug molecule will be released from the endosomes, eventually causing cell death with minimal collateral damage.</p><p>We envisioned linking the Folic acid to a photocaged doxorubicin using click chemistry. Previously, we established a protocol for the synthesis of a photocaged-doxorubicin with an alkyne functional group (6)\nScheme 1. 21 To prepare the required folate-azide we coupled 4-Azidobenzoic succinimidyl ester (1) to bis-amino PEG linker (2) via an amide bond to give compound (3). We then prepared the N-hydroxysuccinimide ester of Folic acid (4) using reaction conditions that are known to be selective for the γ-COOH. 35 This intermediate was coupled with compound (3) to give azido folate conjugate (5) in moderate yield. This azide-derivatized folic acid was coupled to photocaged doxorubicin (6) using standard click chemistry to give PhotoDox-Fol (7). The drug conjugate was purified using HPLC and characterized using mass spectrometry (SI-7).</p><p>To demonstrate the efficiency of our drug conjugate to release drug in the presence of UV-light, we performed a photolysis assay, wherein the release of doxorubicin from the PhotoDox-Fol (7) was analyzed using HPLC.36 During the course of the reaction, the peaks corresponding to the PhotoDox-Fol (7) disappeared with concomitant increase in the intensity of a peak with the same retention time as Dox (Fig. 2), confirming time-dependent Dox release in the presence of light. The majority of doxorubicin was released rapidly within first 4 minutes of irradiating with the UV light (Fig. 3).</p><p>Existing reports that combine folate targeting using light sensitive vehicles commonly employ macromolecules such as dendrimers, micelles, etc. 37–39 For instance, Baker Jr. and colleagues reported synthesis of G5-PAMAM dendrimer coupled to folic acid and methotrexate (MTX), a cytotoxic analog of folic acid and, successfully tested its efficiency to target folate receptors on HeLa cells under light irradiation. 39 In a different approach, Yeh and group reported synthesis of biodegradable PLGA-lipid hybrid nanoconjugate (PLGA= poly (D, L-lactide-co-glycolide)), encapsulating Taxol (anti-microtubule agent), while the surface was coupled to photocaged folic acid to inhibit efficient permeability in cells and hence cytotoxicity. Irradiation with UV light led to uncaging of the drug, eventually leading to enhanced cell death in KB cells. 37 Although these strategies have potential advantages of avidity and the ability to release multiple drug molecules per receptor binding event, there are also some disadvantages such as slower drug release, limited endocytosis and issues with the carriers that are left behind.</p><p>PhotoDox-Fol has several advantages compared to these approaches. First, because PhotoDox-Fol is a low molecular weight compound, it is expected to be more easily endocytosed. Second, upon release, our conjugate does not leave behind any potentially toxic or hard-to-clear nanoparticles or polymers. Third, drug release from the conjugate under UV irradiation is very rapid and highly efficient even at low doses (1.1 J/cm2) (Fig. 2 and 3). Under identical conditions, the release kinetics are significantly faster than a non-folate targeted version of the molecule which required 20 minutes for full release. 21 UV-light at these low doses is also not likely to be cytotoxic on its own. 37,40,41 All these attributes make our approach amenable for rapid release of cytotoxins within folate receptor positive cancer cells.</p><p>One ongoing challenge with the use of light and therapy is the limited tissue penetration of UV light in tissue. Several recent advances in the use of longer, single-photon release such as BODIPY 42–44 and Cyanine molecules, 45 or two photon activation of photocages,46 should ultimately enable dual targeted constructs like PhotoDox-Fol to be applicable in vivo. For ultimate use, more cytotoxic cargoes than Dox will enable enhanced potency in deeper regions of tissue, since less efficient release will be required for potent activity.</p>",
"role": "user"
},
{
"content": "A major area of cancer research focuses on improving the specificity of therapeutic agents by engineering drug-delivery vehicles that target overexpressed receptors on tumor cells. One of the most commonly used approaches involves targeting of folate receptors using folic acid conjugated to a drug-containing macromolecular cargo. Once internalized via endocytosis, the drugs must be released from these constructs in order to avoid being trapped in the endosomes. Here, we describe the synthesis of a small-molecule conjugate that couples folic acid to doxorubicin via a photocleavable linker. Using HPLC we show that the doxorubicin can be released with light rapidly and with high efficiency. This approach has advantages over macromolecular systems due to its simplicity and efficiency.",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.1743 | [
{
"content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nCombined delivery approach of bone marrow mononuclear stem cells early and late after myocardial infarction : the MYSTAR prospective , randomized study . BACKGROUND Combined intracoronary and intramyocardial administration might improve outcomes for bone-marrow-derived stem cell therapy for acute myocardial infarction ( AMI ) . We compared the safety and feasibility of early and late delivery of stem cells with combined therapy approaches . METHODS Patients with left ventricular ejection fraction less than 45 % after AMI were randomly assigned stem cell delivery via intramyocardial injection and intracoronary infusion 3-6 weeks or 3-4 months after AMI . Primary end points were changes in infarct size and left ventricular ejection fraction 3 months after therapy . RESULTS A total of 60 patients were treated . The mean changes in infarct size at 3 months were -3.5 +/- 5.1 % ( 95 % CI -5.5 % to -1.5 % , P = 0.001 ) in the early group and -3.9 +/- 5.6 % ( 95 % CI -6.1 % to -1.6 % , P = 0.002 ) in the late group , and changes in ejection fraction were 3.5 +/- 5.6 % ( 95 % CI 1.3-5.6 % , P = 0.003 ) and 3.4 +/- 7.0 % ( 95 % CI 0.7-6.1 % , P = 0.017 ) , respectively . At 9-12 months after AMI , ejection fraction remained significantly higher than at baseline in both groups . In the early and late groups , a mean of 200.3 +/- 68.7 x 10 ( 6 ) and 194.8 +/- 60.4 x 10 ( 6 ) stem cells , respectively , were delivered to the myocardium , and 1.30 +/- 0.68 x 10 ( 9 ) and 1.29 +/- 0.41 x 10 ( 9 ) cells , respectively , were delivered into the artery . A high number of cells was required for significant improvements in the primary end points . CONCLUSIONS Combined cardiac stem cell delivery induces a moderate but significant improvement in myocardial infarct size and left ventricular function .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"stem cell delivery\", \"stem cells\", \"Combined delivery approach\", \"cardiac stem cell delivery\", \"bone marrow mononuclear stem cells early\", \"intracoronary infusion 3-6 weeks or 3-4 months after AMI\", \"bone-marrow-derived stem cell therapy\", \"intramyocardial injection\"], \"Outcome\": [\"and\", \"ejection fraction\", \"changes in ejection fraction\", \"safety and feasibility\", \"stem cells\", \"left ventricular function\", \"left ventricular ejection fraction 3 months after therapy\", \"mean changes in infarct size at 3 months\", \"number of cells\", \"myocardial infarct size\", \"changes in infarct size\"], \"Participant\": [\"60\", \"myocardial infarction\", \"left ventricular ejection fraction less than 45 % after AMI\"]}",
"role": "assistant"
}
]
|
science.genia_ner | science.genia_ner.992 | [
{
"content": "Analyze the provided text excerpt from a scientific document. Identify and extract distinct entities based on predefined categories.\n\nDeliver the results as a JSON structure where each key represents an entity category, and the associated value is a list of identified entities. If no entities are found for a category, return an empty list.\n\nText Excerpt:\n\nCyclosporin A inhibits early mRNA expression of G0 / G1 switch gene 2 (G0S2) in cultured human blood mononuclear cells. Cyclosporin A (CsA) may achieve its immunosuppressive effects by inhibiting the calcium-and calmodulin-dependent phosphatase calcineurin which is required for activation of target genes by members of the NFAT (nuclear factor of activated T cells) transcription factor family. Among these target genes is the gene encoding interleukin-2 (IL2), a cytokine facilitating progression through the G1 phase of the cell cycle. However, IL2 does not reverse CsA inhibition, suggesting that at least one other NFAT-sensitive gene may be involved. The human G0 / G1 switch gene, G0S2, has potential NFAT-binding sites in the 5' flank and encodes a small basic potential phosphoprotein of unknown function. Using a sensitive, reverse transcription-polymerase chain reaction (RT-PCR) assay, G0S2 mRNA levels were assayed in cultured blood mononuclear cells. Freshly isolated cells contain high levels of G0S2 mRNA which rapidly decline. This \" spontaneous stimulation \" is also noted with some other G0S genes and has been attributed to some aspect of the isolation procedure. In cells that have been preincubated to lower mRNA levels, there is a transient increase in G0S2 mRNA, peaking between 1-2 h, in response to Concanavalin-A (ConA), or to the combination of phorbol ester (TPA), and the calcium ionophore, ionomycin. Both these responses are inhibited by CsA. Our results suggest that G0S2 expression is required to commit cells to enter the G1 phase of the cell cycle, and that, while not excluding other possible targets, early inhibition of G0S2 expression by CsA may be important in achieving immunosuppression. G0S2 may be of value as a reporter gene for analyzing the mechanism of action of CsA and its influence on the positive and negative selection of lymphocytes in response to self and not-self antigens.",
"role": "user"
},
{
"content": "{\"CellLine\": [\"cultured blood mononuclear cells\", \"cultured human blood mononuclear cells\"], \"CellType\": [\"lymphocytes\"], \"DNA\": [\"G0 / G1 switch gene 2\", \"human G0 / G1 switch gene\", \"these target genes\", \"G0S genes\", \"NFAT - sensitive gene\", \"target genes\", \"NFAT - binding sites\", \"G0S2\", \"5\\u0027 flank\"], \"Protein\": [\"small basic potential phosphoprotein\", \"NFAT (nuclear factor of activated T cells) transcription factor family\", \"calcium - and calmodulin - dependent phosphatase\", \"cytokine\", \"interleukin - 2\", \"calcineurin\", \"nuclear factor of activated T cells\", \"IL2\"], \"RNA\": [\"G0S2 mRNA\"]}",
"role": "assistant"
}
]
|
science.chemsum_single_document_summarization | science.chemsum_single_document_summarization.1870 | [
{
"content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nShear stress-mediated refolding of proteins from aggregates and inclusion bodies\n\nContent Extracts:\n\n<p>Overexpressed recombinant proteins for industrial, pharmaceutical, environmental and agricultural applications annually represent a >$160 billion biotechnology world market.[1] Protein expression in yeast or Escherichia coli is highly preferred due to the organisms' rapid growth, low consumable costs, and high yields.[2, 3] However, large proteins overexpressed in bacteria often form aggregates and inclusion bodies.[4–7] Recovery of the correctly folded protein then requires laborious and expensive processing of inclusion bodies by conventional methods.[1, 8] The most common method for refolding such proteins, for example, involves multi-day dialysis with large volumes (typically 1-10 liters for mg quantities of protein).[9] Alternatively, high value proteins (e.g., therapeutic antibodies or GPCRs for structural biology) apply extensively optimized mammalian or insect cell lines, media and bioreactor conditions.[10–12] Recovery of correctly folded proteins from aggregates is inefficient and challenging for large-scale industrial processes. Mechanical methods to solve this problem have been reported. One approach applies very high hydrostatic pressures (400 bar) to refold recombinant proteins from inclusion bodies.[13–16] We report a novel method by applying finely controlled levels of shear stress to refold proteins trapped in the inclusion body. This method may be capable of broadening the utility of bacterial over-expression, and could transform industrial and research production of proteins.</p><p>We report using a vortex fluid device (VFD) to apply shear forces for rapid equilibration of protein folding and isolation of intermediates during protein folding. In this method, a glass cylinder (10 mm by 16 cm) is spun rapidly (5 krpm) at a 45° angle. At high rotational speeds, the solution within the sample tube forms micrometer-thick, thin fluid films, which flow with the same speed and direction as the wall of the glass tube. The rotating glass tube generates a velocity gradient within the thin fluid film, which introduces shear stress into the solution (Figure 1 a). We imagined applying the VFD with a similar range of input energies to refolding proteins; the device produces unusual shear within such films, and has been shown to be effective in disassembling molecular capsules,[15] and reducing the size of micelles used in the fabrication of SBA-15 mesoporous silica with control over the pore size of the material.[16] Importantly, the latter occurs at room temperature rather than requiring hydrothermal processing, and suggests that the constant 'soft' energy in the thin film has application in manipulating macromolecules, such as the refolding of proteins, without requiring heating. Other relevant applications and optimization of a similar vortex fluid device include exfoliating graphite and hexagonal boron-nitride to generate mono and multi-layer structures,[17, 18] controlling the formation of different calcium carbonate polymorphs,[19] and controlling chemical reactivity and selectivity.[20, 21]</p><p>Modeling the fluid behavior in the VFD allowed estimation of the shear forces experienced by proteins folding at various rotational speeds. Our analysis applies the solution for cylindrical Couette flow.[20, 21] The velocity of the solution, vθ, is a function of the radius, r (Figure 1 a). The boundary conditions for the liquid film interfaces are defined as follows. The inner air-liquid interface at r = R1 slips due to discontinuity in viscosity, and results in vanishingly low shear stress \n(dvθdr=0)At the outer liquid-glass interface, the no-slip boundary dictates that the velocity of the liquid at r = R2 matches that of the inner wall of the glass tube (vθ = R2 · Ω), where Ω is the angular velocity of the tube. The resulting velocity profile is a nonlinear function of the form</p><p>where</p><p>and</p><p>From this velocity profile, shear stress can be calculated as</p><p>where μ is the viscosity of water at 20 °C. At a speed of 5 krpm, the calculated shear stress ranges from 0.5246 to 0.5574 Pa (Figure 1 b). While this model provides insight into the shear stress range, the fluid flow will be perturbed by the cross vector of gravity with centrifugal force for a tube orientated at 45°,[20] which may also facilitate protein folding; this angular setting also proved optimal for the aforementioned applications of the VFD. The calculated values of shear stress are similar to the levels previously reported to cause protein unfolding,[22] and we hypothesized that short periods of VFD processing could allow equilibration of protein folding.</p><p>Experiments with native hen egg white were conducted to determine if shear forces could refold denatured hen egg white lysozyme (HEWL) in complex environments. The separated whites were diluted in PBS, and heat-treated at 90 °C for 20 min. The resultant hard-boiled egg white was dissolved in 8 M urea, rapidly diluted and then VFD-processed at the indicated rotational speeds and times (Table S1 and Figure 2 a). The total protein concentration as determined by bicinchoninic acid assay was 44 μg/ml. The recovery of HEWL activity was then demonstrated by lysozyme activity assay (Figure S1). Refolding HEWL within the egg white at 5 krpm recovers glycosidase activity even after a short 2.5 min spin, but continued shear forces unfolds the protein. As mentioned above, shear stress-mediated protein unfolding has been observed for other proteins previously. Optimization of VFD times, speeds, and concentration of chaotropic additives is required to find conditions allowing re-equilibration of protein folding without causing loss of the protein structure. VFD processing for 5 minutes at 5 krpm in 1 M urea results in optimal HEWL refolding as monitored by lysozyme activity (Figure 2 a). This experiment establishes the basic parameters for protein refolding by VFD.</p><p>To demonstrate refolding of recombinantly expressed, reduced HEWL, the cell pellet was first reconstitued in lysis buffer containing 2-mercaptoethanol, denatured in 8 M urea and rapidly diluted into PBS (1:100). Buffers used for the expression and purifications of all recombinant proteins are described, in Table S2. Second, the diluted protein (1 ml, 44 μg/ml protein) was immediately transferred to the VFD sample tube and spun at 22 °C and 5 krpm for 5 min. Circular dichroism (CD) spectra of the VFD-refolded, recombinant HEWL demonstrates restoration of secondary structure from proteins isolated from inclusion bodies. After VFD processing, the CD spectra of identical HEWL samples demonstrates partial recovery of secondary structure compared to the native lysozyme (Figure 2 b). Yields of functional protein determined by lysozyme activity assay are shown in Figure 2 d.</p><p>HEWL can also be refolded by continuous flow VFD. This approach delivers additional sample through an inlet at the cylinder base. The sample (50 ml), added at a flow-rate of 0.1 ml/min, demonstrates significant recovery of HEWL activity for scalable, high volume applications (Figure 2 c). The recombinant HEWL recovers >82% of its activity following VFD treatment. As expected, HEWL isolated from inclusion bodies without VFD processing fails to show any lysozyme activity (Figure 2 d). The continuous flow approach could be readily scaled up and parallelized for industrial applications requiring treatment of very large volumes.</p><p>After refolding denatured lysozyme in both complex (egg white) and simple (purified recombinant protein) environments, the next experiments focused on refolding the protein caveolin-1, as an example of a protein requiring an inordinate amount of processing time by conventional approaches (e.g., four days of dialysis). A caveolin variant without its transmembrane domain (caveolin-ΔTM) was recombinantly expressed, and the inclusion body was purified under denaturing conditions. Purified caveolin-ΔTM was diluted, and then given a short dialysis for 1 h to decrease the urea concentration to 1 M. The protein was then VFD-treated for 0, 10, or 30 min at 5 krpm at a concentration of 186 μg/ml. The CD spectra of the VFD processed caveolin-ΔTM shows a pronounced minima at 208 and 220 nm, which are indicative of α -helical secondary structure.[23] Solution turbidity also decreases sharply following VFD treatment, which illustrates VFD solubilization and refolding of partially aggregated proteins (Figure 3 b). ELISA experiments examined binding by the refolded caveolin-ΔTM to HIV glycoprotein 41 (gp41), a known caveolin binding partner.[24–26] VFD processing significantly restores protein function, as shown through binding to gp41 (Figure 3 c).</p><p>Larger-sized proteins initially failed to refold despite VFD treatment. For example, the catalytic domain of cAMP-dependent protein kinase A (PKA, 42 kDa) is significantly bulkier than HEWL (14 kDa) and caveolin-ΔTM (17 kDa), and did not refold from inclusion bodies after treatment with similar protocols to the above experiments. To refold full-length PKA in vitro, we adapted the VFD to provide a closer mimic of cellular folding. In cells, the nascent polypeptide can fold as the N-terminus extrudes from the ribosome, whereas in vitro refolding must address the entire protein at once.[27] Thus, we attempted to focus shear stress on the N-terminus of His-tagged PKA by binding the unfolded protein to Ni2+-charged immobilized metal affinity chromatography (IMAC) resin. The His6-PKA-IMAC complex (1 ml, 0.2 – 1 mg/ml) was then subjected to refolding by VFD. Following VFD treatment, His-PKA separated from the IMAC resin, and recovered 69% of its kinase activity (Figure 4). Interestingly, the remaining His-PKA eluted from the IMAC resin by elution with imidazole yielded far less active protein (Figure S3). We hypothesize that protein folding makes the His6 epitope less accessible for strong binding to the IMAC resin subjected to shear by the VFD. Under conventional conditions, IMAC resin binds to folded PKA, but we recovered protein remaining on the IMAC resin after VFD treatment to demonstrate its lack of folding and catalytic activity (Figure S3). Thus, as the VFD folds the protein, PKA elutes from the affinity resin. Negative control experiments with identical conditions, but with uncharged IMAC resin, decreased quantities of charged resin, or 500 mM imidazole to block the Ni2+-His6 tag interaction, showed only low levels of kinase activity (Figure 4).</p><p>As reported here, protein refolding by VFD requires optimization for each protein. Buffers, chaotrope additive, protein concentration, and processing time were optimized for HEWL, caveolin-ΔTM, and PKA. The refolding of HEWL from the complex mixture of boiled egg whites appears less efficient than recovery of the folded protein isolated from inclusion bodies. In egg whites, the mechanical energy of the VFD could be misdirected to the other >96% of proteins present.</p><p>This report offers significant advantages over conventional approaches to protein refolding. First, VFD-mediated refolding requires much smaller solution volumes (approximately 1% of the volumes required for conventional dialysis). Second, this key step in protein production occurs >100-times faster than overnight dialysis with >1000-fold improvements for proteins such as a caveolin. Notably, introducing high shear in thin fluid films is a low energy, inexpensive process, and can be readily implemented for relatively low cost in conventional biochemistry laboratories.</p><p>The advantages of VFD refolding open new possibilities for increasing protein yields in simple cell lines. Using the constant soft energy of the thin microfluidic films, the VFD can untangle complex mixtures, aggregates and insoluble inclusion bodies. In industrial and academic applications, high concentrations of a chemical inducer like IPTG could drive overexpressed proteins into insoluble inclusion bodies before VFD-based refolding. Conversely, most conventional processes avoid inclusion bodies by optimization of growth conditions and special cell lines at the expense of higher yields and purer protein isolated directly from bacterial cells. As reported here, the continuous flow mode of the VFD or parallel processing with multiple VFD units could allow scale-up to accommodate much larger solution volumes. Thus, the approach could drastically lower the time and financial costs required to refold inactive proteins at an industrial scale. The VFD sample tube itself can also be modified to amplify or otherwise direct the intensity of shear forces applied; for example, modified surfaces with high contact angle and/or with textured features could enhance the turbulent flow, altering the applied shear stress. Harnessing shear forces to achieve rapid equilibration of protein folding could be expanded to a wide-range of applications for research and manufacturing.</p>",
"role": "user"
},
{
"content": "Recombinant protein overexpression of large proteins in bacteria often results in insoluble and misfolded proteins directed to inclusion bodies. We report the application of shear stress in micrometer-wide, thin fluid films to refold boiled hen egg white lysozyme, recombinant hen egg white lysozyme, and recombinant caveolin-1. Furthermore, the approach allowed refolding of the much larger protein, cAMP-dependent protein kinase A (PKA). The reported methods require only minutes, which is >100-times faster than conventional, overnight dialysis. This rapid refolding technique could significantly shorten the times, lower costs, and reduce the waste streams associated with protein expression for a wide-range of industrial and research applications.",
"role": "assistant"
}
]
|
science.healthver_entailment | science.healthver_entailment.4164 | [
{
"content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: cloth face masks are not effective in preventing the spread of COVID-19\n\nResearch Abstract:\nBackground Protecting Health Care Workers (HCWs) during routine care of suspected or confirmed COVID-19 patients is of paramount importance to halt the SARS-CoV-2 (Severe Acute Respiratory Syndrome-Coronavirus-2) pandemic.\nThe WHO, ECDC and CDC have issued conflicting guidelines on the use of respiratory filters (N95) by HCWs.\nMethods We searched PubMed, Embase and The Cochrane Library from the inception to March 21, 2020 to identify randomized controlled trials (RCTs) comparing N95 respirators versus surgical masks for prevention of COVID-19 or any other respiratory infection among HCWs.\nThe grading of recommendations, assessment, development, and evaluation (GRADE) was used to evaluate the quality of evidence.\nFindings Four RCTs involving 8736 HCWs were included.\nWe did not find any trial specifically on prevention of COVID-19.\nHowever, wearing N95 respirators can prevent 73 more (95% CI 46-91) clinical respiratory infections per 1000 HCWs compared to surgical masks (2 RCTs; 2594 patients; low quality of evidence).\nA protective effect of N95 respirators in laboratory-confirmed bacterial colonization (RR= 0.41; 95%CI 0.28-0.61) was also found.\nA trend in favour of N95 respirators was observed in preventing laboratory-confirmed respiratory viral infections, laboratory-confirmed respiratory infection, and influenza like illness.\nInterpretation We found no direct high quality evidence on whether N95 respirators are better than surgical masks for HCWs protection from SARS-CoV-2.\nHowever, low quality evidence suggests that N95 respirators protect HCWs from clinical respiratory infections.\nThis finding should be contemplated to decide the best strategy to support the resilience of healthcare systems facing the potentially catastrophic SARS-CoV-2 pandemic.",
"role": "user"
},
{
"content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"However, wearing N95 respirators can prevent 73 more (95% CI 46-91) clinical respiratory infections per 1000 HCWs compared to surgical masks (2 RCTs; 2594 patients; low quality of evidence).\", \"A trend in favour of N95 respirators was observed in preventing laboratory-confirmed respiratory viral infections, laboratory-confirmed respiratory infection, and influenza like illness.\"]}",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.2836 | [
{
"content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nHeterozygousCbCln3Deltaex7/8cellscontainedamixtureofCln3mRNAproductsfromboththewild-typealleleandthemutantallele,andbatp1signalwassimilartothatseeninwild-typecells(datanotshown).",
"role": "user"
},
{
"content": "[\"mRNA products\"]",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.607 | [
{
"content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: Quality of Service of Routing Protocols in Wireless Sensor Networks: A Review \nChapter Title: a: RACOON \n1. Abstract of Cited Paper (BIB001): A Sensor Equipped Aquatic (SEA) swarm is a sensor cloud that drifts with water currents and enables 4-D (space and time) monitoring of local underwater events such as contaminants, marine life, and intruders. The swarm is escorted on the surface by drifting sonobuoys that collect data from the underwater sensors via acoustic modems and report it in real time via radio to a monitoring center. The goal of this study is to design an efficient anycast routing algorithm for reliable underwater sensor event reporting to any surface sonobuoy. Major challenges are the ocean current and limited resources (bandwidth and energy). In this paper, these challenges are addressed, and HydroCast, which is a hydraulic-pressure-based anycast routing protocol that exploits the measured pressure levels to route data to the surface sonobuoys, is proposed. This paper makes the following contributions: a novel opportunistic routing mechanism to select the subset of forwarders that maximizes the greedy progress yet limits cochannel interference and an efficient underwater dead end recovery method that outperforms the recently proposed approaches. The proposed routing protocols are validated through extensive simulations.\n\nReview Chapter:",
"role": "user"
},
{
"content": "In BIB001 , this issue of the mobility of the networks and priority scheme for medical applications are addressed. Network Lee et al. BIB002 have proposed a protocol called HydroCast. It takes the node mobility into consideration which enhances the propagation delay performance and energy consumption. It takes the wireless channel quality into consideration to improve the routeing performance under continuous node movement conditions.",
"role": "assistant"
}
]
|
science.healthver_entailment | science.healthver_entailment.2068 | [
{
"content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: Masks can lead to pneumonia or other lung infections\n\nResearch Abstract:\nHerein, we report that nosocomial infection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) may be mitigated by using surgical masks and closed looped ventilation for both non-critical and critical patients.\nThese preventive measures resulted in no viral contamination of surfaces in negative pressure environments.",
"role": "user"
},
{
"content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"Herein, we report that nosocomial infection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) may be mitigated by using surgical masks and closed looped ventilation for both non-critical and critical patients.\"]}",
"role": "assistant"
}
]
|
science.cdr_ner | science.cdr_ner.121 | [
{
"content": "Examine the provided text to identify entities. Focus on extracting relevant information.\n\nPresent your findings in a structured JSON format. Each category should list the entities found.\n\nSource Material:\n\nEffect of some anticancer drugs and combined chemotherapy on renal toxicity. The nephrotoxic action of anticancer drugs such as nitrogranulogen (NG), methotrexate (MTX), 5-fluorouracil (5-FU) and cyclophosphamide (CY) administered alone or in combination [MTX + 5-FU + CY (CMF)] was evaluated in experiments on Wistar rats. After drug administration, creatinine concentrations in the plasma and in the urine of the rats were determined, as well as creatinine clearance. Histopathologic evaluation of the kidneys was also performed. After MTX administration a significant increase (p = 0.0228) in the plasma creatinine concentration and a significant (p = 0.0001) decrease in creatinine clearance was noted compared to controls. After the administration of NG, 5-FU and CY neither a statistically significant increase in creatinine concentration nor an increase in creatinine clearance was observed compared to the group receiving no cytostatics. Following polytherapy according to the CMF regimen, a statistically significant decrease (p = 0.0343) in creatinine clearance was found, but creatinine concentration did not increase significantly compared to controls. CY caused hemorrhagic cystitis in 40% of rats, but it did not cause this complication when combined with 5-FU and MTX. Histologic changes were found in rat kidneys after administration of MTX, CY and NG, while no such change was observed after 5-FU and joint administration of MTX + 5-FU + CY compared to controls. Our studies indicate that nephrotoxicity of MTX + 5-FU + CY administered jointly is lower than in monotherapy.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"nitrogranulogen\", \"5-FU\", \"NG\", \"MTX\", \"5-fluorouracil\", \"creatinine\", \"CY\", \"methotrexate\", \"cyclophosphamide\"], \"Disease\": [\"nephrotoxicity\", \"hemorrhagic cystitis\", \"renal toxicity\", \"hemorrhagic\", \"cystitis\", \"nephrotoxic\"]}",
"role": "assistant"
}
]
|
science.bc7_litcovid_topic_classification | science.bc7_litcovid_topic_classification.4550 | [
{
"content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nBACKGROUND AND AIMS: Although coronavirus disease 2019 (COVID-19) has affected endoscopy services globally, the impact on trainees has not been evaluated. We aimed to assess the impact of COVID-19 on procedural volumes and on the emotional well-being of endoscopy trainees worldwide. METHODS: An international survey was disseminated over a 3-week period in April 2020. The primary outcome was the percentage reduction in monthly procedure volume before and during COVID-19. Secondary outcomes included potential variation of COVID-19 impact between different continents and rates and predictors of anxiety and burnout among trainees. RESULTS: Across 770 trainees from 63 countries, 93.8% reported a reduction in endoscopy case volume. The median percentage reduction in total procedures was 99% (interquartile range, 85%-100%), which varied internationally (P < .001) and was greatest for colonoscopy procedures. Restrictions in case volume and trainee activity were common barriers. A total of 71.9% were concerned that the COVID-19 pandemic could prolonged training. Anxiety was reported in 52.4% of respondents and burnout in 18.8%. Anxiety was independently associated with female gender (odds ratio [OR], 2.15; P < .001), adequacy of personal protective equipment (OR, 1.75; P = .005), lack of institutional support for emotional health (OR, 1.67; P = .008), and concerns regarding prolongation of training (OR, 1.60; P = .013). Modifying existing national guidelines to support adequate endoscopy training during the pandemic was supported by 68.9%. CONCLUSIONS: The COVID-19 pandemic has led to restrictions in endoscopic volumes and endoscopy training, with high rates of anxiety and burnout among endoscopy trainees worldwide. Targeted measures by training programs to address these key issues are warranted to improve trainee well-being and support trainee education.",
"role": "user"
},
{
"content": "[\"Prevention\"]",
"role": "assistant"
}
]
|
science.chemdner_ner | science.chemdner_ner.554 | [
{
"content": "Analyze the given text to identify specific entities. Focus on extracting relevant data.\n\nProvide your findings in JSON format. Each category should list the entities found.\n\nText:\n\nEGCG inhibits CTGF expression via blocking NF-κB activation in cardiac fibroblast. Connective tissue growth factor (CTGF) has been reported to play an important role in tissue fibrosis and presents a promising therapeutic target for fibrotic diseases. In heart, inappropriate increase in level of CTGF promotes fibroblast proliferation and extracellular matrix (ECM) accumulation, thereby exacerbating cardiac hypertrophy and subsequent failure. Epigallocatechin-3-gallate (EGCG), the major polyphenol found in green tea, possesses multiple protective effects on the cardiovascular system including cardiac fibrosis. However, the molecular mechanism by which EGCG exerts its anti-fibrotic effects has not been well investigated. In this study, we found that EGCG could significantly reduce collagen synthesis, fibronectin (FN) expression and cell proliferation in rat cardiac fibroblasts stimulated with angiotensinII (AngII). It also ameliorated cardiac fibrosis in rats submitted to abdominal aortic constriction (AAC). Moreover, EGCG attenuated the excessive expression of CTGF induced by AAC or AngII, and reduced the nuclear translocation of NF-κB p65 subunit and degradation of IκB-α. Subsequently, we demonstrated that in cardiac fibroblasts NF-κB inhibition could suppress AngII-induced CTGF expression. Taken together, these findings provide the first evidence that the effect of EGCG against cardiac fibrosis may be attributed to its inhibition on NF-κB activation and subsequent CTGF overexpression, suggesting the therapeutic potential of EGCG on the prevention of cardiac remodeling in patients with pressure overload hypertrophy.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"polyphenol\", \"Epigallocatechin-3-gallate\", \"EGCG\"]}",
"role": "assistant"
}
]
|
science.healthver_entailment | science.healthver_entailment.894 | [
{
"content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: Cold weather kills coronavirus 2019 and 13 other COVID-19\n\nResearch Abstract:\nThe undefendable outbreak of novel coronavirus (SARS-COV-2) lead to a global health emergency due to its higher transmission rate and longer symptomatic duration, created a health surge in a short time.\nSince Nov 2019 the outbreak in China, the virus is spreading exponentially everywhere.\nThe current study focuses on the relationship between environmental parameters and the growth rate of COVID-19.\nThe statistical analysis suggests that the temperature changes retarded the growth rate and found that -6.28{degrees}C and +14.51{degrees}C temperature is the favorable range for COVID-19 growth.\nGutenberg- Richter's relationship is used to estimate the mean daily rate of exceedance of confirmed cases concerning the change in temperature.\nTemperature is the most influential parameter that reduces the growth at the rate of 13-16 cases/day with a 1{degrees}C rise in temperature.",
