dataset
stringclasses
45 values
id
stringlengths
17
64
messages
listlengths
2
2
science.pico_ner
science.pico_ner.1827
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nPlease return the output as a JSON object of the format: {\"Participant\": [\"patients with COPD\", ...], \"Intervention\": [\"Atenolol\", ...], \"Outcome\": [\"blood pressure\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nFixed-dose manidipine/delapril versus losartan/hydrochlorothiazide in hypertensive patients with type 2 diabetes and microalbuminuria . INTRODUCTION Patients with diabetes complicated by hypertension and microalbuminuria have elevated cardiovascular risk , and controlling blood pressure in these patients is an urgent clinical priority . The present study aimed to examine the effects of a fixed-dose combination of antihypertensives on blood pressure and microalbuminuria . METHODS Patients with type 2 diabetes , mild-to-moderate hypertension ( diastolic blood pressure 85-105 mmHg , systolic blood pressure < 160 mmHg , and 24-hour mean systolic blood pressure > 130 mmHg ) , and microalbuminuria were randomized to 1 year of doubleblind treatment with fixed-dose manidipine/delapril ( n=54 ) or losartan/hydrochlorothiazide ( HCTZ ) ( n=56 ) . RESULTS Blood pressure was significantly reduced at 1 year in both groups ( -22.2/-14.6 mmHg and -19.5/-14.3 mmHg , for systolic and diastolic blood pressure respectively , P < 0.001 for each ) , with no significant between-group difference . Reductions in microalbuminuria occurred in both groups , with mean changes at 1 year of -3.9 mg/mmol creatinine ( 95 % CI -5.3 , -2.5 ) for manidipine/delapril ( P < 0.001 vs. baseline ) and -2.7 mg/mmol creatinine ( 95 % CI -4.0 , -1.3 ) for losartan/HCTZ ( P < 0.001 vs. baseline and P=0.199 between groups ) . Glycemia over the 1-year study was largely unaffected ; the blood glucose concentration was reduced from baseline with manidipine/delapril , although not statistically significant ( mean change -0.2 mmol/L , P=0.064 ) . Both treatments were well tolerated , with discontinuation for adverse events for one ( 1.9 % ) patient in the manidipine/delapril group and two ( 3.6 % ) in the losartan/HCTZ group . CONCLUSIONS A fixed-dose manidipine/delapril combination represents a useful addition to the treatment options available to control hypertension complicated by diabetes and microalbuminuria .", "role": "user" }, { "content": "{\"Intervention\": [\"manidipine/delapril\", \"losartan/HCTZ\", \"losartan/hydrochlorothiazide\", \"fixed-dose manidipine/delapril\", \"losartan/hydrochlorothiazide ( HCTZ )\"], \"Outcome\": [\"blood glucose concentration\", \"Blood pressure\", \"Glycemia\", \"adverse events\", \"systolic and diastolic blood pressure\", \"microalbuminuria\", \"blood pressure\"], \"Participant\": [\"hypertensive\", \"type 2 diabetes\", \"diabetes\", \"microalbuminuria\", \"hypertension\"]}", "role": "assistant" } ]
science.scicite_classification
science.scicite_classification.56
[ { "content": "You will be presented with a citation sentence from a research paper. Classify the intent behind this citation by choosing from one of the following categories:\n\n- Method: Cites the paper for its methodology or procedure.\n- Background: Cites the paper to provide background information.\n- Result: Cites the paper for its findings or results.\n\nYour answer should be a single word from the following list of options: [\"Method\", \"Background\", \"Result\"]. Do not include any other text in your response.\n\nCitation sentence:\n\nFor example, elk may form smaller groups when exposed to wolf predation risk in relatively closed habitats (Creel & Winnie 2005), but form larger groups in open habitats where wolf densities are higher (Gower et al. 2009).", "role": "user" }, { "content": "Background", "role": "assistant" } ]
science.qasa_abstractive_qa
science.qasa_abstractive_qa.802
[ { "content": "You will be shown an excerpt from a computer science research paper, followed by a question about the paper. Please answer the question given the context. Do not include any text in your response other than the answer.\n\nContext: Before a face image is fed to an FR module, face anti-spoofing, which recognizes whether the face is live or spoofed, is applied to avoid different types of attacks. Then, recognition can be performed. As shown in Fig. 3(c), an FR module consists of face processing, deep feature extraction and face matching, and it can be described as follows: As mentioned in [32], there are three modules needed for FR system, as shown in Fig. 3. First, a face detector is used to localize faces in images or videos. Second, with the facial landmark detector, the faces are aligned to normalized canonical coordinates. Third, the FR module is implemented with these aligned face images. We only focus on the FR module throughout the remainder of this paper.\n\nQuestion: What are the three main modules of a face recognition system?", "role": "user" }, { "content": "The 3 main modules are: face detection, facial landmark detector, and FR module.", "role": "assistant" } ]
science.scireviewgen_multidoc_summarization
science.scireviewgen_multidoc_summarization.9346
[ { "content": "You are presented with multiple paper abstracts, a literature review title, and a specific chapter title. Your task is to write a focused literature review chapter that aligns with the given chapter title. The review should synthesize the content from the provided abstracts, draw connections between different works, highlight major findings, and identify any gaps in the existing research.\nLiterature Review Title: Semantics-aware detection of targeted attacks: a survey \nChapter Title: Host domain \n1. Abstract of Cited Paper (BIB001): With recent advances in network based technology and increased dependability of our every day life on this technology, assuring reliable operation of network based systems is very important. During recent years, number of attacks on networks has dramatically increased and consequently interest in network intrusion detection has increased among the researchers. This paper provides a review on current trends in intrusion detection together with a study on technologies implemented by some researchers in this research area. Honey pots are effective detection tools to sense attacks such as port or email scanning activities in the network. Some features and applications of honey pots are explained in this paper. \n2. Abstract of Cited Paper (BIB002): Abstract 31 Introduction 42 What is Malware? 4 2.1 Who are the Users and Creators of Malware? . . . . . . . . . . . . . . . 6 3 The Malware Detector 64 Malware Detection Techniques 7 4.1 Anomaly-based Detection . . . . . . . . . . . . . . . . . . . . . . . . . . 94.1.1 Dynamic Anomaly-based Detection . . . . . . . . . . . . . . . . 104.1.2 Static Anomaly-based Detection . . . . . . . . . . . . . . . . . . 154.1.3 Hybrid Anomaly-based Detection . . . . . . . . . . . . . . . . . . 164.2 Specification-based Detection . . . . . . . . . . . . . . . . . . . . . . . . 184.2.1 Dynamic Specification-based Detection . . . . . . . . . . . . . . 184.2.2 Static Specification-based Detection . . . . . . . . . . . . . . . . 264.2.3 Hybrid Specification-based Detection . . . . . . . . . . . . . . . 284.3 Signature-based detection . . . . . . . . . . . . . . . . . . . . . . . . . . 314.3.1 Dynamic Signature-based Detection . . . . . . . . . . . . . . . . 334.3.2 Static Signature-based Detection . . . . . . . . . . . . . . . . . . 344.3.3 Hybrid Signature-based Detection . . . . . . . . . . . . . . . . . 38 \n3. Abstract of Cited Paper (BIB003): Anti-virus vendors are confronted with a multitude of potentially malicious samples today. Receiving thousands of new samples every day is not uncommon. The signatures that detect confirmed malicious threats are mainly still created manually, so it is important to discriminate between samples that pose a new unknown threat and those that are mere variants of known malware. This survey article provides an overview of techniques based on dynamic analysis that are used to analyze potentially malicious samples. It also covers analysis programs that leverage these It also covers analysis programs that employ these techniques to assist human analysts in assessing, in a timely and appropriate manner, whether a given sample deserves closer manual inspection due to its unknown malicious behavior. \n4. Abstract of Cited Paper (BIB004): This paper details a schema developed for defining malicious behavior in software. The presented approach enables malware analysts to identify and categorize malicious software through its high-level goals as well as down to the individual functions executed on operating system level. We demonstrate the practical application of the schema by mapping dynamically extracted system call patterns to a comprehensive hierarchy of malicious behavior. \n5. Abstract of Cited Paper (BIB005): Due to the increasing threat from malicious software (malware), monitoring of vulnerable systems is becoming increasingly important. The need to log and analyze activity encompasses networks, individual computers, as well as mobile devices. While there are various automatic approaches and techniques available to detect, identify, or capture malware, the actual analysis of the ever-increasing number of suspicious samples is a time-consuming process for malware analysts. The use of visualization and highly interactive visual analytics systems can help to support this analysis process with respect to investigation, comparison, and summarization of malware samples. Currently, there is no survey available that reviews available visualization systems supporting this important and emerging field. We provide a systematic overview and categorization of malware visualization systems from the perspective of visual analytics. Additionally, we identify and evaluate data providers and commercial tools that produce meaningful input data for the reviewed malware visualization systems. This helps to reveal data types that are currently underrepresented, enabling new research opportunities in the visualization community.\n\nLiterature Review:", "role": "user" }, { "content": "Host-based solutions can be understood as detection systems running on the endpoint. We identified memory-based approaches, numerous behavioral detection and analysis systems, function call monitoring solutions, host-based intrusion Most cyber-attacks involve malware smuggled onto the system to perform its sinister deed. Malware can generally be defined as \"any software that does something that causes harm to a user, computer, or network\" . Examples include viruses, Trojan horses, backdoors, worms, rootkits, scareware, or spyware. Malicious software is known to exploit vulnerabilities of the system it is designed to run on. Flaws in applications can serve as drop vector and may be exploited as part of a privilege escalation routine required for administrative tasks. In the case of ATAs, this often includes hitherto unknown exploits known as zero-days. Common malware i.e. aims at financial gain through fraud or blackmail; it is delivered to a large number of recipients in hope that a sufficient number of people unknowingly install it on their machines. Malware used for targeted attacks is much more sophisticated and typically includes additional components for e.g. long-term persistent installation and more complex command and control communication than can be found in other malicious software. The main distinguishing factor is its tailoring to a specific environment, however. APT malware is designed to attack a particular device, operating system, or specific application version. This influences the choice of dropping technique, evasion routines, and attacks against specific defensive measures employed by the victim. While this fact makes such software dangerous to only a limited number of systems, the damage caused by targeted malware can be much more severe. Malware analysis is probably the most widely used and arguably most important class of host-based approaches. Solutions range from analysis suites built to determine a sample's general maliciousness to interpretation of behavior or clustering of potential malware into families. Egele et al. BIB004 and BIB003 offer an overview of dynamic malware analysis tools and describe various monitoring and detection techniques. In BIB006 , Wagner et al. expanded on some of the tools and assessed the information they provide. There is a multitude of information to be gleaned from various malware analysis techniques, each offering specific insight into the nature and functionality of a malicious program. This includes the virus definition, packer information like packer designations and general compression information about the sample, file and header information and code sections, library and function imports, CPU instructions and their associated assembly operations, system and API calls executed by the sample, file system operations indicating the creation, modification, and deletion of files, as well as interpreted registry, process, thread, and network operations. A large number of the data providers surveyed below focus on the detection or analysis of malware. We generally define malware data providers as tools that utilize static or dynamic analysis methods as well as signature-and behavior based detection techniques to gather information about a potentially malicious piece of software BIB006 : Static analysis describes techniques that do not require the sample under scrutiny to be actually executed. Depending on the depth of analysis, a file may be checked for its basic properties like file type, checksum, easily extractable information such as null-terminated strings or DLL import information, or be fully disassembled . The analysis environment -bare metal, virtual machine, or emulation -plays a negligible role for static analyses -the analyst simply chooses a platform compatible with the tools of her choice. Dynamic analysis goes a step further and executes the file on a dedicated host system. Various tools then monitor the execution and log relevant information into an execution trace. This ranges from simple file system operations to a full instruction list captured through a debugger. The analysis environment is essential for the dynamic approach since the type of data logged depends on both the platform as well as on the techniques used to capture system events. On the detection side we differentiate between signaturebased and behavior-based techniques: Signature-based approaches are best known for their prominent role in antivirus software and traditional intrusion detection systems. A so-called definition or signature is created to describe an entire file or parts of the code that are known to be malicious BIB006 . The detection software then compares the appearance of a file or packet to this set of known signatures. Signature-based detection has several shortcomings BIB005 : Firstly, obfuscation techniques commonly utilize polymorphic or metamorphic mutation to generate an evergrowing number of malware variants that are different in appearance, but functionally identical. This leads to bloated signature databases and, ultimately, to an overall slowdown of the detection process. Secondly, signature-based techniques only detect malware which has already been identified and analyzed; new species or hitherto unknown variants are often overlooked. Behavior-based techniques, on the other hand, focus on specific system activities or software behavior typically captured through dynamic analysis. Malicious actions are defined through patterns or behavioral anomalies. Since the behavior-based approach can be semantics-aware, it is largely immune to obfuscation BIB005 . Its performance is limited, however: While signature matching takes but the fraction of a second, dynamic execution and trace analysis can take several minutes. The second big area of host-based threat mitigation is intrusion detection. IT systems intrusion describes the act of accessing a local or network-based resource without proper authorization. It can basically be defined as computer breakin leaving the targeted system vulnerable to theft or sabotage . In many cases the line between black-hat hacking and malicious software becomes blurred BIB002 . Most typical intrusions involve malware or tools designed to circumvent security measures of the target system. The attack procedure varies from case to case and can be considered 'targeted'; few intruders act without knowing which system they are attacking. On the defense side, intrusion detection is primarily concerned with activities deemed illegal by the system operator . These may include digital breaking and entering but generally encompasses all 'malicious actions' aimed at e.g. privilege acquisition or resource abuse. Literature differentiates two classes of intrusion detection systems (IDS): network-based and host-based BIB001 . The main differences are the type and number of sources used to detect adversary activity; network-based IDS analyze the traffic transmitted between systems and typically utilize a number of sensors distributed throughout the network. Host-based systems, on the other hand, attempt to discover attacks taking place on the very machine the sensor component is installed on. There are two approaches to detecting malicious activity through an IDS: Anomaly detection and misuse (pattern) detection . Anomaly detection is based on the premise that illegal activity manifests as abnormality and that it can be identified through measuring the variance of certain key metrics. This may include the excessive use of system functions, high resource utilization at unusual times, or other behavior deviating from a defined baseline. Misuse detection, on the other hand, is based on predefined patterns. Knowledge of an attacker's methods or the expected consequences of an attack are encoded into behavior sequences that can be found by an IDS looking for their occurrence . Examples include sequences of suspicious function calls, certain network packet payloads, or the exploitation of known bugs. Many of the reviewed papers describe various host-based approaches to locate, identify, categorize, or analyze malicious software. Both semantics-aware as well as a few semantics-based techniques are used. Most focus on determining the maliciousness of a piece of software or attempt to classify a set of samples. There are also various data providers that fall under the wider definition of an intrusion detection system. Since IDSs can be both host-and network-based, tools range from local process or system call tracers to traffic anomaly detectors utilizing various statistical methods or data mining approaches. Network-based systems are reviewed in Sect. 5.2.", "role": "assistant" } ]
science.pico_ner
science.pico_ner.4487
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nPlease return the output as a JSON object of the format: {\"Participant\": [\"patients with COPD\", ...], \"Intervention\": [\"Atenolol\", ...], \"Outcome\": [\"blood pressure\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nEffect of hydrochlorothiazide therapy on cardiac arrhythmias in African-American men with systemic hypertension and moderate to severe left ventricular hypertrophy . The effect of hydrochlorothiazide therapy on ventricular arrhythmias was studied in 45 hypertensive African-American men with moderate to severe left ventricular ( LV ) hypertrophy . After medication washout , patients were treated with placebo followed by hydrochlorothiazide . Clinical , biochemical , and 48-hour ambulatory electrocardiographic data was collected after each treatment phase . Signal-averaged electrocardiograms were recorded in a subgroup of 24 patients . Average LV posterior wall thickness was 15 +/- 1.1 mm , septum 16 +/- 2 mm , LV mass 420 +/- 90 g , and LV mass index 212 = 51 g/m2 . Systolic blood pressure ( BP ) was 168 +/- 18 mm Hg after the placebo phase and 146 +/- 15 mm Hg after hydrochlorothiazide ; diastolic BP was 103 +/- 6 mm Hg and 89 +/- 9 mm Hg , respectively . Serum potassium decreased significantly from 4.2 +/- 0.4 mmol/L to 3.7 +/- 0.6 mmol/L after hydrochlorothiazide therapy . The average hourly incidence of ventricular premature contractions was 22 with placebo and 25 with hydrochlorothiazide . There were 3 and 1 couplets and 0.2 and 0.2 runs of ventricular tachycardia per patient per hour , respectively . Variables of signal-averaged electrocardiography did not differ between the 2 treatments . Thus , in hypertensive African-American men with moderate to severe LV hypertrophy , hydrochlorothiazide does not worsen ventricular arrhythmias or signal-averaged electrocardiographic variables .", "role": "user" }, { "content": "{\"Intervention\": [\"hydrochlorothiazide therapy\", \"hydrochlorothiazide\", \"placebo\"], \"Outcome\": [\"ventricular tachycardia\", \"Clinical , biochemical , and 48-hour ambulatory electrocardiographic data\", \"signal-averaged electrocardiographic variables\", \"Average LV posterior wall thickness\", \"Serum potassium\", \"signal-averaged electrocardiography\", \"Signal-averaged electrocardiograms\", \"Effect\", \"ventricular premature contractions\", \"cardiac arrhythmias\", \"ventricular arrhythmias\", \"Systolic blood pressure ( BP )\"], \"Participant\": [\"men\", \"45 hypertensive African-American\", \"subgroup of 24 patients\", \"with moderate to severe left ventricular ( LV ) hypertrophy\", \"hypertensive African-American men with moderate to severe LV hypertrophy\", \"cardiac arrhythmias in African-American men with systemic hypertension and moderate to severe left ventricular hypertrophy\"]}", "role": "assistant" } ]
science.healthver_entailment
science.healthver_entailment.1568
[ { "content": "You will be shown a claim about public health and the abstract of a biomedical research paper. Each sentence from the abstract will be on a separate line. Your task is to return a JSON object with two fields:\n\n- \"verdict\": The fact-checking verdict. If the information in the abstract supports the claim, write \"SUPPORT\". If the abstract contradicts the claim, write \"CONTRADICT\". If the abstract does not provide enough information to arrive at a verdict, write \"NEI\" (for \"not enough information\").\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract. If the verdict was \"NEI\", then return an empty array.\n\nFor instance, if the model were given the claim \"wearing masks can prevent the spread of COVID\", the output might be:\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that mass mask-wearing reduces the transmission rate for COVID-19.\"]\n}\n\nClaim: High-dose vitamin C can fight coronavirus.\n\nAbstract:\nBACKGROUND The coronavirus disease 2019 (COVID-19) is a pandemic caused by coronavirus with mild to severe respiratory symptoms.\nThis paper aimed to investigate the effect of nutrients on the immune system and their possible roles in the prevention, treatment, and management of COVID-19 in adults.\nMETHODS This Systematic review was designed based on the guideline of the Preferred Reporting for Systematic Reviews (PRISMA).\nThe articles that focussed on nutrition, immune system, viral infection, and coronaviruses were collected by searching databases for both published papers and accepted manuscripts from 1990 to 2020.\nIrrelevant papers and articles without English abstract were excluded from the review process.\nRESULTS Some nutrients are actively involved in the proper functioning and strengthening of the human immune system against viral infections including dietary protein, omega-3 fatty acids, vitamin A, vitamin D, vitamin E, vitamin B1, vitamin B6, vitamin B12, vitamin C, iron, zinc, and selenium.\nFew studies were done on the effect of dietary components on prevention of COVID-19, but supplementation with these nutrients may be effective in improving the health status of patients with viral infections.\nCONCLUSION Following a balanced diet and supplementation with proper nutrients may play a vital role in prevention, treatment, and management of COVID-19.\nHowever, further clinical trials are needed to confirm these findings and presenting the strong recommendations against this pandemic.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"RESULTS Some nutrients are actively involved in the proper functioning and strengthening of the human immune system against viral infections including dietary protein, omega-3 fatty acids, vitamin A, vitamin D, vitamin E, vitamin B1, vitamin B6, vitamin B12, vitamin C, iron, zinc, and selenium.\", \"Few studies were done on the effect of dietary components on prevention of COVID-19, but supplementation with these nutrients may be effective in improving the health status of patients with viral infections.\"]}", "role": "assistant" } ]
