Datasets:

kejian

/

sciriff-tulu-none-2000-template-1-summratio-0.85

like 0

[ { "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\nElevated serum BAFF levels are involved in the pathogenesis of B cell-mediated autoimmune diseases such as systemic lupus erythematosus (SLE) [12], multiple sclerosis (MS) [13], systemic sclerosis (SS) [14] and RA [15].", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "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\nEstrogen Receptor-α Variant, ER-α36, is Involved in Tamoxifen Resistance and Estrogen Hypersensitivity. Antiestrogens such as tamoxifen provided a successful treatment for ER-positive breast cancer for the past two decades. However, most breast tumors are eventually resistant to tamoxifen therapy. The molecular mechanisms underlying tamoxifen resistance have not been well established. Recently, we reported that breast cancer patients with tumors expressing high concentrations of ER-α36, a variant of ER-α, benefited less from tamoxifen therapy than those with low concentrations of ER-α36, suggesting that increased ER-α36 concentration is one of the underlying mechanisms of tamoxifen resistance. Here, we investigated the function and underlying mechanism of ER-α36 in tamoxifen resistance. We found that tamoxifen increased ER-α36 concentrations and tamoxifen-resistant MCF7 cells expressed high concentrations of ER-α36. In addition, MCF7 cells with forced expression of recombinant ER-α36 and H3396 cells expressing high concentrations of endogenous ER-α36 were resistant to tamoxifen. ER-α36 downregulation in tamoxifen-resistant cells with the shRNA method restored tamoxifen sensitivity. We also found tamoxifen acted as a potent agonist by activating phosphorylation of the AKT kinase in ER-α36 expressing cells. Finally, we found that cells with high concentration of ER-α36 protein were hypersensitive to estrogen; activating ERK phosphorylation at pM range. Our results thus demonstrated that elevated ER-α36 concentration is one of the mechanisms by which ER-positive breast cancer cells escape tamoxifen therapy and provided a rational to develop novel therapeutic approaches for tamoxifen resistant patients by targeting ER-α36.", "role": "user" }, { "content": "{\"Chemical\": [\"Estrogen\", \"estrogen\", \"tamoxifen\", \"Tamoxifen\"]}", "role": "assistant" } ]

[ { "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: I have a supervised model for object detection and want to improve it.\n\nKeyphrases: object detection images text\n\nDataset description:\nImageNet: The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection.\nCIFAR-10: The CIFAR-10 dataset (Canadian Institute for Advanced Research, 10 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The images are labelled with one of 10 mutually exclusive classes: airplane, automobile (but not truck or pickup truck), bird, cat, deer, dog, frog, horse, ship, and truck (but not pickup truck).\nSyn2Real: Syn2Real, a synthetic-to-real visual domain adaptation benchmark meant to encourage further development of robust domain transfer methods. The goal is to train a model on a synthetic \"source\" domain and then update it so that its performance improves on a real \"target\" domain, without using any target annotations.\nDailyDialog++: Consists of (i) five relevant responses for each context and (ii) five adversarially crafted irrelevant responses for each context.\nTHEODORE: Recent work about synthetic indoor datasets from perspective views has shown significant improvements of object detection results with Convolutional Neural Networks(CNNs). In this paper, we introduce THEODORE: a novel, large-scale indoor dataset containing 100,000 high- resolution diversified fisheye images with 14 classes.\n\nOptions:- A: ImageNet B: CIFAR-10 C: Syn2Real D: DailyDialog++ E: THEODORE", "role": "user" }, { "content": "[\"ImageNet\", \"CIFAR-10\"]", "role": "assistant" } ]

[ { "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\nWhile in our case we were worried about the compatibility of the most simple updating rules of the regularization parameter with the preservation of optimal complexity results, in [16] the main concern was the determination of regularizing parameters that optimize the accuracy of the quadratic model.", "role": "user" }, { "content": "Method", "role": "assistant" } ]

[ { "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:\nComparison of two automated periodontal probes and two probes with a conventional readout in periodontal maintenance patients.\nAbstract 1:\nAIM The aim of the present study was to test in periodontal maintenance patients whether the systems for pressure control that have been commercially developed contribute to more reproducible probing depth measurements as compared with a manual probe . MATERIAL AND METHODS In 12 patients duplicate measurements were made at day 0 and 1 week later . In each patient four teeth with the deepest pockets were measured at six sites . In total 288 sites were available for comparisons . The Florida Probe ( FP ) ( 159 N/cm(2 ) ) , the Jonker Probe ( JP ) ( 153 N/cm(2 ) ) , the Brodontic probe ( BP ) ( 255 N/cm(2 ) ) and the manual probe ( MP ) were used in a r and omized scheme . RESULTS Mean probing measurements showed for the FP and the JP lower recordings than for the BP and manual probe . The FP , the BP and the MP showed no differences between the duplicate measurements , except for the JP where the second measurement was deeper . Correlation coefficients between measurements at day 0 and 1 week show for the BP and the MP are 0.90 and 0.89 , respectively , while for the FP and the JP they are 0.76 and 0.75 , respectively . CONCLUSION The BP and the MP appear to be reliable tools for reproducible pocket depth measurements in periodontal maintenance patients\n\n\nTitle 2:\nComparison of manual and pressure-controlled periodontal probing.\nAbstract 2:\nOver 25,000 sites around natural teeth in three stages of periodontal therapy ( prior to instrumentation , following closed subgingival instrumentation and following surgical therapy ) were independently probed by two examiners . Examiner A used a conventional periodontal probe with uncontrolled pressure . Examiner B used an identical probe tip mounted in a h and le which controlled vertical probing force at 50 g. The pressure-controlled technique produced significantly deeper clinical probing measurements on the direct facial and lingual aspects of teeth regardless of the stage of periodontal therapy that had been completed . Manual probing obtained deeper measurements on the distal-lingual aspects of teeth in the posterior regions which had not received surgical therapy . The percentage match between probing depths obtained by the two methods declined as the probing depths increased . Control of vertical force during probing may provide a more objective method of monitoring periodontal status during longitudinal trials\n\n\nTitle 3:\nEvaluation of four modalities of periodontal therapy. Mean probing depth, probing attachment level and recession changes.\nAbstract 3:\nEighty-two periodontally involved patients were treated in a split mouth design such that one quadrant received coronal scaling ( CS ) , root planing ( RP ) , modified Widman surgery ( MW ) , and flap with osseous resection surgery ( FO ) . The therapy was performed in three phases : Phase I : the teeth previously design ated to receive RP , MW , and FO were thoroughly root planed and the teeth design ated to receive CS were scaled with no subgingival instrumentation , plaque control was initiated and reinforced for the entire mouth ; Phase II : the design ated teeth received MW or FO surgery ; and Phase III : maintenance therapy every three months . The CS teeth received coronal scaling and polishing during maintenance appointments , while RP , MW , and FO teeth received supragingival instrumentation , subgingival instrumentation and polishing . Clinical measurements were taken initially , four weeks post-Phase I , 10 weeks post-Phase II , and after each of two years of maintenance care . All therapy modalities result ed in a decrease of mean probing depth with the FO producing the greatest decrease followed by MW , RP , and CS . The deeper the initial probing depth , the greater was the mean reduction of probing depth . FO created a loss of mean probing attachment in the 1 to 4 mm category . RP and MW produced the greatest gain of mean probing attachment in the 5 to 6 mm category . RP , MW , and FO produced similar gains in the greater than or equal to 7 mm category . FO created the most gingival recession followed by MW , RP , and CS\n\n\nTitle 4:\nClinical evaluation of tine shape of 3 periodontal probes using 2 probing forces.\nAbstract 4:\nThe objective of this study was to evaluate the effect of the tine shape of 3 different periodontal probes . One tapered , one parallel-sided and one WHO-probe tine , each with a diameter of 0.5 mm at the tip , were mounted in hinged h and les exerting a constant probing force ( Brodontic ) . The h and les were adjusted to either 0.25 N ( 127 N/cm2 ) or 0.5 N ( 255 N/cm2 ) . 12 patients with moderate to severe periodontitis were measured after supra- and subgingival debridement , using all 6 possible tine/force combinations in 3 sessions . In each session one tine/force combination was used in the 1st and 3rd quadrants , and another tine/force combination in the 2nd and 4th quadrant . The measurements in the same quadrants could therefore be used for comparisons within the same site . The selection for the 2 quadrants in which a given tine/force combination was to be used , was r and omised . Calculations of differences ( mean per patient ) between probing measurements show that the WHO tine yields deeper recording than the parallel/sided and tapered tines , both at 127 N/cm2 and 255 N/cm2 . We conclude that in addition to probing force , the tine shape of a periodontal probe is of significant importance for the recorded probing depth\n\n\nTitle 5:\nGingival resistance to probing forces. II. The effect of inflammation and pressure on probe displacement in beagle dog gingivitis.\nAbstract 5:\nThis study was undertaken to determine the effect of gingival inflammation and probing pressure on probe tip placement in relation to the base of the gingival crevice and the most coronal connective tissue attachment fibers . Nine young male beagle dogs were divided into three groups as determined by clinical status of the gingiva following implementation of a protocol design ed to produce gingival health and disease . An electromechanical device was used to advance 0.6 mm diameter probes into the facial gingival crevices of selected teeth and to obtain force-displacement curves . The instrument stopped the probe at pressure of either 80 , 160 , 320 , 640 , 1280 , or 2560 kPa which were r and omly allocated to 12 test teeth in each dog . After the probe came to rest , it was attached to the tooth . When all 12 probes were attached , the animal was sacrificed . Blocks consisting of gingiva , probe , and tooth were processed to obtain two buccolingual sections , one containing the probe and the other immediately adjacent to it . Clinical and histometric measurements were performed and the data evaluated . Although three groups of animals were discernable by clinical criteria , only two groups , health and disease , could be formulated based on the degree of histologic inflammation . The histologic grouping was used in data analysis . Histometric distances from the cemento-enamel junction to the base of the crevice ( cJ ) , to most coronal connective tissue attachment ( cC ) and to the probe tip ( cP ) all increased with change from health to disease . However , changes in health/disease did not influence difference between distances ( cP-cJ , cP-cC ) . ( ABSTRACT TRUNCATED AT 250 WORDS\n\n\nTitle 6:\nProbe penetration in relation to the connective tissue attachment level: influence of tine shape and probing force.\nAbstract 6:\nPrevious research has shown that probing force and probe tine shape influence the clinical ly assessed probing depth . The purpose of the present study was to investigate the effect of tine shape and probing force on probe penetration , in relation to the microscopically assessed attachment level in untreated periodontal disease . In 22 patients , scheduled for partial or full mouth tooth extraction and no history of periodontal treatment , 135 teeth were selected . At mesial and distal sites of the teeth reference marks were cut . Three probe tines , mounted in a modified Florida Probe h and piece , were tested : a tapered , a parallel and a ball-ended ; tip-diameter 0.5 mm . The three tines were distributed at r and om over the sites . At each site increasing probing forces of 0.10 N , 0.15 N , 0.20 N , 0.25 N were used . After extraction , the teeth were cleaned and stained for connective tissue fiber attachment . The distance between the reference mark and the attachment level was determined using a stereomicroscope . The results showed that the parallel and ball-ended tine measured significantly beyond the microscopically assessed attachment level at all force levels ; with increasing forces , the parallel tine measured 0.96 to 1.38 mm and the ball-ended tine 0.73 to 1.06 mm deeper . The tapered tine did not deviate significantly from the microscopic values at the forces of 0.15 , 0.20 and 0.25 N. It can be concluded that for the optimal assessment of the attachment level in inflamed periodontal conditions , a tapered probe with a tip diameter of 0.5 mm and exerting a probing force of 0.25 N may be most suitable\n\n\nTitle 7:\nHistological location of a standardized periodontal probe in man.\nAbstract 7:\nThe purpose of this study was to locate the position of the periodontal probe tip using a pressure of 126 N/cm2 ( force of 0.30N using a round periodontal probe tip with a diameter of 0.55 mm ) . The influence of gingival inflammation on this position was also studied . Subjects with three levels of periodontal health and disease were entered into the study and each contributed one experimental tooth . At each site a st and ardized probing system was used to place a probe into a clinical pocket . The probe tip was luted to the test tooth surface . The tooth with its gingival tissue and probe tip was extracted , fixed , and processed for histological measurements . Distances in mm were obtained from the cemento-enamel junction ( CEJ ) to the probe tip , to the base of the crevice/pocket , and to the most coronal connective tissue attachment . Analysis of the data indicated that clinical inflammation was not a factor in the placement of the probe tip at crevice/pocket 's l and marks relative to the CEJ ; however variability of probing may have caused the non- significance . The probing system placed the probe tip 0.66 mm apical to the base of the crevice/pocket and 0.06 mm coronal to the most coronal connective tissue attachment . These conclusions corroborated the results of the previous study in dogs which predicted probe placement of 0.44 mm apical to the base of the crevice using the st and ardized pressure of this probing system", "role": "user" }, { "content": "The incremental change in PPD in healthy/treated sites decreased as the pressure increased above 398 N/cm(2 ) .\nIn diseased sites , this phenomenon was already present at pressures above 100 N/cm(2 ) .\nThe results show that with increasing probing pressure , the PPD increases .\nThe dimensions of the increase are dependent on the periodontal tissue conditions", "role": "assistant" } ]

[ { "content": "You will be given an abstract from a computer science research paper. Given the abstract, your task is to extract all unique relationships between entities of the following, and ONLY the following, types:\n\n- \"USED-FOR\": For instance, \"Our method models user proficiency\" -> [\"method\", \"user proficiency\", \"USED-FOR\"].\n- \"EVALUATE-FOR\": For instance, \"We evaluate our method using F1-measure\" -> [\"F1-measure\", \"method\", \"EVALUATE-FOR\"].\n- \"FEATURE-OF\": For instance, \"prior knowledge of the model\" -> [\"prior knowledge\", \"model\", \"FEATURE-OF\"].\n- \"HYPONYM-OF\": For instance, \"TUIT is a software library\" -> [\"TUIT\", \"software library\", \"HYPONYM-OF\"].\n- \"PART-OF\": For instance, \"We incorporate NLU module into the system\" -> [\"NLU module\", \"system\", \"PART-OF\"].\n- \"COMPARE\": For instance, \"Unlike the quantitative prior, the qualitative prior is often ignored\" -> [\"quantitative prior\", \"qualitative prior\", \"COMPARE\"].\n- \"CONJUNCTION\": For instance, \"obtained from human expert or knowledge base\" -> [\"human expert\", \"knowledge base\", \"CONJUNCTION\"].\n\nFormat your output as a JSON array. Each entry in the array should express a single relation, formatted as [\"<Entity_A>\", \"<Entity_B>\", \"<RELATION_A_B>\"]. An example output might look like:\n\n[[\"neural networks\", \"classification\", \"USED-FOR\"], [\"neuron\", \"neural network\", \"PART-OF\"]].\n\nIf no relations are found, please return an empty JSON array \"[]\".\n\nAbstract:\n\nWe present a new HMM tagger that exploits context on both sides of a word to be tagged, and evaluate it in both the unsupervised and supervised case. Along the way, we present the first comprehensive comparison of unsupervised methods for part-of-speech tagging, noting that published results to date have not been comparable across corpora or lexicons. Observing that the quality of the lexicon greatly impacts the accuracy that can be achieved by the algorithms, we present a method of HMM training that improves accuracy when training of lexical probabilities is unstable. Finally, we show how this new tagger achieves state-of-the-art results in a supervised, non-training intensive framework.", "role": "user" }, { "content": "[[\"accuracy\", \"unsupervised methods\", \"EVALUATE-FOR\"], [\"supervised, non-training intensive framework\", \"HMM tagger\", \"EVALUATE-FOR\"], [\"unsupervised methods\", \"part-of-speech tagging\", \"USED-FOR\"], [\"unsupervised and supervised case\", \"HMM tagger\", \"EVALUATE-FOR\"]]", "role": "assistant" } ]

[ { "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:\nHuman Activity Recognition in RGB-D videos has been an active research topic during the last decade. However, no efforts have been found in the literature, for recognizing human activity in RGB-D videos where several performers are performing simultaneously. In this paper we introduce such a challenging dataset with several performers performing the activities. We present a novel method for recognizing human activities in such videos. The proposed method aims in capturing the motion information of the whole video by producing a dynamic image corresponding to the input video. We use two parallel ResNext-101 to produce the dynamic images for the RGB video and depth video separately. The dynamic images contain only the motion information and hence, the unnecessary background information are eliminated. We send the two dynamic images extracted from the RGB and Depth videos respectively, through a fully connected layer of neural networks. The proposed dynamic image reduces the complexity of the recognition process by extracting a sparse matrix from a video. However, the proposed system maintains the required motion information for recognizing the activity. The proposed method has been tested on the MSR Action 3D dataset and has shown comparable performances with respect to the state-of-the-art. We also apply the proposed method on our own dataset, where the proposed method outperforms the state-of-the-art approaches.\n\nCited Abstract(s):\n[1]: People detection is a key issue for robots and intelligent systems sharing a space with people. Previous works have used cameras and 2D or 3D range finders for this task. In this paper, we present a novel people detection approach for RGB-D data. We take inspiration from the Histogram of Oriented Gradients (HOG) detector to design a robust method to detect people in dense depth data, called Histogram of Oriented Depths (HOD). HOD locally encodes the direction of depth changes and relies on an depth-informed scale-space search that leads to a 3-fold acceleration of the detection process. We then propose Combo-HOD, a RGB-D detector that probabilistically combines HOD and HOG. The experiments include a comprehensive comparison with several alternative detection approaches including visual HOG, several variants of HOD, a geometric person detector for 3D point clouds, and an Haar-based AdaBoost detector. With an equal error rate of 85 in a range up to 8m, the results demonstrate the robustness of HOD and Combo-HOD on a real-world data set collected with a Kinect sensor in a populated indoor environment.\n\n[2]: Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which change significantly with viewpoint. In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations. Our technique consists of a novel descriptor and keypoint detection algorithm. The proposed descriptor is extracted at a point by encoding the Histogram of Oriented Principal Components (HOPC) within an adaptive spatio-temporal support volume around that point. Based on this descriptor, we present a novel method to detect Spatio-Temporal Key-Points (STKPs) in 3D pointcloud sequences. Experimental results show that the proposed descriptor and STKP detector outperform state-of-the-art algorithms on three benchmark human activity datasets. We also introduce a new multiview public dataset and show the robustness of our proposed method to viewpoint variations.\n\n[3]: A number of review or survey articles have previously appeared on human action recognition where either vision sensors or inertial sensors are used individually. Considering that each sensor modality has its own limitations, in a number of previously published papers, it has been shown that the fusion of vision and inertial sensor data improves the accuracy of recognition. This survey article provides an overview of the recent investigations where both vision and inertial sensors are used together and simultaneously to perform human action recognition more effectively. The thrust of this survey is on the utilization of depth cameras and inertial sensors as these two types of sensors are cost-effective, commercially available, and more significantly they both provide 3D human action data. An overview of the components necessary to achieve fusion of data from depth and inertial sensors is provided. In addition, a review of the publicly available datasets that include depth and inertial data which are simultaneously captured via depth and inertial sensors is presented.\n\n[4]: We present a new descriptor for activity recognition from videos acquired by a depth sensor. Previous descriptors mostly compute shape and motion features independently, thus, they often fail to capture the complex joint shape-motion cues at pixel-level. In contrast, we describe the depth sequence using a histogram capturing the distribution of the surface normal orientation in the 4D space of time, depth, and spatial coordinates. To build the histogram, we create 4D projectors, which quantize the 4D space and represent the possible directions for the 4D normal. We initialize the projectors using the vertices of a regular polychoron. Consequently, we refine the projectors using a discriminative density measure, such that additional projectors are induced in the directions where the 4D normals are more dense and discriminative. Through extensive experiments, we demonstrate that our descriptor better captures the joint shape-motion cues in the depth sequence, and thus outperforms the state-of-the-art on all relevant benchmarks.\n\n[5]: In this paper, we present an action recognition framework leveraging data mining capabilities of random decision forests trained on kinematic features. We describe human motion via a rich collection of kinematic feature time-series computed from the skelet al representation of the body in motion. We discriminatively optimize a random decision forest model over this collection to identify the most effective subset of features, localized both in time and space. Later, we train a support vector machine classifier on the selected features. This approach improves upon the baseline performance obtained using the whole feature set with a significantly less number of features (one tenth of the original). On MSRC-12 dataset (12 classes), our method achieves 94 accuracy. On the WorkoutSU-10 dataset, collected by our group (10 physical exercise classes), the accuracy is 98 . The approach can also be used to provide insights on the spatiotemporal dynamics of human actions.", "role": "user" }, { "content": "Recognizing human activity in RGB-D videos is an active research area in computer vision and robotics [3] . Most of the approaches for depth based activity recognition are based on handcrafted features ranging from gradient, optical flow, HOG, interest points, etc. Oreifej [4] proposed Histogram of oriented 4D surface normals (HON4D), based on the assumption that, the normal orientation captures more information than the gradient orientation. The descriptors are acquired from 4D volumes for recognition. Spinello [1] used HOG to find the objects. Then Histogram of Oriented Depth value (HOD) is used for extracting depth information. Rahmani [2] proposed Histogram of Oriented Principal Components(HOPC) to tackle the issues related to viewpoint variations. Koch [5] proposed a volumetric approach for finding the depth estimates for all pixels and projected in the voxelized 3D space. Each depth estimate votes for a voxel probabilistically and the surfaces are extracted by thresholding. The handcrafted features are often found unable to find the motion in depth sequences, due to the 2D representation of the depth map, available with the data.", "role": "assistant" } ]

[ { "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: Fine-tuning the target classifier is the most critical part of the transfer learning method. Overly aggressive fine-tuning will cause catastrophic forgetting, eliminating the benefit of the information captured through language modeling; too cautious fine-tuning will lead to slow convergence (and resultant overfitting). Besides discriminative fine-tuning and triangular learning rates, we propose gradual unfreezing for fine-tuning the classifier. We show that not the idea of LM fine-tuning but our lack of knowledge of how to train them effectively has been hindering wider adoption. LMs overfit to small datasets and suffered catastrophic forgetting when fine-tuned with a classifier. Compared to CV, NLP models are typically more shallow and thus require different fine-tuning methods. On all datasets, fine-tuning the full model leads to the lowest error comparatively early in training, e.g. already after the first epoch on IMDb. The error then increases as the model starts to overfit and knowledge captured through pretraining is lost. In contrast, ULMFiT is more stable and suffers from no such catastrophic forgetting; performance remains similar or improves until late epochs, which shows the positive effect of the learning rate schedule.\n\nQuestion: What is catastrophic forgetting?", "role": "user" }, { "content": "Catastrophic forgetting involved increasing error as a model start to overfit and knowledge captured through pretraining is lost.", "role": "assistant" } ]

[ { "content": "You will be shown inclusion or exclusion criteria for a clinical trial. Given these criteria, your task is to extract all unique entities of the following types: [\"Person\", \"Condition\", \"Value\", \"ReferencePoint\", \"Temporal\", \"Qualifier\", \"Observation\", \"Visit\", \"Measurement\", \"Mood\", \"Device\", \"Scope\", \"Negation\", \"Drug\", \"Procedure\", \"Multiplier\"].\n\nPlease return the output as a JSON object of the format: {\"Condition\": [\"breast cancer\", ...], \"Device\": [\"ports\", ...], \"Drug\": [\"Atenolol\", ...], \"Measurement\": [\"blood pressure\", ...], \"Mood\": [\"suspected\", ...], \"Multiplier\": [\"more than two\", ...], \"Negation\": [\"no\", ...], \"Observation\": [\"history\", ...], \"Person\": [\"male\", ...], \"Procedure\": [\"surgery\", ...], \"Qualifier\": [\"severe\", ...], \"ReferencePoint\": [\"enrollment\", ...], \"Scope\": [\"infection\", ...], \"Temporal\": [\"one day\", ...], \"Value\": [\"50%\", ...], \"Visit\": [\"ICU\", ...]}. 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\nMale or female = 18 years of age at Visit 1.\nSweat chloride equal or greater than 60 mEq/L by quantitative pilocarpine iontophoresis test.\nTwo well-characterized mutations in the cystic fibrosis transmembrane conductance regulator (CFTR) gene\nAbnormal nasal potential difference (NPD) as measured by a change in NPD in response to a low chloride solution and isoproterenol of less than -5 mV.\nDocumentation of the presence of an acute pulmonary exacerbation, based on CF Foundation guidelines, as diagnosed by a faculty member of the Denver Adult CF Program.\nRespiratory culture(s) demonstrating evidence of Pseudomonas aeruginosa or Achromobacter species airway infection.\nSubject is able to produce sputum, undergo phlebotomy, and provide written consent.\nThe subject's treating physician has determined that they should receive either tobramycin or colistin intravenously as one of the designated agents for their APE treatment. Subjects who are able to receive either tobramycin or colistin as part of their antibiotic regimen will be randomized into one of three arms. If a treating physician deems that a subject cannot receive tobramycin due to vestibular toxicity, ototoxicity or bacterial resistance, the subject will be randomized to either standard or PK-adjusted colistin.", "role": "user" }, { "content": "{\"Condition\": [\"stic fibrosis transmembrane conductance regulator ( ne\\nA\", \"CFTR\", \"airway infection\", \"acute pulmonary exacerbation\", \"mutations\"], \"Device\": [], \"Drug\": [], \"Measurement\": [\"CF Foundation guidelines\", \"NPD\", \"quantitative pilocarpine iontophoresis test\", \"Sweat chloride\", \"nasal potential difference\", \"Respiratory culture(s)\"], \"Mood\": [], \"Multiplier\": [\"Two\"], \"Negation\": [], \"Observation\": [], \"Person\": [\"female\", \"Male\", \"age\"], \"Procedure\": [], \"Qualifier\": [], \"ReferencePoint\": [\"Visit 1\"], \"Scope\": [\"Pseudomonas aeruginosa or Achromobacter species\"], \"Temporal\": [\"at Visit 1.\"], \"Value\": [\"equal or greater than 60 mEq/L\", \"= 18 years\", \"Achromobacter species\", \"Pseudomonas aeruginosa\", \"less than -5 mV\", \"Abnormal\"], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Given a short query with keyphrases about a research idea in 2019 in the domain of artificial intelligence, recommend the relevant datasets to validate the research idea from the options provided. A short description of the datasets is also provided to help you.\n\nQuery: A method for reconstructing photoacoustic images by optimizing raw data and beamformed images once with a convolutional\n\nKeyphrases: photoacoustic imaging video\n\nDataset description:\nReal Blur Dataset: The dataset consists of 4,738 pairs of images of 232 different scenes including reference pairs. All images were captured both in the camera raw and JPEG formats, hence generating two datasets: RealBlur-R from the raw images, and RealBlur-J from the JPEG images.\nCam2BEV: The dataset contains two subsets of synthetic, semantically segmented road-scene images, which have been created for developing and applying the methodology described in the paper \"A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird’s Eye View\" (IEEE Xplore, arXiv, YouTube) The dataset can be used through the official code implementation of the Cam2BEV methodology described on Github. | Dataset | # Training Samples | # Validation Samples | # Vehicle Cameras | # Semantic Classes | Contained Images (examples) | | --- | --- | --- | --- | --- | --- | | Dataset 1: 360° Surround | 33199 | 3731 | 4 (front, rear, left, right) | 30 (CityScapes) | front camera, rear camera, left camera, right camera, bird's eye view, bird's eye view incl.\nDOTmark: DOTmark is a benchmark for discrete optimal transport, which is designed to serve as a neutral collection of problems, where discrete optimal transport methods can be tested, compared to one another, and brought to their limits on large-scale instances. It consists of a variety of grayscale images, in various resolutions and classes, such as several types of randomly generated images, classical test images and real data from microscopy.\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.\n\nOptions: A: Real Blur Dataset B: Cam2BEV C: DOTmark D: DRIVE", "role": "user" }, { "content": "DRIVE", "role": "assistant" } ]

[ { "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\nExpression of IkappaBalpha in the nucleus of human peripheral blood T lymphocytes. According to current models the inhibitory capacity of I (kappa) B (alpha) would be mediated through the retention of Rel / NF-kappaB proteins in the cytosol. However, I (kappa) B (alpha) has also been detected in the nucleus of cell lines and when overexpressed by transient transfection. To gain better insight into the potential role of nuclear I (kappa) B (alpha) in a physiological context we have analysed its presence in the nucleus of human peripheral blood T lymphocytes (PBL). We demonstrate the nuclear localization of I (kappa) B (alpha) in PBL by different techniques: Western blot, indirect immunofluorescence and electron microscopy. Low levels of nuclear I (kappa) B (alpha) were detected in resting cells whereas a superinduction was obtained after PMA activation. The nuclear pool of I (kappa) B (alpha) showed a higher stability than cytosolic I (kappa) B (alpha) and was partially independent of the resynthesis of the protein. Unexpectedly, the presence of nuclear I (kappa) B (alpha) did not inhibit NF-kappaB binding to DNA and this phenomenon was not due to the presence of IkappaBbeta at the nuclear level. Immunoprecipitation experiments failed to demonstrate an association between nuclear I (kappa) B (alpha) and NF-kappaB proteins. Our results demonstrate that in resting and PMA-activated human PBL, I (kappa) B (alpha) is present in the nucleus in an apparently inactive form unable to disrupt NF-kappaB binding from DNA.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"human peripheral blood T lymphocytes\", \"PMA - activated human PBL\", \"cytosol\", \"PBL\"], \"DNA\": [\"DNA\"], \"Protein\": [\"nuclear I (kappa) B (alpha)\", \"Rel / NF - kappaB proteins\", \"the protein\", \"I (kappa) B (alpha)\", \"NF - kappaB\", \"IkappaBbeta\", \"IkappaBalpha\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "Given a short query with keyphrases about a research idea in 2019 in the domain of artificial intelligence, recommend the relevant datasets to validate the research idea from the options provided. A short description of the datasets is also provided to help you.\n\nQuery: I want to train a supervised model for semantic image retrieval.\n\nKeyphrases: semantic image retrieval images\n\nDataset description:\nSNIPS: The SNIPS Natural Language Understanding benchmark is a dataset of over 16,000 crowdsourced queries distributed among 7 user intents of various complexity: SearchCreativeWork (e.g. Find me the I, Robot television show), GetWeather (e.g.\nYouTube-8M: The YouTube-8M dataset is a large scale video dataset, which includes more than 7 million videos with 4716 classes labeled by the annotation system. The dataset consists of three parts: training set, validate set, and test set.\nImageNet: The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection.\nCLUECorpus2020: CLUECorpus2020 is a large-scale corpus that can be used directly for self-supervised learning such as pre-training of a language model, or language generation. It has 100G raw corpus with 35 billion Chinese characters, which is retrieved from Common Crawl.\n\nOptions: A: SNIPS B: YouTube-8M C: ImageNet D: CLUECorpus2020", "role": "user" }, { "content": "ImageNet", "role": "assistant" } ]

[ { "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: Does p85α homodimerize?\n\nContext: homodimerized p85α\np110α-free p85α homodimerizes\nhomodimeric but not monomeric p85α", "role": "user" }, { "content": "yes", "role": "assistant" } ]

[ { "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\nOverproduction of NFKB2 (lyt-10) and c-Rel: a mechanism for HTLV-I Tax-mediated trans-activation via the NF-kappa B signalling pathway. Molecular, biochemical and epidemiological evidence implicate HTLV-I as an etiologic agent of adult T cell leukemia (ATL). The Tax protein of HTLV-I, a positive transcriptional activator of HTLV-I gene expression, is a viral oncogene that also increases transcription of cellular genes including GM-CSF, IL-2R alpha and IL-2. One of the cellular targets of the trans-activating effects of Tax is the NF-kappa B / Rel family of transcription factors, pleiotropic regulators of immunoregulatory, cytokine and viral gene expression. In this report, we demonstrate that NFKB2 (lyt-10) and c-Rel are overexpressed in HTLV-I infected and Tax-expressing cells and, together, account for the majority of the constitutive NF-kappa B binding activity in these cells before and after PMA stimulation. Most importantly, we show a Tax-dependent correlation between expression of NFKB2 (p100) and processing to the DNA binding NFKB2 (p52) form, induction of c-Rel, and trans-activation of NF-kappa B-mediated gene expression. Furthermore, the NFKB2 precursor is physically associated with c-Rel and with Tax in HTLV-I infected cells. We propose that NFKB2 synthesis and processing allows continuous nuclear expression of an otherwise cytoplasmic protein and, in conjunction with overexpression of c-Rel, NFKB2 alters the NF-kappa B signalling pathway and contributes to leukemic transformation of T cells by HTLV-I.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"T cells\", \"HTLV - I infected cells\", \"Tax - expressing cells\"], \"DNA\": [\"cellular genes\"], \"Protein\": [\"Tax protein\", \"lyt - 10\", \"pleiotropic regulators\", \"transcription factors\", \"c - Rel\", \"IL - 2\", \"HTLV - I\", \"GM - CSF\", \"p100\", \"positive transcriptional activator\", \"NF - kappa B\", \"NFKB2\", \"cytoplasmic protein\", \"Tax\", \"NF - kappa B / Rel family\", \"HTLV - I Tax\", \"p52\", \"IL - 2R alpha\"], \"RNA\": []}", "role": "assistant" } ]

[ { "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: Has the fungus Ashbya gossypii got many nuclei that share cytoplasm?\n\nContext: multinucleated Ashbya gossypii cells.\nmultinucleated Ashbya gossypii fungal cells\nNuclei in the filamentous, multinucleated fungus Ashbya gossypii divide asynchronously.\nmultinucleated Ashbya gossypii cells\nWe analyzed a unique asynchronous nuclear division cycle in a multinucleated filamentous fungus, Ashbya gossypii.\nmultinucleated hyphae in Ashbya gossypii.\nWe have followed the migration of GFP-labelled nuclei in multinucleate hyphae of Ashbya gossypii\nmultinucleate fungus Ashbya gossypii\nAshbya gossypii grows as multinucleated and constantly elongating hyphae\nmultinucleated hyphae of Ashbya gossypii.\nWe report the mechanistic basis guiding the migration pattern of multiple nuclei in hyphae of Ashbya gossypii.\nmultinucleate fungal cells\nmultinucleate Ashbya gossypii cells relies on a minimal network of genes\nClustering of nuclei in multinucleated hyphae is prevented by dynein-driven bidirectional nuclear movements and microtubule growth control in Ashbya gossypii.\nIn the multinucleate fungus Ashbya gossypii, cytoplasmic microtubules (cMTs) emerge from the spindle pole body outer plaque (OP) in perpendicular and tangential directions.\nmultinucleated hyphae of Ashbya gossypii.\nmultiple nuclei in Ashbya gossypii hyphae\nAshbya gossypii has a budding yeast-like genome but grows exclusively as multinucleated hyphae.", "role": "user" }, { "content": "yes", "role": "assistant" } ]

[ { "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\nAn optogenetic approach in epilepsy. Optogenetic tools comprise a variety of different light-sensitive proteins from single-cell organisms that can be expressed in mammalian neurons and effectively control their excitability. Two main classes of optogenetic tools allow to either depolarize or hyperpolarize, and respectively generate or inhibit action potentials in selective populations of neurons. This opens unprecedented possibilities for delineating the role of certain neuronal populations in brain processing and diseases. Moreover, optogenetics may be considered for developing potential treatment strategies for brain diseases, particularly for excitability disorders such as epilepsy. Expression of the inhibitory halorhodopsin NpHR in hippocampal principal cells has been recently used as a tool to effectively control chemically and electrically induced epileptiform activity in slice preparations, and to reduce in vivo spiking induced by tetanus toxin injection in the motor cortex. In this review we give a comprehensive summary of what has been achieved so far in the field of epilepsy using optogenetics, and discuss some of the possible strategies that could be envisaged in the future. We also point out some of the challenges and pitfalls in relation to possible outcomes of using optogenetics for controlling network excitability, and associated brain diseases. This article is part of the Special Issue entitled 'New Targets and Approaches to the Treatment of Epilepsy'.", "role": "user" }, { "content": "{\"Chemical\": []}", "role": "assistant" } ]

[ { "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\nDeterminants of Maternal Triglycerides in Women With Gestational Diabetes Mellitus in the Metformin in Gestational Diabetes (MiG) Study. OBJECTIVEFactors associated with increasing maternal triglyceride concentrations in late pregnancy include gestational age, obesity, preeclampsia, and altered glucose metabolism. In a subgroup of women in the Metformin in Gestational Diabetes (MiG) trial, maternal plasma triglycerides increased more between enrollment (30 weeks) and 36 weeks in those treated with metformin compared with insulin. The aim of this study was to explain this finding by examining factors potentially related to triglycerides in these women.RESEARCH DESIGN AND METHODSOf the 733 women randomized to metformin or insulin in the MiG trial, 432 (219 metformin and 213 insulin) had fasting plasma triglycerides measured at enrollment and at 36 weeks. Factors associated with maternal triglycerides were assessed using general linear modeling.RESULTSMean plasma triglyceride concentrations were 2.43 (95% CI 2.35-2.51) mmol/L at enrollment. Triglycerides were higher at 36 weeks in women randomized to metformin (2.94 [2.80-3.08] mmol/L; +23.13% [18.72-27.53%]) than insulin (2.65 [2.54-2.77] mmol/L, P = 0.002; +14.36% [10.91-17.82%], P = 0.002). At 36 weeks, triglycerides were associated with HbA1c (P = 0.03), ethnicity (P = 0.001), and treatment allocation (P = 0.005). In insulin-treated women, 36-week triglycerides were associated with 36-week HbA1c (P = 0.02), and in metformin-treated women, they were related to ethnicity.CONCLUSIONSAt 36 weeks, maternal triglycerides were related to glucose control in women treated with insulin and ethnicity in women treated with metformin. Whether there are ethnicity-related dietary changes or differences in metformin response that alter the relationship between glucose control and triglycerides requires further study.", "role": "user" }, { "content": "{\"Chemical\": [\"glucose\", \"triglyceride\", \"metformin\", \"triglycerides\", \"Triglycerides\", \"Metformin\"]}", "role": "assistant" } ]

[ { "content": "Given an abstract from a research paper, your task is to identify and label relationships between chemical compounds and genes mentioned in the abstract.\n\nThe relationship type must be one of ['DOWNREGULATOR', 'SUBSTRATE', 'INDIRECT-REGULATOR', 'PART-OF', 'MODULATOR-ACTIVATOR', 'REGULATOR', 'INHIBITOR', 'COFACTOR', 'UPREGULATOR', 'ACTIVATOR', 'ANTAGONIST', 'NOT', 'INDIRECT-DOWNREGULATOR', 'SUBSTRATE_PRODUCT-OF', 'INDIRECT-UPREGULATOR', 'AGONIST', 'PRODUCT-OF', 'MODULATOR', 'DIRECT-REGULATOR', 'UNDEFINED', 'AGONIST-INHIBITOR', 'AGONIST-ACTIVATOR', 'MODULATOR-INHIBITOR'].\n\nPlease format your output as a JSON array. Each entry in the array should express a single relation, formatted as [\"<Entity_A>\", \"<RELATION_A_B>\", \"<Entity_B>\"]. If no relations can be found, please output an empty JSON array [].\n\nAbstract:\n\nCholinesterase inhibitors for Alzheimer 's disease. BACKGROUND: Since the introduction of the first cholinesterase inhibitor (ChEI) in 1997, most clinicians and probably most patients would consider the cholinergic drugs, donepezil, galantamine and rivastigmine, to be the first line pharmacotherapy for mild to moderate Alzheimer 's disease. The drugs have slightly different pharmacological properties, but they all work by inhibiting the breakdown of acetylcholine, an important neurotransmitter associated with memory, by blocking the enzyme acetylcholinesterase. The most that these drugs could achieve is to modify the manifestations of Alzheimer 's disease. Cochrane reviews of each ChEI for Alzheimer 's disease have been completed (Birks 2005, Birks 2005b and Loy 2005). Despite the evidence from the clinical studies and the intervening clinical experience the debate on whether ChEIs are effective continues. OBJECTIVES: To assess the effects of donepezil, galantamine and rivastigmine in people with mild, moderate or severe dementia due to Alzheimer 's disease. SEARCH STRATEGY: The Cochrane Dementia and Cognitive Improvement Group 's Specialized Register was searched using the terms 'donepezil', 'E2020', 'Aricept', galanthamin * galantamin * reminyl, rivastigmine, exelon, \" ENA 713 \" and ENA-713 on 12 June 2005. This Register contains up-to-date records of all major health care databases and many ongoing trial databases. SELECTION CRITERIA: All unconfounded, blinded, randomized trials in which treatment with a ChEI was compared with placebo or another ChEI for patients with mild, moderate or severe dementia due to Alzheimer 's disease. DATA COLLECTION AND ANALYSIS: Data were extracted by one reviewer (JSB), pooled where appropriate and possible, and the pooled treatment effects, or the risks and benefits of treatment estimated. MAIN RESULTS: The results of 13 randomized, double blind, placebo controlled trials demonstrate that treatment for periods of 6 months and one year, with donepezil, galantamine or rivastigmine at the recommended dose for people with mild, moderate or severe dementia due to Alzheimer 's disease produced improvements in cognitive function, on average -2.7 points (95%CI -3.0 to -2.3), in the midrange of the 70 point ADAS-Cog Scale. Study clinicians blind to other measures rated global clinical state more positively in treated patients. Benefits of treatment were also seen on measures of activities of daily living and behaviour. None of these treatment effects are large. There is nothing to suggest the effects are less for patients with severe dementia or mild dementia, although there is very little evidence for other than mild to moderate dementia. More patients leave ChEI treatment groups, approximately 29%, on account of adverse events than leave the placebo groups (18%). There is evidence of more adverse events in total in the patients treated with a ChEI than with placebo. Although many types of adverse event were reported, nausea, vomiting, diarrhoea, were significantly more frequent in the ChEI groups than in placebo. There are four studies, all supported by one of the pharmaceutical companies, in which two ChEIs were compared, two studies of donepezil compared with galantamine, and two of donepezil compared with rivastigmine. In three studies the patients were not blinded to treatment, only the fourth, DON vs RIV/Bullock is double blind. Two of the studies provide little evidence, they are of 12 weeks duration, which is barely long enough to complete the drug titration. There is no evidence from DON vs GAL/Wilcock of a treatment difference between donepezil and galantamine at 52 weeks for cognition, activities of daily living, the numbers who leave the trial before the end of treatment, the number who suffer any adverse event, or any specific adverse event. There is no evidence from DON vs RIV/Bullock of a difference between donepezil and rivastigmine for cognitive function, activities of daily living and behavioural disturbance at two years. Fewer patients suffer adverse events on donepezil than rivastigmine. AUTHORS 'CONCLUSIONS: The three cholinesterase inhibitors are efficacious for mild to moderate Alzheimer's disease. It is not possible to identify those who will respond to treatment prior to treatment. There is no evidence that treatment with a ChEI is not cost effective. Despite the slight variations in the mode of action of the three cholinesterase inhibitors there is no evidence of any differences between them with respect to efficacy. There appears to be less adverse effects associated with donepezil compared with rivastigmine. It may be that galantamine and rivastigmine match donepezil in tolerability if a careful and gradual titration routine over more than three months is used. Titration with donepezil is more straightforward and the lower dose may be worth consideration.", "role": "user" }, { "content": "[[\"rivastigmine\", \"INHIBITOR\", \"cholinesterase\"], [\"galantamine\", \"INHIBITOR\", \"cholinesterase\"], [\"acetylcholine\", \"SUBSTRATE\", \"acetylcholinesterase\"], [\"donepezil\", \"INHIBITOR\", \"cholinesterase\"]]", "role": "assistant" } ]

