dataset
stringclasses 45
values | id
stringlengths 17
64
| messages
listlengths 2
2
|
|---|---|---|
science.bioasq_factoid_qa
|
science.bioasq_factoid_qa.521
|
[
{
"content": "Answer the following biomedical question based on the given context. Provide only the answer without additional explanation.\n\nQuestion: Viliuisk encephalomyelitis is diagnosed in which geographical area?\n\nContext: BACKGROUND: Viliuisk encephalomyelitis (VE) is an endemic neurological disease in Northeast Siberia and generally considered to be a chronic encephalomyelitis of unknown origin actually spreading in the Sakha (Yakutian) Republic.\nCommunicating hydrocephalus following eosinophilic meningitis is pathogenic for chronic Viliuisk encephalomyelitis in Northeastern Siberia.\nEpidemiology of Viliuisk encephalomyelitis in Eastern Siberia.\n. An epidemic of this disease has been spreading throughout the Yakut Republic of the Russian Federation.\nMETHODS: Detailed clinical, pathologic, laboratory, and epidemiologic studies have identified 414 patients with definite Viliuisk encephalomyelitis in 15 of 33 administrative regions of the Yakut Republic between 1940 and 1999.\nViliuisk encephalomyelitis in Eastern Siberia - analysis of 390 cases.\nViliuisk encephalomyelitis (VE) is a unique disease occurring in the Yakut (Sakha) population of Eastern Siberia.\nViliuisk encephalomyelitis in Northeastern Siberia is not caused by Borrelia burgdorferi infection.\nViliuisk encephalomyelitis (VE) is an endemic neurological disease in Northeastern Siberia and generally believed to be a chronic encephalomyelitis of unknown origin.\nViliuisk encephalomyelitis (VE) is an endemic neurological disease in Northeastern Siberia and generally believed to be a chronic encephalomyelitis of unknown origin.\nViliuisk encephalomyelitis (VE) is an endemic neurological disease in Northeast Siberia and generally considered to be a chronic encephalomyelitis of unknown origin actually spreading in the Sakha (Yakutian) Republic.\nViliuisk encephalomyelitis in the Iakut people of Siberia.\nInitially identified in a small Yakut-Evenk population on the Viliui River of eastern Siberia, the disease subsequently spread through human contacts to new geographic areas, thus characterizing Viliuisk encephalomyelitis as an emerging infectious disease.\nViliuisk encephalomyelitis (VE) is an unique neurological disease occurring in the Iakut (Sakha) people of Siberia.\nViliuisk encephalomyelitis (VEM) appears to be endemic disease, affecting native population in Yakutia (Yakut, Even, Evenk).\nViliuisk encephalomyelitis (VE) is an endemic neurological disease in Northeast Siberia and generally considered to be a chronic encephalomyelitis of unknown origin actually spreading in the Sakha (Yakutian) Republic.In search for the pathophysiology and causative agent of VE, we performed a cross-sectional study on clinical, serological and neuroimaging data on chronic VE patients during two medical expeditions to three villages within the Viliuiski river basin in the Republic of Sakha in 2000 and to the capital Yakutsk in 2006\nInitially identified in a small Yakut-Evenk population on the Viliui River of eastern Siberia, the disease subsequently spread through human contacts to new geographic areas, thus characterizing Viliuisk encephalomyelitis as an emerging infectious disease\nViliuisk encephalomyelitis (VE) is a unique disease occurring in the Yakut (Sakha) population of Eastern Siberia\nViliuisk encephalomyelitis in Northeastern Siberia is not caused by Borrelia burgdorferi infection\nViliuisk encephalomyelitis (VE) is an endemic neurological disease in Northeastern Siberia and generally believed to be a chronic encephalomyelitis of unknown origin\nInitially identified in a small Yakut-Evenk population on the Viliui River of eastern Siberia, the disease subsequently spread through human contacts to new geographic areas, thus characterizing Viliuisk encephalomyelitis as an emerging infectious disease.\nViliuisk encephalomyelitis (VE) is an endemic neurological disease in Northeast Siberia and generally considered to be a chronic encephalomyelitis of unknown origin actually spreading in the Sakha (Yakutian) Republic.In search for the pathophysiology and causative agent of VE, we performed a cross-sectional study on clinical, serological and neuroimaging data on chronic VE patients during two medical expeditions to three villages within the Viliuiski river basin in the Republic of Sakha in 2000 and to the capital Yakutsk in 2006.\nIgG antibodies to HTLV-I were measured in the sera and/or cerebrospinal fluid from 82 Guamanian patients with amyotrophic lateral sclerosis and parkinsonism-dementia, 164 Guamanian normal controls, 10 patients with kuru from the Eastern Highlands of Papua New Guinea, 4 patients with Viliuisk encephalomyelitis from the Iakut region of eastern Siberia, 45 Italian patients with multiple sclerosis, and 56 patients with polymyositis (49 from the United States and 7 from Jamaica).\nViliuisk encephalomyelitis (VE), a progressive neurological disorder with a fatal outcome usually in several months to 6 yrs after disease onset, is seen only among the Iakut people of Siberia.\nTransmission to unrelated persons was documented in a densely populated region around the city of Yakutsk in which Viliuisk encephalomyelitis had not been previously known.\nInitially identified in a small Yakut-Evenk population on the Viliui River of eastern Siberia, the disease subsequently spread through human contacts to new geographic areas, thus characterizing Viliuisk encephalomyelitis as an emerging infectious disease..\nEpidemiology of Viliuisk encephalomyelitis in Eastern Siberia.\nViliuisk encephalomyelitis in the Iakut people of Siberia.\nViliuisk encephalomyelitis in Eastern Siberia - analysis of 390 cases.",
"role": "user"
},
{
"content": "Northeast Siberia",
"role": "assistant"
}
] |
science.chemsum_single_document_summarization
|
science.chemsum_single_document_summarization.75385
|
[
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nSynthesis of 4-O-alkylated N-acetylneuraminic acid derivatives\n\nPaper sections:\nIntroduction\n<p>N-acetylneuraminic acid (Neu5Ac, 1, Figure 1) is typically found at the terminal end of glycolipids and glycoproteins that decorate the surfaces of all mammalian cell types. Neu5Ac is involved in mediating or modulating a variety of physiological and pathophysiological processes. 1 One of the most well-known roles of Neu5Ac is in the replication cycle of influenza virus. 2 Accordingly, substantial efforts have been placed on the development of Neu5Ac-based antivirals, 3 where modifications of the C4-position of 2deoxy-2,3-didehydro-N-acetylneuraminic acid (DANA, 2, Figure 1) have been of central importance. [4][5][6][7][8][9][10][11][12] This culminated in the development of Relenza® (3, Figure 1), a C4-modified analog of 2 designed to mimic the transition state of 1 during the neuraminidase catalyzed hydrolysis reaction required for release of virus progeny from infected cells. 5 C4-modified analogs of 2 including nitrogen 4 , sulfur 4 , and deoxygenated 7 compounds are efficiently accessed via selective ring opening at position 5 of the allylic oxazoline of 2,3-didehydro-N-acetylneuraminic acid (4, Figure 1). 4 However, in the case of oxygen nucleophiles opening occurs at position 2 of the oxazoline ring. 7 Hence, the method is not applicable to the synthesis of 4-O-modified analogs of 2 (or 1) with retained stereochemistry. C4-deoxy and C4nitrogen analogs of 1 can however be accessed using the ring-opening methodology but require reinstallment of the glycosidic bond which produces two stereoisomers of equal proportions. 13,14 The interest in Neu5Ac analogs and their roles in biological systems is constantly increasing. Therefore, efficient methods that allow site-selective modifications of the Neu5Ac-template are of great utility for studying Neu5Ac biology and for drug discovery. Methods to selectively access C4-modified analogs of 1 are scarce, with relatively few reported examples. These include carba 15,16 , keto 16 , ether 14,[17][18][19][20] , nitrogen 13 , and deoxygenated 21 derivatives. A potential drawback in the development of direct methods could be the competing formation of intramolecular lactams [22][23][24] and lactones 25 that occur under both basic and acidic conditions. To date, examples of selectively 4-O-modified Neu5Ac analogs include 4-O-Ac, -benzyl [26][27][28][29][30] , -allyl 23 , -silyl 15 , -methyl 14,17,18 , -ethyl 18 , -cyanomethyl 19 , and -tertbutoxyacetate 20 groups. The electrophiles used to produce these 4-O-modified analogs all have in common that they are activated, highly reactive, and with few exceptions lack the presence of b-hydrogens. Further, the commercial availability of suitable electrophiles remains limited. Herein, we set out to study the scope and the 4-O-alkylation of Neu5Ac.