"role": "user"
},
{
"content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"The statistical analysis suggests that the temperature changes retarded the growth rate and found that -6.28{degrees}C and +14.51{degrees}C temperature is the favorable range for COVID-19 growth.\", \"Temperature is the most influential parameter that reduces the growth at the rate of 13-16 cases/day with a 1{degrees}C rise in temperature.\"]}",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.4161 | [
{
"content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nA weakly supervised learning based clustering framework is proposed in this paper. As the core of this framework, we introduce a novel multiple instance learning task based on a bag level label called unique class count ( @math ), which is the number of unique classes among all instances inside the bag. In this task, no annotations on individual instances inside the bag are needed during training of the models. We mathematically prove that a perfect @math classifier, in principle, can be used to perfectly cluster individual instances inside the bags. In other words, perfect clustering of individual instances is possible even when no annotations on individual instances are given during training. We have constructed a neural network based @math classifier and experimentally shown that the clustering performance of our framework with our @math classifier is comparable to that of fully supervised learning models. We have also observed that our @math classifiers can potentially be used for zero-shot learning as they learn better semantic features than fully supervised models for unseen classes', which have never been input into the models during training.\n\nCited Works Summary:\n[1]: Multiple-instance problems arise from the situations where training class labels are attached to sets of samples (named bags), instead of individual samples within each bag (called instances). Most previous multiple-instance learning (MIL) algorithms are developed based on the assumption that a bag is positive if and only if at least one of its instances is positive. Although the assumption works well in a drug activity prediction problem, it is rather restrictive for other applications, especially those in the computer vision area. We propose a learning method, MILES (multiple-instance learning via embedded instance selection), which converts the multiple-instance learning problem to a standard supervised learning problem that does not impose the assumption relating instance labels to bag labels. MILES maps each bag into a feature space defined by the instances in the training bags via an instance similarity measure. This feature mapping often provides a large number of redundant or irrelevant features. Hence, 1-norm SVM is applied to select important features as well as construct classifiers simultaneously. We have performed extensive experiments. In comparison with other methods, MILES demonstrates competitive classification accuracy, high computation efficiency, and robustness to labeling uncertainty",
"role": "user"
},
{
"content": "MIL algorithms are grouped into three: , and , in which each bag is transformed to a feature vector and discriminative classifier trained on feature vectors in embedded space [1] . Our @math model also employs embedded-space paradigm such that each bag embedding is done by using KDE on feature vectors of instances inside the bag, which are extracted by a neural network.",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_elife_single_doc_summ | science.scientific_lay_summarisation_elife_single_doc_summ.1122 | [
{
"content": "Transform the provided sections of a biomedical research paper into a digestible summary for a general audience. Focus on simplifying complex ideas while retaining key scientific insights.\n\nResearch Title: Dreaming with hippocampal damage\nContent Overview:\nAbstract:\nThe hippocampus is linked with both sleep and memory, but there is debate about whether a salient aspect of sleep – dreaming – requires its input. To address this question, we investigated if human patients with focal bilateral hippocampal damage and amnesia engaged in dreaming. We employed a provoked awakening protocol where participants were woken up at various points throughout the night, including during non-rapid eye movement and rapid eye movement sleep, to report their thoughts in that moment. Despite being roused a similar number of times, dream frequency was reduced in the patients compared to control participants, and the few dreams they reported were less episodic-like in nature and lacked content. These results suggest that hippocampal integrity may be necessary for typical dreaming to occur, and aligns dreaming with other hippocampal-dependent processes such as episodic memory that are central to supporting our mental life.\nIntroduction:\nDreaming has intrigued humans for thousands of years, being variously interpreted as having premonitory, religious, psychoanalytic, or mnemonic significance. Defined as an internally-generated subjective mental experience during the sleep state( Cipolli et al., 2017), dreaming can be present at initial sleep onset( hypnagogic sleep; Horikawa et al., 2013; Stickgold et al., 2000), during non-rapid eye movement( NREM) sleep( Antrobus et al., 1995; Foulkes, 1962; Nielsen, 2000; Siclari et al., 2017; Wamsley, 2013; Wamsley et al., 2007), and rapid eye movement( REM) sleep( Hobson et al., 2000; Maquet et al., 2000; Maquet et al., 2005). Although dreams are not a precise replay of our memories( Fosse et al., 2003; Stickgold et al., 2001a), it has been proposed that dreaming may be associated with memory consolidation processes( Payne, 2010; Wamsley, 2014; Wamsley et al., 2010; Wamsley and Stickgold, 2019). Indeed, in rodents and humans, patterns of brain activity exhibited during a learning experience were found to be subsequently expressed during sleep( Peigneux et al., 2004; Wilson and McNaughton, 1994). Bilateral damage to a brain structure called the hippocampus is known to adversely affect memory processing( Miller et al., 2017; Miller et al., 2020; Scoville and Milner, 1957; Spiers et al., 2001) and daydreaming( McCormick et al., 2018). While sleep dreaming has been examined previously in patients with hippocampal lesions, results are mixed, with some studies reporting repetitious and stereotyped dreams( Torda, 1969a; Torda, 1969b; Stickgold et al., 2000), whereas others claim that hippocampal damage has no effect on dreaming( Solms, 1997; Solms, 2013). Possible reasons for these disparate findings include differences in the sleep stages sampled, the inclusion in several studies of patients with psychiatric conditions and below-average IQ and, in other instances, patients were interviewed at a point temporally remote from any dreaming that might have occurred, presenting a challenge for these patients who usually suffer from amnesia. It remains uncertain, therefore, whether hippocampal integrity is necessary for dreaming to occur. If, as we predicted, bilateral hippocampal damage degrades dreaming, this would reinforce the link between dreaming and hippocampal-dependent processes such as memory, potentially moving us closer to an understanding of why we dream. By contrast, if hippocampal-damaged patients who have a reduced ability to experience complex, imagery-rich, spatio-temporal mental events during wake are nevertheless able to have such experiences during sleep, this would need to be explicitly accounted for within theories of hippocampal function. Here, we sought to mitigate the issues affecting previous studies while investigating the frequency, features and content of dreaming in rare patients with selective bilateral hippocampal damage and matched control participants. To do this we employed a provoked awakening protocol( Nguyen et al., 2013; Siclari et al., 2013; Wamsley et al., 2016). This widely-used approach involved waking participants up at various times during their night’s sleep to report their thoughts in that moment. In this way we examined sleep mentation in a direct and immediate manner.\nDiscussion:\nBy studying rare patients with selective bilateral hippocampal damage we found that dream frequency was reduced compared to control participants, and the few dreams they had were less episodic-like in nature and lacked content. This accords with previous studies that reported stereotyped dreaming in patients with brain damage that extended beyond the hippocampi( Torda, 1969a; Torda, 1969b; Stickgold et al., 2000), and echoes the effects of hippocampal damage on imagination( Hassabis et al., 2007), episodic memory( Miller et al., 2017; Miller et al., 2020; Spiers et al., 2001) and daydreaming( McCormick et al., 2018). Given our patients’ circumscribed lesions, these results suggest that hippocampal integrity may be necessary for typical dreaming to occur. There are several possible explanations for degraded dreaming in the patients, which we consider in turn. Despite the tendency to confine dreaming to the sleep state, studies have shown that there is often continuity between waking life experiences and dreaming( Andrillon et al., 2015; Fosse et al., 2003; Horikawa et al., 2013; Schredl and Hofmann, 2003). Given that the patients had difficulty retaining information over longer time scales while awake, then perhaps during subsequent sleep there was little material to process. Hence it could be that the capacity to dream was intact, but underused, in the patients. Alternatively, the core capacity for dreaming might have been compromised, with this in turn affecting memory processing. Dreaming has been linked with the consolidation of information into long-term memory( Payne, 2010; Wamsley, 2013; Wamsley, 2014; Wamsley et al., 2010; Wamsley and Stickgold, 2019), but it is unknown whether dreaming plays a functional role in this process( Wamsley, 2014). If it does, then patients with hippocampal damage may lack this dream-related mechanism for facilitating memory processing, and this could contribute to their amnesia. Another aspect of sleep that has been associated with episodic memory consolidation is slow-wave sleep( SWS), a stage within NREM sleep( Rasch and Born, 2013). We have previously shown that the hippocampal-damaged patients tested here had significantly reduced SWS and slow wave activity, whereas the time spent in other sleep stages was comparable to that of control participants( Spanò et al., 2020). It is unlikely that the patients’ degraded dreaming was caused solely by decreased SWS. This is because we sampled dreaming across both NREM and REM sleep, and of the dreams sampled during NREM sleep in the control participants, just 5%( SD 11. 3) were during SWS. Overall, however, reduced slow wave activity along with sub-optimal dreaming – if dreaming plays a functional role – may constitute a twofold blow that adversely affected the proper functioning of episodic memory in these patients. A different perspective on the current results involves looking beyond memory. The hippocampus has been implicated in a range of other cognitive functions including thinking about the future( Addis et al., 2007; Hassabis et al., 2007; Kurczek et al., 2015), spatial navigation( Maguire et al., 2006; O'Keefe and Nadel, 1978), daydreaming( Karapanagiotidis et al., 2017; McCormick et al., 2018), aspects of decision making( Mullally and Maguire, 2014; McCormick et al., 2016), and visual perception( Lee et al., 2005; McCormick et al., 2017; Mullally et al., 2012). Patients with bilateral hippocampal damage are also impaired at mentally constructing scene imagery( Hassabis et al., 2007), and scene imagery features prominently across cognition( Clark et al., 2019; Clark et al., 2020). Consequently, it has been proposed that one role of the hippocampus could be to facilitate the scene construction process( Hassabis and Maguire, 2007; Maguire and Mullally, 2013). This may explain why dreaming is degraded in the context of hippocampal pathology, as it too typically involves( and possibly requires) scene imagery. In summary, while the functional role of dreaming is as yet unknown, we conclude from our results that hippocampal integrity may be a prerequisite for typical dreaming to occur, and that dreaming seems to align with an array of other cognitive functions that are hippocampal-dependent and which play crucial roles in supporting our everyday mental life.",
"role": "user"
},
{
"content": "Dreaming has intrigued humans for thousands of years , but why we dream still remains somewhat of a mystery . Although dreams are not a precise replay of our memories , one idea is that dreaming helps people process past experiences as they sleep . If this is true , then part of the brain called the hippocampus that is important for memory should also be necessary for dreaming . Damage to the hippocampus can cause a condition called amnesia that prevents people from forming new memories and remembering past experiences . However , studies examining dreaming in people with amnesia have produced mixed results: some found that damage to the hippocampus had no effect on dreams , while others found it caused people to have repetitive dreams that lacked detail . One reason for these inconsistencies is that some studies asked participants about their dreams the next morning by which time most people , particularly those with amnesia , have forgotten if they dreamed . To overcome this limitation , Spanò et al . asked participants about their dreams immediately after being woken up at various points during the night . The experiment was carried out with four people who had damage to both the left and right hippocampus and ten healthy volunteers . Spanò et al . found that the people with hippocampal damage reported fewer dreams and the dreams they had were much less detailed . These findings suggest that a healthy hippocampus is necessary for both memory and dreaming , reinforcing the link between the two . Hippocampal damage is associated with a number of diseases , including dementia . If these diseases cause patients to dream less , this may worsen the memory difficulties associated with these conditions .",
"role": "assistant"
}
]
|
science.chemdner_ner | science.chemdner_ner.393 | [
{
"content": "Analyze the given text to identify specific entities. Focus on extracting relevant data.\n\nProvide your findings in JSON format. Each category should list the entities found.\n\nText:\n\nFungicide prochloraz and environmental pollutant dioxin induce the ABCG2 transporter in bovine mammary epithelial cells by the arylhydrocarbon receptor signaling pathway. The molecular mechanisms by which environmental pollutants including 2,3,7,8-tetrachlorodibenzo-p-dioxin (TCDD) or widely used imidazole fungicide prochloraz display their toxic effects in vertebrates are still not well understood. Using computer analysis, we recently identified nuclear aryl hydrocarbon receptor (AhR) binding sites termed \"dioxin response elements\" (DREs) in the 5'-untranslated region (5'-UTR) of efflux transporter ABCG2 (Accession No. EU570105) from the bovine mammary gland. As these regulatory motifs mediate regulation of target genes by AhR agonists including TCDD and prochloraz, we have systematically investigated the effect of both contaminants on functional ABCG2 transport activity in primary bovine mammary epithelial cells. TCDD or prochloraz doubled ABCG2-mediated Hoechst H33342 secretion. This effect was almost completely reversed by specific ABCG2 inhibitor Ko143. In further mechanistic studies, we showed that this induction was due to binding of activated AhR to DRE sequences in the ABCG2 5'-UTR. Receptor binding was significantly reduced by specific AhR antagonist salicyl amide. Induction of AhR by TCDD and prochloraz resulted in a time- and dose-dependent increase of ABCG2 gene expression and transporter protein levels. As ABCG2 represents the main mammary transporter for xenobiotics including drugs and toxins, exposure to prevalent AhR agonists may enhance transporter-mediated secretion of potential harmful compounds into milk. Through identification of mammary ABCG2 as a novel target gene of pesticide prochloraz and dioxin, our results may therefore help to improve the protection of breast-feeding infants and the consumer of dairy products.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"Ko143\", \"salicyl amide\", \"arylhydrocarbon\", \"imidazole\", \"aryl hydrocarbon\", \"prochloraz\", \"dioxin\", \"Hoechst H33342\", \"2,3,7,8-tetrachlorodibenzo-p-dioxin\", \"TCDD\"]}",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.4839 | [
{
"content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nA recent data visualization literacy study shows that most people cannot read networks that use hierarchical cluster representations such as \"super-noding\" and \"edge bundling.\" Other studies that compare standard node-link representations with map-like visualizations show that map-like visualizations are superior in terms of task performance, memorization and engagement. With this in mind, we propose the Zoomable Multilevel Tree (ZMLT) algorithm for map-like visualization of large graphs that is representative, real, persistent, overlap-free labeled, planar, and compact. These six desirable properties are formalized with the following guarantees: (1) The abstract and embedded trees represent the underlying graph appropriately at different level of details (in terms of the structure of the graph as well as the embedding thereof); (2) At every level of detail we show real vertices and real paths from the underlying graph; (3) If any node or edge appears in a given level, then they also appear in all deeper levels; (4) All nodes at the current level and higher levels are labeled and there are no label overlaps; (5) There are no crossings on any level; (6) The drawing area is proportional to the total area of the labels. This algorithm is implemented and we have a functional prototype for the interactive interface in a web browser.\n\nCited Works Summary:\n[1]: We consider a class of optimization problems where the input is an undirected graph with two weight functions defined for each node, namely the node's profit and its cost. The goal is to find a connected set of nodes of low cost and high profit. We present approximation algorithms for three natural optimization criteria that arise in this context, all of which are NP-hard. The budget problem asks for maximizing the profit of the set subject to a budget constraint on its cost. The quota problem requires minimizing the cost of the set subject to a quota constraint on its profit. Finally, the prize collecting problem calls for minimizing the cost of the set plus the profit (here interpreted as a penalty) of the complement set. For all three problems, our algorithms give an approximation guarantee of @math , where @math is the number of nodes. To the best of our knowledge, these are the first approximation results for the quota problem and for the prize collecting problem, both of which are at least as hard to approximate as the set cover. For the budget problem, our results improve on a previous @math result of Our methods involve new theorems relating tree packings to (node) cut conditions. We also show similar theorems (with better bounds) using edge cut conditions. These imply bounds for the analogous budget and quota problems with edge costs which are comparable to known (constant factor) bounds.\n\n[2]: \n\n[3]: The Steiner tree problem is one of the most fundamental NP-hard problems: given a weighted undirected graph and a subset of terminal nodes, find a minimum-cost tree spanning the terminals. In a sequence of papers, the approximation ratio for this problem was improved from 2 to the current best 1.55 [Robins,Zelikovsky-SIDMA'05]. All these algorithms are purely combinatorial. A long-standing open problem is whether there is an LP-relaxation for Steiner tree with integrality gap smaller than 2 [Vazirani,Rajagopalan-SODA'99]. In this paper we improve the approximation factor for Steiner tree, developing an LP-based approximation algorithm. Our algorithm is based on a, seemingly novel, iterative randomized rounding technique. We consider a directed-component cut relaxation for the k-restricted Steiner tree problem. We sample one of these components with probability proportional to the value of the associated variable in the optimal fractional solution and contract it. We iterate this process for a proper number of times and finally output the sampled components together with a minimum-cost terminal spanning tree in the remaining graph. Our algorithm delivers a solution of cost at most ln(4) times the cost of an optimal k-restricted Steiner tree. This directly implies a ln(4)+e\n\n[4]: Abstract In this paper we study the Steiner tree problem in graphs for the case when vertices as well as edges have weights associated with them. A greedy approximation algorithm based on “spider decompositions” was developed by Klein and Ravi for this problem. This algorithm provides a worst case approximation ratio of 2 ln k , where k is the number of terminals. However, the best known lower bound on the approximation ratio is (1− o (1)) ln k , assuming that NP ⊈ DTIME [ n O (log log n ) ], by a reduction from set cover. We show that for the unweighted case we can obtain an approximation factor of ln k . For the weighted case we develop a new decomposition theorem and generalize the notion of “spiders” to “branch-spiders” that are used to design a new algorithm with a worst case approximation factor of 1.5 ln k . We then generalize the method to yield an approximation factor of (1.35+ e ) ln k , for any constant e >0. These algorithms, although polynomial, are not very practical due to their high running time, since we need to repeatedly find many minimum weight matchings in each iteration. We also develop a simple greedy algorithm that is practical and has a worst case approximation factor of 1.6103 ln k . The techniques developed for this algorithm imply a method of approximating node weighted network design problems defined by 0–1 proper functions as well. These new ideas also lead to improved approximation guarantees for the problem of finding a minimum node weighted connected dominating set. The previous best approximation guarantee for this problem was 3 ln n by Guha and Khuller. By a direct application of the methods developed in this paper we are able to develop an algorithm with an approximation factor of (1.35+ e ) ln n for any fixed e >0.\n\n[5]: This paper studies a multi-facility network synthesis problem, called the Two-level Network Design (TLND) problem, that arises in the topological design of hierarchical communication, transportation, and electric power distribution networks. We are given an undirected network containing two types of nodes---primary and secondary---and fixed costs for installing either a primary or a secondary facility on each edge. Primary nodes require higher grade interconnections than secondary nodes, using the more expensive primary facilities. The TLND problem seeks a minimum cost connected design that spans all the nodes, and connects primary nodes via edges containing primary facilities; the design can use either primary or secondary edges to connect the secondary nodes. The TLND problem generalizes the well-known Steiner network problem and the hierarchical network design problem. In this paper, we study the relationship between alternative model formulations for this problem (e.g., directed and undirected models), and analyze the worst-case performance for a composite TLND heuristic based upon solving embedded subproblems (e.g., minimum spanning tree and either Steiner tree or shortest path subproblems). When the ratio of primary to secondary costs is the same for all edges and when we solve the embedded subproblems optimally, the worst-case performance ratio of the composite TLND heuristic is 4 3. This result applies to the hierarchical network design problem with constant primary-to-secondary cost ratio since its subproblems are shortest path and minimum spanning tree problems. For more general situations, we express the TLND heuristic worst-case ratio in terms of the performance of any heuristic used to solve the embedded Steiner tree subproblem. A companion paper develops and tests a dual ascent procedure that generates tight upper and lower bounds on the optimal value of a multi-level extension of this problem.\n\n[6]: Consider the following classical network design problem: a set of terminals T = [t i wants to send traffic to a \"root\" r in an n-node graph G = (V,E). Each terminal t i sends d i units of traffic, and enough bandwidth has to be allocated on the edges to permit this. However, bandwidth on an edge e can only be allocated in integral multiples of some base capacity u e --- and hence provisioning k x u e bandwidth on edge e incurs a cost of [k] times the cost of that edge. The objective is a minimum-cost feasible solution.This is one of many network design problems widely studied where the bandwidth allocation being governed by side constraints: edges may only allow a subset of cables to be purchased on them, or certain quality-of-service requirements may have to be met.In this work, we show that the above problem, and in fact, several basic problems in this general network design framework, cannot be approximated better than Ω(log log n) unless NP ⊆ DTIME (nO(log log log n). In particular, we show that this inapproximability threshold holds for (i) the Priority-Steiner Tree problem [7], (ii) the Cost-Distance problem [31], and the single-sink version of an even more fundamental problem, (iii) Fixed Charge Network Flow [33]. Our results provide a further breakthrough in the understanding of the level of complexity of network design problems. These are the first non-constant hardness results known for all these problems.\n\n[7]: \n\n[8]: \n\n[9]: An improved card for use in an automated machine to detect the continued existence of microbes in a plurality of wells containing different media so that the organism can be speciated. The card includes an improved configuration wherein the wells have different reduced oxygen environments and all of the wells have an improved bubble chamber connected to the well by a bifurcated passage.\n\n[10]: We give the first approximation algorithm for the node-weighted Steiner tree problem. Its performance guarantee is within a constant factor of the best possible unless @math . Our algorithm generalizes to handle other network design problems.\n\n[11]: We consider a network design problem, where applications require various levels of Quality-of-Service (QoS) while connections have limited performance. Suppose that a source needs to send a message to a heterogeneous set of receivers. The objective is to design a low-cost multicast tree from the source that would provide the QoS levels (e.g., bandwidth) requested by the receivers. We assume that the QoS level required on a link is the maximum among the QoS levels of the receivers that are connected to the source through the link. In accordance, we define the cost of a link to be a function of the QoS level that it provides. This definition of cost makes this optimization problem more general than the classical Steiner tree problem. We consider several variants of this problem all of which are proved to be NP-Hard. For the variant where QoS levels of a link can vary arbitrarily and the cost function is linear in its QoS level, we give a heuristic that achieves a multicast tree with cost at most a constant times the cost of an optimal multicast tree. The constant depends on the best constant approximation ratio of the classical Steiner tree problem. For the more general variant, where each link has a given QoS level and cost we present a heuristic that generates a multicast tree with cost O(min log r, k ) times the cost of an optimal tree, where r denotes the number of receivers, and k denotes the number of different levels of QoS required. We generalize this result to hold for the case of many multicast groups.\n\n[12]: Given a graph @math and a subset @math of terminals, a of @math is a tree that spans @math . In the vertex-weighted Steiner tree (VST) problem, each vertex is assigned a non-negative weight, and the goal is to compute a minimum weight Steiner tree of @math . We study a natural generalization of the VST problem motivated by multi-level graph construction, the (V-GSST), which can be stated as follows: given a graph @math and terminals @math , where each terminal @math requires a facility of a minimum grade of service @math , compute a Steiner tree @math by installing facilities on a subset of vertices, such that any two vertices requiring a certain grade of service are connected by a path in @math with the minimum grade of service or better. Facilities of higher grade are more costly than facilities of lower grade. Multi-level variants such as this one can be useful in network design problems where vertices may require facilities of varying priority. While similar problems have been studied in the edge-weighted case, they have not been studied as well in the more general vertex-weighted case. We first describe a simple heuristic for the V-GSST problem whose approximation ratio depends on @math , the number of grades of service. We then generalize the greedy algorithm of [Klein & Ravi, 1995] to show that the V-GSST problem admits a @math -approximation, where @math is the set of terminals requiring some facility. This result is surprising, as it shows that the (seemingly harder) multi-grade problem can be approximated as well as the VST problem, and that the approximation ratio does not depend on the number of grades of service.",
"role": "user"
},
{
"content": "Steiner Trees: The Steiner tree problem is one of Karp's original 21 NP-Complete problems [3]0 . A polynomial time approximation scheme exists if the underlying graph is planar [3]9 , but not for general graphs [7] . More importantly, the Steiner tree can be efficiently approximated within a factor of @math [3] . In the vertex-weighted Steiner tree problem, the cost of the tree is determined by the weights of the vertices included in the solution (rather than the weights of the edges). This version of problem is also NP-hard [1] but can be approximated within a logarithmic factor [3]1 [10] . The classic Steiner tree problem has also generalized to a multi-level setting [5] [11] [6] , where the terminals appear on different levels and must be connected by edges of appropriate levels, as described in the introduction. In particular, Ahmed . [2] showed that the standard (edge-weighted) Steiner tree problem can be efficiently approximated to within a constant factor. Similarly, Darabi [12] described a multi-level version of the vertex-weighted Steiner tree, and showed that it can be approximated as well as the single-level version.",
"role": "assistant"
}
]
|
science.healthver_entailment | science.healthver_entailment.3831 | [
{
"content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: What does it feel like to recover from Covid-19? - It can take a while to feel normal after a viral infection.\n\nResearch Abstract:\nCOVID-19 caused by SARS-CoV-2 has recently affected over 200,000 people and killed more than 8000.\nImmune system dysregulation such as lymphopenia and inflammatory cytokine storm has been observed in COVID-19 patients, but it remains unclear for the change of key immune cell subsets and their states during COVID-19.\nHere, we applied single-cell technology to comprehensively characterize transcriptional changes of peripheral blood mononuclear cells in ten patients recovered from COVID-19.\nCompared with healthy control, COVID-19 induced a unique signature of immune cells in humans, especially in the early recovery stage (ERS).\nIn ERS patients, T cells were decreased remarkably, while monocytes were increased.\nA detailed analysis of monocytes showed that there was an increased ratio of classical CD14++ monocytes with highly inflammatory genes expression, as well as a greater abundance of CD14++IL1B+ monocytes.\nFor nature killer (NK) cells and T cells, CD4+ T cells were significantly decreased and expressed high level of inflammatory markers, while NK cells were increased.\nIn addition, T cells were highly expanded clone, especially in CD4+ T memory cells and CD8+ T cells.\nAmong B cells, plasma cells were increased remarkably, and naïve B cells were reduced.\nOur study also identified several novel B cell receptor (BCR) changes (such as IGHV1-8 and IGHV3-7), and confirmed isotypes (IGKV3-11 and IGHV3-21) previously used for virus vaccine development.\nThe strongest pairing frequencies, IGHV3-23+IGHJ4, indicated a monoclonal state associated with SARS-CoV-2 specificity.\nFurthermore, integrated analysis predicated that IL-1B and M-CSF may be novel candidate target gene for inflammatory storm, and TNFSF13, IL-18 and IL-4 may be benefit for the recovery of COVID-19 patients.\nOur study provides the first evidence of inflammatory immune signature in early recovery stage, suggesting that the COVID-19 patients are still vulnerable after hospital discharge.\nOur identification of novel BCR signaling may lead to the development of vaccine and antibodies for the treatment of COVID-19.",
"role": "user"
},
{
"content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Our study provides the first evidence of inflammatory immune signature in early recovery stage, suggesting that the COVID-19 patients are still vulnerable after hospital discharge.\"]}",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_elife_single_doc_summ | science.scientific_lay_summarisation_elife_single_doc_summ.2044 | [
{