[ { "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: C-type Lectin Mincle Recognizes Glucosyl-diacylglycerol of Streptococcus pneumoniae and Plays a Protective Role in Pneumococcal Pneumonia\nArticle:\nAbstract:\nAmong various innate immune receptor families, the role of C-type lectin receptors( CLRs) in lung protective immunity against Streptococcus pneumoniae( S. pneumoniae) is not fully defined. We here show that Mincle gene expression was induced in alveolar macrophages and neutrophils in bronchoalveolar lavage fluids of mice and patients with pneumococcal pneumonia. Moreover, S. pneumoniae directly triggered Mincle reporter cell activation in vitro via its glycolipid glucosyl-diacylglycerol( Glc-DAG), which was identified as the ligand recognized by Mincle. Purified Glc-DAG triggered Mincle reporter cell activation and stimulated inflammatory cytokine release by human alveolar macrophages and alveolar macrophages from WT but not Mincle KO mice. Mincle deficiency led to increased bacterial loads and decreased survival together with strongly dysregulated cytokine responses in mice challenged with focal pneumonia inducing S. pneumoniae, all of which was normalized in Mincle KO mice reconstituted with a WT hematopoietic system. In conclusion, the Mincle-Glc-DAG axis is a hitherto unrecognized element of lung protective immunity against focal pneumonia induced by S. pneumoniae.\nIntroduction:\nStreptococcus pneumoniae is the most prevalent pathogen causing community-acquired pneumonia( CAP). Pneumococcal CAP frequently progresses to invasive pneumococcal disease( IPD), which is associated with high morbidity and mortality rates worldwide[1–3]. Resident alveolar macrophages( AM) and neutrophils represent the first lines of host defense against lung-tropic bacterial pathogens, and have been characterized to express multiple pattern recognition receptors( PRRs), including Toll-like receptors( TLRs), NOD-like receptors( NLRs), and RIG-I-like receptors, as well as C-type lectin receptors( CLRs), all of which sense pathogen-associated molecular patterns( PAMPs) and/or danger-associated molecular patterns( DAMPs). Activation of PRRs leads to production of NF-ĸB-dependent proinflammatory cytokines such as TNF-α, IL-6, and IL-1β, followed by overlapping release of anti-inflammatory mediators, such as IL-1ra and IL-10, which together orchestrate and shape downstream lung antibacterial immune responses by recruitment and activation/de-activation of inflammatory leukocyte subsets[3–6]. However, dysregulated pro-/anti-inflammatory cytokine responses( ‘cytokine storms’) have been recognized to contribute to severe lung tissue damage, which is typically observed in severe CAP( sCAP)[7, 8]. The macrophage-inducible C-type lectin receptor Mincle( also termed Clec4e or Clecsf9) is a type II transmembrane C-type lectin, which is strongly induced in response to inflammatory stimuli, such as LPS, TNF-α, IL-6 or IFN-γ, and cellular stress[9, 10]. Mincle is expressed on myeloid cells including macrophages, dendritic cells, neutrophils, but also on B cells, but not on NK cells[10–12]. In its transmembrane region, Mincle has a positively charged arginine residue[10] and is associated with an ITAM-containing adaptor molecule Fc receptor common γ chain( FcRγ) through charge-charge interaction to transduce activating signals into the cell[10, 13]. Ligand binding to Mincle leads to phosphorylation of ITAM in the FcRγ chain and downstream recruitment of Syk kinase, followed by a heterotypic aggregation of Card9 with Bcl10 and Malt1. This signaling pathway results in an adaptive Th1 and Th17 cytokine-dominated immune response and triggers production of cytokines such as TNF-α, IL-6, MIP-2, IFN-γ and IL-17[13–15]. Mincle has been identified as sensor for the mycobacterial cell wall component trehalose-6, 6’-dimycolate( TDM, Cord Factor) as well as its synthetic derivative trehalose-6, 6’-dibehenate( TDB)[15, 16]. Molecules with a similar structure like TDM are also reported to be Mincle ligands. For example, human Mincle recognizes glycerol monocorynomycolate derived from mycobacteria[17]. Brartemicin derived from actinomycetes binds to human and bovine Mincle[18]. Except for molecules having a similar structure with TDM, mannosyl fatty acids and β-gentiobiosyl glyceroglycolipids derived from Malassezia spp. are also reported as Mincle ligands[19]. Additionally, Mincle is induced in response to the pathogenic fungi Candida albicans as well as Malassezia spp.[19–21]. We recently demonstrated that Mincle is expressed on AM, newly recruited exudate macrophages and alveolar recruited neutrophils in response to Myocobacterium bovis( M. bovis) BCG infection, where it critically shaped the lung inflammatory response after mycobacterial challenge, and contributed to control of extrapulmonary M. bovis BCG infection in mice[22, 23]. Lung infections with S. pneumoniae usually manifest as lobar pneumonia either or not progressing to invasive pneumococcal disease( IPD), partially depending on the serotypes involved[24]. To mimic these different disease courses, in the current study, we used different serotypes of S. pneumoniae either causing focal pneumonia in the absence of bacteremia( type 19F S. pneumoniae), or invasive serotype 3 S. pneumoniae rapidly progressing to IPD[25, 26]. We here report that Mincle is specifically important to lung protective immunity against lobar pneumonia but not IPD.\nDiscussion:\nThe current study aimed to evaluate the role of C-type lectin Mincle in lung protective immunity against pneumococcal pneumonia in mice, using a focal pneumonia-inducing type 19F strain of S. pneumoniae. We here identified Glc-DAG to be the specific ligand by which S. pneumoniae is recognized by Mincle, which is supported by the following aspects: 1) Glc-DAG satisfies the common signature of Mincle ligand deduced from its known crystal structure[29, 30], 2) the Glc-DAG activity is eliminated in Mincle-deficient cells, demonstrating that Glc-DAG signals exclusively via Mincle, and 3) the observed in vitro activity of Glc-DAG is not due to contaminations such as e. g., endotoxin, as Glc-DAG has no activity on sensitive TLR4 reporter cells. Diacylglycerol-containing glycolipids from S. pneumoniae were previously reported to be presented by CD1d for recognition by natural killer T cells via their invariant T cell receptor[31]. Our study shows for the first time that C-type lectin Mincle expressed by professional phagocytes is another receptor of the innate immune system to recognize the pneumococcus-derived diacylglycerol-containing glycolipid Glc-DAG. In fact, Glc-DAG represents a lipid anchor moiety of the TLR2 ligand lipoteichoic acid( LTA), one of the best characterized pathogen-associated molecular patterns of Gram-positive bacteria, such as S. pneumoniae and S. aureus[32, 33]. Though LTA itself does not act as a Mincle ligand[19], the current data show that Mincle can be activated through LTA fragments, i. e. its lipid anchor moiety Glc-DAG. These data add to our understanding how different moieties of the same ligand may be recognized by different classes of pattern recognition receptors. Most of the currently available literature on the role of Mincle in infectious diseases relates to its role in fungal and mycobacterial infections[13, 15, 16, 21], whereas relatively little knowledge exists regarding its role in bacterial infections. Recently, a protective role of Mincle in bacterial pneumonia caused by Gram-negative Klebsiella pneumoniae was reported, where lack of Mincle resulted in defective neutrophil phagocytosis of K. pneumoniae[34]. In the current model of pneumococcal pneumonia, macrophage and neutrophil phagocytosis as well as ROS production and hence oxidative intracellular killing were not dependent on the presence of Mincle. Moreover, neutrophil-dependent NET formation reported to play a role in host defense against K. pneumoniae[34], according to previous reports, appears to be ineffective in antibacterial responses against S. pneumoniae[35]. More recent reports even demonstrate that NET formation may facilitate outgrowth of type 19F S. pneumoniae in a model of middle ear infection[36]. Based on currently available data, Mincle does not appear to induce direct effectors involved in antibacterial immunity against S. pneumoniae. Rather, we suggest that in pneumococcal pneumonia, the principal function of Mincle as ITAM-coupled receptor is to orchestrate immediate-early pro- and anti-inflammatory responses regulating lung protective immunity against pneumococci. We found that Mincle is not protective in a model of IPD, consistent with earlier reports[28]. In contrast, Mincle was indispensable for protection against focal pneumonia. The observed role for Mincle in protective immunity against focal pneumonia but not IPD is most likely due to the different pathogenicity profiles, and thus clinical disease courses, of the employed non-invasive as compared to invasive S. pneumoniae serotypes used in the current study. Since highly invasive strains of S. pneumoniae such as the currently employed serotype 3( A66. 1) S. pneumoniae are known to cause early bacteremia and IPD in mice within 24 h[26], lung-directed antibacterial immunity mediated by Mincle-expressing phagocytes is expected to be more effective against non-invasive as compared to invasive serotypes of S. pneumoniae rapidly escaping lung innate immune surveillance. This view is supported by our observation in chimeric Mincle KO mice( carrying the hematopoietic system of WT mice) that were found to recruit Mincle-expressing neutrophils to the alveolar air space in response to pneumococcal infection, which was sufficient to normalize antibacterial and cytokine responses after pneumococcal challenge. These data demonstrate a critical role for Mincle expressing leukocytes, most apparently neutrophils, to contribute to regulation of protective immunity against focal pneumonia-causing S. pneumoniae. Collectively, the current study provides novel informations about lung phagocyte recognition of S. pneumoniae by C-type lectin receptor Mincle, which critically contributes to lung protective immunity against this serious lung pathogen. The study may be relevant to the development of novel interventions to enhance lung phagocytic responses against this prototypic lung pathogen in a CLR specific manner.", "role": "user" }, { "content": "Bacterial infections of the lung cause significant morbidity and mortality worldwide . The Gram-positive bacterium Streptococcus pneumoniae is the most prevalent pathogen causing bacterial lung infections in humans . Among the various innate immune receptors by which lung sentinel cells are able to sense bacterial invasion of the lung , relatively little knowledge exists regarding the role of C-type lectins in the process of bacterial recognition by the immune system . In this report , we show that S . pneumoniae is recognized by the C-type lectin receptor Mincle , which is a receptor specialized to bind pathogen-derived carbohydrate structures . In the current study , we identify a specific glycolipid of S . pneumoniae by which the bacterium is recognized by lung sentinel cells . Moreover , we show the critical importance of the described receptor-ligand interaction for survival of pneumococcal pneumonia in mice . Collectively , we identify the Mincle-Glc-DAG axis as an important element of lung host defense against focal pneumococcal pneumonia .", "role": "assistant" } ]

[ { "content": "You will be shown a claim related to the COVID-19 pandemic, 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\".\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract.\n\nFor instance, if the model were given the claim \"the COVID vaccine is safe for healthy adults\", the output might be:\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that the risks of severe COVID vaccine side effects are low for healthy adults.\"]\n}\n\nClaim: A granulocytic signature identifies covid-19 and its genes\n\nAbstract:\nBACKGROUND: An unbiased approach to SARS-CoV-2-induced immune dysregulation has not been undertaken so far.\nWe aimed to identify previously unreported immune markers able to discriminate COVID-19 patients from healthy controls and to predict mild and severe disease.\nMETHODS: An observational, prospective, multicentric study was conducted in patients with confirmed mild/moderate (n = 7) and severe (n = 19) COVID-19.\nImmunophenotyping of whole-blood leukocytes was performed in patients upon hospital ward or intensive care unit admission and in healthy controls (n = 25).\nClinically relevant associations were identified through unsupervised analysis.\nRESULTS: Granulocytic (neutrophil, eosinophil, and basophil) markers were enriched during COVID-19 and discriminated between patients with mild and severe disease.\nIncreased counts of CD15+CD16+ neutrophils, decreased granulocytic expression of integrin CD11b, and Th2-related CRTH2 downregulation in eosinophils and basophils established a COVID-19 signature.\nSeverity was associated with emergence of PD-L1 checkpoint expression in basophils and eosinophils.\nThis granulocytic signature was accompanied by monocyte and lymphocyte immunoparalysis.\nCorrelation with validated clinical scores supported pathophysiological relevance.\nCONCLUSIONS: Phenotypic markers of circulating granulocytes are strong discriminators between infected and uninfected individuals as well as between severity stages.\nCOVID-19 alters the frequency and functional phenotypes of granulocyte subsets with emergence of CRTH2 as a disease biomarker.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"Increased counts of CD15+CD16+ neutrophils, decreased granulocytic expression of integrin CD11b, and Th2-related CRTH2 downregulation in eosinophils and basophils established a COVID-19 signature.\"]}", "role": "assistant" } ]

[ { "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\nMesenchymal stem cells as delivery vehicle of porphyrin loaded nanoparticles: Effective photoinduced in vitro killing of osteosarcoma. Mesenchymal stem cells (MSC) have the unique ability to home and engraft in tumor stroma. These features render them potentially a very useful tool as targeted delivery vehicles which can deliver therapeutic drugs to the tumor stroma. In the present study, we investigate whether fluorescent core-shell PMMA nanoparticles (FNPs) post-loaded with a photosensitizer, namely meso-tetrakis (4-sulfonatophenyl) porphyrin (TPPS) and uploaded by MSC could trigger osteosarcoma (OS) cell death in vitro upon specific photoactivation. In co-culture studies we demonstrate using laser confocal microscopy and time lapse imaging, that only after laser irradiation MSC loaded with photosensitizer-coated fluorescent NPs (TPPS@FNPs) undergo cell death and release reactive oxygen species (ROS) which are sufficient to trigger cell death of all OS cells in the culture. These results encourage further studies aimed at proving the efficacy of this novel tri-component system for PDT applications.", "role": "user" }, { "content": "{\"Chemical\": [\"oxygen\", \"TPPS\", \"meso-tetrakis (4-sulfonatophenyl) porphyrin\", \"porphyrin\"]}", "role": "assistant" } ]

[ { "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:\nMost existing algorithms for depth estimation from single monocular images need large quantities of metric groundtruth depths for supervised learning. We show that relative depth can be an informative cue for metric depth estimation and can be easily obtained from vast stereo videos. Acquiring metric depths from stereo videos is sometimes impracticable due to the absence of camera parameters. In this paper, we propose to improve the performance of metric depth estimation with relative depths collected from stereo movie videos using existing stereo matching algorithm. We introduce a new \"Relative Depth in Stereo\" (RDIS) dataset densely labelled with relative depths. We first pretrain a ResNet model on our RDIS dataset. Then we finetune the model on RGB-D datasets with metric ground-truth depths. During our finetuning, we formulate depth estimation as a classification task. This re-formulation scheme enables us to obtain the confidence of a depth prediction in the form of probability distribution. With this confidence, we propose an information gain loss to make use of the predictions that are close to ground-truth. We evaluate our approach on both indoor and outdoor benchmark RGB-D datasets and achieve state-of-the-art performance.\n\nCited Abstract(s):\n[1]: We propose a framework that infers mid-level visual properties of an image by learning about ordinal relationships. Instead of estimating metric quantities directly, the system proposes pairwise relationship estimates for points in the input image. These sparse probabilistic ordinal measurements are globalized to create a dense output map of continuous metric measurements. Estimating order relationships between pairs of points has several advantages over metric estimation: it solves a simpler problem than metric regression, humans are better at relative judgements, so data collection is easier, ordinal relationships are invariant to monotonic transformations of the data, thereby increasing the robustness of the system and providing qualitatively different information. We demonstrate that this frame-work works well on two important mid-level vision tasks: intrinsic image decomposition and depth from an RGB image. We train two systems with the same architecture on data from these two modalities. We provide an analysis of the resulting models, showing that they learn a number of simple rules to make ordinal decisions. We apply our algorithm to depth estimation, with good results, and intrinsic image decomposition, with state-of-the-art results.\n\n[2]: This paper studies single-image depth perception in the wild, i.e., recovering depth from a single image taken in unconstrained settings. We introduce a new dataset “Depth in the Wild” consisting of images in the wild annotated with relative depth between pairs of random points. We also propose a new algorithm that learns to estimate metric depth using annotations of relative depth. Compared to the state of the art, our algorithm is simpler and performs better. Experiments show that our algorithm, combined with existing RGB-D data and our new relative depth annotations, significantly improves single-image depth perception in the wild.\n\n[3]: The paper is concerned with learning to rank, which is to construct a model or a function for ranking objects. Learning to rank is useful for document retrieval, collaborative filtering, and many other applications. Several methods for learning to rank have been proposed, which take object pairs as 'instances' in learning. We refer to them as the pairwise approach in this paper. Although the pairwise approach offers advantages, it ignores the fact that ranking is a prediction task on list of objects. The paper postulates that learning to rank should adopt the listwise approach in which lists of objects are used as 'instances' in learning. The paper proposes a new probabilistic method for the approach. Specifically it introduces two probability models, respectively referred to as permutation probability and top k probability, to define a listwise loss function for learning. Neural Network and Gradient Descent are then employed as model and algorithm in the learning method. Experimental results on information retrieval show that the proposed listwise approach performs better than the pairwise approach.", "role": "user" }, { "content": "Ordinal relationships and rankings have also been exploited for mid-level vision tasks including depth estimation in recent years. [1] learned the ordinal relationships between pairs of points using a classification loss, then they solved a constrained quadratic optimization problem to map the ordinal estimates to metric values. [2] proposed to learn ordinal relationships through a ranking loss [3] and retrieve the metric depth values by simple normalization. Notably, [2] also proposed a new dataset Depth in the Wild (DIW) consisting of images in the wild labelled with relative depths.", "role": "assistant" } ]

[ { "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: How is spastic diplegia diagnosed?\n\nContext: Spastic diplegia is the most common form of cerebral palsy worldwide.\nHereditary spastic paraplegia (HSP) and spastic diplegia (SD) patients share a strong clinical resemblance. Thus, HSP patients are frequently misdiagnosed with a mild form of SD. Clinical gait analysis (CGA) has been highlighted as a possible tool to support the differential diagnosis of HSP and SD\nThe predominant clinical feature of patients with Hereditary Spastic Paraparesis (HSP) is gait disturbance owing to spasticity and weakness of the lower limbs; the spasticity in early-onset disease (infancy or childhood) often cannot be distinguished from mild form of spastic diplegia (SD)\nThe aim of this study was to quantify the gait strategy in HSP and SD children, focusing on the differences between groups as concerns functional limitation during gait. 9 HSP and 16 SD children were evaluated using Gait Analysis; kinematic and kinetic parameters and EMG pattern during walking were identified and calculated to compare the two gait strategies\nIn contrast to other urea cycle disorders, hyperammonemic encephalopathy is rarely observed in patients with argininemia. Rather, most exhibit an insidious onset and progression of neurologic manifestations, including spastic diplegia.\nWe conclude that argininemia should be considered more frequently in the differential diagnosis of a patient with slowly progressive neurologic manifestations, especially progressive spastic diplegia, even in a population where argininemia was previously unknown\nTo assess the reliability and validity of a newly described classification of sagittal plane alignment in spastic diplegic gait.\nThe objective of this prospective study was the application of proton magnetic resonance spectroscopy in children with spastic diplegia (SD) to determine the metabolite profile of SD children in the left basal ganglia, and to assess the relationship of this profile with motor and mental developmen\nThe aim of this study was to establish the reliability and validity of visual gait assessment in children with spastic diplegia, who were community or household ambulators, using a modified version of the Physicians Rating Scale, known as the Observational Gait Scale (OGS).\nThe aim of this study was to analyse quantitatively the gait of HSP and SD subjects in order to define the gait pattern in HSP and the differences between the two conditions\nThis study shows that GA complements traditional clinical evaluations, making it possible to distinguish, clearly, between motor ability in HSP and in SD patients; the duration of the knee hyperextension during midstance was found to discriminate between the two gait patterns.\nnstruct validity of the In-Hand Manipulation Test (IMT) by assessing the test's ability to discriminate between samples of children with and without known fine motor problems.METHOD: The IMT was administered to 55 children without known fine motor problems and 24 children with spastic diplegia who had mild to moderate fine motor problems.\nA discriminant analysis indicated that IMT total score correctly classified 83.33% of the participants as having or not having fine motor problems.\nCalcaneal gait or deformity can be a significant complication after heel cord lengthening. After heel cord lengthening, 20 children with spastic diplegia were evaluated by gait analysis to define calcaneal gait objectively and describe associated morbidity.\nSignificant differences were found in birth weight, birth head circumference, and the one-minute Apgar score\nIntracranial hemorrhage and neonatal seizures occurred significantly more often in infants with SD\nOn the Movement Assessment of Infants at 4 months of age, the children with hemiplegia and quadriplegia showed significantly higher risk scores than the nonhandicapped group\nAt 1 year of age, however, the Bayley Motor Scale was extremely sensitive in picking up motor deficits in children with all three types of cerebral palsy.\nHip flexion combined with knee extension (leg elevation) and isolated knee movements were not seen in diplegic infants, but were seen in all control preterm infants with a good prognosis, after five and six months corrected age, respectively. The absence of these movements is a useful diagnostic item for spastic diplegia.\nFull body gait analysis may improve diagnostic discrimination between hereditary spastic paraplegia and spastic diplegia\nClinical gait analysis (CGA) has been highlighted as a possible tool to support the differential diagnosis of HSP and SD. Previous analysis has focused on the lower-body but not the upper-body, where numerous compensations during walking occur. The aim of this study was to compare the full-body movements of HSP and SD groups and, in particular, the movement of the upper limbs\nThe study subjects were eight patients with spastic diplegia and eight normal children. Three-dimensional gait analysis was used for the survey. The measured gait variables were the joints of the lower extremity in the sagittal plane, frontal plane, and transverse planes and the maximum and minimum angles of their stance phase and swing phases\nRelationships between spasticity, strength, gait, and the GMFM-66 in persons with spastic diplegia cerebral palsy.\n[Purpose] This study aimed to investigate the effects of Vojta therapy on spatiotemporal gait parameters in children with spastic diplegia. [Methods] The study population consisted of 3 children diagnosed with spastic diplegia.\nThe aim of this study was to explore the physical status and gait patterns of children with spastic diplegia secondary to human immunodeficiency virus encephalopathy (HIVE). A cross-sectional study was conducted on children diagnosed with HIVE and spastic diplegia.\nThe results demonstrated that HSP patients used more spine movement to compensate for lower limb movement alterations, whereas SD patients used their arms for compensation\nTo investigate the association between magnetic resonance imaging (MRI) patterns and motor function, epileptic episodes, and IQ or developmental quotient in patients born at term with spastic diplegia\nTo examine the validity and clinical utility of functional assessments (1-minute walk test, 10-meter walk test, Timed Up&Go [TUG] test, Timed Up and Down Stairs [TUDS]test, sit-to-stand [STS] test, and lateral step-up [LSU]test)\nThese functional assessments (1-minute walk, LSU, and 10-meter walk tests) are simple to administer, quick, low cost, and user-friendly. Although these assessments are not a substitute for the criterion standard (GMFM-88), they may be used for a quick assessment in adolescents with cerebral palsy (levels I-III) either at school or during rehabilitation, especially when time is limited\nThe aim of this study was to evaluate the effect of dynamic bilateral postural stability on balance control and gait parameters in children with cerebral palsy.DESIGN: Thirty children with spastic diplegia (8-10 yrs) were included in this study", "role": "user" }, { "content": "Clinical gait analysis (CGA) has been highlighted as a possible tool to support the differential diagnosis of Hereditary Spastic Paraplegia (HSP) and Spastic Diplegia (SD). Argininaimia should be considered more frequently in the differential diagnosis of a patient with slowly progressive neurologic manifestations, especially progressive spastic diplegia. Gait Analysis (GA) complements traditional clinical evaluations, making it possible to distinguish, clearly, between motor ability in HSP and in SD patients; the duration of the knee hyperextension during midstance was found to discriminate between the two gait patterns.", "role": "assistant" } ]

[ { "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:\nintroduction\n\nContext before the citation:\nThus, over the past few years, along with advances in the use of learning and statistical methods for acquisition of full parsers (Collins, 1997; Charniak, 1997a; Charniak, 1997b; Ratnaparkhi, 1997), significant progress has been made on the use of statistical learning methods to recognize shallow parsing patterns syntactic phrases or words that participate in a syntactic relationship (Church, 1988; Ramshaw and Marcus, 1995; Argamon et al., 1998; Cardie and Pierce, 1998; Munoz et al., 1999; Punyakanok and Roth, 2001; Buchholz et al., 1999; Tjong Kim Sang and Buchholz, 2000). While earlier work in this direction concentrated on manual construction of rules, most of the recent work has been motivated by the observation that shallow syntactic information can be extracted using local information by examining the pattern itself, its nearby context and the local part-of-speech information. to ] [NP only $ 1.8 billion ] [PP in ] [NP September] .\n\nCitation Sentence:\nThus , over the past few years , along with advances in the use of learning and statistical methods for acquisition of full parsers ( Collins , 1997 ; Charniak , 1997a ; Charniak , 1997b ; Ratnaparkhi , 1997 ) , significant progress has been made on the use of statistical learning methods to recognize shallow parsing patterns syntactic phrases or words that participate in a syntactic relationship ( Church , 1988 ; Ramshaw and Marcus , 1995 ; Argamon et al. , 1998 ; Cardie and Pierce , 1998 ; Munoz et al. , 1999 ; Punyakanok and Roth , 2001 ; Buchholz et al. , 1999 ; Tjong Kim Sang and Buchholz , 2000 ) .\n\nContext after the citation:\nResearch on shallow parsing was inspired by psycholinguistics arguments (Gee and Grosjean, 1983) that suggest that in many scenarios (e.g., conversational) full parsing is not a realistic strategy for sentence processing and analysis, and was further motivated by several arguments from a natural language engineering viewpoint. First, it has been noted that in many natural language applications it is sufficient to use shallow parsing information; information such as noun phrases (NPs) and other syntactic sequences have been found useful in many large-scale language processing applications including information extraction and text summarization (Grishman, 1995; Appelt et al., 1993). Second, while training a full parser requires a collection of fully parsed sentences as training corpus, it is possible to train a shallow parser incrementally. If all that is available is a collection of sentences annotated for NPs, it can be used to produce this level of analysis.", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "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:\noroantral communications ( oac ) are rare complications in oral surgery , which recognize upper molars extraction as the most common etiologic factor ( frequencies between 0.31% and 4.7% after the extraction of upper teeth1 ) , followed by maxillary cysts , tumors , trauma , osteoradionecrosis , flap necrosis and dehiscence following implant failure in atrophied maxilla .\nthere is no agreement about the indication of techniques for the treatment of this kind of surgical complication .\nspontaneous healing of 1 to 2 mm openings can occur , while untreated larger defects are connected with the pathogenesis of sinusitis ( 50% of patients after 48 hours - 90% of patients after 2 weeks2 ) .\ntherefore , management of communications between oral cavity and sinus after tooth extraction is recommended to promote closure within 24 hours1 - 3 .\nhowever , in patients with larger oroantral communications and those with a history of sinus disease , surgical closure is often indicated 1,2 .\noroantral fistula ( oaf ) is an epithelialized communication between the oral cavity and the maxillary sinus .\nthe fistula is established for migration of the oral epithelium in the communication , event that happens when the perforation lasts from at least 48 - 72 hours .\nafter some days , the fistula is organized more and more , preventing therefore the spontaneous closing of the perforation3 .\nmany techniques have been described in order to prevent the consequences of a chronical presence of oac , such as buccal flap , palatal rotation - advancement flap and buccal fat pad1,3 - 7 .\nthe problems linked to these techniques are related to the morbidity of the donor site , discomfort for the patient , and no possibility to repeat the same technique after surgical failure .\nthe aim of the present case report is to analyze the healing of oaf with the associated use of an autologous bone graft , integrated by xenologous particulate bone graft , and a non- reabsorbable membrane .\nwe report a 65-years - old female patient who was referred to our attention for the presence of sporadic intraoral drainage in posterior left maxilla .\nthe discomfort was of a few years duration and had its origin following an endodontic treatment of tooth 2.6 provided four years before by her dentist .\nthe radiograph shows many characteristics of oac / oaf ; the apexes of tooth 26 were in extremely close approximation to the maxillary sinus , and an area of periapical rarefaction was evident ( fig .\nthe same tooth was subsequently extracted about five months later by the same practitioner for the persistence of symptomatology .\nthe patient was able to give consent after receiving oral and written information . from the anamnesis , no systemic pathology came out .\nperiodontally , there were no pockets , none of the remaining teeth were percussion positive , and the palpation was negative for loss of periodontal attach and abnormal movements .\nthe radiographic ( fig.2 ) examination did not underline any discontinuity of the sinus floor , but showed radiographic loss of lamina dura at the inferior border of the maxillary sinus over the involved tooth and the localized swelling and thickening of the sinus mucosa ; only close the root of 2.7 a periapical lesion was present ; radiopacity of different degrees was evident in sinus space .\nan explorative surgery was planned in order to evaluate the presence of a possible communication .\none hour before the surgical procedure an antibiotic prophilaxis was performed with amoxicillin and clavulanic acid 2 g. the fixed partial prosthesis was removed and the contiguous mucosa appeared healthy .\na buccal full thickness flap was harvested and the presence of a small oaf was verified .\n4 ) , the surgical procedure was conducted by performing an incision on the bone tissue surrounding the lesion with bone drills and by harvesting a squared wedge bone on the alveolar ridge , in order to avoid the persistence of fibrotic tissue and to permit an adequate bleeding .\nan autologous bone graft was taken by a contiguous cortical site using a trephine with an inner diameter matching the size of the bony defect .\nthe graft was press - fit into the defect and a screw was inserted for internal fixation to increase stability ( fig .\nthe remaining vertical bone defect was filled with a xenogenous bone graft ( bioss ) ( fig 7 ) , associated to an expanded polytetrafluoroethylene titanium - reinforced membrane ( gore - tex ) .\na 3.0 silk detached suture was performed ( fig.8 ) and topic medication with povidone - iodine solution was applied .\na systemic antibiotic prophylaxis with amoxicilline and clavulanic acid 1 g was prescribed after 6 hours from surgery . at 10 days from surgery the suture was removed and the mucosa appeared healthy . at 45 days from surgery , after non - reabsorbable membrane removal ( fig .\n9 ) , the clinical control showed an uneventful healing process with complete elimination of the bone defect .\nthe soft tissues appeared healthy , with normal color , consistence and no bleeding was present in the incision site and around the periodontal pockets of mesial and distal teeth .\nthe radiographic evaluation with computerized tomography demonstrated a complete regeneration of the osseous sinus floor ( fig.11 ) .\nperiapical periodontitis may result in maxillary sinusitis of dental origin with resultant inflammation and thickening of the mucosal lining of the sinus in areas adjacent to the involved teeth4 .\nthis inflammation may be a consequence of overinstrumentation and/or inadvertent injection or extrusion of irrigants , intracanal medicaments , sealers or solid obturation materials .\nfurthermore , endodontic surgery performed on maxillary teeth may result in sinus perforation that develop into oac4 , than into oaf .\nnumerous surgical techniques introduced to close oac and oaf include rotating or advancing local tissues such as the buccal or palatal mucosa , buccal fat pad , submucosal tissue , or tongue tissue6 .\nmost of them rely on mobilizing the tissue and advancing the resultant flap into the defect5 .\nthe closure of oaf is a major problem considering the phlogistic consequences of sinus membrane infection , with the impossibility to perform implant rehabilitation and pre - implant surgical procedures .\nin addition , further implant surgery generally requires more reconstructed bone at the implantation site with a monocortical block .\nthe final result is a vascularized new bone formation which eventually osseo - integrated with the surrounding bone .\nmoreover , experimental studies confirm that autogeneous bone graft assure more predictable results than xenogenous graft , in term of osteo - integration on the receiving site , in order to obtain the closure of oac , such as synthetic bone graft substitutes constitute a valid alternative to flap based techniques7 - 11 .\nthe bone graft techniques for the treatment of moderate to large oac or oaf demonstrate to be innovative , successful and predictable and permit to avoid the clinical collateral effects , like morbidity of the donor site , related to soft tissue flaps .\nthese techniques , similar to the one that we reported , were innovative and successful for treating moderate to large oaf .\noaf should be treated by establishing a physical barrier to prevent infection of the maxillary sinus .\nthe closure of the communications with autologous bone graft substitutes is a valid alternative to flap based techniques . because of the continued need for implant rehabilitation and the necessity of preimplant surgical procedures , such as sinus floor elevation\ntherefore , a method that makes use of autogenous bone grafts harvested from the iliac crest for the closure of the defects has been used 12 .\nthis method causes matting of the mucosae and schneiderian membrane and makes elevation of the sinus membrane without disruption impossible 2 .\nthe principal advantage of the technique described here is the use of autologous bone graft with an expanded polytetrafluoroethylene titanium - reinforced membrane ( gore - tex ) to guide the bone regeneration assures a predictable healing and the possibility of a following implant - prosthetic rehabilitation12 .\nwritten informed consent was obtained from the patients for publication of this study and accompanying images .\na copy of the written consent is available for review by the editor - in - chief of this journal .", "role": "user" }, { "content": "aim : the aim of the current report is to illustrate an alternative technique for the treatment of oroantral fistula ( oaf ) , using an autologous bone graft integrated by xenologous particulate bone graft.background : acute and chronic oroantral communications ( oac , oaf ) can occur as a result of inadequate treatment . in fact surgical procedures into the maxillary posterior area can lead to inadvertent communication with the maxillary sinus . \n spontaneous healing can occur in defects smaller than 3 mm while larger communications should be treated without delay , in order to avoid sinusitis . \n the most used techniques for the treatment of oaf involve buccal flap , palatal rotation - advancement flap , bichat fat pad . \n all these surgical procedures are connected with a significant risk of morbidity of the donor site , infections , avascular flap necrosis , impossibility to repeat the surgical technique after clinical failure , and patient discomfort.case presentation : we report a 65-years - old female patient who came to our attention for the presence of an oaf and was treated using an autologous bone graft integrated by xenologous particulate bone graft . \n an expanded polytetrafluoroethylene titanium - reinforced membrane ( gore - tex ) was used in order to obtain an optimal reconstruction of soft tissues and to assure the preservation of the bone graft from epithelial connection.conclusions : this surgical procedure showed a good stability of the bone grafts , with a complete resolution of the oaf , optimal management of complications , including patient discomfort , and good regeneration of soft tissues.clinical significance : the principal advantage of the use of autologous bone graft with an expanded polytetrafluoroethylene titanium - reinforced membrane ( gore - tex ) to guide the bone regeneration is that it assures a predictable healing and allows a possible following implant - prosthetic rehabilitation .", "role": "assistant" } ]

[ { "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:\nFlunarizine for treatment of partial seizures: results of a concentration-controlled trial.\nAbstract 1:\nThe National Institutes of Health sponsored a randomized, double-blind, multicenter, placebo-controlled trial of flunarizine (FNR) in epileptic patients receiving concomitant phenytoin (PHT) or carbamazepine (CBZ). Because of FNR's long half-life (up to 7 weeks), a parallel rather than crossover design was used. Each patient received an individualized loading dose and maintenance dosage targeted at a 60-ng/ml plasma FNR concentration. Of 93 patients randomized, 92 provided seizure data for the full 25-week treatment period; one placebo-treated patient dropped out for personal reasons. Fifty-four patients received CBZ only, nine received PHT only, and 30 received both CBZ and PHT. Eighty-seven patients had a history of complex partial seizures, and 60 had secondarily generalized seizures. Eight patients discontinued FNR prematurely, all because of adverse neurologic or psychiatric signs or symptoms; depression was the specific cause in three cases. Calculated maintenance dosages, based on single-dose pharmacokinetic profiles, ranged from 7 to 138 mg/day (mean, 40 mg/day). Plasma FNR concentrations generally exceeded the target, with the highest concentrations observed immediately after loading; excluding the first three treatment weeks and all concentrations after a FNR dosage change, the median plasma FNR concentration was 71.7 ng/ml. The percent reduction from baseline seizure rate was statistically greater (p = 0.002) in the FNR-treated group (mean, 24.4%) than in the placebo-treated group (mean, 5.7%).\n\n\nTitle 2:\nNimodipine in refractory epilepsy: a placebo-controlled, add-on study.\nAbstract 2:\nTwenty-two patients (8 male, 14 female) with refractory epilepsy entered a balanced, double-blind, placebo-controlled crossover trial of nimodipine as adjunctive therapy. Treatment periods of 12 weeks (nimodipine 30 mg tds, 60 mg tds, 90 mg tds each for 4 weeks and matched placebo) were followed by wash-out intervals of 4 weeks. Five patients withdrew (2 side-effects, 1 intercurrent illness, 2 non-compliance). Median values (placebo vs. nimodipine) did not vary for total (17 vs. 18), partial (14 vs. 18) and generalised tonic-clonic seizures (2 vs. 5) or seizure days (13 vs. 13). Monthly analysis also failed to uncover any benefit for nimodipine. Side-effects were reported no more frequently with nimodipine than with placebo and pulse and blood pressure did not alter significantly. Antiepileptic drug levels were not affected by nimodipine treatment but circulating nimodipine concentrations were low. In this trial, nimodipine did not fulfil the promise of its success in animal models of epilepsy. Enzyme induction by concurrent antiepileptic therapy may provide an explanation.\n\n\nTitle 3:\nDouble-blind placebo-controlled trial of flunarizine as add-on therapy in epilepsy.\nAbstract 3:\nIn a therapy-resistant epileptic population with partial complex seizures with or without secondary generalization, addition of flunarizine to existing therapy was accompanied by a significant reduction in complex partial and tonic-clonic seizures. This result did not appear to be due to serial effects or changes in the plasma levels of the co-medication. Side effects were rare. The serum flunarizine levels (13.8 ng/ml; range, 3-32.5 ng/ml) were lower than previously reported on a daily dose of 10 mg. This may reflect increased metabolism due to induction of liver enzymes by the co-medication. Given this finding, together with the low incidence of side effects, a further study is required to determine whether higher blood levels would give an improved degree and incidence of seizure reduction.\n\n\nTitle 4:\nFlunarizine as a supplementary medication in refractory childhood epilepsy: a double-blind crossover study.\nAbstract 4:\nWe report a double blinded cross-over study involving Flunarizine versus placebo in the treatment of refractory childhood epilepsy. The patients studied were between the ages of 2 and 18; and were having more than 4 seizures per month not responsive to regular anticonvulsant medications. Of the 34 patients treated, 8 had a 50% decrease in their seizures during the placebo phase, 5 had a 50% decrease during the Flunarizine phase, and 1 patient had a 50% increase in seizures while taking Flunarizine. The remaining 25 patients showed no change in seizure activity in either phase. Patients having partial seizures with secondary generalization tended to do better on Flunarizine than those with other seizure types. Monitoring serum Flunarizine levels showed no significant difference between patients having improved seizure control and those who were unimproved. No significant side effects were noted with this medication, nor were any significant drug interactions noted.\n\n\nTitle 5:\nDouble-blind cross-over placebo controlled study of flunarizine in patients with therapy resistant epilepsy.\nAbstract 5:\nTwenty-five patients with long-standing therapy resistant epilepsy were studied in an eight-month double-blind cross-over add-on trial with a daily dose of 15 mg flunarizine. In five patients the seizure frequency decreased 50% or more. The mean seizure frequency reduction in the patients on flunarizine was 35%. Particularly the control of secondary generalized seizures improved. Flunarizine did not significantly alter the plasma levels of the regular anticonvulsant drugs. Minimal adverse side effects were reported equally in the flunarizine and the placebo group. In three patients depressive symptoms improved and two patients became free of postictal headaches. Flunarizine appears to be a safe adjuvant anticonvulsant.\n\n\nTitle 6:\nDouble-blind placebo-controlled trial of flunarizine as add-on therapy in refractory childhood epilepsy.\nAbstract 6:\nFlunarizine (FLN) has been suggested as an add-on treatment in drug-resistant epilepsy patients. In view of the discordant experiences and of the paucity of controlled trials in children, we studied its effectiveness in 20 patients aged 6 to 18 years (10 males and 10 females), affected by drug-resistant epilepsy. 14 had symptomatic generalized epilepsy (the Lennox-Gastaut syndrome in 10; other forms in 4); 3 had cryptogenic generalized epilepsy (the Lennox-Gastaut syndrome in 2; myoclonic absences epilepsy in 1); 3 had symptomatic partial epilepsy (temporal lobe epilepsy). 7 of them were withdrawn: only 1 because of side effects. An initial four-month baseline pretrial period was followed by two four-month periods of administration of FLN or a placebo, under double blind conditions, in a randomized sequence. Preexisting antiepileptic (AEDs) medication was maintained at a constant dose throughout the study. FLN was administered as drops in a single evening dose of 5 mg (patients less than 10 years) or 10 mg. (patients greater than 10 years). During the pretrial phase, after phase 1 and phase 2, a waking EEG was recorded and blood samples were taken for hematology, hepatic-function tests, and AED serum levels. The evaluation of the activity of FLN was based on the total number of seizures. A 30-60% reduction in seizure frequency was found in 5 out of the 13 patients completing the trial (no changes occurred in the remainders). This result did not appear to be due to changes in the plasma levels of the AEDs. No significant differences were seen in the EEG paroxysmal activity in the three phases of the study. Side effects were rare. The serum FLN levels ranged between 16.4 and 109 ng/ml. It seems that the antiepileptic properties of FLN need further validation, particularly in childhood.\n\n\nTitle 7:\nDouble-blind placebo-controlled trial with flunarizine in therapy-resistant epileptic patients.\nAbstract 7:\nThe anticonvulsant efficacy and side-effect liability of flunarizine (15 mg/day) was investigated in a randomized, double-blind, placebo-controlled, crossover design in 30 outpatients with drug-resistant complex partial seizures. Flunarizine or placebo was added to the preexisting medication and each patient was followed up for 10 months. At the end of the study data from 22 patients were available for evaluation. In patients taking first flunarizine and then placebo, plasma levels of flunarizine were still detectable at the end of the 4 months' placebo phase. In the group of 13 patients starting therapy with placebo, a significant seizure frequency reduction was observed during the flunarizine period in 11 patients, whereas one patient showed no change and seizure frequency increased in another patient. Two patients had a 50% reduction in seizure frequency. Flunarizine was well tolerated and few side effects were noted.\n\n\nTitle 8:\nNifedipine for epilepsy? A double-blind, placebo-controlled trial.\nAbstract 8:\nThe movement of calcium into neurons may be the common denominator for the triggering and propagation of seizure activity. We report results of the first double-blind, placebo-controlled, crossover trial with the dihidropyridine calcium antagonist nifedipine (NFD) as adjuvant therapy in refractory epilepsy. Twenty-two students (12 male, 10 female, age 17-22 years) attending Lingfield Hospital School received NFD retard and matched placebo for 8 weeks in 2 doses (20 and 40 mg b.i.d. each for 4 weeks) with a washout period of 8 weeks between treatment phases. In the 20 students who completed the trial, fewer partial seizures (p less than 0.05) were documented during the first 2 weeks of NFD administration. Similarly, fewer seizure days (p less than 0.05) were reported in the first month of active treatment. This response was not sustained into the second month of the trial. Blind scoring of EEGs suggested a small improvement with NFD (p less than 0.05). More patients reported headache when receiving NFD (p less than 0.02) than placebo, but heart rate and erect and supine blood pressure remained unaffected. Mean maximum NFD concentrations were 13.1 +/- 10.4 ng/ml. A weak correlation was noted between total (p less than 0.05) and partial (p = 0.025) seizure numbers and NFD concentrations following 8 weeks of treatment. This study does not support important anticonvulsant efficacy for NFD as adjuvant therapy for refractory epilepsy at doses appropriate for the treatment of angina or hypertension. Further trials are recommended using higher doses of NFD in less severely affected patients.\n\n\nTitle 9:\nDouble-blind placebo-controlled evaluation of flunarizine as adjunct therapy in epilepsy with complex partial seizures.\nAbstract 9:\nFlunarizine was compared to placebo in a double-blind cross-over trial of 2 16-week treatment periods separated by a 4-week wash-out period. The patients had epilepsy with complex partial seizures with or without secondary generalised seizures. Twenty-nine patients entered the trial, but 7 dropped out. Of the 22 patients completing the trial, 13 were women; the median was 39 years (range 15-58) and the median duration of epilepsy 23 years (range 4-55). There was no statistically significant difference between flunarizine 15 mg daily and placebo as adjunct therapy in total seizure frequency, neuropsychological tests, and patient's preferences. No interactions with concomitant antiepileptic drugs and no laboratory abnormalities were registered.\n\n\nTitle 10:\nFlunarizine as add-on therapy in epilepsy. Crossover study vs placebo.\nAbstract 10:\nThe anticonvulsive effect of flunarizine was studied in a multicenter trial, by means of a randomized, double-blind, single crossover design. The subjects who entered the study were 51 males and 39 females, aged 15 to 73 years. They were epileptic patients who suffered from at least two generalized seizures per month or more than 4 partial seizures per month. The patients were already being treated with major antiepileptic drugs. Flunarizine was administered in a single evening dose of 10 mg/die in patients who weighed less than 70 kg and of 15 mg/die in patients who weighed more 70 kg. Our results show that flunarizine, given as add-on therapy, produced a slight but significant decrease in the number of monthly seizures at the end of a 3-month period, while placebo did not significantly change the seizures frequency.", "role": "user" }, { "content": "Flunarizine may have a weak effect on seizure frequency but had a significant withdrawal rate, probably due to adverse effects, and should not be recommended for use as an add-on treatment. Similarly, there is no convincing evidence to support the use of nifedipine or nimodipine as add-on treatments for epilepsy.", "role": "assistant" } ]