</p>\n\nResults and discussion\n<p>In an ongoing research project, we were interested in studying the potential of 4-O-alkyl analogs of 5 (Figure 1) as probes targeting cell attachment during adenovirus [31][32][33] and coxsackievirus infections 34,35 .</p><p>We hypothesized that 6 (Scheme 1) would be a suitable substrate to study O-alkylation. This previously described protective group strategy is straightforward, high yielding, and allow removal of the protective groups in a final single step. 15 Propargyl bromide was selected as the model electrophile. The lack of b-protons minimizes the competing E2 reaction, thus providing a fair measure of the effectiveness of the SN2 reaction. In addition, the generated alkynyl product can be further modified under mild conditions 36,37 . Compound 5 38 (Figure 1) was obtained from 1, and then converted by standard methods to the known derivative 7 39 Attempts to alkylate 6 using Ba(OH)2/BaO in DMF 23,30,40 , K2CO3 in THF, or CsCO3 in MeCN, resulted in minimal amounts of 16. However, promising observations were made in THF using KHMDS or NaH, with NaH providing superior conversion and product formation. Standard O-alkylation conditions were screened by treating 6 with NaH on ice prior to the addition of propargyl bromide (entries 1 and 2, Table 1). In DMF, this resulted in nearly complete decomposition and only trace amounts of 16 (entry 1). However, in THF the 4-O-propargylated derivative 17 was isolated in 50% yield over two steps (entry 2). The O-deacetylation was performed to compensate for formation of hydrolyzed species during the reaction (Figure S1), and thus facilitate isolation of the desired 4-O-alkyl product. The O-deacetylation of purified 16 gave 17 in 85% yield, the value that was used to estimate the yield for the O-alkylation (Table 1). Alkoxide formation was studied by mixing compound 6 with NaH in DMF-d7 and in THF-d8, respectively, and recording 1 H-NMR spectra at two different time points (Figure 2A-D, and Figure S2A-F). Within 10 minutes, compound 6 was essentially consumed in DMF-d7 resulting in a complex mixture of products (Figure 2A and B). In contrast, only minimal signs of degradation were observed in THF-d8 10 minutes post-addition of NaH (Figure 2C and D), and the majority of 6 was largely intact after 1 hour (Figure S2F). This prompted us to reverse the addition order, 6 was mixed with propargyl bromide in the selected solvent on ice before adding NaH. Furthermore, the stoichiometry of NaH was increased from 1.1 to 2.0 equivalents to assure complete deprotonation of both the hydroxyl and acetamide of 6. These modifications drastically improved the yield of 17 in DMF (40%; entry 3, Table 1), while no significant effect was observed in THF (52% yield; entry 4). This highlights the importance of avoiding preformation of the alkoxide in DMF. The 4-O-alkylated product 17 was confirmed by 2D NMR analysis, and by treatment with acetic anhydride in pyridine which afforded 16 in 60% yield. the optimized conditions at hand the stoichiometry of NaH was adjusted to 1.5 equivalents as conversion was incomplete in some reactions when using 1.1 equivalents. This resulted in complete conversion of 6, providing 17 in 67% yield (entry 17). To conclude, the optimal conditions are a concentration of 0.3 M (in THF), 5.0 equivalents of propargyl bromide, and 1.1-1.5 equivalents of NaH.</p>\n\nScheme 2. Orthogonal protection of Neu5Ac derivates at the 7-, 8-, and 9-positions.\n<p>In an attempt to further improve the yields of the O-alkylation, compounds 15 and 18 were prepared (Scheme 1 and 2, respectively). Compound 15 with its tertiary amide renders it resistant toward potential side products arising from lactamization [22][23][24] . In two steps, 15 was accessed from 11 by treatment with Boc anhydride and DMAP in THF followed by cleavage of the TBDMS group using TBAF (Scheme 1).</p><p>Surprisingly, the reactivity of 15 was completely abolished towards O-alkylation (entry 1, Table 2).</p><p>Prolonged reaction times (2.5 h), heating (60 °C for 16 h), and irradiation in a microwave reactor (100 °C for 20 min) were inefficient in causing conversion. Compound 18 was prepared from the known derivative 19 41 including selective reduction with borane-trimethyl amine and aluminum chloride in THF affording 20 that upon treatment with 2,2-dimethoxypropane and camphor sulfonic acid in MeCN gave the 9-O-benzyl-7,8-acetonide protected 18 in 96% yield. This protective group strategy is orthogonal allowing site-selective removal and functionalization of the glycerol side chain (C7, C8, and C9).</p><p>Further, the protective groups have increased resistance toward hydrolysis under basic conditions.</p><p>Upon O-alkylation 18 gave 22 in 57% yield (entry 2). Compound 13 was prepared in analogous manner to 6 (Scheme 1), and upon O-alkylation afforded 23 in 74% yield (entry 3, Table 2). Compound 23, and analogs thereof, significantly broaden the scope due to their potential for modifications at the C2position via glycosylation, or elimination to access 4-O-alkyl DANA analogs. 19 The developed conditions were applied to synthetic intermediates 7 and 8 which provided 24 and 25 in 48% and 71% yields, respectively (entries 4 and 5, Table 2). Thus, supporting access to 7-O-alkylated species. Synthetic intermediates 26 and 27 selectively afforded the 4-O-alkylated products 28 and 29 in 31% and 49% yields (entries 6 and 7, Table 2), respectively. Thus, significantly decreasing the number of steps to</p>",
"role": "user"
},
{
"content": "The synthesis of 4-O-alkyl analogs of Neu5Ac and the scope of the 4-O-alkylation reaction are described. The experimental results support the use of activated alkyl halides and sulfonates, in addition to primary alkyl iodides. Primary alkyl bromides and tosylates provide 4-O-alkylated compounds in low yields, while primary alkyl chlorides and secondary alkyl bromides fail to afford alkylated products. In addition, we exemplified the utility of the methodology using a thiophenyl Neu5Ac building block to synthesize a 4-O-alkyl 2-deoxy-2,3-didehydro-N-acetylneuraminic acid (DANA) analog. The results presented expand the toolbox of Neu5Ac chemistry and the findings will be of value in the design of novel tools to study the biology of Neu5Ac binding proteins and as starting points for drug discovery.",
"role": "assistant"
}
] |
science.data_reco_mcq_mc
|
science.data_reco_mcq_mc.440
|
[
{
"content": "Based on the dataset descriptions below, which datasets would be suitable for the following research question? Your response should be a JSON array.\n\nQuestion: I want to train a fully supervised model for cooperative 3D object detection\n\nKeywords: cooperative 3d object detection point clouds\n\nDataset descriptions:\nKITTI: KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) is one of the most popular datasets for use in mobile robotics and autonomous driving. It consists of hours of traffic scenarios recorded with a variety of sensor modalities, including high-resolution RGB, grayscale stereo cameras, and a 3D laser scanner.\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.\nBSDS500: Berkeley Segmentation Data Set 500 (BSDS500) is a standard benchmark for contour detection. This dataset is designed for evaluating natural edge detection that includes not only object contours but also object interior boundaries and background boundaries.\nUAVA: The UAVA,<i>UAV-Assistant</i>, dataset is specifically designed for fostering applications which consider UAVs and humans as cooperative agents. We employ a real-world 3D scanned dataset (<a href=\"https://niessner.github.io/Matterport/\">Matterport3D</a>), physically-based rendering, a gamified simulator for realistic drone navigation trajectory collection, to generate realistic multimodal data both from the user’s exocentric view of the drone, as well as the drone’s egocentric view.\nCARLA: CARLA (CAR Learning to Act) is an open simulator for urban driving, developed as an open-source layer over Unreal Engine 4. Technically, it operates similarly to, as an open source layer over Unreal Engine 4 that provides sensors in the form of RGB cameras (with customizable positions), ground truth depth maps, ground truth semantic segmentation maps with 12 semantic classes designed for driving (road, lane marking, traffic sign, sidewalk and so on), bounding boxes for dynamic objects in the environment, and measurements of the agent itself (vehicle location and orientation).\n\nOptions: A: KITTI B: SNIPS C: BSDS500 D: UAVA E: CARLA",