science.data_reco_mcq_mc
science.data_reco_mcq_mc.2080
[ { "content": "You are provided with a research question, keyphrases about the question, a description of candidate datasets and dataset options. Read the description of popular datasets provided below and select the ones that can be used to validate the following research question. Use your knowledge of machine learning datasets to make the best judgement.\nYour response should be formatted as a `json` array. For instance, for the query \"Semi supervised image classification\", a sample response might be: [\"CIFAR-10\", \"CIFAR-100\"]. Do not include any extra text in the response other than the answer array.\n\nQuery: This paper focuses on the following problems: 1) semi-supervised learning for vessel segmentation\n\nKeyphrases: vessel segmentation funduscopy\n\nDataset description:\nDCASE 2018 Task 4: DCASE2018 Task 4 is a dataset for large-scale weakly labeled semi-supervised sound event detection in domestic environments. The data are YouTube video excerpts focusing on domestic context which could be used for example in ambient assisted living applications.\nDRIVE: The Digital Retinal Images for Vessel Extraction (DRIVE) dataset is a dataset for retinal vessel segmentation. It consists of a total of JPEG 40 color fundus images; including 7 abnormal pathology cases.\nHRF: The HRF dataset is a dataset for retinal vessel segmentation which comprises 45 images and is organized as 15 subsets. Each subset contains one healthy fundus image, one image of patient with diabetic retinopathy and one glaucoma image.\nRITE: The RITE (Retinal Images vessel Tree Extraction) is a database that enables comparative studies on segmentation or classification of arteries and veins on retinal fundus images, which is established based on the public available DRIVE database (Digital Retinal Images for Vessel Extraction). RITE contains 40 sets of images, equally separated into a training subset and a test subset, the same as DRIVE.\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.\nVoxPopuli: VoxPopuli is a large-scale multilingual corpus providing 100K hours of unlabelled speech data in 23 languages. It is the largest open data to date for unsupervised representation learning as well as semi-supervised learning.\n\nOptions:- A: DCASE 2018 Task 4 B: DRIVE C: HRF D: RITE E: IntrA F: VoxPopuli", "role": "user" }, { "content": "[\"DRIVE\", \"HRF\"]", "role": "assistant" } ]
science.scientific_lay_summarisation_elife_single_doc_summ
science.scientific_lay_summarisation_elife_single_doc_summ.441
[ { "content": "You will be presented with the abstract, introduction, and discussion section from a biomedical research article. Your task is to create a summary that a layperson can understand, capturing the essence of the research article. Keep essential scientific terms, but ensure that the language remains clear and the concepts are explained in an uncomplicated manner.\n\nTitle: Testing the Münch hypothesis of long distance phloem transport in plants\nArticle:\nAbstract:\nLong distance transport in plants occurs in sieve tubes of the phloem. The pressure flow hypothesis introduced by Ernst Münch in 1930 describes a mechanism of osmotically generated pressure differentials that are supposed to drive the movement of sugars and other solutes in the phloem, but this hypothesis has long faced major challenges. The key issue is whether the conductance of sieve tubes, including sieve plate pores, is sufficient to allow pressure flow. We show that with increasing distance between source and sink, sieve tube conductivity and turgor increases dramatically in Ipomoea nil. Our results provide strong support for the Münch hypothesis, while providing new tools for the investigation of one of the least understood plant tissues.\nIntroduction:\nVascular systems allow organisms to distribute resources internally by bulk flow and thus to overcome size limitations set by diffusion. In plants, the evolution of vascular tissues enabled the development of trees and forests and was accompanied by a major increase in the productivity of terrestrial ecosystems. Plant vascular tissues are of two types: the xylem allows water to be pulled from the soil to maintain the hydration of leaves surrounded by air, while the phloem distributes the products of photosynthesis throughout the plant, allowing non-photosynthetic structures, such as roots, to be formed. The current hypothesis for phloem transport dates to 1930 when Ernst Münch proposed that transport through the phloem results from osmotically generated differences between the pressure in sources( e. g. leaves) and sinks( e. g. roots), and occurs without any additional input of energy along the transport path( Münch, 1930). The Münch hypothesis has gained wide acceptance based to a large extent on its simplicity and plausibility, rather than on experimental evidence. A fundamental issue bedeviling the pressure flow hypothesis is the long standing question of whether sieve tubes have sufficient hydraulic conductivity to allow sugars to be transported from leaves to roots in the largest and longest of plants. Increasing distances between sources and sinks would appear to require greater pressure to drive flow, but measurements suggest lower source turgor in trees compared to smaller, herbaceous plants( e. g., crops or weeds; Turgeon, 2010). A number of authors have emphasized the difficulty of accommodating the Münch hypothesis in trees, leading to the proposal of re-loading mechanisms via relays( Lang, 1979; Aikman, 1980). However, it is important to note that such challenges derive in large part from mathematical models of phloem transport in which the values of one or more of the key variables are unknown or poorly constrained( Tyree et al., 1974; Pickard and Abraham-Shrauner, 2009; Thompson and Holbrook, 2003; Hölttä et al., 2009). Phloem transport ceases immediately when sources and sinks become disconnected, which is always the case when preparing sieve tubes for in vitro studies. In situ studies on the other hand are challenging, especially in large plants. Thus, despite its importance, phloem transport and resource allocation is the least understood major process in plant function. Over the last years we have developed in situ methods to measure with high precision all of the parameters needed to quantify laminar flow through passive microtubes as described by the Hagen-Poiseuille equation( 1) U=kηΔpL,, where U is the flow velocity, Δp is the pressure differential, L is the tube length, η is the sap viscosity, and k is the conductivity of the tube. Previously, methods only existed for two of the five parameters: length, which is the distance between source and sink, and velocity, which can be determined using radioisotopes( Babst et al., 2005), magnetic resonance imaging( Mullendore et al., 2010), or dye tracking( Savage et al., 2013). We have recently introduced methods to measure the missing parameters including new EM preparation protocols and mathematical modeling to quantify sieve tube hydraulic resistance( Froelich et al., 2011; Mullendore et al., 2010; Jensen et al., 2012); a novel micro-capillary pressure probe to determine pressure in small and sensitive cells such as sieve tubes( Knoblauch et al., 2014); and protocols for in situ observation and flow velocity measurements in individual tubes( Froelich et al., 2011). A new method for determining phloem sap viscosity in vivo using fluorescence lifetime imaging of the fluorophore 2-NBDG is described. Here we present a study on phloem flow relevant parameters that tackles the major question on the pressure flow hypothesis. Our data provide strong support for the Münch hypothesis as a unifying mechanism of long distance transport in plants. The results also call into question current understanding of downstream events such as the “high pressure manifold model” of phloem unloading and carbohydrate delivery to sinks. The toolset described here will allow for detailed research on phloem transport and resource allocation, processes critical for food security and improvement of bioenergy crops, as well as understanding ecosystem ecology and the global carbon cycle.\nDiscussion:\nIn this study we address the major question about phloem transport in angiosperms: do phloem parameters scale in accord with the Münch hypothesis? We found that large morning glory vines exhibited a significant increase in the conductivity of sieve tubes in the external phloem and that this increase was primarily due to larger sieve plate pores. In addition to changes in sieve tube structure, the pressure in sieve tubes scaled with the distance between leaves and roots, such that morning glory plants with greater distance separating leaves and roots had significantly higher source turgor pressures. In summary, plants actively adjust flow relevant parameters to accommodate a passive pressure driven mass flow. After almost a century, we finally have experimental evidence that addresses the key challenge to the pressure flow hypothesis. Although many cellular aspects, such as the function of most p-proteins and sieve element plastids, remains unclear, the overall transport concept proposed by Münch is supported. Prior to our study, many of the parameters governing phloem transport were poorly quantified. Thus, an additional important outcome of the study is a toolkit' for determining all of the parameters affecting flow. This means, that our work opens the door to new studies of phloem function. Foremost among the questions to be answered are how plants control the distribution of resources needed to support assimilate storage and the growth of new tissues. Phloem unloading fills the reservoirs of the most important human food sources( primary sources such as fruits, roots, tubers, cereals, and through consumption also other sources such as meat) but our understanding of the unloading mechanism is similarly rudimentary. A currently popular modification of the Münch hypothesis that also accounts for phloem unloading is the high pressure manifold model( Patrick, 2013). This model proposes maintenance of high hydrostatic pressures throughout the sieve tube system with minimal pressure differences from source to sink, but high differences between sieve elements and surrounding cells in the unloading zone( Figure 6A). Our data, however, suggest that tube resistance will consume most of the energy provided by the source pressure to allow flow at the measured velocities( Figure 6B). Most importantly and contrary to the high pressure manifold model, small morning glory plants generate only low pressures sufficient for flow, but not additional large margins to maintain high pressure differentials in the unloading zone. This suggests that at least in the species investigated, either plasmodesmal conductance in the unloading zone is very high for passive unloading, or additional energy, e. g. in form of active unloading processes, is required. A better understanding of short and long distance flow patterns and assimilate distribution in plants will be necessary to resolve these important questions. 10. 7554/eLife. 15341. 021Figure 6. Phloem pressure gradients in relation to phloem unloading. Schematic drawing of a single source leaf( green) loading assimilates into the phloem( blue) and unloading through plasmodesmata( black) into a single root tip( yellow).( A) Independent of the plant size the pressure manifold model proposes nearly uniform high pressure along the stem, but large differences between sieve elements and surrounding cells in the unloading zone where the steepest gradients are found.( B) Our data suggest that tube resistance in the stem of morning glory plants consumes most of the pressure gradient, contrary to the high pressure manifold model. DOI: http://dx. doi. org/10. 7554/eLife. 15341. 021 Organisms are structures whose integrity depends on active and passive flows. While active flows are dominated by proteins in the form of cytoskeletal elements or membrane transporters, passive flow is dependent on cell geometry and cellular connections in orchestration with concentration gradients and osmotic potentials( which are again generated by active flows). The lack of precise geometrical data of cellular connections is therefore a major problem, as this information forms the basis for modeling long distance flow patterns of assimilates, signaling molecules, and other substances. Large-scale efforts to collect cell geometrical data( a field one may call quantitative anatomy or 'Anatomics') at a resolution sufficient to extract sieve tube connections, diameters, length as well as plasmodesmal frequencies etc. throughout the plant are needed. Integration of physiological and molecular data( e. g. cell surface specific distribution of membrane transporters etc.) into a 'virtual model plant could lead to a major step forward in rationally designing crop plants to meet future societal and environmental needs. To accomplish this methods for tissue preparation, automated acquisition, and reconstruction need to be combined, but the technology is available.", "role": "user" }, { "content": "Plants use energy from sunlight to make sugars in a process called photosynthesis . Most photosynthesis takes place in the leaves and so much of the sugar needs to be transported to other parts of the plant , such as fruits or roots . The sugars are transported by phloem tubes , which form a system that spans the entire plant . In 1930 , a German scientist called Ernst Münch proposed a hypothesis for how phloem tubes move sugars and other molecules around the plant . He proposed that the loading of these molecules into phloem tubes in the leaves or other “source\" tissues makes the fluid inside the vessels more concentrated so that water is drawn into the phloem from neighboring “xylem” vessels . This creates pressure that pushes the fluid along the phloem tube towards the fruit , roots and other “sink” tissues . In the sink tissues the sugars are consumed , which reduces their concentration in the phloem and the pressure . Overall , this results in the flow of sugars and other molecules from where they are produced to where they are most needed . However , this hypothesis is still largely untested because it has proved difficult to carry out experiments on phloem . Detaching the source tissues from the sink tissues stops the flow of fluid so only experiments in whole plants can provide meaningful data . Knoblauch et al . have now developed new methods to study phloem in an ornamental plant called morning glory . The experiments show that plants can alter the shape of phloem vessels and the pressure within the vessels to allow them to transport sugars and other molecules over different distances . These findings strongly support the Münch hypothesis and make other alternative hypotheses seem unlikely . Furthermore , the methods developed by Knoblauch et al . will allow others to further investigate phloem transport . New findings in this area may allow plant biologists to direct the flow of sugars and other molecules towards particular plant tissues to improve the nutritional quality of food crops in the future .", "role": "assistant" } ]
science.multixscience_multidoc_summarization
science.multixscience_multidoc_summarization.10176
[ { "content": "You are provided with the abstract of a scientific paper and the abstracts of the papers it references. Your task is to write a Related Work section for the main paper. This section should concisely summarize and integrate the key points from the cited abstracts, reflecting how they relate to the main paper's contributions and context. In your summary, use numerical citation markers like [1], [2], etc., to refer to the corresponding papers.\n\nMain Abstract:\nWe study the problem of allocating indivisible goods among n agents in a fair manner. For this problem, maximin share (MMS) is a well-studied solution concept which provides a fairness threshold. Specifically, maximin share is defined as the minimum utility that an agent can guarantee for herself when asked to partition the set of goods into n bundles such that the remaining (n-1) agents pick their bundles adversarially. An allocation is deemed to be fair if every agent gets a bundle whose valuation is at least her maximin share. Even though maximin shares provide a natural benchmark for fairness, it has its own drawbacks and, in particular, it is not sufficient to rule out unsatisfactory allocations. Motivated by these considerations, in this work we define a stronger notion of fairness, called groupwise maximin share guarantee (GMMS). In GMMS, we require that the maximin share guarantee is achieved not just with respect to the grand bundle, but also among all the subgroups of agents. Hence, this solution concept strengthens MMS and provides an ex-post fairness guarantee. We show that in specific settings, GMMS allocations always exist. We also establish the existence of approximate GMMS allocations under additive valuations, and develop a polynomial-time algorithm to find such allocations. Moreover, we establish a scale of fairness wherein we show that GMMS implies approximate envy freeness. Finally, we empirically demonstrate the existence of GMMS allocations in a large set of randomly generated instances. For the same set of instances, we additionally show that our algorithm achieves an approximation factor better than the established, worst-case bound.\n\nCited Abstract(s):\n[1]: This paper proposes a new mechanism for combinatorial assignment—for example, assigning schedules of courses to students—based on an approximation to competitive equilibrium from equal incomes (CEEI) in which incomes are unequal but arbitrarily close together. The main technical result is an existence theorem for approximate CEEI. The mechanism is approximately efficient, satisfies two new criteria of outcome fairness, and is strategyproof in large markets. Its performance is explored on real data, and it is compared to alternatives from theory and practice: all other known mechanisms are either unfair ex post or manipulable even in large markets, and most are both manipulable and unfair.\n\n[2]: \n\n[3]: The fairness notion of maximin share (MMS) guarantee underlies a deployed algorithm for allocating indivisible goods under additive valuations. Our goal is to understand when we can expect to be able to give each player his MMS guarantee. Previous work has shown that such an MMS allocation may not exist, but the counterexample requires a number of goods that is exponential in the number of players; we give a new construction that uses only a linear number of goods. On the positive side, we formalize the intuition that these counterexamples are very delicate by designing an algorithm that provably finds an MMS allocation with high probability when valuations are drawn at random.", "role": "user" }, { "content": "As mentioned earlier, [1] introduced the notion of maximin share guarantee ( @math ), and it has been extensively studied since then. In particular, [2] showed that if the agents' valuations are additive, then an envy free (or proportional) allocation will be @math as well. They also established that @math exists under binary, additive valuations. Their experiments, using different distributions over the valuations, did not yield a single example wherein an @math allocation did not exist. [3] showed that @math allocations exist with high probability when valuations are drawn randomly.", "role": "assistant" } ]
science.bioasq_general_qa
science.bioasq_general_qa.227