"content": "Transform the provided sections of a biomedical research paper into a digestible summary for a general audience. Focus on simplifying complex ideas while retaining key scientific insights.\n\nResearch Title: Resilience of small intestinal beneficial bacteria to the toxicity of soybean oil fatty acids\nContent Overview:\nAbstract:\nOver the past century, soybean oil( SBO) consumption in the United States increased dramatically. The main SBO fatty acid, linoleic acid( 18:2), inhibits in vitro the growth of lactobacilli, beneficial members of the small intestinal microbiota. Human-associated lactobacilli have declined in prevalence in Western microbiomes, but how dietary changes may have impacted their ecology is unclear. Here, we compared the in vitro and in vivo effects of 18:2 on Lactobacillus reuteri and L. johnsonii. Directed evolution in vitro in both species led to strong 18:2 resistance with mutations in genes for lipid biosynthesis, acid stress, and the cell membrane or wall. Small-intestinal Lactobacillus populations in mice were unaffected by chronic and acute 18:2 exposure, yet harbored both 18:2- sensitive and resistant strains. This work shows that extant small intestinal lactobacilli are protected from toxic dietary components via the gut environment as well as their own capacity to evolve resistance.\nIntroduction:\nWhile antibiotics can cause lasting alterations to the microbiome( David et al., 2014a; Dethlefsen et al., 2008; Dethlefsen and Relman, 2011; Jakobsson et al., 2010), dietary perturbations rarely do so( Sonnenburg et al., 2016). In humans and in mice, the gut microbiome can be quickly altered by diet but community composition generally recovers within days( Carmody et al., 2015; David et al., 2014a; David et al., 2014b; Zhang et al., 2012). Resilience to dietary perturbation may be direct, as gut microbes functionally adapt to diet, or indirect through buffering by the gut habitat. During the 20th century, the greatest dietary change in the United States was in the consumption of soybean oil( SBO), which increased from less than 0. 001 kg/person/year to 12 kg/person/year( Blasbalg et al., 2011). Conventional( ‘commodity’) soybean oil, frequently labeled as ‘vegetable oil’, is a mixture of triglycerides composed of five long chain fatty acids( FAs), with linoleic acid( 18:2) comprising over 50% of the FAs. After triglycerides are hydrolyzed by lipases active in the saliva, stomach, and upper duodenum, free FAs and monoglycerides are absorbed in the small intestine( Mansbach et al., 2000). The microbiota of the human small intestine is exposed to FAs during this process( El Aidy et al., 2015; Kishino et al., 2013): therefore, an increase in the concentration of specific FAs has the potential to reshape microbial communities and select for microbes that thrive in the novel environment. Linoleic acid and the other two major unsaturated FAs in SBO, oleic acid( 18:1), and alpha-linolenic acid( 18:3), are known to be bacteriostatic and/or bactericidal to small intestinal bacteria as non-esterified( free) fatty acids in vitro at concentrations found in the small intestine( Kabara et al., 1972; Kankaanpää et al., 2001; Kodicek, 1945; Nieman, 1954). The primary modes of killing include permeabilization of cell membranes( Greenway and Dyke, 1979) and interference with FA metabolism( Zheng et al., 2005). Affected microbes are predominantly Gram-positive bacteria including the genus Lactobacillus( Nieman, 1954). Lactobacilli are particularly important as they are considered beneficial members of the human small intestine( Walsh et al., 2008; Walter et al., 2007; Walter et al., 2011). They have been shown to be growth inhibited by the specific FAs present in SBO( Boyaval et al., 1995; De Weirdt et al., 2013; Jenkins and Courtney, 2003; Jiang et al., 1998; Kabara et al., 1972; Kankaanpää et al., 2001; Kodicek, 1945; Raychowdhury et al., 1985). It is interesting to note that the human-associated L. reuteri underwent a population bottleneck that coincides with the increase in SBO consumption in the U. S. and is far less prevalent than it was in the past( Walter et al., 2011). Despite its decline, L. reuteri and other lactobacilli persist in the small intestine of Western individuals, suggesting mechanisms to counter the inhibitory effects of FAs in vivo. Here, we explored mechanisms of microbiome resistance to toxic dietary components with a focus on linoleic acid( 18:2) toxicity to L. reuteri and L. johnsonii. Using an in vitro evolution assay, we assessed the capacity for these species to develop 18:2 resistance. To assess resistance in the host, we fed mice from two vendors diets high or low in 18:2 for 10 weeks and exposed their intestinal microbes to acute dosing of 18:2 via gavage. Lactobacilli populations were quantified in live-only and whole cell fractions obtained from the small intestine, and isolates from mice were assessed for resistance in vitro.\nDiscussion:\nA drastic change in dietary macronutrient composition has the capacity to restructure the microbiome within a day( David et al., 2014b; Faith et al., 2011; Turnbaugh et al., 2009) and is one of the most influential contributors to microbiome composition( Carmody et al., 2015). Here, we consider how the gut microbiome is influenced by diet from the perspective of a single FA known to be toxic to gut microbes: specifically, the interaction between lactobacilli and linoleic acid( 18:2). In accord with previous reports, we observed 18:2 to inhibit the growth of most naturally-derived lactobacilli in vitro. However, in the mouse gut, L. reuteri and L. johnsonii persisted through both chronic and acute exposures to 18:2. L. reuteri isolates derived from mice on a diet high in 18:2 included some that were more resistant to 18:2. This observation suggests that 18:2 resistance has the potential to be selected in a host. In vitro, L. reuteri and L. johnsonii both evolved 18:2 resistance through mutations in the cell wall/membrane and fat metabolism genes. Collectively, these data indicate that the host gut environment protects gut microbes from the inhibitory effects of FAs, but that these microbes can also evolve resistance, providing additional resilience. The mutations our 18:2 in vitro adapted lactobacilli strains acquired are consistent with the known bacteriostatic and bactericidal mechanisms of 18:2: by increasing membrane fluidity and permeability( Greenway and Dyke, 1979) potentially leading to cell lysis or leakage( Galbraith and Miller, 1973b; Parsons et al., 2012), by blocking absorption of essential nutrients( Nieman, 1954), and by inhibiting FA synthesis( Zheng et al., 2005) and oxidative phosphorylation( Galbraith and Miller, 1973a). Lactobacilli are also capable of combating 18:2 toxicity by converting 18:2 to conjugated 18:2 and subsequently a monounsaturated or saturated fatty acid( Jenkins and Courtney, 2003; Kishino et al., 2013). We did not recover any mutations in genes known to be involved in the production of conjugated 18:2. Despite the toxicity of 18:2 towards lactobacilli, mouse-associated L. reuteri and L. johnsonii were present at equivalent relative abundances in mice fed diets high or low in 18:2. Moreover, these microbes survived a gavage of 18:2 equal to double what mice normally encounter in their daily diet. Our results are consistent with the findings of Holmes and colleagues, who analyzed the fecal microbiomes of mice on 25 different SBO diets varying in their macronutrient( fat, protein, carbohydrate) composition. Their results demonstrate that fat has only a minor effect on microbiome structure( Holmes et al., 2017). In contrast, in microbial systems engineered for waste processing, concentrations of linoleic acid within the range predicted to be consumed by animals can cause failure of the desired microbial biodegradation processes( Lalman and Bagley, 2000). The resistance of lactobacilli to linoleic acid in the mouse host is therefore inferred to be dependent on the complexity of the gut habitat. In mice, lactobacilli colonize both the small intestine and forestomach( Walter et al., 2007). While lingual lipases exist in mice( DeNigris et al., 1988), fat digestion occurs primarily in the small intestine. As a result, forestomach microbes should not be exposed to a high concentration of free FAs, and SBO itself is not toxic. A gavage of 18:2, on the other hand, exposes forestomach microbes to free 18:2. Lactobacilli may be protected from this direct exposure by their capacity to form a dense biofilm on non-mucus secreting stratified epithelial cells( Frese et al., 2013). In the human host, other aspects of the small intestinal habitat likely buffer the microbiota. The decline of L. reuteri in Western populations may never be fully explained. In the 1960’s and 1970’s prior to the emergence of SBO as a major dietary fat source, L. reuteri was recovered from the intestinal tract of 50% of subjects surveyed and was considered a dominant Lactobacillus species of the human gut( Reuter, 2001). Today, however, it is found in less than 10% of humans in the USA and Europe( Molin et al., 1993; Qin et al., 2010; Walter et al., 2011), yet it is present at a reported 100% prevalence in rural Papua New Guineans( Martínez et al., 2015). Moreover, human L. reuteri strains show very little genetic variation( Duar et al., 2017; Oh et al., 2010), and one human associated lineage of L. reuteri appears to have arisen approximately when SBO consumption increased( Walter et al., 2011). These observations raise the question of whether a change in dietary habits drove the decline in the prevalence of L. reuteri in Western populations. In humans, L. reuteri forms neither high gastric populations nor biofilms( Frese et al., 2011; Walter, 2008), thus human-derived L. reuteri strains may have survived increased exposure to 18:2 by developing resistance. Indeed, we did observe that some human L. reuteri strains are resistant to 18:2, but not all. While the increase in SBO consumption may have conspired with other facets of modernization to reduce the prevalence of L. reuteri in Western populations, it did not appear to have resulted in a selective sweep of 18:2 resistant L. reuteri. The mechanistic underpinnings of how dietary components shape the composition of the gut microbiome need to be further elucidated if manipulation of the microbiome for therapeutic applications is to succeed. Dietary components have the potential to inhibit microbes directly through their toxicity, or indirectly by promoting the growth of other, more fit, microbes. While FAs are generally toxic to many lactobacilli, this work suggests that toxicity is greatly reduced when lactobacilli are host-associated. Future work in this area will elucidate how the host environment protects gut microbes from otherwise toxic dietary components such as FAs, and the ways specific strains within the microbiome can be resilient to such stresses.",
"role": "user"
},
{
"content": "Though “you are what you eat” may just be a figure of speech , it is clear that what we eat does affect our own cells and the microbes that live in our gut . During the 20th century , the American diet changed dramatically and now includes a lot more vegetable oil from soybeans , the main component of which – a fat called linoleic acid – is toxic to many microbes . Among the microbes inhibited by linoleic acid is a beneficial bacterium called Lactobacillus reuteri . This microbe has become less common in Western populations , and the timing of its decline approximately follows when the consumption of soybean oil began increasing . However , L . reuteri and other related microbes still exist in people who eat a Western diet . This suggests that these bacteria must be protected from linoleic acid in the gut , or that they can become resistant to this toxic molecule . Now , Di Rienzi et al . report that both protection in the gut and resistance could explain how L . reuteri can persist in the presence of linoleic acid . First , experiments in the laboratory showed that these microbes could indeed become resistant to linoleic acid , either by gaining mutations in genes involved in creating fats , by growing in an acid , and by forming a cell wall . Further experiments involving mice then showed that the gut protects also L . reuteri from this molecule: linoleic acid did not inhibit L . reuteri within the mouse , but those same L . reuteri were inhibited when grown outside of a mouse . Di Rienzi et al . went on to recover some resistant L . reuteri from mice , implying that there is a mix of resistant and non-resistant strains in the mouse gut . However , notably , the resistant bacteria recovered from the mice did not have mutations in the genes that had been identified from the earlier experiments . Together these findings show that gut bacteria have several means of surviving the high levels of potentially toxic fat molecules . Also , the specific finding that linoleic acid does not inhibit L . reuteri within the gut may help scientists to understand how a high fat diet affects microbes; for example , it is possible that the decrease in carbohydrates or protein that occurs in high fat diets may explain why such diets cause microbes to be lost . Lastly , and on a practical level , linoleic acid-resistant L . reuteri may in the future be used as a probiotic in foods rich in vegetable oil .",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.183 | [
{
"content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nTodetermineifalbinismaltersIOP,weanalyzedB6micethatwereeitherpigmentedoralbino.",
"role": "user"
},
{
"content": "[\"pigmented\"]",
"role": "assistant"
}
]
|
science.data_reco_mcq_sc | science.data_reco_mcq_sc.3533 | [
{
"content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: A system for 3D reconstruction using quadric loss.\n\nKeywords: 3d reconstruction models\n\nDataset Information:\nETH3D: ETHD is a multi-view stereo benchmark / 3D reconstruction benchmark that covers a variety of indoor and outdoor scenes. Ground truth geometry has been obtained using a high-precision laser scanner.\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.\nICL-NUIM: The ICL-NUIM dataset aims at benchmarking RGB-D, Visual Odometry and SLAM algorithms. Two different scenes (the living room and the office room scene) are provided with ground truth.\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.\n\nAvailable Datasets: A: ETH3D B: IntrA C: ICL-NUIM D: ShapeNet",
"role": "user"
},
{
"content": "ShapeNet",
"role": "assistant"
}
]
|
science.mslr2022_cochrane_multidoc_summarization | science.mslr2022_cochrane_multidoc_summarization.203 | [
{
"content": "Review the provided collection of medical RCT summaries. Your objective is to distill the essential insights into a brief conclusion. Focus solely on the synthesis of findings without additional commentary. The RCT summaries are as follows:\n\n\n\nReport Title 1:\nPhase III randomized trial of Calendula officinalis compared with trolamine for the prevention of acute dermatitis during irradiation for breast cancer.\nReport Abstract 1:\nThe effectiveness of nonsteroid topical agents for the prevention of acute dermatitis during adjuvant radiotherapy for breast carcinoma has not been demonstrated. The goal of this study was to compare the effectiveness of calendula (Pommade au Calendula par Digestion; Boiron Ltd, Levallois-Perret, France) with that of trolamine (Biafine; Genmedix Ltd, France), which is considered in many institutions to be the reference topical agent.\n Between July 1999 and June 2001, 254 patients who had been operated on for breast cancer and who were to receive postoperative radiation therapy were randomly allocated to application of either trolamine (128 patients) or calendula (126 patients) on the irradiated fields after each session. The primary end point was the occurrence of acute dermatitis of grade 2 or higher. Prognostic factors, including treatment modalities and patient characteristics, were also investigated. Secondary end points were the occurrence of pain, the quantity of topical agent used, and patient satisfaction.\n The occurrence of acute dermatitis of grade 2 or higher was significantly lower (41% v 63%; P <.001) with the use of calendula than with trolamine. Moreover, patients receiving calendula had less frequent interruption of radiotherapy and significantly reduced radiation-induced pain. Calendula was considered to be more difficult to apply, but self-assessed satisfaction was greater. Body mass index and adjuvant chemotherapy before radiotherapy after lumpectomy were significant prognostic factors for acute dermatitis.\n Calendula is highly effective for the prevention of acute dermatitis of grade 2 or higher and should be proposed for patients undergoing postoperative irradiation for breast cancer.\n\n\nReport Title 2:\nA pilot, randomized, double-blinded, placebo-controlled trial of individualized homeopathy for symptoms of estrogen withdrawal in breast-cancer survivors.\nReport Abstract 2:\nTo pilot an investigation of individualized homeopathy for symptoms of estrogen withdrawal in breast cancer survivors.\n Randomized, double-blinded, placebo-controlled trial.\n Outpatient department of a National Health Service (NHS) homeopathic hospital.\n Fifty-seven (57) women met inclusion criteria and 53 were randomized to the study.\n After 2 weeks of baseline assessment, all participants received a consultation plus either oral homeopathic medicine or placebo, assessed every 4 weeks for 16 weeks.\n The primary outcome measures were the activity score and profile score of the Measure Yourself Medical Outcome Profile (MYMOP).\n Eighty-five percent (85%) (45/53) of women completed the study. There was no evidence of a difference seen between groups for either activity (adjusted difference =-0.4, 95% confidence interval CI -1.0 to 0.2, p = 0.17) or profile scores (adjusted difference = -0.4, 95% CI -0.9 to 0.1, p = 0.13) using this trial design, although post hoc power calculations suggests that 65-175 would be needed per group to detect differences of this magnitude with sufficient precision. Clinically relevant improvements in symptoms and mood disturbance were seen for both groups over the study period.\n Improvements were seen for symptom scores over the study period. However, presuming these improvements were caused by the individualized homeopathic approach, the study failed to show clearly that the specific effect of the remedy added further to the nonspecific effects of the consultation. Future trial design must ensure adequate power to account for the nonspecific impact of such complex individualized interventions while pragmatic designs may more readily answer questions of clinical and cost effectiveness.\n\n\nReport Title 3:\nEfficacy of homeopathic treatment of skin reactions during radiotherapy for breast cancer: a randomised, double-blind clinical trial.\nReport Abstract 3:\nThe aim of this study was to assess the effects of Belladonna 7cH and X-ray 15cH associated in the treatment of acute radiodermatitis. A randomized double-blind placebo-controlled clinical trial involving 66 patients who had been operated on for breast cancer and were undergoing radiotherapy was conducted. The following parameters were assessed over ten weeks: breast skin colour, warmth, swelling and pigmentation. The efficacy of the treatment was assessed by the comparison of these parameters taken individually and by calculating an Index of Total Severity (sum of the scores of the four parameters) during radiotherapy, and during recovery, 15 and 30 d after the end of the radiotherapy. The differences of the scores of the Index of Total Severity during Radiotherapy were not statistically significant, but showed a trend towards a better activity of the homoeopathic medicine compared to placebo. Analysis of the data on Total Severity during recovery, showed a statistically significant benefit of the active medicines over placebo. The homeopathic medicines had particular effectiveness on the heat of the skin. The limited number of patients observed and the posology employed could have interfered with the significance of the results. Chemotherapy and hormonotherapy do not seem to affect the results.\n\n\nReport Title 4:\nA randomized, controlled clinical trial of the homeopathic medication TRAUMEEL S in the treatment of chemotherapy-induced stomatitis in children undergoing stem cell transplantation.\nReport Abstract 4:\nStomatitis is a common consequence of chemotherapy and a condition for which there is little effective treatment. Although the management of patients with other chemotherapy-related toxicities has improved in recent years, the incidence of stomatitis is increasing because of more intensive treatment and is often a dose limiting factor in chemotherapy. The authors assessed the efficacy of a homeopathic remedy, TRAUMEEL S(R), in the management of chemotherapy-induced stomatitis in children undergoing bone marrow transplantation.\n A randomized, placebo-controlled, double-blind clinical trial was conducted in 32 patients ages 3-25 years who had undergone allogeneic (16 patients) or autologous (16 patients) stem cell transplantation. Of the 30 evaluable patients, 15 were assigned placebo, and 15 were assigned TRAUMEEL S both as a mouth rinse, administered five times daily from 2 days after transplantation for a minimum of 14 days, or until at least 2 days after all signs of stomatitis were absent. Stomatitis scores were evaluated according to the World Health Organization grading system for mucositis.\n A total of five patients (33%) in the TRAUMEEL S treatment group did not develop stomatitis compared with only one patient (7%) in the placebo group. Stomatitis worsened in only 7 patients (47%) in the TRAUMEEL S treatment group compared with 14 patients (93%) in the placebo group. The mean area under the curve stomatitis scores were 10.4 in the TRAUMEEL S treatment group and 24.3 in the placebo group. This difference was statistically significant (P < 0.01).\n This study indicates that TRAUMEEL S may reduce significantly the severity and duration of chemotherapy-induced stomatitis in children undergoing bone marrow transplantation.\n Copyright 2001 American Cancer Society.",
"role": "user"
},
{
"content": "This review found preliminary data in support of the efficacy of topical calendula for prophylaxis of acute dermatitis during radiotherapy and Traumeel S mouthwash in the treatment of chemotherapy-induced stomatitis. These trials need replicating. There is no convincing evidence for the efficacy of homeopathic medicines for other adverse effects of cancer treatments. Further research is required.",
"role": "assistant"
}
]
|
science.genia_ner | science.genia_ner.1213 | [
{
"content": "Analyze the provided text excerpt from a scientific document. Identify and extract distinct entities based on predefined categories.\n\nDeliver the results as a JSON structure where each key represents an entity category, and the associated value is a list of identified entities. If no entities are found for a category, return an empty list.\n\nText Excerpt:\n\nGlucocorticoid-resistance in peripheral-blood lymphocytes does not correlate with number of affinity of glucocorticoid-receptors in chronic renal failure patients. Glucocorticoid (GC) resistance in patients with chronic renal failure (CRF) seriously impairs successive GC therapy after renal transplantation. We examined the relationship between GC-receptor (GC-R) parameters in peripheral-blood mononuclear cells (PBMC) and PBMC resistance to GC in 21 CRF patients and 18 healthy subjects. Each subject group was divided into two subgroups according to PBMC sensitivity to prednisolone in a mitogen assay procedure; i. e., sensitive (IC50 < 381 ng / mL) and resistant (IC50 > 381 ng / mL) groups. In healthy subjects, the mean GC-R Bmax and Kd in quiescent PBMC of the GC-sensitive group were 2. 89 + /-1. 23 fmol / 10 (6) cells and 4. 00 + /-2. 24 nM, respectively. The Bmax in these subjects significantly increased to 6. 61 + /-2. 02 (257. 7 + /-107. 8%) after 24 h stimulation with concanavalin A (p < 0. 01), while the Kd change was not significant. The GC-R Bmax and Kd in quiescent PBMC of the GC-resistant group were 5. 33 + /-1. 37 fmol / 10 (6) cells and 3. 20 + /-1. 39 nM, respectively. Both of these parameters, however, did not change significantly after mitogen stimulation. There was a significant negative correlation between IC50S of prednisolone and increase-ratios (post / pre ratio) of Bmax after mitogen stimulation (p < 0. 05). In CRF patients, Bmax and Kd in quiescent PBMC of the GC-sensitive group were 6. 04 + /-2. 35 fmol / 10 (6) cells and 3. 49 + /-1. 72 nM, respectively, while those in PBMC of the GC-resistant group were 5. 13 + /-2. 31 fmol / 10 (6) cells and 4. 04 + /-1. 62 nM, respectively. The Bmax and Kd were not significantly changed after mitogen stimulation in both subgroups of CRF. Moreover, in contrast to healthy subjects, there was no correlation between IC50 and GC-R parameters in CRF. We concluded that, in healthy subjects, decreased PBMC capacity to amplify GC-R numbers in response to mitogen is correlated with GC resistance, whereas in CRF patients the resistant mechanism is not correlated with GC-R parameters. An unknown event might be involved in GC-resistance of CRF.",
"role": "user"
},
{
"content": "{\"CellLine\": [], \"CellType\": [\"peripheral - blood mononuclear cells\", \"PBMC\", \"peripheral - blood lymphocytes\"], \"DNA\": [], \"Protein\": [\"mitogen\", \"glucocorticoid - receptors\", \"GC - R\"], \"RNA\": []}",
"role": "assistant"
}
]
|
science.mslr2022_cochrane_multidoc_summarization | science.mslr2022_cochrane_multidoc_summarization.1767 | [
{
"content": "Review the provided collection of medical RCT summaries. Your objective is to distill the essential insights into a brief conclusion. Focus solely on the synthesis of findings without additional commentary. The RCT summaries are as follows:\n\n\n\nReport Title 1:\nComparison of laparoscopic and open repair with mesh for the treatment of ventral incisional hernia: a randomized trial.\nReport Abstract 1:\nLaparoscopic repair of ventral incisional hernias has not been proved to be safer than open mesh repair.\n Prospective randomized trial conducted between February 1, 2004, to January 31, 2007.\n Four Veterans Affairs medical centers.\n One hundred sixty-two patients with ventral incisional hernias.\n Standardized laparoscopic or open repair.\n Overall complication rates at 8 weeks and the odds of complications, adjusted for study site, body mass index, and hernia type.\n Of the 162 randomized patients, 146 underwent surgery (73 open and 73 laparoscopic repairs). Complications were less common in the laparoscopic group (23 patients [31.5%]) compared with the open repair group (35 patients [47.9%]; adjusted odds ratio [AOR], 0.45; 95% confidence interval [CI], 0.22-0.91; P = .03). Surgical site infection through 8 weeks was less common in the laparoscopic group (5.6% vs 23.3%; AOR, 0.2; 95% CI, 0.1-0.6). The mean worst pain score in the laparoscopic group was 15.2 mm lower on a visual analog scale at 52 weeks (95% CI, 1.0-29.3; P = .04). Time to resume work activities was shorter for the laparoscopic group than for the open repair group (median, 23.0 days vs 28.5 days), with an adjusted hazard ratio of 0.54 (95% CI, 0.28-1.04; P = .06). Overall recurrence at 2 years was 12.5% in the laparoscopic group and 8.2% in the open repair group (AOR, 1.6; 95% CI, 0.5-4.7; adjusted P = .44).\n Laparoscopic repair was associated with fewer, albeit more severe, complications and improved some patient-centered outcomes. Trial Registration clinicaltrials.gov Identifier: NCT00240188.\n\n\nReport Title 2:\nLaparoscopic treatment vs open surgery in the solution of major incisional and abdominal wall hernias with mesh.\nReport Abstract 2:\nDespite being one of the most exact indications, laparoscopic treatment of eventrations and ventral hernias is barely known among the array of laparoscopic techniques.\n A total of 60 patients were assigned at random over a 3-year period to two homogeneous groups to be operated on for major ventral hernias with mesh. Half of them were operated upon laparoscopically and the rest with open surgery. Early and longer-term complications were analyzed, as were operative time and postoperative hospital stays.\n The two groups were homogeneous in terms of demographic and clinical characteristics. The group that was operated on laparoscopically presented a lower rate of postoperative and longer-term complications; similarly, surgery time was significantly lower (p < 0.05). Hospitalization time was also significantly lower than in the group undergoing conventional open surgery (p < 0.05).\n Laparoscopic treatment of postoperative eventration and primary ventral hernia reduces complications and relapse rates, eliminates reintervention through mesh infection, reduces operative time, and considerably shortens the hospital stay.\n\n\nReport Title 3:\nOpen vs laparoscopic repair of spigelian hernia: a prospective randomized trial.\nReport Abstract 3:\nThe elective treatment of a spigelian hernia is still under discussion, fundamentally owing to its rarity. The purpose of the study is to analyze the elective surgical treatment of spigelian hernia.\n A prospective, randomized controlled trial.\n University teaching hospital.\n Two surgeons performed 11 conventional and 11 laparoscopic repairs for a spigelian hernia, alternating roles as primary surgeon and assistant. Each time the type of technique was randomly chosen using a computerized program.\n Epidemiological, clinical, and surgical factors are analyzed according to treatment, ie, the open or laparoscopic approach.\n The statistical study shows no significant differences for epidemiological or diagnostic factors, but it does show significant advantages for laparoscopy in terms of morbidity (P<.05) and hospital stay (P<.001).\n The approach using extraperitoneal laparoscopy is the technique that offers best results in the elective treatment of spigelian hernia.\n\n\nReport Title 4:\nLaparoscopic versus open ventral hernia repair: a randomized controlled trial.\nReport Abstract 4:\nLaparoscopic and open techniques are both recognized treatment options for ventral hernias. We conducted a prospective randomized trial of both methods, to assess hernia recurrence, postoperative recovery and complications. Fifty-eight patients with ventral hernias were enrolled into the trial between August 2003 and December 2005. Of these, 31 underwent laparoscopic repair and 27 underwent open repair. Clinical parameters were documented on all patients during a median follow-up period of 27.5 months. The demographics of the two groups were similar. There was one recurrence in each of the laparoscopic and open groups. There was an equivalent rate of operative time, length of stay, postoperative pain scores, return to normal activities, wound infection and seroma formation between the two groups. Laparoscopic and open ventral hernia repair are comparable and offer low recurrence rates.\n\n\nReport Title 5:\nComparison of laparoscopic and open repair of incisional and primary ventral hernia: results of a prospective randomized study.\nReport Abstract 5:\nIncisional hernia is an important complication of abdominal surgery. Its repair has progressed from a primary suture repair to various mesh repairs and laparoscopic repair. Laparoscopic mesh repair is a promising alternative, and in the absence of consensus, needs prospective randomized controlled trials.\n Between April 2003 and April 2005, 66 patients with incisional, primary ventral and recurrent hernias were randomized to receive either open retro-rectus mesh repair or laparoscopic mesh repair. These patients were followed up at 1-, 3-, and 6-month intervals thereafter for a mean of 12.17 months (open repair group) and 13.73 months (laparoscopic repair group).\n Lower abdominal hernias after gynecologic operations constituted the majority of the hernias (approximately 50%) in both groups. There was no significant injury to viscera or vessel in either group and no conversions. The defect size was 42.12 cm in the open (group 1) and 65.66 cm2 in the laparoscopic group (group 2), and the prosthesis sizes were, respectively, 152.67 cm2 and 203.83 cm2. The hospital stay was 3.43 days in open group and 1.47 days in laparoscopic group (p = 0.007). There was no significant difference in the pain scores between the two groups. More wound-related infectious complications occurred in the open group (33%) than in the laparoscopic group (6%) (p = 0.013). There was one recurrence in the open repair group (3%) and two recurrences in laparoscopic group (6%) (p = 0.55).\n Laparoscopic repair of incisional and ventral hernias is superior to open mesh repair in terms of significantly less blood loss, fewer complications, shorter hospital stay, and excellent cosmetic outcome.\n\n\nReport Title 6:\nOpen randomized clinical trial of laparoscopic versus open incisional hernia repair.\nReport Abstract 6:\nIncisional hernia is a common complication following abdominal surgery. Although the use of prosthetics has decreased recurrence rates, the standard open approach is still unsatisfactory. Laparoscopic techniques are an attempt to provide similar outcomes with the advantages of minimally invasive surgery.\n Open randomized controlled clinical trial with follow-up at 1, 2, 3, 7, and 15 days, and 1, 3, and 12 months from hernia repair. The study was carried out in the surgery departments of three general hospitals of the Valencia Health Agency.\n To compare laparoscopic with anterior open repair using health-related quality of life outcomes as main endpoints.\n Eighty-four patients with incisional hernia were randomly allocated to an open group (OG) (n = 39) or to a laparoscopic group (LG) (n = 45). Seventy-four patients completed 1-year follow up. Mean length of stay and time to oral intake were similar between groups. Operative time was 32 min longer in the LG (p < 0.001). Conversion rate was 11%. The local complication rate was superior in the LG (33.3% versus 5.2%) (p < 0.001). Recurrence rate at 1 year (7.9% versus 9.7%) was similar in the two groups. There were no significant differences in the pain scores or the EQ5D tariffs between the two groups during follow-up.\n Laparoscopic incisional hernia repair does not seem to be a better procedure than the open anterior technique in terms of operative time, hospitalization, complications, pain or quality of life.\n\n\nReport Title 7:\nThe comparison of laparoscopic and open ventral hernia repairs: a prospective randomized study.\nReport Abstract 7:\nThe laparoscopic approach has emerged in the search for a surgical technique to decrease the morbidity associated with conventional repair of ventral hernias. In this study we aimed to compare the results of our open and laparoscopic ventral hernia repairs prospectively.\n Between January 2001 and October 2005, a total of 46 patients diagnosed with ventral hernias (primary and incisional) who were admitted to our surgical unit and accepted to be included in this study group were examined. All patients were divided into laparoscopic repair (n = 23) and open repair (n = 23) subgroups in a randomized fashion. The patients' demographic characteristics, operation times, body mass indices, sizes of fascial defects, hernia locations, durations of hospital stay, presence and degrees of postoperative pain, and postoperative minor and major complications were analysed and compared. All the data were expressed as means +/- SDs. Chi-square and Wilcoxon tests were used for statistical analysis, and P < 0.05 was accepted as a significant statistical value (SPSS 11.0 for Windows).\n The demographic characteristics of both groups were similar. Women predominated, especially in the laparoscopy group (P < 0.05). The comparison of the results revealed that the major advantage of laparoscopy was the shortened postoperative hospital stay and the reduced incidence of mesh infection (P < 0.05, P < 0.05). On the other hand, operation time was significantly longer in the laparoscopy group (P < 0.05). The major complications encountered in the laparoscopy group were ileus and a missed enterotomy. The most frequent minor complication was seroma, which was significantly more frequent in the laparoscopy group (P < 0.05). Postoperative pain assessment revealed similar results in both groups (P > 0.05).\n The laparoscopic approach appears to be as effective as open repairs in the treatment of ventral hernias. Advanced surgical skill, laparoscopic experience and high technology are mandatory factors for successful ventral hernia repair.\n\n\nReport Title 8:\nRetromuscular sutured incisional hernia repair: a randomized controlled trial to compare open and laparoscopic approach.\nReport Abstract 8:\nTo compare the early and intermediate results of the open and laparoscopic tension-free repair of incisional hernia, 24 patients were randomized prospectively to undergo laparoscopic or open repair of incisional hernia with retromuscular placement of the prosthesis using transabdominal sutures for mesh fixation. All the procedures were completed as planned. The mean duration of surgery was not significantly different between the 2 groups (P=0.15). Time to oral solid food intake was longer in the open group (P=0.002). The analgesic requirement was lower in the laparoscopic group (P=0.05). One patient after open surgery and 2 in the laparoscopic group suffered postoperative complications (P=0.71). Postoperative stay was shorter in the laparoscopic group (P=0.006). No readmission or recurrence was registered within 6 months from surgery in either group. Laparoscopic incisional hernia repair, based on the Rives-Stoppa technique, is a safe, feasible alternative to open techniques. However, larger studies and long-term follow-up are required to further evaluate the true effectiveness of this operation.\n\n\nReport Title 9:\nLaparoscopic versus open incisional hernia repair: an open randomized controlled study.\nReport Abstract 9:\nIncisional hernia is a common complication of abdominal surgery, and it is often a source of morbidity and high costs for health care. This is a case-control study to compare laparoscopic versus anterior-open incisional hernia repair.\n 170 patients with incisional hernia were enrolled in this study between September 2001 and December 2004. Of these, 85 underwent anterior-open repair (open group: OG), and 85 underwent laparoscopic repair (laparoscopic group: LG). The clinical outcome was determined by a median follow-up of 24.0 months for LG and OG.\n No difference was noticed between the two groups in age, American Society of Anesthesiologists (ASA) score, body mass index (BMI), and incisional hernia diameter. Mean operative time was 61.0 min for LG patients and 150.9 min for OG patients (p < .05). Mean hospitalization was 2.7 days for LG patients and 9.9 days for OG patients (p < .05). Mean return to work was 13 days (range, 6-15 days) in LG patients and 25 days (range, 16-30 days) in OG patients. Complications occurred in 16.4 % of LG patients and 29.4 % of OG patients, with a relapse rate of 2.3% in LG and 1.1% in OG patients.\n Short-term results indicate that laparoscopic incisional hernia repair is associated with a shorter operative time and hospitalization, a faster return to work, and a lower incidence of wound infections and major complications compared to the anterior-open procedure. Further studies and longer follow-up are required to confirm these findings.",
"role": "user"
},
{
"content": "The short-term results of laparoscopic repair in ventral hernia are promising. In spite of the risks of adhesiolysis, the technique is safe. Nevertheless, long-term follow-up is needed in order to elucidate whether laparoscopic repair of ventral/incisional hernia is efficacious.",
"role": "assistant"
}
]
|
science.scitldr_aic | science.scitldr_aic.42 | [
{