"role": "user"
},
{
"content": "[\"KITTI\", \"CARLA\"]",
"role": "assistant"
}
] |
science.qasper_extractive_qa
|
science.qasper_extractive_qa.463.0
|
[
{
"content": "Read the following paper excerpts and answer the question. Output a JSON object with \"answer\" and \"evidence\" fields. The answer must be extracted directly from the paper text.\n\nIf the question cannot be answered from the given text, respond with \"null\".\n\nPaper: Simultaneous Neural Machine Translation using Connectionist Temporal Classification\n\nSimultaneous machine translation is a variant of machine translation that starts the translation process before the end of an input. This task faces a trade-off between translation accuracy and latency. We have to determine when we start the translation for observed inputs so far, to achieve good practical performance. In this work, we propose a neural machine translation method to determine this timing in an adaptive manner. The proposed method introduces a special token ' ', which is generated when the translation model chooses to read the next input token instead of generating an output token. It also introduces an objective function to handle the ambiguity in wait timings that can be optimized using an algorithm called Connectionist Temporal Classification (CTC). The use of CTC enables the optimization to consider all possible output sequences including ' ' that are equivalent to the reference translations and to choose the best one adaptively. We apply the proposed method into simultaneous translation from English to Japanese and investigate its performance and remaining problems.\n\nSimultaneous machine translation by Wait-k model\nFirst, we review a general NMT model following the formulation by BIBREF1 and the “Wait-k\" model BIBREF2 that is the baseline model for simultaneous NMT.\nGiven a source sentence $X$ and a target sentence $Y$ as follows:\nwhere $\\textbf {x}_i \\in \\mathbb {R}^{S \\times 1}$ is a one-hot vector of the i-th input word, $I$ is the length of the input sentence $X$, $\\textbf {y}_i \\in \\mathbb {R}^{T \\times 1}$ is a one-hot vector of the i-th output word, and $J$ is the length of the output sentence $Y$.\nThe problem of translation from the source to the target language can be solved by finding the best target language sentence $\\hat{Y}$ that maximizes the conditional probability\nIn general NMT manner, the conditional probability is decomposed by the product of conditional generation probabilities of $\\textbf {y}_{j}$ given the source sentence $X$ and preceding target words $\\textbf {y}_{<j}$:\nwhere $\\textbf {y}_{<j}$ represents the target words up to position $j$, and $\\theta $ indicates the model parameters. In contrast, the model for simultaneous translation has to output translated words given only prefix words of the source sentence. Therefore, the conditional probability is decomposed as follows:\nwhere $\\textbf {x}_{<g(j)}$ are the target words up to position $g(j)$ and $g(j)$ represents the number of encoded source tokens when the model outputs $j$ words. In the “Wait-k\" model, $g(j)$ is defined as follows:\nHere, $k$ is the hyperparameter which indicates the target sentence generation is $k$ tokens behind the source sentence input and it takes a constant value in the “Wait-k\" model.\nThe model is composed of an encoder (§SECREF5) and a decoder with the attention mechanism (§SECREF7) that are both implemented using recurrent neural networks (RNNs); the encoder converts source words into a sequence of vectors, and the decoder generates target language words one-by-one with the attention mechanism based on the conditional probability shown in the equation DISPLAY_FORM2 and DISPLAY_FORM3. The details are described below.\n\nSimultaneous machine translation by Wait-k model ::: Encoder\nThe encoder takes a sequence of a source sentence $X$ as inputs and returns forward hidden vectors $\\overrightarrow{\\textbf {h}_i}(1 \\le i \\le I)$ of the forward RNNs:\nIn the general NMT model, they also calculate backward hidden vectors of backward RNNs from a reversed source sentence. However, we only use forward hidden vectors because we cannot use the information of the whole sentence on the simultaneous translation task.\n\nSimultaneous machine translation by Wait-k model ::: Decoder with Attention\nThe decoder takes source hidden vectors as inputs and returns target language words one-by-one with the attention mechanism. The decoder RNNs recurrently generates target words using its hidden state and an output context. The conditional generation probability of the target word $\\textbf {y}_i$ defined as follows:\nHere, $\\textbf {W}_c, \\textbf {W}_p$ are trainable parameters and $\\textbf {c}_j$ is a context vector to retrieve source language inputs in forms of a weighted sum of the source hidden vectors $\\textbf {h}_j$, defined as follows.\nThe score function above can be defined in some different ways as discussed by BIBREF1. In this paper, we use dot attention for this score function.\n\nProposed Method\nIn this work, we proposed the method to decide the output timing adaptively. The proposed method introduces a special token <wait> which is output instead of delaying translation to target-side vocabulary.\nIn this section, we first review a standard objective function, softmax cross-entropy and show the problem that occurs when this function is applied to <wait> (§SECREF10). After that, we introduce an objective function, called Connectionist Temporal Classification, to handle this problem (§SECREF12). Finally, we propose a new objective function to adjust a trade-off between translation accuracy and latency (§SECREF14) and explain how to combine these objective functions (§SECREF16).\n\nProposed Method ::: Softmax Cross-Entropy\nSoftmax Cross-Entropy (SCE) is a commonly used token-level objective function for multi-class classification including word generation in NMT, defined as follows:\nwhere $\\textbf {y}_{ij}$ is a j-th element of the one-hot vector corresponding to the i-th words of the reference sentence and $p(\\textbf {y}_{jk}|\\cdot )$ is the generation probability of $\\textbf {y}_{jk}$.\nA correct sequence that corresponds to an output sequence one-by-one is necessary to use SCE as an objective function for NMT. However, in the proposed method, we cannot simply use SCE because we don't know when we should cause delay. To avoid this problem, we set the loss for delay tokens to 0 during the time step $t\\ (t \\le g(I))$ which the model can output <wait> , or while a source sentence is inputted.\n\nProposed Method ::: Connectionist Temporal Classification\nAs we mentioned in the previous section, we set the loss value for <wait> to 0, but this causes the problem that it does not optimize about generating <wait> . Against this problem, we use an objective function called Connectionist Temporal Classification (CTC) BIBREF0 for sequence-level optimization.\nCTC extends output sequence, called Path $\\mathbf {\\pi } = \\Omega (\\textbf {y})$, to the length $T$ by allowing token repetitions and outputting <wait> . Conversely, we can obtain an original output sequence $\\textbf {y} = \\Omega ^{-1}(\\mathbf {\\pi })$ by removing <wait> and all token repetitions. The objective function is defined the sum of the probabilities of all possible paths $\\mathbf {\\pi } \\in \\Omega (\\textbf {y})$ by using the forward-backward algorithm, as follows:\nwhere $\\pi _t$ is a t-th element of $\\mathbf {\\pi }$.\n\nProposed Method ::: Delay Penalty\nFurthermore, we introduce a new objective function, called Delay Penalty, to control latency. We use this function only when an output token causes the delay; that is, when the model outputs <wait> or the same token as a previous one. Delay Penalty is defined by a negative log-likelihood of the probabilities for non-delayed tokens, as follows:\n\nProposed Method ::: Objective Function\nFor optimization, we combine three objective functions introduced so far, as follows:\nHere, $\\alpha $ is a hyperparameter to adjust the amount of latency directly.\n\nExperiments\nWe conducted simultaneous translation experiments from English to Japanese and discussed accuracy, latency, and issues for translation results.