[ { "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: Low-Power Neuromorphic Hardware for Signal Processing Applications: A review of architectural and system-level design approaches \nChapter Title: BrainScaleS-1 \n1. Abstract of Cited Paper (BIB001): Neuromorphic information processing systems offer the potential to overcome imminent problems of state-of-the-art computers, in particular the energy efficiency problem, the device reliability problem and the software complexity problem. This paper starts with a short overview of state-of-the-art neuromorphic hardware implementations and their applications. It then describes the time-accelerated mixed-signal approach of the BrainScaleS project in some detail. \n2. Abstract of Cited Paper (BIB002): We present results from a new approach to learning and plasticity in neuromorphic hardware systems: to enable flexibility in implementable learning mechanisms while keeping high efficiency associated with neuromorphic implementations, we combine a general-purpose processor with full-custom analog elements. This processor is operating in parallel with a fully parallel neuromorphic system consisting of an array of synapses connected to analog, continuous time neuron circuits. Novel analog correlation sensor circuits process spike events for each synapse in parallel and in real-time. The processor uses this pre-processing to compute new weights possibly using additional information following its program. Therefore, learning rules can be defined in software giving a large degree of flexibility. Synapses realize correlation detection geared towards SpikeTiming Dependent Plasticity (STDP) as central computational primitive in the analog domain. Operating at a speed-up factor of 1000 compared to biological time-scale, we measure timeconstants from tens to hundreds of micro-seconds. We analyze variability across multiple chips and demonstrate learning using a multiplicative STDP rule. We conclude, that the presented approach will enable flexible and efficient learning as a platform for neuroscientific research and technological applications.\n\nLiterature Review:", "role": "user" }, { "content": "The BrainScaleS system is a mixed-signal platform that combines analog neuron circuits with digital communication BIB002 . Its unique feature is a speedup factor of 10 3 -10 4 for spiking network emulations, meaning that a network model running for 1 s of wall time on the hardware emulates up to 10,000 s of biological simulation time. BrainScaleS supports the adaptive exponential I&F model that can be parameterized to exhibit diverse firing patterns. The BrainScaleS system's smallest unit of silicon is the High-Input Count Analog Neuronal Network (HiCANN) chip BIB001 . The number of neurons per chip can be configured within wide limits, following a tradeoff between the number of input synapses and the number of neurons. A single chip supports a maximum of 512 spiking neurons and up to about 14,000 synapses per neuron. Larger networks are supported by wafer-scale integration of HiCANN chips, which are wired directly on the silicon wafer without cutting it into discrete elements. A single wafer supports 4 10 7 # synapses and up to 180,000 neurons. Prototypes of the next BrainScaleS generation support programmable plasticity via general-purpose processors embedded on the die alongside the neuromorphic circuitry BIB003 . These processors have access to dedicated sensors at the synapses that measure the time interval between pre-and postsynaptic spikes. Arbitrary functions can be defined that compute updates to the synaptic weights from this information. This enables highly flexible learning rules to be implemented on BrainScaleS, including reward-based learning. BrainScaleS, like SpiNNaker, leverages the PyNN application programming interface (http://neuralensemble.org/PyNN) to allow the user to specify spiking networks for emulation on the hardware.", "role": "assistant" } ]

[ { "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: [\"AnatomicalEntity\"].\n\nPlease return the output as a JSON object of the format: {\"AnatomicalEntity\": [\"tumor cells\", ...]}. 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 an empty JSON array \"[]\".\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nPhonology: a review and proposals from a connectionist perspective.\nA parallel distributed processing (PDP) model of phonological processing is developed, including components to support repetition, auditory processing, comprehension, and language production. From the performance of the PDP reading model of Plaut, McClelland, Seidenberg, and Patterson (1996), it is inferred that the acoustic-articulatory motor pattern associator that supports repetition provides the basis for phonological sequence knowledge. From the observation that many patients make phonemic paraphasic errors in language production, as in repetition, it is argued that there must be a direct link between distributed concept representations (lexical semantic knowledge) and this network representation of sequence knowledge. In this way, both lexical semantic and phonotactic constraints are brought to bear on language production. The literature on phonological function in normal subjects (slip-of-the-tongue corpora) and in patients with aphasia is critically reviewed from this perspective. The relationship between acoustic and articulatory motor representations in the process of phonetic perception is considered. Repetition and reproduction conduction aphasia are reviewed in detail and extended consideration is given to the representation of auditory verbal short-term memory in the model. Finally, the PDP model is reconciled with information processing models of phonological processing, including that of Lichtheim, and with current knowledge of the anatomic localization of phonological processing. Although no simulations of the model were run, a number of simulation studies are proposed.", "role": "user" }, { "content": "{\"AnatomicalEntity\": []}", "role": "assistant" } ]

[ { "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:\nAbstract Community structure is one of the most prominent features of complex networks. Community structure detection is of great importance to provide insights into the network structure and functionalities. Most proposals focus on static networks. However, finding communities in a dynamic network is even more challenging, especially when communities overlap with each other. In this article, we present an online algorithm, called OLCPM, based on clique percolation and label propagation methods. OLCPM can detect overlapping communities and works on temporal networks with a fine granularity. By locally updating the community structure, OLCPM delivers significant improvement in running time compared with previous clique percolation techniques. The experimental results on both synthetic and real-world networks illustrate the effectiveness of the method.\n\nCited Abstract(s):\n[1]: Community discovery has emerged during the last decade as one of the most challenging problems in social network analysis. Many algorithms have been proposed to find communities on static networks, i.e. networks which do not change in time. However, social networks are dynamic realities (e.g. call graphs, online social networks): in such scenarios static community discovery fails to identify a partition of the graph that is semantically consistent with the temporal information expressed by the data. In this work we propose Tiles, an algorithm that extracts overlapping communities and tracks their evolution in time following an online iterative procedure. Our algorithm operates following a domino effect strategy, dynamically recomputing nodes community memberships whenever a new interaction takes place. We compare Tiles with state-of-the-art community detection algorithms on both synthetic and real world networks having annotated community structure: our experiments show that the proposed approach is able to guarantee lower execution times and better correspondence with the ground truth communities than its competitors. Moreover, we illustrate the specifics of the proposed approach by discussing the properties of identified communities it is able to identify.", "role": "user" }, { "content": "[1] defined TILES, which also proceeds in a streaming fashion, i.e., dynamics of the network is described as flows of interactions (also called perturbations) between users where nodes and edges can be created or removed over time. Each perturbation is considered as a fall of domino tile: every time a new interaction appears in the network, TILES updates the community locally and then propagates the changes to the node surroundings to adjust the neighbors' community memberships.", "role": "assistant" } ]

[ { "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\nA double-blind placebo controlled trial of Ginkgo biloba added to risperidone in patients with autistic disorders . Ginkgo biloba has been reported to affect the neurotransmitter system and to have antioxidant properties that could impact the pathogenesis of Autism Spectrum Disorder . Based on these studies , we decided to assess the effectiveness of Ginkgo biloba extract ( Ginko T.D. , Tolidaru , Iran ) as an adjunctive agent to risperidone in the treatment of autism . Forty-seven outpatients with a DSM-IV-TR diagnosis of autism ages between 4 and 12 years were assigned to this double blinded clinical trial and were randomly divided into two groups . One group received risperidone plus Ginko T.D and the other received risperidone plus placebo . The dose of risperidone was 1-3 mg/day and the dose of Ginko T.D . was 80 mg/day for patients under 30 kg and 120 mg/day for patients above 30 kg . Patients were assessed using Aberrant Behavior Checklist-Community ( ABC-C ) rating scale and the side effect check list every 2 weeks until the endpoint . None of the 5 subscales of ABC-C rating scale showed significant differences between the two groups . Incidents of side effects were not significantly different between the two groups . Adding Ginkgo biloba to risperidone did not affect the treatment outcome of ADs . Nevertheless , further observations are needed to confirm this result .", "role": "user" }, { "content": "{\"Intervention\": [\"Ginko T.D .\", \"risperidone plus Ginko T.D and the\", \"Ginkgo biloba to risperidone\", \"Ginkgo biloba\", \"risperidone\", \"placebo\"], \"Outcome\": [\"side effect check list\", \"Incidents of side effects\", \"ABC-C rating scale\", \"and the\", \"Aberrant Behavior Checklist-Community ( ABC-C ) rating scale\"], \"Participant\": [\"patients under 30 kg\", \"patients above 30 kg .\", \"ages between 4 and 12 years\", \"DSM-IV-TR diagnosis of autism\", \"Autism Spectrum Disorder .\", \"patients with autistic disorders .\", \"Forty-seven\"]}", "role": "assistant" } ]

[ { "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: Security and Privacy in Location-Based Services for Vehicular and Mobile Communications: An Overview, Challenges, and Countermeasures \nChapter Title: 1) Mix-Zones Approaches in Vehicular Networks: \n1. Abstract of Cited Paper (BIB001): Vehicular Networks (VNs) seek to provide, among other applications, safer driving conditions. To do so, vehicles need to periodically broadcast safety messages providing preciseposition information ... \n2. Abstract of Cited Paper (BIB002): Vehicular ad hoc networks (VANETs) and vehicular communications are considered a milestone in improving the safety, efficiency and convenience in transportation. Vehicular ad hoc networks and many vehicular applications rely on periodic broadcast of the vehicles' location. For example, the location of vehicles can be used for detecting and avoiding collisions or geographical routing of data to disseminate warning messages. At the same time, this information can be used to track the users' whereabouts. Protecting the location privacy of the users of VANETs is important, because lack of privacy may hinder the broad acceptance of this technology. Frequently changing pseudonyms are commonly accepted as a solution to protect the privacy in VANETs. In this paper, we discuss their effectiveness and different methods to change pseudonyms. We introduce the context mix model that can be used to describe pseudonym change algorithms. Further, we asses in which situations, i.e. mix contexts, a pseudonym change is most effective and improves the privacy in vehicular environments. \n3. Abstract of Cited Paper (BIB003): Receiver-location privacy is an important security requirement in privacy-preserving Vehicular Ad hoc Networks (VANETs), yet the unavailable receiver's location information makes many existing packet forwarding protocols inefficient in VANETs. To tackle this challenging issue, in this paper, we propose an efficient social-tier-assisted packet forwarding protocol, called STAP, for achieving receiver-location privacy preservation in VANETs. Specifically, by observing the phenomena that vehicles often visit some social spots, such as well-traversed shopping malls and busy intersections in a city environment, we deploy storage-rich Roadside Units (RSUs) at social spots and form a virtual social tier with them. Then, without knowing the receiver's exact location information, a packet can be first forwarded and disseminated in the social tier. Later, once the receiver visits one of social spots, it can successfully receive the packet. Detailed security analysis shows that the proposed STAP protocol can protect the receiver's location privacy against an active global adversary, and achieve vehicle's conditional privacy preservation as well. In addition, performance evaluation via extensive simulations demonstrates its efficiency in terms of high delivery ratio and low average delay. \n4. Abstract of Cited Paper (BIB004): Location privacy is one of the Quality of Privacies (QoP) in vehicular ad hoc network (VANET) and imperative for the VANET's full flourish. Frequent pseudonym changing can provide a promising solution to achieve location privacy, however if the pseudonyms are changed in an improper occasion, the solution is ineffective. In this paper, to improve the effectiveness of this kind of solution, we first introduce the social spot where many vehicles could aggregate, e.g., a road intersection when the traffic light is red or a free parking lot near a shopping mall. We then propose a social spot based pseudonyms changing technique to achieve the location privacy. By taking the anonymity set size as the privacy metric, we develop two anonymity analytic models to quantitatively investigate the location privacy achieved in the technique. The analytical results show that better location privacy can be achieved when a vehicle changes its pseudonyms at some highly social spots, and as a result, the proposed models can be used to assist vehicles to change their pseudonyms for better location privacy at the right moment and place. \n5. Abstract of Cited Paper (BIB005): As a prime target of the quality of privacy in vehicular ad hoc networks (VANETs), location privacy is imperative for VANETs to fully flourish. Although frequent pseudonym changing provides a promising solution for location privacy in VANETs, if the pseudonyms are changed in an improper time or location, such a solution may become invalid. To cope with the issue, in this paper, we present an effective pseudonym changing at social spots (PCS) strategy to achieve the provable location privacy. In particular, we first introduce the social spots where several vehicles may gather, e.g., a road intersection when the traffic light turns red or a free parking lot near a shopping mall. By taking the anonymity set size as the location privacy metric, we then develop two anonymity set analytic models to quantitatively investigate the location privacy that is achieved by the PCS strategy. In addition, we use game-theoretic techniques to prove the feasibility of the PCS strategy in practice. Extensive performance evaluations are conducted to demonstrate that better location privacy can be achieved when a vehicle changes its pseudonyms at some highly social spots and that the proposed PCS strategy can assist vehicles to intelligently change their pseudonyms at the right moment and place. \n6. Abstract of Cited Paper (BIB006): Vehicular social network (VSN) is envisioned to serve as an essential data sensing, exchanging and processing platform for the future Intelligent Transportation Systems. In this paper, we aim to address the location privacy issue in VSNs. In traditional pseudonym-based solutions, the privacy-preserving strength is mainly dependent on the number of vehicles meeting at the same occasion. We notice that an individual vehicle actually has many chances to meet several other vehicles. In most meeting occasions, there are only few vehicles appearing concurrently. Motivated by these observations, we propose a new privacy-preserving scheme, called MixGroup, which is capable of efficiently exploiting the sparse meeting opportunities for pseudonym changing. By integrating the group signature mechanism, MixGroup constructs extended pseudonym-changing regions, in which vehicles are allowed to successively exchange their pseudonyms. As a consequence, for the tracking adversary, the uncertainty of pseudonym mixture is accumulatively enlarged, and therefore location privacy preservation is considerably improved. We carry out simulations to verify the performance of MixGroup. Results indicate that MixGroup significantly outperforms the existing schemes. In addition, MixGroup is able to achieve favorable performance even in low traffic conditions.\n\nLiterature Review:", "role": "user" }, { "content": "Mix-zones enhance location privacy using anonymous communication zones. These zones are mostly road intersections where the speed and direction of a vehicle is likely to change. When a vehicle enters a mix-zone, it stops sending messages and updates its pseudonym. The effect of changing pseudonyms frequently in location privacy is examined by Buttyán et al. BIB001 . In this approach, traffic is generated on nontrivial road maps with realistic parameters. The authors assumed that the antennas are positioned by attackers in the network to overhear communication. In their analysis of the effectiveness of mix-zones, they conclude that the optimal frequency of pseudonym change depends on the attributes of the mix-zones such as the location, size and the number of entry points. In BIB002 , mix-zones are created using cryptographic techniques CMIX at road intersections within the broadcast distance of the RSUs. The CMIX protocol distributes symmetric keys using traditional asymmetric cryptography for the establishment of the cryptographic mix-zones. In the CMIX-zone, all broadcast messages by vehicles are encrypted with the symmetric key distributed by the RSU. The authors claim that CMIX makes it difficult for an attacker to link the identity of a vehicle since the same key is used by all vehicles. A context mix model is introduced in and BIB003 to protect location privacy in vehicular networks. They argue that even pseudonyms are changed at random intervals, several approaches can be used by the attacker to identify the nodes. They describe the mix-zones in as mix-context situations and include the use of context information such as speed, direction and number of vehicles to initiate a pseudonym change. To protect vehicles from location tracking, they define a threshold for the minimum entropy to identify the best opportunity for a pseudonym change. The user or the application where the pseudonym change is triggered is used to define the minimum entropy. To achieve receiver-location privacy in VANETs, Lin et al. BIB004 proposed a social-tier-assisted message forwarding protocol (STAP). STAP protects receiver location privacy from active global attackers by disseminating messages to social tiers. Similar to the works in BIB005 and BIB006 , they use social spots to observe busy intersections in a city environment. The social tier is a virtual tier formed by social spots. RSUs are deployed at social spots and a virtual tier is formed with them without knowledge of the location of the receiver. When the receiver enters one of the social spots, it can successfully receive the message that was disseminated to the social tier. The receiver holds the family of the pseudo-IDs which are unlinkable and the pseudo-IDs are repeatedly used in the mutual authentication between the RSUs and the receivers at social spots. Lu et al. BIB005 , BIB006 proposed changing of pseudonym at social spots (PCS) as a strategy to achieve high location privacy. Vehicles temporarily gather at social spots such as free parking lots that may be close to a shopping mall or at road intersections when the traffic light turns red. They state that a social spot becomes a mix-zone if pseudonyms are changed by all the vehicles before leaving that spot. An indistinguishable information is broadcast as safety message which shows the location of the vehicle as a social spot at a velocity of 0 with an unlinkable pseudonym. They show that when pseudonyms are changed by all the vehicles simultaneously, the high density makes it difficult for attackers to track the vehicles. However, pseudonym changing at social spots does not provide sufficient privacy protection when the vehicle density is low. In , a user-centric game-theoretic mix-zone approach is introduced to measure the evolution of location privacy over time and evaluates its behavior in mobile, vehicular and delay tolerant networks. They argue that even though the cost of location privacy is reduced by selfish nodes, it can also threaten the efficiency achieved by multiple pseudonyms in noncooperative scenarios. They carry out an analysis on static games using a complete information to get pure and mixed Nash equilibria. Using a Bayesian approach, they study an incomplete information scenario where nodes have no complete knowledge of the pay-offs of neighboring nodes. They look for a symmetric equilibrium where all the nodes cooperate with the same probability and analyze a dynamic version of the game showing how it copes with uncertainty. The pseudonym changes are coordinated by Pseudo-game protocols which are designed to implement pseudonym change strategies. Yu et al. BIB007 proposed a MixGroup scheme for location privacy. Based on sporadic observations, they exploit meeting opportunities to change pseudonyms and improve location privacy. Observations are made from real vehicle traces based on social spots and sporadic observations. MixGroup is used to construct an extended pseudonym group region where vehicles can change their accumulated pseudonyms. Each group has a group leader and a group identifier. When a vehicle enters a group, the group leader will assign a group ID with a certificate and a private key to the new vehicle after authentication. The group ID, certificate, and the private key are used for changing pseudonyms and broadcasting safety messages. An entropy-optimal negotiation procedure is used to facilitate the process of exchanging pseudonyms among vehicles. They quantitatively measure the risk and benefits associated with the pseudonym exchange using a predefined pseudonym entropy.", "role": "assistant" } ]

[ { "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\nNovel 5-(benzyloxy)pyridin-2(1H)-one derivatives as potent c-Met inhibitors. A series of novel 5-(benzyloxy)pyridin-2(1H)-ones were designed, synthesized and biologically evaluated for c-Met inhibition. Various amides and benzoimidazoles at C-3 position were investigated. A potent compound 12b with a c-Met IC50 of 12nM was identified. This compound exhibited potent inhibition of EBC-1 cell associated with c-Met constitutive activation and showed high selectivity for c-Met than other tested 11 kinases. The binding model 12b with c-Met was disclosed by docking analysis.", "role": "user" }, { "content": "{\"Chemical\": [\"5-(benzyloxy)pyridin-2(1H)-one\", \"5-(benzyloxy)pyridin-2(1H)-ones\", \"benzoimidazoles\", \"amides\"]}", "role": "assistant" } ]

[ { "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: [\"Gene\"].\n\nPlease return the output as a JSON object of the format: {\"Gene\": [\"IGF\", ...]}. 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\nRenal pro-apoptotic proteins are reduced by growth hormone resistance but not by visceral fat removal. Growth hormone (GH) receptor knockout (GHRKO) mice are highly insulin sensitive and long-lived. Surgical visceral fat removal (VFR) improves insulin signaling in normal mice and rats and extends longevity in rats. We have previously demonstrated decreased expression of certain pro-apoptotic genes in kidneys of GHRKO mice and suggested that this could contribute to the increased longevity of these animals. The aim of the present study was to examine the level of the following proteins: caspase-3, caspase-9, caspase-8, bax, bad, phospho-bad, bcl-2, Smac/DIABLO, Apaf-1, phospho-p53 (pp53) and cytochrome c in male GHRKO and normal (N) mice subjected to VFR or sham surgery, at approximately six months of age. The kidneys were collected two months after VFR. Caspase-3, caspase-8, bax, bad, Smac/DIABLO, Apaf-1 and pp53 levels were decreased in GHRKO mice as compared to N animals. VFR did not change the level of any of the examined proteins. The decreased renal levels of pro-apoptotic proteins could contribute to the extended life-span caused by targeted disruption of the GH receptor gene but are apparently not involved in mediating the effects of VFR.", "role": "user" }, { "content": "{\"Gene\": [\"caspase-3\", \"growth hormone\", \"insulin\", \"phospho-bad\", \"caspase-9\", \"Growth hormone (GH) receptor\", \"Apaf-1\", \"bad\", \"Caspase-3\", \"DIABLO\", \"bcl-2\", \"pro-apoptotic genes\", \"GH receptor\", \"pro-apoptotic proteins\", \"Smac\", \"phospho-p53\", \"GHR\", \"caspase-8\", \"bax\", \"p53\", \"pp53\", \"cytochrome c\"]}", "role": "assistant" } ]

[ { "content": "You will be shown inclusion or exclusion criteria for a clinical trial. Given these criteria, your task is to extract all unique entities of the following types: [\"Person\", \"Condition\", \"Value\", \"ReferencePoint\", \"Temporal\", \"Qualifier\", \"Observation\", \"Visit\", \"Measurement\", \"Mood\", \"Device\", \"Scope\", \"Negation\", \"Drug\", \"Procedure\", \"Multiplier\"].\n\nPlease return the output as a JSON object of the format: {\"Condition\": [\"breast cancer\", ...], \"Device\": [\"ports\", ...], \"Drug\": [\"Atenolol\", ...], \"Measurement\": [\"blood pressure\", ...], \"Mood\": [\"suspected\", ...], \"Multiplier\": [\"more than two\", ...], \"Negation\": [\"no\", ...], \"Observation\": [\"history\", ...], \"Person\": [\"male\", ...], \"Procedure\": [\"surgery\", ...], \"Qualifier\": [\"severe\", ...], \"ReferencePoint\": [\"enrollment\", ...], \"Scope\": [\"infection\", ...], \"Temporal\": [\"one day\", ...], \"Value\": [\"50%\", ...], \"Visit\": [\"ICU\", ...]}. 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\nDiagnosis of asthma", "role": "user" }, { "content": "{\"Condition\": [\"asthma\"], \"Device\": [], \"Drug\": [], \"Measurement\": [], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [], \"Procedure\": [], \"Qualifier\": [], \"ReferencePoint\": [], \"Scope\": [], \"Temporal\": [], \"Value\": [], \"Visit\": []}", "role": "assistant" } ]

[ { "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: In which yeast chromosome does the rDNA cluster reside?\n\nContext: Chromosome XII context is important for rDNA function in yeast\nThe rDNA cluster in Saccharomyces cerevisiae is located 450 kb from the left end and 610 kb from the right end of chromosome XII and consists of approximately 150 tandemly repeated copies of a 9.1 kb rDNA unit\nTo explore the biological significance of this specific chromosomal context, chromosome XII was split at both sides of the rDNA cluster and strains harboring deleted variants of chromosome XII consisting of 450 kb, 1500 kb (rDNA cluster only) and 610 kb were created. In the strain harboring the 1500 kb variant of chromosome XII consisting solely of rDNA, the size of the rDNA cluster was found to decrease as a result of a decrease in rDNA copy number\nThese observations suggest that the context of chromosome XII plays an important role in maintaining a constant rDNA copy number and in physiological processes related to rDNA function in S.cerevisiae.\nNotably, strains harboring the 450 kb chromosome XII variant and/or the 1500 kb variant consisting solely of rDNA had shorter life spans than wild type and also accumulated extrachromosomal rDNA circles\nCondensation of a unique region of chromosome XVI and the highly repetitive ribosomal DNA (rDNA) cluster from chromosome XII were also examined in budding yeast.\nCondensation of a unique region of chromosome XVI and the highly repetitive ribosomal DNA (rDNA) cluster from chromosome XII were also examined in budding yeast.\nTo explore the biological significance of this specific chromosomal context, chromosome XII was split at both sides of the rDNA cluster and strains harboring deleted variants of chromosome XII consisting of 450 kb, 1500 kb (rDNA cluster only) and 610 kb were created.\nIn the strain harboring the 1500 kb variant of chromosome XII consisting solely of rDNA, the size of the rDNA cluster was found to decrease as a result of a decrease in rDNA copy number.\nApart from chromosome XII, which contains the 1-2 Mb rDNA cluster, chromosome IV is the longest S. cerevisiae chromosome.\nWe studied the largest yeast chromosome XII, which contains the rDNA locus, and we investigated its instability using cell cycle checkpoint-, DNA damage- and antioxidative defence-deficient, and lifespan-deregulated yeast mutant strains.\nChromosome XII context is important for rDNA function in yeast.\nCondensation of a unique region of chromosome XVI and the highly repetitive ribosomal DNA (rDNA) cluster from chromosome XII were also examined in budding yeast.\nClonal size-variation of rDNA cluster region on chromosome XII of Saccharomyces cerevisiae.\nUsing pulsed-field gel electrophoresis (PFGE), we have demonstrated clonal variation in the size of chromosome XII in a diploid strain of Saccharomyces cerevisiae X2180-2D.\nThe sizes of the two chromosome XII homologues were very different: 2600 (L-type) and 1450 kb (S-type).\nThe size variation was shown to be derived from size changes in the rDNA cluster region, which is present in chromosome XII, by digesting the chromosome with XhoI, whose cutting site is not present in a rDNA repeat unit, and hybridizing to rDNA probes.\nApart from chromosome XII, which contains the 1-2 Mb rDNA cluster, chromosome IV is the longest S. cerevisiae chromosome.\nCondensation of a unique region of chromosome XVI and the highly repetitive ribosomal DNA (rDNA) cluster from chromosome XII were also examined in budding yeast.\nChromosome XII context is important for rDNA function in yeast.", "role": "user" }, { "content": "chromosome XII", "role": "assistant" } ]

[ { "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\nTobacco smoke induces coordinate activation of HSF and inhibition of NFkappaB in human monocytes: effects on TNFalpha release. Tobacco smoke (TS) exposure is a major risk factor for human disease, and macrophages of healthy smokers have a depressed capacity to release cytokines, including tumor necrosis factor (TNF) alpha. TS induces the synthesis of heat shock (HS) / stress proteins (HSP), and, in particular, of Hsp70. We determined whether Hsp70 induction by TS was mediated by the activation of the HS transcription factor, HSF. HSF activation has been shown to inhibit NFkappaB. Thus, we also determined the effects of TS on NFkappaB. U937 cells and human peripheral blood monocytes were exposed to TS, binding activities of the respective transcription factors were analyzed, and Hsp70 expression and TNFalpha release were determined in parallel. TS activated HSF, which was associated with Hsp70 overexpression and inhibition of NFkappaB binding activity and TNFalpha release. The altered cytokine profile observed in smokers may relate to an HSF / Hsp70-mediated inhibition of NFkappaB activity. Copyright 1998 Academic Press.", "role": "user" }, { "content": "{\"CellLine\": [\"U937 cells\"], \"CellType\": [\"human peripheral blood monocytes\", \"macrophages\", \"human monocytes\"], \"DNA\": [], \"Protein\": [\"cytokines\", \"HS transcription factor\", \"Hsp70\", \"transcription factors\", \"HSP\", \"HSF\", \"tumor necrosis factor (TNF) alpha\", \"TNFalpha\", \"the HS transcription factor\", \"cytokine profile\", \"NFkappaB\", \"heat shock (HS) / stress proteins\"], \"RNA\": []}", "role": "assistant" } ]

[ { "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:\nExpanding on a suggestion of Michiels (1982), we classify verbs as Subject Equi, Object Equi, Subject Raising or Object Raising for each sense which has a predicate complement code associated with it. In these situations the parser can use the semantic type of the verb to compute this relationship. In any subcategorisation frame which involves a predicate complement there will be a non-transparent relationship between the superficial syntactic form and the underlying logical relations in the sentence.\n\nCitation Sentence:\nExpanding on a suggestion of Michiels ( 1982 ) , we classify verbs as Subject Equi , Object Equi , Subject Raising or Object Raising for each sense which has a predicate complement code associated with it .\n\nContext after the citation:\nThese terms, which derive from Transformational Grammar, are used as convenient labels for what we regard as a semantic distinction; the actual output of the program is a specification of the mapping from superficial syntactic form to an underlying logical representation. For example, labelling believe(3) (Type 2 ORaising) indicates that this is a two place predicate and that, if believe(3) occurs with a syntactic direct object, as in (1) John believes the Earth to be round it will function as the logical subject of the predicate complement.", "role": "user" }, { "content": "Extends", "role": "assistant" } ]

[ { "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\nComparison of non-invasive methods for the assessment of haemodynamic drug effects in healthy male and female volunteers : sex differences in cardiovascular responsiveness . 1 . The study was performed to determine the sensitivity and short-term and day-to-day variability of a novel technique based on laser interferometry of ocular fundus pulsations and of non-invasive methods for the quantification of haemodynamic drug effects . An additional aim was to assess sex differences in haemodynamic responsiveness to cardiovascular drugs in male and female healthy volunteers . 2 . Ten males and nine females ( age range 20-33 years ) were studied in a double-blind , randomized , cross-over trial . Simultaneous measurements from systemic haemodynamics , laser interferometry of ocular fundus pulsations , systolic time intervals from mechanocardiography , a/b ratio from oxymetric fingerplethysmography and Doppler sonography of the radial artery were used to describe the haemodynamic effects of cumulative , stepwise increasing intravenous doses of phenylephrine , isoprenaline , sodium nitroprusside and of placebo . 3 . Laser interferometry detected the isoprenaline-effects at the lowest dose level of 0.1 micrograms min-1 with a high signal-to-noise ratio . The reproducibility of measurements under baseline was high , no changes were observed after systemically effective doses of phenylephrine or sodium nitroprusside . Systolic time intervals were sensitive and specific for isoprenaline-induced effects , PEP and QS2c-measurements had high reproducibility . Fingerplethysmography proved a sensitive measurement for the detection of the vasodilating effects of sodium nitroprusside , but was not specific , and showed low reproducibility . Measurements from Doppler sonography had lower reproducibility and sensitivity compared with the other applied methods . 4 . There was a significant sex difference for several of the haemodynamic parameters under baseline conditions ; however , the responsiveness to the drugs under study was not different , when drug effects were expressed as % -change from the baseline . 5 . Laser interferometry is a valuable non-invasive , highly sensitive and specific approach for the detection of pulse pressure changes . A battery of non-invasive tests appears useful for the characterization of cardiovascular drugs . Gender differences may not pose a relevant problem for the study of acute haemodynamic effects of cardiovascular drugs .", "role": "user" }, { "content": "{\"Intervention\": [\"Laser interferometry\", \"intravenous doses of phenylephrine\", \"sodium nitroprusside\", \"mechanocardiography\", \"haemodynamic\", \"oxymetric fingerplethysmography\", \"placebo\", \"haemodynamics\", \"isoprenaline\", \"laser interferometry of ocular fundus pulsations\", \"non-invasive methods\", \"Doppler sonography\"], \"Outcome\": [\"systemic haemodynamics , laser interferometry of ocular fundus pulsations , systolic time intervals from mechanocardiography , a/b ratio from oxymetric fingerplethysmography and Doppler sonography of the radial artery\", \"reproducibility and sensitivity\"], \"Participant\": [\"males\", \"Ten\", \"nine\", \"females\"]}", "role": "assistant" } ]

[ { "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:\nEfficacy of metoclopramide as an adjunct to duodenal placement of small-bore feeding tubes: a randomized, placebo-controlled, double-blind study.\nAbstract 1:\nWe examined whether metoclopramide would improve the success rate of transpyloric intubation of a weighted Corpak feeding tube when fluoroscopic guidance is not used. Seventy patients were randomized in a prospective, double-blind fashion to receive either placebo (n = 35) or metoclopramide, 10 mg (n = 35) parenterally, administered immediately after the feeding tube was inserted. Tube location was determined independently by two observers who examined radiographs obtained after barium was instilled via the tube. There was no significant increase in the success rate of duodenal intubation in the total group following metoclopramide, 60%, compared to placebo, 49%. However, analysis of subgroups among the placebo-treated patients revealed that diabetes mellitus, but not other medical conditions, decreased the success rate for duodenal intubation, 20 vs 60% (p less than 0.05). Among diabetic patients, metoclopramide resulted in a significant increase in duodenal placement compared to placebo (p less than 0.05). We conclude that parenteral metoclopramide significantly increases the frequency of transpyloric intubation with small feeding tubes without fluoroscopic guidance in diabetic patients but not in nondiabetic patients.\n\n\nTitle 2:\nEnteral feeding tube placement success with intravenous metoclopramide administration in ICU patients.\nAbstract 2:\nThe purpose of this study was to determine if intravenous push metoclopramide would facilitate immediate transpyloric passage of a small-bore feeding tube without fluoroscopy or endoscopy.\n Prospective, randomized trial.\n One hundred five medical and surgical ICU patients at a community teaching hospital.\n Patients were randomized to receive 10 mg of metoclopramide 10 min before tube insertion or no medication.\n Successful placement was stated as radiologically verified transduodenal tube location.\n A 54% success rate was shown with administration of the drug with 46% success for the control. Chi square analysis of the success rate showed no significant relationship between administration of metoclopramide and successful tube placement (p = 0.38). Increasing years of physician training was the only variable associated with successful placement (p = 0.003). No association was found between successful tube placement and presence of endotracheal tube, tracheostomy, or cervical immobility, nor any interaction of metoclopramide with these variables.\n Intravenous metoclopramide, 10 mg, administered 10 min prior to intubation with a small-bore feeding tube (10F), was ineffective in facilitating transpyloric intubation.\n\n\nTitle 3:\nWhen does metoclopramide facilitate transpyloric intubation?\nAbstract 3:\nPostpyloric feeding probably reduces the incidence of tracheobronchial aspiration and improves feeding tolerance. However, duodenal intubation is often unsuccessful in critically ill patients due to gastric atony. Metoclopramide improves gastric emptying. In a pilot study, 12 adult patients were administered 10 to 20 mg of intravenous metoclopramide after weighted nasal feeding tubes had failed to spontaneously pass distal to the pylorus. In no patient did metoclopramide induce transpyloric passage of the tube. A randomized prospective study involving 10 adult patients was conducted to examine the effect of preinsertion intravenous metoclopramide on transpyloric intubation. All patients had failed to achieve spontaneous duodenal intubation. Five patients received 20 mg of metoclopramide 10 min prior to nasal insertion of a weighed feeding tube. Five control patients received no premedication. Four metoclopramide patients achieved duodenal intubation immediately. In none of the control patients did transpyloric intubation occur (p = 0.048). Metoclopramide, administered after nasogastric intubation, is ineffective in promoting transpyloric advancement of feeding tubes. There is a significant increase in transpyloric intubation when metoclopramide is administered prior to tube insertion.", "role": "user" }, { "content": "Metoclopramide enhanced the migration of naso-enteral tubes, but the results did not reach conventional statistical significance. The reasons may include: small studies, underpowered, varying doses, etc. In clinical practice, clinicians should no longer use metoclopramide for this purpose. However, more randomised clinical trials should be performed with a significant sample size, administering metoclopramide or not. The use of metoclopramide may include adverse reactions, such as depression, high blood pressure, decrease of libido, headache, skin rash, fatigue, fever, hyperactivity, insomnia, nausea, sedation, drowsiness, agitation, extrapyramidal reactions (impaired speech or impaired swallowing, unsteady gait, inflexibility of upper and lower members, tremor).", "role": "assistant" } ]

[ { "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\nFracture Resistance of Endodontically Treated Teeth Restored With Bulk Fill, Bulk Fill Flowable, Fiber-reinforced, and Conventional Resin Composite The aim of this in vitro study was to evaluate the fracture resistance of endodontically treated teeth restored with different types of restorative resins. Seventy-two sound maxillary premolar teeth were randomly divided into six groups (n=12). The teeth in the first group were left intact and tested as unprepared negative control (group I) specimens. The teeth in the remaining five groups were prepared with MOD cavities and endodontically treated. The teeth in one of the five groups (positive control group II) were unrestored. The rest of the prepared cavities were restored as follows: group III: bulk fill resin composite / Filtek Bulk Fill (3M ESPE); group IV: bulk fill flowable resin composite + nanohybrid / SureFil SDR Flow + Ceram.X Mono (Dentsply); group V: fiber-reinforced composite + posterior resin composite / GC everX posterior + G-aenial posterior (GC Corp .); and group VI: nanohybrid resin composite / Tetric N-Ceram (Ivoclar/Vivadent). Each restorative material was used with its respective adhesive system. The restored teeth were stored in distilled water for 24 hours at 37°C and were then thermocycled (5-55°C, 1000×). Specimens were subjected to a compressive load until fracture at a crosshead speed of 0.5 mm/min. The data were analyzed using one-way analysis of variance followed by the post hoc Tukey honestly significantly different test (p<0.05). Sound premolar teeth (group I negative control) showed significantly higher fracture resistance than did the other tested groups (p<0.05). No statistically significant differences were found in the fracture resistance values of the restored groups (groups III, IV, V, and VI) (p>0.05). The lowest values were obtained in the positive control group (group II); these values were significantly lower than those of the other groups (p<0.05). The fracture resistance values of endodontically treated teeth restored with either bulk fill / bulk fill flowable or fiber-reinforced composite were not different from those restored with conventional nanohybrid resin composite.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"teeth\", \"premolar teeth\", \"maxillary\", \"Sound premolar teeth\"], \"Bacterium\": [], \"BiologicFunction\": [\"endodontically treated teeth\", \"cavities\", \"Endodontically Treated Teeth\", \"MOD cavities\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"Tetric N-Ceram\", \"bulk fill flowable resin composite\", \"posterior resin composite\", \"Conventional Resin Composite\", \"adhesive system\", \"Fiber-reinforced\", \"distilled water\", \"bulk fill flowable\", \"Filtek Bulk Fill\", \"fiber-reinforced composite\", \"Bulk Fill Flowable\", \"nanohybrid resin composite\", \"bulk fill\", \"Ceram.X Mono\", \"nanohybrid\", \"SureFil SDR Flow\", \"Bulk Fill\", \"restorative material\", \"G-aenial posterior\", \"GC everX posterior\", \"bulk fill resin composite\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"found\", \"fracture resistance\", \"unrestored\", \"Fracture Resistance\"], \"Food\": [], \"HealthCareActivity\": [\"restored\", \"Restored\", \"test\", \"evaluate\", \"post hoc Tukey\", \"endodontically treated\"], \"InjuryOrPoisoning\": [\"fracture\"], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [\"Ivoclar/Vivadent\", \"Dentsply\", \"GC Corp\"], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"analyzed\"], \"SpatialConcept\": [], \"Virus\": []}", "role": "assistant" } ]

[ { "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\nCorrelation between Decreased Parasympathetic Activity and Reduced Cerebrovascular Reactivity in Patients with Lacunar Infarct Reduced cerebrovascular reactivity (CVR) was found in patients with recent lacunar infarct. However, its mechanisms were controversial. The breath holding maneuver as a vasodilatory stimulus is clinically useful for an estimation of cerebrovasomotor reactivity in well co-operative patients. Patients with lacunar infarct have no higher cortical dysfunction and remain well co-operation. The breath holding maneuver is feasible and safe to perform in patients with lacunar infarct. Autonomic nervous system regulates systemic vascular activity. Regulation of autonomic function to cerebrovascular reactivity has been reported in the literature. We examined the correlation between autonomic functions with frequency and nonlinear heart rate variability (HRV) and cerebrovascular reactivity in patients with lacunar infarct by application of breath holding maneuver. Fifteen patients with lacunar infarct (8 women, age 65.6 ± 13.61) and 16 healthy controls (11 women, age 27.33 ± 3.85) were continuously monitored at baseline before maneuver (basal phase), during CVR induction (experimental phase) with breath holding maneuver and after maneuver (recovery phase), for arterial blood pressure (ABP), electrocardiography (EKG), mean cerebral blood flow velocity (mCBFV) of middle cerebral arteries (MCA) by transcranial doppler (TCD). The short term-one minute HRV was analyzed from EKG signals for low frequency (LF)/ high frequency (HF) ratio, nonlinear of standard deviation 1 (SD1), standard deviation 2 (SD2), cardiac Sample Entropy (SampEn) and Shannon Entropy. Significant increasing in mCBFV, LF / HF ratio, SD2 / SD1, Shannon Entropy and inversely decreasing SampEn during breath holding maneuver compared with baseline were found in both groups (p<0.05). The trend of cerebrovascular reactivity is similar in both groups. However, there were differences of mCBFV, systolic blood pressure (SysBP) in the whole phases (basal, experiment and recovery) between patients and controls (p<0.05). Less scattered signals of SD1 with low value in patient group were illustrated from Poincaré (p<0.05). This indicated less degree of parasympathetic drive in the patients compared to the controls. Moreover, significant positive correlation between systolic bloods pressure and mCBFV in patients suggests impact of autonomic control and cerebral blood flow on the patho-physiological mechanism of vasodilatation, triggered by hypercapnia from breath holding maneuver in patients with lacunar infarct. Reduction of cerebrovascular reactivity in patients with lacunar infarct may relate with decreased parasympathetic activity. Further study is required to demonstrate whether these findings mean mechanisms of lacunar infarct or the effect of hypertensive response.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"MCA\", \"middle cerebral arteries\"], \"Bacterium\": [], \"BiologicFunction\": [\"Decreased Parasympathetic Activity\", \"patho-physiological\", \"nonlinear heart rate variability\", \"CVR\", \"HRV\", \"Cerebrovascular Reactivity\", \"Regulation\", \"lacunar infarct\", \"regulates\", \"vasodilatory stimulus\", \"drive\", \"cortical dysfunction\", \"autonomic functions\", \"autonomic function\", \"decreased parasympathetic activity\", \"autonomic control\", \"vasodilatation\", \"cerebrovascular reactivity\", \"Lacunar Infarct\", \"estimation\", \"short term-one minute HRV\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [\"cerebrovascular\", \"systemic vascular\", \"Autonomic nervous system\", \"parasympathetic\", \"cerebrovasomotor\"], \"Chemical\": [], \"ClinicalAttribute\": [\"systolic bloods pressure\", \"systolic blood pressure\", \"SysBP\"], \"Eukaryote\": [], \"Finding\": [\"co-operative\", \"hypertensive\", \"breath holding\", \"mCBFV\", \"cerebral blood flow\", \"decreasing\", \"positive\", \"no higher\", \"arterial blood pressure\", \"hypercapnia\", \"mean cerebral blood flow velocity\", \"ABP\"], \"Food\": [], \"HealthCareActivity\": [\"monitored\", \"EKG\", \"transcranial doppler\", \"TCD\", \"electrocardiography\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [\"women\"], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [], \"SpatialConcept\": [\"scattered\"], \"Virus\": []}", "role": "assistant" } ]