"content": "Review the provided sections from a computer science paper and distill the primary contribution into a single sentence. Provide only the summary sentence.\n\nSections:\n\nThe exposure bias problem refers to the training-inference discrepancy caused by teacher forcing in maximum likelihood estimation (MLE) training for auto-regressive neural network language models (LM).\nIt has been regarded as a central problem for natural language generation (NLG) model training.\nAlthough a lot of algorithms have been proposed to avoid teacher forcing and therefore to alleviate exposure bias, there is little work showing how serious the exposure bias problem is.\nIn this work, we first identify the auto-recovery ability of MLE-trained LM, which casts doubt on the seriousness of exposure bias.\nWe then develop a precise, quantifiable definition for exposure bias.\nHowever, according to our measurements in controlled experiments, there's only around 3% performance gain when the training-inference discrepancy is completely removed.\nOur results suggest the exposure bias problem could be much less serious than it is currently assumed to be.\nLanguage model (LM) is a central module for natural language generation (NLG) tasks (Young et al., 2017) such as machine translation (Wu et al., 2017) , dialogue response generation , image captioning (Lin et al., 2014) , etc.\nFor decades, maximum likelihood estimation (MLE) has been the the most widely used objective for LM training.\nHowever, there is a popular belief in the natural language processing (NLP) community that standard MLE training will cause \"exposure bias\" and lead to a performance degradation during the test-time language generation.\nThe exposure bias problem (Bengio et al., 2015; Ranzato et al., 2016) refers to the following discrepancy between MLE training and test-time generation for language models: During training, the language model predicts the next word conditioned on history words sampled from the groundtruth data distribution.\nAnd during generation, the model generates words conditioned on history sequences generated by the model itself.\nHowever, due to the exposure to real data during training, the language model is biased to only perform well on the ground-truth history distribution.\nAs a result, during generation the errors will accumulate along the generated sequence, and the distribution generated by the model will be distorted.\nThe forced exposure to ground-truth data during training is also referred to as \"teacher forcing\".\nGiven its defintion, the exposure bias problem could rise in the general cases when the model needs to make a sequence of decisions or generations (e.g. music/pixel/speech generation (Lamb et al., 2016) ).\nIn this work, we focus on the task of language generation, because the exposure bias problem is originally proposed in this field (Bengio et al., 2015) , and has since attracted huge research attention.\nIn order to avoid teacher forcing, many training algorithms (Bengio et al., 2015; Lamb et al., 2016; Ranzato et al., 2016; Yu et al., 2016; Zhu et al., 2018; Lu et al., 2018; Lin et al., 2017; Guo et al., 2017; Rajeswar et al., 2017; Wiseman & Rush, 2016; Nie et al., 2019; Shi et al., 2018) have been proposed as alternatives to MLE training.\nMost of these works utilize techniques from generative adversarial network (GAN) (Goodfellow et al., 2014) or reinforcement learning (RL) (Sutton & Barto, 1998) .\nIn this paper, we refer to these algorithms as non-MLE methods or text GANs.\nDespite the huge research efforts devoted to alleviate exposure bias, surprisingly, its existence or significance is much less studied.\nIn particular, to the best of our knowledge, no existing work Table 1 : Samples of a MLE-trained STOA transformer LM when fed with different types of length-10 history prefix.\nTo save space, we omitted the first 7 words of the random history.\nattempts to directly show the seriousness of exposure bias in an empirical or theoretical way.\nThis work is motivated by the belief that a good solution should be built upon a testable and quantifiable problem definition.\nIn this rest of this paper, we first identify the \"self-recovery\" ability of popular LM models, which casts doubt on the original claim of exposure bias.\nWe then develop a precise and quantifiable definition of exposure bias, and validate its seriousness in controlled experiments.\nIn this section, we focus on answering the following question: \"Does the EB-M measurement correctly reflect the significance of exposure bias?\"\nIn short, our answer is not really.\nThe problem is that the distortion of the marginal P l+1 M |M is not only affected by the presumably existing exposure bias problem alone, but also by the mismatch between the history distribution P M from P D for W 1:l , which grows with the length of the history.\nTherefore, even if the measured EB-M is significantly larger than one, we can not conclude that exposure bias causes serious deterioration.\nWe provide an example to illustrate this argument: Example 1.\nSuppose L = 2, and V = {A, B}.\nP D and P M are crafted as follows:\nHowever, the only problem P M has is the mismatch between the history distributions (P M and P D ) for W 1 .\nThe next set of experiments also suggest that EB-M does not precisely reflect exposure bias.\nOn the EMNLP-news data-set (specified in Appendix B), we compare EB-M measurements for several non-MLE training methods with the baseline MLE model.\nWe include results for Scheduled Sampling (SS) (Bengio et al., 2015) , Cooperative Training (CoT) (Lu et al., 2018) , and Adversarial Ranking (RankGAN) (Lin et al., 2017) .\nWe provide implementation details for non-MLE methods in Appendix C. Intuitively, these methods will cause the model to be biased to behave well with model samples as history, instead of data samples.\nTherefore, we expect EB-M measurement for non-MLE trained models to be smaller than MLE trained models.\nHowever, Figure 1 shows that the measurements for different training frameworks are almost the same.\nWe believe the reason is that the EB-M measurements are only reflecting the trivial mismatch between the history distributions.\nIs it possible that the original definition of exposure bias (Bengio et al., 2015; Ranzato et al., 2016) exactly refers to this mismatch between the model and data history distributions?\nHowever, note that this mismatch is inevitable for any imperfect model, and non-MLE training algorithms can not solve it.\nWe believe a better, more precise definition is needed to discriminate exposure bias from this trivial mismatch.\nMotivated by this view, we propose a second approach in the section below.\nFollowing the discussion in the last section, we wish our measurement to be independent of the quality of the history distribution.\nIn light of that, we design a quantity to measure the model's conditional generation quality.\nLet P H ∈ {P M , P D } denote the history distribution as in the MGD definition (5).\nWith history length l fixed, we define the conditional generation deviation (CGD) with history distribution P H for P M using metric d as:\nwhere we assume that P D (· | W 1:l )) is computable, and use it to measure the quality of the model's conditional distribution.\nFor the choice of the distribution distance d, in addition to d T V and d JS , we introduce greedy decoding divergence (d GD ) defined as:\nwhere 1 is the indicator function, and P, Q ∈ P. The distance d GD 2 reflects the model's accuracy during greedy decoding.\nSimilar to MGD, exposure bias should imply a significant gap between CGD(P M |M , l, d) and CGD(P M |D , l, d).\nWe again define rate of exposure bias at history length l with metric d to be:\nFor our definition of EB-C, a natural question is why we only focus on the generation distribution of the very next word.\nThe reason is we want to precisely measure how the error caused by the history part affect the generation part, by keeping them separate.\nIf we measure the deviation of, for example, two sampled tokens, the definition will be confusing: Because the second sampled token will be affected not only by the accumulated error induced by the history (sampled from the model), but also by the first generated token as history.\nTo get a better understanding of the intuition behind the definition of EB-C, we recommend readers to read Appendix A about our NMT experiment.\nSince CGD requires inference for ground-truth data distribution P D , we first consider experiments in a synthetic setting.\nIn text-GAN literature (Yu et al., 2016; Lin et al., 2017) , a randomly-initialized one-layer LSTM model with hidden dimension of 32 is usually used as P D in synthetic experiments (we denote this setting as M random 32\n).\nHowever, the model is small-scale and does not reflect any structure existing in real-world text.\nTo improve upon this approach, we take the MLE baseline model trained on EMNLP-news data (described in Appendix B) as P D in this synthetic setting.\nWe denote the data model (P D ) as M news 512 .\nWe then train two LSTM LM (P M ) with different capacities using samples from the data model, with the standard MLE objective.\nOne is a one-layer LSTM with hidden width of 512 (denoted as LSTM-512), the other one is with hidden width of 32 (denoted as LSTM-32).\nWe train P M for 100 epochs using the Adam optimizer with learning rate 0.001.\nIn each epoch, 250k sentences (same to the size of the original EMNLP-news data) of length L = 50 are sampled from M news-512 as training data to avoid over-fitting.\nWe show perplexity (PPL) results of the trained models in Appendix F. Finally, EB-C is calculated using 100k 3 samples from P M and P D .\nIn Figure 2 , we show EB-C measurements with different metrics d m , and the two models give similar results.\nIt is shown that EB-C has a steady but slow increasing trend as history length increases.\nThis is expected as a consequence of exposure bias, because P M deviates farther from P D as history length increases.\nHowever, the average value of EB-C is less than 1.03 (the largest average value is from d JS for the LSTM-512 experiment), meaning that the gap between CGD(P M |M , l, d) and CGD(P M |D , l, d) is not large.\nAlso, note that in most NLG applications (such as machine translation or image captioning), the generated sequence typically has short length (less than 20).\nIn that range of history length, the EB-C measurements that exposure bias only has minimal influence.\nIn Appendix E, we repeat the experiment for a transformer LM (Dai et al., 2019) , and get very similar EB-C measurements.\nThese measurements imply a striking conclusion : (Informal) Even if all the bad effects from exposure bias for MLE LM training are removed, the relative performance gain is at most 3%.\nIf the sequence length is not very long, the gain is less than 1%..\nTo dive deeper into the cause of the gap in CGD, we experiment with corrupted versions of P M as history distribution.\nWe first specify a corrupt rate c ∈ [0, 1], and randomly substitute words in a history sample from P M to a \"noise\" word drawn uniformly from the vocabulary with probability c.\nConsequently, larger c will cause the history distribution to deviate farther from the groundtruth P D .\nIn Figure 3 , we show CGD measurement versus the corrupted history P corrupt M .\nLarge gaps are observed between CGD(P M |M corrupt ) and CGD(P M |D ).\nTherefore, the small gap between CGD(P M |M ) and CGD(P M |D ) in Figure 2 results from the small deviation between the history distribution P M and P D .\nIn other word, P M has learned a \"good enough\" distribution that is able to keep it in the well-behaving region during sampling.\nWith these observations, we conclude that, in the synthetic setting considered, exposure bias does exist, but is much less serious than it is presumed to be.\nAlthough there exists mismatch between the history distribution P M and P D , the mismatch is still in the model's \"comfortable zone\".\nIn other words, the LSTM LM is more robust than exposure bias claims it to be.\nTo concretize the this argument, we provide an example LM and show that MLE training is unlikely to generate models with a large EB-C value.\nExample 2.\nAgain suppose L = 2, and V = {A, B}, the ground-truth data distribution is uniform on {AA, AB, BB, BA}.\nP M is crafted as follows:\n. Note that the model behaves bad when W 1 = A, which is of high probability during sampling.\nIn this work, we first identify the self-recovery ability of MLE-trained LM, which casts doubt on the seriousness of exposure bias, which has been regarded as a central problem for MLE training by the LM community.\nWe then explore two intuitive approaches to quantify the significance of exposure bias for LM training.\nThe first quantification EB-M relies on the marginal generation distribution and reveals some vagueness in the original definition of exposure bias.\nWe argue that we should focus on the model's generation performance in terms of its conditional distribution and propose a second quantification EB-C, which we regard as the precise definition for exposure bias.\nWe design a evaluation of EB-C at different history length with real human (turkers from AMT) as the data model, for a SOTA transformer LM.\nIt is shown that removing the training-testing discrepancy only gives around 2% of performance gain.\nOur synthetic experiments also gives very similar measurements.\nBy analyzing EB-C measurements with perturbed history samples, we hypothesise that although the mismatch between the data and model distribution for history prefix exists, it is still in the model's \"comfortable zone\".\nWith these results, we claim that on the contrary to the popular belief, exposure bias is only a minor problem in MLE-based LM training.\nTo wrap up, we discuss the fundamental question \"Is MLE training really biased?\", from the perspective of objective functions.\nNote that the MLE objective (1) can be re-written as:\nwhere D KL denotes the Kullback-Leibler divergence, and θ denotes the trainable parameters in P M .\nTherefore, MLE training is minizing the divergence from P M , which is exactly the model's sampling distribution, from P D .\nWhile it's true that the training is \"exposed\" to data samples, we can not simply deduce the objective is \"biased\".\nWe want to end our discussion with two remarks.\nFirst, the proposed quantification approaches should not be used as the only metric for NLG.\nFor example, a position-aware uni-gram LM, which generates words independent of previous context, has no exposure bias problem and can pass our test easily.\nSecond, the intention of this work is not to discourage researchers from exploring non-MLE training algorithms for LM.\nIt is completely possible that an training objective different from\n, can lead to better generation performance (Lu et al., 2018; Huszr, 2015) .\nHowever, though non-MLE algorithms avoid teacher forcing, these algorithms (using GAN or RL for example) are usually less stable and more difficult to tune.\nGiven that the quantified measurement of exposure bias is insignificant, we think it should be questioned whether adopting these techniques to avoid exposure bias is a wise trade-off.",
"role": "user"
},
{
"content": "We show that exposure bias could be much less serious than it is currently assumed to be for MLE LM training.",
"role": "assistant"
}
]
|
science.cdr_ner | science.cdr_ner.325 | [
{
"content": "Examine the provided text to identify entities. Focus on extracting relevant information.\n\nPresent your findings in a structured JSON format. Each category should list the entities found.\n\nSource Material:\n\nA case of massive rhabdomyolysis following molindone administration. Rhabdomyolysis is a potentially lethal syndrome that psychiatric patients seem predisposed to develop. The clinical signs and symptoms, typical laboratory features, and complications of rhabdomyolysis are presented. The case of a schizophrenic patient is reported to illustrate massive rhabdomyolysis and subsequent acute renal failure following molindone administration. Physicians who prescribe molindone should be aware of this reaction.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"molindone\"], \"Disease\": [\"psychiatric\", \"schizophrenic\", \"rhabdomyolysis\", \"Rhabdomyolysis\", \"acute renal failure\"]}",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.4115 | [
{
"content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nAllexperimentswereperformedusingsex-andage-matchedorlittermatecontrolsasnoted.",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_plos_single_doc_summ | science.scientific_lay_summarisation_plos_single_doc_summ.3332 | [
{
"content": "Transform the following sections from a biomedical study into a simple summary for the general public. Focus on making the information accessible and easy to understand.\n\nResearch Heading: The Desensitization Gating of the MthK K+ Channel Is Governed by Its Cytoplasmic Amino Terminus\nContent:\nAbstract:\nThe RCK-containing MthK channel undergoes two inactivation processes: activation-coupled desensitization and acid-induced inactivation. The acid inactivation is mediated by the C-terminal RCK domain assembly. Here, we report that the desensitization gating is governed by a desensitization domain( DD) of the cytoplasmic N-terminal 17 residues. Deletion of DD completely removes the desensitization, and the process can be fully restored by a synthetic DD peptide added in trans. Mutagenesis analyses reveal a sequence-specific determinant for desensitization within the initial hydrophobic segment of DD. Proton nuclear magnetic resonance( 1H NMR) spectroscopy analyses with synthetic peptides and isolated RCK show interactions between the two terminal domains. Additionally, we show that deletion of DD does not affect the acid-induced inactivation, indicating that the two inactivation processes are mutually independent. Our results demonstrate that the short N-terminal DD of MthK functions as a complete moveable module responsible for the desensitization. Its interaction with the C-terminal RCK domain may play a role in the gating process.\nIntroduction:\nK+ channels are found in almost every free-living organism, with a universally conserved architecture. Typically, a functional K+ channel is composed of four copies of a pore-forming subunit of two or six transmembrane( TM) helices with the amino( N)- and carboxyl( C)-termini usually residing in the cytoplasm. These cytoplasmic N- or C-terminal domains can control channel assembly and trafficking, as well as function as a gatekeeper to regulate the access of K+ to the ion-conducting pathway[1–5]. A particular form of control by cytoplasmic domain is exemplified by the RCK[6]( also known as KTN[7]) domain found in a large number of prokaryotic K+ transport systems, including ion channels and transporters[8], and also in the animal Slo-type K+ channels[6]. The crystal structure of the RCK-containing MthK channel( M107I mutant), from the archaeon Methanobacterium thermoautotrophicum, provides a relatively simple model, allowing direct structural, biochemical, and functional correlations to understand the regulatory roles of the RCK domain in K+ channels[9]. Each subunit of MthK is composed of a short cytoplasmic N terminus of 18 amino acid residues followed by a 2-TM pore-forming domain. A RCK domain of approximately 220 residues is covalently linked to the C terminus of the second TM through a linker of 18 residues( Figure 1A, left). On the basis of the crystal structure of MthK( M107I mutant), four copies of a separately expressed, soluble RCK domain have been proposed to interact with the four membrane-tethered RCK domains in a pairwise manner to form a “gating ring” complex. Binding of Ca2+ to the domains extends the diameter of the ring and thus accounts for the activation gating[9, 10]. Later on, it was discovered that besides Ca2+, MthK is also regulated by the pH of the cytoplasmic side such that the channel becomes completely inactivated at a pH value below 6. 0[11, 12]. This acid inactivation has been proposed to be modulated by disassociation of a high-order RCK oligomer into dimers as demonstrated by both structural and biochemical analyses on the isolated RCK domain[10–13]. More recently, we discovered that the macroscopic current of MthK declines spontaneously after Ca2+ activation on a timescale of seconds, indicating the channel undergoes a process called desensitization[11]. This set of experiments was carried out by directly patch clamping the MthK channels expressed in enlarged E. coli membrane. However, the purified MthK channels studied in black lipid membrane( BLM) has not been observed to undergo desensitization[12, 14, 15]. This inconsistent observation raised a question as to whether this unique desensitization phenomenon observed in the enlarged E. coli system is an intrinsic molecular property or an experimental artifact. Besides the difference in the desensitization phenomenon, another set of inconsistent results was also observed from MthK studied by these two different recording systems. Single-channel analysis of purified MthK in the BLM system has shown that the open probability of MthK is drastically increased when the pH of the cytoplasmic side is raised to 8. 0 and above, even without Ca2+[12]. A gating ring model has been proposed to explain this alkaline-activation phenomenon in which alkaline pH extends the diameter of the octomeric gating ring in the absence of Ca2+ to open the channel gate[12]. However, this alkaline activation was not observed from the MthK studied in the enlarged E. coli system. Instead, the macroscopic currents show that MthK continues to require Ca2+ for activation followed by subsequent desensitization at alkaline pH up to 8. 5[11]. Additionally, our biochemical analysis of the isolated RCK domain at pH values higher than 8. 0 has shown that the domain is predominantly monomeric when Ca2+ is absent[11]. This biochemical observation is also inconsistent with the proposed gating ring model made up by a stable octomeric RCK assembly[12]. In this report, we first demonstrate that the desensitization phenomenon is indeed intrinsic to the MthK channel, and the gating process is controlled by the cytoplasmic N-terminal 17 residues. By mutational and 1H NMR analyses, we further demonstrate that the desensitization gating mechanism may involve interactions between the N-terminal desensitization domain( DD) and C-terminal RCK domain. Additionally, we show that the desensitization and acid-inactivation gatings are controlled by distinct parts of the channel, and the processes are mutually independent. Finally, we demonstrate that MthK requires Ca2+ for activation in all ranges of pH as high as pH 9. 0, the pH at which the isolated RCK domain undergoes a monomer-to-oligomer conversion by the presence of Ca2+.\nDiscussion:\nPrevious studies of MthK were carried out by purifying the channel proteins and reconstituting them in BLM[12, 14, 15]. Although this method ensures that the activities observed originate from the pure proteins, the BLM system cannot readily resolve the rapid ligand-gating kinetics because of the time required for chamber perfusion. Therefore, the gating properties previously studied in BLM may not reflect those of activation gating[19]. Biochemical analyses of the isolated RCK domain of MthK have shown that the domain is able to form various oligomeric states, including 1-mer, 2-mer, 4-mer, 6-mer, and 8-mer, depending on the pH and Ca2+[10, 11, 13]. In this study, we propose that the synthetic N-terminal DD induces desensitization by interacting with the RCK domain( below). Based on these observations, it is possible that the separately expressed free RCK protein, which has been shown to be copurified with the full-length MthK[9, 14], can bind to either the N-terminal DD or the membrane-tethered C-terminal RCK domain. Although the native form of the DD-RCK or RCK-RCK interaction is unclear, these interactions could possibly be altered during the purification and reconstitution processes. For instance, the crystal structure of the MthK( M107I mutant) shows that the two channels interact with each other through the member-tethered RCK domains after being extracted and purified[9]. Therefore, whether the conformation of the reconstituted MthK in the BLM system remains the same as those in the cell membrane needs to be established. To avoid possible alternations in the natural conformation, we have expressed MthK in the membrane of giant E. coli spheroplasts for direct patch clamp[11]. The desensitization property was discovered when the excised patches were bathed in a stream of perfusate that can be switched within tens of milliseconds[11]. The E. coli patch-clamp method forgoes the simplicity of BLM reconstitution but provide a natural setting to examine the channel without altering the native RCK assembly. However, a logical possibility exists that a protein native to E. coli may interact with the MthK protein from the cytoplasm, causing it to desensitize. In this study, we addressed this question by showing that the desensitization phenomenon of MthK can be removed by deleting its N-terminal DD and can be re-established by a synthetic DD peptide, and its shorter variants, added in trans. These results are consistent with the conclusion that the desensitization process is an intrinsic molecular property. To further characterize how the DD and RCK domains modulate the gating of MthK, reconstituting purified channels into an artificial liposome for patch clamp may provide a more advanced system to circumvent possible heterologous interactions in giant E. coli system, as well as to resolve rapid kinetics[20–22]. Our initial observations had reminisced the works of the N-type ball-and-chain inactivation model in the voltage-gated Shaker K+( Kv) channels[17]. In Shaker-type Kv channels, the N-type inactivation was restored to inactivation peptide( IP)-truncated channels by a synthetic IP segment of approximately 20 amino acids located at the N-terminal end of the Shaker channel subunits[23, 24]. The current model for Shaker inactivation is that the IP ball, as an unfolded chain, reaches the intracellular cavity of the pore through the lateral opening between T1 and the TM domain of the channel. In this model, a single IP acts like a quaternary ammonium channel blocker and can access and physically occlude the central ion pathway of an open channel[25–33]. In MthK, the DD, which is about the size of the IP ball, is directly attached to the MthK channel body without a “chain” as seen in the Shaker channels. Therefore, does the DD desensitize MthK by reaching the intracellular cavity to block the pore, or by interacting with other parts of the channel to cause allosteric blockage? Our analyses using the synthetic DD peptide showed that the rate of peptide desensitization varies between subseconds to tens of seconds, depending on the peptide concentration. And the recovery of the peptide-desensitized channel depends on Ca2+, such that the recovery is much faster when Ca2+ is removed than when present. This kinetic behavior of DD peptide blockage is quite different from that of the TBA( tetrabutylammonium) pore blockage. When examined between 0. 01 and 10 mM, the rates of TBA blockage and recovery on open Δ2–17 MthK channels are both around tens of milliseconds( unpublished data). Since the quaternary ammonium compound is known to block K+ channels by directly plugging into the intracellular cavity of the pore[31], the much slower rates of DD peptide blockage suggest that the blocking mechanism may not simply be the same as the TBA pore blocker. Consistent with this conclusion is the observations that the shorter aa1–6 peptide has almost no blocking effect, and the aa1–11 peptide is not able to fully block the Δ2–17 MthK channels as the aa1–17 peptide does at steady state. These results indicate that the initial hydrophobic segment of the DD alone is not able to act like the quaternary ammonium pore blocker. Instead, the subsequent residues, from Ile7 to Lys17, also play a role to complete the gating modulation. Furthermore, in Figure 5, we showed that perfusion of DD peptide at substantially high concentration to the cytoplasmic side of Δ2–17 MthK can desensitize the channels without opening. This result indicates that the binding site for the DD peptide is accessible in the closed channel, and the DD blockage is rather allosteric. In the 1H NMR analyses, we demonstrated that the aa1–17 and aa1–11 peptides, but not the mutant aa1–17( L3D) or aa1–6 peptide, directly interact with the isolated RCK domain. These binding results correlate well with the functional analyses in which the aa1–17 and aa1–11 peptides, but not the mutant aa1–17( L3D) or aa1–6 peptide, are able to inhibit the K+ current. This direct correlation between protein binding and channel blockage suggests that the physical interaction of the synthetic DD peptide to the RCK domain is required to cause the peptide-desensitization. Although the results of peptide desensitization should be interpreted with caution to surmise the native desensitization mechanism, it is plausible that the N-terminal DD in the wild-type MthK interacts with the C-terminal RCK domain in the similar way to render the channel into the desensitized state after Ca2+ activation. Further functional characterizations of the natural and peptide desensitization are required to compare the differences and similarities of these two mechanisms. Note that this set of experiments highlights that an interaction between the N-terminal DD and C-terminal RCK domain may be responsible for the desensitization gating process; however, it does not exclude additional interaction of DD with other parts of the channel, including the transmembrane pore region. Given that the structure of DD is not resolved in the crystal structure of MthK( M107I), further elucidating the detailed DD-RCK interaction of the entire MthK structure at atomic scale may help understanding how the interactions participate in the gating process. Results in this report together with previous studies of others provide a converging view that the gating mechanisms of activation, of activation-coupled desensitization and of the acid-induced inactivation are largely mediated by conformational changes in the RCK domain, namely the desensitization by DD and the acid inactivation by RCK disassembly into dimers at acidic pH[11–13]. For activation gating, however, it remains to be better understood how Ca2+-triggered conformational change of the RCK domains results in channel opening. In conclusion, these dynamic Ca2+-, pH-, and DD-dependent conformational changes of RCK domain underlie the mechanistic basis of MthK gating.",
"role": "user"
},
{
"content": "Nerve cells use ion channels , pores in the cell membrane , to send messages in the form of electrical signals between cells . Most ion channels have evolved several elaborate mechanisms that allow the channels to close quickly after opening to prevent wasteful leakage of the electrochemical potential—the currency of neuron communication—across the cell membrane . The process is known as inactivation or desensitization . Previous study on the model RCK-containing MthK K+ channel in the enlarged Escherichia coli membrane has shown that this archaeon channel also undergoes desensitization . Using the same method , we demonstrate that the desensitization is indeed an intrinsic molecular property of the MthK protein . We show that a specific region of MthK , the short N terminus of the protein , functions as a structurally independent domain and is entirely responsible for the desensitization gating process . Moreover , we show that this N-terminal domain interacts with the C-terminal RCK domain as part of the desensitization mechanism . This unique desensitization mechanism , by interaction between the two cytoplasmic termini , is distinct from those traditional mechanisms known as N- and C-type inactivation found in many voltage-gated Na+ and K+ channels or as the desensitization observed in the glutamate receptors . Since the KTN/RCK domain is found in a large number of prokaryotic K+ channels and transporters , this unique mechanism may be common to these transport systems for regulating the K+ flux through the cell membrane .",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.1749 | [
{
"content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nConclusions",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.2883 | [
{
"content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nStudy design and rationale of a dose-ranging trial of LX4211 , a dual inhibitor of SGLT1 and SGLT2 , in type 2 diabetes inadequately controlled on metformin monotherapy . Sodium-glucose cotransporters 1 ( SGLT1 ) and 2 ( SGLT2 ) are the major cellular transporters responsible for gastrointestinal ( GI ) glucose absorption and renal glucose reabsorption , respectively . LX4211 , a dual inhibitor of SGLT1 and SGLT2 , reduces glucose absorption from the GI tract and enhances urinary glucose excretion . Although several SGLT2-selective inhibitors have been tested in large phase 2 studies , dual inhibition of SGLT1 and SGLT2 is novel at this stage of drug development , and it has implications for clinical-trial design . In this article , we describe the design and rationale of a phase 2 , multicenter , randomized , double-blind , placebo-controlled , parallel group study to evaluate the safety and efficacy of LX4211 in subjects with type 2 diabetes mellitus who have inadequate glycemic control on metformin monotherapy . The primary endpoint is the change in glycated hemoglobin A1c from baseline to week 12 . Secondary endpoints include the proportion of subjects achieving a glycated hemoglobin A1c value of < 7 % , change from baseline in fasting plasma glucose and postprandial glucose ( as part of an oral glucose tolerance test ) , body weight , and blood pressure . Safety is evaluated with particular focus on hypoglycemia , GI symptoms , and incidence of genitourinary tract infections .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"LX4211\", \"placebo-controlled\"], \"Outcome\": [\"Safety\", \"glycated hemoglobin A1c\", \"safety and efficacy\", \"proportion of subjects achieving a glycated hemoglobin A1c value of \\u003c 7 % , change from baseline in fasting plasma glucose and postprandial glucose ( as part of an oral glucose tolerance test ) , body weight , and blood pressure .\", \"glycemic control\", \"hypoglycemia , GI symptoms , and incidence of genitourinary tract infections\"], \"Participant\": []}",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.2199 | [
{
"content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nWe propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, obtained using either an encoder or through class specific k-d trees, significantly speed up the the search for counterfactual instances and result in more interpretable explanations. We introduce two novel metrics to quantitatively evaluate local interpretability at the instance level. We use these metrics to illustrate the effectiveness of our method on an image and tabular dataset, respectively MNIST and Breast Cancer Wisconsin (Diagnostic). The method also eliminates the computational bottleneck that arises because of numerical gradient evaluation for @math models.\n\nCited Works Summary:\n[1]: We discuss a method for selecting prototypes in the classification setting (in which the samples fall into known discrete categories). Our method of focus is derived from three basic properties that we believe a good prototype set should satisfy. This intuition is translated into a set cover optimization problem, which we solve approximately using standard approaches. While prototype selection is usually viewed as purely a means toward building an efficient classifier, in this paper we emphasize the inherent value of having a set of prototypical elements. That said, by using the nearest-neighbor rule on the set of prototypes, we can of course discuss our method as a classifier as well. We demonstrate the interpretative value of producing prototypes on the well-known USPS ZIP code digits data set and show that as a classifier it performs reasonably well. We apply the method to a proteomics data set in which the samples are strings and therefore not naturally embedded in a vector space. Our method is compatible with any dissimilarity measure, making it amenable to situations in which using a non-Euclidean metric is desirable or even necessary.\n\n[2]: A recent approach to few-shot classification called matching networks has demonstrated the benefits of coupling metric learning with a training procedure that mimics test. This approach relies on a complicated fine-tuning procedure and an attention scheme that forms a distribution over all points in the support set, scaling poorly with its size. We propose a more streamlined approach, prototypical networks, that learns a metric space in which few-shot classification can be performed by computing Euclidean distances to prototype representations of each class, rather than individual points. Our method is competitive with state-of-the-art one-shot classification approaches while being much simpler and more scalable with the size of the support set. We empirically demonstrate the performance of our approach on the Omniglot and mini-ImageNet datasets. We further demonstrate that a similar idea can be used for zero-shot learning, where each class is described by a set of attributes, and achieve state-of-the-art results on the Caltech UCSD bird dataset.\n\n[3]: This paper develops the multidimensional binary search tree (or k -d tree, where k is the dimensionality of the search space) as a data structure for storage of information to be retrieved by associative searches. The k -d tree is defined and examples are given. It is shown to be quite efficient in its storage requirements. A significant advantage of this structure is that a single data structure can handle many types of queries very efficiently. Various utility algorithms are developed; their proven average running times in an n record file are: insertion, O (log n ); deletion of the root, O ( n ( k -1) k ); deletion of a random node, O (log n ); and optimization (guarantees logarithmic performance of searches), O ( n log n ). Search algorithms are given for partial match queries with t keys specified [proven maximum running time of O ( n ( k - t ) k )] and for nearest neighbor queries [empirically observed average running time of O (log n ).] These performances far surpass the best currently known algorithms for these tasks. An algorithm is presented to handle any general intersection query. The main focus of this paper is theoretical. It is felt, however, that k -d trees could be quite useful in many applications, and examples of potential uses are given.\n\n[4]: \n\n[5]: We propose a general framework for nonparametric classification of multi-dimensional numerical patterns. Given training points for each class, it builds a set cover with convex sets each of which contains some training points of the class but no points of the other classes. Each convex set has thus an associated class label, and classification of a query point is made to the class of the convex set such that the projection of the query point onto its boundary is minimal. In this sense, the convex sets of a class are regarded as ''prototypes'' for that class. We then apply this framework to two special types of convex sets, minimum enclosing balls and convex hulls, giving algorithms for constructing a set cover with them and for computing the projection length onto their boundaries. For convex hulls, we also give a method for implicitly evaluating whether a point is contained in a convex hull, which can avoid computational difficulty for explicit construction of convex hulls in high-dimensional space.\n\n[6]: In this paper we propose an efficient algorithm ProtoDash for selecting prototypical examples from complex datasets. Our work builds on top of the learn to criticize (L2C) work by (2016) and generalizes it to not only select prototypes for a given sparsity level @math but also to associate non-negative weights with each of them indicative of the importance of each prototype. Unlike in the case of L2C, this extension provides a single coherent framework under which both prototypes and criticisms (i.e. lowest weighted prototypes) can be found. Furthermore, our framework works for any symmetric positive definite kernel thus addressing one of the open questions laid out in (2016). Our additional requirement of learning non-negative weights introduces technical challenges as the objective is no longer submodular as in the previous work. However, we show that the problem is weakly submodular and derive approximation guarantees for our fast ProtoDash algorithm. Moreover, ProtoDash can not only find prototypical examples for a dataset @math , but it can also find (weighted) prototypical examples from @math that best represent another dataset @math , where @math and @math belong to the same feature space. We demonstrate the efficacy of our method on diverse domains namely; retail, digit recognition (MNIST) and on the latest publicly available 40 health questionnaires obtained from the Center for Disease Control (CDC) website maintained by the US Dept. of Health. We validate the results quantitatively as well as qualitatively based on expert feedback and recently published scientific studies on public health.\n\n[7]: Example-based explanations are widely used in the effort to improve the interpretability of highly complex distributions. However, prototypes alone are rarely sufficient to represent the gist of the complexity. In order for users to construct better mental models and understand complex data distributions, we also need criticism to explain what are captured by prototypes. Motivated by the Bayesian model criticism framework, we develop MMD-critic which efficiently learns prototypes and criticism, designed to aid human interpretability. A human subject pilot study shows that the MMD-critic selects prototypes and criticism that are useful to facilitate human understanding and reasoning. We also evaluate the prototypes selected by MMD-critic via a nearest prototype classifier, showing competitive performance compared to baselines.\n\n[8]: This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion",