\n\nExperiments ::: Settings\nAll models were implemented as described in the previous sections using PyTorch. Both the encoders and the decoders were two-layered uni-direcitional LSTM BIBREF3, and the decoder used input feedingBIBREF1. The number of dimensions in word embeddings and hidden vectors was set to 512, and the minibatch size was 64. We use Adam BIBREF4 for optimization with the default parameters. The learning rate was set to $10^{-1}$, and gradient clipping was set to 5. The dropout probability was set to $0.3$. The learning rate was adjusted by a decay factor of $1/\\sqrt{2}$ when the validation loss was larger than that in the previous epoch. Then, we chose the best parameter/model with the smallest validation loss for evaluation.\nWe used two different corpora for the experiments: small_parallel_enja and Asian Scientific Paper Excerpt Corpus (ASPEC) BIBREF5. small_parallel_enja is a small-scale corpus that is consist of sentences filtered sentence length 4 to 16 words, and ASPEC is a mid-scale corpus of the scientific paper domain. Table TABREF21 shows their detailed statistics.\nAll datasets were tokenized into subword unit BIBREF6, BIBREF7 by using Sentencepiece . The source and target language vocabularies were independent, and their size was set to 4000 tokens for small_parallel_enja and 8000 tokens for ASPEC, respectively. We filtered out the sentence whose number of tokens was more than 60 tokens, or the length ratio was more than 9 from the training set.\nWe used “Wait-k” models and general NMT models as baseline models. General NMT models were attention-based encoder-decoder and it translated sentences from full-length source sentences (called Full Sentence). For evaluation metrics, we used BLEU BIBREF8 and RIBES BIBREF9 to measure translation accuracy, and token-level delay to measure latency. We used Kytea BIBREF10 as a tokenize method for evaluations of Japanese translation accuracy.\n\nExperiments ::: Experiments with Small-scale Corpus\nWe conducted small-scale experiments using small_parallel_enja. We compared different hyperparameters: $k = \\lbrace 3, 5\\rbrace $ and $\\alpha = \\lbrace 0, 0.01, 0.03, 0.05\\rbrace $.\nTable TABREF24 shows the results in latency and automatic evaluation scores on small_parallel_enja. The full sentence scores are upper bounds of incremental methods. The proposed method reduced the average latency in more than 50% from the full sentence baseline with some loss in BLEU and RIBES. The BLEU and RIBES results by the proposed method were worse than those by Wait-k. Th would be due to some degradation in smaller latency parts that were determined adaptively by the proposed methods while Wait-k keeps the fixed latency.\n\nExperiments ::: Experiments with Mid-scale Corpus\nWe investigated the performance on longer and more complex sentences by the experiments using ASPEC. We compared different hyperparameters: $k = \\lbrace 5, 7\\rbrace $ and $\\alpha = \\lbrace 0.03, 0.05, 0.1\\rbrace $.\nTable TABREF26 shows the results in latency and automatic evaluation scores on ASPEC. We can see the proposed method showed much larger latency than Wait-k. This is probably due to many long and complex phrases used in scientific articles in ASPEC. Wait-k has to translate such a long phrase without sufficient input observations due to its strict fixed latency strategy. On the other hand, the proposed method can wait for more input tokens adaptively by generating <wait> at the cost of large latency.\n\nExperiments ::: Discussion\nIn the experimental results above, the proposed method determined the translation latency adaptively, short delay for short and simple inputs as in small_parallel_enja and long delay for long and complex inputs as in ASPEC. Here we discuss our results in detail using some examples.\nTable TABREF28 shows translation examples on small_parallel_enja. In the first example, the proposed method gives a correct translation result by adaptive waits. Wait-k generated unrelated words UTF8min野球 (baseball) and UTF8min飲-み (drink) due to the poor input observations with its small fixed latency. The proposed method waited until a subword swim was observed and successfully generate a word UTF8min泳-ぐ (swim).\nHowever, the proposed method sometimes generated consecutive <wait> symbols until the end of input, as shown in the second example. This is probably due to our training strategy; the latency penalty would not be large enough to choose small latency translation at the cost of some increase in SCE- and CTC-based loss. The translation data in the experiments are not from simultaneous interpretation but standard translation, so the current task does not match with the proposed approach. The use of specialized data for simultaneous translation would be important in practice, such as monotonic translations like simultaneous translation.\n\nConclusion\nIn this paper, we proposed an adaptive latency control method for simultaneous neural machine translation in syntactically distant language pairs. We introduced a meta token <wait> to wait until the observation of the next input token. We proposed a CTC-based loss function to perform optimization using bilingual data without appropriate positions of <wait> , which is used along with the latency penalty and a standard word prediction loss. The experimental results suggest the proposed method determines when to translate or when to wait in an adaptive manner. Future work includes further analyses on translation accuracy in different latency conditions and time-based latency evaluation instead of the token-based one.\n\nAcknowledgments\nA part of this work is supported by JSPS Kakenhi JP17H06101.\n\nTable 1: Number of sentences for each corpus used in the experiments.\n\nTable 2: Latency and automatic evaluation scores with small parallel enja. Latencies are shown by averages and standard deviations (in parentheses) in the number of tokens.\n\nTable 3: Latency and automatic evaluation scores with ASPEC.\n\nTable 4: Translation examples in small parallel enja. w shows the generation of <wait> token.\n\nQuestion: Which dataset do they use?",
"role": "user"
},
{
"content": "{\"answer\": [\"small_parallel_enja\", \"Asian Scientific Paper Excerpt Corpus (ASPEC) BIBREF5\"], \"evidence\": [\"We used two different corpora for the experiments: small_parallel_enja and Asian Scientific Paper Excerpt Corpus (ASPEC) BIBREF5. small_parallel_enja is a small-scale corpus that is consist of sentences filtered sentence length 4 to 16 words, and ASPEC is a mid-scale corpus of the scientific paper domain. Table TABREF21 shows their detailed statistics.\"]}",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.4286
|
[
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nAntifungal prophylaxis during remission induction therapy for acute leukemia fluconazole versus intravenous amphotericin B . BACKGROUND Fungal infection is a frequent and often fatal complication in patients undergoing remission induction therapy for acute leukemia . Although candidiasis is the most common infection , mold infections are increasing in frequency . Fluconazole ( FLU ) is a new antifungal agent that has been used successfully to treat Candida infections and has modest activity against aspergillosis in animal models . Subtherapeutic doses of amphotericin B ( AMB ) have been considered effective as prophylaxis in these patients . This study was designed to compare the efficacy and toxicity of these agents as antifungal prophylaxis . METHODS Adults with acute leukemia undergoing remission induction chemotherapy randomly were assigned to receive antifungal prophylaxis with AMB ( 0.5 mg/kg three times weekly ) or FLU ( 400 mg daily ) . Trimethoprim-sulfamethoxazole was administered as an antibacterial prophylaxis . Prophylaxis was continued until the patient achieved complete remission or was treated for 8 weeks without antileukemic response . Prophylaxis was discontinued if the patient experienced a possible or proven fungal infection or a serious toxicity . RESULTS Overall , 58 % of the 36 patients assigned to AMB successfully completed prophylaxis compared with 80 % of the 41 patients assigned to FLU ( < 0.05 ) . Proven , probable , or possible fungal infections occurred in 31 % and 17 % of the patients , respectively . The risk of discontinuing prophylaxis due to fungal infection or toxicity increased with time in the study and was significantly greater for AMB ( P = 0.02 ) . CONCLUSIONS At the dose used in this study , AMB was no more effective and was more toxic than FLU for prophylaxis of fungal infections in patients undergoing remission induction chemotherapy for acute leukemia .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"amphotericin B ( AMB )\", \"AMB\", \"Trimethoprim-sulfamethoxazole\", \"antifungal prophylaxis with AMB ( 0.5 mg/kg three times weekly\", \"FLU\", \"versus intravenous amphotericin B\", \"Fluconazole ( FLU )\"], \"Outcome\": [\"toxicity\", \"fungal infections\", \"fungal infection\", \"Proven , probable , or possible fungal infections\", \"efficacy and toxicity\"], \"Participant\": [\"41 patients\", \"36 patients\", \"acute leukemia\"]}",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.4689