[ { "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:\nrelated work\n\nContext before the citation:\nThe extracted frames are noisy as a result of parser errors and so are filtered using the binomial hypothesis theory (BHT), following Brent (1993). frame definitions, and the extracted frames include details of specific prepositions. He assumes 19 different subcategorization \u0000\u0000\n\nCitation Sentence:\nThe extracted frames are noisy as a result of parser errors and so are filtered using the binomial hypothesis theory ( BHT ) , following Brent ( 1993 ) .\n\nContext after the citation:\nApplying his technique to approximately four million words of New York Times newswire, Manning acquired 4,900 verb-subcategorization frame pairs for 3,104 verbs, an average of 1.6 frames per verb. Briscoe and Carroll (1997) predefine 163 verbal subcategorization frames, obtained by manually merging the classes exemplified in the COMLEX (MacLeod, Grishman, and Meyers 1994) and ANLT (Boguraev et al. 1987) dictionaries and adding around 30 frames found by manual inspection. The frames incorporate control information and details of specific prepositions. Briscoe and Carroll (1997) refine the BHT with a priori information about the probabilities of subcategorization frame membership and use it to filter the induced frames.", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "You will be shown inclusion or exclusion criteria for a clinical trial. Given these criteria, your task is to extract all unique entities of the following types: [\"Person\", \"Condition\", \"Value\", \"ReferencePoint\", \"Temporal\", \"Qualifier\", \"Observation\", \"Visit\", \"Measurement\", \"Mood\", \"Device\", \"Scope\", \"Negation\", \"Drug\", \"Procedure\", \"Multiplier\"].\n\nPlease return the output as a JSON object of the format: {\"Condition\": [\"breast cancer\", ...], \"Device\": [\"ports\", ...], \"Drug\": [\"Atenolol\", ...], \"Measurement\": [\"blood pressure\", ...], \"Mood\": [\"suspected\", ...], \"Multiplier\": [\"more than two\", ...], \"Negation\": [\"no\", ...], \"Observation\": [\"history\", ...], \"Person\": [\"male\", ...], \"Procedure\": [\"surgery\", ...], \"Qualifier\": [\"severe\", ...], \"ReferencePoint\": [\"enrollment\", ...], \"Scope\": [\"infection\", ...], \"Temporal\": [\"one day\", ...], \"Value\": [\"50%\", ...], \"Visit\": [\"ICU\", ...]}. 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\nall adult patients with a nasal or facial skin/soft tissue defect requiring reconstruction limited to or including a full-thickness skin graft", "role": "user" }, { "content": "{\"Condition\": [\"facial skin/soft tissue defect\", \"nasal skin/soft tissue defect\"], \"Device\": [\"full-thickness skin graft\"], \"Drug\": [], \"Measurement\": [], \"Mood\": [\"requiring\"], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [], \"Procedure\": [\"reconstruction\"], \"Qualifier\": [], \"ReferencePoint\": [], \"Scope\": [\"nasal or facial skin/soft tissue defect\"], \"Temporal\": [], \"Value\": [], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nthe current situation of cmb anisotropy measurements is summarized in figure [ fig : wmap ] .\nwe have an exquisitely accurate reconstruction of the temperature anisotropy angular power spectrum from the wmap satellite @xcite , which is essentialy cosmic variance limited up to the first acoustic peak .\nthe second peak is also determined quite well .\nwhat this tells us is that acoustic oscillations actually took place in the primeval plasma and that inflationary adiabatic perturbations are the best candidate to explain structure formation in the universe by gravitational instability .\nwe also have a very good measurement of the baryon content ( @xmath1 @xcite ) from the ratio of first to second peak heights , in agreement with the primordial nucleosynthesis predictions of the observed light nuclei abundances .\nthe acoustic angular scale at recombination is determined with high precision ( @xmath2 degrees @xcite ) and is providing us with strong evidence that we live in a nearly flat universe .\noverall , a flat model with only six free parameters ( the densities of baryons and cold dark matter , the amplitude and spectral index of scalar density perturbations , the present value of the hubble parameter , and the optical depth to reionization ) is a very good fit to the current cmb data . cdm best fit model , and the shaded area is the associated cosmic variance . [\nfig : wmap ] ] polarization information has also started to be collected , although we are still very far from the accuracy attained by temperature data .\nthe b2k experiment @xcite recently measured the ee and te power spectra , and the same did wmap @xcite .\nwhat these first results are telling us is that there is a consistency between the predicted level of polarized signal in the standard cosmological model and what we actually observe .\nthis reinforces the case for adiabatic perturbations and inflation .\npolarization measurements , however , are still too uncertain to provide constraints on cosmological parameters with an accuracy comparable to those coming from temperature data .\nwhen we look at these wonderful results , we are confronted with the unavoidable question : what remains to be done after wmap ?\nthe answer is : quite a lot , actually .\nto put things in the right context , we can quickly go through a list of some of the major questions left fully or partially unanswered by wmap .\nfirst , there is a need for improved tests of inflation , through better constraints on the spectral index of scalar perturbations and the measurement of its variation ( or lack thereof ) with @xmath3 ( i.e. running ) .\nwmap seemed to show hints of deviations from a harrison - zeldovich spectrum ( @xmath4 ) although this is still within the 2@xmath5 bound @xcite .\na significant departure from simple scale invariance would be a smoking gun for realistic inflationary models .\naccurate measurements of matter density from the cmb are still lacking .\nthis is due to the fact that the information on the breakdown of total matter content into baryons and dark matter can only be done when the third acoustic peak is reconstructed with an accuracy comparable to that of the first two .\nthis is definetely not possible with current data .\nthe uncertainty on @xmath6 affects the determination of other parameters , including curvature ( since this can be measured from the acoustic angular scale only if we also know the distance to last scattering , which depends on @xmath7 and @xmath8 )\n. then we enter into polarization muddy waters .\nwe would very much need a measurement of the ee power spectrum , since this would help with the determination of the detailed reionization history .\nthis , in turn , would lead to improved constraints on the scalar spectral index , by removing its degeneracy with the optical depth . measuring b mode would also be nice , since this would tell us about a tensor mode contribution to primordial perturbations , leading to a better discrimination of inflationary model .\nfinally , there is interesting science hidden in the contribution from secondary anisotropy ( for example from the sunyaev - zeldovich effect in clusters of galaxies , weak lensing of the large scale structure on the cmb photons , and so on ) , which is expected to peak at much smaller scales than those accessible to wmap .\nthere is also the issue of testing primordial non gaussianity ( another important signature of specific models of inflation ) through higher order statistics in multipole space ( such as the bispectrum , trispectrum and so on ) or analysis in the pixel domain ( such as those based on minkowski functionals ) : the latter would greatly benefit from high signal - to - noise maps of the cmb .\nthese goals will definitely be within the capabilities of the upcoming planck mission .\nthe planck esa s satellite is currently scheduled for launch in august 2007\n. it will be the first mission to map the entire sky at a resolution as high as @xmath9 with @xmath0k sensitivity ( three times better resolution than wmap , and an order of magnitude lower noise at 100 ghz ) .\nthe frequency coverage will also be impressive , spanning the range @xmath10 ghz with 9 channels and two different detector techniques ( hemt arrays for the low frequency instrument and bolometers arrays for the high frequency instrument ) .\nthis will allow for optimal foreground separation and for superb control on systematics .\nthe technical details of the planck mission are described elsewhere : see for example the planck blue book @xcite , which also illustrates the science goals that planck is expected to achieve . in the following\ni will summarize what seem to me the most important assets of planck , particullarly when compared to the recent wmap results .\nplanck will essentially be the definitive mission as far as primary cmb temperature anisotropy is concerned\n. the reconstructed power spectrum will be cosmic variance limited up to the fourth acoustic peak , and will get impressive accuracy at even higher multipoles , well into the anisotropy damping tail .\nthis will have important consequences on cosmology .\na forecast of how the temperature power spectrum of the @xmath11cdm concordance model will be reconstructed by planck is shown in figure [ fig : planck ] .\ncdm wmap best fit .\n( from @xcite ) .\n[ fig : planck ] ] figure [ ns ] shows just one example of the giant step forward that the planck data will represent .\nthe spectral index of scalar primordial perturbations and its running will be measured by planck with great precision , allowing to distinguish among different models of inflation .\nthe longer lever arm in multipole space will also be crucial to determine the quantity of matter in the universe .\nthe parameter @xmath6 , which affects the third peak height relative to the first and second , will be measured to better than @xmath12 accuracy @xcite ( compared to the current @xmath13 @xcite ) .\nthis will allow increased accuracy on the determination of the distance to last scattering .\ncombining this with the precise measurement of the angular diameter distance to recombination , one will firmly establish the geometrical properties of the universe , with less need for prior assumptions .\ncdm concordance model with scale invariant spectrum ( @xmath4 ) .\nthe points are simulated observations from wmap ( left panel ) and planck ( right panel ) of the same cosmological model , except that @xmath14 .\nthe residuals ( showed below the two plots ) quantify the ability of the two experiments to discriminate different values of the spectral index . in the lower panels ,\nthe same exercise is performed assuming no running of the spectral index ( continuous line ) and a run of @xmath15 ( simulated data points ) .\n( from @xcite ) .\n[ ns],title=\"fig : \" ] cdm concordance model with scale invariant spectrum ( @xmath4 ) .\nthe points are simulated observations from wmap ( left panel ) and planck ( right panel ) of the same cosmological model , except that @xmath14 .\nthe residuals ( showed below the two plots ) quantify the ability of the two experiments to discriminate different values of the spectral index . in the lower panels ,\nthe same exercise is performed assuming no running of the spectral index ( continuous line ) and a run of @xmath15 ( simulated data points ) .\n( from @xcite ) .\n[ ns],title=\"fig : \" ] although cmb temperature anisotropy is not the primary tool to investigate the properties of the mysterious dark energy component which makes up the @xmath16 of the universe ( see , e.g. @xcite ) , it can be a valuable complementary tool , in at least two ways . first , by accurately determining the curvature of the universe it can remove geometrical degeneracies and serve as a strong prior for other astrophysical observations ( see , e.g. @xcite ) .\nsecond , it can be correlated to tracers of the large scale structure ( such as galaxy redshift surveys ) to detect variations of the gravitational potential occurring during the transition from matter to dark energy domination , through the integrated sachs - wolfe effect ( for an example of current results obtained with this tool see , e.g. @xcite and references therein ) .\nthe planck maps , with their high signal - to - noise and minimal foreground contamination , will be an excellent target for this kind of analysis .\nalthough not specifically designed for polarization measurements , planck will nevertheless be able to determine the ee , bb and te angular power spectra with good accuracy .\nfigure [ planckpol ] shows the forecasted te and ee power spectrum for planck .\ncdm with tensor - to - scalar ratio @xmath17 and optical depth to reionization @xmath18 .\n( from @xcite ) .\n[ planckpol],title=\"fig : \" ] cdm with tensor - to - scalar ratio @xmath17 and optical depth to reionization @xmath18 .\n( from @xcite ) .\n[ planckpol],title=\"fig : \" ] the are several major breakthroughs than can be expected from accurate measurements of the polarized component of the cmb anisotropy .\nthe predicted polarization ee power spectrum shows the same kind of acoustic features that are now well known to exist in the temperature anisotropy spectrum .\nthe peaks in polarization , however , are out of phase with those in the temperature : the ee spectrum has maximum intensity were the temperature is at a minimum , and viceversa .\nthis is due to the fact that polarization is generated by quadrupolar anisotropy at last scattering , and this is closely related to the velocity of the coupled photon - barion fluid .\nthe maximum compression or rarefaction ( and minimum velocity ) of the fluid corresponds to peaks in the temperature anisotropy ( and troughs in the polarization ) . for the same reason ,\nthe te cross - correlation power spectrum shows pronounced peaks corresponding to the interleaved sets of maxima and minima in the two separate components\n. a detection of such features in the polarization and cross - polarization power spectra would then be crucial : it would give an independent confirmation of the fact that acoustic oscillations took place in the primeval plasma .\nthis would strengthen the case for the adiabatic nature of primordial perturbations thus providing strong support to cosmic inflation .\n[ bmode ] ( from @xcite ) . ]\nsince it probes the epoch of decoupling , polarization allows one to perform detailed tests of the recombination physics .\nin particular , it is a well known fact that the universe underwent a phase of reionization at redshifts of at least @xmath19 , during the early stages of structure formation .\nthe investigation of these so - called dark ages is an active subject of investigation .\nwhen photons are diffused by free electrons along the line of sight , the cmb temperature anisotropy signal gets damped .\nthe amount of damping would be a powerful probe of the optical depth to reionization .\nhowever this effect is masked by other physical mechanisms .\nfor example , there is a strong degeneracy between the optical depth and the spectral index of primordial perturbations .\ncmb polarization would prove very powerful in breaking this degeneracy : if the optical depth is non zero , a recognizable polarization signature gets generated at large angular scales , allowing investigation of the detailed reionization history , e.g. by discriminating models that have the same optical depth but a different evolution of the ionization fraction with redshift .\nnot only the characterization of the detailed ionization history of the universe would have a strong scientific impact in itself , but it would also greatly increase the accuracy of the determination of other cosmological parameters , such as the above mentioned spectral index of scalar primordial perturbations .\nthis , in turn , would be extremely important when constraining models of inflation .\none crucial aspect of cmb polarization has to do with the properties of its b component .\na forecast of the bb power spectrum as should be observed by planck is shown in figure [ bmode ] .\nthe consequences of detecting b polarization for theoretical models would be enormous .\nb modes can only be generated when a tensor component of primordial perturbations is present ( namely , a background of primordial gravitational waves ) .\nthis is precisely one of the predictions of inflationary models .\nthe ratio of scalar to tensor fluctuations @xmath20 , is a direct signature of the inflation energy scale , and is strongly related to the amplitude of b modes .\nknowledge of @xmath20 and of the spectral index of the perturbation scalar component can be translated into a measurement of the inflationary slow - roll parameters , thus allowing to discriminate specific models of inflation .\nin the next few years , we can expect a huge breakthrough in our knowledge of cosmology from the planck mission results\n. we will be able to extract the complete information embedded in the temperature primary anisotropy data and have good ( although not optimal ) reconstruction of the polarized component of the cmb anisotropy .\nforegrounds contamination will be minimal and systematics will be under control\n. this will allow percent accuracy on the measurements of cosmological parameters and will be used as an invaluable source of prior knowledge for upcoming probes of the local universe .\nhinshaw , g. et al .\n2006 astro - ph/0603451 spergel , d. n. , et al .\n2006 , submitted to apj , astro - ph/0603449 montroy , t. e. , et al .\n2006 , apj in press astro - ph/0507514 page , l. , et al .\n2006 , submitted to apj , astro - ph/0603450 w. h. kinney , e. w. kolb , a. melchiorri , a. riotto 2006 , astro - ph/0605338 `` the scientific programme of planck '' , esa - sci(2005)1 , astro - ph/0604069 .\nriess , a. g. , et al .\n2004 , apj 607 , 665 sachs , r. k. & a. m. wolfe 1967 , apj 147 , 73 a. balbi , c. baccigalupi , f. perrotta , s. matarrese , n. vittorio , 2003 , apj 588 l5-l8 pietrobon , d. , balbi , a , , marinucci , d. 2006 , phys . rev .\nd 74 , 043524 , astro - ph/0606475 t. roy choudhury & a. ferrara 2006 , astro - ph/0603149 w. hu & g. p. holder , 2003 , _ phys .\n, 68 , 023001", "role": "user" }, { "content": "i briefly review some of the main scientific outputs expected from the upcoming planck mission . \n planck will map the cmb sky with 5 resolution and @xmath0k sensitivity , with minimal foreground contribution and superb control on systematics . \n it will collect the entire information enclosed in the temperature primary anisotropy signal and will also get a good measurement of the polarized component of the cmb . \n this will have profound implications on our knowledge of the physics of the early universe and on the determination of cosmological parameters .", "role": "assistant" } ]

[ { "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:\ncDNAidentificationandRACEdatahavebeenusedtodeterminegenestructureforabout30genes,see,forexample,[19,23].", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "You will be presented with a paragraph from a COVID-19 literature. Your task is to classify the topics of this piece of text by choosing from the following categories:\n\n- Epidemic Forecasting: The content relates to predictions about the spread of COVID-19.\n- Treatment: The paragraph discusses therapeutic methods or medication for COVID-19.\n- Prevention: The content covers measures to prevent the spread of COVID-19.\n- Mechanism: The paragraph explains the biological mechanisms of the virus.\n- Case Report: The content is a report of a COVID-19 case.\n- Transmission: The paragraph discusses how COVID-19 is transmitted.\n- Diagnosis: The content is about diagnosing COVID-19 in individuals.\n\nYour classification should be provided as an element within a JSON array. The array should be formatted with topics enclosed in double quotes and separated by commas, following the JSON format, for example: [\"Topic1\", \"Topic2\", ...]. Include all applicable categories within the array. \nYour output should be a valid JSON array, and no additional text should be included in your response.\n\nArticle:\n\nOBJECTIVE: To determine if COVID-19 was associated with a change in patient refusals after Emergency Medical Services (EMS) administration of naloxone. METHODS: This is a retrospective cohort study in which the incidence of refusals after naloxone administration in a single EMS system was evaluated. The number of refusals after naloxone administration was compared across the before-pandemic interval (01/01/20 to 02/15/20) and the during-pandemic interval (03/16/20 to 04/30/20). For comparison the incidence of all other patient refusals before and during COVID-19 as well as the incidences of naloxone administration before and during COVID-19 were also reported. RESULTS: Prior to the widespread knowledge of the COVID-19 pandemic, 24 of 164 (14.6%) patients who received naloxone via EMS refused transport. During the pandemic, 55 of 153 (35.9%) patients who received naloxone via EMS refused transport. Subjects receiving naloxone during the COVID-19 pandemic were at greater risk of refusal of transport than those receiving naloxone prior to the pandemic (RR = 2.45; 95% CI 1.6-3.76). Among those who did not receive naloxone, 2067 of 6956 (29.7%) patients were not transported prior to the COVID-19 pandemic and 2483 of 6016 (41.3%) were not transported during the pandemic. Subjects who did not receive naloxone with EMS were at greater risk of refusal of transport during the COVID-19 pandemic than prior to it (RR = 1.39; 95% CI 1.32-1.46). CONCLUSION: In this single EMS system, more than a two-fold increase in the rate of refusal after non-fatal opioid overdose was observed following the COVID-19 outbreak.", "role": "user" }, { "content": "[\"Prevention\"]", "role": "assistant" } ]

[ { "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: Perspectives on anthracyclines plus ifosfamide in advanced soft tissue sarcomas. Doxorubicin and ifosfamide are currently the two main drugs for the treatment of soft tissue sarcomas in adults . Given in combination at full doses, with or without dacarbazine, these agents have induced higher response rates than were obtained with single-agent therapy. Because they involve considerable myelotoxicity, however, full-dose regimens should be reserved for patients with good performance status and without potential septic foci. Obviously, higher response rates do not automatically translate into improved survival. In soft tissue sarcomas, full-dose polychemotherapy will most probably provide a survival benefit only in selected patients in whom surgery can be performed in combination with chemotherapy. Prospective trials in such patients, although difficult to carry out, would be highly desirable. The information they would provide might help the clinician tailor treatment in a more rational way and improve chances of cure or long-term survival in at least some patient subgroups.\n\nsentence: Doxorubicin and ifosfamide are currently the two main drugs for the treatment of soft tissue sarcomas in adults .", "role": "user" }, { "content": "[[\"Doxorubicin\", \"ifosfamide\", \"POS\"]]", "role": "assistant" } ]

[ { "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 proposes a simple and effective approach to combine high-level and low-level features for image\n\nKeyphrases: image classification\n\nDataset description:\nCIFAR-10: The CIFAR-10 dataset (Canadian Institute for Advanced Research, 10 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The images are labelled with one of 10 mutually exclusive classes: airplane, automobile (but not truck or pickup truck), bird, cat, deer, dog, frog, horse, ship, and truck (but not pickup truck).\nStory Commonsense: Story Commonsense is a new large-scale dataset with rich low-level annotations and establishes baseline performance on several new tasks, suggesting avenues for future research.\nVIsual PERception (VIPER): VIPER is a benchmark suite for visual perception. The benchmark is based on more than 250K high-resolution video frames, all annotated with ground-truth data for both low-level and high-level vision tasks, including optical flow, semantic instance segmentation, object detection and tracking, object-level 3D scene layout, and visual odometry.\nCityscapes: Cityscapes is a large-scale database which focuses on semantic understanding of urban street scenes. It provides semantic, instance-wise, and dense pixel annotations for 30 classes grouped into 8 categories (flat surfaces, humans, vehicles, constructions, objects, nature, sky, and void).\nEDEN: EDEN (Enclosed garDEN) is a multimodal synthetic dataset, a dataset for nature-oriented applications. The dataset features more than 300K images captured from more than 100 garden models.\nDocBank: A benchmark dataset that contains 500K document pages with fine-grained token-level annotations for document layout analysis. DocBank is constructed using a simple yet effective way with weak supervision from the \\LaTeX{} documents available on the arXiv.com.\nObstacle Tower: Obstacle Tower is a high fidelity, 3D, 3rd person, procedurally generated environment for reinforcement learning. An agent playing Obstacle Tower must learn to solve both low-level control and high-level planning problems in tandem while learning from pixels and a sparse reward signal.\n\nOptions:- A: CIFAR-10 B: Story Commonsense C: VIsual PERception (VIPER) D: Cityscapes E: EDEN F: DocBank G: Obstacle Tower", "role": "user" }, { "content": "[\"CIFAR-10\", \"Cityscapes\"]", "role": "assistant" } ]

[ { "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: Pharmacokinetics , Safety , and Antitumor Effect of Apalutamide with Abiraterone Acetate plus Prednisone in Metastatic Castration-Resistant Prostate Cancer : Phase Ib Study . apalutamide is a next-generation androgen receptor (AR) inhibitor approved for patients with nonmetastatic castration-resistant prostate cancer (CRPC) and metastatic castration-sensitive prostate cancer. We evaluated the pharmacokinetics, safety, and antitumor activity of apalutamide combined with abiraterone acetate plus prednisone (AA-P) in patients with metastatic CRPC (mCRPC). ### Patients And Methods Multicenter, open-label, phase Ib drug-drug interaction study conducted in 57 patients with mCRPC treated with 1,000 mg abiraterone acetate plus 10 mg prednisone daily beginning on cycle 1 day 1 (C1D1) and 240 mg apalutamide daily starting on C1D8 in 28-day cycles. Serial blood samples for pharmacokinetic analysis were collected on C1D7 and C2D8. ### results Systemic exposure to abiraterone, prednisone, and prednisolone decreased 14%, 61%, and 42%, respectively, when apalutamide was coadministered with AA-P. No increase in mineralocorticoid excess-related adverse events was observed. Patients without prior exposure to AR signaling inhibitors had longer median treatment duration and greater mean decrease in prostate-specific antigen (PSA) from baseline compared with those who had received prior therapy. Confirmed PSA reductions of ≥50% from baseline at any time were observed in 80% (12/15) of AR signaling inhibitor-naïve patients and 14% (6/42) of AR signaling inhibitor-treated patients. ### conclusions Treatment with apalutamide plus AA-P was well tolerated and showed evidence of antitumor activity in patients with mCRPC, including those with disease progression on AR signaling inhibitors. No clinically significant pharmacokinetic interaction was observed between abiraterone and apalutamide; however, apalutamide decreased exposure to prednisone. These data support development of 1,000 mg abiraterone acetate plus 10 mg prednisone daily with 240 mg apalutamide daily in patients with mCRPC.\n\nsentence: Pharmacokinetics , Safety , and Antitumor Effect of Apalutamide with Abiraterone Acetate plus Prednisone in Metastatic Castration-Resistant Prostate Cancer : Phase Ib Study .", "role": "user" }, { "content": "[[\"Apalutamide\", \"Abiraterone\", \"Prednisone\", \"POS\"]]", "role": "assistant" } ]

[ { "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\nIt may also be that disease activity in psoriasis correlates with levels of CD-associated antibodies (Lindqvist et al., 2002; Woo et al., 2004).", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "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: BCG vaccine can not protect against COVID-19 infection\n\nAbstract:\nThe non-specific beneficial effects of Bacille Calmette-Guérin (BCG) vaccination suggest that this vaccine might play a role in protecting individuals against severe coronavirus disease (COVID-19).Several studies propose that BCG vaccination may increase the body's immunity, thereby preventing respiratory infections caused by other respiratory pathogens.\nAs the number of deaths due to COVID-19 is increasing rapidly and there is no specific treatment available to date, scientists are evaluating the effectiveness of already approved drugs as therapies against COVID-19, and the results were found to vary widely: from no significant effect being observed to a reduction in the time taken for clinical improvement.\nThis study thus aims to evaluate whether it is worth performing clinical trials to examine the effects of the BCG vaccine on COVID-19.\nWe herein emphasize the need to conduct phase III randomized controlled trials with an adequate sample size and quality to investigate the effects of the BCG vaccine on COVID-19.\nIn the event that BCG vaccination provides non-specific protection against COVID-19, administering it could be helpful in controlling the transmission of COVID-19 and other infectious diseases during future pandemics.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"In the event that BCG vaccination provides non-specific protection against COVID-19, administering it could be helpful in controlling the transmission of COVID-19 and other infectious diseases during future pandemics.\"]}", "role": "assistant" } ]

[ { "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: [\"Gene\"].\n\nPlease return the output as a JSON object of the format: {\"Gene\": [\"IGF\", ...]}. 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\nRegulatory network of inflammation downstream of proteinase-activated receptors. BACKGROUND: Protease-activated receptors (PAR) are present in the urinary bladder, and their expression is altered in response to inflammation. PARs are a unique class of G protein-coupled that carry their own ligands, which remain cryptic until unmasked by proteolytic cleavage. Although the canonical signal transduction pathway downstream of PAR activation and coupling with various G proteins is known and leads to the rapid transcription of genes involved in inflammation, the effect of PAR activation on the downstream transcriptome is unknown. We have shown that intravesical administration of PAR-activating peptides leads to an inflammatory reaction characterized by edema and granulocyte infiltration. Moreover, the inflammatory response to intravesical instillation of known pro-inflammatory stimuli such as E. coli lipopolysaccharide (LPS), substance P (SP), and antigen was strongly attenuated by PAR1- and to a lesser extent by PAR2-deficiency. RESULTS: Here, cDNA array experiments determined inflammatory genes whose expression is dependent on PAR1 activation. For this purpose, we compared the alteration in gene expression in wild type and PAR1-/- mice induced by classical pro-inflammatory stimuli (LPS, SP, and antigen). 75 transcripts were considered to be dependent on PAR-1 activation and further annotated in silico by Ingenuity Pathways Analysis (IPA) and gene ontology (GO). Selected transcripts were target validated by quantitative PCR (Q-PCR). Among PAR1-dependent transcripts, the following have been implicated in the inflammatory process: b2m, ccl7, cd200, cd63, cdbpd, cfl1, dusp1, fkbp1a, fth1, hspb1, marcksl1, mmp2, myo5a, nfkbia, pax1, plaur, ppia, ptpn1, ptprcap, s100a10, sim2, and tnfaip2. However, a balanced response to signals of injury requires a transient cellular activation of a panel of genes together with inhibitory systems that temper the overwhelming inflammation. In this context, the activation of genes such as dusp1 and nfkbia seems to counter-balance the inflammatory response to PAR activation by limiting prolonged activation of p38 MAPK and increased cytokine production. In contrast, transcripts such as arf6 and dcnt1 that are involved in the mechanism of PAR re-sensitization would tend to perpetuate the inflammatory reaction in response to common pro-inflammatory stimuli. CONCLUSION: The combination of cDNA array results and genomic networks reveals an overriding participation of PAR1 in bladder inflammation, provides a working model for the involvement of downstream signaling, and evokes testable hypotheses regarding the transcriptome downstream of PAR1 activation. It remains to be determined whether or not mechanisms targeting PAR1 gene silencing or PAR1 blockade will ameliorate the clinical manifestation of cystitis.", "role": "user" }, { "content": "{\"Gene\": [\"dusp1\", \"fth1\", \"PAR\", \"sim2\", \"b2m\", \"p38 MAPK\", \"cd200\", \"dcnt1\", \"pax1\", \"plaur\", \"ptpn1\", \"ptprcap\", \"s100a10\", \"PAR2\", \"fkbp1a\", \"marcksl1\", \"cdbpd\", \"Protease-activated receptors\", \"nfkbia\", \"tnfaip2\", \"arf6\", \"ppia\", \"PAR-1\", \"hspb1\", \"mmp2\", \"proteinase-activated receptors\", \"PAR1\", \"ccl7\", \"myo5a\", \"cd63\", \"G proteins\", \"cfl1\"]}", "role": "assistant" } ]

[ { "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\nSurvival status and functional outcome of children who required prolonged intensive care after cardiac surgery Children who require prolonged intensive care after cardiac surgery are at risk of high mortality. The long-term survival and functional outcome of these children have not been studied in detail. Children who stayed in intensive care for >28 days after cardiac surgery from 1997 to 2012 were studied in a single institution. A total of 116 patients were identified; 107 (92%) were <1 year of age and 63 (54%) had univentricular physiology. The incidence of children requiring prolonged intensive care increased from 1.01/100 undergoing cardiac surgery in 1997 to 2000 to 2.66/100 in 2009 to 2012 (P trend = .002). This increase coincided with an increase in the number of children with hypoplastic left heart syndrome having prolonged intensive care during the same period (0.13/100 in 1997-2000 to 1.0/100 in 2009-2012; P trend = .001). Survival to pediatric intensive care unit (PICU) discharge was 74% (95% confidence interval [CI], 65-82) and 51% (95% CI, 41-59) at 3 years. Factors associated with mortality were univentricular repair (hazard ratio [HR], 2.12; 95% CI, 1.21-3.70; P = .008) and acute renal failure (HR, 3.01; 95% CI, 1.77-5.12; P < .001), but era did not influence mortality (1997-2005 vs 2006-2012; log-rank P = .66). Among PICU survivors, 3- year survival in those who did not need early reoperation was 81% (95% CI, 66-90), compared with 58% (95% CI, 42-71) in those who required early reoperation (log-rank P = .01). Among survivors, 36% had either moderate or severe disability and 13% had poor quality of life. The incidence of children requiring prolonged intensive care after cardiac surgery has increase d in our institution. Our data suggest that the long-term outcome for most of these children is poor, especially after univentricular repair.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"univentricular physiology\"], \"Bacterium\": [], \"BiologicFunction\": [\"hypoplastic left heart syndrome\", \"acute renal failure\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"stayed\", \"severe disability\", \"survival\", \"Survival status\", \"moderate\", \"Survival\"], \"Food\": [], \"HealthCareActivity\": [\"discharge\", \"univentricular repair\", \"reoperation\", \"cardiac surgery\", \"intensive care\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [\"PICU\", \"pediatric intensive care unit\", \"institution\"], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [], \"SpatialConcept\": [], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Given an abstract from a research paper, your task is to identify and label relationships between chemical compounds and genes mentioned in the abstract.\n\nThe relationship type must be one of ['DOWNREGULATOR', 'SUBSTRATE', 'INDIRECT-REGULATOR', 'PART-OF', 'MODULATOR-ACTIVATOR', 'REGULATOR', 'INHIBITOR', 'COFACTOR', 'UPREGULATOR', 'ACTIVATOR', 'ANTAGONIST', 'NOT', 'INDIRECT-DOWNREGULATOR', 'SUBSTRATE_PRODUCT-OF', 'INDIRECT-UPREGULATOR', 'AGONIST', 'PRODUCT-OF', 'MODULATOR', 'DIRECT-REGULATOR', 'UNDEFINED', 'AGONIST-INHIBITOR', 'AGONIST-ACTIVATOR', 'MODULATOR-INHIBITOR'].\n\nPlease format your output as a JSON array. Each entry in the array should express a single relation, formatted as [\"<Entity_A>\", \"<RELATION_A_B>\", \"<Entity_B>\"]. If no relations can be found, please output an empty JSON array [].\n\nAbstract:\n\nInhibition of NF-kappa B by sodium salicylate and aspirin. The transcription factor nuclear factor-kappa B (NF-kappa B) is critical for the inducible expression of multiple cellular and viral genes involved in inflammation and infection including interleukin-1 (IL-1), IL-6, and adhesion molecules. The anti-inflammatory drugs sodium salicylate and aspirin inhibited the activation of NF-kappa B, which further explains the mechanism of action of these drugs. This inhibition prevented the degradation of the NF-kappa B inhibitor, I kappa B, and therefore NF-kappa B was retained in the cytosol. Sodium salicylate and aspirin also inhibited NF-kappa B-dependent transcription from the Ig kappa enhancer and the human immunodeficiency virus (HIV) long terminal repeat (LTR) in transfected T cells.", "role": "user" }, { "content": "[[\"Sodium salicylate\", \"INHIBITOR\", \"Ig kappa\"], [\"sodium salicylate\", \"INHIBITOR\", \"NF-kappa B\"], [\"aspirin\", \"INHIBITOR\", \"NF-kappa B\"], [\"aspirin\", \"INHIBITOR\", \"Ig kappa\"]]", "role": "assistant" } ]

[ { "content": "You will be shown a paragraph from a biomedical research paper, followed by a question about the paper. Please extract text from the paragraph to answer the question. Do not include any text in your response other than the answer.\n\nParagraph: Each mosquito tested was highly susceptible to infection by a full-length infectious clone of the La Réunion Island isolate, CHIKV LR2006 OPY1 strain. Even though the Ae. albopictus strains were more susceptible to infection, overall ecology and differences in human biting patterns need to be studied further Characteristically, there are two rounds of translation: (+) sense genomic RNA (49S9 = 11.7 kb) acts directly as mRNA and is partially translated (59 end) to produce non-structural proteins (nsp's). These proteins are responsible for replication and formation of a complementary (2) strand, the template for further (+) strand synthesis. Subgenomic mRNA (26 S = 4.1 kb) replication occurs through the synthesis of full-length (2) intermediate RNA, which is regulated by nsp4 and p123 precursor in early infection and later by mature nsp's. Translation of the newly synthesized sub-genomic RNA results in production of structural proteins such as Capsid and protein E2-6k-E1 (from 39 end of genome). Assembly occurs at the cell surface, and the envelope is acquired as the virus buds from the cell and release and maturation almost simultaneous occurred. Replication occurs in the cytoplasm and is very rapid (,4 h) [28, 29] . doi:10.1371/journal.pntd.0000623.g002 www.plosntds.org to gain a more accurate understanding of a potential CHIKV epidemic in the US [32] . During the 7 d preceding birth, no human mother has been reported to transmit the disease vertically. However, about 50% of newborns delivered while the mother was infected with CHIKV contracted the disease from their mother, despite the method of delivery. Furthermore, there have been instances of CHIKV transmission from mother to fetus causing congenital illness and fetal death [33] . During the 2005-2006 La Reunion Island outbreaks, Ramful et al. discovered that mothers could transmit CHIKV to their progeny during the perinatal period (Day 24 to Day +1) [33, 34] , and it is associated with a high degree of morbidity. By mean Day 4 of life, all of the neonates were symptomatic for CHIKV, exhibiting common CHIKF symptoms. Six neonates were confirmed to have contracted CHIKV and developed mengoencephalitis. Of those mothers who, during the La Reunion Island epidemic, were infected long before delivery, only three fetal deaths were reported [12, 33] . Ramful et al. theorized that motherto-child transmission most likely happens transplacentally shortly before delivery [33] . A similar study by Gerardin et al. reported nineteen cases of neonatal infection associated with intrapartum maternal viremia that progressed to develop encephalitis owing to vertical transmission from infected mothers [34] . Clinical and epidemiological similarities with dengue fever make CHIKV diagnosis difficult, which may lead physicians to misdiagnose CHIKV as dengue fever; therefore, the incidence of CHIKV may actually be higher than currently believed (Table 1 ) [6, 12, 35] . The amount of time elapsed since disease onset is the most critical parameter when choosing a diagnostic test. CHIKV can be detected and isolated by culturing with mosquito cells (C6/36), Vero cells (mammalian), or in mice [26] . However, this method can take at least a week and only achieves a high sensitivity during the viremic phase, which usually only lasts up to 48 h after the bite. Five days post-infection, the viral isolation approach has a low sensitivity but is still the preferred method for detecting the CHIKV strain [12, 26, 31, 35] . RT-PCR on the other hand is a faster and more sensitive method that can be used within the first week of disease onset [26] , and it is currently the most sensitive method for detecting and quantifying viral mRNA [4, 36] . Classic serological detection, by assays such as ELISA [37] , immunofluorescence [5, 38] , complement binding, and haemagglutination inhibition [39] , constitutes the second diagnostic tool used for biological diagnosis of CHIKV infection. These proven techniques are useful for detection of Antigen in mosquitoes during epidemiological studies. These assays detect virus-specific IgM and IgG, however the sensitivity and specificity of these assays has been poorly characterized. Viral competence, or the potential of viral infection and transmission, is an important parameter that can be quantified by ELISA, viral culture, and PCR. A study by Ng et al. showed biomarkers indicative of severe CHIKV infection [40] . They found decreased levels of RANTES and increased levels of Interleukin-6 (IL-6) and Interleukin-1b (IL-1b) that could be sued for CHIKV detection in patients as indicators of CHIKV-driven cytokine storm. Couderc et al. demonstrate another cytokine, type-I IFN, as a key player in the progression to CHIKV infection [26] . Using an IFN-a/b null mouse model, they demonstrated evidence of muscles, joints, and skin as privileged CHIKV targets, which is consistent with human pathology. Although Ng et al. concluded that RANTES levels were significantly suppressed in severe CHIKF patients [40] , interestingly, an increase in levels of RANTES has been observed in dengue infection [41] . Since the symptoms of CHIKF mimic those of dengue fever, results obtained from this study strongly suggest that RANTES could be a potential distinctive biomarker that differentiates between these two clinically similar diseases. There are no approved antiviral treatments currently available for CHIKV [1, 3, 12, 42] . Currently, CHIKF is treated symptomatically, usually with non-steroidal anti-inflammatory drugs or steroids, bed rest, and fluids. Movement and mild exercise are thought to decrease stiffness and morning arthralgia, but heavy exercise may exacerbate rheumatic symptoms. Corticosteroids may be used in cases of debilitating chronic CHIKV infection. There is a debate about the appropriateness of chloroquine as treatment for unresolved, non-steroidal anti-inflammatory drugresistant arthritis [43] . A study showed that viral production was www.plosntds.org drastically reduced at 16 h post-infection after treatment with 100 mM dec-RVKR-cmk (Decanoyl-Arg-Val-Lys-Arg-chloromethylketone), a furine inhibitor [42, 44] . Chloroquine acted by raising the pH, blocking low pH-dependent entry of virus into the cell. It is important to note that dec-RVKR-cmk or chloroquine only inhibited viral spreading from cell to cell, not CHIKV replication once it had entered the cell [43] . However, most would agree that the best weapon against CHIKV is prevention. A live CHIKV vaccine developed by the United States reached phase II clinical trial encompassing 59 healthy volunteers [45] . Eight percent of the volunteers experienced transient arthralgia, while 98% of the volunteers had seroconversion [45] . However, live CHIKV vaccines are still questionable. One cannot discount the risk of a live vaccine possibly inducing chronic rheumatism. Also, there is the question as to whether widespread use among the public could trigger mosquito transmission or lead to chronic infection or viral reversion [1] . An alternative approach would be to produce a chimeric vaccine against CHIKV. Wang et al. developed a chimeric alphavirus vaccine that is uniformly attenuated and does not cause reactogenicity in mice [3] . Three different versions of this vaccine were made using three different backbone vectors: Venezuelan equine encephalitis virus (VEEV) attenuated vaccine strain T-83, naturally attenuated eastern equine encephalitis virus (EEEV), and attenuated Sindbis virus (SINV). In short, CHIKV structural proteins were engineered into the backbones of the aforementioned vaccines to produce the chimeras [3] . These chimeras were found to stimulate a strong humoral immunity, and even at doses of 5.3-5.8 log 10 PFU, they did not trigger reactogenicity. When vaccinated mice were challenged with CHIKV, neither adult nor neonatal mice gained weight, had fever, or displayed signs of neurological illness. Upon comparison of the chimeras with the Army181/25 vaccine, the Army vaccine resulted in higher levels of viremia and replication in the joints of neonatal mice. Because the joints are known targets of CHIKV, Wang et al. noted their vaccine might avoid the negative reactogenic side effects of the Army vaccine. After being subcutaneously vaccinated with 5.3-5.8 log 10 PFU of the chimeric vaccines, mice produced strong neutralizing antibody titers. The VEEV and EEEV chimeras yielded higher neutralizing antibody titers than the SINV chimera without being more virulent. On top of this, the VEEV and EEEV CHIKV chimeras seemed to be more immunogenic than the Army vaccine despite the chimeras' lower viremia and replication in the joints of neonatal mice [3] . Tiwari et al. [46] adopted a different strategy using formalin inactivated CHIKV in combination with alhydrogel (Aluminum Hydroxide) as an adjuvant. This study clearly suggests that this vaccine elicits both humoral and cell-mediated immune responses in mice, providing its immunogenic potential. A recent study by Couderc et al. [47] showed passive immunization as a potential treatment for CHIKV infection. Using purified immunoglobulin extracted from convalescent CHIKV patients, they demonstrated effective neutralizing activity against CHIKV infection both in vitro and in vivo. This thereby establishes a potential preventive and therapeutic approach to combat CHIKV infection. Pathogenesis studies conducted with related alpha virus, like RRV, have shown the role of macrophages in persistence on infection [48] . They also demonstrated the role of RRV-specific CD8 T cells in clearing viral load in infected patients, thereby warranting similar investigations with CHIKV and the importance of investigating a cell-mediated immune response-based vaccine against CHIKV [49] . There are always certain risks associated with live attenuated or inactivated viral vaccines [50] . One way to avoid these potential problems is to construct a consensus-based DNA vaccine. DNA based vaccines have an improved safety profile as compared to live or attenuated vaccines [51, 52] . A consequence of CHIKV's rapid evolution is difficulty in constructing a vaccine that will be able to Figure 3 . Levels of CHIKV-specific IgG in mice immunized with CHIKV vaccines. Each group of C57BL/6 mice (n = 5) was immunized with 12.5 mg of pVax1 control vector or CHIKV vaccine plasmids as indicated at 0 and 2 wk. Mice were bled 2 wk after each immunization, and each group's serum pool was diluted to 1:100 and 1:500 for reaction with specific vaccine constructs. Serum was incubated for 1 h at 37uC on 96-well plates coated with 2 mg/ml of respective CHIKV peptides, and antibody was detected using anti-mouse IgG-HRP and OD was measured at 405 nm. doi:10.1371/journal.pntd.0000623.g003 www.plosntds.org effectively protect large populations from multiple strains of the virus. One of the strengths of DNA consensus vaccines is its ability to induce cross-reactive immune responses against the three distinct phylogenetic groups of CHIKV. Also DNA-based vaccines can be produced more rapidly than protein-based vaccines. Recently, Muthumani et al. constructed a vaccine that was shown to induce both humoral and cellular immunity in vivo in 3-4-wk-old female C57/BL6 mice [49] . These mice were immunized using an in vivo electroporation method to deliver the vaccine into the quadriceps muscle. The consensus construct was designed against E1, E2, and the core protein capsid. To design the construct, they aligned 21 sequences of CHIKV isolated between 1952 and 2006, using strains from differing countries, including La Reunion Island. The most common nucleotide among the sequences was chosen at each position to be used in the consensus construct, taking care not to alter the reading frame. They conducted codon and RNA optimization, added a strong Kozak sequence, and substituted signal peptide with an immunoglobulin E leader sequence to improve vaccine efficacy. After immunizing the mice, spleens were harvested along with serum and tested to determine antibody titer. After three immunizations, consensus E1, E2, and C vaccines were shown to induce T-cell immune responses leading to strong IFN-c responses and proliferation in C57/BL6 mice. Furthermore, when compared with control mice, immunized mice had higher total IgG levels as well as higher anti-E1 specific, anti-E2 specific, and anti-C specific IgG antibodies, suggesting a strong humoral immune response ( Figure 3 ) and also specificity for the antigens encoded in the vaccine constructs ( Figure 4 ). Because of its promising results and the need for a safer vaccine, this consensus DNA vaccine deserves further investigation. Determining longevity of protective effects of the vaccine and persistence of antibody and IFN-c responses could be the next step of investigation. Challenged studies of immunized mice must also be carried out. CHIKV mosquito-borne disease has caused massive outbreaks for at least half a century but is no longer confined to the www.plosntds.org developing nations. It began to encroach into the boundaries of the developing world. As a result, the NIAID has designated CHIKV as a Category C pathogen alongside the influenza and SARS-CoV viruses [3] . Realization of the potential severity of this disease is exigent; for instance, if used as a biological weapon, the world economy could be severely crippled; if enough members of the armed forces were to become infected during a military deployment, military operations could be significantly affected. Efforts to monitor the disease will only provide minimal warning in a global society, and steps to prevent the morbidity and mortality associated with pandemic are imperative [21, 31] . Despite the gravity of its infectious potency and the fear of it being a potential biological weapon, there is currently no vaccine for CHIKV infections. Live attenuated vaccine trials were carried out in 2000, but funding for the project was discontinued.\n\nQuestion: What is the NIAID designation of CHIKV?", "role": "user" }, { "content": "as a Category C pathogen alongside the influenza and SARS-CoV viruses", "role": "assistant" } ]

[ { "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: We use the Imagen saharia2022photorealistic text-guided synthesis model as a backbone. Since the composition and geometry are mostly determined at the 64\\times 64 resolution, we only adapt the text-to-image diffusion model, using the super-resolution process as is.Recall that each diffusion step t consists of predicting the noise \\epsilon from a noisy image z_{t} and text embedding \\psi(\\mathcal{P}) using a U-shaped network ronneberger2015u . At the final step, this process yields the generated image \\mathcal{I}=z_{0}.Most importantly, the interaction between the two modalities occurs during the noise prediction, where the embeddings of the visual and textual features are fused using Cross-attention layers that produce spatial attention maps for each textual token. More formally, as illustrated in fig. 3(Top), the deep spatial features of the noisy image \\phi(z_{t}) are projected to a query matrix Q=\\ell_{Q}(\\phi(z_{t})), and the textual embedding is projected to a key matrix K=\\ell_{K}(\\psi(\\mathcal{P})) and a value matrix V=\\ell_{V}(\\psi(\\mathcal{P})), via learned linear projections \\ell_{Q},\\ell_{K},\\ell_{V}.The attention maps are thenM=\\text{Softmax}\\left(\\frac{QK^{T}}{\\sqrt{d}}\\right),(1)where the cell M_{ij} defines the weight of the value of the j-th token on the pixel i, and where d is the latent projection dimension of the keys and queries. Finally, the cross-attention output is defined to be \\widehat{\\phi}\\left(z_{t}\\right)=MV, which is then used to update the spatial features \\phi(z_{t}).\n\nQuestion: How the embeddings of visual and textual features are fused during the noise prediction process?", "role": "user" }, { "content": "They are fused using Cross-attention layers, to illustrate more in Figure 3, the deep spatial features of noisy image φ(zt) are projected to a query matrix Q = lQ(φ(zt)), and the textual embedding is projected to a key matrix K = lK(ψ(P)) and a value matrix V = lV (ψ(P)), via learned linear projections lQ, lK, lV.", "role": "assistant" } ]