[ { "content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: What is the Timothy syndrome?\n\nContext: A point mutation in the gene encoding Ca(V)1.2 causes Timothy syndrome, a neurodevelopmental disorder associated with autism spectrum disorders (ASDs).\no circumvent this issue, we have developed a method using human-induced pluripotent stem cells to generate cardiomyocytes from individuals with Timothy syndrome (TS), a genetic disorder characterized by QT prolongation, ventricular tachycardia, and autism.\nTwo de novo point mutations of Ca(v)1.2 glycine residues, G406R and G402S, cause a rare multisystem disorder called Timothy syndrome (TS).\nHere, we discuss recent work on the mechanisms by which Ca(v)1.2 channels bearing TS mutations display slowed inactivation that leads to increased Ca(2+) influx, prolonging the cardiac AP and promoting lethal arrhythmias\nTimothy syndrome is a human genetic disorder due to mutations in the Ca(V)1.2 gene.\nTimothy syndrome (TS) is a disease caused by a gain-of-function mutation in the CaV1.2 channel (CaV1.2-TS) that decreases inactivation of the channel, which increases Ca(2+) influx, prolongs APs, and causes lethal arrhythmias.\nRecent reports suggest that parental mosaicism is involved in the heritability of type 1 Timothy syndrome (TS1), an extremely rare and life-threatening multisystem disorder characterized by severe QT interval prolongation, syndactyly, and several other complications.\nTimothy syndrome, long QT syndrome type 8, is highly malignant with ventricular tachyarrhythmia.\nTimothy syndrome (TS) is a rare long-QT syndrome caused by CACNA1C mutations G406R in exon 8A (TS1) and G402S/G406R in exon 8 (TS2).\nTimothy syndrome is caused by a missense mutation in the L-type calcium channel Ca(v)1.2 that is associated with developmental delay and autism.\nLong QT, syndactyly, joint contractures, stroke and novel CACNA1C mutation: expanding the spectrum of Timothy syndrome.\nTimothy syndrome (TS) is an autosomal dominant condition with the constellation of features including prolonged QT interval, hand and foot abnormalities, and mental retardation or autism.\nTimothy syndrome type 1 (TS-1) is a rare disorder that affects multiple organ systems and has a high incidence of sudden death due to profound QT prolongation and resultant ventricular arrhythmias.\nIn some rare cases, such as Timothy syndrome (TS), a specific mutation in a single gene can be sufficient to generate autism or ASD in most patients, potentially offering insights into the etiology of autism in general. Both variants of TS (the milder TS1 and the more severe TS2) arise from missense mutations in alternatively spliced exons that cause the same G406R replacement in the Ca(V)1.2 L-type calcium channel.\nA gain-of-function G406R mutation in a cytoplasmic loop of Ca(V)1.2 channels causes long QT syndrome 8 (LQT8), a disease also known as Timothy syndrome.\nA missense mutation in the L-type calcium channel Ca(V)1.2 leads to LQTS in patients with Timothy syndrome.\nTimothy syndrome is a multisystem disorder characterized by cardiac, hand/foot, facial, and neurodevelopmental features. The two forms are type 1 (classic) and type 2, a rare form caused by mutations in a transcript variant of the same gene. Cardiac findings include a rate-corrected QT interval of between 480 ms and 700 ms and congenital heart defects (patent ductus arteriosus, patent foramen ovale, ventricular septal defect, tetralogy of Fallot, hypertrophic cardiomyopathy). Hand/foot findings are unilateral or bilateral cutaneous syndactyly variably involving fingers two (index), three (middle), four (ring), and five (little) and bilateral cutaneous syndactyly of toes two and three. Facial findings include flat nasal bridge, low-set ears, thin upper lip, and round face. Neuropsychiatric involvement includes global developmental delays and autism spectrum disorders. Ventricular tachyarrhythmia is the leading cause of death, followed by infection and complications of intractable hypoglycemia. Average age of death is 2.5 years.\nThe gain-of-function mutations were found at two mutually exclusive exons in patients with Timothy syndrome (TS). These patients exhibit prolonged QT interval and lethal cardiac arrhythmias.\nTS patients also suffer from multi-organ dysfunction that includes neurological disorder such as autism and mental retardation reflecting the wide tissue distribution of CaV1.2 channel.\nUnexpectedly, TS patients may develop recurrent infections and bronchitis that suggests a role of CaV1.2 channel in the immune system.\nTimothy syndrome (TS) is a disease of excessive cellular Ca(2+) entry and life-threatening arrhythmias caused by a mutation in the primary cardiac L-type Ca(2+) channel (Ca(V)1.2). The TS mutation causes loss of normal voltage-dependent inactivation of Ca(V)1.2 current (I(Ca)). During cellular Ca(2+) overload, the calmodulin-dependent protein kinase II (CaMKII) causes arrhythmias.\nTimothy syndrome is a multisystem disorder associated with the mutation of a Gly residue (G402 or G406) in the Ca(v)1.2 Ca(2+) channel. G406 is localized at the end of the IS6 segment and just before the intracellular I-II loop, which is important for the regulation of channel inactivation and the binding of the Ca(v)beta subunit.\nInactivation of Ca2+ channel activity is perturbed in a rare yet devastating disorder known as Timothy syndrome (TS), whose features include autism or autism spectrum disorder along with severe cardiac arrhythmia and developmental abnormalities. Most cases of TS arise from a sporadic single nucleotide change that generates a mutation (G406R) in the pore-forming subunit of the L-type Ca2+ channel Ca(V)1.2.\nTimothy syndrome is a multisystem disorder associated with QT interval prolongation and ventricular cardiac arrhythmias. The syndrome has been linked to mutations in Ca(V)1.2 resulting in gain of function of the L-type calcium current (I(Ca,L)).", "role": "user" }, { "content": "Timothy syndrome is a multisystem disorder characterized by cardiac, hand/foot, facial, and neurodevelopmental features. The two forms are type 1 (classic) and type 2, a rare form caused by mutations in a transcript variant of the same gene. Cardiac findings include a rate-corrected QT interval of between 480 ms and 700 ms and congenital heart defects (patent ductus arteriosus, patent foramen ovale, ventricular septal defect, tetralogy of Fallot, hypertrophic cardiomyopathy). Hand/foot findings are unilateral or bilateral cutaneous syndactyly variably involving fingers two (index), three (middle), four (ring), and five (little) and bilateral cutaneous syndactyly of toes two and three. Facial findings include flat nasal bridge, low-set ears, thin upper lip, and round face. Neuropsychiatric involvement includes global developmental delays and autism spectrum disorders. Ventricular tachyarrhythmia is the leading cause of death, followed by infection and complications of intractable hypoglycemia. Average age of death is 2.5 years.", "role": "assistant" } ]
science.ncbi_ner
science.ncbi_ner.252
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Disease\"].\n\nPlease return the output as a JSON object of the format: {\"Disease\": [\"COVID-19\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nIdentification of mutations in the ALD-gene of 20 families with adrenoleukodystrophy/adrenomyeloneuropathy. Adrenoleukodystrophy (ALD), an X-linked inherited metabolic disorder, is the most frequent inborn peroxisomal disease. It leads to demyelination in the central and peripheral nervous system. Defective beta-oxidation of saturated very long chain fatty acids (VLCFAs; C22 0-C26 0) in peroxisomes has been shown to lead to an accumulation of VLCFAs in leukoid areas of the central nervous system, peripheral nerves, adrenal gland, and blood. The ALD gene has been recently identified and encodes a 745-amino-acid protein. We screened patients with adrenoleukodystrophy/adrenomyeloneuropathy (ALD/AMN) from 20 kindreds for mutations in the ALD gene. Eleven missense and two nonsense mutations, five deletions, and one insertion were detected by direct sequencing of eight reverse transcribed fragments of the ALD-gene mRNA. Four mutations could be shown to be de novo. All mutations could be confirmed in carriers by sequencing genomic DNA. No correlation between the type of mutation and the severity of the phenotype could be observed. The mutations were not detected in the ALD gene of 30 healthy persons..", "role": "user" }, { "content": "{\"Disease\": [\"Adrenoleukodystrophy\", \"AMN\", \"adrenomyeloneuropathy\", \"adrenoleukodystrophy\", \"inborn peroxisomal disease\", \"demyelination in the central and peripheral nervous system\", \"ALD\", \"X-linked inherited metabolic disorder\"]}", "role": "assistant" } ]
science.bioasq_general_qa
science.bioasq_general_qa.820
[ { "content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: What is Heterochromia Iridis?\n\nContext: The purpose of this study is to report a new and promising method for changing iris color in a sectorial heterochromia iridis patient. A 22-year-old man with a complaint of innate color disparity between his eyes presented to our clinic to seek medical advice.\nTo present a case of iatrogenic Horner's syndrome seen together with the heterochromia in the post-thyroidectomy period.METHODS: A 23-year-old female patient was admitted to our clinic with complaints of low vision in the eye and difference in eye color that developed over the past two years.\nHeterochromia iridis, asymmetry of iris pigmentation, has been well described with congenital Horner syndrome.\nBACKGROUND Heterochromia iridis, asymmetry of iris pigmentation, has been well described with congenital Horner syndrome.\nBACKGROUND Heterochromia iridis, asymmetry of iris pigmentation, has been well described with congenital Horner syndrome.", "role": "user" }, { "content": "Heterochromia iridis is a rare autosomal recessive disorder of the iris, characterized by a heterochromatic pattern of inheritance, variable expressivity, and partial or total absence of iris and/or blonde hair.", "role": "assistant" } ]
science.genia_ner
science.genia_ner.1085
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"RNA\", \"CellType\", \"CellLine\", \"Protein\", \"DNA\"].\n\nPlease return the output as a JSON object of the format: {\"DNA\" : [\"TAL1\", ...], \"RNA\": [\"mRNAs\", ...], \"CellLine\": [\"T cells\", ...], \"CellType\": [\"monocytes\", ...], \"Protein\": [\"IL-2\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nc-Myb and Ets proteins synergize to overcome transcriptional repression by ZEB. The Zfh family of zinc finger / homeodomain proteins was first identified in Drosophila where it is required for differentiation of tissues such as the central nervous system and muscle. ZEB, a vertebrate homolog of Zfh-1, binds a subset of E boxes and blocks myogenesis through transcriptional repression of muscle genes. We present evidence here that ZEB also has an important role in controlling hematopoietic gene transcription. Two families of transcription factors that are required for normal hematopoiesis are c-Myb and Ets. These factors act synergistically to activate transcription, and this synergy is required for transcription of at least several important hematopoietic genes. ZEB blocks the activity of c-Myb and Ets individually, but together the factors synergize to resist this repression. Such repression imposes a requirement for both c-Myb and Ets for transcriptional activity, providing one explanation for why synergy between these factors is important. The balance between repression by ZEB and transcriptional activation by c-Myb / Ets provides a flexible regulatory mechanism for controlling gene expression in hematopoietic cells. We demonstrate that one target of this positive / negative regulation in vivo is the alpha4 integrin, which play a key role in normal hematopoiesis and function of mature leukocytes.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"hematopoietic cells\", \"mature leukocytes\"], \"DNA\": [\"c - Myb\", \"hematopoietic genes\", \"E boxes\", \"hematopoietic gene\", \"muscle genes\"], \"Protein\": [\"alpha4 integrin\", \"ZEB\", \"transcription factors\", \"/ Ets\", \"c - Myb\", \"Zfh family\", \"zinc finger / homeodomain proteins\", \"Zfh - 1\", \"Ets\", \"Ets proteins\"], \"RNA\": []}", "role": "assistant" } ]
science.scientific_papers_summarization_single_doc_pubmed
science.scientific_papers_summarization_single_doc_pubmed.6459
[ { "content": "You will be presented with the full text of a biomedical research paper. Please write an abstract for this paper. Your response should only include the abstract and no additional text.\n\nPaper text:\nwe obtained data on persons with hiv / aids and tb from the national databank at the centers for disease control ( cdc taiwan ) of the department of health , taiwan .\ncoinfection with hiv and tb was defined as hiv infection in persons in whom tb was later diagnosed . a total of 660 persons with both hiv and tb were reported during 19932006 .\nwe used microsoft excel xp spreadsheet ( microsoft , redmond , wa , usa ) and sas version 9.1 ( sas institute inc . ,\nthe goodness - of - fit test with type i error = 0.05 was used to examine differences in demographic , clinical , and behavioral characteristics of persons with hiv and tb coinfection during 19932006 .\nmultivariates for analysis were sex and age , results of sputum smear and sputum culture , pulmonary radiographic diagnosis , tb types ( extrapulmonary and nonextrapulmonary ) , mode of hiv transmission , sexual behavior , compliance with haart , and use of the surveillance system ( table 1 ) .\nwe used the kaplan - meier method ( 4 ) from sas to evaluate and compare the effect on survival rates of different factors in persons coinfected with hiv and tb 1 year after reported tb diagnosis . *\n goodness - of - fit test with type i error = 0.05 used to examine differences in demographic , clinical , and behavioral characteristics . \nkaplan - meier analysis yielded the following results : 63% of persons coinfected with hiv and tb survived during 19931996 ; 78% survived during 19982000 ; and 93% survived during 20022006 ( p<0.0001 ) ( figure ) .\nwe then applied cox proportional hazards modeling ( 5 ) to each variable to assess the effect on survival rates after implementation of haart and the surveillance system .\nage < 45 years , negative sputum smear , availability of free haart , and implementation of the national surveillance system substantially increased survival rates of persons coinfected with hiv and tb ( table 2 ) .\nkaplan - meier analysis of survival of hiv - infected patients with tuberculosis in taiwan during 3 different periods : before free highly active antiretroviral therapy ( haart ) was available ( 19931996 , black line ) ; b ) after free haart was available but before the national web - based reporting and management surveillance system was implemented ( 19982000 , red line ) ; and c ) after free haart and the surveillance system were available ( 20022006 , blue line ) .\nmany factors can increase survival rates of hiv - infected persons , such as haart ( 69 ) , prevention of opportunistic infections , patient attitude , healthcare worker knowledge , and promotion of health education .\nour data indicate that national web - based surveillance reporting and management , coupled with the availability of free haart , increase survival rates of persons coinfected with hiv and tb ( p<0.0001 ) .\ntaiwan s national web - based surveillance system enables healthcare workers to follow , record , and understand the conditions of patients without geographic limitations .\nphysicians , public health nurses , health administrators , and other healthcare professionals in local through federal government agencies can use the system to follow up and manage the condition of persons coinfected with hiv and tb .\nfor example , public health nurses from national healthcare centers visit such patients regularly , record treatments , and assess their conditions and compliance with therapy ; staff from central health department monitor and supervise the condition of each patient through the system . in this way\n, the system may increase patients compliance and thus their survival rates ( 1014 ) .", "role": "user" }, { "content": "in 1997 , taiwan made highly active antiretroviral therapy ( haart ) available without cost to hiv - infected persons ; in 2001 , a national web - based surveillance system was implemented . \n healthcare workers use the system to monitor patients ' conditions and can intervene when necessary . \n free haart , coupled with the surveillance system , appears to have increased survival rates of hiv - infected persons with tuberculosis in taiwan .", "role": "assistant" } ]
science.multixscience_multidoc_summarization
science.multixscience_multidoc_summarization.6591
[ { "content": "You are provided with the abstract of a scientific paper and the abstracts of the papers it references. Your task is to write a Related Work section for the main paper. This section should concisely summarize and integrate the key points from the cited abstracts, reflecting how they relate to the main paper's contributions and context. In your summary, use numerical citation markers like [1], [2], etc., to refer to the corresponding papers.\n\nMain Abstract:\nIn Bayesian inference, the posterior distributions are difficult to obtain analytically for complex models such as neural networks. Variational inference usually uses a parametric distribution for approximation, from which we can easily draw samples. Recently discrete approximation by particles has attracted attention because of its high expression ability. An example is Stein variational gradient descent (SVGD), which iteratively optimizes particles. Although SVGD has been shown to be computationally efficient empirically, its theoretical properties have not been clarified yet and no finite sample bound of the convergence rate is known. Another example is the Stein points (SP) method, which minimizes kernelized Stein discrepancy directly. Although a finite sample bound is assured theoretically, SP is computationally inefficient empirically, especially in high-dimensional problems. In this paper, we propose a novel method named maximum mean discrepancy minimization by the Frank-Wolfe algorithm (MMD-FW), which minimizes MMD in a greedy way by the FW algorithm. Our method is computationally efficient empirically and we show that its finite sample convergence bound is in a linear order in finite dimensions.\n\nCited Abstract(s):\n[1]: We study parallel and distributed Frank-Wolfe algorithms; the former on shared memory machines with mini-batching, and the latter in a delayed update framework. In both cases, we perform computations asynchronously whenever possible. We assume block-separable constraints as in Block-Coordinate Frank-Wolfe (BCFW) method (Lacoste-, 2013), but our analysis subsumes BCFW and reveals problemdependent quantities that govern the speedups of our methods over BCFW. A notable feature of our algorithms is that they do not depend on worst-case bounded delays, but only (mildly) on expected delays, making them robust to stragglers and faulty worker threads. We present experiments on structural SVM and Group Fused Lasso, and observe significant speedups over competing state-of-the-art (and synchronous) methods.", "role": "user" }, { "content": "Lastly, we use FW to establish a greedy algorithm. This enables us to utilize many useful variants of the FW algorithm such as a distributed variant [1] . For details, see Appendix. However, compared with SP, we cannot evaluate the objective function directly, so we resort to other performance measures such as the log likelihood, accuracy, or RMSE in test datasets. For SP, we can directly evaluate KSD at each iteration.", "role": "assistant" } ]
science.acl_arc_intent_classification
science.acl_arc_intent_classification.1013
[ { "content": "You will be presented with a citation segment from the section of an NLP research paper, as well as the context surrounding that citation. Classify the intent behind this citation by choosing from one of the following categories:\n- Background: provides context or foundational information related to the topic.\n- Extends: builds upon the cited work.\n- Uses: applies the methods or findings of the cited work.\n- Motivation: cites the work as inspiration or rationale for the research.\n- CompareOrContrast: compares or contrasts the cited work with others.\n- FutureWork: cites the work as a direction for future research.\n\nYour answer should be a single word from the following list of options: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. Do not include any other text in your response.\n\nSection Title:\nNone\n\nContext before the citation:\nA number of speech understanding systems have been developed during the past fifteen years (Barnett et al. 1980, Dixon and Martin 1979, Erman et al. 1980, Haton and Pierrel 1976, Lea 1980, Lowerre and Reddy 1980, Medress 1980, Reddy 1976, Walker 1978, and Wolf and Woods 1980).\n\nCitation Sentence:\nA number of speech understanding systems have been developed during the past fifteen years ( Barnett et al. 1980 , Dixon and Martin 1979 , Erman et al. 1980 , Haton and Pierrel 1976 , Lea 1980 , Lowerre and Reddy 1980 , Medress 1980 , Reddy 1976 , Walker 1978 , and Wolf and Woods 1980 ) .\n\nContext after the citation:\nMost of these efforts concentrated on the interaction between low level information sources from a speech recognizer and a natural language processor to discover the meaning of an input sentence. While some of these systems did exhibit expectation capabilities at the sentence level, none acquired dialogues of the kind described here for the sake of dialogue level expectation and error correction. A detailed description of the kinds of expectation mechanisms appearing in these systems appears in Fink (1983). The problem of handling ill-formed input has been studied by Carbonell and Hayes (1983), Granger (1983), Jensen et al. (1983), Kwasny and Sondheimer (1981), Riesbeck and Schank (1976), Thompson (1980), Weischedel and Black (1980), and Weischedel and Sondheimer (1983).", "role": "user" }, { "content": "CompareOrContrast", "role": "assistant" } ]
science.mslr2022_cochrane_multidoc_summarization
science.mslr2022_cochrane_multidoc_summarization.1455
[ { "content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nEvaluation of prophylactic use of tetracycline after evacuation in abortion in Harare Central Hospital.\nAbstract 1:\nA randomised controlled trial involving 140 non-septic incomplete abortions was performed to determine the efficacy of prophylactic tetracycline as practiced in these cases in Harare Central Hospital. The treatment group (62) received tetracycline (500 mg four times daily) for a week. The remainder acted as controls. No significant difference in sepsis rate between treatment and control groups was noted. The high sepsis recorded in the treatment group was thought to be due to poor compliance. A new prophylaxis regimen has been suggested.", "role": "user" }, { "content": "There is not enough evidence to evaluate a policy of routine antibiotic prophylaxis to women with incomplete abortion.", "role": "assistant" } ]
science.scientific_papers_summarization_single_doc_arxiv
science.scientific_papers_summarization_single_doc_arxiv.78721