|
[
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nAtrioventricular conduction during long-term follow-up of patients with sick sinus syndrome . BACKGROUND It has been claimed that patients with sick sinus syndrome have an increased risk of developing AV block , but this has never been assessed prospectively . The aim of the present study was to evaluate in a prospective trial AV conduction during the long-term follow-up of patients with sick sinus syndrome . METHODS Two hundred twenty-five consecutive patients with sick sinus syndrome and intact AV conduction were randomized to undergo single-chamber atrial pacing ( 110 patients ) or single-chamber ventricular pacing ( 115 patients ) . Follow-up after 3 months and then yearly included measurement of the PQ interval and , in patients with atrial pacemakers , determination of the atrial stimulus-Q intervals at pacing rates of 100 and 120 bpm . The occurrence of AV block in the atrial group was recorded . During follow-up ( mean , 5.5+/-2.4 years ) , there was no change in PQ interval in either group and no change in atrial stimulus-Q intervals or Wenckebach block point in the atrial group . Four of 110 patients in the atrial group developed grade 2 to 3 AV block that required upgrading of the pacemaker ( 0.6 % per year ) . Two of these 4 patients had right bundle-branch block at pacemaker implantation . CONCLUSIONS AV conduction , estimated as PQ interval and atrial stimulus-Q interval at atrial pacing rates of 100 and 120 bpm and the Wenckebach block point , remains stable during long-term follow-up . Thus , treatment with single-chamber atrial pacing is safe and can be recommended to patients with sick sinus syndrome without bundle-branch block .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"single-chamber ventricular pacing\", \"single-chamber atrial pacing\"], \"Outcome\": [\"grade 2 to 3 AV block\", \"atrial stimulus-Q interval\", \"risk of developing AV block\", \"PQ interval\", \"Wenckebach block point\", \"occurrence of AV block\", \"safe\", \"right bundle-branch block\", \"atrial stimulus-Q intervals at pacing rates of 100 and 120 bpm\", \"atrial stimulus-Q intervals\"], \"Participant\": [\"sick sinus syndrome\", \"Two hundred twenty-five\"]}",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.899
|
[
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nImpact of antioxidants , zinc , and copper on cognition in the elderly : a randomized , controlled trial . Participants in the Age-Related Eye Disease Study were randomly assigned to receive daily antioxidants ( vitamin C , 500 mg ; vitamin E , 400 IU ; beta carotene , 15 mg ) , zinc and copper ( zinc , 80 mg ; cupric oxide , 2 mg ) , antioxidants plus zinc and copper , or placebo . A cognitive battery was administered to 2,166 elderly persons after a median of 6.9 years of treatment . Treatment groups did not differ on any of the six cognitive tests ( p > 0.05 for all ) . These results do not support a beneficial or harmful effect of antioxidants or zinc and copper on cognition in older adults .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"zinc\", \"antioxidants\", \"antioxidants or zinc\", \"vitamin E , 400 IU\", \"copper ( zinc , 80 mg\", \"copper\", \"placebo\", \"cupric oxide , 2 mg\", \"antioxidants plus zinc\", \"beta carotene , 15 mg\", \"vitamin C\"], \"Outcome\": [\"six cognitive tests\", \"beneficial or harmful effect of antioxidants or zinc and copper\", \"cognition\"], \"Participant\": []}",
"role": "assistant"
}
] |
science.qasper_extractive_qa
|
science.qasper_extractive_qa.706.1
|
[
{
"content": "Read the following paper excerpts and answer the question. Output a JSON object with \"answer\" and \"evidence\" fields. The answer must be extracted directly from the paper text.\n\nIf the question cannot be answered from the given text, respond with \"null\".\n\nPaper: A Multi-cascaded Deep Model for Bilingual SMS Classification\n\nMost studies on text classification are focused on the English language. However, short texts such as SMS are influenced by regional languages. This makes the automatic text classification task challenging due to the multilingual, informal, and noisy nature of language in the text. In this work, we propose a novel multi-cascaded deep learning model called McM for bilingual SMS classification. McM exploits n-gram level information as well as long-term dependencies of text for learning. Our approach aims to learn a model without any code-switching indication, lexical normalization, language translation, or language transliteration. The model relies entirely upon the text as no external knowledge base is utilized for learning. For this purpose, a 12 class bilingual text dataset is developed from SMS feedbacks of citizens on public services containing mixed Roman Urdu and English languages. Our model achieves high accuracy for classification on this dataset and outperforms the previous model for multilingual text classification, highlighting language independence of McM.\n\nIntroduction\nSocial media such as Facebook, Twitter, and Short Text Messaging Service (SMS) are popular channels for getting feedback from consumers on products and services. In Pakistan, with the emergence of e-government practices, SMS is being used for getting feedback from the citizens on different public services with the aim to reduce petty corruption and deficient delivery in services. Automatic classification of these SMS into predefined categories can greatly decrease the response time on complaints and consequently improve the public services rendered to the citizens. While Urdu is the national language of Pakistan, English is treated as the official language of the country. This leads to the development of a distinct dialect of communication known as Roman Urdu, which utilizes English alphabets to write Urdu. Hence, the SMS texts contain multilingual text written in the non-native script and informal diction. The utilization of two or more languages simultaneously is known as multilingualism BIBREF0. Consequently, alternation of two languages in a single conversation, a phenomenon known as code-switching, is inevitable for a multilingual speaker BIBREF1. Factors like informal verbiage, improper grammar, variation in spellings, code-switching, and short text length make the problem of automatic bilingual SMS classification highly challenging.\nIn Natural Language Processing (NLP), deep learning has revolutionized the modeling and understanding of human languages. The richness, expressiveness, ambiguities, and complexity of the natural language can be addressed by deep neural networks without the need to produce complex engineered features BIBREF2. Deep learning models have been successfully used in many NLP tasks involving multilingual text. A Convolutional Neural Network (CNN) based model for sentiment classification of a multilingual dataset was proposed in BIBREF3. However, a particular record in the dataset belonged to one language only. In our case, a record can have either one or two languages. There is very little published work on this specific setting. One way to classify bilingual text is to normalize the different variations of a word to a standard spelling before training the model BIBREF4. However, such normalization requires external resources such as lexical database, and Roman Urdu is under-resourced in this context. Another approach for an under-resourced language is to adapt the resources from resource-rich language BIBREF5. However, such an approach is not generalizable in the case of Roman Urdu text as it is an informal language with no proper grammatical rules and dictionary. More recent approach utilizes code-switching annotations to improve the predictive performance of the model, where each word is annotated with its respective language label. Such an approach is not scalable for large data as annotation task becomes tedious.