"role": "user"
},
{
"content": "One of the key contributions of this paper is the use of prototypes to guide the counterfactual search process. [7] [6] use prototypes as example-based explanations to improve the interpretability of complex datasets. Besides improving interpretability, prototypes have a broad range of applications like clustering [4] , classification [1] [5] , and few-shot learning [2] . If we have access to an encoder [8] , we follow the approach of [2] who define a class prototype as the mean encoding of the instances which belong to that class. In the absence of an encoder, we find prototypes through class specific k-d trees [3] .",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.3605 | [
{
"content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: Emergency Message Dissemination in Vehicular Networks: A Review \nChapter Title: VI. SIMULATING THE NETWORK TRAFFIC \n1. Abstract of Cited Paper (BIB001): MATLAB is one of the most widely used mathematical computing environments in technical computing. It is an interactive environment that provides high-performance computational routines and an easy-to-use, C-like scripting language. It started out as an interactive interface to EISPACK and LINPACK and has remained a serial program. In 1995, C. Moler of Mathworks argued that there was no market at the time for a parallel MATLAB. But times have changed and we are seeing increasing interest in developing a parallel MATLAB, from both academic and commercial sectors. In a recent survey, 27 parallel MATLAB projects have been identified. We expand upon that survey and discuss the approaches the projects have taken to parallelize MATLAB. Also, we describe innovative features in some of the parallel MATLAB projects. Then we will conclude with an idea of a \"right\" parallel MATLAB. Finally we will give an example of what we think is a \"right\" parallel MATLAB: MATLAB*P. \n2. Abstract of Cited Paper (BIB002): The OMNeT++ discrete event simulation environment has been publicly available since 1997. It has been created with the simulation of communication networks, multiprocessors and other distributed systems in mind as application area, but instead of building a specialized simulator, OMNeT++ was designed to be as general as possible. Since then, the idea has proven to work, and OMNeT++ has been used in numerous domains from queuing network simulations to wireless and ad-hoc network simulations, from business process simulation to peer-to-peer network, optical switch and storage area network simulations. This paper presents an overview of the OMNeT++ framework, recent challenges brought about by the growing amount and complexity of third party simulation models, and the solutions we introduce in the next major revision of the simulation framework. \n3. Abstract of Cited Paper (BIB003): Realistic simulation is a necessary tool for the proper evaluation of newly developed protocols for Vehicular Ad Hoc Networks (VANETs). Several recent efforts focus on achieving this goal. Yet, to this date, none of the proposed solutions fulfil all the requirements of the VANET environment. This is so mainly because road traffic and communication network simulators evolve in disjoint research communities. We are developing TraNS, an open-source simulation environment, as a step towards bridging this gap. This short paper describes the TraNS architecture and our ongoing development efforts. \n4. Abstract of Cited Paper (BIB004): Wireless communication technologies have now greatly impact our daily lives. From indoor wireless LANs to outdoor cellular mobile networks, wireless technologies have benefited billions of users around the globe. The era of vehicular ad hoc networks (VANETs) is now evolving, gaining attention and momentum. Researchers and developers have built VANET simulation software to allow the study and evaluation of various media access, routing, and emergency warning protocols. VANET simulation is fundamentally different from MANETs (mobile ad hoc networks) simulation because in VANETs, vehicular environment imposes new issues and requirements, such as constrained road topology, multi-path fading and roadside obstacles, traffic flow models, trip models, varying vehicular speed and mobility, traffic lights, traffic congestion, drivers' behavior, etc. Currently, there are VANET mobility generators, network simulators, and VANET simulators. This paper presents a comprehensive study and comparisons of the various publicly available VANET simulation software and their components. In particular, we contrast their software characteristics, graphical user interface (GUI), popularity, ease of use, input requirements, output visualization capability, accuracy of simulation, etc. Finally, while each of the studied simulators provides a good simulation environment for VANETs, refinements and further contributions are needed before they can be widely used by the research community. Copyright © 2009 John Wiley & Sons, Ltd. \n5. Abstract of Cited Paper (BIB005): These days wireless communication has impacted our daily lives. The developments achieved in this field have made our lives amazingly simpler, easier, convenient and comfortable. One of these developments has occurred in Car to Car Communication (C2CC). Communication between cars often referred to vehicular ad hoc networks (VANET) has many advantages such as: reducing cars accidents, minimizing the traffic jam, reducing fuel consumption and emissions and etc. For a closer look on C2CC studies the necessity of simulation is obvious. Network simulators can simulate the Ad-hoc network but they cannot simulate the huge traffic of cities. In order to solve this problem, in this paper we study the Veins framework which is used to run a Traffic (SUMO) and a Network (OMNET++) simulator in parallel and we simulate the realistic traffics of the city of Cologne, Germany, as an ad-hoc network.\n\nReview Chapter:",
"role": "user"
},
{
"content": "Many simulators are available to help us simulate our research model and deduce the outcomes BIB005 . Some of the common simulators that are used in emergency traffic management are described below. QualNet is a tool that is used for training, testing, and planning of network simulation models and mimics the behavior of real physical networks. It supports a wide range of networks. An advantage of QualNet is that it is fast, accurate and has powerful GUI for modeling. The drawback of Qualnet is that it is complicated and not free. 5) MATLAB BIB002 Matlab is a very popular high performance mathematical technical computation tool that is widely used by researchers. It has high-performance architecture and is easy to use. It integrates programming with computation where the problems are addressed in familiar mathematical notations. Matlab makes testing, implementation and debugging of algorithms easy. It also performs visualization and analysis of extension data. 6) NetSim BIB001 NetSim is an end-to-end, full-stack and packet-level simulator that is very helpful for engineers to design networks. It's network libraries contain various protocols and topologies. NetSim makes building and debugging of your code easier and features a GUI interface. NetSim is expensive to operate as well as the users should be properly trained. It requires high system resources. It becomes difficult to operate as the size of the network increases. 7) OMNet++ BIB003 OMNet++ is a modular framework, component-based and runs on C++ that is used to building network simulators. Non-commercial use is very common in academic institutes. It's powerful GUI makes the tracing of packets easier as compared to other simulators. It is simple and easy to operate. It is free when used for non-commercial purposes like education and research. 8) SUMO SUMO is a tool that generates a traffic mobility framework and has integrated network simulators. SUMO is an open-source, portable and extensively used tool for monitoring continuous traffic analytics. It is designed for large scale road network simulations. An advantage is that it can evaluate traffic signal lights and forecast traffic statistics. It is used to model traffic management and simulate automatic driving. 9) VEINS BIB006 VEINS is an open-source framework that is used to simulate vehicular networks. It is a combination of OMNet++ and SUMO and it uses their features to offer a comprehensive model to make the simulation as realistic as possible. It can support the parallel running of the two simulators. VEINS makes the interaction of nodes with running traffic simulation easy. Its development is based on MiMiX and uses the 802.11p communication protocol. 10) TraNS BIB004 TraNS is a tool based on GUI that is used in VANETs which combine the traffic (SUMO) and network simulation (NS 2) into realistic traffic mobility simulations. It also stimulates the exchange of information between vehicles to analyze the behavior of different schemes. However, the development of TraNS has been suspended that is why it cannot support the latest versions of NS 2 and SUMO thus, there is no support for this tool as well. Different Simulators are designed for different environments and each of them has different usage. Every simulator has its pros and cons. The simulators along with their pros and cons are listed in table 2.",
"role": "assistant"
}
]
|
science.healthver_entailment | science.healthver_entailment.3067 | [
{
"content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: The coronavirus has been found to live on some surfaces for longer than 9 days\n\nResearch Abstract:\nWith limited infection control practices in overcrowded Bangladeshi hospitals, surfaces may play an important role in the transmission of respiratory pathogens in hospital wards and pose a serious risk of infection for patients, health care workers, caregivers and visitors.\nIn this study, we aimed to identify if surfaces near hospitalized patients with respiratory infections were contaminated with respiratory pathogens and to identify which surfaces were most commonly contaminated.\nBetween September-November 2013, we collected respiratory (nasopharyngeal and oropharyngeal) swabs from patients hospitalized with respiratory illness in adult medicine and paediatric medicine wards at two public tertiary care hospitals in Bangladesh.\nWe collected surface swabs from up to five surfaces near each case-patient including: the wall, bed rail, bed sheet, clinical file, and multipurpose towel used for care giving purposes.\nWe tested swabs using real-time multiplex PCR for 19 viral and 12 bacterial pathogens.\nCase-patients with at least one pathogen detected had corresponding surface swabs tested for those same pathogens.\nOf 104 patients tested, 79 had a laboratory-confirmed respiratory pathogen.\nOf the 287 swabs collected from surfaces near these patients, 133 (46%) had evidence of contamination with at least one pathogen.\nThe most commonly contaminated surfaces were the bed sheet and the towel.\nSixty-two percent of patients with a laboratory-confirmed respiratory pathgen (49/79) had detectable viral or bacterial nucleic acid on at least one surface.\nKlebsiella pneumoniae was the most frequently detected pathogen on both respiratory swabs (32%, 33/104) and on surfaces near patients positive for this organism (97%, 32/33).\nSurfaces near patients hospitalized with respiratory infections were frequently contaminated by pathogens, with Klebsiella pneumoniae being most common, highlighting the potential for transmission of respiratory pathogens via surfaces.\nEfforts to introduce routine cleaning in wards may be a feasible strategy to improve infection control, given that severe space constraints prohibit cohorting patients with respiratory illness.",
"role": "user"
},
{
"content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Surfaces near patients hospitalized with respiratory infections were frequently contaminated by pathogens, with Klebsiella pneumoniae being most common, highlighting the potential for transmission of respiratory pathogens via surfaces.\"]}",
"role": "assistant"
}
]
|
science.pico_ner | science.pico_ner.4669 | [
{
"content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\n[ Pharmacokinetics of theophylline in sustained-release formulation in young asthmatics ] . Pharmacokinetics of two theophylline ( CAS 58-55-9 ) sustained release preparations ( T : Bronchoretard Capsules/R : Capsule formulation from the US market ) were investigated in an open randomised two-way crossover design . The capsules of the test formulation were opened and administered on a tablespoonful of apple sauce . Nineteen asthmatics aged 6 to 12 years participated in this study . Following individual dosing of 100-300 mg theophylline twice a day , a pharmacokinetic profile for 24 h was derived after seven days of multiple dosing . All relevant parameters for rate ( Cmax ss , Cmin ss , Cav ss , plateau time , peak-trough fluctuation , nocturnal excess , tmax ss ) and extent of absorption ( AUCss ) were calculated for both formulations . With long plateau times ( T : 17.3 h ) and small peak-trough fluctuations ( T : 49.0 % ) , established quality criteria for high quality theophylline preparations were fulfilled by the test formulation . Furthermore , symmetrical peaks resulted after morning and evening administration of the test formulation . In conclusion , smooth and predictable concentration/time profiles were achieved , enabling an efficacious and safe therapy of asthma . This individual mode of administration allows not only a perfect dose titration in young asthmatics , but is also helpful to patients who have difficulty in swallowing large dosage forms .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"two theophylline ( CAS 58-55-9 ) sustained release preparations\", \"pharmacokinetic profile for 24 h was derived after seven days of multiple dosing\", \"T : Bronchoretard Capsules/R : Capsule formulation from the US market\", \"Following individual dosing of 100-300 mg theophylline twice a day\"], \"Outcome\": [\"Cmax ss , Cmin ss , Cav ss , plateau time , peak-trough fluctuation , nocturnal excess , tmax ss\", \"small peak-trough fluctuations\", \"plateau times\", \"extent of absorption\", \"symmetrical peaks\", \"concentration/time profiles\"], \"Participant\": [\"Nineteen asthmatics aged 6 to 12 years\", \"young asthmatics ]\"]}",
"role": "assistant"
}
]
|
science.craftchem_ner | science.craftchem_ner.3400 | [
{
"content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nBlackdottedlinesdemarcatethebasementmembranethatseparatestheepidermis(epi)fromdermis(der).",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.3381 | [
{
"content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nIn this paper, we address the problem of unsupervised video summarization that automatically extracts key-shots from an input video. Specifically, we tackle two critical issues based on our empirical observations: (i) Ineffective feature learning due to flat distributions of output importance scores for each frame, and (ii) training difficulty when dealing with long-length video inputs. To alleviate the first problem, we propose a simple yet effective regularization loss term called variance loss. The proposed variance loss allows a network to predict output scores for each frame with high discrepancy which enables effective feature learning and significantly improves model performance. For the second problem, we design a novel two-stream network named Chunk and Stride Network (CSNet) that utilizes local (chunk) and global (stride) temporal view on the video features. Our CSNet gives better summarization results for long-length videos compared to the existing methods. In addition, we introduce an attention mechanism to handle the dynamic information in videos. We demonstrate the effectiveness of the proposed methods by conducting extensive ablation studies and show that our final model achieves new state-of-the-art results on two benchmark datasets.\n\nCited Works Summary:\n[1]: This paper addresses the problem of unsupervised video summarization, formulated as selecting a sparse subset of video frames that optimally represent the input video. Our key idea is to learn a deep summarizer network to minimize distance between training videos and a distribution of their summarizations, in an unsupervised way. Such a summarizer can then be applied on a new video for estimating its optimal summarization. For learning, we specify a novel generative adversarial framework, consisting of the summarizer and discriminator. The summarizer is the autoencoder long short-term memory network (LSTM) aimed at, first, selecting video frames, and then decoding the obtained summarization for reconstructing the input video. The discriminator is another LSTM aimed at distinguishing between the original video and its reconstruction from the summarizer. The summarizer LSTM is cast as an adversary of the discriminator, i.e., trained so as to maximally confuse the discriminator. This learning is also regularized for sparsity. Evaluation on four benchmark datasets, consisting of videos showing diverse events in first-and third-person views, demonstrates our competitive performance in comparison to fully supervised state-of-the-art approaches.\n\n[2]: Video summarization has unprecedented importance to help us digest, browse, and search today's ever-growing video collections. We propose a novel subset selection technique that leverages supervision in the form of human-created summaries to perform automatic keyframe-based video summarization. The main idea is to nonparametrically transfer summary structures from annotated videos to unseen test videos. We show how to extend our method to exploit semantic side information about the video's category genre to guide the transfer process by those training videos semantically consistent with the test input. We also show how to generalize our method to subshot-based summarization, which not only reduces computational costs but also provides more flexible ways of defining visual similarity across subshots spanning several frames. We conduct extensive evaluation on several benchmarks and demonstrate promising results, outperforming existing methods in several settings.\n\n[3]: We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots. Casting the task as a structured prediction problem, our main idea is to use Long Short-Term Memory (LSTM) to model the variable-range temporal dependency among video frames, so as to derive both representative and compact video summaries. The proposed model successfully accounts for the sequential structure crucial to generating meaningful video summaries, leading to state-of-the-art results on two benchmark datasets. In addition to advances in modeling techniques, we introduce a strategy to address the need for a large amount of annotated data for training complex learning approaches to summarization. There, our main idea is to exploit auxiliary annotated video summarization datasets, in spite of their heterogeneity in visual styles and contents. Specifically, we show that domain adaptation techniques can improve learning by reducing the discrepancies in the original datasets’ statistical properties.\n\n[4]: Video summarization is a challenging problem with great application potential. Whereas prior approaches, largely unsupervised in nature, focus on sampling useful frames and assembling them as summaries, we consider video summarization as a supervised subset selection problem. Our idea is to teach the system to learn from human-created summaries how to select informative and diverse subsets, so as to best meet evaluation metrics derived from human-perceived quality. To this end, we propose the sequential determinantal point process (seqDPP), a probabilistic model for diverse sequential subset selection. Our novel seqDPP heeds the inherent sequential structures in video data, thus overcoming the deficiency of the standard DPP, which treats video frames as randomly permutable items. Meanwhile, seqDPP retains the power of modeling diverse subsets, essential for summarization. Our extensive results of summarizing videos from 3 datasets demonstrate the superior performance of our method, compared to not only existing unsupervised methods but also naive applications of the standard DPP model.",
"role": "user"
},
{
"content": "Zhang al [3] introduced two LSTMs to model the variable range dependency in video summarization. One LSTM was used for video frame sequences in the forward direction, while the other LSTM was used for the backward direction. In addition, a determinantal point process model [4] [2] was adopted for further improvement of diversity in the subset selection. Mahasseni al. [1] proposed an unsupervised method that was based on a generative adversarial framework. The model consists of the summarizer and discriminator. The summarizer was a variational autoencoder LSTM, which first summarized video and then reconstructed the output. The discriminator was another LSTM that learned to distinguish between its reconstruction and the input video.",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.3151 | [
{
"content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nFor example, while the ISO 24617-2 (Bunt et al., 2012) would tag ‘What?’ as AutoNegative thus capturing that the speaker is signaling non-understanding, we instead focus on what reaction the speaker expects to trigger in the listener by tagging this as a request to repeat.",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
]
|
science.drug_combo_extraction_re | science.drug_combo_extraction_re.915 | [
{
"content": "Analyze the given paragraph from a biomedical study. Focus on identifying drug pairings within a specified sentence. Your goal is to determine the nature of these pairings.\n\nPresent your findings as a JSON array. Each element should be an array containing the drug names and their interaction type. Use the exact names from the sentence.\n\nOnly consider the specified sentence for your analysis. The paragraph is for context only.\n\nReturn solely the JSON array. If no pairings are found, return an empty array.\n\nContext Paragraph: One-hour paclitaxel plus carboplatin in the treatment of advanced non-small cell lung cancer : results of a multicentre , phase II trial . The aim of this phase II study was to determine the activity and toxicity of paclitaxel (administered by 1-h infusion) and carboplatin in advanced non-small cell lung cancer when used in a multicentre, community-based treatment setting. 100 chemotherapy-naive patients with stage IIIB or IV non-small cell lung cancer were treated between March 1995 and February 1996. All patients had Karnofsky performance status 70-100, measurable disease and adequate bone marrow, kidney and liver function. All patients received intravenous (i.v.) paclitaxel 225 mg/m2 by 1-h infusion followed immediately by carboplatin at a targeted area under the concentration time curve (AUC) of 6.0 using the Calvert formula. Courses were repeated every 21 days. Colony stimulating factors were not used routinely. 38 of 94 evaluable patients (40%) had objective responses to treatment (3 complete responses, 35 partial responses). An additional 32 patients had stable disease at initial re-evaluation. Weight gain during treatment was experienced by 47% of patients with objective response or stable disease. The median survival in this group of 100 patients was 8 months, with an actuarial 1-year survival of 42%. Leucopenia was common, but hospitalisation for treatment of neutropenia and fever occurred in only 3% of courses. Cumulative peripheral neuropathy was common, but usually appeared after the third or fourth course and was severe (grade 3) in only 15% of patients. Other grade 3 and 4 toxicity was uncommon. There was one treatment-related death due to sepsis. This large multicentre community-based phase II trial demonstrated the efficacy of paclitaxel and carboplatin combination chemotherapy in advanced non-small cell lung cancer. When paclitaxel is given by 1-h infusion, this regimen is easily administered in the outpatient setting.\n\nTarget Sentence: One-hour paclitaxel plus carboplatin in the treatment of advanced non-small cell lung cancer : results of a multicentre , phase II trial .",
"role": "user"
},
{
"content": "[[\"paclitaxel\", \"carboplatin\", \"POS\"]]",
"role": "assistant"
}
]
|
science.scientific_lay_summarisation_elife_single_doc_summ | science.scientific_lay_summarisation_elife_single_doc_summ.3310 | [
{
"content": "Transform the provided sections of a biomedical research paper into a digestible summary for a general audience. Focus on simplifying complex ideas while retaining key scientific insights.\n\nResearch Title: Microsaccadic sampling of moving image information provides Drosophila hyperacute vision\nContent Overview:\nAbstract:\nSmall fly eyes should not see fine image details. Because flies exhibit saccadic visual behaviors and their compound eyes have relatively few ommatidia( sampling points), their photoreceptors would be expected to generate blurry and coarse retinal images of the world. Here we demonstrate that Drosophila see the world far better than predicted from the classic theories. By using electrophysiological, optical and behavioral assays, we found that R1-R6 photoreceptors’ encoding capacity in time is maximized to fast high-contrast bursts, which resemble their light input during saccadic behaviors. Whilst over space, R1-R6s resolve moving objects at saccadic speeds beyond the predicted motion-blur-limit. Our results show how refractory phototransduction and rapid photomechanical photoreceptor contractions jointly sharpen retinal images of moving objects in space-time, enabling hyperacute vision, and explain how such microsaccadic information sampling exceeds the compound eyes’ optical limits. These discoveries elucidate how acuity depends upon photoreceptor function and eye movements.\nIntroduction:\nThe acuity of an eye is limited by its photoreceptor spacing, which provides the grain of the retinal image. To resolve two stationary objects, at least three photoreceptors are needed for detecting the intensity difference in between. To resolve two moving objects is harder, as vision becomes further limited by each photoreceptor’s finite integration time and receptive field size( Srinivasan and Bernard, 1975; Juusola and French, 1997; Land, 1997). Nevertheless, animals- from insects to man- view the world by using saccades, fast movements, which direct their eyes to the surroundings, and fixation intervals between the saccades, during which gaze is held near stationary( Land, 1999). Because of photoreceptors’ slow integration-time, saccades should blur image details and these are thought to be sampled when gaze is stabilized. Thus, information would be captured during fixations whilst during saccades animals would be effectively blind. This viewpoint, however, ignores fast photoreceptor adaptation, which causes perceptual fading during fixation( Ditchburn and Ginsborg, 1952; Riggs and Ratliff, 1952), reducing visual information and possibly rendering perception to mean light only. Therefore, to maximize information and acuity, it is plausible that evolution has optimized photoreceptor function in respect to visual behaviors and needs. We have now devised a suite of new experimental and theoretical methods to study this question both in time and over space in Drosophila R1-R6 photoreceptors. The Drosophila compound eyes are composed of ~750 seemingly regular lens-capped modules called ommatidia, which should provide the fly a panoramic visual field of low optical resolution( Barlow, 1952; Land, 1997). Each ommatidium contains eight photoreceptor cells( R1-R8), pointing to seven different directions. The ultraviolet and blue-green-sensitive outer photoreceptors, R1-R6, initiate the motion vision pathway, whilst the central R7 and R8, which lie on top of each other, detect different colors from one direction( Wardill et al., 2012). Owing to the eye’s neural superposition principle, R1, R2, R3, R4, R5 and R6, each from a separate neighboring ommatidium, also point to the same direction. By pooling their output for synaptic transmission, the photoreceptor spacing( spatial resolution) effectively matches the ommatidium spacing( average interommatidial angle, Δφ = 4. 5o( Götz, 1964; Land, 1997; Gonzalez-Bellido et al., 2011) but the signal-to-noise ratio of the transmitted image could improve by √6( de Ruyter van Steveninck and Laughlin, 1996; Zheng et al., 2006). Here we show how evolution has improved Drosophila vision beyond these classic ideas, suggesting that light information sampling in R1-R6 photoreceptors is tuned to saccadic behavior. Our intracellular recordings reveal that R1-R6s capture 2-to-4-times more information in time than previous maximum estimates( Juusola and Hardie, 2001a; Song et al., 2012; Song and Juusola, 2014) when responding to high-contrast bursts( periods of rapid light changes followed by quiescent periods) that resemble light input from natural scenes generated by saccadic viewing. Biophysically-realistic model simulations suggest that this improvement largely results from interspersed ‘fixation’ intervals, which allow photoreceptors to sample more information from phasic light changes by relieving them from refractoriness( Song et al., 2012; Song and Juusola, 2014; Juusola et al., 2015). Remarkably, over space, our intracellular recordings, high-speed microscopy and modeling further reveal how photomechanical photoreceptor contractions( Hardie and Franze, 2012) work together with refractory sampling to improve spatial acuity. We discover that by actively modulating light input and photoreceptor output, these processes reduce motion blur during saccades and adaptation during gaze fixation, which otherwise could fade vision( Ditchburn and Ginsborg, 1952; Riggs and Ratliff, 1952; Land, 1997). The resulting phasic responses sharpen retinal images by highlighting the times when visual objects cross a photoreceptor’s receptive field, thereby encoding space in time( see also: Ahissar and Arieli, 2001; Donner and Hemilä, 2007; Rucci et al., 2007; Kuang et al., 2012a; Kuang et al., 2012; Franceschini et al., 2014; Viollet, 2014). Thus, neither saccades nor fixations blind the flies, but together improve vision. Incorporation of this novel opto-mechano-electric mechanism into our ‘microsaccadic sampling’-model predicts that Drosophila can see >4 fold finer details than their eyes’ spatial sampling limit – a prediction directly confirmed by optomotor behavior experiments. By demonstrating how fly photoreceptors’ fast microsaccadic information sampling provides hyperacute vision of moving images, these results change our understanding of insect vision, whilst showing an important relationship between eye movements and visual acuity.\nDiscussion:\nWe have provided deep new insight into spatiotemporal information processing in Drosophila R1-R6 photoreceptors and animal perception in general. Our results indicate that the dynamic interplay between saccades and gaze fixation is important for both the maintenance and enhancement of vision already at the photoreceptor level. This interplay, which is commonly observed in locomoting Drosophila( Geurten et al., 2014), makes light input to photoreceptors bursty. We showed that high-contrast bursts, which resemble light input during a fly’s saccadic behaviors, maximize photoreceptors’ information capture in time, and provided evidence that such encoding involves four interlinked mechanisms. Light input is first regulated by two processes inside photoreceptors: slower screening pigment migration( intracellular pupil, 1–10 s) and much faster photomechanical rhabdomere contractions( 0. 01–1 s). These modulations have low noise( Figure 2—figure supplement 2), enabling refractory photon sampling by microvilli to enhance information intake in phasic stimulus components. Finally, asymmetric synaptic inputs from the network differentiate individual R1-R6 outputs. Remarkably, over space, these mechanisms further sharpen neural resolvability by ~4 fold below the theoretical limit of the compound eye optics, providing hyperacute vision. Further analyses imply that these mechanisms with systematic rhabdomere size variations combat aliasing( Appendixes 2 and 5). Thus, with microsaccadic sampling, a fly’s behavioral decisions govern its visual information/acuity trade-off. To see the finest image details it should scan the world slowly, which probably happens during normal gaze fixation. But gaze fixation cannot be too slow; otherwise, adaptation would fade vision. Conversely, by locomoting faster, in a saccadic or bursty fashion, visual information capture in time is increased( see also: Juusola and de Polavieja, 2003), while surprisingly little spatial details about its surroundings would be lost. This viewing strategy corresponds well with the recent human psychophysics results and modeling of ganglion cell firing( Rucci and Victor, 2015), which indicate that microsaccades and ocular drift in the foveal region of the retina actively enhance perception of spatial details( Rucci et al., 2007; Poletti et al., 2013; Rucci and Victor, 2015). Interestingly, here our findings further imply that, in Drosophila, the extraction of phasic stimulus features, which characterize object boundaries and line elements in visual scenes, already starts during sampling and integration of visual information in the microvilli, at the first processing stage( rather than later on in the retinal network or in the brain). Our results make a general prediction about the optimal viewing strategy for maximizing information capture from the world. Animals should fixate gaze on darker features, as this resensitizes photoreceptors by relieving their refractory sampling units( e. g. microvilli). And then, rapidly move gaze across to brighter image areas, as saccadic crossings over high-contrast boundaries enhance information intake by increasing photoreceptors’ sample( quantum bump) rate changes/time( Appendix 9). Given the high occurrence of eye/head-saccades in animals with good vision( Land, 1999), it seems plausible that their photoreceptors could also have adapted encoding dynamics to quicken response modulation, reducing motion blur. Therefore, if information sampling biophysics in rods and cones were matched to microsaccadic eye movements, this could provide a mechanistic explanation to the old paradox: how saccadic gaze fixation provides stable perception of the world, while curtailing motion blur effects.",