[ { "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\nDoes wavelength matter when photocoagulating eyes with macular degeneration or diabetic retinopathy ?", "role": "user" }, { "content": "{\"Intervention\": [], \"Outcome\": [], \"Participant\": []}", "role": "assistant" } ]

[ { "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:\nEstimation of net-costs for prevention of occupational low back pain: three case studies from the US.\nAbstract 1:\nBACKGROUND Occupational low back pain ( OLBP ) is widespread in industrialized societies . We present a model to estimate the net economic costs of investments in ergonomic interventions at the company level to reduce work-related low back pain . METHODS Costs of interventions are defined by incorporating not only the costs of investment of equipment and labor , but also by taking into account the avoided costs of lost work time , medical care costs , and productivity improvements . In the net-cost model , all costs are annualized and are calculated at the level of an individual organization . Three case studies have been performed based on data from three companies in the manufacturing sector of the United States using the above approach . RESULTS The net-cost estimates for the three case studies consistently show that ergonomic interventions applied appropriately can result in substantial cost savings for the companies . CONCLUSIONS Although generalizing on the basis of three case studies is not ideal , our analyses show that it might be in the economic interest of management to play a more active role to prevent back pain . Gathering useful retrospective cost data , even on interventions deemed effective by corporate innovators , proved to be extremely difficult . We conclude that it is essential to incorporate a protocol for collecting cost and effectiveness data in the st and ard operating procedures of ergonomists and companies introducing such innovation . We intend to vali date the net-cost model for the monitoring and reporting of such data through prospect i ve studies in a variety of industrial setting s and in countries at various stages of economic development\n\n\nTitle 2:\nEffects of a participatory ergonomics team among hospital orderlies.\nAbstract 2:\nBACKGROUND High rates of work-related injuries are seen among health care workers involved in lifting and transferring patients . We studied the effects of a participatory worker-management ergonomics team among hospital orderlies . METHODS This prospect i ve intervention trial examined work injuries and other outcomes before and after the intervention , with other hospital employees used as a concurrent control . All orderlies in a 1,200-bed urban hospital were studied using passively collected data ( mean employment during study period 100 - 110 orderlies ) ; 67 orderlies ( preintervention ) and 88 orderlies ( postintervention ) also completed a question naire . The intervention was the formation of a participatory ergonomics team with three orderlies , one supervisor , and technical advisors . This team design ed and implemented changes in training and work practice s. RESULTS The 2-year postintervention period was marked by decreased risks of work injury ( RR = 0.50 , 95 % CI 0.35 - 0.72 ) , lost time injury ( RR = 0.26 , 95 % CI 0.14 - 0.48 ) , and injury with three or more days of time loss ( RR = 0.19 , 95 % CI 0.07 - 0.53 ) . Total lost days declined from 136.2 to 23.0 annually per 100 full-time worker equivalents ( FTE ) . Annual workers ' compensation costs declined from $ 237/FTE to $ 139/FTE . The proportion of workers with musculoskeletal symptoms declined and there were statistically significant improvements in job satisfaction , perceived psychosocial stressors , and social support among the orderlies . CONCLUSION Substantial improvements in health and safety were seen following implementation of a participatory ergonomics program\n\n\nTitle 3:\nA randomised controlled trial evaluating the effects of two workstation interventions on upper body pain and incident musculoskeletal disorders among computer operators\nAbstract 3:\nBackground : Call centre work with computers is associated with increased rates of upper body pain and musculoskeletal disorders . Methods : This one year , r and omised controlled intervention trial evaluated the effects of a wide forearm support surface and a trackball on upper body pain severity and incident musculoskeletal disorders among 182 call centre operators at a large healthcare company . Participants were r and omised to receive ( 1 ) ergonomics training only , ( 2 ) training plus a trackball , ( 3 ) training plus a forearm support , or ( 4 ) training plus a trackball and forearm support . Outcome measures were weekly pain severity scores and diagnosis of incident musculoskeletal disorder in the upper extremities or the neck/shoulder region based on physical examination performed by a physician blinded to intervention . Analyses using Cox proportional hazard models and linear regression models adjusted for demographic factors , baseline pain levels , and psychosocial job factors . Results : Post-intervention , 63 participants were diagnosed with one or more incident musculoskeletal disorders . Hazard rate ratios showed a protective effect of the armboard for neck/shoulder disorders ( HR = 0.49 , 95 % CI 0.24 to 0.97 ) after adjusting for baseline pain levels and demographic and psychosocial factors . The armboard also significantly reduced neck/shoulder pain ( p = 0.01 ) and right upper extremity pain ( p = 0.002 ) in comparison to the control group . A return-on-investment model predicted a full return of armboard and installation costs within 10.6 months . Conclusion : Providing a large forearm support combined with ergonomic training is an effective intervention to prevent upper body musculoskeletal disorders and reduce upper body pain associated with computer work among call centre employees\n\n\nTitle 4:\nA controlled trial of an educational program to prevent low back injuries.\nAbstract 4:\nBACKGROUND Low back injuries are common and costly , accounting for 15 to 25 percent of injuries covered by workers ' compensation and 30 to 40 percent of the payments made under that program . The high costs of injury , the lack of effective treatment . and the evidence that there are behavioral risk factors have led to widespread use of employee education programs that teach safe lifting and h and ling . The effectiveness of those programs , however , has received little rigorous evaluation . METHODS We evaluated an educational program design ed to prevent low back injury in a r and omized , controlled trial involving about 4000 postal workers . The program , similar to that in wide use in so-called back schools , was taught by experienced physical therapists . Work units of workers and supervisors were trained in a two-session back school ( three hours of training ) , followed by three to four reinforcement sessions over the succeeding few years . Injured subjects ( from both the intervention and the control groups ) were r and omized a second time to receive either training or no training after their return to work . RESULTS Physical therapists trained 2534 postal workers and 134 supervisors . Over 5.5 years of follow-up , 360 workers reported low back injuries , for a rate of 21.2 injuries per 1000 worker-years of risk . The median time off from work per injury was 14 days ( range , 0 to 1717 ) ; the median cost was $ 204 ( range , zero to $ 190,380 ) . After their return to work , 75 workers were injured again . Our comparison of the intervention and control groups found that the education program did not reduce the rate of low back injury , the median cost per injury , the time off from work per injury , the rate of related musculoskeletal injuries , or the rate of repeated injury after return to work ; only the subjects ' knowledge of safe behavior was increased by the training . CONCLUSIONS A large-scale , r and omized , controlled trial of an educational program to prevent work-associated low back injury found no long-term benefits associated with training\n\n\nTitle 5:\nThe Cost‐Effectiveness of a Back School Program in Industry: A Longitudinal Controlled Field Study\nAbstract 5:\nTo define the cost-effectiveness of a back school program in industry , a controlled longitudinal field study was carried out in a Dutch bus company . The experimental group received a program consisting of information on back care , physical fitness , nutrition , stress , and relaxation . Objective data on absenteeism were collected and compared during a 6-year period for the control and experimental groups . Results showed that a tailor-made back school program reduced absenteeism by at least 5 days per year per employee , therefore being cost-effective to industry . A reduction was not observed in incidence , but in mean length of absenteeism . This effect turned out to be persistent during a 2-year period following the program", "role": "user" }, { "content": "Results In the manufacturing and warehousing sector strong evidence was found in support of the financial merits of ergonomic interventions from a firm perspective .\nIn the administrative support and health care sectors moderate evidence was found , in the transportation sector limited evidence , and in remaining sectors insufficient evidence .\nConclusions Most intervention studies focus on effectiveness .\nFew consider their financial merits .\nOften only a small part of the overall evaluation of many studies focused on evaluating their cost-effectiveness", "role": "assistant" } ]

[ { "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(OBJECTIVE) To determine how often primary care physicians prescribe eradication therapy for peptic ulcer disease (PUD) and nonulcer dyspepsia (NUD).\n(STUDY DESIGN) During a 2-year period (1998-2000) we analyzed data concerning patients with PUD or NUD seen by 80 Italian primary care physicians uniformly distributed throughout the country. We classified patients as having a definitive or a presumptive diagnosis on the basis of the completeness of the diagnostic workup and interpreted the prescription of antibiotics for dyspepsia as evidence of attempted eradication of Helicobacter pylori.\n(POPULATION) Consecutive ambulatory patients.\n(OUTCOMES MEASURED) The frequency with which predefined groups of patients received eradication therapy.\n(RESULTS) Of 6866 patients, 690 (10%) received eradication therapy. Of 2162 patients with PUD, 596 (27.6%) received eradication therapy; of 4704 patients with NUD, however, only 94 (2%) received this treatment (P =.0001). A total of 341 (37.7%) of 904 PUD patients with a definitive diagnosis were given eradication therapy and 255 (20.3%) of 1258 PUD patients with a presumptive diagnosis were given therapy (P&lt.0001). In NUD patients, 7 of 743 (0.9%) with a definitive diagnosis received eradication therapy, while 87 (2.2%) of 3961 of those with a presumptive diagnosis were given the same therapy (P =.025).\n\nQuestion:\nDo primary care physicians underprescribe antibiotics for peptic ulcer disease?\n\nAnswer:", "role": "user" }, { "content": "YES", "role": "assistant" } ]

[ { "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 it feasible to obtain DNA read lengths that exceed 30 Kb?\n\nContext: Single-molecule, real-time sequencing (SMRT) developed by Pacific BioSciences produces longer reads than secondary generation sequencing technologies such as Illumina. The long read length enables PacBio sequencing to close gaps in genome assembly, reveal structural variations, and identify gene isoforms with higher accuracy in transcriptomic sequencing.\nThird-generation sequencing, with read lengths>10 kb, will improve the assembly of complex genomes, but these techniques require high-molecular-weight genomic DNA (gDNA), and gDNA extraction protocols used for obtaining smaller fragments for short-read sequencing are not suitable for this purpose.\nThe emergence and development of so called third generation sequencing platforms such as PacBio has permitted exceptionally long reads (over 20 kb) to be generated.", "role": "user" }, { "content": "no", "role": "assistant" } ]

[ { "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\nA human putative lymphocyte G0 / G1 switch gene homologous to a rodent gene encoding a zinc-binding potential transcription factor. G0S24 is a member of a set of genes (putative G0 / G1 switch regulatory genes) that are expressed transiently within 1-2 hr of the addition of lectin or cycloheximide to human blood mononuclear cells. Comparison of a full-length cDNA sequence with the corresponding genomic sequence reveals an open reading frame of 326 amino acids, distributed across two exons. Potential phosphorylation sites include the sequence PSPTSPT, which resembles an RNA polymerase II repeat reported to be a target of the cell cycle control kinase cdc2. Comparison of the derived protein sequence with those of rodent homologs allows classification into three groups. Group 1 contains G0S24 and the rat and mouse TIS11 genes (also known as TTP, Nup475, and Zfp36). Members of this group have three tetraproline repeats. Groups 1 and 2 have a serine-rich region and an \" arginine element \" (RRLPIF) at the carboxyl terminus. All groups contain cysteine-and histidine-rich putative zinc finger domains and a serine-phenylalanine \" SFS \" domain similar to part of the large subunit of eukaryotic RNA polymerase II. Comparison of group 1 human and mouse genomic sequences shows high conservation in the 5' flank and exons. A CpG island suggests expression in the germ line. G0S24 has potential sites for transcription factors in the 5' flank and intron; these include a serum response element. Protein and genomic sequences show similarities with those of a variety of proteins involved in transcription, suggesting that the G0S24 product has a similar role.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"human blood mononuclear cells\"], \"DNA\": [\"rat and mouse TIS11 genes\", \"open reading frame\", \"exons\", \"Nup475\", \"G0S24\", \"rodent gene\", \"full - length cDNA sequence\", \"5\\u0027 flank\", \"Zfp36\", \"intron\", \"serum response element\", \"putative G0 / G1 switch regulatory genes\", \"human putative lymphocyte G0 / G1 switch gene\", \"TTP\", \"human and mouse genomic sequences\"], \"Protein\": [\"RNA polymerase II repeat\", \"transcription factors\", \"arginine element\", \"cysteine - and histidine - rich putative zinc finger domains\", \"PSPTSPT\", \"zinc - binding potential transcription factor\", \"three tetraproline repeats\", \"carboxyl terminus\", \"eukaryotic RNA polymerase II\", \"serine - rich region\", \"phosphorylation sites\", \"G0S24 product\", \"RRLPIF\", \"serine - phenylalanine \\\" SFS \\\" domain\", \"lectin\", \"cell cycle control kinase cdc2\"], \"RNA\": []}", "role": "assistant" } ]

[ { "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\nDisease management programs for patients with type 2 diabetes mellitus in Germany: a longitudinal population-based descriptive study The primary aim of the disease management program (DMP) for patients with diabetes mellitus type 2 is to improve the quality of health care and the treatment process. 12 years after its introduction in Germany, there is still no consensus as to whether DMP has been effective in reaching these goals. A retrospective longitudinal population-based study between 2004 and 2015 were conducted to evaluate the DMP for type 2 diabetes in Bavaria using routinely collected patient medical records hold from the National Association of Statutory Health Insurance Physicians of Bavaria. During the first 12 years of DMP, the number of participants increased continually to reach 580,222 in 2015. The proportion of participants older than 70 years increased during the observation from 41.6 to 51.1%. The percentage of smokers increased slightly from 9 to 11%. Similarly, the distribution of body mass index remained with approximately 50% of patients having a body mass index >30 kg/m(2). Control of HbA1c was without an appreciable change over the course, with between 8.3 and 9.4% of all patients with uncontrolled values higher than 8.5%. Prescription of metformin increased from 40.5% in 2004 to 54.1% in 2015. Among patients receiving insulin, the proportion receiving a combined therapy with metformin increased from 28.4% in 2004 to 50.8% in 2015. In contrast, the percentage with insulin monotherapy decreased from 55.4 to 33.7%. The proportion of patients with a diabetic education increased within the course from 12.8 to 29.3%. Data from the German DMP for type 2 diabetes demonstrates an improvement in the quality of care with respect to pharmacotherapy and patient education and therefore to an improved adherence to guidelines. However, no appreciable improvement was observed with regard to smoking status, obesity or HbA1c control.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"diabetes mellitus type 2\", \"type 2 diabetes\", \"obesity\", \"type 2 diabetes mellitus\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"HbA1c\", \"metformin\", \"insulin\"], \"ClinicalAttribute\": [\"body mass index\", \"smoking status\"], \"Eukaryote\": [], \"Finding\": [\"improve\", \"smokers\"], \"Food\": [], \"HealthCareActivity\": [\"diabetic education\", \"Prescription\", \"Disease management programs\", \"quality of care\", \"pharmacotherapy\", \"monotherapy\", \"evaluate\", \"DMP\", \"disease management program\", \"National Association of Statutory Health Insurance\", \"combined therapy\", \"health care\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"medical records\", \"guidelines\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [\"participants\"], \"ProfessionalOrOccupationalGroup\": [\"Physicians\"], \"ResearchActivity\": [\"population-based descriptive study\", \"population-based study\"], \"SpatialConcept\": [\"German\", \"Germany\", \"longitudinal\"], \"Virus\": []}", "role": "assistant" } ]

[ { "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: [\"UnapprovedDrug\", \"Brand\", \"DrugGroup\", \"Drug\"].\n\nPlease return the output as a JSON object of the format: {\"Brand\": [\"Aspirin\", ...], \"DrugGroup\": [\"Salicylate\", ...], \"Drug\": [\"Phenobarbital\", ...], \"UnapprovedDrug\": [\"Heroin\", ...]}. 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 action of nondepolarizing relaxants is augmented by Enflurane. Less than the usual amounts of these medicines should be used. If the usual amounts of nondepolarizing relaxants are given, the time for recovery from neuromuscular blockade will be longer in the presence of Enflurane than when halothane or nitrous oxide with a balanced technique are used.", "role": "user" }, { "content": "{\"Brand\": [], \"Drug\": [\"Enflurane\", \"halothane\", \"nitrous oxide\"], \"DrugGroup\": [], \"UnapprovedDrug\": []}", "role": "assistant" } ]

[ { "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\nClinical Study to Assess the Efficacy and Safety of a Citrus Polyphenolic Extract of Red Orange, Grapefruit, and Orange (Sinetrol-XPur) on Weight Management and Metabolic Parameters in Healthy Overweight Individuals. The present study investigated the efficacy and safety effects of Sinetrol-XPur (polyphenolic citrus dry extract) in weight management; metabolic parameters; and inflammatory, glycemic and oxidative status. In a 12-week, randomized, double-blind, placebo-controlled trial, Sinetrol-XPur was given to overweight subjects twice daily with meals in the tested group (N = 47) versus a placebo group (N = 48). Waist and hip circumference and abdominal fat were decreased in the Sinetrol-XPur group as compared with the placebo group (p < 0.0001) (-5.71% vs -1.56% for waist, -4.71% vs -1.35% for hip and -9.73% vs -3.18% for fat). Inflammatory markers were reduced (C-reactive protein: -22.87% vs +61%; fibrinogen: -19.93% vs -1.61%, p < 0.01). Oxidative stress was lowered as seen by the reduction of malondialdehyde (-14.03% vs 2.76%) and the increase in superoxide dismutase and glutathione (17.38% vs 2.19% and 4.63% vs -2.36%, respectively, p < 0.01). No adverse effects were observed. Kidney, liver, and lipid panels remained unchanged. These results indicated that Sinetrol-XPur supplementation is a viable option for reducing abdominal fat, waist and hip circumference, and body weight and for improving inflammatory, glycemic, and oxidative status in healthy overweight individuals. Copyright © 2013 John Wiley & Sons, Ltd.", "role": "user" }, { "content": "{\"Chemical\": [\"glutathione\", \"malondialdehyde\", \"superoxide\"]}", "role": "assistant" } ]

[ { "content": "Given an abstract from a research paper, your task is to identify and label relationships between chemical compounds and genes mentioned in the abstract.\n\nThe relationship type must be one of ['DOWNREGULATOR', 'SUBSTRATE', 'INDIRECT-REGULATOR', 'PART-OF', 'MODULATOR-ACTIVATOR', 'REGULATOR', 'INHIBITOR', 'COFACTOR', 'UPREGULATOR', 'ACTIVATOR', 'ANTAGONIST', 'NOT', 'INDIRECT-DOWNREGULATOR', 'SUBSTRATE_PRODUCT-OF', 'INDIRECT-UPREGULATOR', 'AGONIST', 'PRODUCT-OF', 'MODULATOR', 'DIRECT-REGULATOR', 'UNDEFINED', 'AGONIST-INHIBITOR', 'AGONIST-ACTIVATOR', 'MODULATOR-INHIBITOR'].\n\nPlease format your output as a JSON array. Each entry in the array should express a single relation, formatted as [\"<Entity_A>\", \"<RELATION_A_B>\", \"<Entity_B>\"]. If no relations can be found, please output an empty JSON array [].\n\nAbstract:\n\nMechanisms of agonist-induced down-regulation of the human kappa-opioid receptor: internalization is required for down-regulation. Previously, we showed that the human kappa-opioid receptor (hkor) stably expressed in Chinese hamster ovary (CHO) cells underwent down-regulation after prolonged U50,488H treatment. In the present study, we determined the mechanisms underlying this process. U50, 488H caused a significant down-regulation of the hkor, although etorphine did not. Neither U50,488H nor etorphine caused down-regulation of the rat kappa-opioid receptor. Thus, similar to internalization, there are agonist and species differences in down-regulation of kappa-opioid receptors. Expression of the dominant negative mutants arrestin-2 (319-418) or dynamin I-K44A significantly reduced U50,488H-induced down-regulation of the hkor. Coexpression of GRK2 or GRK2 and arrestin-2 permitted etorphine to induce down-regulation of the hkor, although expression of arrestin-2 or dynamin I alone did not. Expression of the dominant negative mutants rab5A-N133I or rab7-N125I blunted U50,488H-induced down-regulation. Pretreatment with lysosomal enzyme inhibitors [ (2S, 3S) trans-epoxysuccinyl-L-leucylamido-3-methylbutane ethyl ester or chloroquine ] or proteasome inhibitors (proteasome inhibitor I, MG-132, or lactacystin) decreased the extent of U50,488H-induced down-regulation. A combination of chloroquine and proteasome inhibitor I abolished U50,488H-induced down-regulation. These results indicate that U50,488H-induced down-regulation of the hkor involves GRK-, arrestin-2-, dynamin-, rab5-, and rab7-dependent mechanisms and receptors seem to be trafficked to lysosomes and proteasomes for degradation. Thus, U50,488H-induced internalization and down-regulation of the hkor share initial common mechanisms. To the best of our knowledge, these results represent the first report on the involvement of both rab5 and rab7 in agonist-induced down-regulation of a G protein-coupled receptor. In addition, this study is among the first to show the involvement of proteasomes in agonist-induced down-regulation of a G protein-coupled receptor.", "role": "user" }, { "content": "[[\"U50,488H\", \"DOWNREGULATOR\", \"human kappa-opioid receptor\"], [\"U50,488H\", \"DOWNREGULATOR\", \"hkor\"], [\"etorphine\", \"NOT\", \"hkor\"], [\"lactacystin\", \"INHIBITOR\", \"proteasome\"], [\"U50,488H\", \"NOT\", \"rat kappa-opioid receptor\"], [\"etorphine\", \"DOWNREGULATOR\", \"hkor\"], [\"etorphine\", \"NOT\", \"rat kappa-opioid receptor\"], [\"MG-132\", \"INHIBITOR\", \"proteasome\"], [\"U50 \", \"488H\", \"DOWNREGULATOR\", \"hkor\"]]", "role": "assistant" } ]

[ { "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:\nAdvantages of CO2 laser use in surgical management of otosclerosis.\nAbstract 1:\nBACKGROUND Otosclerosis is a progressive osteo-destructive disorder of the bony labyrinth in which the fixation of the stapes causes the hearing loss . The aim of this study was the postoperative determination of parameters of the effect of surgical intervention on hearing and the incidence of complications and , on the basis of the differences in the examined parameters of the study , the estimation of the efficacy of the two mentioned surgical techniques in the treatment of otosclerosis . METHODS In our research 40 patients with conductive hearing loss caused by otosclerosis underwent surgery with CO2 laser . Functional results were compared postoperatively with the results of 40 patients operated by the classical technique without the use of CO2 laser . The research was accomplished as a prospect i ve comparative study . RESULTS The air-bone interval ( gap ) as the difference between the rim of air and bone conductivity for separate frequencies did not significantly differ between the control and the experimental group . Both methods were effective in closing the air-bone gap with the rates of closure to within 10 dB in 82.6 % and 75.3 % for the laser and drill , respectively . The incidence of tinnitus was significantly lower in patients who underwent surgery with CO2 laser . The frequency of intraoperative and postoperative complications was significantly lower in the laser group . Differences were statistically significant for all parameters ( p < 0.05 ) . CONCLUSION On the basis of the degree of postoperative hearing improvement , tinnitus and the incidence of complications it can be concluded that the use of CO2 laser during inverse stapedoplasty represents an effective and safe method , justifying the promotion of its use in the surgical management of otosclerosis\n\n\nTitle 2:\nEffect of the stapedotomy technique on early post-operative hearing results--Preliminary results.\nAbstract 2:\nOBJECTIVE To compare three stapedotomy modalities used to fenestrate the stapes footplate in patients with primary otosclerosis . MATERIAL S The non-r and omized and unblinded one-center study included 48 patients with primary otosclerosis who underwent stapes surgery between May 2008 and April 2009 . The patients were divided into three groups ( single shot and two-shot CO(2 ) laser stapedotomy , perforator ) depending on the modality used for stapedotomy . Bone conduction ( BC ) and air conduction ( AC ) thresholds , air-bone gap ( ABG ) , and the difference between mean pre-operative and 2- to 3-week post-operative BC thresholds were analyzed . RESULTS The temporary BC deterioration was most pronounced at 6 and 8kHz after 2-shot laser stapedotomy . A significant drop in AC or BC was not found in any of our 48 patients . Age , high-dose cortisone therapy , and ' preoperative hearing ' did not influence the post-operative hearing results . CONCLUSION Even though the number of patients presented here was small and statistical analysis was limited , the study showed a trend toward worse BC thresholds at 6 and 8kHz after a second shot CO(2 ) application . Whenever possible , treatment should avoid a second laser shot on the already opened inner ear with the laser parameters used for the initial shot\n\n\nTitle 3:\nStapedotomy with and without piezosurgery: 4 years' experience.\nAbstract 3:\nOBJECTIVE The aim of this study was to present our experiences and results of stapedotomy performed with and without the piezoelectric device . DESIGN The article evaluates and compares the use of the piezoelectric device in performing primary stapedotomy in patients affected by otosclerosis with the traditional method of microdrilling . SETTING The study was conducted with 100 patients in the Department of Otolaryngology of the University of Genoa ( Italy ) , between January 2007 and January 2008 . METHODS A prospect i ve , r and omized , controlled trial was undertaken on 100 stapedotomy patients performed using the piezoelectric device ( 50 patients ) or the microdrill ( 50 patients ) . MAIN OUTCOME MEASURES Before surgery and at 1 and 12 months afterward , all patients underwent the following : otomicroscopic evaluation of the external and middle ear , pure-tone audiometry , tympanometry , transient evoked otoacoustic emissions , distortion product otoacoustic emissions , and auditory brainstem response . RESULTS All patients treated with the piezoelectric device had an air-bone gap reduction , with a closure of the air-bone gap within 10 dB ; 44 ( 88 % ) patients who underwent traditional surgery had an air-bone gap reduction , with a closure of the air-bone gap within 10 dB. CONCLUSION All of our postoperative data confirm the safety of the device on the anatomic structures of the middle and inner ear and demonstrate the efficacy of the piezoelectric device in terms of safety , cutting precision , and protection of anatomic structures and its applicability to stapedotomy\n\n\nTitle 4:\nStatistical Analysis of Otosclerosis Surgery Performed by Jean Marquet\nAbstract 4:\nThe early and long-term hearing results of 1,681 primary otosclerosis operations performed by the same surgeon , Jean Marquet , were review ed retrospectively and analyzed with very strict statistical st and ards . Significantly better short- and long-term results were achieved with the stapedotomy technique compared to total stapedectomy , mainly at the higher frequencies ( 4 and 8 kHz ) important for speech discrimination . Whatever technique was used to open the footplate ( micropick , microdrill , or laser ) , no statistical audiometric difference could be found . The results were equal whether or not the stapedial tendon was preserved . Perioperative problems like pronounced oozing , difficult anatomic relationships , and accidental perilymph aspiration could affect hearing at higher frequencies . The calibrated hole technique was equally as good as conventional oval window sealing in sealing of the fenestra to prevent fistula . The stapedotomy technique was found the safest , having fewer complications\n\n\nTitle 5:\nStapedotomy: Is the Color of the Footplate Important in the Choice of the Type of Perforator?\nAbstract 5:\nObjective : To valuate the influence of the color of footplate in the choice of the type of perforator . Study Design : Prospect i ve study . Level of Evidence 1b . Setting s : Single hospital study in Avellino , Italy . Subjects and Methods : From the first of September 2008 to the 30th of June 2009 , we considered 83 patients affected by otosclerosis . Patients were divided into 2 groups under footplate perforator used . In the group A , manual perforators ( the more traumatic drills ) were used . In group B , CO2 laser ( the less traumatic drill ) was used . The 2 groups under the color of visible portion of the footplate before removing the stapes superstructure were divided in 2 subgroups . Group IA includes 33 blue footplates and Group IIA 10 white footplates . Group IB includes 30 blue footplates and Group IIB 10 white footplates . We estimated whether there is statistical correlation between type of perforator , incidence of footplate complications , and color of footplate . Results : In group IA , we had 0 complications . In group IB , we had 0 complications . In group IIA , we had 7 complications . In group IIB , we had 2 complications . Comparison of incidence of footplate complications showed no statistical significance between group IA and IB and statistical significance between group IIA and IIB . Conclusion : The footplate color is important in the choice of the type of perforator\n\n\nTitle 6:\nThe Influence of the Sequence of Surgical Steps on Complications Rate in Stapedotomy\nAbstract 6:\nObjective : To assess whether the incidence of complications of stapes surgery depended on the sequence of surgical steps and CO2 laser use in stapes surgery . Study Design and Setting : Retrospective and prospect i ve analysis of 420 consecutive stapedotomies was set in tertiary referral University Hospital . Patients : 376 patients with otosclerosis in whom 420 primary stapedotomies were performed . Intervention : Stapedotomy under local anesthesia using manual perforators and CO2 laser . Main Outcome Measure : The incidence of incus subluxation , floating footplate during stapedotomy . Results : Comparison of the incidence of incus luxation in groups with the piston inserted after removal of the stapes arch , and groups with the piston inserted on the intact ossicular chain showed statistical significance . In the group where perforation of the footplate was performed after removal of the stapes arch floating footplate occurred more often than in groups with reversed sequence of steps . Conclusion : Perforation of the footplate before removal of stapes arch reduces the risk of floating footplate , and placing the prosthesis on the incus before removal of stapes arch reduces the risk of subluxation of the incus . CO2 laser stapedotomy with reversed sequence of steps was the safest method of stapes surgery\n\n\nTitle 7:\nLaser stapedotomy.\nAbstract 7:\nThirty-four ears with conductive hearing loss due to otosclerosis were operated upon using the laser stapedotomy technique . Audiological results were compared with the results of 316 non-laser stapedotomies . The post-operative air-bone gap , calculated as the difference between the post-operative air and bone conduction levels , was smaller with the laser stapedotomy group . Also , the bone conduction showed significant improvement with the use of laser . Significant sensorineural hearing loss was not found in any of the laser-treated patients . According to our results , we concluded that laser is of benefit in stapes surgery for improving the hearing results and minimizing the inner ear trauma", "role": "user" }, { "content": "Our overall results suggest that the laser stapedotomy had significantly better hearing results than non-laser stapedotomy .", "role": "assistant" } ]

[ { "content": "You will be shown the title of a chemistry paper, together with sections excerpted from the body of the paper. The paper sections may include HTML tags like `<p>` and `</p>`; please ignore these. Your task is to write an abstract for the paper. Your response should include the abstract and no other text.\n\nTitle:\nTime-Resolved Visual Chiral Discrimination of Cysteine Using Unmodified CdTe Quantum Dots\n\nPaper sections:\n\n<p>Chirality is known as a determinative feature in biological phenomena. Many drugs, bioactive compounds and organic molecules exist in chiral form. In general, two enantiomers of a chiral compound exhibit different biochemical activity, pharmaceutical and physiological effects, depending on their absolute configurations [1][2][3][4] . Enantiomeric recognition of amino acids, as essential bioactive substances and building blocks of proteins, polypeptides, and various drugs, is of vital importance in both process development and quality control [5][6][7] .</p><p>Various methods have been reported to distinguish the chirality of amino acids, including high performance liquid chromatography [8][9][10] , gas chromatography 11 , mass spectrometry 12 , electrochemistry [13][14][15] , and capillary electrophoresis 16,17 . However, most of these techniques require complicated sample pretreatment and sophisticated instrumentation which makes them impractical for real-time analysis. Rapid enantiosensing technique, i.e., circular dichroism (CD), suffers from low sensitivity and low tolerance against contamination 18 . Thus, it is intriguing and useful to develop a rapid, simple, sensitive, and high-throughput assay especially, a solution-based sensor capable of visual discrimination of enantiomers. Colorimetric and fluorometric assays are highly demanded due to their ease of detection, even by naked eye and without the need of elaborate equipment.</p><p>Due to their unique optical properties, quantum dots (e.g., cadmium-telluride (CdTe) QDs) 19 , gold, and silver nanoparticles 20,21 possess a tremendous potential for applications in optical sensing. Reported colorimetric and fluorimetric chiral recognition probes for amino acids are based on either the inherent chirality of metal surfaces [22][23][24] or chiral molecules adsorbed on the nanoparticle surface 7,[25][26][27][28][29][30] . Metallic nanoparticles with intrinsic chiral structure are numerable and the adsorption of chiral molecules onto the surface of nanoparticles leads to complex chiral detection.</p><p>In the present study we report a new strategy for chiral recognition in aqueous solution using CdTe QDs. We show that both D-and L-cysteine induce aggregation in CdTe QDs, but with different kinetics leading to distinct emission spectra and color change (see Fig. 1).</p>\n\nResults and Discussion\n<p>Time-resolved chiral recognition. TGA-capped CdTe QDs exposing green emission were directly synthesized in aqueous solution. The absorption and fluorescence spectra of the as-prepared thioglycolic acid (TGA)capped CdTe QDs are demonstrated in Fig. S1 in Supporting Information (SI). L-and D-cysteine were added to the QDs' solution and after 15 min NaOH was inserted to the mixture. Time-course emission behavior of QDs toward D-and L-cysteine is shown in Fig. 2. The emission of QDs was quenched thoroughly upon the addition of cysteine in the basic media. Recovery in fluorescence-intensity and redshift of the spectral peak were thereafter observed. In the case of L-cysteine, the fluorescence intensity reached a maximum value after 138 min with an intensity very close to the emission of the blank (solution with no cysteine, shown in Fig. S2). However, for D-cysteine, it took 78 min to obtain the maximal fluorescence intensity which was twice as high as the blank. In both cases, after reaching a maximum, fluorescence quenching and further redshift in the emission peak were observed.</p><p>As shown in Fig. 2, the presence of cysteine in solution triggered fluorescence quenching which can be attributed to the photoinduced electron transfer (PET) 31 . Unprotonated amino groups are particularly suitable as electron donors in PET mechanism 32 . Therefore, in the presence of cysteine, containing an amino unit, PET can take place between the nitrogen lone pair and QDs, causing quenching (see Fig. 3).</p><p>Due to the high binding affinity of thiol groups toward Cd atoms at the surface of CdTe QDs, cysteine can attach to CdTe through the formation of Cd-S bonds 33,34 . Therefore, after the addition of cysteine to QDs solution, cysteine was gradually bonded to the surface of QDs. It is assumed that the affinity of thiol to QDs can actually push the amino group away from the surface of QDs. Thus, considering the strong dependency of PET on the electron donor-fluorophore distance 32 , PET was suppressed and allowed the fluorescence to be switched on (see Fig. 3).</p><p>The rate of fluorescence-intensity recovery by D-cysteine was faster than by L-cysteine. In addition, a higher fluorescence-intensity was observed for D-cysteine (see Fig. 2). Compared to L-cysteine, D-cysteine exhibits a stronger interaction affinity to CdTe QDs 34 . Consequently, it is expected that a higher number of D-cysteine compounds can attach to the surface of QDs, which caused enhancement in both the rate of recovery and the emission (due to better passivation of the QDs' surface) 35,36 .</p><p>As demonstrated in Fig. 2, the redshift in the emission spectra was initiated upon the entrance of cysteine in the basic media. The presence of cysteine molecules on the surface of QDs induced the aggregation process due to the hydrogen bonding between the adsorbed thiols. Aggregation of QDs then caused a redshift in the emission spectra that can be explained by two possible reasons: (1) electronic coupling between neighbouring QDs in the aggregates which can lead to a redshift in both absorption and emission spectra; (2) exciton energy transfer between QDs in small distance which will not exhibit any redshift in the absorption spectra 37 . The observed redshift in the absorption spectra, cuased by the aggregation of QDs in the presence of cysteine (see Fig. S4), confirms that the redshift appeared in the emission spectra can be originated from electronic coupling between QDs.</p><p>Another point to be considered from Fig. 2 is that CdTe QDs displayed a gradual quenching after reaching a maximum emission intensity. In agreement with our findings, Koole et al. 37 had reported that exciton energy transfer is absent in small green QDs, while it can occur in aggregated QDs. Furthermore, a reduction in fluorescence intensity can be induced by exciton energy transfer 37 . Over time, the size and the number of aggregates increases which leads to exciton energy transfer between QDs in one aggregate, and consequently causes emission quenching.</p><p>Figure 4 illustrates the peak wavelengths related to the spectra given in Fig. 2, against time. In a certain time, the amount of redshift caused by D-cysteine was more than by L-cysteine. As mentioned earlier, the aggregation of QDs caused redshift in the emission spectra. Therefore, we hypothesized that the rate of aggregation is higher in the presence of D-cysteine, rather than L-cysteine. This can be used for visual discrimination between L-and D-forms of cysteine (see inset in Fig. 4). Over time, the difference in redshifts of QDs declined for both D-and L-cysteine. Dynamic light scattering (DLS) measurements confirm that D-cysteine mediates more aggregated QDs compared to L-cysteine (See Fig. S5). TEM images further confirmed the aggregation of QDs in the presence of cysteine (see Fig. 5). Figure 2c shows representative emitted colors from QDs over time after the addition of D-cysteine and NaOH under UV irradiation.</p>\n\nFluorometric determination of enantiomeric excess.\n<p>Since it is essential to determine enantiomeric excess (i.e., the difference between the mole fractions of enantiomers) in chiral drug and asymmetric catalyst development 38,39 , our chiral assay was applied to quantify the enantiomeric excess of cysteine. NaOH concentration, as an effective parameter on emission, was optimized. The difference between peak wavelengths of QDs' emission in the presence of D-and L-cysteine (∆λ D, L ) was monitored at different concentrations of NaOH (see Fig. S6). ∆λ D, L rised up to 60 mmol L −1 , and then no further change was observed. Therefore, we selected 60 mmol L −1 of NaOH as the optimal concentration for further experiments. The emission spectra of CdTe QDs in different enantiomeric excess of cysteine (total concentration 1 mmol L −1 ) are demonstrated in Fig. 6. The highest and lowest signals were observed for absolute D-and L-cysteine, respectively. A good linear relationship was obtained between emission signal at 530 nm and enantiomeric excess of D-cysteine.</p>\n\nThe response of unmodified CdTe QDs to other α-amino acids. The response of the unmodified\n<p>CdTe QDs in the presence of other α-amino acids including arginine, tryptophan, tyrosine, proline, and histidine was negligible regrdless to their D-and L-forms (see Fig. 7). However, the response of D-cysteine was the highest and distinct from L-cysteine. All α-amino acids consist of a carboxylic acid and an amino functional group. However, cysteine is distinctive from the rest due to the presence of its thiol group. Considering that a chiral CdTe QD was employed in the proposed assay, the key role of the thiol group in the differentiation of Land D-cysteine is evident. In fact, both D-and L-cysteine are bonded to the surface of QDs through S-Cd bond, but with a different strength that makes them distinguishable. The CD measurement (Fig. S7) confirmed that the applied CdTe QDs were achiral. Similarly, the CD spectra of L-and D-cysteine exhibited mirror-image profiles (see Fig. S8). Aditional CD features emerged for the mixture of QDs and cysteine, compared to pure cysteine (see Fig. S9). These features can be attributed to the formation of Cd x (cystine) y complex and to the chirality induced by the absorbed cysteine molecules on QDs surface 34 . This assumption has been experimentally and theoretically proven by Zhou et al. 34 studying CdTe QDs: since an atom with four different substituents produces a chiral center, if all four atomic positions in a tetrahedron formed by Te and Cd atoms are different, a chiral center will be formed. As they have presented, the adsorption of cysteine molecules on the surface of QDs induces four different substituents, resulting in a chiral center.</p>\n\nConclusions\n<p>In summary, a fluorometric chiral recognition assay was developed for detection of cysteine using unmodified CdTe QDs. We found that the rate of QDs' aggregation was quite different in the presence of D-and L-cysteine. The chiral assay took advantage of the aggregation rate of unmodified QDs for enantioselective recognition of cysteines. The emission color variation of QDs revealed its promissing chiral detection of cysteine even by the naked eye. Moreover, this novel chiral sensor can be applied for the measurement of enantiomeric excess. Compared with other developed fluorimetric methods, the present strategy is fascinating mainly because the CdTe QDs employed do not require any labeling or modification with chiral molecules.</p>\n\nMethods\n<p>Reagents. Cysteine and other amino acids were purchased from Merck. Tellurium powder (Te), thioglycolic acid (TGA), Sodium borohydride (NaBH 4 ), and cadmium chloride (CdCl 2 .2H 2 O) were purchased from Sigma. Deionized water was used throughout the experiment.</p><p>Instrumentation. Absorbance spectra were recorded on a Lambda spectrophotometer from Perkin Elmer using 1.0 cm glass cell. The fluorescence spectra were measured on a Cary Eclipse fluorescence spectrometer (Varian) with the use of 1 × l cm quartz cell. All the spectra were recorded at room temperature. Size distributions were obtained using Zetasizer Viscotec 802 at ambient temperature. Circular dichroism (CD) measurements were made using Jasco J-810 CD recorder.</p><p>Synthesis of TGA functionalized CdTe QDs. TGA-capped CdTe QDs were prepared according to the procedure described previously (Ghasemi et al. 2016 40 ). Typically, 2.87 mmol of TGA was added to 10 mL of CdCl 2 solution (0.29 mol L −1 ) and the pH was adjusted to 9.0 with NaOH solution. Then, the solution was stirred under argon bubbling for 5 min. 0.76 mmol of Te powder was separately mixed with 75 mL of NaBH 4 solution (64 mmol L −1 ) under argon flow at 50 °C. After 20 min, 10 mL of pH-adjusted CdCl 2 solution was added, and the temperature was increased to 150 °C. The resulting TGA-capped CdTe QDs with green emission (reaction time 45 min) were taken out and allowed to cool in ice bath.</p>", "role": "user" }, { "content": "Herein, we demonstrate a simple yet novel luminescence assay for visual chiral discrimination of cysteine. Thioglycolic acid (TGA)-capped cadmium-telluride (CdTe) quantum dots (QDs) exposing green emission were directly synthesized in aqueous solution. The interaction between cysteine molecules and CdTe QDs induced the aggregation of QDs via hydrogen bonding. As a result of electronic coupling within these aggregates, a redshift both in the absorption and emission spectra of QDs occured. The difference in the kinetics of the interactions between L-and D-cysteine with CdTe QDs led to chiral recognition of these enantiomers. Addition of D-cysteine to CdTe QDs in a basic media caused a green-to-yellow color change, while no color alteration in QDs emission was observed in the presence of L-cysteine after 2 hours. Notably, the QDs used in the proposed assay are free from any labling/ modification, which makes the present strategy highly attractive for sensing applications. Furthermore, the presented chiral assay is able to determine the enantiomeric excess (ee) of D-cysteine in the whole range of ee values (from −100% to 100%).", "role": "assistant" } ]

[ { "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\nImmunogenicity and safety of a plasma-derived heat-inactivated hepatitis B vaccine ( CLB ) . Studies in volunteers at a low risk of infection with hepatitis B virus . The safety and immunogenicity of a plasma-derived heat-inactivated hepatitis B vaccine ( CLB ) were evaluated in 471 healthy human volunteers , who , both in their occupations and in their private lives , had been at minimal risk of being infected with hepatitis B virus . The first 202 individuals received three 3-micrograms doses of heat-inactivated hepatitis B surface antigen ( HBsAg ) at one-month intervals ( trial A ) . A total of 42 % one month after the first injection , 84 % after two months , and 93 % after five months had become anti-HBs ( antibody to hepatitis B surface antigen ) positive . In a second randomized study ( trial B ) , the immunogenicity of five different dosages of the vaccine was compared in 269 volunteers . When the dose of HBsAg was diminished from 3 micrograms to 1.5 , 0.6 , and 0.25 microgram , no decrease of the anti-HBs response was observed . However , when the dose was diminished to 0.1 microgram of HBsAg , the anti-HBs response dropped significantly to 63 % ( p less than 0.001 ) . In the recipients of all five vaccine dosages , no influence of sex and age was found on the anti-HBs conversion rates . During the eight-month observation period , none of the vaccinees became HBsAg and/or anti-HBc ( antibody to hepatitis B core antigen ) positive , and none developed antibodies associated with autoimmune liver disease . No serious side effects were observed .", "role": "user" }, { "content": "{\"Intervention\": [\"three 3-micrograms doses of heat-inactivated hepatitis B surface antigen ( HBsAg ) at one-month intervals\", \"plasma-derived heat-inactivated hepatitis B vaccine ( CLB )\", \"of five different dosages of the vaccine\"], \"Outcome\": [\"HBsAg and/or anti-HBc ( antibody to hepatitis B core antigen ) positive\", \"Immunogenicity\", \"immunogenicity\", \"safety\", \"anti-HBs response\", \"anti-HBs conversion rates .\", \"serious side effects\", \"antibodies\"], \"Participant\": [\"471\", \"healthy\", \"low risk of infection with hepatitis B virus\", \"hepatitis B virus\"]}", "role": "assistant" } ]