\nIn this paper, we propose a multi-cascaded deep learning network, called as McM for multi-class classification of bilingual short text. Our goal is to achieve this without any prior knowledge of the language, code-switching indication, language translation, normalizing lexical variations, or language transliteration. In multilingual text classification, previous approaches employ a single deep learning architecture, such as CNN or Long Short Term Memory (LSTM) for feature learning and classification. McM, on the other hand, employs three cascades (aka feature learners) to learn rich textual representations from three perspectives. These representations are then forwarded to a small discriminator network for final prediction. We compare the performance of the proposed model with existing CNN-based model for multilingual text classification BIBREF3. We report a series of experiments using 3 kinds of embedding initialization approaches as well as the effect of attention mechanism BIBREF6.\nThe English language is well studied under the umbrella of NLP, hence many resources and datasets for the different problems are available. However, research on English-Roman Urdu bilingual text lags behind because of non-availability of gold standard datasets. Our second contribution is that we present a large scale annotated dataset in Roman Urdu and English language with code-switching, for multi-class classification. The dataset consists of more than $0.3$ million records and has been made available for future research.\nThe rest of the paper is organized as follows. Section SECREF2 defines the dataset acquiring process and provides an explanation of the class labels. In section SECREF3, the architecture of the proposed model, its hyperparameters, and the experimental setup is discussed. We discuss the results in section SECREF4 and finally, concluding remarks are presented in section SECREF5.\n.\n\nDataset Acquisition and Description\nThe dataset consists of SMS feedbacks of the citizens of Pakistan on different public services availed by them. The objective of collecting these responses is to measure the performance of government departments rendering different public services. Preprocessing of the data is kept minimal. All records having only single word in SMS were removed as cleaning step. To construct the “gold standard\", $313,813$ samples are manually annotated into 12 predefined categories by two annotators in supervision of a domain-expert. Involvement of the domain-expert was to ensure the practicality and quality of the “gold standard\". Finally, stratified sampling method was opted for splitting the data into train and test partitions with $80-20$ ratio (i.e., $80\\%$ records for training and $20\\%$ records for testing). This way, training split has $251,050$ records while testing split has $62,763$ records. The rationale behind stratified sampling was to maintain the ratio of every class in both splits. The preprocessed and annotated data along with train and test split is made available . Note that the department names and service availed by the citizens is mapped to an integer identifier for anonymity.\nClass label ratios, corresponding labels, and it's description are presented in Table TABREF1.\n\nProposed Model and Experimentation\nThe proposed model, named McM, is mainly inspired by the findings by Reimers, N., & Gurevych (2017) , who concluded that deeper model have minimal effect on the predictive performance of the model BIBREF7. McM manifests a wider model, which employ three feature learners (cascades) that are trained for classification independently (in parallel).\nThe input text is first mapped to embedding matrix of size $l \\times d$ where $l$ denotes the number of words in the text while $d$ is dimensions of the embedding vector for each of these words. More formally, let $\\mathcal {T} \\in \\lbrace w_1, w_2, ..., w_l\\rbrace $ be the input text with $l$ words, embedding matrix is defined by ${X} \\in \\mathbb {R}^{l \\times d}$. This representation is then fed to three feature learners, which are trained with local supervision. The learned features are then forwarded to discriminator network for final prediction as shown in Fig. FIGREF3. Each of these components are discussed in subsequent subsections.\n\nProposed Model and Experimentation ::: Stacked-LSTM Learner\nThe traditional methods in deep learning do not account for previous information while processing current input. LSTM, however, is able to memorize past information and correlate it with current information BIBREF10. LSTM structure has memory cells (aka LSTM cells) that store the information selectively. Each word is treated as one time step and is fed to LSTM in a sequential manner. While processing the input at current time step $X_t$, LSTM also takes into account the previous hidden state $h_{t-1}$. The LSTM represents each time step with an input, a memory, and an output gate, denoted as $i_t, f_t$ and $o_t$ respectively. The hidden state $h_t$ of input $X_t$ for each time step $t$ is given by:\nWhere, the $*$ is element-wise multiplication and $\\sigma $ is sigmoid activation function.\nStacked-LSTM learner is comprised of two LSTM layers. Let ${H_1}$ be a matrix consisting of output vectors $\\lbrace h_1, h_2, ..., h_l\\rbrace $ that the first LSTM layer produced, denoting output at each time steps. This matrix is fed to second LSTM layer. Similarly, second layer produces another output matrix $H_2$ which is used to apply global max-pooling and global-average pooling. These two outputs are concatenated and forwarded to a two layered feedforward network for intermediate supervision (prediction), identical to previously described stacked-CNN learner.\n\nProposed Model and Experimentation ::: LSTM Learner\nLSTM learner is employed to learn long-term dependencies of the text as described in BIBREF10. This learner encodes complete input text recursively. It takes one word vector at a time as input and outputs a single vector. The dimensions of the output vector are equal to the number of LSTM units deployed. This encoded text representation is then forwarded to a small feedforward network, identical to aforementioned two learners, for intermediate supervision in order to learn features. This learner differs from stacked-LSTM learner as it learns sentence features, and not average and max features of all time steps (input words).\n\nProposed Model and Experimentation ::: Discriminator Network\nThe objective of discriminator network is to aggregate features learned by each of above described three learners and squash them into a small network for final prediction. The discriminator employs two fully-connected layers with batch-normalization and dropout layer along with ReLU activation function for non-linearity. The softmax activation function with categorical cross-entropy loss is used on the final prediction layer to get probabilities of each class. The class label is assigned based on maximum probability. This is treated as final prediction of the proposed model. The complete architecture, along with dimensions of each output is shown in Fig. FIGREF3.\n\nResults and Discussion\nBefore evaluating the McM, we first tested the baseline model on our dataset. Table TABREF23 presents results of baseline and all variations of our experiments. We focus our discussion on F1-score as accuracy is often misleading for dataset with unbalanced class distribution. However, for completeness sake, all measures are reported.\nIt is observed from the results that baseline model performs worst among all the experiments. The reason behind this degradation in performance can be traced back to the nature of the texts in the datasets (i.e., datasets used in original paper of baseline model BIBREF3 and in our study). The approach in base model measure the performance of the model on multilingual dataset in which there is no code-switching involved. The complete text belongs to either one language or the other. However, in our case, the SMS text can have code-switching between two language, variation of spelling, or non-standard grammar. Baseline model is simple 1 layered CNN model that is unable to tackle such challenges. On the other hand, McM learns the features from multiple perspectives, hence feature representations are richer, which consequently leads to a superior predictive performance. As every learner in McM is also supervised, all 4 components of the proposed model (i.e., stacked-CNN learner, stacked-LSTM learner, LSTM-learner, and discriminator) can also be compared with each other.