[ { "content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nearly ultraviolet ( uv ) emission from type ia supernovae ( sne ia ) is poorly known by now . only a very few brightest events have been observed a decade ago with the international ultraviolet explorer ( iue ) . although observational data were sometimes quite fascinating , as in the case of sn 1990n ( leibundgut et al .\n@xcite , jeffery et al .\n@xcite ) , an amount of observed uv light curves and spectra remained too small to reveal what is typical for the uv emission from sne ia and how individual features of the explosion can be displayed .\nthe hubble space telescope ( hst ) has slightly improved the situation .\nmore data of better quality were obtained .\nthis allowed theorists to make a comparison between the predictions of explosion models and the observational results .\nreproduction of supernova uv emission is a good test for an explosion model because this spectral region reflects more directly the distribution of synthesized during the explosion and the conditions in the exploding star .\nseveral models were already used to fit the observed spectra .\nanalyses of early and late emission from sne ia by kirshner et al .\n@xcite , ruiz - lapuente et al .\n@xcite , nugent et al .\n@xcite show that chandrasekhar - mass models dd4 ( woosley & weaver @xcite ) and w7 ( nomoto et al .\n@xcite ) and sub - chandrasekhar - mass helium detonation models ( see livne @xcite ; livne & glasner @xcite ; woosley & weaver @xcite ; hflich & khokhlov @xcite ) can reproduce some features of uv spectra of sne ia quite well . in this letter we calculate the light curves of the similar models and discuss how they differ from each other in several uv wavelength ranges .\nit is quite probable that more observational data will soon be available with the hst , and that the far - ultraviolet spectroscopic explorer ( fuse ) , operating at shorter wavelengths ( sembach @xcite ) , will be able to obtain light curves and spectra of sne ia in the range where they were not observed so far .\nthe analysis proposed here can help to distinguish which mode of explosion is actually realized in the sne ia .\nin our analysis we have studied two chandrasekhar - mass models : the classical deflagration model w7 ( nomoto et al .\n@xcite ) and the delayed detonation model dd4 ( woosley & weaver @xcite ) , as well as two sub - chandrasekhar - mass models : helium detonation model 4 of livne & arnett ( @xcite ) ( hereafter , la4 ) and low - mass detonation model with low production ( hereafter , wd065 ; ruiz - lapuente et al .\nmain parameters of these models are gathered in the table [ uvfluxes ] , as well as the values of rise time and maximum uv fluxes in the standard iue range ( just as it is the most typical form of representation ; e.g. , pun et al .\n@xcite ) and in the fuse range . for definiteness the distance to a supernova\nis supposed to be 10 mpc .\nthe method used here for light curve modeling is multi - energy group radiation hydrodynamics .\nour code stella ( blinnikov & bartunov @xcite ; blinnikov et al .\n@xcite ) solves simultaneously hydrodynamic equations and time - dependent equations for the angular moments of intensity averaged over fixed frequency bands , using up to @xmath0 zones for the lagrangean coordinate and up to 100 frequency bins ( i.e. , energy groups ) .\nthis allows us to have a reasonably accurate representation of non - equilibrium continuum radiation in a self - consistent calculation when no additional estimates of thermalization depth are needed . local thermodynamic equilibrium ( lte ) for ionization and atomic level populations is assumed in our modeling . in the equation of state ,\nlte ionization and recombination are taken into account .\nthe effect of line opacity is treated as an expansion opacity according to the prescription of eastman & pinto ( @xcite ) and blinnikov ( @xcite ) .\nthe main results of our calculations are presented in figs .\n[ iue ] , [ fuse ] .\nthe light curves of our models are shown in near and far uv ranges .\nthe fluxes are plotted as they would be seen for supernovae at distance of 10 mpc .\ndeclared sensitivity of fuse is @xmath1 ergs s@xmath2 @xmath3 @xmath2 , and sensitivity of hst ( at working range of wavelengths almost equal to that of iue ) is roughly @xmath4 ergs s@xmath2 @xmath3 @xmath2 .\nthis allows us to estimate that sne ia could be observed up to 300 mpc in the near uv and up to 30 mpc in the far uv ( with hst and fuse , respectively ) .\nyet it should be noticed that in the far uv sne ia are bright enough only during several days , and their flux declines very quickly after the maximum light , so the probability of discovering for them is quite low , unless they are very close to us ( a few mpc or even less ) .\n+ @xmath8 & 5.7 & 5.3 & 1.4 & 7.7 + @xmath9 & 3.28 & 11.0 & 1.97 & @xmath10 + + @xmath8 & 6.7 & 6.4 & 1.8 & 7.7 + @xmath9 & 41.7 & 51.8 & 9.21 & @xmath11 + + @xmath8 & 7.5 & 7.4 & 2.0 & 8.0 + @xmath9 & 53.2 & 50.4 & 6.90 & @xmath12 + + @xmath8 & 8.7 & 9.1 & 7.5 & 8.1 + @xmath9 & 46.0 & 45.8 & 17.7 & 0.447 + + @xmath8 & 13.5 & 13.4 & 8.5 & 8.2 + @xmath9 & 52.7 & 48.9 & 38.3 & 2.87 + + @xmath8 & 7.9 & 7.4 & 7.6 & 8.2 + @xmath13 & 11.0 & 11.4 & 3.72 & 0.161 + + + + @xmath14 in @xmath15 ergs s@xmath2 @xmath3 @xmath2 + + differences in the shapes and absolute brightness of sne ia light curves become more pronounced in this spectral range , especially in far uv , for different modes of explosion . as we have found in our paper ( sorokina et al .\n@xcite ) , the light curves of w7 and dd4 are very similar in _ b _ band close to the maximum light and differ drastically several days after it .\nwe can see likely behaviour in near - uv wavelengths ( fig .\n[ iue ] ) . in far uv\n, differences grow up , so that even at maximum light one can distinguish between two chandrasekhar - mass models .\nsuch a behaviour can most probably be explained by different distribution of inside debris of exploded star . in our case ,\nthe fraction of decreases more sharply in the model w7 , and this perhaps leads to the faster decline of its light curve .\nthe shape of the uv light curve of wd065 is conformal to those of chandrasekhar - mass models , though it shows much lower absolute flux ( due to an order - of - magnitude lower mass ) .\nthe light curve maxima of the chandrasekhar - mass models are shifted progressively towards later epochs for longer wavelengths remaining almost equal in brightness , while the wd065 maxima occur at nearly the same epoch for all of the iue and fuse ranges , and the emission virtually disappears at the shorter edge of the spectrum ( see table [ uvfluxes ] and fig .\n[ iue ] ) , since such a small amount of as present in this model is not able to maintain high temperature inside the ejecta .\nthe emission of wd065 in far uv becomes so weak that it could be detected only if supernova exploded in our neighbourhood ( not farther than a few hundreds of parsecs from us ) .\nthe model la4 ( helium detonation in outer layers ) is apparently distinguished by its rise time in the shortest spectral bands .\nthe most interesting feature of this light curve is its clear two - maxima structure in the short lwp range .\nthe earliest spike of the far - uv radiation is due to the outer layer specific for this model .\nit is well known that those helium detonation models are too blue near visual maximum ( hflich & khokhlov @xcite ; ruiz - lapuente et al .\nthis is also confirmed by our _ ubvri _ computations ( sorokina et al .\n@xcite ) . in far uv\n, la4 looks out not so hot , yet it can be detected in far uv earlier than in visual light .\none should be cautious applying our results directly to observations in uv range .\na large fraction of sne ia shows a significant correlation with star - forming regions ( bartunov et al .\n@xcite ; mcmillan & ciardullo @xcite ; bartunov & tsvetkov @xcite ) .\nthe circumstellar medium in those regions can absorb radiation , especially in uv band . in this case\nour predictions should be used as an input for calculations of reprocessing of uv photons to redder wavelengths .\ncertainly , more thorough investigation of the uv emission from sne ia has to be done .\nit is still necessary to calculate uv light curves of wider range of sne ia models and to predict their uv spectra .\nthis work is worth doing because , as it is seen from this letter , near - uv and far - uv observations with modern uv space telescopes , when combined with standard _\nubvri _ study , could be used as an efficient means to distinguish modes of explosion of thermonuclear supernovae leading us to better understanding of these phenomena .\nwe would like to thank w. hillebrandt , who has encouraged us to do this work .\nwe are grateful to e. livne , k. nomoto , p. ruiz - lapuente , and s. woosley for constructing the sne ia models used in our analysis , and we are thankful to p. lundqvist for his comments on the possibilities of modern space telescopes .\nthe work of sb is supported in russia by istc grant 37097 , in germany by mpa , and in japan by ile , osaka university .", "role": "user" }, { "content": "ultraviolet light curves are calculated for several thermonuclear supernova models using a multifrequency radiation hydrodynamic code . \n it is found that chandrasekhar - mass models produce very similar light curves both for detonation and deflagration . \n sub - chandrasekhar - mass models essentially differ from `` normal '' chandrasekhar ones regarding behaviour of their uv fluxes . \n differences in absolute brightness and in shape of light curves of thermonuclear supernovae could be detectable up to 300 mpc with modern uv space telescopes .", "role": "assistant" } ]
science.scientific_lay_summarisation_plos_single_doc_summ
science.scientific_lay_summarisation_plos_single_doc_summ.806
[ { "content": "You will be presented with the abstract, introduction, and discussion section from a biomedical research article. Your task is to create a summary that a layperson can understand, capturing the essence of the research article. Keep essential scientific terms, but ensure that the language remains clear and the concepts are explained in an uncomplicated manner.\n\nTitle: A Comprehensive tRNA Deletion Library Unravels the Genetic Architecture of the tRNA Pool\nArticle:\nAbstract:\nDeciphering the architecture of the tRNA pool is a prime challenge in translation research, as tRNAs govern the efficiency and accuracy of the process. Towards this challenge, we created a systematic tRNA deletion library in Saccharomyces cerevisiae, aimed at dissecting the specific contribution of each tRNA gene to the tRNA pool and to the cell's fitness. By harnessing this resource, we observed that the majority of tRNA deletions show no appreciable phenotype in rich medium, yet under more challenging conditions, additional phenotypes were observed. Robustness to tRNA gene deletion was often facilitated through extensive backup compensation within and between tRNA families. Interestingly, we found that within tRNA families, genes carrying identical anti-codons can contribute differently to the cellular fitness, suggesting the importance of the genomic surrounding to tRNA expression. Characterization of the transcriptome response to deletions of tRNA genes exposed two disparate patterns: in single-copy families, deletions elicited a stress response; in deletions of genes from multi-copy families, expression of the translation machinery increased. Our results uncover the complex architecture of the tRNA pool and pave the way towards complete understanding of their role in cell physiology.\nIntroduction:\nMessenger RNA translation is a central molecular process in any living cell and is among the most complicated and highly regulated of cellular processes[1],[2]. The tRNA pool is a fundamental component in that process, serving as the physical link between the nucleotide sequence of mRNAs and the amino acid sequence of proteins. In the cycle of translation elongation, tRNA selection is considered the rate-limiting step[3], therefore tRNA availability is one of the major factors that govern translation-efficiency and accuracy of genes[4],[5]. Previous studies have established that efficient translation can increase protein levels and provide a global fitness benefit by elevating the cellular concentrations of free ribosomes[6],[7], while accurate translation benefits the cell by reducing the metabolic cost of mis-incorporation events[8]. The tRNA pool is composed of various tRNA isoacceptor families, each family carries a different anti-codon sequence that decodes the relevant codon by Watson-Crick base pairing, or codons with non-perfect base pairing of the third nucleotide by the wobble interaction. tRNA families are further classified to isotypes if they carry the same amino acid. In all eukaryotic genomes, each tRNA family can be encoded by a single or multiple gene copies[9],[10]. It was previously shown for several organisms that the concentrations of various tRNA isoacceptors positively correlates with the tRNA family's gene copy-number[11],[12]. These observations along with detailed analysis of the relationship between gene copy-number of tRNA families and codon-usage, established the notion that the multiplicity of tRNA genes in yeast is not functionally redundant. Such multiplicity might establish the correct balance between tRNA concentrations and the codon usage in protein-coding genes[13], thus justifying the use of the tRNA gene copy-number as a proxy for actual tRNA amounts[12],[14],[15]. The transcription of tRNA genes is catalyzed by RNA polymerase III( pol III), promoted by highly conserved sequence elements located within the transcribed region[16]. A genome wide analysis of pol III occupancy in yeast revealed that virtually all tRNA genes are occupied by the pol III machinery[17]–[19], and are thus considered to be genuinely transcribed. This observation, combined with the fact that tRNA genes within a family are highly similar, led to the notion that all copies within a family contribute equally to the total expression level and hence to the tRNA pool. Although tRNAs have been extensively studied, until very recently many of the studies were performed on individual genes at the biochemical level. Only in recent years systematic genome-wide approaches started to complement the biochemical approach. These studies reveal a much more complex picture in which pol III occupancy, a proxy for tRNA transcription, varies within families and between tissues[17],[20]–[22]. Expression however does not equal function, and so far no systematic study has been carried out to decipher the specific contribution of each tRNA gene to the tRNA pool and to the cell's fitness. To study the role of individual tRNAs and the architecture of the entire tRNA pool, we created a comprehensive tRNA deletion library in the yeast Saccharomyces cerevisiae. The library includes 204 deletions of nuclear-encoded tRNA genes out of the total 275 present in the yeast genome. In addition, we created double deletions of selected tRNA gene combinations and of specific tRNAs with a tRNA modifying enzyme. We developed a robotic method to screen and score various fitness parameters for these deletion strains, and applied it across various growth conditions. This systematic deletion library revealed an architecture of genetic interactions that feature extensive backup-compensations within and between tRNA families. Such compensation capacity endows the organism with robustness to environmental changes and to genetic mutations. We found that different copies within a tRNA family contribute differently to the organism's fitness, revealing a higher level of complexity in the tRNA pool's architecture, possibly at the regulatory level. Finally, we observed two distinct molecular signatures that underlie the cellular response to changes in the tRNA pool. First, the deletion of non-essential single-copy tRNA genes invoked proteotoxic stress responses, indicating a connection between aberrant tRNA availability and protein misfolding. Second, the deletion of representative tRNAs from multi-copy families triggered milder responses by up-regulating genes that are involved in the translation process. Together our results uncover the complex architecture of the tRNA pool reviling a profound effect on cellular fitness and physiology.\nDiscussion:\nIn this study, we investigated the genetic architecture of the tRNA pool and its effect on cellular fitness using a comprehensive tRNA deletion library. We found extensive dispensability of many tRNA genes, especially under optimal growth conditions. Such lack of essentiality has been studied in protein-coding genes, and is often interpreted to reveal a role for partially redundant genes and pathways providing backup compensation for the deleted gene[33],[34],[54]–[56]. Similar design principles are displayed in the architecture of tRNA genes, which exhibited significant gene redundancy and compensation( either partial or complete) among family members. An additional reason for apparent lack of essentiality of genes is the limited set of examined environmental challenges, and it was indeed shown for protein-coding genes that challenging gene deletion libraries to less favorable conditions exposes more essentiality[57],[58]. We showed that a similar situation holds for tRNA genes. We found condition-specific functional roles for tRNAs, demonstrating increased demand for certain tRNA genes under certain defined conditions. This implies that the compensation within tRNA families changes across conditions. Such changes in the essentiality of tRNA genes can imply that the tRNA pool is dynamic and changes across conditions to accommodate cellular needs, as was recently suggested[59]. Further, we have discovered interesting architecture within families, which questions the prior notion that all tRNA gene copies contribute equally to the pool. Previous work has shown that Pol III transcription machinery displays different occupancy levels at various copies of the same tRNAs in the genome[21],[22],[60]. However, the potential phenotypic consequences of such transcriptional differences have not been previously explored. We report that the flanking sequences around each tRNA gene contains motifs that are predictive of the deletion phenotypic consequences, potentially affecting pol III transcription machinery. We further speculate that some tRNA genes, i. e. the Major copies, might be active across all conditions and with only partial functional redundancy, thus their loss cannot be fully compensated. Minor copies on the other hand are either not transcribed or have a modest contribution to the tRNA pool, with complete functional redundancy by other copies, thus their loss can be fully compensated. Such architecture could provide the cell with means to respond in a dynamic manner to changes in the environment, by transcribing varying portions of the members of each tRNA family depending on demand. As such, differential contribution within tRNA families exposed an additional novel mean to regulate the tRNA pool and as a consequence to regulate the translation process. An interesting finding was that changes in the tRNA pool elicit molecular changes in the cells even when no severe phenotype is detected. Our results demonstrated two distinct molecular signatures which can be attributed to the family architecture and the severity of the changes in the pool. Upon deletion of the two viable single copy tRNAs, and also upon deletion of one of the initiator tRNA methionine copies, the cell exhibited a response reminiscent of a proteotoxic stress. We were able to identify such a stress in these mutant cells. Although the exact mechanisms by which changes in the tRNA pool induces proteotoxic stress remains to be determined, we hypothesize that the elimination or reduction in these tRNAs may lead to events of amino acid misincorporation, ribosome frame-shifting or stalled protein synthesis terminations. Such events would have a clear impact on the protein quality control machinery of the cell by titrating chaperons to deal with misfolded or misassembled proteins. Translation errors such as incorrect tRNA selection and incorrect tRNA aminoacylation have been shown to induce proteotoxic stress in yeast[61],[62]. Given that cells exploit chaperon availability as a sensing mechanism to induce a stress response[63],[64], translation errors may lead to the onset such a response. On the other hand, deletions of tRNAs from multi-copy families results in milder effects on the tRNA pool due to the extensive redundancy or backup-compensation, and they indeed elicit a different cellular response from the one invoked upon deletion of single-member families. In the response to deletion of members from multi-gene families, the pol III transcription machinery seems to be up regulated. Such up-regulation would bring about induced transcription of tRNAs, this would act as a feedback mechanism to bring the tRNA pool closer to its normal state[65]. At least in one case( Supplemental figure S5) our results suggest the existence of such responsive backup among tRNA genes from the same family. Yet, a clearer relationship between changes in the tRNA pool, pol III activation, and tRNA transcription is still lacking. Regardless of the actual mechanism that determines the exact cellular response to tRNA deletions, the fact that such a response wiring exists may be beneficial for maintaining cellular robustness upon environmental changes and mutations. This work provides for the first time a systemic tool to study the functional role of individual tRNA genes. Using this deletion library, we discovered a much more complex picture than was previously known. We anticipate that a high throughput mapping of all genetic interactions between pairs of tRNA genes( as done for protein-coding genes)[66],[67] would reveal the full genetic network. In addition, it might reexamine and potentially refine the wobble interaction rules from a genetic, rather than the traditional biochemical/structural perspective. The design principles defined in this study, consisting of massive gene redundancy as well as differential contribution of gene copies may provide cellular plasticity and allow the tRNA pool to accommodate various growth conditions and developmental planes. Deciphering the effects of tRNA variations as is found in some diseases such as cancer[68] and Huntington[69] can provide possible routes for future treatment. We provide this novel set of minimalist genetic perturbations in the translation machinery as a resource to the yeast community towards further characterization of this highly complex process as well as additional cellular processes.", "role": "user" }, { "content": "Transfer RNAs are an important component of the translation machinery . Despite extensive biochemical investigations , a systems-level investigation of tRNAs' functional roles in physiology , and genetic interactions among them , is lacking . We created a comprehensive tRNA deletion library in yeast and assessed the essentiality of each tRNA in multiple conditions . The majority of tRNA deletions showed no appreciable fitness defect when such strains were grown on rich medium . More challenging environmental conditions , however , revealed a richer set of specific-tRNA phenotypic defects . Co-deletion of tRNA combinations revealed that tRNAs with essential function can be compensated by members of the same or different anti-codon families . We often saw that identical tRNA gene copies contribute deferentially to fitness , suggesting that the genomic context of each gene can affect functionality . Genome-wide expression changes in response to tRNA deletions revealed two different responses . When a deleted tRNA belongs to a family which contains multiple genes with the same anti-codon , the affected cells responded by up-regulating the translation machinery , but upon deletion of singleton tRNAs , the cellular response resembled that of proteotoxic stress . Our tRNA deletion library is a unique resource that paves the way towards fully characterizing the tRNA pool and their role in cell physiology .", "role": "assistant" } ]
science.bioasq_factoid_qa
science.bioasq_factoid_qa.987
[ { "content": "You will be shown biomedical passages and your task is to answer the provided question. Provide a concise and accurate response and do not include any additional text in the response other than the answer.\n\nQuestion: How is ZP-PTH delivered to patients?\n\nContext: To evaluate the clinical PK/PD of PTH(1-34) delivered by a novel transdermal drug-coated microneedle patch system (ZP-PTH) for the treatment of osteoporosis.", "role": "user" }, { "content": "transdermal drug-coated microneedle patch system", "role": "assistant" } ]
science.scicite_classification
science.scicite_classification.4653
[ { "content": "You will be presented with a citation sentence from a research paper. Classify the intent behind this citation by choosing from one of the following categories:\n\n- Method: Cites the paper for its methodology or procedure.\n- Background: Cites the paper to provide background information.\n- Result: Cites the paper for its findings or results.\n\nYour answer should be a single word from the following list of options: [\"Method\", \"Background\", \"Result\"]. Do not include any other text in your response.\n\nCitation sentence:\n\n…P450 1A5 was immunoinhibited (reflecting the contribution of 3A37 only), TLMs produced exo-AFBO and AFQ1, best fitted by sigmoidal kinetic Hill plot in agreement with the previous reports for AFB1 metabolism catalyzed by human P450 3A4 (Ueng et al., 1995) and turkey P450 3A37 (Rawal et al., 2010b).", "role": "user" }, { "content": "Result", "role": "assistant" } ]
science.scientific_papers_summarization_single_doc_pubmed
science.scientific_papers_summarization_single_doc_pubmed.93467