"role": "user"
},
{
"content": "Fruit flies have five eyes: two large compound eyes which support vision , plus three smaller single lens eyes which are used for navigation . Each compound eye monitors 180° of space and consists of roughly 750 units , each containing eight light-sensitive cells called photoreceptors . This relatively wide spacing of photoreceptors is thought to limit the sharpness , or acuity , of vision in fruit flies . The area of the human retina ( the light-sensitive surface at back of our eyes ) that generates our sharpest vision contains photoreceptors that are 500 times more densely packed . Despite their differing designs , human and fruit fly eyes work via the same general principles . If we , or a fruit fly , were to hold our gaze completely steady , the world would gradually fade from view as the eye adapted to the unchanging visual stimulus . To ensure this does not happen , animals continuously make rapid , automatic eye movements called microsaccades . These refresh the image on the retina and prevent it from fading . Yet it is not known why do they not also cause blurred vision . Standard accounts of vision assume that the retina and the brain perform most of the information processing required , with photoreceptors simply detecting how much light enters the eye . However , Juusola , Dau , Song et al . now challenge this idea by showing that photoreceptors are specially adapted to detect the fluctuating patterns of light that enter the eye as a result of microsaccades . Moreover , fruit fly eyes resolve small moving objects far better than would be predicted based on the spacing of their photoreceptors . The discovery that photoreceptors are well adapted to deal with eye movements changes our understanding of insect vision . The findings also disprove the 100-year-old dogma that the spacing of photoreceptors limits the sharpness of vision in compound eyes . Further studies are required to determine whether photoreceptors in the retinas of other animals , including humans , have similar properties .",
"role": "assistant"
}
]
|
science.healthver_entailment | science.healthver_entailment.3281 | [
{
"content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: The virus cannot survive in tropical temperatures:\n\nResearch Abstract:\nOBJECTIVE Coronavirus disease 2019 (COVID-19) is a fatal and fast-spreading viral infection.\nTo date, the number of COVID-19 patients worldwide has crossed over six million with over three hundred and seventy thousand deaths (according to the data from World Health Organization; updated on 2 June 2020).\nAlthough COVID-19 can be rapidly diagnosed, efficient clinical treatment of COVID-19 remains unavailable, resulting in high fatality.\nSome clinical trials have identified vitamin C (VC) as a potent compound pneumonia management.\nIn addition, glycyrrhizic acid (GA) is clinically as an anti-inflammatory medicine against pneumonia-induced inflammatory stress.\nWe hypothesized that the combination of VC and GA is a potential option for treating COVID-19.\nMETHODS The aim of this study was to determine pharmacological targets and molecular mechanisms of VC + GA treatment for COVID-19, using bioinformational network pharmacology.\nRESULTS We uncovered optimal targets, biological processes and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways of VC + GA against COVID-19.\nOur findings suggested that combinatorial VC and GA treatment for COVID-19 was associated with elevation of immunity and suppression of inflammatory stress, including activation of the T cell receptor signaling pathway, regulation of Fc gamma R-mediated phagocytosis, ErbB signaling pathway and vascular endothelial growth factor signaling pathway.\nWe also identified 17 core targets of VC + GA, which suggest as antimicrobial function.\nCONCLUSIONS For the first time, our study uncovered the pharmacological mechanism underlying combined VC and GA treatment for COVID-19.\nThese results should benefit efforts to address the most pressing problem currently facing the world.",
"role": "user"
},
{
"content": "{\"verdict\": \"NEI\", \"evidence\": []}",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.3976 | [
{
"content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nIt was apparent that the AlkOH group content was comparable with previous results obtained with the one-stage organosolv pretreatments of poplar performed at milder conditions (165 C, 40 min, 1.0% H2SO4), (Pan et al., 2006b).",
"role": "user"
},
{
"content": "Result",
"role": "assistant"
}
]
|
science.scicite_classification | science.scicite_classification.3436 | [
{
"content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nThese observations confirm prior data showing that positive AF markers of infection are predictive of PPROM after successful arrest of preterm labor in women treated for preterm labor with intact membranes (10).",
"role": "user"
},
{
"content": "Result",
"role": "assistant"
}
]
|
science.chemprot_re | science.chemprot_re.951 | [
{
"content": "Examine the provided text and determine the interactions between chemical entities and genes. Focus on identifying any connections present.\n\nPresent your findings in a structured JSON format. Each relationship should be represented as an array entry. If no interactions are detected, return an empty array.\n\nText Content:\n\nNarirutin fraction from citrus peels attenuates alcoholic liver disease in mice. This study aimed to demonstrate protective activities of the narirutin fraction from peels of Citrus unshiu against ethanol-induced hepatic damage through an animal study. Citrus narirutin fraction (CNF), contained 75% of narirutin, was obtained by an ultra-sonicated extraction and further purification. ICR mice were divided into four groups; normaldiet control, ethanol control (6.5 g ethanol/kg), low-CNF (ethanol+150 mg CNF/kg) and high-CNF (ethanol+300 mg CNF/kg) groups. Consumption of alcohol for 8weeks induced severe liver damage with increases in prognostic indicators such as aspartate transaminase, alanine transaminase in serum whereas co-administration of CNF suppressed their increases. Excessive accumulations in liver TG and TC in ethanol control group were also suppressed by co-administration of CNF. Co-administration of CNF maintained SOD activity, GSH and malondialdehyde levels close to those of the normal diet group. Chronic consumption of alcohol also stimulated abrupt increases in pro-inflammatory cytokines such as nuclear factor (NF) -κB, tumor necrosis factor (TNF) -α and interleukin (IL) -1β in liver otherwise co-administration of CNF effectively suppressed production of these cytokines dose-dependently. These results indicate that co-administration of CNF with alcohol can alleviate alcohol induced liver damage through preventing lipid formation, protecting antioxidant system and suppressing productions of pro-inflammatory cytokines.",
"role": "user"
},
{
"content": "[[\"alcohol\", \"INDIRECT-UPREGULATOR\", \"aspartate transaminase\"], [\"alcohol\", \"ACTIVATOR\", \"tumor necrosis factor (TNF) -\\u03b1\"], [\"alcohol\", \"ACTIVATOR\", \"nuclear factor (NF) -\\u03baB\"], [\"alcohol\", \"ACTIVATOR\", \"interleukin (IL) -1\\u03b2\"], [\"alcohol\", \"INDIRECT-UPREGULATOR\", \"alanine transaminase\"]]",
"role": "assistant"
}
]
|
science.acl_arc_intent_classification | science.acl_arc_intent_classification.1299 | [
{
"content": "Examine the given text from a research paper in the field of NLP. Your task is to identify the role of the citation within the context provided. Focus on understanding the intent behind the citation and classify it accordingly.\n\nSection Title:\nintroduction\n\nText Before Citation:\nFollowing construction of the marker lexicon, the (source, target) chunks are generalized further using a methodology based on Block (2000) to permit a limited form of insertion in the translation process. Work using the marker hypothesis for MT adapts this monolingual mapping for pairs of languages: It is reasonably straightforward to map an English determiner-noun sequence onto a Japanese nounâcase marker segment, once one has identified the sets of marker tags in the languages to be translated. Nevertheless, Juola (1998, page 23) observes that âa slightly more general mapping, where two adjacent terminal symbols can be merged into a single lexical item (for example, a word and its case-marking), can capture this sort of result quite handily.â\n\nCitation Text:\nFollowing construction of the marker lexicon , the ( source , target ) chunks are generalized further using a methodology based on Block ( 2000 ) to permit a limited form of insertion in the translation process .\n\nText After Citation:\nAs a byproduct of the chosen methodology, we also derive a standard âword-levelâ translation lexicon. These various resources render the set of original translation pairs far more useful in deriving translations of previously unseen input. In Section 3, we describe in detail the segmentation process, together with the procedure whereby target chunks are combined to produce candidate translations. In Section 4, we report initially on two experiments in which we test different versions of our EBMT system against test sets of NPs and sentences.",
"role": "user"
},
{
"content": "Uses",
"role": "assistant"
}
]
|
science.chemdner_ner | science.chemdner_ner.1822 | [
{
"content": "Analyze the given text to identify specific entities. Focus on extracting relevant data.\n\nProvide your findings in JSON format. Each category should list the entities found.\n\nText:\n\nThe Hunger Games: p53 regulates metabolism upon serine starvation. Cancer cells reprogram their metabolism to support a high proliferative rate. A new study shows that, upon serine starvation, the tumor suppressor p53 activates p21 to shift metabolic flux from purine biosynthesis to glutathione production, which enhances cellular proliferation and viability by combating ROS (Maddocks et al., 2013).",
"role": "user"
},
{
"content": "{\"Chemical\": [\"glutathione\", \"purine\", \"serine\"]}",
"role": "assistant"
}
]
|
science.bioasq_general_qa | science.bioasq_general_qa.419 | [
{
"content": "Review the provided biomedical excerpts and respond to the question concisely. Ensure your answer is derived solely from the given context and avoid adding any extraneous information.\n\nQuestion: What is BioCreative?\n\nExcerpts: two biomedical named entity recognition (NER) comparative evaluations that have been held to date, namely BioCreative and Coling\nThe BioCreative II.5 community challenge addressed these tasks in a competition-style assessment to evaluate and compare different methodologies, to make aware of the increasing accuracy of automated methods, and to guide future implementations. In this paper, we present our approaches for protein-named entity recognition,\nIn task 1A of the BioCreAtIvE evaluation, systems had to be devised that recognize words and phrases forming gene or protein names in natural language sentences\nBioCreAtIvE, a competition for automated gene/protein name recognition.\nAn overview of the BioCreative 2012 Workshop Track III: interactive text mining task.\nBiocuration workflows and text mining: overview of the BioCreative 2012 Workshop Track II.\nEvaluation of text-mining systems for biology: overview of the Second BioCreative community challenge.\nHow to link ontologies and protein-protein interactions to literature: text-mining approaches and the BioCreative experience.\nThe 2006 BioCreative competition was aimed at evaluating text-mining procedures in comparison with manual annotation of protein-protein interactions.\nRESULTS: The Biocreative 2010 competition addressed three tasks: gene normalization, article classification and interaction method identification.\nBioCreAtIvE task 2 was an experiment to test if automatically derived classification using information retrieval and extraction could assist expert biologists in the annotation of the GO vocabulary to the proteins in the UniProt Knowledgebase.\nTo this end BioCreative I was held in 2004, BioCreative II in 2007, and BioCreative II.5 in 2009. Each of these workshops involved humanly annotated test data for several basic tasks in text mining applied to the biomedical literature.\nBACKGROUND: The overall goal of the BioCreative Workshops is to promote the development of text mining and text processing tools which are useful to the communities of researchers and database curators in the biological sciences. To this end BioCreative I was held in 2004, BioCreative II in 2007, and BioCreative II.5 in 2009.\nBACKGROUND: The overall goal of the BioCreative Workshops is to promote the development of text mining and text processing tools which are useful to the communities of researchers and database curators in the biological sciences. To this end BioCreative I was held in 2004, BioCreative II in 2007, and BioCreative II.5 in 2009. Each of these workshops involved humanly annotated test data for several basic tasks in text mining applied to the biomedical literature.\nTo this end BioCreative I was held in 2004, BioCreative II in 2007, and BioCreative II.5 in 2009. Each of these workshops involved humanly annotated test data for several basic tasks in text mining applied to the biomedical literature. Participants in the workshops were invited to compete in the tasks by constructing software systems to perform the tasks automatically and were given scores based on their performance.\nOverview of BioCreAtIvE: critical assessment of information extraction for biology.",
"role": "user"
},
{
"content": "A community wide effort to evaluate biomedical information extraction and text mining.",
"role": "assistant"
}
]
|
science.scireviewgen_multidoc_summarization | science.scireviewgen_multidoc_summarization.3161 | [
{
"content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: An overview of Dynamic Software Product Line architectures and techniques: Observations from research and industry \nChapter Title: DSPL organizational changes \n1. Abstract of Cited Paper (BIB001): Replica correlation processing, and associated representative signal-data reduction and reconstruction techniques, are used to detect signals of interest and obtain robust measures of received-signal parameters, such as time differences of signal arrival and directional angles of arrival, that can be used to estimate the location of a cellularized-communications signal source. The new use in the present invention of signal-correlation processing for locating communications transmitters. This enables accurate and efficient extraction of parameters for a particular signal even in a frequency band that contains multiple received transmissions, such as occurs with code-division-multiple-access (CDMA) communications. Correlation processing as disclosed herein further enables extended processing integration times to facilitate the effective detection of desired communications-signal effects and replication measurement of their location-related parameters, even for the communications signals modulated to convey voice conversations or those weakened through propagation effects. Using prior, constructed, signal replicas in the correlation processing enables elimination of the inter-site communications of the signal representations that support the correlation analyses. Reduced-data representations of the modulated signals for voiced conversation, or for the variable components of data communications, are used to significantly reduce the inter-site communications that support the correlation analyses. \n2. Abstract of Cited Paper (BIB002): Software Product Lines, in conjunction with model- driven product derivation, are successful examples for extensive automation and reuse in software development. However, often each single product requires an individual, tailored user interface of its own to achieve the desired usability. Moreover, in some cases (e.g., online shops, games) it is even mandatory that each product has an individual, unique user interface of its own. Usually, this results in manual user interface design independent from the model-driven product derivation. Consequently, each product configuration has to be mapped manually to a corresponding user interface which can become a tedious and error-prone task for large and complex product lines. This paper addresses this problem by integrating concepts from SPL product derivation and Model-based User Interface Development. This facilitates both (1) a systematic and semi-automated creation of user interfaces during product derivation while (2) still supporting for individual, creative design.\n\nReview Chapter:",
"role": "user"
},
{
"content": "In addition of the desired properties a DSPL should have, adding support for runtime changes may lead to some organizational changes in the DSPL versus conventional software product lines. From our observation we believe these organizational changes will modify and/or extend the traditional SPL activities in order to handle runtime activities, such as: runtime reconfiguration, runtime model checking, or transitioning between multiple binding times where re-deployment tasks are sometimes needed. From our perspective, the main challenges and activities that change from conventional SPL that affect the organizational issues of a DSPL are the following: • Domain scoping/analysis: Traditional domain analysis should include now modeling the context properties that are used as context properties by many systems that exploit environmental characteristics at runtime. Hence, while domain scoping still identifies the scope of the product family member, context analysis extends the domain scoping activity to identify those context features that are relevant for DSPL products. • Architecting the DSPL: The traditional product line architecture (PLA) must include specific modules for supporting runtime reconfigurations and dynamic binding in order to automate the decision making process that may happen at execution time, and those runtime checking processes that ensure the consistency and validity of the modified feature model. • Product derivation: The derivation of SPL products has many challenges when giving automated support BIB002 Elsner, 2012) . Some authors suggest semi-automatic derivation procedures using non-functional properties BIB001 or derivation techniques like model-driven engineering BIB003 in order to facilitate the generation of products. Such techniques may change the traditional application engineering phase as they entangle features, code, and automatic procedures to build the selected product more automatically. Semi-automatic derivation techniques are fully compatible with any DSPL derivation activity, as the DSPL products may demand the automation of redeployment and reconfiguration activities. Moreover, DSPL derivation and generation activities provide as much automation as possible and go a step beyond in order to enable the redeployment at the latest time, for which runtime checking of a reconfigured feature model results key. • Product reconfiguration: The dynamic nature of DSPL products demand checking and reconfiguration activities that can be performed in runtime mode, which highlights the difference versus traditional SPL products. Consequently, and based on the challenges described before, the organization of a DSPL varies slightly from the traditional SPL duallifecycle (e.g., including new activities supporting the runtime nature of DSPL assets and products, such as we shown in Fig. 1 . The DSPL dual lifecycle of Fig. 2 extends the one traditionally used by current product lines with the following modifications. In the DSPL runtime domain engineering phase, we the traditional domain analysis activity is extended with a context analysis task, in which we identify not only the asset requirements and family member features but also those context-aware properties relevant for our DSPL products. Therefore, context variability and contextspecific features are identified during the initial modeling phase. Also, multiple binding times and rebinding options of features can be defined as properties in the feature model, as well as the valid states for those context features. The runtime software architecture should include all those mechanisms able to handle the dynamic changes of DSPL assets and products, the activation and deactivation of features dynamically and the possible modification of the structural variability at runtime. This architecture should lead to the implementation of those reconfigurable and nonreconfigurable assets that will be tested at the end of the line, as well as the validity of the feature model. All these artifacts will populate the DSPL repository for the subsequent phase. During the DSPL runtime application engineering phase, runtime and non-runtime requirements drive the construction of DSPL family members. The runtime DSPL architecture will be customized alongside the feature model to produce the DSPL products that will exhibit the reconfigurable characteristics required. Once products are tested, configured, and deployed, if a new software configuration (e.g., due to the activation of features, changes in the quality level of the system, or the selection to new services) is required at runtime, our DSPL dual lifecycle support encompasses post-deployment and reconfiguration task for handling all these changes. In some cases, certain runtime checking, testing and monitoring, and reconfiguration operations have to be made after the product is re-redeployed before it goes to its normal operational mode. Feedback from this task populates again the DSPL repository. As a result, these new activities extend the traditional application engineering phase with new post-reconfiguration tasks that are performed dynamically. Once we have described the major methodological changes 2 using a DSPL, in the following sections we focus on those runtime variability mechanisms that constitute the core of Dynamic Software Product Lines.",
"role": "assistant"
}
]
|
science.cdr_ner | science.cdr_ner.114 | [
{
"content": "Examine the provided text to identify entities. Focus on extracting relevant information.\n\nPresent your findings in a structured JSON format. Each category should list the entities found.\n\nSource Material:\n\nAcute confusion induced by a high-dose infusion of 5-fluorouracil and folinic acid. A 61-year-old man was treated with combination chemotherapy incorporating cisplatinum, etoposide, high-dose 5-fluorouracil (2,250 mg/m2/24 hours) and folinic acid for an inoperable gastric adenocarcinoma. He developed acute neurologic symptoms of mental confusion, disorientation and irritability, and then lapsed into a deep coma, lasting for approximately 40 hours during the first dose (day 2) of 5-fluorouracil and folinic acid infusion. This complication reappeared on day 25 during the second dose of 5-fluorouracil and folinic acid, which were then the only drugs given. Because folinic acid was unlikely to be associated with this condition, neurotoxicity due to high-dose 5-fluorouracil was highly suspected. The pathogenesis of 5-fluorouracil neurotoxicity may be due to a Krebs cycle blockade by fluoroacetate and fluorocitrate, thiamine deficiency, or dihydrouracil dehydrogenase deficiency. High-dose 5-fluorouracil/folinic acid infusion therapy has recently become a popular regimen for various cancers. It is necessary that both oncologists and neurologists be fully aware of this unusual complication.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"thiamine\", \"fluorocitrate\", \"dihydrouracil\", \"cisplatinum\", \"5-fluorouracil\", \"folinic acid\", \"fluoroacetate\", \"etoposide\"], \"Disease\": [\"irritability\", \"coma\", \"disorientation\", \"gastric adenocarcinoma\", \"confusion\", \"cancers\", \"neurotoxicity\"]}",
"role": "assistant"
}
]
|
science.nlmgene_ner | science.nlmgene_ner.164 | [
{
"content": "Analyze the provided text to identify gene-related entities. \n\nFormat your findings as a JSON object: {\"Gene\": [\"ExampleGene\", ...]}. Use the entity type as the key, and list the entities under it. If no entities are found, use an empty list.\n\nFocus solely on the JSON output.\n\nText:\n\nNovel nesprin-1 mutations associated with dilated cardiomyopathy cause nuclear envelope disruption and defects in myogenesis. Nesprins-1 and -2 are highly expressed in skeletal and cardiac muscle and together with SUN (Sad1p/UNC84)-domain containing proteins and lamin A/C form the LInker of Nucleoskeleton-and-Cytoskeleton (LINC) bridging complex at the nuclear envelope (NE). Mutations in nesprin-1/2 have previously been found in patients with autosomal dominant Emery-Dreifuss muscular dystrophy (EDMD) as well as dilated cardiomyopathy (DCM). In this study, three novel rare variants (R8272Q, S8381C and N8406K) in the C-terminus of the SYNE1 gene (nesprin-1) were identified in seven DCM patients by mutation screening. Expression of these mutants caused nuclear morphology defects and reduced lamin A/C and SUN2 staining at the NE. GST pull-down indicated that nesprin-1/lamin/SUN interactions were disrupted. Nesprin-1 mutations were also associated with augmented activation of the ERK pathway in vitro and in hearts in vivo. During C2C12 muscle cell differentiation, nesprin-1 levels are increased concomitantly with kinesin light chain (KLC-1/2) and immunoprecipitation and GST pull-down showed that these proteins interacted via a recently identified LEWD domain in the C-terminus of nesprin-1. Expression of nesprin-1 mutants in C2C12 cells caused defects in myoblast differentiation and fusion associated with dysregulation of myogenic transcription factors and disruption of the nesprin-1 and KLC-1/2 interaction at the outer nuclear membrane. Expression of nesprin-1α2 WT and mutants in zebrafish embryos caused heart developmental defects that varied in severity. These findings support a role for nesprin-1 in myogenesis and muscle disease, and uncover a novel mechanism whereby disruption of the LINC complex may contribute to the pathogenesis of DCM.",
"role": "user"
},
{
"content": "{\"Gene\": [\"Nesprins-1 and -2\", \"kinesin light chain\", \"nesprin-1\\u03b12\", \"lamin\", \"SYNE1\", \"SUN2\", \"nesprin-1\", \"Sad1p/UNC84\", \"nesprin-1/2\", \"Nesprin-1\", \"KLC-1/2\", \"SUN\", \"ERK\", \"lamin A/C\"]}",
"role": "assistant"
}
]
|
science.mslr2022_ms2_multidoc_summarization | science.mslr2022_ms2_multidoc_summarization.12942 | [
{
"content": "Analyze the following collection of medical RCT summaries. Your goal is to craft a concise synthesis of the findings. Focus on the core insights and present them succinctly. Only include the synthesis in your response. Below are the RCT summaries:\n\n\n\nReport 1:\nTitle: The feasibility of creating a checklist for the assessment of the methodological quality both of randomised and non-randomised studies of health care interventions.\nSummary: OBJECTIVE : To test the feasibility of creating a valid and reliable checklist with the following features : appropriate for assessing both r and omised and non-r and omised studies ; provision of both an overall score for study quality and a profile of scores not only for the quality of reporting , internal validity ( bias and confounding ) and power , but also for external validity . DESIGN : A pilot version was first developed , based on epidemiological principles , review s , and existing checklists for r and omised studies . Face and content validity were assessed by three experienced review ers and reliability was determined using two raters assessing 10 r and omised and 10 non-r and omised studies . Using different raters , the checklist was revised and tested for internal consistency ( Kuder-Richardson 20 ) , test-retest and inter-rater reliability ( Spearman correlation coefficient and sign rank test ; kappa statistics ) , criterion validity , and respondent burden . MAIN RESULTS : The performance of the checklist improved considerably after revision of a pilot version . The Quality Index had high internal consistency ( KR-20 : 0.89 ) as did the subscales apart from external validity ( KR-20 : 0.54 ) . Test-retest ( r 0.88 ) and inter-rater ( r 0.75 ) reliability of the Quality Index were good . Reliability of the subscales varied from good ( bias ) to poor ( external validity ) . The Quality Index correlated highly with an existing , established instrument for assessing r and omised studies ( r 0.90 ) . There was little difference between its performance with non-r and omised and with r and omised studies . Raters took about 20 minutes to assess each paper ( range 10 to 45 minutes ) . CONCLUSIONS : This study has shown that it is feasible to develop a checklist that can be used to assess the method ological quality not only of r and omised controlled trials but also non-r and omised studies . It has also shown that it is possible to produce a checklist that provides a profile of the paper , alerting review ers to its particular method ological strengths and weaknesses . Further work is required to improve the checklist and the training of raters in the assessment of external validity\n\n\nReport 2:\nTitle: The affective component of the secure base schema: affective priming with representations of attachment security.\nSummary: Using an affective priming procedure ( S. T. Murphy & R. B. Zajonc , 1993 ) , 7 studies examined the effects of the context ual activation of representations of attachment security ( secure base schema ) on the evaluation of neutral stimuli under either neutral or stressful context s. In all the studies , participants also reported on their attachment style . Results indicated that the subliminal priming of secure base representations led to more positive affective reactions to neutral stimuli than did the subliminal priming of neutral or no pictures under both neutral and stressful context s. Although the subliminal priming of positively valued , attachment-unrelated representations heightened positive evaluations under neutral context s , it failed to elicit positive affect under stressful context s. The results also revealed interesting effects of attachment style . The discussion focuses on the affective component of the secure base schema\n\n\nReport 3:\nTitle: Close Relationships and the Working Self-Concept: Implicit and Explicit Effects of Priming Attachment on Agency and Communion\nSummary: Two studies investigated how context ually activating attachment relationships influences the working self-concept in terms of agency and communion . In Study 1 , 245 participants were primed with a secure , avoidant , or anxious-ambivalent relationship and the implicit accessibility of agency and communion was assessed using word fragments . Activating a secure relationship increased the accessibility of communion , whereas activating an anxious-ambivalent relationship increased the accessibility of agency . In Study 2 , 123 participants were primed with a secure , preoccupied , avoidant-dismissive , or avoidant-fearful relationship and explicit self-perceptions of agency and communion traits were assessed using the Extended Personality Attributes Question naire ( EPAQ ) . Gender interacted with the attachment prime , such that men primed with a secure relationship reported higher communion than did men primed with an avoidant ( dis-missive or fearful ) relationship , whereas women primed with an anxious ( preoccupied or fearful ) relationship reported higher agency than did women primed with a secure relationship\n\n\nReport 4:\nTitle: Attachment Security Priming Decreases Children's Physiological Response to Threat.\nSummary: Ninety 6- and 7-year-olds ( 49.3 % White , mostly middle class ) from greater Washington , DC were r and omly assigned to a subliminal priming condition ( secure , happy , or neutral ) to determine if attachment security priming decreases physiological , expressive , and self-reported fear reactions to threatening stimuli . Dispositional attachment security was also assessed . Secure priming and attachment security each decreased electrodermal reactivity , increased vagal augmentation , and decreased fearful facial expressions compared to control conditions . Examination of a statistical interaction between security priming and child attachment indicated that , although secure children had increased vagal augmentation and fewer fearful expressions than insecure children , the effects of priming were constant across secure and insecure children . There were no priming or attachment effects associated with children 's self-reported fear",
"role": "user"
},
{
"content": "Thirty empirical studies met our inclusion criteria , including 28 adult and 2 child and adolescent sample s. The findings show that attachment security priming improved positive affect and reduced negative affect relative to control primes .\nImportantly , repeated priming studies showed a cumulative positive effect of security priming over time .\nWe conclude that repeated priming study design s may be the most effective .",
"role": "assistant"
}
]
|
science.chemsum_single_document_summarization | science.chemsum_single_document_summarization.4085 | [
{