\nIn our experiments, the best performing variation of the proposed model is McM$_\\textsubscript {D}$. On this particular setting, discriminator is able to achieve an F1-score of $0.69$ with precision and recall values of $0.72$ and $0.68$ respectively. Other components of McM also show the highest stats for all performance measures. However, for McM$_\\textsubscript {DA}$, a significant reduction in performance is observed, although, attention-based models have been proven to show improvement in performance BIBREF6. Investigating the reason behind this drop in performance is beyond the scope of this study. The model variations trained on ELMo embedding have second highest performance. Discriminator of McM$_\\textsubscript {E}$ achieves an F1-score of $0.66$, beating other learners in this experiment. However, reduction in performance is persistent when attention is used for McM$_\\textsubscript {EA}$.\nRegarding the experiments with random embedding initialization, McM$_\\textsubscript {R}$ shows similar performance to McM$_\\textsubscript {EA}$, while McM$_\\textsubscript {RA}$ performs the worst. It is worth noting that in each experiment, discriminator network stays on top or performs equally as compared to other components in terms of F1-score. This is indication that discriminator network is able to learn richer representations of text as compared to methods where only single feature learner is deployed.\nFurthermore, the results for testing error for each component (i.e., 3 learners and a discriminator network) for all 4 variations of the proposed model are presented in Fig. FIGREF24. It is evident that the least error across all components is achieved by McM$_\\textsubscript {D}$ model. Turning now to individual component performance, in ELMo embeddings based two models, lowest error is achieved by discriminator network, closely followed by stacked LSTM learner and stacked-CNN learner, while LSTM learner has the highest error. As far as model variations with random embeddings initializations are concerned, most interesting results are observed. As shown in subplot (c) and (d) in Fig. FIGREF24, McM$_\\textsubscript {R}$ and McM$_\\textsubscript {RA}$ tend to overfit. After second epoch, the error rate for all components of these two variations tend to increase drastically. However, it shows minimum error for discriminator in both variations, again proving that the features learned through multiple cascades are more robust and hold greater discriminative power. Note that in all 6 variations of experiments, the error of discriminator network is the lowest as compared to other components of McM. Hence it can be deduced that learning features through multiple perspectives and aggregating them for final prediction is more fruitful as compared to single method of learning.\n\nFig. 1. Multi-cascaded model (McM) for bilingual short text classification (figure best seen in color)\n\nTable 2. Hyperparameter tuning, the selection range, and final choice\n\nQuestion: What is the size of the dataset?",
"role": "user"
},
{
"content": "{\"answer\": [\"$0.3$ million records\"], \"evidence\": [\"The English language is well studied under the umbrella of NLP, hence many resources and datasets for the different problems are available. However, research on English-Roman Urdu bilingual text lags behind because of non-availability of gold standard datasets. Our second contribution is that we present a large scale annotated dataset in Roman Urdu and English language with code-switching, for multi-class classification. The dataset consists of more than $0.3$ million records and has been made available for future research.\"]}",
"role": "assistant"
}
] |
science.chemsum_single_document_summarization
|
science.chemsum_single_document_summarization.70598
|
[
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nA Novel HDAC Inhibitor with a Hydroxy-Pyrimidine Scaffold\n\nPaper sections:\n\n<p>Post-translational modifications on histones are essential for regulating gene expression.1 A wide variety of chemical modifications, such as methylation, phosphorylation, and acetylation, can alter chromatin structure, influencing levels of gene expression.2 One important modification to histones is N-ε-lysine acetylation. The positive charge of the lysine residues on histone tails allows the negatively charged DNA to tightly coil around histones, contributing to inhibition of transcription. An increase in lysine side chain acetylation has the opposite effect, neutralizing the positive charge and relaxing the DNA from the histone proteins, causing an increase in the amount of transcriptional activity. This tight balance of hyperacetylation and hypoacetylation is maintained by two counteracting family of enzymes, histone acetyltransferases (HATs) and histone deacetylases (HDACs), respectively.</p><p>Since the initial discovery of the first mammalian HDAC,3 17 additional HDACs have been identified. They are divided into several classes based on sequence homology to their respective yeast orthologs.2 The classical zinc-dependent HDACs are divided into three subclasses, class I (HDAC1, 2, 3, and 8), class II (HDAC4, 5, 6, 7, 9, and 10), and class IV (HDAC11). Class III HDACs, also known as sirtuins, are zinc-independent and instead require a NAD+ cofactor for deacetylase activity.4 HDACs are present in a variety of organisms and participate in a myriad of biological functions, including post-translational modification of various non-histone substrates. The aberrant activity of HDACs has been connected to numerous diseases, such as inflammation5 and neurosis,6 as well as regulation of tumor suppressor genes and oncogenes, contributing to cancer pathogenesis.2, 7</p><p>Using small molecules to inhibit HDACs has provided promising clinical results in different models of cancer, such as cutaneous T-cell lymphoma and neuroblastoma.4, 7–8 Among HDAC inhibitors (HDACi) identified so far, four major classes of structures are frequently studied, including hydoxamates (1), benzamides (2), aliphatic acids (3), and cyclic peptides (4a–b) (Fig. 1).7, 9 Most HDACi follow the pharmacophore model of a capping region that interacts with the surface of the protein, a metal-binding region that chelates zinc to disrupt the enzymatic activity, and a linker domain consisting of a hydrophobic spacer that interacts with the hydrophobic-binding channel (Fig. 1).6b, 10</p><p>A key motivation for investigating compounds that inhibit HDACs is to find a compound that selectivity targets individual HDACs or a subclass of HDACs. A few compounds have been found to selectivity target HDACs; however progress has been limited.11 Screening diverse small molecules allows for discovery of structurally novel HDACi that may modulate the proteins through different mechanisms or with previously unobserved patterns of selectivity.12 Here we report a structurally novel HDACi, BRD-2577 (7) that was discovered in a binding assay involving a small-molecule microarray (SMM) (Fig. 2a). It is interesting to note that the structure of BRD-2577 is a hydroxy-pyrimidine scaffold, and does not conform to the four main structural classes of HDACi. We further explored the structure-activity-relationships (SAR) and cellular effects of this molecule. Recently, Donald and coworkers evaluated the pyrimidine hydroxamic acid moiety and found that their compounds were able to inhibit HDACs, demonstrating the potential importance of pyrimidines in inhibition of HDACs.13</p><p>BRD-2577 was originally identified as a binder to purified HDAC8 using SMMs.12 To determine whether the binder inhibits the deacetylase activity of the enzyme, we resynthesized this compound using a nucleophilic substitution reaction between α-chloroketone (5) and mercapto-methylpyrimidine (6) (Fig. 2a) and evaluated it for HDAC inhibitory effects using a trypsin-coupled in vitro biochemical assay (Fig. 2b).14 This biochemical assay employs an acetylated lysine tripeptide substrate amide linked to aminocoumarin (AMC). When HDACs deacetylate the lysine residue, trypsin is able to cleave the AMC from the substrate, thus increasing the fluorescent signal.14–15 Small-molecule HDAC inhibition prevents the deacetylation of the lysine, preventing the generation of fluorescent signal. The effects of various concentrations of BRD-2577 were evaluated, and the data was normalized against a DMSO control. IC50 values were measured by fitting the data to a non-linear regression model. The IC50 values for BRD-2577 against HDAC1-9 ranged from ~11 μM to 74 μM, suggesting it is a non-selective inhibitor of HDACs with modest potency. A counter screen demonstrated that this compound inhibits HDAC activity and does not interfere with the proteolytic activity of trypsin (Supplementary data). The mode of inhibition was also evaluated by analyzing various doses of compound with concentrations of substrate 10 times above and below the Km of HDAC2. The Lineweaver-Burk plot for BRD-2577 and HDAC2 is shown in Figure 2c. The y-intercept does not vary across concentrations of substrate, suggesting that BRD-2577 is a competitive inhibitor, and that the inhibitor is binding to the active site of enzyme.