[ { "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\nProteolipoprotein gene analysis in 82 patients with sporadic Pelizaeus-Merzbacher Disease: duplications, the major cause of the disease, originate more frequently in male germ cells, but point mutations do not. The Clinical European Network on Brain Dysmyelinating Disease. Pelizaeus-Merzbacher Disease (PMD) is an X-linked developmental defect of myelination affecting the central nervous system and segregating with the proteolipoprotein (PLP) locus. Investigating 82 strictly selected sporadic cases of PMD, we found PLP mutations in 77%; complete PLP-gene duplications were the most frequent abnormality (62%), whereas point mutations in coding or splice-site regions of the gene were involved less frequently (38%). We analyzed the maternal status of 56 cases to determine the origin of both types of PLP mutation, since this is relevant to genetic counseling. In the 22 point mutations, 68% of mothers were heterozygous for the mutation, a value identical to the two-thirds of carrier mothers that would be expected if there were an equal mutation rate in male and female germ cells. In sharp contrast, among the 34 duplicated cases, 91% of mothers were carriers, a value significantly (chi2 = 9. 20, P <. 01) in favor of a male bias, with an estimation of the male/female mutation frequency (k) of 9. 3 3. Moreover, we observed the occurrence of de novo mutations between parental and grandparental generations in 17 three-generation families, which allowed a direct estimation of the k value (k = 11). Again, a significant male mutation imbalance was observed only for the duplications.", "role": "user" }, { "content": "{\"Disease\": [\"Brain Dysmyelinating Disease\", \"PMD\", \"X-linked developmental defect of myelination\", \"Pelizaeus-Merzbacher Disease\"]}", "role": "assistant" } ]

[ { "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: In patients with both COVID-19 and cancer, immunotherapy might increase the immune system response, which could already be overactive because of the COVID-19 infection.\n\nAbstract:\nThe rapid global spread of SARS-CoV-2 and resultant mortality and social disruption have highlighted the need to better understand coronavirus immunity to expedite vaccine development efforts.\nMultiple candidate vaccines, designed to elicit protective neutralising antibodies targeting the viral spike glycoprotein, are rapidly advancing to clinical trial.\nHowever, the immunogenic properties of the spike protein in humans are unresolved.\nTo address this, we undertook an in-depth characterisation of humoral and cellular immunity against SARS-CoV-2 spike in humans following mild to moderate SARS-CoV-2 infection.\nWe find serological antibody responses against spike are routinely elicited by infection and correlate with plasma neutralising activity and capacity to block ACE2/RBD interaction.\nExpanded populations of spike-specific memory B cells and circulating T follicular helper cells (cTFH) were detected within convalescent donors, while responses to the receptor binding domain (RBD) constitute a minor fraction.\nUsing regression analysis, we find high plasma neutralisation activity was associated with increased spike-specific antibody, but notably also with the relative distribution of spike-specific cTFH subsets.\nThus both qualitative and quantitative features of B and T cell immunity to spike constitute informative biomarkers of the protective potential of novel SARS-CoV-2 vaccines.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "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:\nPachytenespermatocytenucleifrompostpubertalmutanttestescouldassemblenormalSCcoresandexhibitedfullsynapsisofchromosomesasjudgedbycolabelingofSYCP1andSYCP3alongthefulllengthsofallautosomes(Figure4A).", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Below are the Abstract, Introduction, and Conclusion sections of a computer science research paper. Please summarize the main contribution of the work in a single sentence. Your response should include the summary sentence and no additional text.\n\nPaper text:\n\nDeep Learning has received significant attention due to its impressive performance in many state-of-the-art learning tasks.\nUnfortunately, while very powerful, Deep Learning is not well understood theoretically and in particular only recently results for the complexity of training deep neural networks have been obtained.\nIn this work we show that large classes of deep neural networks with various architectures (e.g., DNNs, CNNs, Binary Neural Networks, and ResNets), activation functions (e.g., ReLUs and leaky ReLUs), and loss functions (e.g., Hinge loss, Euclidean loss, etc) can be trained to near optimality with desired target accuracy using linear programming in time that is exponential in the input data and parameter space dimension and polynomial in the size of the data set; improvements of the dependence in the input dimension are known to be unlikely assuming $P\\neq NP$, and improving the dependence on the parameter space dimension remains open.\nIn particular, we obtain polynomial time algorithms for training for a given fixed network architecture.\nOur work applies more broadly to empirical risk minimization problems which allows us to generalize various previous results and obtain new complexity results for previously unstudied architectures in the proper learning setting.", "role": "user" }, { "content": "Using linear programming we show that the computational complexity of approximate Deep Neural Network training depends polynomially on the data size for several architectures", "role": "assistant" } ]

[ { "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: What drug treatment can cause a spinal epidural hematoma?\n\nContext: Spinal epidural hematomas are rare entity in neurosurgery practice. Most of them are spontaneous due to anticoagulant therapy and called spontaneous spinal epidural hematomas (SSEHs).\nSpinal epidural hematoma (SEH) is a rare disease that causes cord compression and neurologic deficit. Spontaneous SEH is related to minor trauma, bleeding disorders, and anticoagulant medications.\nChronic Spinal Subdural Hematoma Associated with Antiplatelet Therapy.\npinal subdural hematoma associated with antiplatelet therapy\nThe authors report a case of acute spinal epidural hematoma occurring in a patient receiving antiplatelet drugs.\nSpontaneous epidural hematoma of the spine (SEHS) is an extremely rare entity. Patients known to have thrombophilia or on anticoagulant drugs are the most affected\nMost cases of spinal hematoma have a multifactorial etiology whose individual components are not all understood in detail. In up to a third of cases (29.7%) of spinal hematoma, no etiological factor can be identified as the cause of the bleeding. Following idiopathic spinal hematoma, cases related to anticoagulant therapy and vascular malformations represent the second and third most common categories. Spinal and epidural anesthetic procedures in combination with anticoagulant therapy represent the fifth most common etiological group and spinal and epidural anesthetic procedures alone represent the tenth most common cause of spinal hematoma. Anticoagulant therapy alone probably does not trigger spinal hemorrhage.\nWe report the case of a man of 65 who, at 20 and 37 days from surgery of C6 corpectomy, experienced two epidural hematomas at C7-D1. We assume that the pathogenic cause of this rare disease was an overlap between three main factors: the surgical aggression of the internal anterior epidural venous plexus; a possible increase of intra-thoracic pressure due to chronic obstructive pulmonary disease; and double antiplatelet drug therapy.", "role": "user" }, { "content": "Anticoagulant therapy", "role": "assistant" } ]

[ { "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: If we allow group convolution to obtain input data from different groups (as shown in Fig 1 (b)), the input and output channels will be fully related. Specifically, for the feature map generated from the previous group layer, we can first divide the channels in each group into several subgroups, then feed each group in the next layer with different subgroups. This can be efficiently and elegantly implemented by a channel shuffle operation (Fig 1 (c)): suppose a convolutional layer with g groups whose output has g\\times n channels; we first reshape the output channel dimension into (g,n), transposing and then flattening it back as the input of next layer. Note that the operation still takes effect even if the two convolutions have different numbers of groups. Moreover, channel shuffle is also differentiable, which means it can be embedded into network structures for end-to-end training. Channel shuffle operation makes it possible to build more powerful structures with multiple group convolutional layers. In the next subsection we will introduce an efficient network unit with channel shuffle and group convolution. To address the issue, a straightforward solution is to apply channel sparse connections, for example group convolutions, also on 1\\times 1 layers. By ensuring that each convolution operates only on the corresponding input channel group, group convolution significantly reduces computation cost. However, if multiple group convolutions stack together, there is one side effect: outputs from a certain channel are only derived from a small fraction of input channels. Fig 1 (a) illustrates a situation of two stacked group convolution layers. It is clear that outputs from a certain group only relate to the inputs within the group. This property blocks information flow between channel groups and weakens representation.\n\nQuestion: Each convolution operates on that corresponding input channel group. If so, how the model learns the features from entire input space?", "role": "user" }, { "content": "When multiple group convolutions are stacked together, the authors use channel shuffle, which divides the channels into subgroups within groups and shuffles them in a way that each group consists of subgroups from all other groups. It lets the model learn from an entire input space despite the group convolution. However, the paper does not explicitly report such side effects when group convolutions are not stacked together.", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\ncurrently , there is considerable interest in machine learning methods for corpus - based language learning .\na promising technique here is memory - based learning ( mbl ) @xcite , where a task is redescribed as a classification problem .\nthe classification is performed by matching an input item to the most similar of a set of training items and choosing the most frequent classification of the closest item(s ) .\nsimilarity is computed using an explicit similarity metric .\nmbl performs well by bringing all the training data to bear on the task .\nthis is done at the cost , in the worst case , of comparing novel items to all of the training items to find the closest match .\nthere is thus some interest in developing memory editing techniques to select a subset of the items for comparison .\nthis paper investigates whether a self - organising map ( som ) can be used to perform memory editing without reducing performance .\nthe system is tested on base noun - phrase ( np ) chunking using the wall street journal corpus @xcite .\nthe som was developed originally by kohonen and has found a wide range of uses from classification to storing a lexicon .\nit operates as follows ( see figure [ som ] ) .\nthe som consists of two layers , an input layer and the map .\neach unit in the map has a vector of weights associated with it that is the same size as that of the input layer .\nwhen an input is presented to the som , the unit whose weight vector is closest to the input vector is selected as a winner . during training ,\nthe weight vectors of winning unit and a set of units within the neighbourhood of the winner are nudged , by an amount determined by the learning rate , towards the input vector . over time\nthe size of the neighbourhood is decreased .\nsometimes the learning rate may be too . at the end of training , the units form a map of the input space that\nreflects how the input space was sampled in the training data .\nin particular areas of input space in which there were a lot of inputs will be mapped in finer detail , using more units than areas where the inputs were sparsely distributed .\nthe som was chosen because the input is matched to the unit with the closest weight vector .\nthus it is motivated by the same principle as used to find the closest match in mbl .\nit is thus hoped that the som can minimise the risk of failing to select the closest match , since the subset will be chosen according to similarity .\nhowever , daelemans _\net al _ claim that , in language learning , pruning the training items is harmful . when they removed items from the memory base on the basis of their typicality ( i.e. the extent to which the items were representative of other items belonging to the same class ) or their class prediction strength ( i.e. the extent to which the item formed a predictor for its class ) , the generalisation performance of the mbl system dropped across a range of language learning tasks . the memory editing approach used by daelemans\n_ et al _ removes training items independently of the novel items , and the remainder are used for matching with all novel items . if one selects a _ different _ subset for each novel item based on similarity to the novel item , then maybe the risk of degrading performance in memory editing will be reduced .\nthis work aims to achieve precisely this .\na modified som was developed called labelled som . training proceeds as follows : * each training item has an associated label\n. initially all the map units are unlabelled .\n* when an item is presented , the closest unit out of those with the same label as the input and those that are unlabelled is chosen as the winner .\nshould an unlabelled unit be chosen it gets labelled with the input s label . *\nthe weights for neighbouring units are updated as with the standard som if they share the same label as the input or are unlabelled . *\nwhen training ends , all the training inputs are presented to the som and the winners for each training input noted .\nunused units are discarded .\ntesting proceeds as follows : * when an input is presented a winning unit is found _ for each category_. * the closest match is selected from the training items associated with each of the winning units found . * the most frequent classification for that match\nis chosen .\nit is thus hoped that the closest matches for each category are found and that these will include the closest match amongst them .\nassuming each unit is equally likely to be chosen , the average number of comparisons here is given by @xmath0 where @xmath1 is the number of categories , @xmath2 is the number of units in the map and @xmath3 is the number of training items .\nchoosing @xmath4 minimises comparisons to @xmath5 . in the experiments\nthe size of the map was chosen to be close to @xmath6 .\nthis system is referred to as lsommbl . in the experiments , a comparison with using the standard som in a similar manner was performed . here\nthe som is trained as normal on the training items . at the end of training\neach item is presented to the som and the winning unit noted as with the modified som above .\nunused units are discarded as above . during testing ,\na novel item is presented to the som and the top c winners chosen ( i.e. the @xmath1 closest map units ) , where c is the number of categories .\nthe items associated with these winners are then compared with the novel item and the closest match found and then the most frequent classification of that match is taken as before .\nthis system is referred to as sommbl .\nthe task is base np chunking on section 20 of the wall street journal corpus , using sections 15 to 18 of the corpus as training data as in @xcite . for each word in a sentence , the pos tag is presented to the system which outputs whether the word is inside or outside a base np , or on the boundary between 2 base nps .\ntraining items consist of the part of speech ( pos ) tag for the current word , varying amounts of left and right context ( pos tags only ) and the classification frequencies for that combination of tags .\nthe tags were represented by a set of vectors .\n2 sets of vectors were used for comparison .\none was an orthogonal set with a vector of all zeroes for the `` empty '' tag , used where the context extends beyond the beginning / end of a sentence .\nthe other was a set of 25 dimensional vectors based on a representation of the words encoding the contexts in which each word appears in the wsj corpus .\nthe tag representations were obtained by averaging the representations for the words appearing with each tag .\ndetails of the method used to generate the tag representations , known as lexical space , can be found in @xcite .\nreilly found it beneficial when training a simple recurrent network on word prediction .\nthe self - organising maps were trained as follows : * for maps with 100 or more units , the training lasted 250 iterations and the neighbourhood started at a radius of 4 units , reducing by 1 unit every 50 iterations to 0 ( i.e. where only the winner s weights are modified ) .\nthe learning rate was constant at 0.1 .\n* for the maps with 6 units , the training lasted 90 iterations , with an initial neighbourhood of 2 , reducing by one every thirty iterations .\n* for the maps with 30 units , the training lasted 150 iterations , with an initial neighbourhood of 2 , reduced by one every 50 iterations .\na single training run is reported for each network since the results did not vary significantly for different runs .\nthese map sizes were chosen to be close to the square root of the number of items in the training set .\nno attempt was made to systematically investigate whether these sizes would optimise the performance of the system .\nthey were chosen purely to minimise the number of comparisons performed .\n[ cols= \" < , < , < , < , < , < \" , ] table [ sizes ] gives the sizes of the soms used for each context size , and the number of training items . for small context sizes , lsommbl and mbl give the same performance .\nas the window size increases , lsommbl falls behind mbl . the worst drop in performance is just over 1.0% on the fscores ( and just over 0.5% on chunk tag accuracy ) .\nthis is small considering that e.g. for the largest context the number of comparisons used was at most 6.8% of the number of training items . to investigate whether the method is less risky than the memory editing techniques used in @xcite , a re - analysis of their data in performing the same task , albeit with lexical information ,\nwas performed to find out the exact drop in the chunk tag accuracy .\nin the best case with the editing techniques used by @xcite , the drop in performance was 0.66% in the chunk tag accuracy with 50% usage ( i.e. 50% of the training items were used ) .\nour best involves a drop of 0.23% in chunk tag accuracy and only 20.4% usage .\nfurthermore their worst case involves a drop of 16.06% in chunk tag accuracy again at the 50% usage level , where ours involves only a 0.54% drop in accuracy at the 6.8% usage level .\nthis confirms that our method may be less risky , although a more direct comparison is required to demonstrate this in a fully systematic manner .\nfor example , our system does not use lexical information in the input where theirs does , which might make a difference to these results . comparing the sommbl results with the lsommbl results for the same context size and tagset ,\nthe differences in performance are insignificant , typically under 0.1 points on the fscore and under 0.1% on the chunk tag accuracy .\nfurthermore the differences sometimes are in favour of lsommbl and sometimes not .\nthis suggests they may be due to noise due to different weight initialisations in training rather than a systematic difference .\nthus at the moment it is unclear whether sommbl or lsommbl have an advantage compared to each other .\nit does appear however that the use of the orthogonal vectors to represent the tags leads to slightly worse performance than the use of the vectors derived from the lexical space representations of the words .\nthe results suggest that the hybrid system presented here is capable of significantly reducing the number of comparisons made without risking a serious deterioration in performance .\ncertainly , the reduction in the number of comparisons was far greater than with the sampling techniques used by daelemans _\net al _ while yielding similar levels of deterioration .\ngiven that a systematic investigation into what the optimal training regimes and network sizes are has not been performed the results thus seem promising .\nwith regard to the network sizes , for example , one reviewer commented that choosing the number of units to be the square root of the number of training items may not be optimal since the clusters formed in self - organising maps theoretically vary as the squared cube root of the density , thus implying that a larger number of units may offer better performance .\nwhat impact using this insight would have on the performance ( as opposed to the speed ) of the system however is unclear .\nanother variable that has not been systematically investigated is the optimal number of winning units to choose during testing . increasing this value\nshould allow tuning of the system to balance deterioration of the performance against the reduction in comparisons made .\nanother issue regards the nature of the comparisons made . when choosing a winning unit , the input is compared to the centroid of the cluster each unit represents .\nhowever this fails to take into account the distribution of the items around the centroid .\nas one reviewer suggested , it may be that if instead the comparison is made with the periphery of the cluster there would be a reduced risk of missing the closest item .\none possibility for taking this into account would be to compute the average distance of the items from the centroid and subtract this from the raw distance computed between the input and the centroid .\nthis would take into account how spread out the cluster is as well as how far the centroid is from the input item .\nthis would be a somewhat more expensive comparison to make but may be worthwhile to improve the probability that the closest item is found in the clusters that are searched .\nfuture work will therefore include systematically investigating these issues to determine the optimal parameter settings .\nalso a more systematic comparison with other sampling techniques , especially other methods of clustering , is needed to confirm that this method is less risky than other techniques .\nthis work suggests that using the som for memory editing in mbl may be a useful technique for improving the speed of mbl systems whilst minimising reductions in performance .\nfurther work is needed however to find the optimal training parameters for the system and to confirm the utility of this approach .\nthe authors would like to thank the following people for their discussions and advice during this work ; the reviewers of this paper for some helpful comments , antal van den bosch for providing the data from @xcite for our analysis , ronan reilly for his discussions of this work , walter daelemans & other members of the cnts who made the first author s visit to cnts an enjoyable and productive stay .\nthis work was supported by the eu - tmr project `` learning computational grammars '' .\nthe ( l)sommbl simulations were performed using the pdp++ simulator . the mbl simulations were performed using the timbl package w. daelemans , s. buchholz , and j. veenstra .\nmemory - based shallow parsing . in m. osborne and e. tjong kim sang , editors , _ proceedings of the computational natural language learning workshop ( conll-99 ) , university of bergen , bergen , norway _ , somerset , nj , usa . association for computational linguistics . r.g .\nreilly . 1998 .\nenriched lexical representations , large corpora and the performance of srns . in l.\nniklasson , m. bodn , and t. zemke , editors , _ proceedings of icann98 , skovde , sweden _ , pages 405410 .\nj. zavrel and j. veenstra .\n1996 . the language environment and syntactic word class acquisition . in koster\nc. and wijnen f. , editors , _ proceedings of the groningen assembly on language acquisition ( gala 95)_.", "role": "user" }, { "content": "memory - based learning ( mbl ) has enjoyed considerable success in corpus - based natural language processing ( nlp ) tasks and is thus a reliable method of getting a high - level of performance when building corpus - based nlp systems . \n however there is a bottleneck in mbl whereby any novel testing item has to be compared against all the training items in memory base . \n for this reason there has been some interest in various forms of memory editing whereby some method of selecting a subset of the memory base is employed to reduce the number of comparisons . \n this paper investigates the use of a modified self - organising map ( som ) to select a subset of the memory items for comparison . \n this method involves reducing the number of comparisons to a value proportional to the square root of the number of training items . \n the method is tested on the identification of base noun - phrases in the wall street journal corpus , using sections 15 to 18 for training and section 20 for testing .", "role": "assistant" } ]

[ { "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 function of a DEAD box protein?\n\nContext: DEAD-box helicase proteins perform ATP-dependent rearrangements of structured RNAs throughout RNA biology.\nDEAD-box proteins are ubiquitous in RNA-mediated processes and function by coupling cycles of ATP binding and hydrolysis to changes in affinity for single-stranded RNA. Many DEAD-box proteins use this basic mechanism as the foundation for a version of RNA helicase activity\nDEAD-box proteins as RNA helicases and chaperones.\nRNA helicases of the DEAD-box and related families have been found to be required for all processes involving RNA molecules\nDDX3 belongs to the DEAD-box proteins, a large family of ATP-dependent RNA helicases that participate in all aspects of RNA metabolism\nDEAD-box proteins catalyze the ATP-dependent unwinding of RNA duplexes and accompany RNA molecules throughout their cellular life.\nDEAD-box (DDX) proteins belong to the largest subfamily of RNA helicase SF2, which contributes to all biological processes of RNA metabolism\nDDX3Y (also known as DBY) is a member of the DEAD box protein family, which is involved in ATP-dependent RNA unwinding, needed in a variety of cellular processes including splicing, ribosome biogenesis and RNA degradation.\nVASA is a member of the DEAD-box protein family that plays an indispensable role in mammalian spermatogenesis, particularly during meiosis.\nBACKGROUND: Vasa is a member of the DEAD-box protein family that plays an indispensable role in mammalian spermatogenesis, particularly during meiosis.\nThe yeast DEAD box protein Mss116p is a general RNA chaperone that functions in mitochondrial group I and II intron splicing, translational activation, and RNA end processing.\nDEAD box proteins are putative RNA helicases that function in all aspects of RNA metabolism, including translation, ribosome biogenesis, and pre-mRNA splicing. B\nrom unwinding RNA duplexes, which established these proteins as RNA helicases, DEAD box proteins have been shown to also catalyse RNA annealing and to displace proteins from RNA. DEAD bo\nDDX3Y (also known as DBY) is a member of the DEAD box protein family, which is involved in ATP-dependent RNA unwinding, needed in a variety of cellular processes including splicing, ribosome biogenesis and RNA degradation. In\n'DEAD/H' family of putative RNA helicases may help regulate these processes by utilizing intrinsic RNA-dependent ATPase activity to catalyze conformational changes in RNA secondary structure. To\nDEAD-box helicases catalyze the ATP-dependent unwinding of RNA duplexes.\nA DEAD-box protein functions as an ATP-dependent RNA chaperone in group I intron splicing.\nDEAD-box proteins are nonprocessive RNA helicases that play diverse roles in cellular processes.\nA DEAD-box protein alone promotes group II intron splicing and reverse splicing by acting as an RNA chaperone.\nDEAD/H-box proteins are involved in various aspects of RNA metabolism.\nOur results demonstrate that a DExH/D-box protein has a specific, physiologically relevant chaperone function in the folding of a natural RNA substrate.\nDEAD-box proteins are the largest family of nucleic acid helicases, and are crucial to RNA metabolism throughout all domains of life.\nHere, structural, biochemical and genetic analyses of the yeast DEAD-box protein Mss116p indicate that the helicase core domains have modular functions that enable a novel mechanism for RNA-duplex recognition and unwinding.\nThe DEAD-box RNA helicase family comprise enzymes that participate in every aspect of RNA metabolism, associated with a diverse range of cellular functions including response to abiotic stress.\nThe Thermus thermophilus DEAD-box protein Hera is a general RNA binding protein and plays a key role in tRNA metabolism.\nDEAD-box proteins, a large class of RNA-dependent ATPases, regulate all aspects of gene expression and RNA metabolism.\nDEAD box proteins are putative RNA helicases that have been implicated in cellular processes involving alteration of RNA secondary structure, such as translation initiation and splicing.\nDEAD box proteins catalyze the ATP-dependent unwinding of double-stranded RNA (dsRNA).\nDEAD-box proteins are ATP-dependent RNA helicases that function in various stages of RNA processing and in RNP remodeling.\nDEAD-box proteins are ubiquitous in RNA-mediated processes and function by coupling cycles of ATP binding and hydrolysis to changes in affinity for single-stranded RNA.\nDEAD-box proteins ordinarily function as constituents of enormous multi-protein complexes and it is believed that interactions with other components in the complexes might be answerable for the various capacities ascribed to these proteins.\nThere is emerging evidence that DEAD-box family of RNA helicases play pivotal functions in various cellular processes and in numerous cases have been embroiled in cellular proliferation and/or neoplastic transformation.\nThis activity, coupled with mechanisms to direct different DEAD-box proteins to their physiological substrates, allows them to promote RNA folding steps and rearrangements and to accelerate remodeling of RNA–protein complexes.\nMany DEAD-box proteins use this basic mechanism as the foundation for a version of RNA helicase activity, efficiently separating the strands of short RNA duplexes in a process that involves little or no translocation.", "role": "user" }, { "content": "DEAD-box helicases are ubiquitous in RNA-mediated processes and function by coupling cycles of ATP binding and hydrolysis to changes in affinity for single-stranded RNA.", "role": "assistant" } ]

[ { "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 pimavanserin a typical antipsychotic?\n\nContext: Pimavanserin is the first FDA-approved atypical antipsychotic drug indicated for the treatment of hallucinations and delusions associated with Parkinson's disease psychosis (PDP).", "role": "user" }, { "content": "no", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nthe geodesic motion of test particles in a black hole background is one of the most interesting subjects in general relativity .\nmany astronomical phenomena are related with the geodesic , such as light deflection , perihelion shift of planets , shapiro effect , lense - thirring , black hole shadow and so on . in the near future ,\nthe ligo @xcite , the event horizon telescope @xcite , and other experiments @xcite may have a qualitatively new level of precision to explore phenomena near the black hole horizon .\nthe kerr - newman ( kn ) black hole solution describes the gravitational field of a charged and rotating stationary black hole .\nalthough it is not very likely that the astrophysical black hole candidates carry a net charge @xcite , such charged black holes can be formed through a charged stellar collapse @xcite , brane - world - inspired charge - leaking mechanism @xcite , and accretion scenarios @xcite .\nthe geodesic motion in this black hole background has been extensively investigated . for examples , the timelike equatorial and spherical orbits of uncharged particles and\nthe last stable orbit of charged particles were studied in refs .\n@xcite , respectively .\nthe motion of charged particles was also investigated in ref .\n@xcite , while the off - equatorial circular orbits were given in ref .\na comprehensive analysis of the photon orbit and charged particle motion in a kn black hole were presented in refs .\n@xcite . with the help of the multivariable hypergeometric functions of appell - lauricella and weierstrass elliptic functions ,\nthe null geodesics of kn black hole are solved in a close form @xcite .\nanother theoretical interest for the kn black hole is the kn / cfts ( conformal field theory ) dualities @xcite , which are the simple extension of the kerr / cft duality @xcite .\nit was also shown that the near - horizon geometry of a near extremal kn black hole has a warped @xmath0 structure , and analytical results for the pair production were also obtained in ref .\n@xcite . very recently ,\nporfyriadis , shi , and strominger @xcite considered the photon emission near extreme kerr black holes . and they first solved the near - superradiant geodesics analytically .\nsuch results are hoped to apply to a variety of problems related to the observations of electromagnetic radiation . in this paper\n, we would like to generalize the result to the extremal kn black hole spacetime .\nfirst , we analyze the effective potential of the radial motion .\nwe find a critical point , beyond which the photon emitting near the black hole horizon can escape the black hole and can be observed by distant observatories .\nthen near this critical point , we perform the geodesic integrals for both near and far regions .\nfinally , matching the solutions in the two regions , we obtain the analytic result for the extremal kn black hole . using the result , observations in a kn spacetime\nare expected to be analytically researched .\nour paper is organized as follows . in the next section\n, we would like to give a brief review of the geodesic equations in the kn black hole background and analyze the effective potential . in sec .\n[ rth ] the null geodesic motion in the @xmath1-@xmath2 plane is analytically solved . and\n[ rtrphi ] , we deal with the motions in the @xmath1-@xmath3 and @xmath1-@xmath4 planes . at\nlast , the paper ends with a brief summary .\nin this section , we would like to consider the geodesic equations in the background of a kn black hole .\nthe line element of a kn black hole in boyer - lindquist coordinates @xmath5 is read as @xmath6 where the metric functions are @xmath7 the vector potential is given by @xmath8 the parameter @xmath9 , @xmath10 , and @xmath11 are the angular momentum , charge , and mass of the black hole .\nthis black hole solution originates from the four - dimensional einstein - maxwell action @xmath12 the horizons are given by solving the equation @xmath13 , i.e. , @xmath14 the extremal black hole is achieved when the two horizons coincide with each other .\nthe motion of a charged particle with charge @xmath15 moving in the kn black hole background is described by the lagrangian @xmath16 where a dot over a symbol represents the ordinary differentiation with respect to an affine parameter @xmath17 .\nthe affine parameter is related to the proper time by @xmath18 , which is equivalent to the normalization condition @xmath19 .\nthe equation of motion of the charged particle will be @xmath20 where @xmath21 and @xmath22 are the electromagnetic tensor and christoffel symbols for the kn black hole .\nthe equation of motion will reduce to @xcite @xmath23 where @xmath24 for a particle without charge , the equation of motion can be expressed as @xmath25 when the black hole charge @xmath26 , the result for the kerr black hole will be recovered .\nnext , we will consider the null geodesics in an extremal kn black hole background , i.e. , @xmath27 here @xmath28 is the dimensionless black hole charge , and we require @xmath29 .\nwe can reexpress eq .\n( [ rmothion ] ) in a classical form @xmath30 with the effective potential @xmath31 . for a classical motion , we require @xmath32 or @xmath33 .\nthe turning point occurs at @xmath34 or @xmath35 , at which the test particle has a zero radial velocity .\nwe plot the effective potential @xmath36 against @xmath37 in fig.[rhat1 ] by taking @xmath38 , @xmath39 and @xmath40=3 as an example . for this case\n, the effective potential has two zero points at @xmath41 and @xmath42 .\nthe peak of the potential is at @xmath43 .\nnote that the horizon locates at @xmath44 .\nfor the photons coming from far region , they will stop at the point @xmath45 and be reflected to infinity . and\nthe photons emitted near the black hole horizon will be reflected at the point @xmath46 , and be absorbed by the black hole . while the region @xmath47 is forbidden for such photons with such @xmath48 and @xmath49 .\nthere exists a special case that the two zeroes @xmath46 and @xmath45 meet each other and the peak of the potential shift to the horizon , which gives a special bound .\nif the parameters of null geodesics is beyond this bound , photons can freely move in the spacetime . in this paper\n, we will consider these trajectories near such bound in a kn black hole background .\nmoreover , such bound can be obtained by solving @xmath50 .\nwe define as did in ref .\n@xcite a small dimensionless parameter @xmath51 this result will recover the superradiant bound for the kerr black hole with @xmath52 .\nfor @xmath53 , the photons emitted near the black hole horizon could not approach infinity .\nand @xmath54 is a special point in the parameter space of extremal kn black hole geodesics , at which the photons can escape the black hole . as did for the kerr black hole @xcite ,\nthe geodesics for the photons with small @xmath17 emitted from the near - horizon region are analytically solvable .\nlet us introduce the dimensionless bardeen - horowitz coordinates , @xmath55 after this coordinate transformation , the extremal black hole horizon is shifted to @xmath56 . on the other hand ,\nthe energy @xmath57 can be scaled out of the null geodesic with the shifted dimensionless carter constant @xmath58 here we are interested in the photon trajectories starting at @xmath59 near the horizon and ending at @xmath60 , where a distant telescope locates\n. then the geodesic equation can be expressed in terms of the new coordinates ( [ newcoordinate ] ) as @xmath61 where @xmath62 the integrals of ( [ rtheta])-([tftn ] ) can be expressed with elliptic functions and are treated numerically ( for detail see ref .\n@xcite ) . however ,\nin this paper , we will follow the technique of ref .\n@xcite to analytically perform the integrals to the leading order in the small parameter @xmath17 with the matched asymptotic expansions ( mae ) method .\nthe spacetime is divided into different regions @xcite : @xmath63 next , we will fist solve these equations in the near and far regions , respectively , and then match them in the overlap region .\nin this section , we deal with the radial integral @xmath64 taking the mae approximation , we have @xmath65 in the near and far regions , one has @xmath66 it is clear that the black hole charge only influences the geodesics in the near region . in the far region ,\nthe turning points in the radial motion occurs at @xmath67 this result is the same as that of the extremal kerr black hole . in order to require\nthe photon can penetrate the near region from the far one , there must be no turning point , and thus we take @xmath68 . in the near region ,\nthe turning points are at @xmath69 for @xmath70 , there will be no turning point in the near region .\nthus the photon can freely move from the near region to the far one .\nnow we can perform the radial integrals both in the near and far regions , @xmath71 with @xmath72 and @xmath73 the integration constants . in the overlap region ,\nthe radial integrals are @xmath74 taking the match in the overlap region , i.e. , @xmath75 , we have @xmath76 this condition is the same as that of the kerr black hole given in ref . @xcite . using it ,\nwe are allowed to calculate the integral ( [ rmotion ] ) for the photon starting from the near region to the far one . moreover ,\nif the photon is limited in the equatorial plane @xmath77 or @xmath78 , there will be a relation for @xmath79 and @xmath80 , @xmath81 where @xmath82\nto leading order in @xmath17 via mae , we have @xmath83 one can proceed to solve the radial integrals for the motion @xmath84 in the near region , one has @xmath85 and in the far region , it gives @xmath86 now , all integrals can be performed , @xmath87 where @xmath88 and @xmath89 denote the integration constants . in the overlap region , we have @xmath90 matching @xmath91 , the relations between the integration constants are @xmath92 finally , we can get the integrals in eqs .\n( [ phifphin ] ) and ( [ tftn ] ) .\nin particular , for the case that the photons are limited in the equatorial plane @xmath77 or @xmath78 , the shifts in the azimuthal angle @xmath3 and time @xmath4 can be calculated as @xmath93 for the case that the photons are emitted from a distant source , pass by near a black hole , and finally are observed by a distant observer , their deflection angle and time delay can be measured with eqs .\n( [ fphi ] ) and ( [ ft ] ) .\ncorrespondingly , we assume one endpoint is near the photon sphere of the black hole and other one is located at infinity , then we have the deflection angle and time delay in the strong gravitational limit for the photons with @xmath94 , @xmath95 where the factor 2 comes from the symmetry analysis of the geodesics . here\nwe neglect the effects of back - reaction and observer - independence of the speed of light @xcite .\nin this paper , we considered a special class of null geodesics in an extremal kn black hole background .\nthe geodesics are near a critical point , where the turning point locates at the horizon and photons emitted from the near - horizon region can freely travel to a distant observatory . adopting the matched asymptotic expansion method\n, we performed the integrals for the null geodesic and derived the algebraic equations , see eqs .\n( [ rrr ] ) , ( [ fphi ] ) , and ( [ ft ] ) .\nthese equations are parameterized by @xmath96 given in ( [ lambda ] ) and ( [ qq ] ) .\nthey relate two endpoints , one is near the horizon @xmath97 and another locates at a far region from the black hole @xmath98 .\nmoreover , in these equations , we assumed that the polar angles @xmath99 .\nhowever , the photons are free of the polar angle when they move from the near region to the far one .\na stronger constraint is that the photon trajectory is limited in the equatorial plane @xmath100 , which is also a simple requirement when considering the strong black hole lensing . as pointed out in refs .\n@xcite , whether one assumes @xmath99 or not , the parameter @xmath101 must be positive .\nfor the extremal kerr black hole , @xmath2 must be in the region @xmath102 . while for the extremal kn black hole , such region is modified by the black hole charge .\nfor example , the condition @xmath103 must be held , which implies that @xmath2 should lie between @xmath104 and @xmath105 . when the black hole charge vanishes , it recovers the region for the kerr black hole . on the other hand ,\nwhen the black hole charge approaches its maximum @xmath106 , the region will approximately be @xmath107 .\na detailed analysis suggests that this region shrinks with the increase of the black hole charge .\nsince our analysis of the null geodesics is near the critical point that the photons can escape from the black hole , many astronomical phenomena are related with it , such as the black hole lensing and shadow . so using the analytical results obtained in this paper\n, one can consider these phenomena in an analytical way for the extremal black hole .\nmoreover , like the kerr black hole , the kn black hole also has a near - horizon conformal symmetry . and\nit provides a simple extended example differing from the kerr black hole , which is also useful for studying other black holes with more than one rotating parameter .\nthis work was supported by the national natural science foundation of china ( grants no .\n11205074 , no . 11375075 , and no .\n11522541 ) , and the fundamental research funds for the central universities ( no .\nlzujbky-2016 - 121 and lzujbky-2016-k04 ) . c. r. ghezzi and p. s. letelier , _ numeric simulation of relativistic stellar core collapse and the formation of reissner - nordstrom black holes _ ,\nphys . rev . *\nd 75 * , 024020 ( 2007 ) , [ arxiv : astro - ph/0503629 ] .\nv. balek , j. bicak , and z. stuchlik , _ the motion of charged particles in the field of rotating charged black holes and naked singularities - ii .\nthe motion in the equatorial plane _\n. czechosl . * 40 * , 133 ( 1989 ) .\ng. v. kraniotis , _ gravitational lensing and frame dragging of light in the kerr - newman and the kerr - newman-(anti ) de sitter black hole spacetimes _ , gen .\n. grav . * 46 * , 1818 ( 2014 ) , [ arxiv:1401.7118[gr - qc ] ] .", "role": "user" }, { "content": "in this paper , we deal with the null geodesics extending from the near - horizon region out to a distant observatory in an extremal kerr - newman black hole background . in particular , using the matched asymptotic expansion method , we analytically solve the null geodesics near the superradiant bound . for the case that the polar angles of the two endpoints of the geodesic coincide , \n the relation between the radial values of the two endpoints is found , and the shifts in the azimuthal angle and time are also obtained .", "role": "assistant" } ]

[ { "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: [\"AnatomicalEntity\"].\n\nPlease return the output as a JSON object of the format: {\"AnatomicalEntity\": [\"tumor cells\", ...]}. 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 an empty JSON array \"[]\".\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\n2. Methods", "role": "user" }, { "content": "{\"AnatomicalEntity\": []}", "role": "assistant" } ]

[ { "content": "You will be given an abstract from a computer science research paper. Given the abstract, your task is to extract all unique relationships between entities of the following, and ONLY the following, types:\n\n- \"USED-FOR\": For instance, \"Our method models user proficiency\" -> [\"method\", \"user proficiency\", \"USED-FOR\"].\n- \"EVALUATE-FOR\": For instance, \"We evaluate our method using F1-measure\" -> [\"F1-measure\", \"method\", \"EVALUATE-FOR\"].\n- \"FEATURE-OF\": For instance, \"prior knowledge of the model\" -> [\"prior knowledge\", \"model\", \"FEATURE-OF\"].\n- \"HYPONYM-OF\": For instance, \"TUIT is a software library\" -> [\"TUIT\", \"software library\", \"HYPONYM-OF\"].\n- \"PART-OF\": For instance, \"We incorporate NLU module into the system\" -> [\"NLU module\", \"system\", \"PART-OF\"].\n- \"COMPARE\": For instance, \"Unlike the quantitative prior, the qualitative prior is often ignored\" -> [\"quantitative prior\", \"qualitative prior\", \"COMPARE\"].\n- \"CONJUNCTION\": For instance, \"obtained from human expert or knowledge base\" -> [\"human expert\", \"knowledge base\", \"CONJUNCTION\"].\n\nFormat your output as a JSON array. Each entry in the array should express a single relation, formatted as [\"<Entity_A>\", \"<Entity_B>\", \"<RELATION_A_B>\"]. An example output might look like:\n\n[[\"neural networks\", \"classification\", \"USED-FOR\"], [\"neuron\", \"neural network\", \"PART-OF\"]].\n\nIf no relations are found, please return an empty JSON array \"[]\".\n\nAbstract:\n\nThe goal of this research is to develop a spoken language system that will demonstrate the usefulness of voice input for interactive problem solving. The system will accept continuous speech, and will handle multiple speakers without explicit speaker enrollment. Combining speech recognition and natural language processing to achieve speech understanding, the system will be demonstrated in an application domain relevant to the DoD. The objective of this project is to develop a robust and high-performance speech recognition system using a segment-based approach to phonetic recognition. The recognition system will eventually be integrated with natural language processing to achieve spoken language understanding.", "role": "user" }, { "content": "[[\"speech recognition\", \"speech understanding\", \"USED-FOR\"], [\"spoken language system\", \"interactive problem solving\", \"USED-FOR\"], [\"voice input\", \"interactive problem solving\", \"USED-FOR\"], [\"speech recognition\", \"natural language processing\", \"CONJUNCTION\"], [\"phonetic recognition\", \"spoken language system\", \"USED-FOR\"], [\"spoken language system\", \"speech understanding\", \"USED-FOR\"], [\"natural language processing\", \"spoken language system\", \"CONJUNCTION\"], [\"segment-based approach\", \"spoken language system\", \"USED-FOR\"], [\"natural language processing\", \"speech understanding\", \"USED-FOR\"], [\"segment-based approach\", \"phonetic recognition\", \"USED-FOR\"]]", "role": "assistant" } ]