[ { "content": "You will be presented with the full text of a biomedical research paper. Please write an abstract for this paper. Your response should only include the abstract and no additional text.\n\nPaper text:\nthe eukaryotic pathogen database ( eupathdb ) has been developed as a bioinformatics resource center ( brc ) , with support from the us national institutes of health ( nih ) .\nadditional funding for a kinetoplastid component ( tritrypdb ) was recently provided by the bill and melinda gates foundation , in coordination with independent support for kinetoplastid annotation from the wellcome trust .\neupathdb has undergone a dramatic expansion over the past two years , evolving from an apicomplexan - specific database ( apidb ) ( 1 ) to encompass additional non - apicomplexan pathogens of human and veterinary importance , most of which are classified as category b biodefense pathogens by the national institute of allergies and infectious diseases ( niaid ) .\nthe eukaryotic pathogens included in eupathdb are a major source of morbidity and mortality worldwide , causing millions of deaths and an immense economic burden .\nthe current version of eupathdb ( version 2.1 ) serves as a portal for giardiadb ( 2 ) , cryptodb ( 3 ) , plasmodb ( 4 ) , toxodb ( 5 ) , trichdb ( 2 ) and tritrypdb ( companion paper in this issue ) .\nthese databases provide access to genomic and functional genomic data for 22 species ( table 1 ) .\nin addition , eupathdb provides access to genomic and/or expressed sequence tag data for additional related apicomplexan and trypanosomatid species ( table 1 ) .\nusers can access functional data directly via the component web sites or through eupathdb where query execution retrieves data from the component sites via web services .\none advantage of running searches in eupathdb is the ability to leverage functional data from the diverse organisms we support and combine the search results based on orthology ( 6 ) .\nthe diversity of functional genomics data available through eupathdb continues to expand dramatically ( table 1 ) making it essential to provide clients with an interface that is functional , user - friendly and sophisticated ( figure 1 ) . to this end , we have recently introduced a novel search system enabling users to build complex queries comprised of individual searches ( steps ) that are linked with each other using set operations ( union , intersection , and minus ) ( figure 1d ) . \n\ntable 1.species and data types included in the eupathdb family of databasesdata anticipated by march , 2010 is indicated in red .\neupathdb related species include genomic sequences for theileria parva and annulata and est sequences for eimeria spp . , babesia spp . , sarcocystis spp . , theileria spp . , neospora hughesi and gregarina niphandordes\n( a ) interactive banner present on all eupathdb web pages , including quick search windows and a tool bar ( grey ) .\n( b ) side bar components contain expandable sections for release notes , community resources , tutorials and help ( new items are highlighted with a yellow alert ) .\n( c ) hyperlinked logos of the eupathdb component sites direct users to component databases .\n( d ) gene searches , non - gene entity searches , such as ests , orfs of genome sequence and useful tools ( blast against genomes in eupathdb , pubmed records pertaining to eupathdb organisms etc . ) .\n( e ) a multi - step search strategy , leveraging orthology to identify apicoplast targeted genes in toxoplasma .\ng ) the results of a search strategy appear dynamically as the strategy is built and modified .\n( i ) individual gene pages in the component sites can be accessed by clicking on their gene ids .\nspecies and data types included in the eupathdb family of databases data anticipated by march , 2010 is indicated in red .\neupathdb related species include genomic sequences for theileria parva and annulata and est sequences for eimeria spp . , babesia spp . , sarcocystis spp . , theileria spp . , neospora hughesi and gregarina niphandordes .\n( a ) interactive banner present on all eupathdb web pages , including quick search windows and a tool bar ( grey ) .\n( b ) side bar components contain expandable sections for release notes , community resources , tutorials and help ( new items are highlighted with a yellow alert ) .\n( c ) hyperlinked logos of the eupathdb component sites direct users to component databases .\n( d ) gene searches , non - gene entity searches , such as ests , orfs of genome sequence and useful tools ( blast against genomes in eupathdb , pubmed records pertaining to eupathdb organisms etc . ) .\n( e ) a multi - step search strategy , leveraging orthology to identify apicoplast targeted genes in toxoplasma .\ng ) the results of a search strategy appear dynamically as the strategy is built and modified .\n( i ) individual gene pages in the component sites can be accessed by clicking on their gene ids .\nover the past two years eupathdb ( formerly apidb ) has evolved from an apicomplexan - specific resource ( cryptodb , plasmodb and toxodb ) to encompass protozoan pathogens outside this phylum , doubling its repertoire of functional genomic databases ( giardiadb and trichdb in early 2008 , and tritrypdb in early 2009 ) .\nconcurrent with this expansion , eupathdb has undergone dramatic changes specifically designed to enhance data accessibility and provide database users with a graphical query - building interface that effectively creates a venue for constructing complex search strategies with relative ease .\nthe eupathdb homepage provides the user with quick and easy access to information by providing specific , functional sections ( figure 1a d ) , a design feature that is replicated across eupathdb component sites .\nthe top part of the page ( banner ) remains constant throughout eupathdb web pages , providing quick access to text- and gene id - based searches , links to useful pages ( help and information pages , a contact us link , registration / login ) , and a tool bar ( gray ) with links to access diverse searches ( see below ) , the user s personal search history , tools , downloads , data sources , and other links ( figure 1a ) .\nthe left side of the home page ( figure 1b ) provides a series of expandable windows containing news items ( release notes , etc . ) , tutorials ( demonstrating the website ) , community resources , and additional information and help .\nthe number of new items added since the user s last visit is indicated by yellow numbers .\nthe middle of the page includes hyperlinked logos for all eupathdb component sites , providing direct access to taxon - specific databases ( figure 1c ) .\nbelow , three sections provide access to queries and tools ( figure 1d ) : ( i ) gene - centric searches allowing the identification of genes based on text terms , species , transcript and protein expression , go terms , ec numbers , user defined protein motif patterns , phylogenetic profile , etc . ;\n( ii ) other data type searches such as isolates and their geographic or clinical origin , expressed sequence tags ( ests ) , single nucleotide polymorphism ( snp ) data , etc . ; ( iii ) access to useful tools such as blast , the sequence retrieval tool , metabolic pathways and pubmed records . unlike queries available through the organism - specific component databases , where users are restricted to datasets available in that particular database\n, the eupathdb user has the opportunity to explore data from all organisms represented on any component site .\nthis expanded range provides the ability to transform a set of results from one organism into its orthologs in another , making it possible to generate comparable lists of results in organisms where particular functional data are lacking .\nexecution of queries in eupathdb starts by selecting a type of search from the options shown in figure 1d .\na strategy expands upon the first search ( step 1 ) by adding additional searches using set operators such as union , intersect and minus ( graphically displayed with venn diagrams , figure 1e ) .\nany step in the strategy can be transformed into orthologs from selected species of interest .\nfigure 1e presents an example in which orthology is leveraged between organisms to generate a list of potential apicoplast ( plastid - like organelle ) targeted genes in toxoplasma using information from other species . in step one , genes predicted to target to the parasite - specific apicoplast arganelle in p. falciparum are obtained based on available targeting information data ( 7 ) .\nthis list is transformed into orthologs in the related species t. gondii in step two , yielding 138 candidates . in step three , this list is restricted by subtracting genes found in cryptosporidium ( a related organism that has lost its apicoplast ) , leaving 86 possible toxoplasma apicoplast - targeted genes .\nmany of these genes have been experimentally proven to target to the apicoplast , validating this approach .\nanalogous search strategies can be used to generate a wide variety of potentially useful gene lists , such as : genes in toxoplasma and giardia that are orthologs of oocyst genes in cryptosporidium and plasmodium ( for which functional data are available ) ; or orthologous genes expressed in the plasmodium and trypanosoma arthropod stages ; or genes for which reagents are available ( such as antibodies ) in other organisms .\nsteps in a strategy can be renamed , revised , viewed , deleted , downloaded or expanded into sub - strategies .\nin addition , whole strategies can be renamed , saved , copied , closed / opened , deleted or shared with others via a uniquely generated url ( a recipient of the url can click on it to generate the strategy in their own workspace ) .\nresults are dynamically updated below the strategy in an interactive summary table ( figure 1f , green box ) that allows a user to click on the number of genes under the component database to filter the results revealing only genes from that database or all databases by clicking on the all results link .\nthe actual gene list appears dynamically below the summary table ( figure 1 g ) and can be sorted , expanded with additional columns of data ( figure 1h ) or downloaded .\ndetailed gene information can be viewed by visiting specific gene pages , which are accessed by clicking on the gene ids in the result list ( red box in figure 1i ) . in an effort to promote community involvement in annotation\nsuch comments can include pubmed ids ( references are automatically retrieved for final display in the comment ) , genbank accession numbers , files ( such as images ) , and comments that apply to multiple gene or isolate records can be easily replicated by adding the related ids to the comment form .\ncomments immediately appear on record pages and become indexed and searchable via the text search .\nthis feature has positively contributed to genome curation efforts in general and has specifically improved the official annotation of the p. falciparum and trypanosomatidae genomes ( see companion tritrypdb paper for further information ) .\nusers of eupathdb and its family of databases can also upload files to a community file repository that provides a venue for users to share data that are not linked to a specific record , such as , protocols .\nthe eupathdb family of databases is expected to expand further over the coming years , incorporating new species including the amoebozoa ( entamoeba , acanthamoeba ) , microsporidia , and additional apicomplexans , kinetoplastida and diplomonads .\nfeatures and tools will continue to be introduced and improved , such as the ability to make connections between diverse data types , a basket for users to place cherry - picked genes for subsequent manipulation and weighting of queries to enable more effective analysis of complex strategy results .\nof course , we also anticipate that data will continue to be deposited at an ever - increasing rate , including additional genome sequences , microarray data , probe - based hybridization and sequencing data ( e.g. chip - chip and rna - seq ) , proteomics data , isolate data , phenotype information , metabolomic data , etc .\neupathdb is funded with federal funds from the national institute of allergy and infectious diseases , national institutes of health , department of health and human services , under contract no .\n50096 from the bill and melinda gates foundation . funding for open access charge : national institutes of health .", "role": "user" }, { "content": "eupathdb ( http://eupathdb.org ; formerly apidb ) is an integrated database covering the eukaryotic pathogens of the genera cryptosporidium , giardia , leishmania , neospora , plasmodium , toxoplasma , trichomonas and trypanosoma . \n while each of these groups is supported by a taxon - specific database built upon the same infrastructure , the eupathdb portal offers an entry point to all these resources , and the opportunity to leverage orthology for searches across genera . \n the most recent release of eupathdb includes updates and changes affecting data content , infrastructure and the user interface , improving data access and enhancing the user experience . \n eupathdb currently supports more than 80 searches and the recently - implemented \n search strategy system enables users to construct complex multi - step searches via a graphical interface . \n search results are dynamically displayed as the strategy is constructed or modified , and can be downloaded , saved , revised , or shared with other database users .", "role": "assistant" } ]
science.multixscience_multidoc_summarization
science.multixscience_multidoc_summarization.25240
[ { "content": "You are provided with the abstract of a scientific paper and the abstracts of the papers it references. Your task is to write a Related Work section for the main paper. This section should concisely summarize and integrate the key points from the cited abstracts, reflecting how they relate to the main paper's contributions and context. In your summary, use numerical citation markers like [1], [2], etc., to refer to the corresponding papers.\n\nMain Abstract:\nRepresenting videos by densely extracted local space-time features has recently become a popular approach for analysing actions. In this study, the authors tackle the problem of categorising human actions by devising bag of words (BoWs) models based on covariance matrices of spatiotemporal features, with the features formed from histograms of optical flow. Since covariance matrices form a special type of Riemannian manifold, the space of symmetric positive definite (SPD) matrices, non-Euclidean geometry should be taken into account while discriminating between covariance matrices. To this end, the authors propose to embed SPD manifolds to Euclidean spaces via a diffeomorphism and extend the BoW approach to its Riemannian version. The proposed BoW approach takes into account the manifold geometry of SPD matrices during the generation of the codebook and histograms. Experiments on challenging human action datasets show that the proposed method obtains notable improvements in discrimination accuracy, in comparison with several state-of-the-art methods.\n\nCited Abstract(s):\n[1]: We propose a set of kinematic features that are derived from the optical flow for human action recognition in videos. The set of kinematic features includes divergence, vorticity, symmetric and antisymmetric flow fields, second and third principal invariants of flow gradient and rate of strain tensor, and third principal invariant of rate of rotation tensor. Each kinematic feature, when computed from the optical flow of a sequence of images, gives rise to a spatiotemporal pattern. It is then assumed that the representative dynamics of the optical flow are captured by these spatiotemporal patterns in the form of dominant kinematic trends or kinematic modes. These kinematic modes are computed by performing principal component analysis (PCA) on the spatiotemporal volumes of the kinematic features. For classification, we propose the use of multiple instance learning (MIL) in which each action video is represented by a bag of kinematic modes. Each video is then embedded into a kinematic-mode-based feature space and the coordinates of the video in that space are used for classification using the nearest neighbor algorithm. The qualitative and quantitative results are reported on the benchmark data sets.\n\n[2]: The aim of this paper is to introduce a new descriptor for the spatio-temporal volume (STV). Human motion is completely represented by STV (action volume) which is constructed over successive frames by stacking human silhouettes in consecutive frames. Action volume comprehensively contains spatial and temporal information about an action. The main contribution of this paper is to propose a new affine invariant action volume descriptor based on a function of spherical harmonic coefficients. This means, it is invariant under rotation, non-uniform scaling and translation. In the 3D shape analysis literature, there have been a few attempts to use coefficients of spherical harmonics to describe a 3D shape. However, those descriptors are not affine invariant and they are only rotation invariant. In addition, the proposed approach employs a parametric form of spherical harmonics that handles genus zero surfaces regardless of whether they are stellar or not. Another contribution of this paper is the way that action volume is constructed. We applied the proposed descriptor to the KTH, Weizmann, IXMAS and Robust datasets and compared the performance of our algorithm to competing methods available in the literature. The results of our experiments show that our method has a comparable performance to the most successful and recent existing algorithms.\n\n[3]: We propose a new action and gesture recognition method based on spatio-temporal covariance descriptors and a weighted Riemannian locality preserving projection approach that takes into account the curved space formed by the descriptors. The weighted projection is then exploited during boosting to create a final multiclass classification algorithm that employs the most useful spatio-temporal regions. We also show how the descriptors can be computed quickly through the use of integral video representations. Experiments on the UCF sport, CK+ facial expression and Cambridge hand gesture datasets indicate superior performance of the proposed method compared to several recent state-of-the-art techniques. The proposed method is robust and does not require additional processing of the videos, such as foreground detection, interest-point detection or tracking.", "role": "user" }, { "content": "Human action recognition has been addressed extensively in the computer vision community from various perspectives. Some methods rely on global descriptors; two examples are the methods proposed by Ali and Shah [1] and Razzaghi al [2] . [1] , a set of optical flow based kinematic features is extracted. Kinematic models are computed by applying principal component analysis on the volumes of kinematic features. Razzaghi al [2] represent human motion by spatio-temporal volume and propose a new affine invariant descriptor based on a function of spherical harmonics. A downside of global representations is their reliance on localisation of the region of interest, and hence they are sensitive to viewpoint change, noise, and occlusion [3] .", "role": "assistant" } ]
science.mslr2022_cochrane_multidoc_summarization
science.mslr2022_cochrane_multidoc_summarization.1447
[ { "content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nConservative versus surgical treatment for repair of the medial patellofemoral ligament in acute dislocations of the patella.\nAbstract 1:\nThe objective of this study was to analyze and compare the results obtained after 2 types of treatment, surgical and conservative, for acute patellar dislocations.\n We divided 33 patients with acute patellar dislocations into 2 groups. One group with 16 patients underwent conservative treatment (immobilization and subsequent physiotherapy), and the other group with 17 patients underwent surgical treatment. A radiographic examination was performed in the evaluation of the patients to verify predisposing factors for patellofemoral instability, and the Kujala questionnaire was applied with the intention of analyzing the improvement of pain and quality of life. The chi(2) test, t test, and Fisher test were used in the statistical evaluation. A significance level of P < .05 was adopted.\n The groups were considered parametric in relation to age and sex. The conservative treatment group exhibited a higher number of recurrent dislocations (8 patients) than the surgical treatment group, which did not have any relapses. In addition, the surgical treatment group obtained a better mean score on the Kujala test (92) than the conservative treatment group (69).\n We conclude that surgical treatment afforded better results. There were no recurrences in the surgical treatment group, but there were 8 recurrences in the conservative treatment group. The mean Kujala score was 92 in the surgical treatment group and 69 in the conservative treatment group.\n Level II, lesser-quality therapeutic randomized controlled trial.\n\n\nTitle 2:\nOperative versus closed treatment of primary dislocation of the patella. Similar 2-year results in 125 randomized patients.\nAbstract 2:\nTo assess whether initial surgery is beneficial for patients with primary dislocation of the patella, we carried out a prospective randomized study. Knee stability was examined under anesthesia, and associated injuries were excluded by diagnostic arthroscopy. 55 patients then had closed treatment and 70 patients were operated on with individually adjusted proximal realignment procedures. Surgery gave no benefit based on 2 years of follow-up. The subjective result was better in the non-operative group in respect of mean Houghston VAS knee score (closed 90, operative 87), but similar in terms of the patient's own overall opinion and mean Lysholm II knee score. Recurrent instability episodes (redislocation or recurrent subluxation) occurred in 20 nonoperated and in 18 operated patients. Of these, 15 and 12, respectively, then suffered redislocations. Function was better after closed treatment. Serious complications occurred after surgery in 4 patients. In conclusion, the recurrence of patellar dislocation may be more frequent than reported, whatever the form of treatment. Routine operative management cannot be recommended for primary dislocation of the patella.\n\n\nTitle 3:\nTreatment with and without initial stabilizing surgery for primary traumatic patellar dislocation. A prospective randomized study.\nAbstract 3:\nThere is no consensus about the management of acute primary traumatic patellar dislocation in young physically active adults. The objective of this study was to compare the clinical outcomes after treatment with and without initial stabilizing surgery for primary traumatic patellar dislocation in young adults.\n Forty young adults, thirty-seven men and three women with a median age of twenty years (range, nineteen to twenty-two years), who had an acute primary traumatic patellar dislocation were randomly allocated to be treated with initial surgical stabilization (eighteen patients, with each receiving one of two types of initial stabilizing procedures) or to be managed with an orthosis (twenty-two patients, including four who had osteochondral fragments removed arthroscopically). After a median of seven years, thirty-eight patients returned for a follow-up examination. Redislocations, subjective symptoms, and functional limitations were evaluated. Radiographs and magnetic resonance images were obtained at the time of randomization, and twenty-nine (76%) patients underwent magnetic resonance imaging at the time of final follow-up.