"content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nPASADENA hyperpolarized 13C phospholactate\n\nContent Extracts:\n\n<p>Hyperpolarized magnetic resonance (MR) of 13C and 15N exogenous metabolic contrast agents is a rapidly developing field, which progressed from proof-of-principle studies in the early 2000s1,2 to the first clinical trial in men.3 The underlying driving force stems in part from the demonstrated capability to detect abnormal metabolic pathways in cancer4–7 and other diseases with impaired metabolism.8 Hyperpolarization of long-lived nuclear spin states increases sensitivity by 4–6 orders of magnitude2,9 with nuclear spin polarization approaching the order of unity. Hyperpolarized metabolic agents such as 1-13C-pyruvate can report on metabolic status of tumors similarly to positron emission tomography (PET) tracers.</p><p>One of the main bottlenecks for preclinical and clinical application of hyperpolarized MR is the development and validation of relevant compounds that can probe biochemical pathways in vivo. Dynamic nuclear polarization (DNP)10 has been most widely used to date with the main drawback of long (~ 1 h) polarization cycles. Parahydrogen induced polarization (PHIP) offers significantly faster preparations with hyperpolarization cycles as short as 1 minute. However, it is limited by the availability of the required unsaturated molecular precursors that are necessary for molecular addition of parahydrogen11,12, which acts as a source of spin order. An additional requirement for increased relaxation time of the hyperpolarized 13C or 15N site is the absence of directly attached protons allowing for in vivo spin lattice relaxation time T1 as long as 43 seconds13 and 2 minutes14 respectively. As a result, the smallest PHIP moiety consists of an unsaturated C=C or C≡C bond adjacent to a labeled 13C or 15N site. For 13C hyperpolarized compounds, this represents a three carbon limitation successfully exemplified by acrylate moiety by a number of groups.15,16 However, hydrogenation of acrylate results in propionate, which turns out to be useful only for angiographic applications.1,15 In contrast, a leading DNP hyperpolarized metabolic agent 1-13C-pyruvate is also a three-carbon molecule carrying an extra oxygen atom in addition to the three-carbon skeleton of propionate, Fig. 1. Hyperpolarized 1-13C-pyruvate is not amenable by PHIP.</p><p>Here, we describe hyperpolarization of 1-13C-phospholactate by PHIP. While both 1-13C-propionate and 1-13C-phospholactate are carboxylic acids with three-carbon backbones, 1-13C-phospholactate has an extra phosphate protected oxygen. The latter makes it similar to pyruvate, as it can be potentially metabolized, Fig. 1. This is a proof-of-principle study demonstrating (i) the feasibility of molecular addition of parahydrogen with established and commercially available Rh-based water-soluble catalyst and resulting in 13C hyperpolarization, (ii) sufficiently long life time of this potentially new metabolic contrast agent, and (iii) complete characterization of homo- and heteronuclear spin-spin couplings. The latter are necessary for optimization of PHIP polarization efficiency especially for perdeuterated unsaturated precursors, which represent a three spin system consisting of two nascent parahydrogen protons and a 13C or 15N nucleus. In addition, perdeuterated precursors may result in hyperpolarized compounds with longer relaxation time.17 Deuteration minimizes the number of nearby protons, which have significantly greater magnetic moment compared to that of deuterons. As a result, 13C T1 decrease due to dipolar relaxation mechanism may be somewhat minimized.17</p><p>The double C=C bond is stable with phosphate moiety in the second position, Fig. 1, allowing for molecular hydrogenation and PHIP. The unsaturated precursor is non-toxic 1-13C-phosphoenolpyruvate (PEP, Sigma-Aldrich #589,462), which becomes 13C hyperpolarized racemic 1-13C-phospholacate (PLAC) with D- and L- forms. The protection by phosphate group allows stabilizing the carbon-carbon double bond adjacent to the oxygen atom. While other protecting groups can potentially be used, the phosphate moiety could be quickly removed enzymatically18 by a suitable choice of phosphatase to yield hyperpolarized 1-13C-lactate (LAC), Fig. 1. Moreover, phosphate ions are biologically compatible and therefore do not require additional purification steps other than removal of phosphatase prior to in vivo administration.</p><p>Experimental polarization procedures and equipment were identical to those described earlier.9,19 13C PHIP polarization of PLAC, Fig. 2a, was conducted in a 0.0475 T polarizer9 with 2.5 mM water soluble Rh-based catalyst19,20 using the Gold-man polarization transfer sequence.16 99.8% D2O (Sigma-Aldrich-Isotec # 617,385) was used as a medium, pH = 11 using 18 mM phosphate buffer, for 4 second long hydrogenation of 1.8 mM PEP for high resolution 13C studies using an 11.7 T Bruker NMR spectrometer equipped with a 5 mm X-H RF probe, Fig 2. Following the PHIP procedure, hyperpolarized solution was injected in a 5 mm NMR tube. The NMR tube was inserted into the NMR spectrometer and the solution degassed during an ~ 30 second delay. The degassing step is necessary to eliminate residual parahydrogen-nitrogen bubbles and their associated susceptibility gradients and broad lines. 1H decoupled 13C spectra, Fig. 2b, were acquired approximately 60 seconds or 3×T1 after PHIP hyperpolarization resulting in hyperpolarization decay by 20 fold. Nevertheless, a 50 fold signal enhancement of PLAC was observed, Fig. 2b, when compared to the 13C signal recorded from the same sample at Boltzmann levels of 13C polarization, Fig. 2c. This 50-fold enhancement corresponds to a 13C polarization of 0.05% at 11.7 T and 298 K. Taking into account 20-fold polarization loss during ~ 60 s delivery and degassing procedure, polarization of 1% was produced in the polarizer. The conversion of PEP (13C δ = 171.9 ppm) to PLAC (13C δ = 182.1 ppm) was only 25% due to non-optimal catalyst preparation. The Rh-based catalyst was further optimized for low field in situ NMR studies at 0.0475 T by titration of Bis(norbornadiene)rhodium(I) tetrafluoroborate (Strem # 45-0230, Newburyport, MA) and 3, 3′-(1,4-butanediylbis(phenylphosphinidene))bispropanesulfonic, disodium salt (Sigma-Aldrich-Isotec #Q36333-SPEC), Shchepin, R.V., unpublished results.</p><p>Low field in situ detection of 13C hyperpolarization was conducted with 2.0 mM PEP in aqueous medium with double de-ionized water, pH = 9.8 using 22 mM phosphate buffer resulting in 99+% chemical conversion to PLAC, pH = 8.8. While excellent PEP chemical conversion is achieved, in vivo use of the hyperpolarized contrast agent would require additional pH neutralization and catalyst removal. It should also be noted that D-isomers may not be metabolized in vivo and may be toxic. The signal intensity of a single scan 13C hyperpolarized spectrum, 0.007 millimoles of PLAC, Fig. 3b, was compared to that of a 13C spectrum acquired using 170 millimoles of sodium 1-13C-acetate at Boltzmann polarization at 0.0475 T and 308 K, Fig. 3a.9 1.0 % polarization was achieved corresponding to 13C signal enhancement ε = 240,000 fold at 0.0475 T and 308 K. It is in good agreement with our high field studies. 13C T1 was measured by monitoring 13C hyperpolarization decay using a time series of 13C spectra acquired every 20 seconds with 30° excitation pulses, Fig. 3c. The T1 of 1-13C at 0.0475 T was 36 ± 2 seconds, which is twice as long as the T1 measured at 11.7 T in D2O. The T1 decay was simulated as an exponential decay taking into account the effect of RF pulses on 13C magnetization. A likely explanation for longer T1 at low magnetic field is a reduced chemical shift anisotropy, which is expected to dominate T1 relaxation at high magnetic fields.21 Similar field effect was reported for the 13C T1 in 2-hydroxyethyl-1-13C-propionate-2,3,3-d3.9</p><p>The solution used in PHIP low field studies was reduced in volume using a rotary evaporator, dissolved in 99.8% D2O and used for high-resolution studies of PLAC spin-spin couplings, Fig. 4. The combination of heteronuclear spectra, Fig. 4, over-determines the problem of complex multiplets and allows for accurate measurements of the spin-spin coupling magnitudes shown in Fig. 2a.: J3HH = 6.90 Hz, J3HC = 4.07 Hz, J2HC = 3.80 Hz, J3PC = 6.52 Hz, J3HP = 8.60 Hz. The knowledge of spin-spin couplings is critical for optimal performance of PHIP polarization transfer sequences that convert spin order of nascent parahydrogens to detectable 13C magnetization.</p><p>1-13C-phospholactate is suitable for measurement of spin-spin couplings due to 13C enrichment. The PHIP product of perdeuterated 1-13C-PEP, PLAC-d2, could lengthen 13C T1 somewhat and yield higher polarization, with the caveat that the extra deuterons in PLAC would pose synthetic challenges and complicate the spectra of 1H, 13C and 31P, making spin-spin coupling measurements more arduous. An alternative would be to use natural abundance PEP similarly to the strategy utilized for 13C hyperpolarized succinate,17 but this would require recording 13C spectra at natural abundance levels of 13C resulting in many hours of acquisition time. If PEP is perdeuterated, the spin system participating in polarization transfer dynamics would be reduced to three spins: 13C and two nascent parahydrogens in PLAC. Since Goldman's polarization transfer16 is designed for three-spin systems and is not expected to perform well for systems with more than 3 spins, it is likely to result in a significantly greater hyperpolarization using perdeuterated PEP compared to the 5-spin system used here.17,22</p><p>While the metabolic relevance of PLAC itself for biomedical imaging is yet to be seen, the corresponding relevance of LAC as an imaging agent is certainly well-established23. One possibility to produce LAC from PLAC would be to enzymatically cleave the phosphate moiety.18 It is also possible that phosphatases of blood could cleave phosphate moiety after intravenous injection of PLAC. Fast hyperpolarization of LAC by PHIP method would present a clear advantage over DNP method and would make this promising contrast agent available to a broader range of biomedical scientists for cancer and cardiovascular research.7 Moreover, if successful, this strategy of using phosphate protected −C=C-O- motifs and subsequent cleavage could be extended to hyperpolarization of other metabolic contrast agents including 15N-choline.</p>",
"role": "user"
},
{
"content": "We demonstrate that potassium 1-13C-phosphoenolpyruvate becomes hyperpolarized potassium 1-13C \\xe2\\x80\\x93phospholactate with 13C T1 = 36 s after molecular hydrogenation by PASADENA (Parahydrogen and Synthesis Allows Dramatically Enhanced Nuclear Alignment). This proof-of-principle study was conducted with a fully protonated molecular precursor. 13C was polarized to a level of 1 %, corresponding to nearly 4,000 fold sensitivity enhancement at 3 T. The relevant homo- and heteronuclear spin-spin couplings are reported.",
"role": "assistant"
}
]
|
science.bc7_litcovid_topic_classification | science.bc7_litcovid_topic_classification.557 | [
{
"content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nBACKGROUD: The association between underlying comorbidities and cardiac injury and the prognosis in coronavirus disease 2019 (COVID-19) patients was assessed in this study. HYPOTHESIS: The underlying comorbidities and cardiac injury may be associated with the prognosis in COVID-19 patients. METHODS: A systematic search was conducted in PubMed, EMBASE, Web of science, and The Cochrane library from December 2019 to July 2020. The odds ratio (OR) and 95% confidence intervals (95% CI) were used to estimate the probability of comorbidities and cardiac injury in COVID-19 patients with or without severe type, or in survivors vs nonsurvivors of COVID-19 patients. RESULTS: A total of 124 studies were included in this analysis. A higher risk for severity was observed in COVID-19 patients with comorbidities. The pooled result in patients with hypertension (OR 2.57, 95% CI: 2.12-3.11), diabetes (OR 2.54, 95% CI: 1.89-3.41), cardiovascular diseases (OR 3.86, 95% CI: 2.70-5.52), chronic obstractive pulmonary disease (OR 2.71, 95% CI: 1.98-3.70), chronic kidney disease (OR 2.20, 95% CI: 1.27-3.80), and cancer (OR 2.42, 95% CI: 1.81-3.22) respectively. All the comorbidities presented a higher risk of mortality. Moreover, the prevalence of acute cardiac injury is higher in severe group than in nonsevere group, and acute cardiac injury is associated with an increased risk for in-hospital mortality. CONCLUSION: Comorbidities and acute cardiac injury are closely associated with poor prognosis in COVID-19 patients. It is necessary to continuously monitor related clinical indicators of organs injury and concern comorbidities in COVID-19 patients.",
"role": "user"
},
{
"content": "[\"Treatment\", \"Diagnosis\"]",
"role": "assistant"
}
]
|
science.mslr2022_ms2_multidoc_summarization | science.mslr2022_ms2_multidoc_summarization.1846 | [
{
"content": "Analyze the following collection of medical RCT summaries. Your goal is to craft a concise synthesis of the findings. Focus on the core insights and present them succinctly. Only include the synthesis in your response. Below are the RCT summaries:\n\n\n\nReport 1:\nTitle: Expression of a molecular marker panel as a prognostic tool in gastric cancer patients treated postoperatively with docetaxel and irinotecan. A study of the Hellenic Cooperative Oncology Group.\nSummary: INTRODUCTION This study evaluated the prognostic role of vascular epidermal growth factor ( VEGF ) , thymidylate synthase ( TS ) , topoisomerase I ( Topo-I ) , topoisomerase IIalpha ( Topo-IIalpha ) and E-cadherin ( E-cadh ) tumor expression , in patients with resectable gastric cancer , who were treated postoperatively with the docetaxel/irinotecan combination . PATIENTS AND METHODS Forty-five patients with resectable gastric cancer were treated with 6 cycles of docetaxel 30 mg/m2 and irinotecan 110 m/m2 on day 1 and d8 every 21 days . All specimens were examined by using immunohistochemistry ( IHC ) for the expression of VEGF , TS , Topo-I , Topo-IIalpha and E-cadh . RESULTS Positivity for TS was significantly correlated with age and for VEGF with diffuse histological type and good PS . No significant correlation was observed among Topo-I , Topo-IIalpha and E-cadh positivity with any of the clinicopathological parameters studied . Median overall survival ( OS ) was 31.7 , and disease-free survival ( DFS ) 26 months , respectively . None of the above-investigated molecular markers were significantly associated with OS and DFS . Finally , according to the univariate analysis for survival , only advanced stages ( III , IV ) of the disease implied risk of death , mainly due to lymph node involvement and , to a lesser extent , tumor size . None of the studied molecular markers were found to be independent prognostic markers . CONCLUSION These results should be interpreted very cautiously , due to the limited number of patients studied , as well as the limitations of the IHC technique\n\n\nReport 2:\nTitle: Serum Vascular Endothelial Growth Factor Predicts Venous Invasion in Hepatocellular Carcinoma : A Prospective Study\nSummary: Objective To evaluate the correlation between serum vascular endothelial growth factor ( VEGF ) level and the clinicopathologic features in patients with hepatocellular carcinoma ( HCC ) . Summary Background Data VEGF is an important angiogenic factor regulating tumor angiogenesis . A high serum VEGF level has been shown to be associated with tumor progression and metastasis in several human cancers , but its significance in HCC is unclear . The correlation between serum VEGF level and tumor pathologic features in patients with HCC has not been studied before . Methods Preoperative serum sample s and tumor specimens were prospect ively collected in 100 patients undergoing resection of HCC . Serum VEGF level was measured by enzyme-linked immunosorbent assay , and tumor VEGF expression was assessed by immunohistochemical study . Histopathologic examination was performed by a pathologist without prior knowledge of the serum VEGF level or tumor VEGF expression . Results Preoperative serum VEGF levels ranged from 15 to 1,789 pg/mL ( median 269 ) . When serum VEGF levels were compared between groups categorized by different clinicopathologic variables , significant correlation was found between a high serum VEGF level and absence of tumor capsule , presence of intrahepatic metastasis , presence of microscopic venous invasion , and advanced stage . There was a positive correlation between the serum VEGF level and tumor expression of VEGF as well as platelet count . When the 75th percentile serum VEGF level ( 500 pg/mL ) was used as a cutoff level , the frequency of venous invasion in patients with a high serum VEGF level was significantly greater compared with patients with a low serum VEGF level . By multivariate analysis , a serum VEGF level of more than 500 pg/mL and tumor size more than 5 cm were independent preoperative factors predictive of microscopic venous invasion . During a median follow-up of 11.6 months , 48 % of patients with a serum VEGF level of more than 500 pg/mL and 27 % of those with a serum VEGF level of 500 pg/mL or less developed postoperative recurrence . Conclusions These results show that a high preoperative serum VEGF level is a predictor of microscopic venous invasion in HCC , suggesting that the serum VEGF level may be useful as a biologic marker of tumor invasiveness and a prognostic factor in HCC\n\n\nReport 3:\nTitle: High pre-treatment serum level of vascular endothelial growth factor (VEGF) is associated with poor outcome in small-cell lung cancer.\nSummary: Vascular endothelial growth factor ( VEGF ) is an important regulator of angiogenesis and vascular permeability . Increased serum VEGF concentrations ( S-VEGF ) have been found in patients with various types of human cancer , including cancer of the lung . However , the clinical and prognostic significance of S-VEGF in cancer is unknown . We measured S-VEGF , using enzyme-linked immunosorbent assay , in sera taken from 68 untreated patients with small-cell lung cancer ( SCLC ) at the time of diagnosis . The patients were treated with 6 cycles of cisplatin and etoposide , and were r and omly assigned to receive recombinant interferon , leukocyte interferon or neither . S-VEGF ranged from 70 to 1738 pg/ml ( mean , 527 pg/ml ) . The patients who achieved partial or complete response to treatment had lower pre-treatment S-VEGF than the non-responding patients ( p = 0.0083 , Mann-Whitney test ) . High ( > 527 pg/ml ) S-VEGF was associated with poor survival ( p = 0.012 , Log Rank Test ) , and all 3-year survivors had lower than mean pre-treatment S-VEGF . In a multivariate analysis , S-VEGF and stage were the only independent prognostic factors , and the estimated 3-year survival of the patients with limited stage disease and low pretreatment S-VEGF ( n = 17 , 25 % of all patients ) was 41 % ( p = 0.0055 , log rank test ) . These data show that high pretreatment S-VEGF is associated with poor response to treatment and unfavourable survival in patients with SCLC treated with combination chemotherapy with or without interferon\n\n\nReport 4:\nTitle: REporting recommendations for tumor MARKer prognostic studies (REMARK)\nSummary: Despite years of research and hundreds of reports on tumor markers in oncology , the number of markers that have emerged as clinical ly useful is pitifully small . Often initially reported studies of a marker show great promise , but subsequent studies on the same or related markers yield inconsistent conclusions or st and in direct contradiction to the promising results . It is imperative that we attempt to underst and the reasons why multiple studies of the same marker lead to differing conclusions . A variety of method ological problems have been cited to explain these discrepancies . Unfortunately , many tumor marker studies have not been reported in a rigorous fashion , and published articles often lack sufficient information to allow adequate assessment of the quality of the study or the generalizability of study results . The development of guidelines for the reporting of tumor marker studies was a major recommendation of the National Cancer Institute – European Organisation for Research and Treatment of Cancer ( NCI – EORTC ) First International Meeting on Cancer Diagnostics in 2000 . As for the successful CONSORT initiative for r and omized trials and for the STARD statement for diagnostic studies , we suggest guidelines to provide relevant information about the study design , preplanned hypotheses , patient and specimen characteristics , assay methods , and statistical analysis methods . In addition , the guidelines provide helpful suggestions on how to present data and important elements to include in discussion s. The goal of these guidelines is to encourage transparent and complete reporting so that the relevant information will be available to others to help them to judge the usefulness of the data and underst and the context in which the conclusions apply",
"role": "user"
},
{
"content": "Positive expression of tissue VEGF , circulating VEGF , VEGF-C and VEGF-D were all associated with poor prognosis in resected gastric cancer .\nHowever , VEGF demonstrated no significant prognostic value for non-Asian population s. Circulating VEGF may be better than tissue VEGF in predicting prognosis",
"role": "assistant"
}
]
|
science.mslr2022_ms2_multidoc_summarization | science.mslr2022_ms2_multidoc_summarization.4861 | [
{
"content": "Analyze the following collection of medical RCT summaries. Your goal is to craft a concise synthesis of the findings. Focus on the core insights and present them succinctly. Only include the synthesis in your response. Below are the RCT summaries:\n\n\n\nReport 1:\nTitle: TERT promoter mutations: a novel independent prognostic factor in primary glioblastomas.\nSummary: BACKGROUND Activating somatic mutations in the promoter region of the telomerase reverse transcriptase gene ( TERT ) have been detected in several cancers . In this study we investigated the TERT promoter mutations and their impact on patient survival in World Health Organization grade IV glioblastoma multiforme ( GBM ) . METHODS The TERT core promoter region containing the previously described mutations and a common functional polymorphism ( rs2853669 ) was sequenced in tumors and blood sample s from 192 GBM patients . O(6)-methylguanine-DNA methyltransferase ( MGMT ) promoter methylation status was assessed by pyrosequencing in 177 ( 92.2 % ) cases . Relevant clinical data were obtained from a prospect ively maintained electronic data base . RESULTS We detected specific ( -124 C > T and -146 C > T ) TERT promoter mutations in 143/178 ( 80.3 % ) primary GBM and 4/14 ( 28.6 % ) secondary GBM ( P < .001 ) . The presence of TERT mutations was associated with poor overall survival , and the effect was confined to the patients who did not carry the variant G-allele for the rs2853669 polymorphism . An exploratory analysis suggested that TERT mutations might be prognostic only in patients who had incomplete resections and no temozolomide chemotherapy . CONCLUSIONS In this study , specific TERT promoter mutations were markers of primary GBM and predicted patient survival in conjunction with a common functional polymorphism . The prognostic impact of TERT mutations was absent in patients with complete resections and temozolomide chemotherapy . If confirmed in additional studies , these findings may have clinical implication s , that is , TERT mutations appear to characterize tumors that require aggressive treatment\n\n\nReport 2:\nTitle: Telomerase Reverse Transcriptase (TERT) Gene Variations and Susceptibility of Colorectal Cancer.\nSummary: AIM Colorectal cancer is the third most common cause of cancer-related mortality . Previous studies demonstrated increased telomerase activity in colorectal cancer tissue and suggested a prognostic value for patients with colorectal carcinoma . Telomerase reverse transcriptase ( TERT ) , one of the main functional subunits of the telomerase , is an important factor in modulating telomerase activity , telomere length , and genomic stability . However , there are few studies that have addressed the association between genetic variation at TERT and the risk of colorectal cancer . METHOD We evaluated the influence of three common single-nucleotide polymorphisms ( SNPs ) of the TERT gene ( rs2853669 , rs2736100 , rs2736098 ) on susceptibility to colorectal cancer in 104 patients and 135 controls in a Turkish population . RESULTS We observed that rs2736098 was significantly associated with increased risk of colorectal cancer ( OR = 2.53 ; 95 % CI = 1.26 - 5.10 ; p = 0.008 ) . On the other h and , rs2736100 and rs2853669 showed no association with colorectal cancer ( p ≥ 0.128 ) . CONCLUSION These findings are the first results of TERT allele distributions in the Turkish population and also provide increased underst and ing with respect to colorectal cancer etiology",
"role": "user"
},
{
"content": "Subsequent analyses also did not reveal any association between rs2853669 and overall cancer prognosis .\nIn conclusion , our findings suggest that rs2853669 could be important for assessing the prognostic value of TERTp mutations .",
"role": "assistant"
}
]
|
science.scitldr_aic | science.scitldr_aic.422 | [
{
"content": "Review the provided sections from a computer science paper and distill the primary contribution into a single sentence. Provide only the summary sentence.\n\nSections:\n\nTransforming a graphical user interface screenshot created by a designer into computer code is a typical task conducted by a developer in order to build customized software, websites, and mobile applications.\nIn this paper, we show that deep learning methods can be leveraged to train a model end-to-end to automatically generate code from a single input image with over 77% of accuracy for three different platforms (i.e. iOS, Android and web-based technologies).\nThe process of implementing client-side software based on a Graphical User Interface (GUI) mockup created by a designer is the responsibility of developers.\nImplementing GUI code is, however, time-consuming and prevent developers from dedicating the majority of their time implementing the actual functionality and logic of the software they are building.\nMoreover, the computer languages used to implement such GUIs are specific to each target runtime system; thus resulting in tedious and repetitive work when the software being built is expected to run on multiple platforms using native technologies.\nIn this paper, we describe a model trained end-to-end with stochastic gradient descent to simultaneously learns to model sequences and spatio-temporal visual features to generate variable-length strings of tokens from a single GUI image as input.Our first contribution is pix2code, a novel application of Convolutional and Recurrent Neural Networks to generate computer tokens from a single GUI screenshot as input.\nThat is, no engineered feature extraction pipeline nor expert heuristics was designed to process the input data; our model learns from the pixel values of the input image alone.\nOur experiments demonstrate the effectiveness of our method for generating computer code for various platforms (i.e. iOS and Android native mobile interfaces, and multi-platform web-based HTML/CSS interfaces) without the need for any change or specific tuning to the model.\nIn fact, pix2code can be used as such to support different target languages simply by being trained on a different dataset.\nA video demonstrating our system is available online 1 .Our\nsecond contribution is the release of our synthesized datasets consisting of both GUI screenshots and associated source code for three different platforms. Our\ndatasets and our pix2code implemention are publicly available 2 to foster future research.",
"role": "user"
},
{
"content": "CNN and LSTM to generate markup-like code describing graphical user interface images.",
"role": "assistant"
}
]
|
science.bioasq_factoid_qa | science.bioasq_factoid_qa.1315 | [
{
"content": "Given the following biomedical passages, answer the question succinctly. Ensure your response is precise and limited to the answer only.\n\nQuestion: What is carboxyglutamate?\n\nPassages: One of the important glutamic acid modifications is post-translationally modified 4-carboxyglutamate.\nVitamin K serves as an essential co-factor in the γ-carboxylation of glutamate to γ-carboxyglutamate (GLA), a post-translational modification mediated by gamma-glutamyl carboxylase (GGCX) and vitamin K oxidoreductases (VKORC1 or VKORC1L1).\nVitamin K (VK) is an essential cofactor for the post-translational conversion of peptide-bound glutamate to γ-carboxyglutamate.",
"role": "user"
},
{
"content": "carboxyglutamateis a a post-translational glutamic acidof",
"role": "assistant"
}
]
|
science.data_reco_mcq_mc | science.data_reco_mcq_mc.130 | [
{
"content": "Consider the following research inquiry and associated key terms. Review the dataset summaries provided and determine which datasets are suitable for addressing the research question. Base your decision on your understanding of machine learning datasets.\nProvide your answer as a JSON list. For example, for the inquiry \"Semi supervised image classification\", a possible response could be: [\"CIFAR-10\", \"CIFAR-100\"]. Ensure the response contains only the dataset names in JSON format.\n\nResearch Inquiry: I want to learn an action recognition model from video.\n\nKey Terms: action recognition video\n\nDataset Summaries:\nUCF101: UCF101 dataset is an extension of UCF50 and consists of 13,320 video clips, which are classified into 101 categories. These 101 categories can be classified into 5 types (Body motion, Human-human interactions, Human-object interactions, Playing musical instruments and Sports).\nKinetics-600: The Kinetics-600 is a large-scale action recognition dataset which consists of around 480K videos from 600 action categories. The 480K videos are divided into 390K, 30K, 60K for training, validation and test sets, respectively.\nDISFA: The Denver Intensity of Spontaneous Facial Action (DISFA) dataset consists of 27 videos of 4844 frames each, with 130,788 images in total. Action unit annotations are on different levels of intensity, which are ignored in the following experiments and action units are either set or unset.\nKinetics: The Kinetics dataset is a large-scale, high-quality dataset for human action recognition in videos. The dataset consists of around 500,000 video clips covering 600 human action classes with at least 600 video clips for each action class.\nMTL-AQA: A new multitask action quality assessment (AQA) dataset, the largest to date, comprising of more than 1600 diving samples; contains detailed annotations for fine-grained action recognition, commentary generation, and estimating the AQA score. Videos from multiple angles provided wherever available.\nHMDB51: The HMDB51 dataset is a large collection of realistic videos from various sources, including movies and web videos. The dataset is composed of 6,766 video clips from 51 action categories (such as “jump”, “kiss” and “laugh”), with each category containing at least 101 clips.\nEPIC-KITCHENS-100: This paper introduces the pipeline to scale the largest dataset in egocentric vision EPIC-KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M frames, 90K actions in 700 variable-length videos, capturing long-term unscripted activities in 45 environments, using head-mounted cameras.\n\nDataset Options: A: UCF101 B: Kinetics-600 C: DISFA D: Kinetics E: MTL-AQA F: HMDB51 G: EPIC-KITCHENS-100",
"role": "user"
},
{
"content": "[\"UCF101\", \"HMDB51\"]",
"role": "assistant"
}
]
|
science.multixscience_multidoc_summarization | science.multixscience_multidoc_summarization.2697 | [
{
"content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nOne major factor impeding more widespread adoption of deep neural networks (DNNs) is their issues with robustness, which is essential for safety critical applications such as autonomous driving. This has motivated much recent work on adversarial attacks for DNNs, which mostly focus on pixel-level perturbations void of semantic meaning. In contrast, we present a general framework for adversarial black-box attacks on trained agents, which covers semantic perturbations to the environment of the agent performing the task as well as pixel-level attacks. To do this, we re-frame the adversarial attack problem as learning a distribution of parameters that always fool the agent. In the semantic case, our proposed adversary (denoted as BBGAN) is trained to sample parameters that describe the environment with which the black-box agent interacts, such that the agent performs its dedicated task poorly in this environment. We apply BBGAN on three different tasks (primarily targeting aspects of autonomous navigation): object detection, self-driving, and autonomous UAV racing. On these tasks, BBGAN can generate failure cases that consistently fool an agent. We also demonstrate the usefulness of our framework as an analysis tool by visualizing systemic failure cases and uncovering semantic insights about the agents themselves.\n\nCited Works Summary:\n[1]: Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not limited to image classification, text mining, and speech processing. However, recent research on DNNs has indicated ever-increasing concern on the robustness to adversarial examples, especially for security-critical tasks such as traffic sign identification for autonomous driving. Studies have unveiled the vulnerability of a well-trained DNN by demonstrating the ability of generating barely noticeable (to both human and machines) adversarial images that lead to misclassification. Furthermore, researchers have shown that these adversarial images are highly transferable by simply training and attacking a substitute model built upon the target model, known as a black-box attack to DNNs. Similar to the setting of training substitute models, in this paper we propose an effective black-box attack that also only has access to the input (images) and the output (confidence scores) of a targeted DNN. However, different from leveraging attack transferability from substitute models, we propose zeroth order optimization (ZOO) based attacks to directly estimate the gradients of the targeted DNN for generating adversarial examples. We use zeroth order stochastic coordinate descent along with dimension reduction, hierarchical attack and importance sampling techniques to efficiently attack black-box models. By exploiting zeroth order optimization, improved attacks to the targeted DNN can be accomplished, sparing the need for training substitute models and avoiding the loss in attack transferability. Experimental results on MNIST, CIFAR10 and ImageNet show that the proposed ZOO attack is as effective as the state-of-the-art white-box attack (e.g., Carlini and Wagner's attack) and significantly outperforms existing black-box attacks via substitute models.\n\n[2]: Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic algorithm for computing universal perturbations, and show that state-of-the-art deep neural networks are highly vulnerable to such perturbations, albeit being quasi-imperceptible to the human eye. We further empirically analyze these universal perturbations and show, in particular, that they generalize very well across neural networks. The surprising existence of universal perturbations reveals important geometric correlations among the high-dimensional decision boundary of classifiers. It further outlines potential security breaches with the existence of single directions in the input space that adversaries can possibly exploit to break a classifier on most natural images.\n\n[3]:",
"role": "user"
},
{
"content": "Most of these attacks are white-box attacks, in which the algorithm has access to network gradients. Dezfooli al [2] introduce a universal attack that works well on networks that are not used in training the adversary. The work of Chen al [1] develops a black box attack by only assuming access to the output of the classifier. Since back-propagation cannot be performed, the gradient is approximates by finite differences instead. Bhagoji al [3] perform a black-box attack with a small number of network queries by using PCA and randomized dimension selection in the gradient estimation step. While we assume black box constraints in our work, we are interested in the distribution of the semantic parameters that fool the agent, more so than individual fooling examples. This limits the usefulness of approximating the gradient to reach a single local solution.",
"role": "assistant"
}
]
|
science.bioasq_factoid_qa | science.bioasq_factoid_qa.1140 | [
{
"content": "Given the following biomedical passages, answer the question succinctly. Ensure your response is precise and limited to the answer only.\n\nQuestion: What is Aortitis?\n\nPassages: Aortitis is the inflammation of the aorta due to various causes.\nAortitis can be the manifestation of an underlying infectious or noninfectious disease process.\nAortitis includes conditions with infectious or non-infectious etiology, characterized by inflammatory changes in one or more layers in aortic wall.\nAortitis and periaortitis are inflammatory diseases of the aorta and its main branches; they differ in the extension of inflammation, which is confined to the aortic wall in aortitis\nAortitis is classified as non-infectious or infectious.\n\"Aortitis\" is a pathologic term that refers to an abnormal inflammation of the aortic wall.\nIgG4 related thoracic aortitis is a recent addition to the differential diagnosis for inflammatory aortic disease - a condition which is often underappreciated until complications arise such as aneurysmal formation or aortic dissection. C\nBACKGROUND Inflammation of the aortic wall, known as aortitis, is a rare clinical entity which is frequently asymptomatic, or identified when the patient presents with an aortic aneurysm or dissection. It i\nSyphilitic aortitis is a productive inflammatory process, the earliest and most constant feature of which is a perivascular round cell infiltration in the adventitia.\nNon-infectious aortitis represents a common feature of large-vessel vasculitides but can also be isolated or associated with other rheumatologic conditions.\nAortitis is a subtype of the more general term \"vasculitis\", an inflammatory condition of infectious or noninfectious origin involving the vessel wall.\nAortitis and periaortitis are inflammatory diseases of the aorta and its main branches; they differ in the extension of inflammation, which is confined to the aortic wall in aortitis, and spreads to the periaortic space in periaortitis.\nTakayasu aortitis is a well known yet rare form of large vessel vasculitis.\nAortitis is a general term denoting inflammation of the aortic wall.\nPURPOSE OF REVIEW: Aortitis is the inflammation of the aorta due\nAortitis is the all-encompassing pathological term ascribed to inflammation of the aorta.\nAortitis is typically a chronic, progressive disease manifestation associated with large vessel vasculitidies, most notably giant cell, Takayasu arteritis, and a newly described entity, isolated aortitis.\nTEACHING POINTS : • Aortitis is an inflammatory condition of infectious/nonin\nAortitis is a pathological term that refers to the inflammation of one or more layers of the aortic wall.\nAortitis is a pathological term designating inflammation of the aortic wall, regardless of its cause.\nAortitis is defined as an inflammatory process that involves one or more layers of the aortic wall (internal elastic lamina, tunica media, and adventitia) and can be caused by multiple mechanisms.\nAortitis is a general term that refers to a broad category of infectious or noninfectious conditions in which there is abnormal inflammation of the aortic wall.",
"role": "user"
},
{
"content": "inflammation of the aorta",
"role": "assistant"
}
]
|
science.mslr2022_ms2_multidoc_summarization | science.mslr2022_ms2_multidoc_summarization.7428 | [
{