[ { "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: We propose an image parsing approach to jointly solve the semantic segmentation and instance segmentation tasks in a single\n\nKeyphrases: whole image parsing images\n\nDataset description:\nA2D: A2D (Actor-Action Dataset) is a dataset for simultaneously inferring actors and actions in videos. A2D has seven actor classes (adult, baby, ball, bird, car, cat, and dog) and eight action classes (climb, crawl, eat, fly, jump, roll, run, and walk) not including the no-action class, which we also consider.\nCOCO: The MS COCO (Microsoft Common Objects in Context) dataset is a large-scale object detection, segmentation, key-point detection, and captioning dataset. The dataset consists of 328K images.\nTHEODORE: Recent work about synthetic indoor datasets from perspective views has shown significant improvements of object detection results with Convolutional Neural Networks(CNNs). In this paper, we introduce THEODORE: a novel, large-scale indoor dataset containing 100,000 high- resolution diversified fisheye images with 14 classes.\nCIHP: The Crowd Instance-level Human Parsing (CIHP) dataset has 38,280 diverse human images. Each image in CIHP is labeled with pixel-wise annotations on 20 categories and instance-level identification.\nScanNet: ScanNet is an instance-level indoor RGB-D dataset that includes both 2D and 3D data. It is a collection of labeled voxels rather than points or objects.\nCityscapes: Cityscapes is a large-scale database which focuses on semantic understanding of urban street scenes. It provides semantic, instance-wise, and dense pixel annotations for 30 classes grouped into 8 categories (flat surfaces, humans, vehicles, constructions, objects, nature, sky, and void).\nCityscapes-VPS: Cityscapes-VPS is a video extension of the Cityscapes validation split. It provides 2500-frame panoptic labels that temporally extend the 500 Cityscapes image-panoptic labels.\n\nOptions:- A: A2D B: COCO C: THEODORE D: CIHP E: ScanNet F: Cityscapes G: Cityscapes-VPS", "role": "user" }, { "content": "[\"COCO\", \"Cityscapes\"]", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nwe develop new entropy based statistics @xmath2 called _ slide statistics _ which can be computed from any sample data in a metric space . as an application\n, we use these statistics to test whether financial returns are independent observations from a particular distribution .\nfor example , figure [ fig : fig1 ] shows plots of @xmath3 against @xmath14 for data @xmath15 consisting of n - tuples of consecutive returns regarded as a subset of the metric space @xmath16 with the usual metric .\nas can be seen , the lower curve corresponding to the s@xmath0p @xmath1 is very different from the ones obtained for either the normal or laplace distributions . any potential model for\nthe returns of the s@xmath0p @xmath1 must be able simulate the @xmath3 curve in figure [ fig : fig1 ] which is a new requirement that is apparently difficult to meet .\nthe statistics @xmath17 contain information about the interplay between the dimension of a space and distributions on that space and provide a new way of describing continuous random variables and stochastic processes in general .\nthe @xmath17 will take some time to define but we will provide explicit formulas for slide statistics @xmath3 and @xmath4 that are easily computed for any sample in a metric space . against @xmath14 for the s@xmath0p @xmath1 for the @xmath18 trading days ending december 31 , 2014 .\nthe middle cluster of five graphs are the corresponding plots obtained from five different simulated sequences of returns with the laplace distribution .\nthe upper cluster of five graphs are the corresponding plots obtained from five different simulated sequences of normally distributed returns .\n, width=384 ] our applications will focus on financial returns but many other important processes in science and mathematics also yield data in the form of a set of points in a metric space that must be quantified and interpreted .\nfields like fractal analysis have developed in order to obtain dimensional information from a wide range of real world data using quantities like the hausdorff , information and correlation dimensions @xcite .\none of the problems with these traditional measures of dimension is that they tend to concentrate on the geometric properties of a set while ignoring the statistical origins of the data .\nwe will give examples where @xmath19 appears to converge to the reciprocal of the hausdorff dimension when @xmath20 is taken to be a a larger and larger random sample from a fractal .\nit is not clear in general how to assign a dimension to a point process but our theory and simulations suggest a purely statistical way to identify a class of them for which it does make sense to assign a dimension .\nspecifically , we think the dimension of a point process @xmath21 should be defined to be @xmath22 provided @xmath23 and @xmath24 for @xmath25 in which case we say the process is tangible with dimension @xmath22 . in the case of a tangible process , the values of @xmath26\nare entirely determined by the number @xmath22 but this relationship does not hold in general . a possible example of a tangible process is the random generation of points @xmath27 in @xmath8^d$ ] , where the @xmath28 are chosen independently and uniformly at random from @xmath8 $ ] , for which we provide evidence that @xmath29 and @xmath30 . in particular , @xmath3 and\n@xmath4 are new spatial statistics for testing hypotheses concerning the distribution of points in @xmath8^d$ ] .\nalthough we will sometimes use fractals as examples , these statistics can be applied to any random variable with values in a metric space . in particular\n, the slide statistics appear to describe continuous random variables @xmath7 in an entirely new way that has nothing to do with mean and standard deviation since @xmath31 for @xmath32 .\nfor example , the first two slide statistics for any normal variable @xmath11 appear to converge to @xmath12 and @xmath13 which provide the basis for a new goodness of fit test for normality . for any exponential random variable @xmath33 , simulation gives that @xmath34 and @xmath35 and we conjecture from these and other simulations that @xmath36 for any continuous real - valued random variable @xmath7 .\nif we think of @xmath37 as the _ dimension _ of the random variable @xmath7 , then this last conjecture says the uniform distribution on @xmath8 $ ] has the maximum dimension of any continuous real - valued random variable .\nthe second slide statistic @xmath4 is negative for the examples given so far but @xmath4 is positive for the cauchy distribution and is often found to be positive for the log daily returns of the standard and poor 500 index which is yet another demonstration of the non - normality of these returns .\nthe construction of @xmath38 requires several ideas working in concert and can be summarized as follows . in section [ s:2 ] , we introduce a variant of the differential entropy called the genial entropy which is the starting point for defining the slide statistics . unlike the differential entropy ,\nthe genial entropy is scale invariant and in section [ s : inequality ] we prove it is never negative which will give a new lower bound for the differential entropy . given a finite set of distinct points @xmath20 in a metric space , we find the distance from each point to its nearest neighbour and arrange these distances in descending order so @xmath39 .\nlet @xmath40 be the function on @xmath41 whose value on @xmath42 is @xmath43 .\nlet @xmath44 be the area under @xmath45 and let @xmath46 denote the genial entropy of the density @xmath47 which turns out to be @xmath48 at @xmath49 .\nwe then define @xmath50 to be the @xmath14th derivative from the right at @xmath48 of the function @xmath46 which is developed in section [ s : calculus ] . in section [ s : calculus ]\n, we derive an explicit formula for @xmath19 and state a conjectured formula for @xmath51 .\nthe fact that @xmath3 and @xmath4 are easily evaluated using a computer makes them particularly suitable for practical applications .\nthe results obtained from the simulation of @xmath3 and @xmath4 in a variety of contexts are summarized in section [ s : slide ] and demonstrate the interplay between dimension and distribution that is captured by these statistics . as applications in section [ s : returns ] , we consider a variety of possible distributions as models for financial returns and use the slide statistics to illustrate how poorly these models fit the empirical data .\nour starting point for the development of the slide statistics is the differential entropy @xmath52 of a density @xmath53 which is well known in statistics and information theory @xcite\n. our focus will be on a variant of the differential entropy called the genial entropy or g - entropy which will be described in definition [ d:2.02 ] . in the simplest case of a probability density @xmath53 that has an inverse function such as @xmath54 on @xmath55 $ ]\n, the genial entropy is just the sum of the differential entropies of @xmath53 and @xmath56 .\nthe next proposition shows how this sum can be written in a form that makes sense for densities that may not have inverses .\n[ p:2.01 ] suppose @xmath53 is a continuous function on @xmath57 $ ] with the properties that the derivative of @xmath53 exists and is negative on @xmath58 , @xmath59 and @xmath60 . also assume the differential entropies of @xmath53 and @xmath56 both exist .\nthen the sum of their differential entropies is given by @xmath61 .\nsubstitute @xmath62 into the integral @xmath63 to get @xmath64 which equals @xmath65 .\nafter integrating by parts this last integral becomes @xmath66 and the result follows .\nthe genial entropy will only be defined for densities of the following special form .\n[ d:2.01 ] a corner density is a function @xmath67 where @xmath68 is a connected interval contained in @xmath69 , @xmath53 is monotone decreasing and @xmath70 .\nhere is our definition of genial entropy which is motivated by the conclusion of proposition [ p:2.01 ] .\n[ d:2.02 ] let @xmath67 be a corner density .\nthe genial entropy or g - entropy of @xmath53 is defined by @xmath71 when this integral exists , with the usual convention that @xmath72 .\nif @xmath53 satisfies the conditions of proposition [ p:2.01 ] , then @xmath73 so in particular @xmath74 and @xmath75 must have the same genial entropy which happens to be euler s constant as shown in table [ t:2.01 ] . in section [ s : inequality ] , we will prove the genial entropy is always nonnegative .\nthe genial entropy of some corner densities . .\n[ cols=\"^,^,^\",options=\"header \" , ] the stable distributions are often considered @xcite as possible models for financial returns .\nwe now consider the family of stable distributions @xmath76 described in @xcite where @xmath77 $ ] is the stable parameter , @xmath78 $ ] is the skewness parameter , @xmath79 is the scale parameter and @xmath80 is the location parameter . by proposition [ p:5.01 ] , the values of @xmath17\nare not affected by changes in @xmath81 and @xmath82 so we will simply work with the family @xmath83 which we write as @xmath84 .\nfigure [ fig : fig5 ] shows the points @xmath85 from table [ t:5.03 ] plotted together with @xmath86 samples from stable distributions with parameters @xmath87 and @xmath88 chosen uniformly at random from the intervals @xmath89 and @xmath90 respectively .\nwe see that the values in table [ t:5.03 ] lie outside the region corresponding to the stable distributions .\nfigure [ fig : fig6 ] show an expanded view of figure [ fig : fig5 ] showing that the slide statistics for the financial returns in table [ t:5.03 ] are well outside the region corresponding to samples from stable distributions .\nthis failure of the stable distributions to fit financial returns is consistent with the findings of @xcite .\nobtained for @xmath86 samples from stable distributions with parameters @xmath87 and @xmath88 chosen uniformly at random from the intervals @xmath89 and @xmath90 respectively . the values in table [ t:5.03 ]\nare shown plotted with squares .\n, width=384 ] , width=384 ]\nas we have seen , the statistics @xmath3 and @xmath4 can be used as the basis for goodness of fit test for financial returns .\nmuch more research needs to be done to better understand the role of the slide statistics in characterizing financial data .\nin particular , we would like to understand the relationship between the sign of @xmath4 and the behaviour of financial markets .\nthe simulations we have described suggest that @xmath3 and @xmath4 can be used to distinguish between probability distributions and are capapble of detecting dimensional information .\nthe values of @xmath91 we obtained through simulation point to a larger theory of these statistics which is currently being developed . at present\nhowever , the @xmath91 are quite mysterious and much work will need to be done to understand all they are telling us about sets of points in metric spaces , random variables or point processes in general .\nwe gave examples of point processes on the cantor set and the sierpinski triangle for which @xmath5 converged to the dimension of the fractal .\nwe would like to understand when this occurs in general and also the relationship between @xmath5 and the usual definitions of dimension .\nmore generally , we would like to know when a point process is tangible in the sense of definition [ d:5.04 ] .\nwhen a process is tangible it is possible to use the expression @xmath92{\\frac{(-1)^{n+1}(n-1)!(n-1)\\zeta(n)}{\\rho_n(u)}}$ ] as a statistic for estimating the dimension .\nwe gave examples in which it converged to the dimension faster for @xmath93 than for @xmath94 and we would like to know what happens for larger values of @xmath14 .\nin terms of calculations , we need to prove conjecture [ cj:4.01 ] concerning the calculation of @xmath51 and we need formulas for @xmath50 for @xmath95 . given the complexity of our conjecture for @xmath51 , the formulas for larger values of @xmath14 are likely to be very complicated .\nthe convergence of the @xmath50 for real - valued random variables can sometimes be improved by using the distances between consecutive points rather than the distances to nearest neighbours .\nwe would like to have a better understanding of this situation and also to know if there are any higher dimensional analogues . in defining the slide statistics\n, we used the functions @xmath45 which can be thought of as a continuous deformation of @xmath40 at @xmath96 into the constant function @xmath97 at @xmath49 .\nwe can achieve the same effect using the functions @xmath98 and calculate the derivatives corresponding to the slide derivatives in section [ s : calculus ] .\nit turns out that only the first of these statistics is interesting and while it is easier to calculate than @xmath3 it often does nt converge .\nbonetti , m. , forsberg , l. , ozonoff , a. and pagano , m. , _ the distribution of interpoint distances .\nmathematical modeling applications in homeland security _ , ht banks and c castillo chavez , eds . , 2003,87 - 106 .", "role": "user" }, { "content": "we present a new approach to financial returns based on an infinite family of statistics called _ slide statistics _ that we introduce . \n the evidence these statistics provide suggests that certain distributions such as the stable distributions are not good models for the financial returns from various securities or indexes like the s@xmath0p @xmath1 and the dow jones . \n formally , we associate with any finite subset of a metric space an infinite sequence of scale invariant numbers @xmath2 derived from a variant of differential entropy called the genial entropy . \n we give explicit formulas for @xmath3 and @xmath4 that are easily evaluated by a computer and make this theory particularly suitable for applications . as statistics for point processes , these numbers often appear to converge in simulations and we give examples where @xmath5 converges to the hausdorff dimension and we prove that @xmath6 . for a uniform random variable @xmath7 on @xmath8^n$ ] , the evidence from simulations suggests that @xmath9 and @xmath10 which yields new tests for spatial randomness . \n the slide statistics describe continuous random variables in an entirely new way . for example , if @xmath11 is any normal variable then simulations suggest that @xmath12 and @xmath13 which provides new goodness of fit tests for normality .", "role": "assistant" } ]

[ { "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 5hmC (5 hydroxy-methyl-Cytocine) in differentiation?\n\nContext: 5-Methylcytosine (5 mC) in genomic DNA has important epigenetic functions in embryonic development and tumor biology.\nThe modification of DNA by 5-methylcytosine (5mC) has essential roles in cell differentiation and development through epigenetic gene regulation.\nNotably, the balance between 5hmC and 5mC in the genome is linked with cell-differentiation processes such as pluripotency and lineage commitment.\nThis Tet1-mediated antagonism of CpG methylation imparts differential maintenance of DNA methylation status at Tet1 targets, ultimately contributing to mESC differentiation and the onset of embryonic development.\nTet1 and Tet2 catalyzed conversion of 5-methylcytosine (5mC) to 5-hydroxymethylcytosine (5hmC) in Foxp3 to establish a Treg-cell-specific hypomethylation pattern and stable Foxp3 expression\nConsequently, Tet1 and Tet2 deletion led to Foxp3 hypermethylation, impaired Treg cell differentiation and function, and autoimmune disease.\n5-Hydroxymethylcytosine (5hmC), converted from 5-methylcytocine (5mC) by Tet family of dioxygenases (Tet1, Tet2, and Tet3), is enriched in the embryonic stem cells (ESCs) and in the brain\nWe found that Tet3 expression is basically undetectable in ESCs, but its level increases rapidly during neuronal differentiation.\n5mC oxidation by Tet2 modulates enhancer activity and timing of transcriptome reprogramming during differentiation\nRecent experiments have demonstrated that enhancers are enriched for 5-hydroxymethylcytosine (5hmC), an oxidization product of the Tet family of 5mC dioxygenases and an intermediate of DNA demethylation.\nBy mapping DNA methylation and hydroxymethylation at base resolution, we find that deletion of Tet2 causes extensive loss of 5hmC at enhancers, accompanied by enhancer hypermethylation, reduction of enhancer activity, and delayed gene induction in the early steps of differentiation\nLoss of Tet enzymes compromises proper differentiation of embryonic stem cells\nThese findings suggest a requirement for Tet- and 5hmC-mediated DNA demethylation in proper regulation of gene expression during ESC differentiation and development.\nWe show that 5hmC is enriched in the gene body of highly expressed genes at all developmental stages and that its presence correlates positively with gene expression.\nDynamic hydroxymethylation of deoxyribonucleic acid marks differentiation-associated enhancers\nIn this study, we show by genome-wide mapping that the newly discovered deoxyribonucleic acid (DNA) modification 5-hydroxymethylcytosine (5hmC) is dynamically associated with transcription factor binding to distal regulatory sites during neural differentiation of mouse P19 cells and during adipocyte differentiation of mouse 3T3-L1 cells\nHence, acquisition of 5hmC in cell-specific distal regulatory regions may represent a major event of enhancer progression toward an active state and participate in selective activation of tissue-specific genes.\nWe find that 5hmC is mostly associated with euchromatin and that whereas 5mC is under-represented at gene promoters and CpG islands, 5hmC is enriched and is associated with increased transcriptional levels\nKnockdown of Tet1 and Tet2 causes downregulation of a group of genes that includes pluripotency-related genes (including Esrrb, Prdm14, Dppa3, Klf2, Tcl1 and Zfp42) and a concomitant increase in methylation of their promoters, together with an increased propensity of ES cells for extraembryonic lineage differentiation\nTet2 deficiency led to decreased genomic levels of 5hmC and augmented the size of the hematopoietic stem/progenitor cell pool in a cell-autonomous manner. In competitive transplantation assays, Tet2-deficient HSCs were capable of multilineage reconstitution and possessed a competitive advantage over wild-type HSCs, resulting in enhanced hematopoiesis into both lymphoid and myeloid lineages.\nHowever, the role of 5hmC and Tet family in the process of ESC differentiation especially neuronal differentiation remains elusive\nOur data constitute a valuable resource that will facilitate detailed analysis of the role of 5hmC in T-cell development and differentiation\nMore recently, a possible role of 5hmC as an epigenetic modifier and/or transcriptional regulator has started to emerge, with altered levels in early embryonic development, embryonic stem (ES) cell differentiation and tumours (Tahiliani et al, 2009; Yang et al, 2012).\nHere we report a method that combines TET-assisted bisulfite conversion with Illumina 450K DNA methylation arrays for a low-cost high-throughput approach that distinguishes 5hmC and 5mC signals at base resolution. Implementing this approach, termed \"TAB-array\", we assessed DNA methylation dynamics in the differentiation of human pluripotent stem cells into cardiovascular progenitors and neural precursor cells. With the ability to discriminate 5mC and 5hmC, we identified a large number of novel dynamically methylated genomic regions that are implicated in the development of these lineages.\n5-hydroxy methyl cytosine (5hmC) is a modification identified in vertebrates several decades ago. More recently, a possible role of 5hmC as an epigenetic modifier and/or transcriptional regulator has started to emerge, with altered levels in early embryonic development, embryonic stem (ES) cell differentiation and tumours (Tahiliani et al, 2009; Yang et al, 2012).", "role": "user" }, { "content": "The balance between 5hmC and 5mC in the genome is linked with cell-differentiation processes such as pluripotency and lineage commitment. Tet1-mediated antagonism of CpG methylation imparts differential maintenance of DNA methylation status at Tet1 targets, ultimately contributing to mESC differentiation and the onset of embryonic development. By mapping DNA methylation and hydroxymethylation at base resolution, we find that deletion of Tet2 causes extensive loss of 5hmC at enhancers, accompanied by enhancer hypermethylation, reduction of enhancer activity, and delayed gene induction in the early steps of differentiation.", "role": "assistant" } ]

[ { "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\nDandelion leaf extract protects against liver injury induced by methionine- and choline-deficient diet in mice.\nWe investigated the hepatoprotective effects of the extract of dandelion leaves (EDL) on a murine model of methionine- and choline-deficient (MCD) diet-induced nonalcoholic steatohepatitis (NASH). C57BL/6 mice were fed for 4 weeks with one of the following diets: control diet (Cont), MCD diet (MCD), MCD diet supplemented with EDL at 200 mg/kg body weight·daily (MCD+D200), and MCD diet supplemented with EDL at 500 mg/kg body weight·daily (MCD+D500). Hepatic function was assessed by evaluating the following parameters: liver histology; plasma levels of alanine aminotransferase (ALT), triglyceride (TG), malondialdehyde (MDA), and reduced glutathione (GSH); expression levels of TNF-α and IL-6; and levels of caspase-3 and pJNK/JNK protein. Histopathological evaluations revealed that addition of EDL to the MCD diet dampens the severity of the clinical signs of NASH. Moreover, EDL led to a significant decrease in the serum levels of ALT, hepatic TG, and MDA, and in the expression levels of TNF-α, and IL-6; on the contrary, the levels of reduced GSH increased. At the post-transcriptional level, EDL significantly decreased the activation of procaspase-3 to active caspase-3, and the phosphorylation of JNK. These results suggest that the beneficial effects of EDL on NASH are mainly due to its antioxidant and anti-inflammatory activities.", "role": "user" }, { "content": "{\"Chemical\": [\"reduced GSH\", \"methionine\", \"triglyceride\", \"MDA\", \"reduced glutathione\", \"alanine\", \"malondialdehyde\", \"GSH\", \"choline\"], \"Protein\": [\"alanine aminotransferase\", \"caspase-3\", \"pJNK\", \"JNK\", \"TNF-\\u03b1\", \"ALT\", \"IL-6\", \"procaspase-3\"]}", "role": "assistant" } ]

[ { "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: ZP4 confers structural properties to the zona pellucida essential for embryo development\nArticle:\nAbstract:\nZona pellucida( ZP), the extracellular matrix sheltering mammalian oocytes and embryos, is composed by 3 to 4 proteins. The roles of the three proteins present in mice have been elucidated by KO models, but the function of the fourth component( ZP4), present in all other eutherian mammals studied so far, has remained elusive. Herein, we report that ZP4 ablation impairs fertility in female rabbits. Ovulation, fertilization and in vitro development to blastocyst were not affected by ZP4 ablation. However, in vivo development is severely impaired in embryos covered by a ZP4-devoided zona, suggesting a defective ZP protective capacity in the absence of ZP4. ZP4-null ZP was significantly thinner, more permeable, and exhibited a more disorganized and fenestrated structure. The evolutionary conservation of ZP4 in other mammals, including humans, suggests that the structural properties conferred by this protein are required to ensure proper embryo sheltering during in vivo preimplantation development.\nIntroduction:\nMammalian oocytes and early preimplantation embryos are surrounded by a glycoprotein shell termed zona pellucida( ZP) that serves important functions during folliculogenesis, species-specific fertilization and early development. In eutherian mammals, this glycoprotein shell is solely composed of 3 to 4 proteins depending on the species. The differences in ZP composition between eutherian mammals is the consequence of duplication and/or pseudogenization events during evolution. In all eutherian mammals studied so far ZP always contain ZP2 and ZP3 proteins, but ZP1 or ZP4 may be absent, as both are paralogous genes formed by duplication of a common ancestry gene( reviewed by Goudet et al., 2008). The functions of the three proteins( ZP1, ZP2 and ZP3) present in mouse ZP have been elucidated by gene ablation experiments. ZP1 serves a structural function, being dispensable for sperm binding or fertilization( Rankin et al., 1999). ZP1 null females display perturbed folliculogenesis and, although ovulation rates are not affected, both cleavage rate and litter size are reduced, likely due to ZP1-null zona being unable to protect the developing embryo. ZP2 ablation also results in structural defects, which are more severe, as the number of antral follicles is reduced and only few ZP-free oocytes and no two-cell embryos are recovered from Zp2 knock-out( KO) females after mating( Rankin et al., 2001). Finally, Zp3 KO mice are unable to form ZP, showing a drastic reduction in ovulation rates and also being unable to produce cleaved embryos after mating( Liu et al., 1996; Rankin et al., 1996). Given the lack of ZP on ovulated Zp2- or Zp3-null oocytes, these KO models could not assess the role of these proteins on sperm binding. To study that process, more complex gain-of-function transgenic mouse models have been generated. In particular, the generation of ZP composed of different combinations of human ZP proteins( Baibakov et al., 2012) or an heterologous ZP lacking mouse ZP2 protein( Avella et al., 2014) have uncovered a crucial role of ZP2 on mouse and human sperm recognition. The fourth ZP protein component, ZP4, is absent in mice, which seems to be an exception for mammals, as ZP4 is present in multiple mammalian species including humans( Hughes and Barratt, 1999; Lefièvre et al., 2004), rabbits( Stetson et al., 2012), ungulates( Hedrick and Wardrip, 1987; Noguchi et al., 1994; Topper et al., 1997), carnivores( Moros-Nicolás et al., 2018) and other rodents( Hoodbhoy et al., 2005; Izquierdo-Rico et al., 2009). The lack of ZP4 in laboratory mouse( Mus musculus), the only species where KO models were readily available, has precluded the study of the role of this protein by of loss-of-function experiments. Gene ablation experiments are essential to unequivocally know the function of a gene, but were largely restricted to mice, given the technical difficulties to perform site-specific genome modification in other mammalian species( Lamas-Toranzo et al., 2017). Luckily, the advent of site-specific endonucleases, and particularly CRISPR, the last technology to be developed and the easiest to tailor to its genomic target, allows direct KO generation in one step. Using this technology, we have generated ZP4-null rabbits uncovering that ZP4 confers structural properties to the ZP that are essential to protect the developing preimplantation embryo.\nDiscussion:\nDespite its essential functions during folliculogenesis, fertilization and preimplantation embryo development, ZP is composed of just 3 to 4 proteins, depending on the species. Gene ablation experiments have deciphered the functions of the three proteins present in mouse ZP, but the role of the fourth component( ZP4) has remained controversial. Previous studies have suggested that ZP4 may play a role during fertilization. Rabbit ZP4 was found to bind to rabbit sperm acrosome( Prasad et al., 1996), although specific blocking by ZP4-antisera fragments could not be demonstrated. Similarly, other studies based on in vitro protein-binding assays have attributed sperm attachment to the zona matrix to ZP4 in humans( Chiu et al., 2008) or to heterocomplexes of ZP4 and ZP3 in porcine and bovine( Kanai et al., 2007; Yurewicz et al., 1998). In contrast with this notion, the expression of human ZP4 in transgenic mouse ZP was not sufficient to support human sperm binding( Yauger et al., 2011). In this article, we have tested ZP4 role by gene ablation in a species where it is naturally present. Although we cannot assure that ZP4 ablation might reduce sperm binding, acrosome reaction or sperm penetration in vitro, our results unequivocally show that ZP4 does not play an essential role during the fertilization process in vivo, but serves a structural and mechanical function which is fundamental to protect the developing embryo prior to implantation. In agreement with our findings, a recent study on ZP characterization hypothesized a structural role of ZP4 on increasing CP thickness in humans( Nishimura et al., 2019). ZP plays an essential protective role during preimplantation embryo development, as despite the exception of a single case report where zona-free embryos were developed in vitro up to blastocyst before transfer( Shu et al., 2010), zona denuded embryos have been largely considered unable to complete in vivo development( Bronson and McLAREN, 1970; Modliński, 1970). This protective function was severely impaired following ZP4 ablation, ultimately causing embryonic death and infertility. ZP4 ablation in rabbits lead to similar structural defects in ZP to those obtained when ZP1 is ablated in mice( Rankin et al., 1999): reduction in ZP thickness and increased ZP porosity. However, the effects on fertility of Zp1 KO were less severe than those caused by ZP4 ablation, as litter size was halved in Zp1 KO female mice compared to WT mice, whereas ZP4 ablation abolished almost completely embryo development. A plausible explanation for this difference is that mouse embryos may demand a lesser degree of ZP protection during preimplantation development than other domestic mammals, including rabbits. The early blastocyst hatching occurring in mouse( 3. 5 days compared to more than 6 days in humans and most domestic mammalian species) and a reduced hydrostatic pressure in female reproductive tract motivated by its small body size may be partly responsible for this difference. Remarkably, the laboratory mouse remain the only mammalian species studied so far where ZP4 is not present in ZP( Moros-Nicolás et al., 2018), and mouse ZP is noticeably softer and more elastic compared to other mammalian ZPs containing ZP4 with or without ZP1( Yu Sun et al., 2003). Further evidence for the fundamental structural role of ZP4 comes from transgenic mouse models producing humanized ZP: the expression of human ZP4 in mouse ZP was found to be able to recover the thickness and robustness lost following mouse ZP2 ablation( Avella et al., 2014). In order to determine whether ZP4 deficiency could lead to infertility in women, we searched for loss-of-function mutations in the Genome Aggregation Database, which includes data from 141456 individuals( Lek et al., 2016). This search revealed 48 polymorphisms in ZP4 coding region leading to premature stop codons( PTCs), which are the most evident loss-of-function mutations( Supplementary file 2 and Figure 6). The frequency of individuals carrying at least one of these PTC mutations in ZP4 was 0. 3% in the global population analysed, raising to 1% in the African dataset. Hence, in this population, roughly 1 into 40000 women would carry a PTC in both alleles, being thereby potentially infertile due to ZP4 deficiency. Mutations in ZP1-3 genes have been recently associated with women infertility( Zhou et al., 2019; Nishimura et al., 2019) but the association between these PTC mutations in ZP4 and woman infertility remains to be explored. The evolutionary conservation of ZP4 in humans( Hughes and Barratt, 1999; Lefièvre et al., 2004) and many other mammals( Goudet et al., 2008; Hedrick and Wardrip, 1987; Hoodbhoy et al., 2005; Izquierdo-Rico et al., 2009; Moros-Nicolás et al., 2018; Noguchi et al., 1994; Stetson et al., 2012) points towards a conserved role of this protein. In this sense, these results highlight ZP4 mutations as a possible cause for female infertility in both humans and livestock or wild species, and pave the way for the development of contraceptive methods based on ZP4 disruption.", "role": "user" }, { "content": "The egg cells of mammals , called oocytes , are encased in a protective layer called the zona pellucida . This layer is made from proteins called ZP1 to 4 . Most studies of the zona pellucida use mice , which do not have ZP4 . This means that the research community have limited knowledge of what ZP4 does in humans and other mammals . Scientists can now use a technique called CRISPR to selectively modify the genetics of living things to help us to understand what specific genes and proteins do . The ZP4 protein can be eliminated from rabbit oocytes using CRISPR to help understand its role in egg cell fertilization and development . Lamas-Toranzo et al . examined the effect of losing ZP4 from rabbit oocytes . Without ZP4 the zona pellucida becomes thinner , irregular and more flexible . However , the loss of ZP4 did not affect ovulation ( i . e . the release of egg cells from an ovary ) , fertilization , or the early stages of development of embryos when studied in the laboratory . However , rabbits without ZP4 were much less fertile . Indeed , only one out of 10 female rabbits without ZP4 was able to deliver pups because in most cases the development of embryos in the womb failed . These findings show that ZP4 has a structural role in the zona pellucida . Without ZP4 fertility is reduced . This work lays the ground for further investigation of the role of ZP4 . It could also offer new insights into the causes of infertility .", "role": "assistant" } ]

[ { "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: The Cas4-Cas1-Cas2 complex mediates precise prespacer processing during CRISPR adaptation\nArticle:\nAbstract:\nCRISPR adaptation immunizes bacteria and archaea against viruses. During adaptation, the Cas1-Cas2 complex integrates fragments of invader DNA as spacers in the CRISPR array. Recently, an additional protein Cas4 has been implicated in selection and processing of prespacer substrates for Cas1-Cas2, although this mechanism remains unclear. We show that Cas4 interacts directly with Cas1-Cas2 forming a Cas4-Cas1-Cas2 complex that captures and processes prespacers prior to integration. Structural analysis of the Cas4-Cas1-Cas2 complex reveals two copies of Cas4 that closely interact with the two integrase active sites of Cas1, suggesting a mechanism for substrate handoff following processing. We also find that the Cas4-Cas1-Cas2 complex processes single-stranded DNA provided in cis or in trans with a double-stranded DNA duplex. Cas4 cleaves precisely upstream of PAM sequences, ensuring the acquisition of functional spacers. Our results explain how Cas4 cleavage coordinates with Cas1-Cas2 integration and defines the exact cleavage sites and specificity of Cas4.\nIntroduction:\nBacteria and archaea use an adaptive immune system composed of clustered regularly interspaced short palindromic repeats( CRISPR) arrays and CRISPR-associated( Cas) proteins to defend against infection( Barrangou et al., 2007; Brouns et al., 2008; Marraffini and Sontheimer, 2008). Within this system, the CRISPR locus is programmed with ‘spacer’ sequences that are derived from foreign DNA and serve as a record of prior infection events( Bolotin et al., 2005; Mojica et al., 2005; Pourcel et al., 2005). The host adapts to an infection event when Cas proteins insert short fragments from the invader DNA as new spacers between repeating sequence elements within the CRISPR locus( reviewed in Jackson et al., 2017). The locus is transcribed and processed into short CRISPR RNAs( crRNAs), which assemble with Cas proteins to form a RNA-guided surveillance complex( reviewed in Hochstrasser and Doudna, 2015; Charpentier et al., 2015). Finally, the surveillance complex recognizes the target bearing complementarity to the crRNA sequence and a Cas nuclease cleaves or degrades the target during the interference stage( reviewed in Marraffini, 2015). Although the machinery and mechanisms involved in CRISPR interference are extremely diverse( Koonin et al., 2017), the adaptation proteins Cas1 and Cas2 are conserved among most CRISPR systems, suggesting a common molecular mechanism for acquiring spacers. Cas1 and Cas2 form a heterohexameric complex that catalyzes spacer integration via two transesterification reactions mediated by nucleophilic attack of the 3ʹ-hydroxyl on each strand of a double-stranded prespacer substrate at the phosphodiester backbone within the CRISPR array. Integration occurs at the first repeat in the CRISPR array, with one attack occurring between the upstream leader sequence and the repeat and the other occurring on the opposite strand between the repeat and first spacer within the array( Arslan et al., 2014; Nuñez et al., 2015a; Rollie et al., 2015). These reactions result in the insertion of the prespacer between two single-strand repeats, and this gapped intermediate is repaired by host factors( Ivančić-Baće et al., 2015). In order to form a functional spacer, the adaptation complex must capture and process longer fragments of DNA from the invader containing a flanking sequence called a protospacer adjacent motif( PAM)( Nuñez et al., 2015b; Wang et al., 2015; Xiao et al., 2017). The PAM is an essential motif during target recognition by the surveillance complex and must be present next to the target in order for interference to occur( Deveau et al., 2008; Redding et al., 2015; Sashital et al., 2012; Semenova et al., 2011; Sternberg et al., 2014). However, the PAM is not part of the spacer and must be removed from the prespacer prior to integration through a processing step. In addition, integration must occur in the correct orientation to produce a crRNA that is complementary to the PAM-containing strand of the invader. In some systems, additional Cas proteins, such as Cas4, are also required during adaptation. Cas4 is widespread in type I, II, and V systems( Hudaiberdiev et al., 2017). In in vivo studies, deletion of cas4 reduced the adaptation efficiency( Li et al., 2014; Liu et al., 2017) and resulted in the acquisition of non-functional spacers from regions that lacked a correct PAM( Almendros et al., 2019; Kieper et al., 2018; Shiimori et al., 2018; Zhang et al., 2019). Some systems have two cas4 genes that work together to define the PAM, length and orientation of spacers, suggesting that the two Cas4 proteins are involved in processing each end of the prespacer and that they may be present during integration( Shiimori et al., 2018). Similarly, in vitro studies have suggested that Cas4 is involved in PAM-dependent prespacer processing( Lee et al., 2018; Rollie et al., 2018). Cas4 endonucleolytically cleaves PAM-containing 3ʹ-single-stranded overhangs that flank double-stranded prespacers( Lee et al., 2018). Importantly, Cas4 cleavage activity is dependent on the presence of Cas1 and Cas2, and Cas4 inhibits premature integration of unprocessed prespacers. These observations suggest that Cas4 associates with the Cas1-Cas2 complex, although direct biochemical and structural evidence for this Cas4-Cas1-Cas2 complex remains elusive( Lee et al., 2018; Plagens et al., 2012). Here we show that Cas4 forms a complex with Cas1-Cas2 in the presence of dsDNA. Using single-particle negative-stain electron microscopy( EM), we determined the architecture of Bacillus halodurans type I-C Cas1-Cas2 and Cas4-Cas1-Cas2 complexes. Unlike the symmetrical Cas14-Cas22 structure, we observed a mixture of symmetrical( Cas42-Cas14-Cas22) and asymmetrical( Cas41-Cas14-Cas22) complexes, suggesting a structural mechanism for distinguishing between the PAM and non-PAM end of the prespacer following processing. The positioning of Cas4 places it in close proximity to the Cas1 active site, suggesting a mechanism for substrate handoff following prespacer processing. Surprisingly, the Cas4-Cas1-Cas2 complex processes single-strand DNA when an activator duplex DNA is provided in trans. Using this ssDNA cleavage assay, we show that the Cas4-Cas1-Cas2 complex is highly specific for PAM sequences and cleaves precisely upstream of the PAM. In a duplex substrate, the PAM must be positioned within a single-strand region for optimal cleavage, but Cas4 can cleave at various locations within this single-stranded overhang. Collectively, these findings provide the first structural information of the Cas4-Cas1-Cas2 adaptation complex and reveal the precision and specificity of prespacer processing prior to integration.\nDiscussion:\nThe negative-stain EM volumes for the Cas1-Cas2-target, asymmetrical Cas4-Cas1-Cas2-target, symmetrical Cas4-Cas1-Cas2-target, asymmetrical Cas4-Cas1-Cas2-prespacer and symmetrical Cas4-Cas1-Cas2-prespacer complexes have been deposited to EMDB under the accession numbers EMDB-20127, EMDB-20128, EMDB-20129, EMDB-20130 and EMDB-20131, respectively. Further information and requests for resources and reagents should be directed to and will be fulfilled by Dipali Sashital( sashital@iastate. edu).", "role": "user" }, { "content": "Many people have now heard of CRISPR , or CRISPR-Cas9 , as a gene editing technology . Yet CRISPR evolved in bacteria to protect them against viral infections . While parts of the CRISPR system are now being widely used , the research community still does not know everything about how the system operates in its natural setting . In bacteria , CRISPR protects against infection by making lasting records of viruses a cell has encountered . It cuts short sections from the viral DNA and keeps them as a way to fight the virus if it ever returns . The key proteins in collecting and storing the virus DNA are called Cas1 , Cas2 and Cas4 . Previous work suggests that Cas4 is important for cutting suitable lengths of DNA for storage . Yet , how Cas4 , Cas1 and Cas2 work together to select , cut and store DNA is not well studied . Lee et al . have now used electron microscopy to examine how Cas1 , Cas2 and Cas4 cooperate in the CRISPR system . The proteins studied came from bacteria called Bacillus halodurans . The structure revealed direct links between the Cas1 and Cas4 proteins that likely help to ensure these proteins are coordinated correctly to cut and store the DNA sections . Specifically , it showed that two Cas4 proteins interact with the two key active sites of Cas1 . The findings also highlight that Cas4 cuts DNA at specific locations to make sure the resulting DNA sections are suitable for CRISPR protection . The close association between Cas1 and Cas4 could be a critical aspect of the reliability of the CRISPR system in protecting bacteria from viruses . There are more bacteria on Earth than any other living thing . Understanding their biology has wide ranging environmental , health and bioengineering applications . In addition , learning more about the CRISPR system could further expand its potential to drive revolutionary biotechnology tools derived from these bacterial immune systems .", "role": "assistant" } ]

[ { "content": "You will be shown the title of a chemistry paper, together with sections excerpted from the body of the paper. The paper sections may include HTML tags like `<p>` and `</p>`; please ignore these. Your task is to write an abstract for the paper. Your response should include the abstract and no other text.\n\nTitle:\nThe Synthesis and Evaluation of Dihydroquinazolin-4-ones and Quinazolin-4-ones as Thyroid Stimulating Hormone Receptor Agonists\n\nPaper sections:\n\n<p>Thyroid-stimulating hormone (TSH) is an α/β heterodimeric glycoprotein hormone that is produced in the anterior pituitary gland and controls function and proliferation of thyroid follicular cells upon interaction with the TSH receptor (TSHR).1–3 TSHR is a G-protein coupled receptor that belongs to the glycoprotein receptor family.4 Two closely related members of this family include LHCGR (Luteinizing Hormone/Chorionic Gonadotropin Receptor)5 and FSHR (Follicle Stimulating Hormone Receptor).6,7 TSHR was first identified in the thyroid cell plasma membrane in 1966,8 and since that time has been found in bone,9 brain,10 kidney,11 testis,12 endometrium13 and the immune system.14 The primary function of TSHR in thyroid follicular cells is the regulation of thyroid hormone synthesis, as well as thyrocyte size and number,7,15 but the roles of TSHR in the other organs and tissues are not fully understood. The identification of a potent and selective small molecule TSHR agonist could provide a valuable tool for researchers interested in elucidating the roles and importance of this receptor in a variety of tissues. A small molecule TSHR agonist could also be clinically valuable. Recombinant TSH is currently used for patients with thyroid cancer receiving thyroid hormone suppression therapy, but it is difficult to produce and must be administered intramuscularly.16 A small molecule agonist could serve as an orally bioavailable alternative to recombinant TSH with advantages for therapeutic applications.</p><p>There are several reports of TSHR monoclonal antibody agonists,17–19 but very few of small molecule TSHR agonists. Thienopyrimidine Org 41841 (Fig. 1) was first described in 2002 as a partial LHCGR agonist and was later found to be a partial TSHR agonist with an EC50 of 7700 nM compared to 220 nM for LHCGR.20 This finding was followed with a series of synthesized analogues for SAR studies. Some analogues were LHCGR selective with low µM potency, but none were TSHR selective.21,22 Upon screening a library of 73,180 compounds (PubChem Assay ID: 1401), dihydroquinazolin-4-one 1a (Figure 1) was identified as a TSHR agonist.23,24 The dihydroquinazolin-4-one chemotype is present in some known drugs and bioactive compounds, such as the diuretics fenquizone25 and metolazone,26 but had not been previously identified as a TSHR modulator. More importantly, 1a was a selective TSHR agonist with no detectable LHR or FSHR efficacy and was therefore selected for further studies. We previously reported that dihydroquinazolin-4-one 1b was a full TSHR agonist with in vivo efficacy in mice.24 In this paper, we describe the synthesis and structure-activity relationship studies that were undertaken to evaluate a library of dihydroquinazolin-4-one 1a analogues.</p><p>A convergent route was developed for the rapid synthesis of 1a analogues (Scheme 1). The western fragment 3 was synthesized either via coupling of R3NH2 with an acid 2 or ring opening of isatoic anhydride 4. The eastern fragment 7 was synthesized via the benzylation of 6 with 5. This product was combined with fragment 3 in the presence of Yb(OTf)3 to afford dihydroquinazolin-4-ones 1 or 8.27 Quinazolin-4-ones 9 were obtained by oxidation of dihydroquinazolin-4-ones 1 using either DDQ28 or MnO2.29</p><p>Our SAR studies first investigated substitution on the amide and several clear trends were observed (R3, Table 1). First, there was little tolerance for hydrophilic groups, such as the amine (1k), alcohol (1l) or pyridine (1i), at this site. Second, while lipophilic groups are generally well tolerated, there appeared to be steric constraints. The benzyl group (1g) performed the best out of all analogues, but either lengthening (phenethyl 1m) or shortening (phenyl 1f) the tether between the aryl ring and amide resulted in a 2 and 10-fold reduction in potency, respectively. Finally, aliphatic groups were tolerated (n-Bu 1h), albeit not especially potent, but a lone hydrogen (H 1j) resulted in a very low potency and decreased efficacy. Among the tested R3 analogues, the benzyl group (1g) was the most potent with a 4-fold higher potency than the hit compound 1a. Based upon these findings, the optimization of other sites was pursued with R3 fixed as benzyl.</p><p>Aryl ring substitution on the western fragment of the molecule was next explored with a focus on the site ortho to the carbonyl (R2, Table 1). Analogues with H (1g) or F (1e) were equipotent, but the OH (1b) analogue resulted in a 3-fold improvement in potency. The free phenol was found to be critical for activity because when it was replaced with a methyl ether (1c) there was a sharp drop in potency. The orientation of the phenol was also critical for activity because when it was moved meta to the carbonyl (1d) the potency returned to the same level as the unsubstituted analogue (1g). This can be rationalized with a model. In our previously published modeling study, we proposed that 1b bound to the transmembrane helical bundle of TSHR. Both the R2 OH and the carbonyl group of the dihyroquinazolin-4-one were predicted to participate in hydrogen bonding with Asparagine N5.47. This prediction was supported by a point mutation study where 1b lost significant activity with the N5.74A mutation.24 In our analogues, the OH at R1 was not appropriately situated to engage in hydrogen bonding with Asparagine N5.47 and the R2 OMe analogue (1c) had no hydrogen available for hydrogen bonding. The phenol analogue (1b) was the most potent analogue identified from this series. Removal of the R4 methyl ether (1n) resulted in significant losses of potency and efficacy and hence the methyl ether was maintained in all subsequent analogues.</p><p>Substitution on the eastern fragment was next explored (Table 2). There was little tolerance for change on the eastern most ring. The lead compound substituted the R6 site with NHAc. When this site was instead substituted with a OMe (1o), CN (1r) or H (1p) there were losses in potency and efficacy. When NHAc was moved to the R5 position (1q) there were also sharp drops in potency and efficacy. Among the tested analogues, the R6 as NHAc motif of the original hit could not be altered without detrimental effects on the activity. Y was also explored in this series. All of the previous analogues maintained Y as oxygen, but when the oxygen was replaced with a sulfur group there was up to a 5-fold increase in potency (8b\nvs\n1b, 8a\nvs\n1g). In fact, 8b was the most potent compound evaluated from our library and was also found to maintain selectivity for TSHR over LHR and FSHR.</p><p>In solution, dihydroquinazolin-4-one analogues were slowly oxidized by air to the corresponding quinazoline-4-ones. The dihydroquinazolin-4-ones suffer from poor stability in acidic aqueous conditions due to hydrolysis. For example, compound 1b degraded at pH = 2 with a half-life of 3 h.24 Quinazoline-4-ones 9a–c (Table 3) were prepared to preemptively address these issues that could limit the application of these analogues. Although there was a modest decrease in potency of all the oxidized analogues, these compounds still maintained potency in the sub-µM range and had the advantage of improved stability over dihydroquinazolin-4-ones (Table 3). The selectivity of 9c was also tested and it was found to be selective for TSHR over LHR and FSHR.</p><p>In conclusion, we have successfully synthesized a library of analogues for SAR study. Among them, 1b, 8a, and 8b were at least 10-fold more potent than the hit 1a. In addition, we identified several quinazolin-4-one TSHR agonists (9a–c) with improved stability and sub-µM potency.</p>", "role": "user" }, { "content": "We herein describe the rapid synthesis of a diverse set of dihydroquinazolin-4-ones and quinazolin-4-ones, their biological evaluation as thyroid stimulating hormone receptor (TSHR) agonists, and SAR analysis. Among the compounds screened, 8b was 60-fold more potent than the hit compound 1a, which was identified from a high throughput screen of over 73,000 compounds.", "role": "assistant" } ]