\n A hemarthrosis as well as injuries of the medial retinaculum and the medial patellofemoral ligament were found on magnetic resonance imaging in all patients at the time of randomization. During the follow-up period, six of the twenty-one nonoperatively treated patients and none of the seventeen patients treated with surgical stabilization had a redislocation (p = 0.02). Four nonoperatively treated patients and two patients treated with surgical stabilization reported painful patellar subluxation. The median Kujala scores were 91 points for the surgically treated patients and 90 points for the nonoperatively treated patients. Thirteen patients in the surgically treated group and fifteen in the nonoperatively treated group regained their former physical activity level. At the time of follow-up, a full-thickness patellofemoral articular cartilage lesion was detected on magnetic resonance imaging in eleven patients; the lesions were considered to be unrelated to the form of treatment.\n In a study of young, mostly male adults with primary traumatic patellar dislocation, the rate of redislocation for those treated with surgical stabilization was significantly lower than the rate for those treated without surgical stabilization. However, no clear subjective benefits of initial stabilizing surgery were seen at the time of long-term follow-up.\n\n\nTitle 4:\nAcute patellar dislocation in children and adolescents: a randomized clinical trial.\nAbstract 4:\nThe treatment of acute patellar dislocation in children is controversial. Some investigators have advocated early repair of the medial structures, whereas others have treated this injury nonoperatively. The present report describes the long-term subjective and functional results of a randomized controlled trial of nonoperative and operative treatment of primary acute patellar dislocation in children less than sixteen years of age.\n The data were gathered prospectively on a cohort of seventy-four acute patellar dislocations in seventy-one patients (fifty-one girls and twenty boys) younger than sixteen years of age. Sixty-two patients (sixty-four knees) without large (>15 mm) intra-articular fragments were randomized to nonoperative treatment (twenty-eight knees) or operative treatment (thirty-six knees). Operative treatment consisted of direct repair of the damaged medial structures if the patella was dislocatable with the patient under anesthesia (twenty-nine knees) or lateral release alone if the patella was not dislocatable with the patient under anesthesia (seven knees). All but four patients who underwent operative treatment had a concomitant lateral release. The rehabilitation protocol was the same for both groups. The patients were seen at two years, and a telephone interview was conducted at a mean of six years and again at a mean of fourteen years. Fifty-eight patients (sixty-four knees; 94%) were reviewed at the time of the most recent follow-up.\n At the time of the most recent follow-up, the subjective result was either good or excellent for 75% (twenty-one) of twenty-eight nonoperatively treated knees and 66% (twenty-one) of thirty-two operatively treated knees. The rates of recurrent dislocation in the two treatment groups were 71% (twenty of twenty-eight) and 67% (twenty-four of thirty-six), respectively. The first redislocation occurred within two years after the primary injury in twenty-three (52%) of the forty-four knees with recurrent dislocation. Instability of the contralateral patella was noted in thirty (48%) of the sixty-two patients. The only significant predictor for recurrence was a positive family history of patellar instability. The mode of treatment and the existence of osteochondral fractures had no clinical or significant influence on the subjective outcome, recurrent patellofemoral instability, function, or activity scores.\n The long-term subjective and functional results after acute patellar dislocation are satisfactory in most patients. Initial operative repair of the medial structures combined with lateral release did not improve the long-term outcome, despite the very high rate of recurrent instability. A positive family history is a risk factor for recurrence and for contralateral patellofemoral instability. Routine repair of the torn medial stabilizing soft tissues is not advocated for the treatment of acute patellar dislocation in children and adolescents.\n\n\nTitle 5:\nIsolated repair of the medial patellofemoral ligament in primary dislocation of the patella: a prospective randomized study.\nAbstract 5:\nThe purpose of this study was to evaluate the effect of surgical reinsertion of the medial patellofemoral ligament (MPFL) to the adductor tubercle compared with conservative treatment in patients with primary dislocation of the patella.\n Eighty patients with primary patella dislocation were included in the study. Delayed arthroscopy (mean, 50 days after injury) was performed to assess cartilage injury and status. During arthroscopy, patients were randomized to surgical reinsertion of the MPFL or to conservative treatment. Conservative treatment was use of a brace with 0 degrees to 20 degrees motion for the first 2 weeks after dislocation. Patients were followed up for 2 years. The incidence of recurrent patella dislocation was recorded along with the clinical Kujala scores and Knee Injury and Osteoarthritis Outcome Scores.\n The redislocation rates were 17% and 20% in the operative and conservative treatment groups, respectively (P = not significant). Kujala scores were 85 and 78 in the operative and conservative treatment groups, respectively (P = .07). The patella stability subscore was significantly higher in the operative group. No difference in Knee Injury and Osteoarthritis Outcome Scores was found.\n Delayed primary repair of the MPFL by use of an anchor-based reattachment to the adductor tubercle without vastus medialis obliquus repair after primary patella dislocation does not reduce the risk of redislocation nor does it produce any significantly better subjective functional outcome based on the Kujala knee score. Only the specific subjective patella stability score was improved by MPFL repair compared with conservative treatment.\n Level I, therapeutic randomized controlled trial.", "role": "user" }, { "content": "There is insufficient high quality evidence to confirm any significant difference in outcome between surgical or non-surgical initial management of people following primary patellar dislocation, and none examining this comparison in people with recurrent patellar dislocation. Adequately powered randomised, multi-centre controlled trials, conducted and reported to contemporary standards are recommended.", "role": "assistant" } ]
science.genia_ner
science.genia_ner.1170
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"RNA\", \"CellType\", \"CellLine\", \"Protein\", \"DNA\"].\n\nPlease return the output as a JSON object of the format: {\"DNA\" : [\"TAL1\", ...], \"RNA\": [\"mRNAs\", ...], \"CellLine\": [\"T cells\", ...], \"CellType\": [\"monocytes\", ...], \"Protein\": [\"IL-2\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nNuclear factor-kappaB activation in human monocytes stimulated with lipopolysaccharide is inhibited by fibroblast conditioned medium and exogenous PGE2. The nuclear factor kappaB (NF-kappaB) is thought to be crucially involved in the gene activation of several cytokines, including tumor necrosis factor alpha (TNF). Previously, we showed that fibroblast conditioned medium (FCM) is able to inhibit both TNF mRNA accumulation and protein release in peripheral blood-derived human monocytes (PBM) stimulated with lipopolysaccharide (LPS). In this study we have investigated the effect of FCM on the LPS-induced DNA-binding activity of NF-kappaB, by means of electrophoretic shift assay (EMSA). We provide evidence that FCM strongly inhibits the LPS-induced NF-kappaB activation in PBM. Furthermore, we show that exogenous PGE2 mimics the NF-kappaB inhibitory effect of FCM. On the other hand, FCM produced in the presence of indomethacin does not inhibit NF-kappaB activation by LPS. Our results lend further support to the hypothesis that inflammatory and immune responses of monocytes / macrophages may be modulated at the molecular level by signals originating from tissue structural cells such as fibroblasts.", "role": "user" }, { "content": "{\"CellLine\": [\"PBM\", \"peripheral blood - derived human monocytes\"], \"CellType\": [\"fibroblasts\", \"monocytes / macrophages\", \"tissue structural cells\", \"human monocytes\"], \"DNA\": [], \"Protein\": [\"cytokines\", \"tumor necrosis factor alpha\", \"nuclear factor kappaB\", \"TNF\", \"Nuclear factor - kappaB\", \"NF - kappaB\"], \"RNA\": [\"TNF mRNA\"]}", "role": "assistant" } ]
science.qasa_abstractive_qa
science.qasa_abstractive_qa.657
[ { "content": "You will be shown an excerpt from a computer science research paper, followed by a question about the paper. Please answer the question given the context. Do not include any text in your response other than the answer.\n\nContext: Extensive studies have been conducted to find a better activation function than ReLU, and the swish activation function (Ramachandranet al., 2017) was found. Several neural networks (Tan and Le, 2019b; Mei et al., 2019; Tan and Le, 2019a) use swish activation function instead of ReLU to improve accuracy. Howard et al. (Howard et al., 2019) proposed a quantization-friendly version of the swish activation function called h-swish that has a similar impact on accuracy. So, we replace ReLU with h-swish (Howard et al., 2019) activation function. We improve the baseline network by adding the h-swish activation function and squeeze-and-excitation(SE) block to get the ours-M+ model. Figure 12 shows the topology of ours-M+ architecture in which the height of each block is proportional to the expansion ratio of the block. Compared with the baseline network, ours-M, we achieve around 1% accuracy boost with ours-M+, paying the cost of 16% latency increase. This model outperforms the other models, 0.5% higher accuracy and 14% faster than EfficientNet-B2. Since EfficientNet-B2 is too large to run with the default configuration on MIDAP, we increase the memory size for filter weights. To examine how SE and h-swish impact accuracy individually, we compare four combinations as displayed in Table 8. The baseline is ours-M that does not use SE and h-swish activation function. Replacing ReLU with h-swish gives a marginal improvement on accuracy while adding SE blocks improves the accuracy noticeably. Adding both SE and h-swish activation function improves the accuracy by around 1%. For accurate latency estimation, an analytical latency estimator is devised, based on a cycle-level NPU simulator that runs an entire CNN considering the memory access overhead accurately.Since the NPU assumed in this paper can execute depth-wise separable convolution (DWConv), squeeze-and-excitation (SE), and h-swish activation function efficiently, the proposed supernet prefers DWConv to regular convolution. Observing that the accuracy is improved by around 1% if SE and h-swish activation function are used, we add a post-processing phase after a CNN network is found by NAS to add SE layers and to replace ReLU to h-swish activation function.\n\nQuestion: How does the authors verify adding h-swish and SE is beneficial?", "role": "user" }, { "content": "Previous works showed that using swish activation function instead of ReLU showed better accuracy, and h-swish shows similar impact on accuracy. The authors verify that replacing ReLU with h-swish and adding SE improves the accuracy by around 1%.", "role": "assistant" } ]
science.chemprot_ner
science.chemprot_ner.942
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Chemical\", \"Protein\"].\n\nPlease return the output as a JSON object of the format: {\"Chemical\" : [\"Dexamethasone\", ...], \"Protein\" : [\"BRCA-1\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nChemopreventive effects of Ginkgo biloba extract in estrogen-negative human breast cancer cells.\nExcessive level of estrogen is considered as a main cause of breast cancer, therefore, many studies have focused on estrogen receptor (ER)-positive breast cancer, even though ER-negative cancer has a poor prognosis than ER-positive breast cancer. We evaluated the anti-cancer effects of Ginkgo biloba extract (GBE) in estrogen-independent breast cancer. GBE has been traditionally used as a platelet activating factor, a circulatory stimulant, a tonic, and anti-asthmatic drug, and anti-cancer agent. However, anti-cancer effects of GBE on ER-negative breast cancer have not been proved yet. In this study, we tested chemotherapeutic potential of GBE in the MDA-MB-231 (ER-negative) human breast cancer cell line. Our results showed that cytotoxicity effects of GBE in MDA-MB-231 lead to DNA fragmentation at high concentrations (500 and 1,000 μg/ml). Caspase-3 was significantly activated and mRNA levels of apoptosis-related genes (Bcl-2 and Bax) were altered. These results indicate that GBE induces apoptosis in MDA-MB-231 cells. It is presumed that GBE has chemopreventive effects in ER-independent breast cancer through anti-proliferation and apoptosis-inducing activities.", "role": "user" }, { "content": "{\"Chemical\": [\"estrogen\"], \"Protein\": [\"Caspase-3\", \"Bcl-2\", \"ER\", \"estrogen receptor\", \"Bax\"]}", "role": "assistant" } ]
science.scireviewgen_multidoc_summarization
science.scireviewgen_multidoc_summarization.22721
[ { "content": "You are presented with multiple paper abstracts, a literature review title, and a specific chapter title. Your task is to write a focused literature review chapter that aligns with the given chapter title. The review should synthesize the content from the provided abstracts, draw connections between different works, highlight major findings, and identify any gaps in the existing research.\nLiterature Review Title: Aspect Oriented Middleware for Internet of Things: A State-of-the Art Survey of Service Discovery Approaches \nChapter Title: Service Discovery \n1. Abstract of Cited Paper (BIB001): Pervasive computing environments pose unique service discovery challenges. We have developed a taxonomy of existing protocols as a basis for analyzing their approaches and identifying problems and open issues relative to service discovery in pervasive computing environments.\n\nLiterature Review:", "role": "user" }, { "content": "Service discovery is the process of identifying suitable devices according to the service description submitted by the requestor. The identification process involves locating the requested services, retrieving the service description of those services and executing the matchmaking algorithm between those descriptions and request and finally obtaining the description that perfectly matches the request. The service descriptions are description language that is specific to protocols to define keywords and syntax used to describe services and its properties. The description format may be either key/value, template based or semantic description based. The requirements involved in the design of service discovery protocol from the service provider and consumer perspective can be broadly categorized as functional and non-functional BIB001 . The data structures and methods involved therein are main constituents of the functional requirements for service provider. These methods are for publishing, updating and un-publishing the discovery service description. Service description consists of name value pairs describing the attributes and there is no limit imposed over the number of attributes. The functional requirement from the consumer side is the provision of suitable methods to enable querying the discovery service. The end users should be able to specify the upper bound on the number of services to be returned and provide a means for iterating them. The non-functional requirements include the attributes such as low response time, reliability, scalability and so on. The service discovery protocols are generally classified as centralised, distributed and hierarchical approaches. Centralised approach relies on a directory, in which Service Agents (SA) registers their services and User Agents (UA) discovers the services by sending the unicast queries to the directory. In distributed approach the participant nodes communicate through multicasting the queries for discovering the resources. Hierarchical method includes the cluster of nodes with high capabilities. Service discovery architectures are of two types namely directory based and directory less BIB002 . In the directory based model, there will be a dedicated logically centralized and physically distributed directory to maintain the whole service description. These directories are responsible for registering service descriptions and handling user queries. In the latter the individual service provider maintains the service description and is responsible for processing and replying to the incoming queries.", "role": "assistant" } ]
science.pubmedqa_qa
science.pubmedqa_qa.239
[ { "content": "You will be shown an abstract from a research paper and a corresponding research question. Determine the answer to the research question based on the context provided. Your answer should be one of: \"YES\", \"NO\", or \"MAYBE\".\n\nAbstract:\n(OBJECTIVES) To study the relationship between coronary angiography and in-hospital mortality in patients undergoing emergency surgery of the aorta without a history of coronary revascularization or coronary angiography before the onset of symptoms.\n(BACKGROUND) In the setting of acute ascending aortic dissection warranting emergency aortic repair, coronary angiography has been considered to be desirable, if not essential. The benefits of defining coronary anatomy have to be weighed against the risks of additional delay before surgical intervention.\n(METHODS) Retrospective analysis of patient charts and the Cardiovascular Information Registry (CVIR) at the Cleveland Clinic Foundation.\n(RESULTS) We studied 122 patients who underwent emergency surgery of the aorta between January 1982 and December 1997. Overall, in-hospital mortality was 18.0%, and there was no significant difference between those who had coronary angiography on the day of surgery compared with those who had not (No: 16%, n = 81 vs. Yes: 22%, n = 41, p = 0.46). Multivariate analysis revealed that a history of myocardial infarction (MI) was the only predictor of in-hospital mortality (relative risk: 4.98 95% confidence interval: 1.48-16.75, p = 0.009); however, coronary angiography had no impact on in-hospital mortality in patients with a history of MI. Furthermore, coronary angiography did not significantly affect the incidence of coronary artery bypass grafting (CABG) during aortic surgery (17% vs. 25%, Yes vs. No). Operative reports revealed that 74% of all CABG procedures were performed because of coronary dissection, and not coronary artery disease.\n\nQuestion:\nDoes coronary angiography before emergency aortic surgery affect in-hospital mortality?\n\nAnswer:", "role": "user" }, { "content": "NO", "role": "assistant" } ]
science.bioasq_general_qa
science.bioasq_general_qa.199
[ { "content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: what is the role of erythropoietin in cardiac regeneration after myocardial infarction?\n\nContext: EPO in patients with STEMI treated with PCI is associated with an increase in diameter stenosis that is not associated with circulating progenitor cells.\nThe cytokines granulocyte colony-stimulating factor, erythropoietin, and stem cell factor may play a role in helping to stimulate cell regeneration under normal physiologic conditions and in patients with myocardial injury.\nIn preclinical study, G-CSF and erythropoietin improved cardiac function and perfusion by angiomyogenesis and protection of cardiomyocytes in myocardial infarction. However, results from recent clinical trials did not support beneficial effects of cytokine therapy with G-CSF or erythropoietin alone in patients with myocardial infarction.\nEpo overexpression enhances the cellular regenerative properties of MSCs by both autocrine and paracrine pathways.\nTransplantation of MSC combined with cytokine EPO is superior to either of the monotherapy approach for angiomyogenesis and cardiac function recovery.", "role": "user" }, { "content": "In preclinical studies, erythropoietin improved cardiac function and perfusion by angiomyogenesis and protection of cardiomyocytes in myocardial infarction indicating that erythropoietin may play a role in the stimulation of cell regeneration under normal physiologic conditions and in patients with myocardial injury. Epo overexpression was found to enhance the cellular regenerative properties of MSCs by both autocrine and paracrine pathways. However, results from recent clinical trials did not support beneficial effects of cytokine therapy with erythropoietin in patients with myocardial infarction.", "role": "assistant" } ]
science.scireviewgen_multidoc_summarization
science.scireviewgen_multidoc_summarization.21697