"content": "Analyze the following collection of medical RCT summaries. Your goal is to craft a concise synthesis of the findings. Focus on the core insights and present them succinctly. Only include the synthesis in your response. Below are the RCT summaries:\n\n\n\nReport 1:\nTitle: STOPP (Screening Tool of Older Persons' potentially inappropriate Prescriptions): application to acutely ill elderly patients and comparison with Beers' criteria.\nSummary: INTRODUCTION STOPP ( Screening Tool of Older Persons ' potentially inappropriate Prescriptions ) is a new , systems-defined medicine review tool . We compared the performance of STOPP to that of established Beers ' criteria in detecting potentially inappropriate medicines ( PIMs ) and related adverse drug events ( ADEs ) in older patients presenting for hospital admission . METHODS we prospect ively studied 715 consecutive acute admissions to a university teaching hospital . Diagnoses , reason for admission and concurrent medications were recorded . STOPP and Beers ' criteria were applied . PIMs with clear causal connection or contribution to the principal reason for admission were determined . RESULTS median patient age ( interquartile range ) was 77 ( 72 - 82 ) years . Median number of prescription medicines was 6 ( range 0 - 21 ) . STOPP identified 336 PIMs affecting 247 patients ( 35 % ) , of whom one-third ( n = 82 ) presented with an associated ADE . Beers ' criteria identified 226 PIMs affecting 177 patients ( 25 % ) , of whom 43 presented with an associated ADE . STOPP-related PIMs contributed to 11.5 % of all admissions . Beers ' criteria -related PIMs contributed to significantly fewer admissions ( 6 % ) . CONCLUSION STOPP criteria identified a significantly higher proportion of patients requiring hospitalisation as a result of PIM-related adverse events than Beers ' criteria . This finding has significant implication s for hospital geriatric practice\n\n\nReport 2:\nTitle: Potentially inappropriate medications defined by STOPP criteria and the risk of adverse drug events in older hospitalized patients.\nSummary: BACKGROUND Previous studies have not demonstrated a consistent association between potentially inappropriate medicines ( PIMs ) in older patients as defined by Beers criteria and avoidable adverse drug events ( ADEs ) . This study aim ed to assess whether PIMs defined by new STOPP ( Screening Tool of Older Persons ' potentially inappropriate Prescriptions ) criteria are significantly associated with ADEs in older people with acute illness . METHODS We prospect ively studied 600 consecutive patients 65 years or older who were admitted with acute illness to a university teaching hospital over a 4-month interval . Potentially inappropriate medicines were defined by both Beers and STOPP criteria . Adverse drug events were defined by World Health Organization-Uppsala Monitoring Centre criteria and verified by a local expert consensus panel , which also assessed whether ADEs were causal or contributory to current hospitalization . Hallas criteria defined ADE avoidability . We compared the proportions of patients taking Beers criteria PIMs and STOPP criteria PIMs with avoidable ADEs that were causal or contributory to admission . RESULTS A total of 329 ADEs were detected in 158 of 600 patients ( 26.3 % ) ; 219 of 329 ADEs ( 66.6 % ) were considered causal or contributory to admission . Of the 219 ADEs , 151 ( 68.9 % ) considered causal or contributory to admission were avoidable or potentially avoidable . After adjusting for age , sex , comorbidity , dementia , baseline activities of daily living function , and number of medications , the likelihood of a serious avoidable ADE increased significantly when STOPP PIMs were prescribed ( odds ratio , 1.847 ; 95 % confidence interval [ CI ] , 1.506 - 2.264 ; P < .001 ) ; prescription of Beers criteria PIMs did not significantly increase ADE risk ( odds ratio , 1.276 ; 95 % CI , 0.945 - 1.722 ; P = .11 ) . CONCLUSION STOPP criteria PIMs , unlike Beers criteria PIMs , are significantly associated with avoidable ADEs in older people that cause or contribute to urgent hospitalization\n\n\nReport 3:\nTitle: Prevalence of potentially inappropriate prescribing in an acutely ill population of older patients admitted to six European hospitals\nSummary: Purpose Potentially inappropriate prescribing is common in older people presenting to hospital with acute illness in Irel and . The aim of this study was to determine if this phenomenon is unique to Irel and or whether it is a more widespread problem in hospitals across Europe . Methods Prospect i ve data were collected from 900 consecutive older patients admitted to six university teaching hospitals ( 150 patients per centre ) in Geneva ( Switzerl and ) , Madrid ( Spain ) , Oostende ( Belgium ) , Perugia ( Italy ) , Prague ( Czech Republic ) and Cork ( Irel and ) . Age , gender , comorbidity , cognitive status , prescription medicines taken before admission and baseline haematological , biochemical and electrocardiographic data were recorded . STOPP and Beers ’ criteria were applied to detect potentially inappropriate medicines ( PIMs ) . START criteria were applied to detect potentially inappropriate prescribing omissions ( PPOs ) . Results The overall PIM prevalence rate was 51.3 % using STOPP criteria , varying from 34.7 % in Prague to 77.3 % in Geneva , and 30.4 % using Beer ’s criteria , varying from 22.7 % in Prague to 43.3 % in Geneva . Using START criteria , the overall PPO prevalence rate was 59.4 % , ranging from 51.3 % in Cork to 72.7 % in Perugia . Polypharmacy predicted the presence of PIMs using STOPP criteria [ with > 10 medications : odds ratio ( OR ) 7.22 , 95 % confidence interval ( CI ) 4.30–12.12 , p < 0.001 ] and Beers ’ criteria ( with > 10 medications : OR 4.87 , 95 % CI 3.00–7.90 , p < 0.001 ) . Increasing co-morbidity ( Charlson Index ≥2 ) and age ≥85 years significantly predicted PPOs . Conclusion Potentially inappropriate drug prescribing and the omission of beneficial drugs are highly prevalent in acutely ill hospitalized older people in six European centres\n\n\nReport 4:\nTitle: Associations between drug burden index and falls in older people in residential aged care.\nSummary: OBJECTIVES To evaluate the association between the Drug Burden Index ( DBI ) , a measure of a person 's total exposure to anticholinergic and sedative medications that includes principles of dose-response and maximal effect and is associated with impaired physical function in community-dwelling older people , and falls in residents of residential aged care facilities ( RACFs ) . DESIGN Data were drawn from participants in a r and omized controlled trial that investigated falls and fractures . SETTING RACFs in Sydney , Australia . PARTICIPANTS Study participants ( N=602 ; 70.9 % female ) were recruited from 51 RACFs . Mean age was 85.7 ± 6.4 , and mean DBI was 0.60 ± 0.66 . MEASUREMENTS Medication history was obtained on each participant . Drugs were classified as anticholinergic or sedative and a DBI was calculated . Falls were measured over a 12-month period . Comorbidity , cognitive impairment ( Mini-Mental State Examination ) and depression ( Geriatric Depression Scale ) were determined . RESULTS There were 998 falls in 330 individuals during a follow-up period of 574.2 person-years , equating to an average rate of 1.74 falls per person-year . The univariate negative binomial regression model for falls showed incidence rate ratios of 1.69 ( 95 % confidence interval (CI)=1.22 - 2.34 ) for low DBI ( < 1 ) and 2.11 ( 95 % CI=1.47 - 3.04 ) for high DBI ( ≥1 ) when compared with those who had a DBI of 0 . After adjusting for age , sex , history of falling , cognitive impairment , depression , use of a walking aid , comorbidities , polypharmacy , and incontinence , incident rate ratios of 1.61 ( 95 % CI=1.17 - 2.23 ) for low DBI and 1.90 ( 95 % CI=1.30 - 2.78 ) for high DBI were obtained . CONCLUSION DBI is significantly and independently associated with falls in older people living in RACFs . Interventional studies design ed for this population are needed to determine whether reducing DBI , through dose reduction or cessation of anticholinergic and sedative drugs , can prevent falls\n\n\nReport 5:\nTitle: Preventing drug-related morbidity--determining valid indicators.\nSummary: OBJECTIVE To describe the process that is being undertaken to vali date a series of indicators for preventable drug-related morbidity - originally developed in the US - for application in the UK health care system . DESIGN A two-round Delphi question naire survey after a preliminary validation of the indicators within the University of Manchester School of Pharmacy . SETTING A primary care study set in the UK . STUDY PARTICIPANTS A purposively selected sample of general practitioners with a specific responsibility for prescribing-related issues ( n = 6 ) and pharmacists actively involved in medication review in primary care ( n = 10 ) . MAIN OUTCOME MEASURES The establishment of consensus among the participants that an indicator reflected preventable drug-related morbidity in primary care . RESULTS After preliminary validation , 37 of the original 57 US indicators were retained . The Delphi panel generated 16 additional new indicators in the first round . At the end of the second round , the pre-defined level of consensus was reached for 29 indicators ( 19 of the US generated indicators ; 10 generated by the panel in the first round ) . CONCLUSIONS The Delphi results highlighted differences in both the clinical perspective and , possibly , philosophical viewpoints of health professionals practising in the UK and US health care systems . Further work , located in both primary and secondary care , is now in progress to operationalize the indicators . This process will form a key part of the refining , and hence further validation , of the indicators . The future development of prospect i ve medical-record-based indicators should facilitate a reduction in the human , clinical , and economic burden of drug-related morbidity",
"role": "user"
},
{
"content": "Whilst a wide variety of vali date d indicator sets exist , none addressed all aspects of medication-related quality of care pertinent to residential aged care .",
"role": "assistant"
}
]
|
science.scientific_papers_summarization_single_doc_arxiv | science.scientific_papers_summarization_single_doc_arxiv.61657 | [
{
"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:\npulsar radio emission is not well understood .\nmuch current work is grounded in standard models and assumptions about the geometry of the emitting region and about the nature and dynamics of the plasma therein .\nwhile these models work well for some stars , we now know they fail for others . it has become clear from recent work that specific predictions of this model are not always met in real stars , and that important assumptions within the model may be inconsistent with the data .\nthus , while the standard model of the pulsar magnetosphere has served us well , it now seems time to revisit it critically , with a careful eye to what the data tell us about the physics in the radio emission region .\nwe think that the most fruitful research is the study of just those stars in which the standard model fails seriously\n. these will be the stars that reveal the most about conditions in the emission region , and help us to formulate the next generation of models .\nin addition , the high quality of modern pulsar data acquisition systems justifies renewed observational effort : what observations can be carried out which will guide and critically test the models ? because pulsar emission shows strong frequency evolution , low frequency observations are an important part of the answer .\nhowever , although pulsars are strong at low frequencies , good data below @xmath0 mhz are hard to come by .\nthe lwa thus comes at an opportune time . in this paper\n, we discuss some areas in which the standard model fails , and then describe three types of low - frequency experiments which will be important in developing and testing the next generation of pulsar models .\na `` standard model '' of a pulsar s magnetosphere has been developed from early observations and theoretical work .\na rapidly rotating neutron star supports a strong , misaligned , dipolar magnetic field .\nthe plasma - filled magnetosphere corotates with the star , except in the open field line region where the star s magnetic fields connect to the universe beyond the light cylinder .\nplasma in this open field line region ( somehow ) emits coherent radio emission ; we observe `` pulses '' when the star s rotation sweeps this forward - beamed emission region past our line of sight . while this picture is very likely true in general , the devil can be in the details .\nfor example , two interesting results which relate particularly to low frequency observations have emerged from our recent work .\nwe now know the geometry of the emission region is more complex in many stars than had been thought .\nwe also strongly suspect that the plasma in the emission region is much less dense than had been assumed , and thus must be highly turbulent .\na fundamental assumption of the standard model is that a strong , dipolar magnetic field dominates the plasma dynamics in the radio emission region .\nthis picture makes specific , quantitative predictions .\none prediction involves the rotation of the linear polarization angle as the emission beam sweeps past the observer s sight line .\nanother involves the mean emission profile : we should only detect radio emission when the line of sight intersects open field lines .\nin addition , the standard model now includes frequency evolution of the mean profile , based on trends observed in many stars .\nfor instance , `` radius to frequency mapping '' says lower - frequency profiles should be broader ; this may connect to density stratification in the emission region . or , profiles should evolve from `` cone '' emission at high frequencies to `` core '' emission at low frequencies ; this may reflect different plasma states or emission mechanisms in different parts of the open field line region .\nthese predictions are not always borne out by the data .\nwe gathered time - aligned mean profiles and high - quality polarimetry , and used these data to study the geometry of the emission region in 52 bright pulsars ( hankins & rankin 2005 , eilek & hankins 2005 ) .\nwe did , indeed , verify that the standard picture works in about half of the stars but in the other half it does not .\nmany stars show complex frequency - dependent changes in their mean emission profile , which do not follow the trends predicted by the standard model .\nsome stars even show emission at rotation phases which can not arise from open field lines in a simple dipole geometry .\nin addition , many stars show striking deviations from the position angle behavior predicted for a pure dipole magnetic field in the emission region .\nthese deviations can be steady in some stars , fluctuating in others , and can change with observing frequency .\nother stars show evidence that the magnetic field switches between two different , quasi - stable states , which is impossible if the magnetic field is a static dipole .\nanother fundamental assumption in the standard model is that the charge density of the radio - loud plasma is exactly that needed to shield the rotation - induced electric field , and thus to allow the plasma magnetosphere to corotate smoothly with the star ( after goldreich & julian 1969 ) .\nit follows that the plasma in the radio emission region would be undergoing smooth , coasting flow .\nthis assumption is attractive in that it simplifies the modelling ; but it seems to be inconsistent with the fact that we observe pulsars at low radio frequencies .\nthe connection between plasma density and observing frequency comes from the coherent emission mechanism .\nnearly all coherent plasma emission processes operate at the local ( comoving ) plasma frequency , which depends on the local number density of the plasma ( _ e.g. _ , kunzl _ et al._1998 ) .\nour recent observations of the pulsar in the crab nebula support this hypothesis .\nthe radio emission in this pulsar is narrow - band @xmath1 ) and comes in bursts of very short duration ( unresolved at 2 nanoseconds ; hankins _ et al._2003 ) .\nthese observations are consistent with both the bandwidth and the timescales predicted by weatherall s numerical simulations ( 1997 , 1998 ) of radio emission from collapsing solitions in strong plasma turbulence , but they are inconsistent with the timescales predicted by competing models of the emission mechanism .\nit therefore seems likely that strong plasma turbulence creates coherent radio emission in the crab pulsar .\nif plasma emission is indeed the emission mechanism in pulsars , we can directly determine the density ( in the star s frame ) of the emitting plasma ( with some dependence on the streaming speed of the plasma ; we follow modern models which find @xmath2-@xmath3 , _ e.g._arendt & eilek 2002 ) .\nthis exercise tells us that the density of the plasma emitting at , say , 1 ghz or 100 mhz is far below that needed for smooth corotation .\nthis fact has two important consequences .\n\\(1 ) high and low frequency emission must originate in different parts ( high and low density ) of the radio - loud region . in some stars\nthese regions may be stratified in altitude ( consistent with radius - to - frequency mapping in their mean profiles ) , but in other stars the high and low density regions appear to coexist as would be the case in a highly turbulent plasma .\n\\(2 ) the rotation - induced electric field can not be fully shielded .\nthe plasma must be subject to strong local forces , and is probably in a highly unsteady , turbulent state .\nthe lower the density , the more unsteady the plasma should be . because dynamical timescales in this system are on the order of microseconds , we suspect this unsteady plasma flow is the cause of microstructure , which exists in many stars and is especially strong at low frequencies .\nbroad frequency coverage is crucial to testing theoretical models , because the characteristics of pulsar radio emission can change dramatically between 100 mhz and 10 ghz , and because different frequencies are emitted by different parts of the radio - loud plasma .\nin fact , if our hypothesis of radio emission from strong plasma turbulence is correct , the strongest discrepancies between data and models should arise at low frequencies .\nwe describe three types of pulsar observations which address these problems and which we hope could be carried out with the lwa .\ntime - integrated pulsar fluxes are the easiest experiment to do , because the stars are bright at low frequencies ( as in figure 1 ) .\nthe spectrum of some stars turns over well above 100 mhz , while that of others continues rising to the lowest observable frequencies .\nthe integrated spectra are among the hardest data to interpret , because of the lack of robust spectral predictions by different emission models . nonetheless , we suggest that probing the spectrum and frequency range of such emission can be important as a constrant on , or test of , future models .\nthis will require lwa - derived fluxes to be be combined with higher - frequency data from other telescopes to determine broad - band integrated spectra of a large number of stars .\nfor instance , models need to address questions such as what sets the spectral range of the coherent emission ?\nwhy does the spectrum turn over at low frequency ?\nis it a spatial scale ( which could limit maser growth , for instance ) ?\nis it a lack of plasma at the right density , or a lack of turbulent drivers in that plasma ( either of which could limit plasma turbulent emission ) ? the mean profile reveals the structure of the emission region .\nit tells us about the geometry and density structure in the region , as well as the local magnetic field ( which is revealed through its polarization signature ) .\nwhen a broad frequency range can be studied , the mean profiles in many stars turn out to show strong frequency evolution , as illustrated in figure 2 . as we noted above\n, the data often disagree with what the standard model predicts . in order to understand the pulsar emission geometry in the important , `` non - standard '' stars ,\nwe need high quality mean profiles with polarization information .\nwe also need the broadest possible frequency range , which can be reached by combining lwa data with higher - frequency data from other telescopes .\nonce again , such data will be important to lead and test future models .\nfor instance , does the emission geometry of the star change at frequencies below the spectral break ?\nwhy do some pulsars become strongly linearly polarized at low frequencies , and does the emission geometry change with the polarization ?\nhow often does the linear polarization direction change with frequency ( which should not happen at all in the standard model ) ?\nbecause the pulsar signal can be integrated synchronously to form the final profile , we anticipate that many stars will be bright enough to be studied with milliperiod resolution at good s / n .\nwe do note that some stars will be too strongly broadened by interstellar scintillation at these low frequencies ; but dispersion measure is a rough measure of turbulent broadening ( _ e.g. _ , lhmer _\net al._2004 ) , and quite a few stars have sufficiently low dispersion to be profitably studied even at tens of mhz .\nthis is the most challenging experiment but it will be worth the effort .\nsingle pulse studies at high time resolution tell us about the time dependence of the plasma as reflected in such phenomena as microstructure , rapid polarization fluctuations and drifting subpulses . as we have emphasized before , studies over a broad frequency range are needed to understand a star and test the models .\nlow frequencies are particularly interesting here , because microstructure and subpulses tend to be stronger at low frequencies , where we would expect the density imbalance and plasma dynamics to be the most noticable .\nobservations such as these have potentially high payoff , because they come closest to predictions that can be made by theoretical models of the emission region\n. they will be difficult at low frequencies , however , because sub - millisecond time resolution is necessary which makes sensitivity and scattering broadening important issues .\nwe believe a good number of bright puslars will be observable in this mode . by current estimates , the lwa will have thermal noise @xmath4mjy in one hour s integration , around the middle of its frequency range .\nthis scales to @xmath5jy for millisecond time resolution ; so single pulse work at high s / n can only be done on pulsars as bright as , say , 300 jy .\nwhile this is large compared to the time - integrated flux for most pulsars , our experience is that many pulsars show occasional very bright microbursts .\nfigure 3 shows two examples , each of which become brighter than 10 kjy for brief moments , and thus easily detectable in a triggered observation .\nthere is much still to be learned about the physics of pulsar radio emission .\nnew observations have made it clear that the simple model , which has been around nearly since pulsars were discovered , does not supply all the answers .\nwe hope that the data to come from new instruments can inspire a new understanding of the physics , not to mention closer contact between observers and theorists .\nlow - frequency information is particuarly important here .\nalthough the lwa has been envisioned primarily as an imaging instrument , it can also make important contributions to pulsar science , by providing critical low - frequency information which is not easily available anywhere else .\nwe thank don backer and frazer owen for technical discussions , and the members of the socorro pulsar group for ongoing discussions on pulsar physics .\nthis work was partly supported by nsf grant ast-0139641 .\narendt , p. n. jr .\n& eilek , j. a. , 2002 , , 581 , 451 eilek , j. a. & hankins , t. h. , 2005 , submitted to goldreich , p. & julian , w. h. , 1969 , , 157 , 869 hankins , t. h. , 1971 , ph.d .\nthesis , university of california at san diego hankins , t. h. , kern , j. s. , weatherall , j. c. & eilek , j. a. , 2003 , , 422 , 141 hankins , t. h. & rankin , j. m. , 2005 , submitted to kunzl , t. , lesch , h. , jessner , a. & von hoensbroech , a. , 1998 , , , 505 , l139 lhmer , o. , mitra , d. , gupta , y. , kramer , m. & ahuja , a. , 2004 , , 425 , 569 malofeev , v. m. , gil , j. a. , jessner , a. , malof , i. , sieber , w. & wielebinski , r. , , 368 , 230 weatherall , j. c. , 1997 , , 483 , 402 weatherall , j. c. , 1998 , , 506 , 341",
"role": "user"
},
{
"content": "recent work has made it clear that the `` standard model '' of pulsar radio emission can not be the full answer . \n some fundamental assumptions about the magnetic field and plasma flow in the radio - loud region have been called into question by recent observational and theoretical work , but the solutions to the problems posed are far from clear . \n it is time to formulate and carry out new observational campaigns designed to address these problems ; sensitive low - frequency observations will an important part of such a campaign . because pulsars are strong at low frequencies , we believe there will be a good number of candidates even for high - time - resolution single pulse work , as well as mean profile and integrated spectrum measurements . \n such data can push the envelope of current models , test competing theories of the radio loud region , and possibly provide direct measures of the state of the emitting plasma .",
"role": "assistant"
}
]
|
science.covid_deepset_qa | science.covid_deepset_qa.1032 | [
{
"content": "Analyze the following excerpt from a biomedical text. Identify the relevant information needed to respond to the inquiry. Provide only the necessary details in your answer.\n\nContext: Since MAPKs are activated by phosphorylation , de of MAPKs seems to be an efficient process to inactivate their activities. It can be achieved by specific protein kinase phosphatases which can remove the phosphate group from MAPKs. Examples of these phosphatases include tyrosine phosphatases, serine/threonine phosphatases, and dual-specificity phosphatases (DUSPs). Some DUSPs are also known as MAPK phosphatases (MKPs) [6] [7] [8] . Currently, there are at least 10 MKPs identified, while MKP-1 is the most studied member of the family. The regulatory role of MKP-1 on cytokine induction is best demonstrated by MKP-1 knockout (KO) macrophages in response to lipopolysaccharide (LPS), a cell wall component of Gram-negative bacteria. MKP-1 KO macrophages showed prolonged of p38 MAPK and JNK as well as increased production of TNF-α in response to LPS treatment [9] . Consistent with these results, another group further revealed that LPS-treated MKP-1 KO bone marrow-derived macrophages show increased AP-1 DNA-binding activity [10] . Also, they showed that LPS-induced MKP-1 expression is dependent on myeloid differentiation factor 88 (MyD88) and TIR domain-containing adaptor inducing IFN-β (TRIF) [10] , thus demonstrating the role of MKP-1 in signal transduction. Not only LPS, other TLR inducers including CpG, peptidoglycan, poly IC, and Pam 3 Cys can regulate cytokine expressions including TNF-α, IL-10 via MKP-1 activities [10, 11] . In these processes, MKP-1 serves to mitigate the undesirable effects of septic shock and maintain organ functions by restraining the inflammatory responses following bacterial infection. Another example of MKP-1 function is the immune response to Staphylococcus aureus (S. aureus), a Gram positive bacteria. There are higher levels of cytokine production including TNF-α, IL-6, and MIP-1α in MKP-1 KO mice infected with S. aureus [12] . Also, the mice would have a rapid development of multiorgan dysfunction as well as faster mortality rate upon challenge with heat-killed S. aureus [12] . Taken together, these results suggest that MKP-1 protects the host from overactivation of the immune system in response to Gram negative or Gram positive bacteria. In the past, it was believed that different MKP/DUSP family members have overlapping functions. However, the emergence of DUSP2 turned the concept up side down [13] . It was shown that DUSP2 behaves differently and is opposite to the function as stated above. In DUSP2 KO cells, they produced less inflammatory mediators, implying that DUSP2 may play a role in mediating instead of limiting inflammation. For instances, when DUSP2 KO macrophages were treated with LPS, there were less TNF, IL-6, nitric oxide, IL-12-producing cells when compared to those of the wild type counterparts [13] . When the DUSP2 KO bone marrow-derived mast cells were first sensitized with immunoglobulin E (IgE) receptor (FcεRI) and then stimulated with dinitrophenol-heat stable antigen, they produced lower TNF mRNA levels, diminished IL-6 production, less of ERK1/2, p38 MAPK, and less transcriptional activities by Elk1 and NFAT-AP-1 [13] . These unexpected positive regulations of immune cell functions by DUSP2 have been hypothesized to be due to crosstalks between MAPKs [13] . Stimulation of KO mast cells and macrophages showed increases in of JNK. Moreover, inhibition of JNK by small molecule inhibitors showed increases in of ERK [13] . The authors also showed that there were physical interactions of DUSP2 with ERK2, DUSP2 with JNK2, as well as DUSP2 and p38 MAPK after stimulation of the cells with dinitrophenol-heat stable antigen. Nevertheless, the details of the crosstalks between MAPKs and phosphatases need further investigation. Thus, the MKP family plays a critical role in the regulation of immune responses. Innate immune response protects the host from MTB infection by secretion of cytokines including TNF-α in immune cells. Meanwhile, MAPK is one of the critical proteins in the regulation of immunity and cytokine expression. Since MAPK is regulated by MKP-1 in response to LPS and the activation of MAPK is important in BCGinduced cytokine expression, we hypothesize that MKP-1 plays a critical role in the immune regulation of BCG in human monocytes. We examined the involvement of MKP-1 in BCG-induced MAPK activation and its consequent cytokine expression. Here, we present evidences that MKP-1 plays an unexpected role in the regulation of cytokine induction by BCG through its control of MAPK . It has been reported that many inducers including growth factors, LPS, peptidoglycan, and dexamethasone can stimulate the expression of MKP-1 in human macrophages, microglia, mast cells or fibroblasts [6] . To investigate the role of different TLR inducers in MKP-1 induction process in human blood monocytes, the level of MKP-1 mRNA was measured by quantitative polymerase chain reaction (QPCR) method. PBMo were isolated from primary human blood mononuclear cells and stimulated with Pam 3 Cys (TLR2 agonist), poly IC (TLR3 agonist), or LPS (TLR4 agonist) for 1 and 3 hours. Following exposure to Pam 3 Cys or LPS, there were significant inductions of MKP-1 mRNA levels within 1 hour of treatment ( Figure 1A ). These effects on MKP-1 induction continued for 3 hours post-treatment with Pam 3 Cys ( Figure 1A ). In contrast, poly IC did not induce MKP-1 ( Figure 1A ). The results indicate that different inducers showed differential up-regulation of MKP-1 expression. LPS has been extensively used to demonstrate the role of MKP-1 in immune response both in vivo and in vitro [9, 12] . To establish a foundation for interpretation of subsequent experimental results, LPS was used as a positive control for the induction of MKP-1 expression. To determine the levels of MKP-1 in response to LPS, kinetics of MKP-1 transcription were determined by QPCR. There was a significant induction of MKP-1 mRNA, which peaked as early as 1 hour upon LPS stimulation, and the levels gradually decreased over a course of 6 hours. These results showed that LPS induced MKP-1 expression (Figure 1B) . Next, to demonstrate the induction of specific phosphatases by BCG, kinetics of MKP-1 expression in PBMo was studied by using QPCR during BCG treatment. Similar to the results produced by LPS, upon the addition of BCG (MOI = 1 CFU/cell), there was a significant induction of MKP-1 mRNA within 1 hour of BCG treatment as determined by Taqman probe specific for MKP-1 ( Figure 2A ). The effects lasted for at least 6 hours ( Figure 2A ). To examine whether the changes of protein production were in parallel to that of the mRNA levels, the protein levels of MKP-1 were measured by Western blotting. In response to BCG, PBMo produced the MKP-1 protein as early as 30 minutes after treatment. The protein levels were maintained for 2 hours and dropped to basal levels at 3 hours ( Figure 2B ). The results demonstrated that there was MKP-1 induction in response to BCG activation in human monocytes. It has been shown that inhibition of p38 MAPK either by specific inhibitor or siRNA reduced the expression of MKP-1 in LPS-or peptidoglycan-treated macrophages [14] . To determine the mechanisms involved in the BCGinduced MKP-1 expression, PBMo were pretreated with several inhibitors including PD98059 (inhibitor for MAP kinase kinase [MEK] or ERK1/2), SB203580 (inhibitor for p38 MAPK), SP600125 (inhibitor for JNK), and CAPE (inhibitor for NF-κB) for 1 hour. A range of concentrations of each inhibitor was used to test their optimal concentrations and effects on cell viability and kinase inhibitions. BCG was added afterwards and total RNA was harvested. The results demonstrated that, with the inhibition of ERK1/2 and p38 MAPK activities by their corresponding relatively specific inhibitors, MKP-1 expressions were significantly reduced ( Figure 3 ). In addition, using higher dose of SB203580, we showed that the inhibition is increased further (data not shown). On the contrary, pretreatment of the cells with CAPE and SP600125 did not affect the induction of MKP-1 by BCG ( Figure 3 ). These results suggest that BCG-induced MKP-1 expression is dependent on both p38 MAPK and ERK1/2. Throughout the above experiments, the primary goal was to examine the induction of MKP-1 by BCG in human monocytes. Thus, to further examine the role of MKP-1 in BCG-induced signaling, transfection of siRNA into PBMo was used to knockdown the activity of MKP-1. To demonstrate that the MKP-1 siRNA can indeed knockdown the target gene, PBMo were first transfected with control or MKP-1 siRNA and then treated with BCG for 3 hours. Levels of MKP-1 mRNA were measured by RT-PCR method. In Figure 4A , BCG stimulated MKP-1 expression (lanes 1 and 2). In MKP-1 siRNA transfected monocytes, induction of MKP-1 by BCG was significantly decreased (lanes 2 and 4). The results showed that the siRNA does abrogate the levels of MKP-1 mRNA. To further determine whether MKP-1 siRNA affects BCGinduced MKP-1 at protein levels, PBMo were treated as above and MKP-1 proteins were measured by Western blotting. The results showed that BCG could induce MKP-1 proteins as usual for cells transfected with control siRNA ( Figure 4B , lanes 1-3). However, the levels of BCGinduced MKP-1 protein expression were reduced in cells transfected with MKP-1 siRNA ( Figure 4B , lanes 4-6). Together, the results suggest that MKP-1 siRNA not only reduced the MKP-1 mRNA in BCG treatment but also abrogated the BCG-induced MKP-1 protein. As stated in the literature [9] , MKP-1 KO mice showed increased TNF-α production in response to LPS. On the basis of the above MKP-1 siRNA results, LPS was then used as a control to demonstrate the effects of this MKP-1 siRNA system. cytokine expression induced by LPS in MKP-1 siRNA transfected cells suggest that the siRNA system is effective in knocking down the MKP-1 expression and MKP-1 acts as a negative regulator in LPS-induced TNF-α expression. To investigate the effect of MKP-1 siRNA on BCG-induced cytokine expression, the levels of TNF-α, IL-6 and IL-10 mRNA were measured by QPCR method. PBMo were transfected with either control or MKP-1 siRNA. Following exposure to BCG with control siRNA, there were significant inductions of TNF-α, IL-6 and IL-10 mRNA levels for 3 hours after treatment as previously reported ( [5] and data not shown). Next, the effects of MKP-1 siRNA were examined on the cytokine expression induced by BCG. Surprisingly, there was a significant abrogation of BCGinduced TNF-α expression by MKP-1 siRNA ( Figure 4D ). With the knockdown of MKP-1, the level of BCG-induced TNF-α was only 60% compared to that of the control cells, while BCG-induced IL-6 and IL-10 were unchanged in MKP-1 siRNA transfected cells. The results revealed that MKP-1 plays a role in the induction of TNF-α expression upon BCG stimulation, which may be different from that of its conventional functions in which MKP-1 acts as a negative regulator in LPS-induced signaling pathways [7] . The unexpected observations in cytokine expression lead to the investigation on the effects of MKP-1 siRNA on BCG-induced MAPK activation. MKP-1 was found to have a preferential substrate binding to p38 MAPK and JNK than ERK1/2 [7] . The status of MAPKs was assessed in control or MKP-1 siRNA transfected PBMo. Western blotting results demonstrated that BCGinduced both p38 MAPK and ERK1/2 in 15 minutes (data not shown) and peaked at 30 minutes, and then returned to basal levels in cells treated with the control siRNA ( Figure 5 ). Similar to the results of cytokine expression, of both p38 MAPK and ERK1/2 in response to BCG was decreased in monocytes transfected with MKP-1 siRNA instead of the expected increase in ( Figure 5 ). The results suggest that MKP-1 knockdown would result in reduced MAPK by BCG, implying that the reduced level of TNF-α production in BCG stimulated monocytes is due to reduced of MAPKs by MKP-1 siRNA. This report presented evidences that a novel function of MKP-1 is uncovered in cytokine regulation in response to mycobacterial infection. BCG induces MKP-1 as a rapid response (Figure 2) . The induction mechanism of MKP-1 by BCG is dependent on both ERK1/2 and p38 MAPK ( Figure 3 ). Using siRNA approach, the functions of MKP-1 can be examined in primary human monocytes. The results showed that the BCG-induced MAPKs activation as well as cytokine expression are downstream of MKP-1 ( Figures 4D and 5) . Thus, MKP-1 is a critical signaling molecule that is involved in BCG-induced cytokine expression. Previous reports have shown that MKP-1 induced by LPS or peptidoglycan is dependent on p38 MAPK [14] . Accordingly, BCG-induced MKP-1 can be inhibited by both p38 MAPK and ERK1/2 inhibitors. Interestingly, it has been shown that degradation of MKP-1 is reduced after ERK1/2 [15] .\n\nInquiry: How is MAPK activated?",
"role": "user"
},
{
"content": "phosphorylation",
"role": "assistant"
}
]
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.