[ { "content": "You will be shown a paragraph from a biomedical research paper, followed by a question about the paper. Please extract text from the paragraph to answer the question. Do not include any text in your response other than the answer.\n\nParagraph: Epidemiological research priorities for public health control of the ongoing global novel coronavirus (2019-nCoV) outbreak\n\nhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC7029449/\n\nSHA: 90de2d957e1960b948b8c38c9877f9eca983f9eb\n\nAuthors: Cowling, Benjamin J; Leung, Gabriel M\nDate: 2020-02-13\nDOI: 10.2807/1560-7917.es.2020.25.6.2000110\nLicense: cc-by\n\nAbstract: Infections with 2019-nCoV can spread from person to person, and in the earliest phase of the outbreak the basic reproductive number was estimated to be around 2.2, assuming a mean serial interval of 7.5 days [2]. The serial interval was not precisely estimated, and a potentially shorter mean serial interval would have corresponded to a slightly lower basic reproductive number. Control measures and changes in population behaviour later in January should have reduced the effective reproductive number. However, it is too early to estimate whether the effective reproductive number has been reduced to below the critical threshold of 1 because cases currently being detected and reported would have mostly been infected in mid- to late-January. Average delays between infection and illness onset have been estimated at around 5–6 days, with an upper limit of around 11-14 days [2,5], and delays from illness onset to laboratory confirmation added a further 10 days on average [2]. Text: It is now 6 weeks since Chinese health authorities announced the discovery of a novel coronavirus (2019-nCoV) [1] causing a cluster of pneumonia cases in Wuhan, the major transport hub of central China. The earliest human infections had occurred by early December 2019, and a large wet market in central Wuhan was linked to most, but not all, of the initial cases [2] . While evidence from the initial outbreak investigations seemed to suggest that 2019-nCoV could not easily spread between humans [3] , it is now very clear that infections have been spreading from person to person [2] . We recently estimated that more than 75,000 infections may have occurred in Wuhan as at 25 January 2020 [4] , and increasing numbers of infections continue to be detected in other cities in mainland China and around the world. A number of important characteristics of 2019-nCoV infection have already been identified, but in order to calibrate public health responses we need improved information on transmission dynamics, severity of the disease, immunity, and the impact of control and mitigation measures that have been applied to date. Infections with 2019-nCoV can spread from person to person, and in the earliest phase of the outbreak the basic reproductive number was estimated to be around 2.2, assuming a mean serial interval of 7.5 days [2] . The serial interval was not precisely estimated, and a potentially shorter mean serial interval would have corresponded to a Control measures and changes in population behaviour later in January should have reduced the effective reproductive number. However, it is too early to estimate whether the effective reproductive number has been reduced to below the critical threshold of 1 because cases currently being detected and reported would have mostly been infected in mid-to late-January. Average delays between infection and illness onset have been estimated at around 5-6 days, with an upper limit of around 11-14 days [2, 5] , and delays from illness onset to laboratory confirmation added a further 10 days on average [2] . Chains of transmission have now been reported in a number of locations outside of mainland China. Within the coming days or weeks it will become clear whether sustained local transmission has been occurring in other cities outside of Hubei province in China, or in other countries. If sustained transmission does occur in other locations, it would be valuable to determine whether there is variation in transmissibility by location, for example because of different behaviours or control measures, or because of different environmental conditions. To address the latter, virus survival studies can be done in the laboratory to confirm whether there are preferred ranges of temperature or humidity for 2019-nCoV transmission to occur. In an analysis of the first 425 confirmed cases of infection, 73% of cases with illness onset between 12 and 22 January reported no exposure to either a wet market or another person with symptoms of a respiratory illness [2] . The lack of reported exposure to another ill person could be attributed to lack of awareness or recall bias, but China's health minister publicly warned that pre-symptomatic transmission could be occurring [6] . Determining the extent to which asymptomatic or pre-symptomatic transmission might be occurring is an urgent priority, because it has direct implications for public health and hospital infection control. Data on viral shedding dynamics could help in assessing duration of infectiousness. For severe acute respiratory syndrome-related coronavirus (SARS-CoV), infectivity peaked at around 10 days after illness onset [7] , consistent with the peak in viral load at around that time [8] . This allowed control of the SARS epidemic through prompt detection of cases and strict isolation. For influenza virus infections, virus shedding is highest on the day of illness onset and relatively higher from shortly before symptom onset until a few days after onset [9] . To date, transmission patterns of 2019-nCoV appear more similar to influenza, with contagiousness occurring around the time of symptom onset, rather than SARS. Transmission of respiratory viruses generally happens through large respiratory droplets, but some respiratory viruses can spread through fine particle aerosols [10] , and indirect transmission via fomites can also play a role. Coronaviruses can also infect the human gastrointestinal tract [11, 12] , and faecal-oral transmission might also play a role in this instance. The SARS-CoV superspreading event at Amoy Gardens where more than 300 cases were infected was attributed to faecal-oral, then airborne, spread through pressure differentials between contaminated effluent pipes, bathroom floor drains and flushing toilets [13] . The first large identifiable superspreading event during the present 2019-nCoV outbreak has apparently taken place on the Diamond Princess cruise liner quarantined off the coast of Yokohama, Japan, with at least 130 passengers tested positive for 2019-nCoV as at 10 February 2020 [14] . Identifying which modes are important for 2019-nCoV transmission would inform the importance of personal protective measures such as face masks (and specifically which types) and hand hygiene. The first human infections were identified through a surveillance system for pneumonia of unknown aetiology, and all of the earliest infections therefore had Modelling studies incorporating healthcare capacity and processes pneumonia. It is well established that some infections can be severe, particularly in older adults with underlying medical conditions [15, 16] , but based on the generally mild clinical presentation of 2019-nCoV cases detected outside China, it appears that there could be many more mild infections than severe infections. Determining the spectrum of clinical manifestations of 2019-nCoV infections is perhaps the most urgent research priority, because it determines the strength of public health response required. If the seriousness of infection is similar to the 1918/19 Spanish influenza, and therefore at the upper end of severity scales in influenza pandemic plans, the same responses would be warranted for 2019-nCoV as for the most severe influenza pandemics. If, however, the seriousness of infection is similar to seasonal influenza, especially during milder seasons, mitigation measures could be tuned accordingly. Beyond a robust assessment of overall severity, it is also important to determine high risk groups. Infections would likely be more severe in older adults, obese individuals or those with underlying medical conditions, but there have not yet been reports of severity of infections in pregnant women, and very few cases have been reported in children [2] . Those under 18 years are a critical group to study in order to tease out the relative roles of susceptibility vs severity as possible underlying causes for the very rare recorded instances of infection in this age group. Are children protected from infection or do they not fall ill after infection? If they are naturally immune, which is unlikely, we should understand why; otherwise, even if they do not show symptoms, it is important to know if they shed the virus. Obviously, the question about virus shedding of those being infected but asymptomatic leads to the crucial question of infectivity. Answers to these questions are especially pertinent as basis for decisions on school closure as a social distancing intervention, which can be hugely disruptive not only for students but also because of its knock-on effect for child care and parental duties. Very few children have been confirmed 2019-nCoV cases so far but that does not necessarily mean that they are less susceptible or that they could not be latent carriers. Serosurveys in affected locations could inform this, in addition to truly assessing the clinical severity spectrum. Another question on susceptibility is regarding whether 2019-nCoV infection confers neutralising immunity, usually but not always, indicated by the presence of neutralising antibodies in convalescent sera. Some experts already questioned whether the 2019-nCoV may behave similarly to MERS-CoV in cases exhibiting mild symptoms without eliciting neutralising antibodies [17] . A separate question pertains to the possibility of antibody-dependent enhancement of infection or of disease [18, 19] . If either of these were to be relevant, the transmission dynamics could become more complex. A wide range of control measures can be considered to contain or mitigate an emerging infection such as 2019-nCoV. Internationally, the past week has seen an increasing number of countries issue travel advisories or outright entry bans on persons from Hubei province or China as a whole, as well as substantial cuts in flights to and from affected areas out of commercial considerations. Evaluation of these mobility restrictions can confirm their potential effectiveness in delaying local epidemics [20] , and can also inform when as well as how to lift these restrictions. If and when local transmission begins in a particular location, a variety of community mitigation measures can be implemented by health authorities to reduce transmission and thus reduce the growth rate of an epidemic, reduce the height of the epidemic peak and the peak demand on healthcare services, as well as reduce the total number of infected persons [21] . A number of social distancing measures have already been implemented in Chinese cities in the past few weeks including school and workplace closures. It should now be an urgent priority to quantify the effects of these measures and specifically whether they can reduce the effective reproductive number below 1, because this will guide the response strategies in other locations. During the 1918/19 influenza pandemic, cities in the United States, which implemented the most aggressive and sustained community measures were the most successful ones in mitigating the impact of that pandemic [22] . Similarly to international travel interventions, local social distancing measures should be assessed for their impact and when they could be safely discontinued, albeit in a coordinated and deliberate manner across China such that recrudescence in the epidemic curve is minimised. Mobile telephony global positioning system (GPS) data and location services data from social media providers such as Baidu and Tencent in China could become the first occasion when these data inform outbreak control in real time. At the individual level, surgical face masks have often been a particularly visible image from affected cities in China. Face masks are essential components of personal protective equipment in healthcare settings, and should be recommended for ill persons in the community or for those who care for ill persons. However, there is now a shortage of supply of masks in China and elsewhere, and debates are ongoing about their protective value for uninfected persons in the general community. The Table summarises research gaps to guide the public health response identified. In conclusion, there are a number of urgent research priorities to inform the public health response to the global spread of 2019-nCoV infections. Establishing robust estimates of the clinical severity of infections is probably the most pressing, because flattening out the surge in hospital admissions would be essential if there is a danger of hospitals becoming overwhelmed with patients who require inpatient care, not only for those infected with 2019-nCoV but also for urgent acute care of patients with other conditions including those scheduled for procedures and operations. In addressing the research gaps identified here, there is a need for strong collaboration of a competent corps of epidemiological scientists and public health workers who have the flexibility to cope with the surge capacity required, as well as support from laboratories that can deliver on the ever rising demand for diagnostic tests for 2019-nCoV and related sequelae. The readiness survey by Reusken et al. in this issue of Eurosurveillance testifies to the rapid response and capabilities of laboratories across Europe should the outbreak originating in Wuhan reach this continent [23] . In the medium term, we look towards the identification of efficacious pharmaceutical agents to prevent and treat what may likely become an endemic infection globally. Beyond the first year, one interesting possibility in the longer term, perhaps borne of wishful hope, is that after the first few epidemic waves, the subsequent endemic re-infections could be of milder severity. Particularly if children are being infected and are developing immunity hereafter, 2019-nCoV could optimistically become the fifth human coronavirus causing the common cold. None declared.\n\nQuestion: What would a shorter mean serial interval mean?", "role": "user" }, { "content": "slightly lower basic reproductive number.", "role": "assistant" } ]

[ { "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: Advances in renal cell carcinoma treatment. The treatment of advanced renal cell carcinoma has been completely changed by the development of new therapeutic modalities during the past 3 years. In this time period six targeted agents have been approved for the treatment of advanced or metastatic disease. Phase 3 data support the use of sunitinib , bevacizumab plus interferon-α and pazopanib for patients with low and intermediate risk of clear-cell renal cell carcinoma . In the pivotal study of temsirolimus a significant longer overall survival compared with interferon-α in high-risk disease including non-clear-cell histology was observed. Patients pretreated with cytokines will benefit from sorafenib and pazopanib while everolimus has been shown to increase significantly progression-free survival after previous anti-angiogenesis therapy. In addition to these phase 3 data-based recommendations, several other factors have to be considered for treatment selection, for example, side effect profile and patients' comorbidities. Currently, the sequential use of the available targeted drugs and adjuvant treatment are the subject of ongoing clinical trials. However, medical treatment of renal cell carcinoma remains palliative and surgery remains the only curative approach in patients with localized, locally advanced and limited metastatic disease.\n\nsentence: Phase 3 data support the use of sunitinib , bevacizumab plus interferon-α and pazopanib for patients with low and intermediate risk of clear-cell renal cell carcinoma .", "role": "user" }, { "content": "[[\"sunitinib\", \"bevacizumab\", \"pazopanib\", \"interferon-\\u03b1\", \"POS\"]]", "role": "assistant" } ]

[ { "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\nDNA methylation changes in hematologic malignancies: biologic and clinical implications. DNA methylation changes are among the most common detectable abnormalities in human neoplasia. Hypermethylation within the promoters of selected genes appears to be especially common in all types of human hematopoietic neoplasms, and is usually associated with inactivation of the involved gene (s). Such hypermethylation-associated silencing of gene expression has been shown for several genes regulating the growth and differentiation of hematopoietic cells, including the estrogen receptor (ER) gene, P15, P16 and others. Hypermethylation within the promoters of some genes appear to be an early event in the pathogenesis of neoplasia (ER, P15), while other genes seem to become methylated during the progression of leukemias (HIC1, c-abl). The high prevalence of promoter methylation suggests that this molecular abnormality can be used to monitor disease activity during therapy. In addition, new technology allows the sensitive identification of gene hypermethylation in a background of normal cells, suggesting possible new strategies for the detection of minimal residual disease. Finally, reactivation of tumor-suppressor gene expression through pharmacologic inhibition of DNA methyltransferase and resultant DNA demethylation appears to be a promising new avenue of therapy in acute leukemia.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"normal cells\", \"hematopoietic cells\", \"human hematopoietic neoplasms\"], \"DNA\": [\"promoters\", \"P15\", \"estrogen receptor (ER) gene\", \"ER\"], \"Protein\": [\"DNA methyltransferase\"], \"RNA\": []}", "role": "assistant" } ]

[ { "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 Alzheimers disease resilience?\n\nContext: Apolipoprotein E (APOE) ɛ4 and Clusterin (CLU) C alleles are risk factors for Alzheimer's disease (AD) and episodic memory (EM) decline. Memory resilience occurs when genetically at-risk adults perform at high and sustained levels.\nsome 30 to 50% of older individuals who harbor AD pathology do not become symptomatic in their lifetime. It is hypothesized that such individuals exhibit cognitive resilience that protects against AD dementia.\nParticipants with normal cognition (n = 297) and mild cognitive impairment (n = 432) were drawn from the Alzheimer's Disease Neuroimaging Initiative. Resilience metrics were defined at baseline by examining the residuals when regressing brain aging outcomes (hippocampal volume and cognition) on CSF biomarkers. A positive residual reflected better outcomes than expected for a given level of pathology (high resilience). Residuals were integrated into a latent variable model of resilience and validated by testing their ability to independently predict diagnostic conversion, cognitive decline, and the rate of ventricular dilation.\nAlzheimer's disease (AD) represents the most common form of dementia in elder populations with approximately 30 million cases worldwide. Genome wide genotyping and sequencing studies have identified many genetic variants associated with late-onset Alzheimer's disease (LOAD). While most of these variants are associated with increased risk of developing LOAD, only limited number of reports focused on variants that are protective against the disease.", "role": "user" }, { "content": "Some 30 to 50% of older individuals who harbor AD pathology do not become symptomatic in their lifetime. It is hypothesized that such individuals exhibit cognitive resilience that protects against AD dementia.", "role": "assistant" } ]

[ { "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: [\"AnatomicalEntity\"].\n\nPlease return the output as a JSON object of the format: {\"AnatomicalEntity\": [\"tumor cells\", ...]}. 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 an empty JSON array \"[]\".\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nOncogenic mechanisms of Evi-1 protein. \nAlthough Evi-1 is thought to promote growth or block differentiation in some cell types, its biological functions have not been elucidated. To explore the mechanisms underlying Evi-1-induced oncogenesis, we investigated whether Evi-1 affects the signaling of transforming growth factor beta (TGF-beta), which inhibits proliferation of a wide range of cell types and is one of the most studied growth regulatory factors. We demonstrated that Evi-1 represses TGF-beta signaling and antagonizes its growth-inhibitory effects. Two separate regions of Evi-1 are responsible for this repression, one of which is the first zinc-finger domain. Through this domain, Evi-1 physically interacts with Smad3, an intracellular mediator of TGF-beta signaling, thereby suppressing the transcriptional activity of Smad3. These results define a novel function of Evi-1 as a repressor of signaling components of TGF-beta. We also demonstrated that Evi-1 represses Smad-induced transcriptional activation by recruiting CtBP as a corepressor. Evi-1 associates with CtBP1 through one of the CtBP-binding consensus motifs within the region from amino acid 544 to 607, and this association is required for the efficient inhibition of TGF-beta signaling. A specific histone deacetylase (HDAc) inhibitor, trichostatin A (TSA), alleviates Evi-1-mediated repression of TGF-beta signaling, suggesting that HDAc is involved in transcriptional repression by Evi-1. This identifies a novel function of Evi-1 as a member of corepressor complexes and suggests that aberrant recruitment of corepressors is one of the mechanisms involved in Evi-1-induced leukemogenesis. These results indicate that specific HDAc inhibitors may be useful in the treatment of Evi-1-induced neoplastic tumors, including myeloid leukemias.", "role": "user" }, { "content": "{\"AnatomicalEntity\": [\"intracellular\", \"myeloid leukemias\", \"neoplastic tumors\", \"cell\"]}", "role": "assistant" } ]

[ { "content": "You will be presented with a paragraph from a COVID-19 literature. Your task is to classify the topics of this piece of text by choosing from the following categories:\n\n- Epidemic Forecasting: The content relates to predictions about the spread of COVID-19.\n- Treatment: The paragraph discusses therapeutic methods or medication for COVID-19.\n- Prevention: The content covers measures to prevent the spread of COVID-19.\n- Mechanism: The paragraph explains the biological mechanisms of the virus.\n- Case Report: The content is a report of a COVID-19 case.\n- Transmission: The paragraph discusses how COVID-19 is transmitted.\n- Diagnosis: The content is about diagnosing COVID-19 in individuals.\n\nYour classification should be provided as an element within a JSON array. The array should be formatted with topics enclosed in double quotes and separated by commas, following the JSON format, for example: [\"Topic1\", \"Topic2\", ...]. Include all applicable categories within the array. \nYour output should be a valid JSON array, and no additional text should be included in your response.\n\nArticle:\n\nAfter diagnosed in Wuhan, COVID-19 spread quickly in mainland China. Though the epidemic in regions outside Hubei in mainland China has maintained a degree of control, evaluating the effectiveness and timeliness of intervention strategies, and predicting the transmission risk of work resumption as well as lifting the lockdown in Hubei province remain urgent. A patch model reflecting the mobility of population between Hubei and regions outside Hubei is formulated, and parameterized based on multiple source data for Hubei and regions outside Hubei. The effective reproduction numbers for Hubei and regions outside Hubei are estimated as 3.59 and 3.26 before Jan 23rd, 2020, but decrease quickly since then and drop below 1 after Jan 31st and Jan 28th, 2020. It is predicted that the new infections in Hubei province will decrease to very low level in mid-March, and the final size is estimated to be about 68,500 cases. The simulations reveal that contact rate after work resumption or lifting the lockdown in Hubei plays a critical role in affecting the epidemic. If the contact rate could be kept at a relatively low level, work resumption starting as early as on March 2nd in Hubei province may not induce the secondary outbreak, and the daily new infectious cases can be controlled at a low level if the lockdown in Hubei is liftted after March 9th, otherwise both work resumption and lifting the lockdown in Hubei should be postponed.", "role": "user" }, { "content": "[\"Prevention\"]", "role": "assistant" } ]

[ { "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: For which type of diabetes can empagliflozin be used?\n\nContext: Empagliflozin, an SGLT2 inhibitor for the treatment of type 2 diabetes mellitus: a review of the evidence.\nTo review available studies of empagliflozin, a sodium glucose co-transporter-2 (SGLT2) inhibitor approved in 2014 by the European Commission and the United States Food and Drug Administration for the treatment of type 2 diabetes mellitus (T2DM).\nIn Phase II trials in patients with type 2 diabetes, empagliflozin provided improvements in glycosylated hemoglobin (HbA1c) and other measures of glycemic control when given as monotherapy or add-on to metformin, as well as reductions in weight and systolic blood pressure.\nEmpagliflozin: a review of its use in patients with type 2 diabetes mellitus.\nThis article reviews the pharmacological properties and clinical use of empagliflozin in patients with type 2 diabetes.\nEmpagliflozin: a new sodium-glucose co-transporter 2 (SGLT2) inhibitor for the treatment of type 2 diabetes.\nTo evaluate the pharmacodynamics, pharmacokinetics, safety and tolerability of empagliflozin in Japanese patients with type 2 diabetes mellitus.\nA Phase IIb, randomized, placebo-controlled study of the SGLT2 inhibitor empagliflozin in patients with type 2 diabetes.\nPharmacokinetics, pharmacodynamics, safety and tolerability of 4 weeks' treatment with empagliflozin in Japanese patients with type 2 diabetes mellitus.\nWe assessed the efficacy and safety of empagliflozin as an add-on treatment in patients with type 2 diabetes and CKD.\nThe SGLT-2 inhibitor empagliflozin improves glucose control, body weight and blood pressure when used as monotherapy or add-on to other antihyperglycemic agents in patients with type 2 diabetes\nData from five randomized, placebo-controlled, multiple oral dose studies of empagliflozin in patients with type 2 diabetes mellitus (T2DM; N = 974; 1-100 mg q.d.; ≤12 weeks) were used to develop a population pharmacokinetic (PK) model for empagliflozin\nEmpagliflozin, (2S,3R,4R,5S,6R)-2-[4-chloro-3-[[4-[(3S)-oxolan-3-yl]oxyphenyl]methyl]phenyl]-6-(hydroxymethyl)oxane-3,4,5-triol was recently approved by the FDA for the treatment of chronic type 2 diabetes mellitus\nThe SGLT2 inhibitor empagliflozin has gained approval in the EU and in the USA for the treatment of adults with T2DM (there is no current indication in type 1 diabetes)\nPharmacokinetics, pharmacodynamics, safety and tolerability of 4 weeks&apos; treatment with empagliflozin in Japanese patients with type 2 diabetes mellitus\nThe SGLT-2 inhibitor empagliflozin improves glucose control, body weight and blood pressure when used as monotherapy or add-on to other antihyperglycemic agents in patients with type 2 diabetes.\nEfficacy and safety of empagliflozin, a sodium glucose cotransporter 2 (SGLT2) inhibitor, as add-on to metformin in type 2 diabetes with mild hyperglycaemia.\nThe SGLT2 inhibitor empagliflozin ameliorates early features of diabetic nephropathy in BTBR ob/ob type 2 diabetic mice with and without hypertension.\nRationale, design and baseline characteristics of a 4-year (208-week) phase III trial of empagliflozin, an SGLT2 inhibitor, versus glimepiride as add-on to metformin in patients with type 2 diabetes mellitus with insufficient glycemic control.\nExposure-response modelling for empagliflozin, a sodium glucose cotransporter 2 (SGLT2) inhibitor, in patients with type 2 diabetes.\nThis article reviews the pharmacological properties and clinical use of empagliflozin in patients with type 2 diabetes.\nWith its insulin-independent mechanism of action, empagliflozin monotherapy or combination therapy with other antidiabetic drugs, including insulin, provides a useful addition to the therapeutic options for the management of type 2 diabetes.\nIn several phase III trials (104weeks' duration; typically 24weeks' duration) and extension studies (typically76weeks' treatment), empagliflozin monotherapy or add-on therapy to other antihyperglycaemics, including insulin, improved glycaemic control and reduced bodyweight and systolic blood pressure in adult patients with type 2 diabetes.\nOral empagliflozin (Jardiance()), a sodium glucose cotransporter-2 (SGLT2) inhibitor, is a convenient once-daily treatment for adult patients with type 2 diabetes mellitus.\nSodium glucose cotransporter 2 (SGLT2) inhibitors are a new class of treatment for T2DM that reduce hyperglycemia by reducing renal glucose reabsorption and thereby increasing urinary glucose excretion.This paper reviews the pharmacokinetic and pharmacodynamic properties of the SGLT2 inhibitor empagliflozin , the results of clinical trials investigating the efficacy of empagliflozin given as monotherapy or as add-on therapy on glycemic control, body weight, and blood pressure in patients with T2DM, and the safety and tolerability profile of empagliflozin.Empagliflozin offers good glycemic efficacy, weight loss, blood pressure reduction, and a low risk of hypoglycemia.\nEmpagliflozin for the treatment of type 2 diabetes.\nThis paper reviews the pharmacokinetic and pharmacodynamic properties of the SGLT2 inhibitor empagliflozin , the results of clinical trials investigating the efficacy of empagliflozin given as monotherapy or as add-on therapy on glycemic control, body weight, and blood pressure in patients with T2DM, and the safety and tolerability profile of empagliflozin.\nIn patients with type 2 diabetes and stage 2 or 3 CKD, empagliflozin reduced HbA1c and was well tolerated. However, our findings might not be applicable to the general population of patients with type 2 diabetes and renal impairment.\nWith its insulin-independent mechanism of action, empagliflozin monotherapy or combination therapy with other antidiabetic drugs, including insulin, provides a useful addition to the therapeutic options for the management of type 2 diabetes. This article reviews the pharmacological properties and clinical use of empagliflozin in patients with type 2 diabetes.\nIn patients with type 2 diabetes, empagliflozin resulted in dose-dependent, clinically meaningful reductions in HbA1c and FPG, and reductions in body weight compared with placebo. Empagliflozin was well-tolerated with a favourable safety profile.\nNo UTIs or genital infections led to premature discontinuation. In patients with type 2 diabetes, empagliflozin resulted in dose-dependent, clinically meaningful reductions in HbA1c and FPG, and reductions in body weight compared with placebo.\nIn patients with type 2 diabetes, empagliflozin resulted in dose-dependent, clinically meaningful reductions in HbA1c and FPG, and reductions in body weight compared with placebo.\nIn Phase II trials in patients with type 2 diabetes, empagliflozin provided improvements in glycosylated hemoglobin (HbA1c) and other measures of glycemic control when given as monotherapy or add-on to metformin, as well as reductions in weight and systolic blood pressure.\nThis article reviews the pharmacological properties and clinical use of empagliflozin in patients with type 2 diabetes.\nA Phase IIb, randomized, placebo-controlled study of the SGLT2 inhibitor empagliflozin in patients with type 2 diabetes.\nEmpagliflozin: a review of its use in patients with type 2 diabetes mellitus.\nEmpagliflozin: a new sodium-glucose co-transporter 2 (SGLT2) inhibitor for the treatment of type 2 diabetes.\nIn patients with type 2 diabetes, empagliflozin-induced glycosuria improved β cell function and insulin sensitivity, despite the fall in insulin secretion and tissue glucose disposal and the rise in EGP after one dose, thereby lowering fasting and postprandial glycemia.\nSingle-pill combination therapy for type 2 diabetes mellitus: linagliptin plus empagliflozin.", "role": "user" }, { "content": "type 2 diabetes mellitus", "role": "assistant" } ]

[ { "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\nLack of evidence of lower 30-day all-cause readmission in Medicare beneficiaries with heart failure and reduced ejection fraction discharged on spironolactone Therapy with evidence -based heart failure (HF) medications has been shown to be associated with lower risk of 30-day all-cause readmission in patients with HF and reduced ejection fraction (HFrEF). We examined the association of aldosterone antagonist use with 30-day all-cause readmission in this population. Of the 2443 Medicare beneficiaries with HF and left ventricular EF ≤35% discharged home from 106 Alabama hospitals during 1998-2001, 2060 were eligible for spironolactone therapy (serum creatinine ≤2.5 for men and ≤2mg/dl for women, and serum potassium <5mEq/L). After excluding 186 patients already receiving spironolactone on admission, the inception cohort consisted of 1874 patients eligible for a new discharge prescription for spironolactone, of which 329 received one. Using propensity scores for initiation of spironolactone therapy, we assembled a matched cohort of 324 pairs of patients receiving and not receiving spironolactone balanced on 34 baseline characteristics (mean age 72years, 42% women, 33% African American). Thirty-day all-cause readmission occurred in 17% and 19% of matched patients receiving and not receiving spironolactone, respectively (hazard ratio [HR], 0.92; 95% confidence interval [CI], 0.64-1.32; p=0.650). Spironolactone had no association with 30-day all-cause mortality (HR, 0.84; 95% CI, 0.38-1.88; p=0.678) or HF readmission (HR, 0.74; 95% CI, 0.41 1.31; p=0.301). These associations remained unchanged during 12months of post-discharge follow-up. A discharge prescription for spironolactone had no association with 30-day all-cause readmission among older, hospitalized Medicare beneficiaries with HFrEF eligible for spironolactone therapy.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"ejection fraction\", \"heart failure\", \"HF\", \"HFrEF\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"aldosterone antagonist\", \"Spironolactone\", \"spironolactone\"], \"ClinicalAttribute\": [\"left ventricular EF\"], \"Eukaryote\": [], \"Finding\": [\"examined\", \"reduced ejection fraction\", \"serum creatinine\", \"post-discharge follow-up\"], \"Food\": [], \"HealthCareActivity\": [\"discharge\", \"discharged home\", \"Therapy\", \"therapy\", \"discharged\", \"admission\", \"serum potassium\", \"readmission\", \"prescription\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"medications\"], \"MedicalDevice\": [], \"Organization\": [\"hospitals\"], \"PopulationGroup\": [\"population\", \"African American\", \"cohort\"], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [], \"SpatialConcept\": [\"Alabama\"], \"Virus\": []}", "role": "assistant" } ]

[ { "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:\nexperiments\n\nContext before the citation:\nbased parsing algorithms with an arc-factored parameterization (McDonald et al., 2005). • Graph-based: An implementation of graph- \u0000\u0000 All feature conjunctions are included.\n\nCitation Sentence:\nbased parsing algorithms with an arc-factored parameterization ( McDonald et al. , 2005 ) .\n\nContext after the citation:\nWe use the non-projective k-best MST algorithm to generate k-best lists (Hall, 2007), where k = 8 for the experiments in this paper. The graphbased parser features used in the experiments in this paper are defined over a word, wi at position i; the head of this word wρ(i) where ρ(i) provides the index of the head word; and partof-speech tags of these words ti. We use the following set of features similar to McDonald et al. (2005): \u0000\u0000", "role": "user" }, { "content": "Uses", "role": "assistant" } ]

[ { "content": "You will be shown a claim related to the COVID-19 pandemic, 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\".\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract.\n\nFor instance, if the model were given the claim \"the COVID vaccine is safe for healthy adults\", the output might be:\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that the risks of severe COVID vaccine side effects are low for healthy adults.\"]\n}\n\nClaim: Antigen-based testing but strong real-time pcr correlates with sars-cov-2 virus culture\n\nAbstract:\nIndividuals can test positive for SARS-CoV-2 by real-time polymerase chain reaction (RT-PCR) after no longer being infectious.1-8 Positive SARS-CoV-2 antigen-based testing exhibits a temporal pattern that corresponds with active, replicating virus and could therefore be a more accurate predictor of an individuals potential to transmit SARS-CoV-2.2,3,9 Using the BD Veritor System for Rapid Detection of SARS-CoV-2 later flow antigen detection test, we demonstrate a higher concordance of antigen-positive test results with the presence of cultured, infectious virus when compared to RT-PCR.\nWhen compared to infectious virus isolation, the sensitivity of antigen-based testing is similar to RT-PCR.\nThe correlation between SARS-CoV-2 antigen and SARS-CoV-2 culture represents a significant advancement in determining the risk for potential transmissibility beyond that which can be achieved by detection of SARS-CoV-2 genomic RNA.\nCoupled with a rapid time-to-result, low cost, and scalability, antigen-based testing should facilitate effective implementation of testing and public health interventions that will better contain COVID-19.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"The correlation between SARS-CoV-2 antigen and SARS-CoV-2 culture represents a significant advancement in determining the risk for potential transmissibility beyond that which can be achieved by detection of SARS-CoV-2 genomic RNA.\", \"Coupled with a rapid time-to-result, low cost, and scalability, antigen-based testing should facilitate effective implementation of testing and public health interventions that will better contain COVID-19.\"]}", "role": "assistant" } ]

[ { "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\nMediation Analysis for Health Disparities Research Social epidemiologists often seek to determine the mechanisms that underlie health disparities. This work is typically based on mediation procedures that may not be justified with exposures of common interest in social epidemiology. In this analysis, we explored the consequences of using standard approaches, referred to as the difference and generalized product methods, when mediator-outcome confounders are associated with the exposure. We compared these with inverse probability -weighted marginal structural models, the structural transformation method, doubly robust g-estimation of a structural nested model, and doubly robust targeted minimum loss -based estimation. We used data on 900,726 births from 2003 to 2007 in the Penn Moms study, conducted in Pennsylvania, to assess the extent to which breastfeeding prior to hospital discharge explained the racial disparity in infant mortality. Overall, for every 1,000 births, 3.36 more infant deaths occurred among non-Hispanic black women relative to all other women (95% confidence interva l: 2.78, 3.93). Using the difference and generalized product methods to assess the disparity that would remain if everyone breastfed prior to discharge suggested a complete elimination of the disparity (risk difference = -0.87 per 1,000 births; 95% confidence interval: -1.39, -0.35). In contrast, doubly robust methods suggested a reduction in the disparity to 2.45 (95% confidence interva l: 2.20, 2.71) more infant deaths per 1,000 births among non-Hispanic black women. Standard approaches for mediation analysis in health disparities research can yield misleading results.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"breastfed\", \"breastfeeding\", \"interest\", \"births\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"disparity\", \"health disparities\", \"racial disparity\", \"Health Disparities\", \"infant deaths\"], \"Food\": [], \"HealthCareActivity\": [\"hospital discharge\", \"discharge\", \"reduction\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"structural transformation method\", \"generalized product methods\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [\"non-Hispanic black women\", \"women\"], \"ProfessionalOrOccupationalGroup\": [\"epidemiologists\"], \"ResearchActivity\": [\"Research\", \"Penn Moms study\"], \"SpatialConcept\": [\"Pennsylvania\"], \"Virus\": []}", "role": "assistant" } ]

[ { "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:\na 54-year - old woman with gravidity 3 and parity 1 , who had been postmenopausal for two years , presented with a 6-month history of vaginal bleeding and general weakness .\nthe patient looked generally anemic and fatigued , and had no past history of taking estrogen replacement therapy .\nin addition , the patient had a body mass index of 24.5 kg / m and a blood cancer antigen 125 level of 24.2 u / ml ( normal range , 0 to 35 u / ml ) . the patient had a normal papanicolaou smear but no notable gynecological history .\ntransvaginal ultrasound showed a 7-cm protruding mass in the endometrial cavity with an endometrial thickness of 22.3 mm .\nin addition , the mass was surrounded by echogenic blood flow and it showed an ill - defined margin with the myometrium .\nthe patient underwent total hysterectomy with a bilateral salpingo - oophorectomy under the laparoscopic guidance under a provisional diagnosis of submucosal leiomyoma .\nthe tumor did not involve the serosal surface of the uterus or the abdominal cavity .\ngrossly , there was an ill - defined , relatively solid endometrial mass with a spotty necrosis , measuring 765 cm .\nin addition , it involved the myometrium at the fundus and body but not its serosal tissue . following a careful examination ,\nthe entire uterine cervix was divided into 12 sections in total from the 12 o'clock position .\nmicroscopically , the tumor showed a clear evidence of squamous differentiation , such as presence of intercellular bridges and keratinization ( fig .\n1a , b ) , thus confirming a well - differentiated , invasive scc of the endometrium .\nthe tumor involved more than 80% of the myometrial thickness and it showed a vascular invasion to the myometrium . in the adjacent non - neoplastic endometrium , there were glands with both a pseudostratification and a ciliary change and their stroma was infiltrated by inflammatory cells , plasma cells and neutrophils in particular ( fig .\nthere were no evidences demonstrating the presence of squamous metaplasia of the endometrium , endometrial adenocarcinoma , cervical scc and a connection between the endometrial tumor and the squamous epithelium of the cervix .\non immunohistochemistry , there was a positive immunoreactivity for cytokeratin 7 , p63 ( fig .\n1d ) , but not for cytokeratin 20 and estrogen receptor ( er ) and progesterone receptor ( pr ) .\nbut hpv was not detected on either in situ hybridization ( ish ) or hpv dna chip analysis .\nthe patient showed a disease - free course during a 13-month follow - up period .\nthe connection between the endometrium and the cervix should therefore be ruled out in making a diagnosis of pescc .\nsquamous differentiation of an endometrioid adenocarcinoma must also be excluded.2 several theories regarding the cellular origin of pescc have been proposed : 1 ) reserve or stem cells located between the glandular basement membrane and the endometrial columnar cell layer;4 2 ) squamous metaplasia of the normal endometrium;5 and 3 ) heterotopic cervical tissue.6 it has been reported that vitamin a deficiency , anti - estrogen treatment , pyometra , chronic infection , uterine prolapse , myoma , intrauterine device , history of pelvic irradiation and curettage are associated with squamous metaplasia of the endometrium.2,5,7,8 hpv infection plays a key role in the pathogenesis of squamous neoplasms of the uterine cervix,9 whose role in that of pescc remains controversial . of note ,\nkataoka et al.10 demonstrated the presence of hpv type 31 by the polymerase chain reaction ( pcr ) in one patient with pescc .\nbut there were no other reports demonstrating a clear association between hpv and pescc.11 - 13 horn et al.11 performed an hpv analysis with general primers and hpv typing in eight patients with pescc .\ngiordano et al.12 failed to detect hpv dna by pcr in one patient with pescc .\nin addition , i m et al.13 could not detect hpv by ish in three patients with pescc . according to review of literatures about five korean women with pescc ( table 1 ) , there were one positive case for hpv 16/18 in the cervix but not the endometrium by ish and pcr assay14 and another negative case for hpv 16/18 by pcr assay.15 moreover , we did not find any evidence of hpv in our patient .\nwe therefore suggest that hpv may not be the primary causative factor for pescc . a cyclin - dependent kinase-4 inhibitor involved in the prb pathway\n, p is a surrogate marker for hpv infection in cervical neoplasms.9 it has been reported that p is expressed in some cases of endometrial carcinoma.11,16 to date , however , fewer attempts have been made to evaluate both the hpv status and p expression .\nansari - lari et al.16 reported that p expression is moderate to strong and diffuse in endocervical adenocarcinoma and weak and patchy in endometrial adenocarcinoma .\nthese findings suggest that p immunohistochemistry may be helpful for distinguishing endocervical adenocarcinoma from endometrial adenocarcinoma . according to horn et\nal.,11 50% of the cases showed a positive p immunoreactivity but there was only one positive case for hpv .\nthese reports suggest that alterations of the p pathway may play a role in the pathogenesis of some cases of pescc , if any , without an hpv involvement .\nsimilarly , our case showed weak and patchy p expression and negative results for hpv by both ish and dna chip analysis .\nour case therefore indicates that p overexpression may be involved in the development of pescc with no respect to hpv infection .\nthe clinical applicability of the er and pr status as a prognostic indicator of pescc is still uncertain .\nconsidering that most patients are postmenopausal , however , a loss of estrogen can not be completely ruled out as an etiologic factor .\nthis is not only because most cases of pescc occur in postmenopausal women but also because one of the most frequent presenting symptoms is vaginal bleeding . the average duration of symptoms before diagnosis is 11.5 months.8 total hysterectomy with a bilateral salpingo - oophorectomy is the first line of choice for menopausal women .\nthe effectiveness of radiotherapy and chemotherapy as adjuvant treatments remains highly controversial.7,8 pescc has a poor prognosis compared with endometrial adenocarcinoma .\nthat is , it is well documented that the 5-year survival rates in endometrial adenocarcinoma at stages i , ii , iii , and iv are 89.1% , 78.8% , 57.8% , and 22.8% , respectively.17 however , the 5-year survival rate of pescc is difficult to assess because of its rarity . with a survival period ranging from 14 to 36 months , it has been reported that the 1-year survival rates in pescc at stages i , iii , and iv are 80% , 20% , and 0% , respectively.7,8 the mean age of the six korean patients ( table 1 ) , including our case , was 62 years ( range , 54 to 68 years ) , all of whom were postmenopausal.14,15,18 - 20 most of the korean women with pescc are multiparous , which is contradictory to the report , by goodman et al.,8 made from nulliparous women . in addition , vaginal bleeding is one of the typical symptoms that occur in korean women . in summary\n, there was positive p immunoreactivity with no evidence of hpv by ish and dna chip analysis in our case .\nour case highlights the significant role of p overexpression , regardless of the hpv status in the pathogenesis of pescc .\nhenceforth , however , further large - scale studies are warranted to gain a deeper insight into its characteristics of pescc .", "role": "user" }, { "content": "primary endometrial squamous cell carcinoma ( pescc ) is an extremely rare tumor with unclear pathogenesis . \n a 54-year - old postmenopausal woman presented with a 6-month history of vaginal bleeding . \n the patient was provisionally diagnosed with uterine submucosal leiomyoma . \n this was followed by total hysterectomy with a bilateral salpingo - oophorectomy under the laparoscopic guidance . \n histopathologically , the tumor was pescc which was accompanied by a lack of the tumor in the uterine cervix . \n the tumor showed positive immunoreactivity for p16ink4a . \n but there was no evidence of human papillomavirus ( hpv ) on in situ hybridization and hpv dna chip analysis . \n we also present a review of the relevant literature on korean women .", "role": "assistant" } ]

[ { "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: The large-scale multimodal dataset [35] with billions of text-image pairs crawled from Internet has enabled breakthrough in open-domain Text-to-Image (T2I) generation [25, 29, 4, 6, 34]. To replicate this success in Text-to-Video (T2V) generation, recent works [36, 14, 17, 48] extend the spatial-only T2I generation models to the spatio-temporal domain.These models generally adopt the standard paradigm to finetune T2I models on large-scale text-video datasets (e.g., WebVid-10M [2]).Although this paradigm produces decent results for T2V generation, it requires extensive training, which is expensive and not affordable to everyone. Human is capable of one-shot learning [22, 23, 42]. For instance, given a video paired with a textual description of “a man is skiing on snow” as a hint, we might hallucinate how a panda skis on snow if we could picture what a panda looks like.Since T2I models pre-trained with large-scale image-text data already capture the knowledge of open-domain concepts,an intuitive question arises:can it infer other novel videos from a single video example like human beings?A new T2V generation problem is therefore introduced, namely, One-Shot Video Generation, where only a single text-video pair is presented for training an open-domain T2V generator.The generator is expected to capture necessary motion knowledge from the input video and synthesize novel videos guided by edited prompts. Intuitively, the key to video generation is to keep the continuous motion of consistent objects.So we make the following observations on state-of-the-art T2I diffusion models [31] that motivate our method accordingly.(1) Regarding motion: T2I models are able to generate images that align well with the text, including the verb terms. For example, given the text prompt “a man is running on the beach”, the T2I models produce the snapshot where a man is running (not walking or jumping), but not continuously (the first row of Fig. 2).This serves as evidence that T2I models can properly attend to verbs via cross-modal attention for static motion generation.(2) Regarding consistent objects: Simply extending the self-attention in the T2I model from one image to multiple images maintains content consistency across frames.Taking the same example, when we generate consecutive frames in parallel with extended cross-frame attention to the 1st frame, the same man and the same beach can be observed in the resultant sequence though the motion is still not continuous (the second row of Fig. 2). This implies that the self-attention layers in T2I models are only driven by spatial similarities rather than pixel positions. We provide several applications of our Tune-A-Video in generating videos with novel visual concepts (e.g., subjects, backgrounds, attributes, styles, etc.) guided by the text prompt. Here, we showcase two training examples: “a polar bear is walking on ice” (“walking bear”, the 1st row of Fig. 7), “a young man is running on the beach” (“running man”, the 5th row of Fig. 7), and their variations with edited prompts. More examples can be found in Fig. 12-14. Our Tune-A-Video also enables changing the video background (i.e., place where the subject is), while keeping the motions of the subject and the temporal information consistent. For example, we can “send” a polar bear walking on the ice to Time Square (the 3rd of Fig. 7), and a man running on the beach to mountain (the 6th row of Fig. 7). We observe that some background semantic is tied to the subject, e.g., in the case of “walking bear”, although the background is replaced with Time Square, the color of the ground still remains similar to ice. We conjecture this is due to the strong regularities between “polar bear” and “ice”. We examine the ability of our Tune-A-Video in modifying the attributes such as color (e.g., a man wearing yellow to be in red, the 2nd row of Fig. 1) and age (e.g., a young man to become old, the 6th row of Fig. 7). We found that our Tune-A-Video even enables modifying the attribute that is not specified in the training prompt (e.g., we do not tell the model the skiing man in the training video wears yellow clothes). Notably, other properties in training video could be well preserved (e.g., the black backpack wore by the skiing man, and the blue shirts and black shorts wore by the running man). We implement our findings into a simple yet effective method, dubbed as Tune-A-Video, for the task of One-Shot Video Generation.Tune-A-Video is based on a simple inflation of pre-trained T2I diffusion models [31] over time dimension, by extending the 3\\times 3 convolution to 1\\times 3\\times 3, and spatial self-attention to spatio-temporal cross-frame attention.We propose an efficient tuning strategy that only updates the projection matrices in attention blocks to capture continuous motion dynamics from the one-shot video, with the rest of parameters being frozen. To imitate how humans adapt new visual concepts from a single exemplar, we introduce a new T2V generation task called One-Shot Video Generation, where only a single text-video pair is provided for training an open-domain T2V generator.To this end, we propose Tune-A-Video, a simple yet effective solution based on pretrained T2I diffusion models.Our method exploits the properties of pretrained T2I models by extending spatial self-attention to spatio-temporal domain with a tailored Sparse-Causal Attention.To capture necessary motion knowledge, we update the projection matrices in attention block on one training sample. Given this, our Tune-A-Video supports several T2V applications, including subject replacement, background change, attribute modification, style transfer, and etc.\n\nQuestion: What is the reason for adopting this?", "role": "user" }, { "content": "To imitate human's ability to adapt new visual concets, One-Shot Video Generation task is proposed. Tune-A-Video generates videos with novel visual concepts (e.g., subjects, backgrounds, attributes, styles, etc.) guided by the text prompt. It is expensive to finetune T2I models on large-scale text-video datasets and not affordable to everyone.", "role": "assistant" } ]