[ { "content": "You are presented with multiple paper abstracts, a literature review title, and a specific chapter title. Your task is to write a focused literature review chapter that aligns with the given chapter title. The review should synthesize the content from the provided abstracts, draw connections between different works, highlight major findings, and identify any gaps in the existing research.\nLiterature Review Title: The complexity of small universal Turing machines: a survey \nChapter Title: Further work \n1. Abstract of Cited Paper (BIB001): A Post machine is a Turing machine which cannot both write and move on the same machine step. It is shown that the halting problem for the class of 2-state Post machines is solvable. Thus, there can be no universal 2-state Post machine. This is in contrast with the result of Shannon that there exist universal 2-state Turing machines when the machines are capable of both writing and moving on the same step. \n2. Abstract of Cited Paper (BIB002): Abstract The standard way of assigning complexity to a one-tape Turing machine, by the state-symbol product, is clearly inadequate for machines with more than one tape. Letting an (m,n,p)-machine be a Turing machine with m states, n symbols (including any end markers), and p tapes, the number m· n p gives the maximum number of operating rules for an (m,n,p)-machine and serves as a fairly reasonable complexity criterion, reducing to the state-symbol product when p = 1. A (2,3,2)-machine has been designed to simulate an arbitrary tag system with deletion number 2, and therefore is universal [1]. Also a (1,2,4)-machine, having a fixed loop for one of its four tapes, has been designed ; this machine is universal by its ability to simulate an arbitrary “B machine” (6). Under the criterion stated above, these machines have complexities of 18 and 16, respectively, both less than any reported state-symbol product. Moreover, any (m,n,p)-machine may be simulated, step-by-step, by a (1,2,p′)-machine, where p′ = p⌜log 2 (n)⌝ + ⌜log 2 (m)⌝ . If the logarithms are integral, this transformation is realized with no increase in complexity. However, since the full power of the additional tapes is not utilized in this transformation, it appears that this complexity criterion does not provide a severe enough penalty for the introduction of additional tapes to a Turing machine. \n3. Abstract of Cited Paper (BIB003): SummaryThe Busy Beaver Competition is held by Turing machines. The better ones halt taking much time or leaving many marks, when starting from a blank tape. In order to understand the behavior of some Turing machines that were once record holders in the five-state Busy Beaver Competition, we analyze their halting problem on all inputs. We prove that the halting problem for these machines amounts to a well-known problem of number theory, that of the behavior of the repeated iteration of Collatz-like functions, that is functions defined by cases according to congruence classes. \n4. Abstract of Cited Paper (BIB004): This volume provides an ideal introduction to key topics in parallel computing. With its cogent overview of the essentials of the subject as well as lists of P -complete- and open problems, extensive remarks corresponding to each problem, a thorough index, and extensive references, the book will prove invaluable to programmers stuck on problems that are particularly difficult to parallelize. In providing an up-to-date survey of parallel computing research from 1994, Topics in Parallel Computing will prove invaluable to researchers and professionals with an interest in the super computers of the future. \n5. Abstract of Cited Paper (BIB005): Abstract After recalling the definition of decidability and universality, we first give a survey of results on the as exact as possible border betweeen a decidable problem and the corresponding undecidablity question in various models of discrete computation: diophantine equations, word problem, Post systems, molecular computations, register machines, neural networks, cellular automata, tiling the plane and Turing machines with planar tape. We then go on with results more specific to classical Turing machines, with a survey of results and a sketchy account on technics. We conclude by an illustration on simulating the 3x+1 problem. \n6. Abstract of Cited Paper (BIB006): In this paper we will give an outline of the proof of the solvability of the halting and reachability problem for 2-symbolic tag systems with a deletion number v = 2. This result will be situated in a more general context of research on limits of solvability in tag systems. \n7. Abstract of Cited Paper (BIB007): Tibor Rado defined the Busy Beaver Competition in 1962. He used Turing machines to give explicit definitions for some functions that are not computable and grow faster than any computable function. He put forward the problem of computing the values of these functions on numbers 1, 2, 3, ... More and more powerful computers have made possible the computation of lower bounds for these values. In 1988, Brady extended the definitions to functions on two variables. We give a historical survey of these works. The successive record holders in the Busy Beaver Competition are displayed, with their discoverers, the date they were found, and, for some of them, an analysis of their behavior.\n\nLiterature Review:", "role": "user" }, { "content": "There are many avenues for further work, here we highlight a few examples. Applying computational complexity theory to the area of small universal Turing machines allows us to ask a number of questions that are more subtle than the usual questions about program size. As we move towards the origin in Figure 1 , the universal machines have larger (but polynomial) time overheads. Can the time overheads in Figure 1 be further improved (lowered)? Can we prove lower bounds on the simulation time of machines with a given state-symbol pair? Proving non-trivial simulation time lower bounds seems like a difficult problem. Such results could be used to prove that there is a polynomial trade-off between simulation time and universal program size. As we move away from the origin, the non-universal machines seem to have more power. For example Kudlek's classification of 2-state, 2-symbol machines shows that the sets accepted by these machines are regular, with the exception of one context free language (a n b n ). Can we hope to fully characterise the sets accepted by non-universal machines (e.g. in terms of complexity or automata theoretic classes) with given state-symbol pairs or other program restrictions? When discussing the complexity of small machines the issue of encodings becomes very important. For example, when proving that the prediction problem for a small machine is P-complete BIB005 , the relevant encodings should be in logspace, and this is the case for all of the polynomial time machines in Figure 1 . Of course there are many models of computation that we have not mentioned where researchers have focused on finding small universal programs. Post's tag systems are an interesting example. Minsky BIB001 showed that tag systems are universal with deletion number 6. Cocke and Minsky lowered the deletion number to 2, by showing that 2-tag systems were universal. They used productions (appendants) of length at most 4. Wang further lowered the production length to 3. Recently, De Mol BIB007 has given a lower bound by showing that the reachability (and thus halting) problems are decidable for 2-tag systems with 2 symbols; a problem which Post claimed to have solved but never published. It would be interesting to find the smallest universal tag systems in terms of number of symbols, deletion length, and production length. The space between the non-universal curve and the smallest non-weakly universal machines in Figure 1 contains some complicated beasts. These lend weight to the feeling that finding new lower bounds on universal program size is tricky. Most noteworthy are the weakly and semi-weakly universal machines discussed earlier. Table 2 highlights that the existence of general models that provably have less states and symbols than the standard universal machines can have (for example the machines with (states, symbols, dimensions, tapes) of (2,3,2,1) , BIB002 BIB002 , and (1,2,1,4) BIB003 ). Also of importance are the busy beavers BIB008 and small machines of Margenstern BIB006 , Baiocchi , and Michel BIB004 that live in this region and simulate iterations of the 3x+1 problem and other Collatz-like functions. So it seems that there are plenty of animals yet to be tamed. Table 2 . Small non-standard universal Turing machines. Semi-weak machines are denoted by †, weak machines by ‡, machines coupled with a finite automaton by ⋆, and a machine with 2 tape heads by △.", "role": "assistant" } ]
science.scireviewgen_multidoc_summarization
science.scireviewgen_multidoc_summarization.73405
[ { "content": "You are presented with multiple paper abstracts, a literature review title, and a specific chapter title. Your task is to write a focused literature review chapter that aligns with the given chapter title. The review should synthesize the content from the provided abstracts, draw connections between different works, highlight major findings, and identify any gaps in the existing research.\nLiterature Review Title: A Survey of Learning Causality with Data: Problems and Methods \nChapter Title: Reinforcement Learning \n1. Abstract of Cited Paper (BIB001): This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes to the system. Such predictions allow both humans and algorithms to select the changes that would have improved the system performance. This work is illustrated by experiments on the ad placement system associated with the Bing search engine. \n2. Abstract of Cited Paper (BIB002): The Multi-Armed Bandit problem constitutes an archetypal setting for sequential decision-making, permeating multiple domains including engineering, business, and medicine. One of the hallmarks of a bandit setting is the agent's capacity to explore its environment through active intervention, which contrasts with the ability to collect passive data by estimating associational relationships between actions and payouts. The existence of unobserved confounders, namely unmeasured variables affecting both the action and the outcome variables, implies that these two data-collection modes will in general not coincide. In this paper, we show that formalizing this distinction has conceptual and algorithmic implications to the bandit setting. The current generation of bandit algorithms implicitly try to maximize rewards based on estimation of the experimental distribution, which we show is not always the best strategy to pursue. Indeed, to achieve low regret in certain realistic classes of bandit problems (namely, in the face of unobserved confounders), both experimental and observational quantities are required by the rational agent. After this realization, we propose an optimization metric (employing both experimental and observational distributions) that bandit agents should pursue, and illustrate its benefits over traditional algorithms. \n3. Abstract of Cited Paper (BIB003): We leverage causal inference tools to support a principled and more robust transfer of knowledge in reinforcement learning (RL) settings. In particular, we tackle the problem of transferring knowledge across bandit agents in settings where causal effects cannot be identified by Pearl's {do-calculus} nor standard off-policy learning techniques. Our new identification strategy combines two steps -- first, deriving bounds over the arm's distribution based on structural knowledge; second, incorporating these bounds in a novel bandit algorithm, B-kl-UCB. Simulations demonstrate that our strategy is consistently more efficient than the current (non-causal) state-of-the-art methods.\n\nLiterature Review:", "role": "user" }, { "content": "Reinforcement learning (RL) BIB001 is studied for solving sequential decision-making problems. The three key variables in RL are the action A, the state (of the world) Z and the reward Y . When an agent performs an action based on the current state, it will reach the next state and receive a reward. To describe the relationships between these variables, researchers adopt the Markov decision process, which means the next state Z t +1 depends only on the current state Z t and action A t and the reward of the next state Y t +1 is determined only by Z t , Z t +1 and A t . A RL model learns a strategy or policy π (a, z) = P(A t = a|Z t = z) which determines which action to take given the current state Z t . The objective is to maximize the sum of the rewards. In the running example, we can assume that the state Z t represents the location of a restaurant, the action A t can be moving to a certain place or staying at the same place and the reward is the customer flow Y . In each time step, the restaurant owner decides which action to take and then observe the customer flow. Then the owner will make decision for the next time step based on whether the customer flow increases or not. One key issue is the unobserved confounders for multi-armed bandits (MAB) BIB003 . Without knowing the underlying causal relationships, traditional MAB algorithms fail to outperform the strategy that randomly picks an action in each time step. Specifically, the Causal Thompson Sampling algorithm BIB003 is proposed to deal with unobserved confounders in MAB problems. The reward distributions of those arms that are not preferred by the current strategy can also be estimated through hypothetical interventions on the action (choice of arm). By doing this we can avoid confounding bias in estimating the causal effect of choosing an arm on the expected reward. To connect causality with RL, we view a strategy or a policy in RL as an intervention . Given rewards of an observed strategy, we can utilize causal inference methods to predict rewards for another strategy, especially for Episodic RL (ERL) problems. ERL is a subclass of RL where the state is reset after a finite number of actions. ERL helps decision-making in a wide range of real-world applications such as the card game Blackjack and the advertisement placement BIB002 . One popular approach leverages IPTW (see Section 3) for reward prediction. In this approach, a treatment refers to an action and the strategy-specific propensity score is defined as the probability to perform the observed action given the observed state. Particularly, sequences of actions, states and rewards produced by running an observed strategy π are recorded in the data as [(A 1 (1), Z 1 (1)), (A 2 (1), Z 2 (1)), ...], [(A 1 (2), Z 1 (2)), (A 2 (2), Z 2 (2)), ...], .... Then we can estimate the expected sum of rewards of a strategyπ with IPTW on the rewards observed for strategy π :ξ n, ERL := 1 n n i=1 Y (i) K j=1π (A j (i)|Z j (i)) K j=1 π (A j (i)|Z j (i)) , where n and K denote the number of repentance of the strategy π in data and the number of time steps in each episode. In BIB002 , an improved variant of this approach is also mentioned. Other recent work bridging RL and causality includes causal approaches for transfer learning in RL models BIB004 and data-fusion for online reinforcement learners .", "role": "assistant" } ]
science.bioasq_general_qa
science.bioasq_general_qa.364
[ { "content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: Describe the isolation of transcription factor complexes by in vivo biotinylation tagging and direct binding to streptavidin beads, as applied for the case of the essential hematopoietic transcription factor GATA-1.\n\nContext: Using the biotin tagged erythroid transcription factor GATA-1 as example, we describe several optimization steps for the application of the high affinity biotin streptavidin system in ChIP\nIsolation and characterization of hematopoietic transcription factor complexes by in vivo biotinylation tagging and mass spectrometry\nEfficient tagging methodologies are an integral aspect of protein complex characterization by proteomic approaches. Owing to the very high affinity of biotin for avidin and streptavidin, biotinylation tagging offers an attractive approach for the efficient purification of protein complexes. The very high affinity of the biotin/(strept)avidin system also offers the potential for the single-step capture of lower abundance protein complexes, such as transcription factor complexes. The identification of short peptide tags that are efficiently biotinylated by the bacterial BirA biotin ligase led to an approach for the single-step purification of transcription factor complexes by specific in vivo biotinylation tagging. A short sequence tag fused N-terminally to the transcription factor of interest is very efficiently biotinylated by BirA coexpressed in the same cells, as was demonstrated by the tagging of the essential hematopoietic transcription factor GATA-1. The direct binding to streptavidin of biotinylated GATA-1 in nuclear extracts resulted in the single-step capture of the tagged factor and associated proteins, which were eluted and identified by mass spectrometry. This led to the characterization of several distinct GATA-1 complexes with other transcription factors and chromatin remodeling cofactors, which are involved in activation and repression of gene targets. Thus, BirA-mediated tagging is an efficient approach for the direct capture and characterization of transcription factor complexes\nWe have described the application of a simple biotinylation tagging approach for the direct purification of tagged transcription factor complexes, based on the use of artificial short peptide tags that are specifically and efficiently biotinylated by the bacterial BirA biotin ligase, which is co-expressed in cells with the tagged factor. We used this approach to initially characterize complexes formed by the hematopoietic transcription factor GATA-1 in erythroid cells\nEpitope tags have often been used as more reliable alternatives. In addition, we have employed protein in vivo biotinylation tagging as a very high affinity alternative to antibodies\nUsing a biotinylation tagging/proteomics approach in erythroid cells, we describe distinct GATA-1 interactions with the essential hematopoietic factor Gfi-1b, the repressive MeCP1 complex and the chromatin remodeling ACF/WCRF complex, in addition to the known GATA-1/FOG-1 and GATA-1/TAL-1 complexes.\nA short sequence tag fused N-terminally to the transcription factor of interest is very efficiently biotinylated by BirA coexpressed in the same cells, as was demonstrated by the tagging of the essential hematopoietic transcription factor GATA-1.\nIsolation and characterization of hematopoietic transcription factor complexes by in vivo biotinylation tagging and mass spectrometry.\nA short sequence tag fused N-terminally to the transcription factor of interest is very efficiently biotinylated by BirA coexpressed in the same cells, as was demonstrated by the tagging of the essential hematopoietic transcription factor GATA-1.\nThe direct binding to streptavidin of biotinylated GATA-1 in nuclear extracts resulted in the single-step capture of the tagged factor and associated proteins, which were eluted and identified by mass spectrometry.\nUsing a biotinylation tagging/proteomics approach in erythroid cells, we describe distinct GATA-1 interactions with the essential hematopoietic factor Gfi-1b, the repressive MeCP1 complex and the chromatin remodeling ACF/WCRF complex, in addition to the known GATA-1/FOG-1 and GATA-1/TAL-1 complexes.\nUsing a biotinylation tagging/proteomics approach in erythroid cells, we describe distinct GATA-1 interactions with the essential hematopoietic factor Gfi-1b, the repressive MeCP1 complex and the chromatin remodeling ACF/WCRF complex, in addition to the known GATA-1/FOG-1 and GATA-1/TAL-1 complexes\nA short sequence tag fused N-terminally to the transcription factor of interest is very efficiently biotinylated by BirA coexpressed in the same cells, as was demonstrated by the tagging of the essential hematopoietic transcription factor GATA-1", "role": "user" }, { "content": "Owing to the very high affinity of biotin for avidin and streptavidin, biotinylation tagging offers an attractive approach for the efficient purification of protein complexes. The very high affinity of the biotin/(strept)avidin system also offers the potential for the single-step capture of lower abundance protein complexes, such as transcription factor complexes. The identification of short peptide tags that are efficiently biotinylated by the bacterial BirA biotin ligase led to an approach for the single-step purification of transcription factor complexes by specific in vivo biotinylation tagging. A short sequence tag fused N-terminally to the transcription factor of interest is very efficiently biotinylated by BirA coexpressed in the same cells, as was demonstrated by the tagging of the essential hematopoietic transcription factor GATA-1. The direct binding to streptavidin of biotinylated GATA-1 in nuclear extracts resulted in the single-step capture of the tagged factor and associated proteins, which were eluted and identified by mass spectrometry. This led to the characterization of several distinct GATA-1 complexes with other transcription factors and chromatin remodeling cofactors, which are involved in activation and repression of gene targets. Thus, BirA-mediated tagging is an efficient approach for the direct capture and characterization of transcription factor complexes.", "role": "assistant" } ]
science.scireviewgen_multidoc_summarization
science.scireviewgen_multidoc_summarization.51069
[ { "content": "You are presented with multiple paper abstracts, a literature review title, and a specific chapter title. Your task is to write a focused literature review chapter that aligns with the given chapter title. The review should synthesize the content from the provided abstracts, draw connections between different works, highlight major findings, and identify any gaps in the existing research.\nLiterature Review Title: Bond-Slip Monitoring of Concrete Structures Using Smart Sensors—A Review \nChapter Title: Monitoring Bond-Slip in Other Structures \n1. Abstract of Cited Paper (BIB001): Introduction:Steel-concrete composite structures are playing an increasingly important role in economic construction because of a series of advantages of great stiffness, good seismic performance, ...\n\nLiterature Review:", "role": "user" }, { "content": "Different from conventional steel plate concrete structures, the structure used in Rucka's paper BIB001 was made by bonding two steel plates to the concrete through high-strength, two-component structural epoxy. Nine steel-concrete specimens were tested in this study and the failure of specimens were divided into two sets according to observed failure modes. Different failure modes can be detected and monitored well using proposed ultrasonic method. Yan et al. BIB002 proposed a signal energy-based interface damage detection algorithm. A push-out test for four steel and concrete composite beams was carried out and the results showed that the proposed algorithm is highly efficient in interface state evaluation and monitoring of composite beams. In summary, the active sensing methods require the embedment of the sensors prior to cast of the concrete structure. For an existing concrete structure, to monitor its bond-slip, passive sensing methods are the choice which will be reviewed in Section 4.1.2. Active sensing methods can provide accurate bond-slip monitoring results at the location where the sensors are installed. However, each piezoceramic sensor requires two wires which makes it unsuitable for many points monitoring. In addition, piezoceramic based sensors are prone to electro-magnetic interference and corrosion. The fiber optic sensors, which will be reviewed in Section 4.2, are better choice than piezoceramic based sensors are.", "role": "assistant" } ]
science.pico_ner
science.pico_ner.1378
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nPlease return the output as a JSON object of the format: {\"Participant\": [\"patients with COPD\", ...], \"Intervention\": [\"Atenolol\", ...], \"Outcome\": [\"blood pressure\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\np16 ( INK4a ) Expression does not predict the outcome of cervical intraepithelial neoplasia grade 2 . Spontaneous regression of cervical intraepithelial neoplasia grade 2 ( CIN2 ) lesions has been recognized since 1955 , but predictors of this are poorly understood . Among the predictive markers studied , p16 ( INK4a ) has been suggested to be of some value in monitoring the diagnosis of CIN2 . In this clinical trial , 90 Brazilian women , diagnosed to CIN2 and high-risk human papillomavirus infection , were randomized into two groups of equal size : 45 women whose lesions were excised and 45 women subjected to prospective follow-up at 3-month intervals at least for 1 year ( mean 6.8 months ) . p16 ( INK4a ) expression was analyzed in paraffin-embedded sections using immunohistochemical staining . Among the 45 women in the follow-up group , 42 % experienced spontaneous regression , 11 % showed persistence , 22 % progressed to CIN3 , and 20 % had partial regression to CIN1 or ASCUS ( atypical squamous cell undetermined signifiance ) . p16 ( INK4a ) expression was detected in 68.9 % of the patients . In univariate survival ( Cox ) analysis , no significant difference in regression was obtained between p16 ( INK4a ) -negative and -positive CIN2 lesions ( adjusted HR = 1.1 ; 95 % CI 0.6-2.0 ) . In conclusion , p16 ( INK4a ) expression could be useful in the diagnosis of CIN2 . However , it failed to predict the outcome of CIN2 . Because of its high spontaneous regression rate , follow-up could be considered as a management option of CIN2 in young and compliant women .", "role": "user" }, { "content": "{\"Intervention\": [\"and -positive\", \"prospective follow-up\", \"p16 ( INK4a )\", \"lesions were excised\", \"p16 ( INK4a ) Expression\", \"immunohistochemical staining\", \"p16 ( INK4a ) -negative\"], \"Outcome\": [\"diagnosis of CIN2\", \"CIN2\", \"univariate survival ( Cox ) analysis\", \"p16 ( INK4a ) Expression\", \"p16 ( INK4a ) expression\"], \"Participant\": [\"90 Brazilian women , diagnosed to CIN2 and high-risk human papillomavirus infection , were randomized into two groups of equal size : 45 women whose lesions were excised and 45 women subjected to prospective follow-up at 3-month intervals at least for 1 year ( mean 6.8 months ) .\", \"45 women\"]}", "role": "assistant" } ]
science.pico_ner
science.pico_ner.169
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nPlease return the output as a JSON object of the format: {\"Participant\": [\"patients with COPD\", ...], \"Intervention\": [\"Atenolol\", ...], \"Outcome\": [\"blood pressure\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nThe effectiveness of omeprazole , clarithromycin and tinidazole in eradicating Helicobacter pylori in a community screen and treat programme . Leeds Help Study Group . INTRODUCTION Helicobacter pylori screening and treatment has been proposed as a cost-effective method of preventing gastric cancer . AIM To assess , in a randomized controlled trial , the efficacy of therapy in eradicating H. pylori as part of a screening programme , and to report the adverse events associated with this strategy . METHODS Subjects between the ages of 40-49 years were randomly selected from the lists of 36 primary care centres . Participants attended their local practice and H. pylori status was determined by 13C-urea breath test . Infected subjects were randomized to receive omeprazole 20 mg b.d. , clarithromycin 250 mg b.d . and tinidazole 500 mg b.d . for 7 days ( OCT ) or identical placebos . Eradication was determined by a 13C-urea breath test 6 months and 2 years after the first visit . Successful eradication was defined as two negative 13C-urea breath tests or one negative and one missing test . Adverse events and compliance were assessed at the 6-month visit . RESULTS A total of 32 929 subjects were invited to attend , 8407 were evaluable , and 2329 ( 28 % ) of these were H. pylori-positive . A total of 1161 subjects were randomized to OCT and 1163 to placebo ; over 80 % returned for a repeat 13C-urea breath test on at least one occasion . The eradication rates in those allocated to OCT were as follows : intention-to-treat , 710 out of 1161 ( 61 % ; 95 % confidence interval : 58-64 % ) ; evaluable 710 out of 967 ( 73 % ; 95 % CI : 71-76 % ) ; took all medication 645 out of 769 ( 84 % ; 95 % CI : 81-87 % ) . Adverse events occurred in 45 % of the treatment group and in 18 % of the placebo group ( relative risk 2.5 ; 95 % CI : 2.1-2.9 ) . Compliance , male gender , no antibiotic prescription in the subsequent 2 years and experiencing a bitter taste with the medication were independently associated with treatment success . CONCLUSIONS The OCT regimen has an eradication rate of 61 % in intention-to-treat analysis and is therefore less successful in treating H. pylori as part of a screening programme compared with hospital studies in dyspeptic patients .", "role": "user" }, { "content": "{\"Intervention\": [\"clarithromycin\", \"omeprazole\", \"tinidazole\", \"and tinidazole 500 mg b.d .\", \"clarithromycin 250 mg b.d\", \"placebos\", \"omeprazole 20 mg b.d.\"], \"Outcome\": [\"eradicating Helicobacter pylori\", \"Eradication\", \"experiencing a bitter taste\", \"eradication rate\", \"one negative and one missing test\", \"Successful eradication\", \"Adverse events\", \"compliance\", \"negative 13C-urea breath tests\", \"pylori-positive\", \"eradication rates\"], \"Participant\": [\"32 929\", \"8407\", \"between the ages of 40-49 years\", \"1161\", \"2329\", \"dyspeptic\", \"H. pylori-positive\"]}", "role": "assistant" } ]
science.healthver_entailment
science.healthver_entailment.2639
[ { "content": "You will be shown a claim about public health and the abstract of a biomedical research paper. Each sentence from the abstract will be on a separate line. Your task is to return a JSON object with two fields:\n\n- \"verdict\": The fact-checking verdict. If the information in the abstract supports the claim, write \"SUPPORT\". If the abstract contradicts the claim, write \"CONTRADICT\". If the abstract does not provide enough information to arrive at a verdict, write \"NEI\" (for \"not enough information\").\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract. If the verdict was \"NEI\", then return an empty array.\n\nFor instance, if the model were given the claim \"wearing masks can prevent the spread of COVID\", the output might be:\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that mass mask-wearing reduces the transmission rate for COVID-19.\"]\n}\n\nClaim: Should all diabetics be labeled 'high risk' for COVID-19? Maybe not\n\nAbstract:\nSome comorbidities are associated with severe coronavirus disease (Covid-19) but it is unclear whether some increase susceptibility to Covid-19.\nIn this case-control Mexican study we found that obesity represents the strongest predictor for Covid-19 followed by diabetes and hypertension in both sexes and chronic renal failure in females only.\nActive smoking was associated with decreased odds of Covid-19.\nThese findings indicate that these comorbidities are not only associated with severity of disease but also predispose for getting Covid-19.\nFuture research is needed to establish the mechanisms involved in each comorbidity and the apparent \"protective\" effect of cigarette smoking.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"In this case-control Mexican study we found that obesity represents the strongest predictor for Covid-19 followed by diabetes and hypertension in both sexes and chronic renal failure in females only.\"]}", "role": "assistant" } ]
science.medmentions_ner
science.medmentions_ner.412
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Finding\", \"Bacterium\", \"ProfessionalOrOccupationalGroup\", \"InjuryOrPoisoning\", \"Eukaryote\", \"BodySystem\", \"Virus\", \"ResearchActivity\", \"BodySubstance\", \"PopulationGroup\", \"Chemical\", \"AnatomicalStructure\", \"SpatialConcept\", \"HealthCareActivity\", \"Organization\", \"BiomedicalOccupationOrDiscipline\", \"Food\", \"ClinicalAttribute\", \"MedicalDevice\", \"BiologicFunction\", \"IntellectualProduct\"].\n\nPlease return the output as a JSON object of the format: {\"Virus\": [\"HIV\", ...], \"Bacterium\": [\"MRSA\", ...], \"AnatomicalStructure\": [\"Lung\", ...], \"BodySystem\": [\"CNS\", ...], \"BodySubstance\": [\"Serum\", ...], \"Finding\": [\"Headache\", ...], \"InjuryOrPoisoning\": [\"Fracture\", ...], \"BiologicFunction\": [\"Death\", ...], \"HealthCareActivity\": [\"Biopsy\", ...], \"ResearchActivity\": [\"Clinical trial\", ...], \"MedicalDevice\": [\"Lenses\", ...], \"SpatialConcept\": [\"Camps\", ...], \"BiomedicalOccupationOrDiscipline\": [\"Forensic medicine\", ...], \"Organization\": [\"WHO\", ...], \"ProfessionalOrOccupationalGroup\": [\"Provider\", ...], \"PopulationGroup\": [\"Swimmers\", ...], \"Chemical\": [\"Gold\", ...], \"Food\": [\"Rice\", ...], \"IntellectualProduct\": [\"RPAM\", ...], \"ClinicalAttribute\": [\"Biomarker\", ...], \"Eukaryote\": [\"Dogs\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nReintervention after endovascular repair for aortic dissection: A systematic review and meta-analysis Thoracic endovascular aortic repair has been chosen as a less-invasive alternative to open surgery for the treatment of aortic dissections; however, the advantages have been challenged by the postoperative reintervention during the follow-up period. This study aimed at evaluating the incidence, reasons, and potential risk factors for reintervention. Studies reporting reintervention after endovascular repair were identified by searching PubMed and Embase in accordance with preferred reporting items for systematic reviews and meta-analyses guidelines, and by reviewing the reference lists of retrieved articles. Sensitivity analysis and subgroup analyses were performed to determine the sources of heterogeneity. Funnel plot and Egger's test were used to determine the publication bias. A total of 27 studies encompassing 2403 patients with aortic dissection were identified. The pooled incidence of reintervention after endovascular repair was 15% (95% confidence interval, 12-19) during 33.7 months of follow-up. The 3 most common reasons for reintervention were endoleak (33.2%), false lumen perfusion and aortic dilation (19.8%), and new dissection (6.9%). The potential factors for reintervention were the mean age of onset and diabetes mellitus determined by performing a single meta-regression analysis (P < .001 and .044, respectively). Current data suggest that the incidence of reintervention after endovascular therapy is relatively high during midterm follow-up. Advanced age of onset is a risk factor and diabetes mellitus is a protective factor of reintervention after endovascular therapy. The possible mechanism that diabetes mellitus protects patients from reintervention should be explored further.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"diabetes mellitus\", \"aortic dissections\", \"endoleak\", \"dissection\", \"false lumen perfusion\", \"aortic dissection\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"risk factors\", \"aortic dilation\", \"sources\", \"risk factor\"], \"Food\": [], \"HealthCareActivity\": [\"reintervention\", \"Reintervention\", \"follow-up\", \"open surgery\", \"endovascular therapy\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"systematic reviews\", \"subgroup\", \"guidelines\", \"systematic review\", \"single meta-regression analysis\", \"retrieved articles\", \"Embase\", \"PubMed\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"analyses\", \"meta-analysis\", \"analysis\", \"meta-analyses\"], \"SpatialConcept\": [\"further\"], \"Virus\": []}", "role": "assistant" } ]
science.craftchem_ner
science.craftchem_ner.1882
[ { "content": "You will be presented with a sentence from biomedical research text. Extract all terms that correspond to chemical entities of biological interest (ChEBI).\nReturn your identified terms in a JSON array, formatted like this: [\"Entity1\", \"Entity2\", ...].\nIf no such entities are detected, respond by providing an empty JSON array [].\n\nBiomedical context:\nMousetailDNAwasisolatedandpurifiedbycuttingapproximately0.5cmofmousetailanddigestingitin500mullysisbuffer(50mMTris-HCl,pH8.0,100mMEDTA,125mMNaCl,1%SDS,200mugProteinaseK)withrockingovernightat55degreesC.", "role": "user" }, { "content": "[\"Tris\", \"HCl\", \"EDTA\", \"NaCl\", \"SDS\"]", "role": "assistant" } ]
science.drug_combo_extraction_re
science.drug_combo_extraction_re.1096
[ { "content": "You will be shown a paragraph from a biomedical research article. Your task is to extract all drug combinations appearing in a specific sentence within the paragraph. Each drug combination should be assigned to one of the following three categories:\n\n- POS: Indicates a positive interaction between the drugs in the combination; for instance, drugs that have an additive or synergistic effect.\n- NEG: Indicates a negative interaction between the drugs in the combination; for instance, combining these drugs might result in adverse side effects, or might reduce their efficacy.\n- COMB: Indicates that the drugs are given in combination, but the type of interaction between the drugs cannot be determined based on the provided context.\n\nPlease format your answer as a JSON array. Each entry in the array should itself be an array formatted as [<drug_1>, <drug_2>, ..., <drug_n>, <category>] where <category> is one of the three categories listed above and <drug_1>, ..., <drug_n> are drug names copied verbatim from the input sentence. Different combinations may involve different numbers of drugs; in other words, the `n` in <drug_n> may vary.\n\nAs an example, the following output describes two extracted drug combinations; one between two drugs, and one between three drugs:\n\n[[\"artesunate\", \"artemether\", \"COMB\"], [\"Nifedipine\", \"Labetalol\", \"Prazosin\", \"POS\"]]\n\nThe paragraph and specific sentence are below. You should only extract relationships expressed in the specific sentence; the paragraph is provided for context.\n\nIn your output, return only the JSON array and no other text. If no drug combinations appear, return an empty array `[]`.\n\nparagraph: Effect of angiotensin converting enzyme inhibition on the incidence of restenosis after percutaneous transluminal coronary angioplasty. To determine whether angiotensin converting enzyme (ACE) inhibition may reduce the incidence of restenosis after percutaneous transluminal coronary angioplasty (PTCA), we retrospectively identified 322 consecutive patients who underwent a successful procedure from June 1988 to December 1989. No patients developed chest pain, ST segment elevation, positive cardiac enzymes, or other evidence of abrupt vessel closure following the PTCA. All patients received intravenous heparin after PTCA and aspirin was begun on the day prior to PTCA . Patients were separated into two groups: those at hospital discharge incidentally treated for hypertension or heart failure with ACE inhibitors (n = 36), and those treated with a drug regimen which did not include ACE inhibitors (n = 286). The two groups were similar with respect to age (61 +/- 13.5 vs. 60 +/- 12.5, p = NS) and other demographic characteristics. Restenosis, defined as the presentation to a physician with symptoms of angina within 6 months of the PTCA and the finding on repeat catheterization of a significant restenosis at the site of the PTCA, occurred in 30% of the patients who were discharged on a drug regimen which did not include ACE inhibitors vs. 3% (p less than .05) in those treated with an ACE inhibitor. Thus, it appears that the use of ACE inhibitors may significantly reduce the incidence of restenosis after successful PTCA.\n\nsentence: All patients received intravenous heparin after PTCA and aspirin was begun on the day prior to PTCA .", "role": "user" }, { "content": "[]", "role": "assistant" } ]
science.chemdner_ner
science.chemdner_ner.3295
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Chemical\"].\n\nPlease return the output as a JSON object of the format: {\"Chemical\": [\"Arsenic\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nControl of one-dimensional magnetism in graphene via spontaneous hydrogenation of the grain boundary. We propose that control of one-dimensional (1D) magnetism in graphene could be made easier by spontaneous hydrogenation of chemically reactive grain boundaries (GBs) in polycrystalline graphenes. Unlike pristine graphene, where hydrogen adsorption favors the formation of zero-dimensional (0D) clusters, the defect cores (pentagon, heptagon and octagon) at the GBs in polycrystalline graphene promote hydrogenation along the GBs. The hydrogenation in polycrystalline graphene starts at the GBs, proceeds gradually towards the grain interior (GI) and results in smooth 1D graphane-graphene interfaces. Our calculations show that the type (ferro- or antiferro-magnetism) and strength of the magnetism can be controlled by controlling the orientation of GBs. Since GBs in single-layer graphenes can be fabricated in a controllable way in experiments, the hydrogenation of GBs could be a unique method to realize large-area magnetic graphenes for future spintronic applications.", "role": "user" }, { "content": "{\"Chemical\": [\"ferro\", \"hydrogen\", \"graphenes\", \"graphene\", \"graphane\"]}", "role": "assistant" } ]
science.medmentions_ner
science.medmentions_ner.1384
[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Finding\", \"Bacterium\", \"ProfessionalOrOccupationalGroup\", \"InjuryOrPoisoning\", \"Eukaryote\", \"BodySystem\", \"Virus\", \"ResearchActivity\", \"BodySubstance\", \"PopulationGroup\", \"Chemical\", \"AnatomicalStructure\", \"SpatialConcept\", \"HealthCareActivity\", \"Organization\", \"BiomedicalOccupationOrDiscipline\", \"Food\", \"ClinicalAttribute\", \"MedicalDevice\", \"BiologicFunction\", \"IntellectualProduct\"].\n\nPlease return the output as a JSON object of the format: {\"Virus\": [\"HIV\", ...], \"Bacterium\": [\"MRSA\", ...], \"AnatomicalStructure\": [\"Lung\", ...], \"BodySystem\": [\"CNS\", ...], \"BodySubstance\": [\"Serum\", ...], \"Finding\": [\"Headache\", ...], \"InjuryOrPoisoning\": [\"Fracture\", ...], \"BiologicFunction\": [\"Death\", ...], \"HealthCareActivity\": [\"Biopsy\", ...], \"ResearchActivity\": [\"Clinical trial\", ...], \"MedicalDevice\": [\"Lenses\", ...], \"SpatialConcept\": [\"Camps\", ...], \"BiomedicalOccupationOrDiscipline\": [\"Forensic medicine\", ...], \"Organization\": [\"WHO\", ...], \"ProfessionalOrOccupationalGroup\": [\"Provider\", ...], \"PopulationGroup\": [\"Swimmers\", ...], \"Chemical\": [\"Gold\", ...], \"Food\": [\"Rice\", ...], \"IntellectualProduct\": [\"RPAM\", ...], \"ClinicalAttribute\": [\"Biomarker\", ...], \"Eukaryote\": [\"Dogs\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nThe mechanism and application of the protein -stabilized gold nanocluster sensing system Protein -stabilized gold nanoclusters (protein - Au NCs) have been an attractive frontier of nanoparticle research. Due to their unique fluorescence properties, high stability, environmentally friendly synthetic routes and nontoxicity, protein - Au NCs could find applications in highly sensitive and selective detection of metal ions, inorganic ions and biomolecules in food, soil, water and biological samples. The past few years have witnessed the development of many successful strategies for the preparation of numerous protein - Au NC -based sensing systems. In this review, we focus on a number of sensing systems based on protein - Au NCs for the detection of various analytes of interest with a special emphasis on their corresponding sensing mechanisms.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"water\", \"Au\", \"inorganic ions\", \"protein\", \"Protein\", \"metal ions\", \"gold\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"sensing\", \"detection\"], \"Food\": [\"food\"], \"HealthCareActivity\": [], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"nanoparticle research\"], \"SpatialConcept\": [], \"Virus\": []}", "role": "assistant" } ]
science.bioasq_yesno_qa
science.bioasq_yesno_qa.316
[ { "content": "You have to answer a biomedical question in binary format, i.e., only yes and no are acceptable answers. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Is COL5A2 gene associated to ischemic heart disease?\n\nContext: Analysis of a gene co-expression network establishes robust association between Col5a2 and ischemic heart disease\nCol5a2, a gene previously not specifically linked to MI response but responsible for the classic type of Ehlers-Danlos syndrome, was found to have many and strong co-expression associations within this community\nCol5a2 shows predictive potential in MI, and in principle may represent a novel candidate marker for the identification and treatment of ischemic cardiovascular disease\nAnalysis of a gene co-expression network establishes robust association between Col5a2 and ischemic heart disease.", "role": "user" }, { "content": "yes", "role": "assistant" } ]
science.drug_combo_extraction_re
science.drug_combo_extraction_re.1172
[ { "content": "You will be shown a paragraph from a biomedical research article. Your task is to extract all drug combinations appearing in a specific sentence within the paragraph. Each drug combination should be assigned to one of the following three categories:\n\n- POS: Indicates a positive interaction between the drugs in the combination; for instance, drugs that have an additive or synergistic effect.\n- NEG: Indicates a negative interaction between the drugs in the combination; for instance, combining these drugs might result in adverse side effects, or might reduce their efficacy.\n- COMB: Indicates that the drugs are given in combination, but the type of interaction between the drugs cannot be determined based on the provided context.\n\nPlease format your answer as a JSON array. Each entry in the array should itself be an array formatted as [<drug_1>, <drug_2>, ..., <drug_n>, <category>] where <category> is one of the three categories listed above and <drug_1>, ..., <drug_n> are drug names copied verbatim from the input sentence. Different combinations may involve different numbers of drugs; in other words, the `n` in <drug_n> may vary.\n\nAs an example, the following output describes two extracted drug combinations; one between two drugs, and one between three drugs:\n\n[[\"artesunate\", \"artemether\", \"COMB\"], [\"Nifedipine\", \"Labetalol\", \"Prazosin\", \"POS\"]]\n\nThe paragraph and specific sentence are below. You should only extract relationships expressed in the specific sentence; the paragraph is provided for context.\n\nIn your output, return only the JSON array and no other text. If no drug combinations appear, return an empty array `[]`.\n\nparagraph: Interpatient variability in dexmedetomidine response: a survey of the literature. Fifty-five thousand patients are cared for in the intensive care unit (ICU) daily with sedation utilized to reduce anxiety and agitation while optimizing comfort. The Society of Critical Care Medicine ( SCCM ) released updated guidelines for management of pain , agitation , and delirium in the ICU and recommended nonbenzodiazepines , such as dexmedetomidine and propofol , as first line sedation agents . Dexmedetomidine, an alpha-2 agonist, offers many benefits yet its use is mired by the inability to consistently achieve sedation goals. Three hypotheses including patient traits/characteristics, pharmacokinetics in critically ill patients, and clinically relevant genetic polymorphisms that could affect dexmedetomidine response are presented. Studies in patient traits have yielded conflicting results regarding the role of race yet suggest that dexmedetomidine may produce more consistent results in less critically ill patients and with home antidepressant use. Pharmacokinetics of critically ill patients are reported as similar to healthy individuals yet wide, unexplained interpatient variability in dexmedetomidine serum levels exist. Genetic polymorphisms in both metabolism and receptor response have been evaluated in few studies, and the results remain inconclusive. To fully understand the role of dexmedetomidine, it is vital to further evaluate what prompts such marked interpatient variability in critically ill patients.\n\nsentence: The Society of Critical Care Medicine ( SCCM ) released updated guidelines for management of pain , agitation , and delirium in the ICU and recommended nonbenzodiazepines , such as dexmedetomidine and propofol , as first line sedation agents .", "role": "user" }, { "content": "[]", "role": "assistant" } ]
README.md exists but content is empty.
Downloads last month
27