</p><p>The structural novelty of BRD-2577 as compared to other HDACi motivated further studies to gain insight into the molecular features that may be responsible for target inhibition. Towards this end, we investigated whether two major substructures of BRD-2577, 5 and 6, were independently capable of inhibition. Neither the α-chloroketone group (5) nor the pyrimidine ring (6) exhibited inhibition in the biochemical assay. This may indicate that activity is not derived from a single biasing element but rather by the whole skeleton.</p><p>Using simple reactions, we synthesized a set of analogs to investigate the effects of chemical modifications at different positions (Table 1). The initial SAR study focused on the pyrimidine group and its substituent groups. The hydroxyl group was necessary for activity (8–10). The replacement of pyrimidine by a phenyl group resulted in loss of activity (11). Interestingly, the activity was retained when the sulfur atom was substituted by oxygen (12), albeit at a reduced potency and with an altered selectivity pattern. Additionally, removing nitrogen at the 1-position from 12 (13) led to loss of activity, demonstrating that both nitrogen atoms are essential for binding.</p><p>Next, we investigated the consequences of chemical modification of the opposing end of the structure of BRD-2577 (Table 2). The removal or the reduction of the carbonyl group (14 and 15, respectively) resulted in a loss of potency, suggesting the carbonyl function is indispensable. Similarly, the modifications and the replacement of the acetamide group with various functionalities (16–22) resulted in decreased potencies for most of the HDACs, while the chloride analog (21) retained some inhibition of HDAC1, 2, 4 and 6. The dihydroxy analog (23) was found only to inhibit HDAC6. Protection of the dihydroxy group via a dioxin (24) led to a completely inactive compound. The acetamide was also replaced with a more rigid oxindole group (25). The role of the phenyl group was further explored. Replacing the phenyl group with a more hydrophobic thiophene (26) preserved inhibitory activity for HDAC6. Replacing the aromatic ring with an aliphatic chain (27–30) was not tolerant to its inhibition activity although 30 retained some activity for HDACs 1, 2, 3, 5, and 6. The linker region between the carbonyl group and phenyl group was also examined by synthesizing compounds 31–33. Although most of the modifications described here lead to inactive analogs, several of the compounds retained inhibition of HDAC6, which is possibly due its unique enzymatic structure consisting of two catalytic domains.8</p><p>We examined the effects of selected compounds on both histone and α-tubulin lysine acetylation in cells.16 Tubulin acetylation is regulated by HDAC617 and many of the analogs inhibited its activity. HeLa cells were plated in 384-well plates with 2000 cells/well and treated with compounds at various concentrations for 16 h. Acetylation levels were measured using antibodies that recognize acetylated α-tubulin or acetylated lysine residues in post-translationally modified proteins. The fluorescence levels were measured for each antibody and normalized to the DMSO control. Treatment with BRD-2577 leads to an increase in both total lysine and tubulin acetylation (Fig. 3), consistent with our biochemical assay data demonstrating that it inhibits class I and class II HDACs. Other compounds that inhibited HDAC6 in the enzymatic assay were also evaluated for their activity in cells but did not show a significant increase in acetylation level at a concentration of 20 μM (data not shown). Our positive control compound, SAHA, increases both global lysine and α-tubulin acetylation levels, consistent with the ability to inhibit both class I and class II HDACs. MS-275, a control compound, increased global lysine acetylation, but caused little change in tubulin acetylation, which is consistent with its selective inhibition of HDAC1-3 versus HDAC6 in our biochemical assay.</p><p>In summary, we have identified a novel, pan-selective HDAC inhibitor from an SMM-based binding screen and demonstrated inhibitory activity against HDACs using an in vitro biochemical assay and cellular acetylation assays. The scaffold does not resemble previously established pharmacophore models for HDAC inhibitors. This novel HDACi structure may be explored further using structure-guided approaches to elucidate binding mechanism and to enhance the potency and selectivity through various structural modifications, leading towards broad biological and therapeutic applications.</p>",
"role": "user"
},
{
"content": "Histone deacetylases (HDACs) are enzymes involved in many important biological functions. They have been linked to a variety of cancers, psychiatric disorders, and other diseases. Since small molecules can serve as probes to study the relevant biological roles of HDACs, novel scaffolds are necessary to develop more efficient, selective drug candidates. Screening libraries of molecules may yield structurally diverse probes that bind these enzymes and modulate their functions in cells. Here we report a small molecule with a novel hydroxy-pyrimidine scaffold that inhibits multiple HDAC enzymes and modulates acetylation levels in cells. Analogs were synthesized in an effort to evaluate structure-activity relationships.",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.7067
|
[
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nBACKGROUND: COVID-19, caused by SARS-CoV-2, is a potentially lethal, rapidly-expanding pandemic and many efforts are being carried out worldwide to understand and control the disease. COVID-19 patients may display a cytokine release syndrome, which causes severe lung inflammation, leading, in many instances, to death. OBJECTIVE: This paper is intended to explore the possibilities of controlling the COVID-19-associated hyperinflammation by using licensed drugs with anti-inflammatory effects. HYPOTHESIS: We have previously described that pentoxifylline alone, or in combination with oxypurinol, reduces the systemic inflammation caused by experimentally-induced pancreatitis in rats. Pentoxifylline is an inhibitor of TNF-alpha production and oxypurinol inhibits xanthine oxidase. TNF-alpha, in turn, activates other inflammatory genes such as Nos2, Icam or IL-6, which regulate migration and infiltration of neutrophils into the pulmonary interstitial tissue, causing injury to the lung parenchyma. In acute pancreatitis, the anti-inflammatory action of pentoxifylline seems to be mediated by the prevention of the rapid and presumably transient loss of PP2A activity. This may also occur in the hyperinflammatory -cytokine releasing phase- of SARS-CoV-2 infection. Therefore, it may be hypothesized that early treatment of COVID-19 patients with pentoxifylline, alone or in combination with oxypurinol, would prevent the potentially lethal acute respiratory distress syndrome. CONCLUSION: Pentoxifylline and oxypurinol are licensed drugs used for diseases other than COVID-19 and, therefore, phase I clinical trials would not be necessary for the administration to SARS-CoV-2- infected people. It would be worth investigating their potential effects against the hyperinflammatory response to SARS-CoV-2 infection.",
"role": "user"
},
{
"content": "[\"Treatment\", \"Mechanism\"]",
"role": "assistant"
}
] |
science.acl_arc_intent_classification
|
science.acl_arc_intent_classification.1572
|
[
{
"content": "Classify the intent of this citation from an NLP research paper. \n\nYour answer must be one word from: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. No other text allowed.\n\nSection Title:\nNone\n\nContext before:\nThe combination of likelihood and prior modeling, HMMs, and Viterbi decoding is fundamentally the same as the standard probabilistic approaches to speech recognition (Bahl, Jelinek, and Mercer 1983) and tagging (Church 1988). Dialogue Act Modeling sequence with the highest posterior probability: Stolcke et al.\n\nCitation:\nThe combination of likelihood and prior modeling , HMMs , and Viterbi decoding is fundamentally the same as the standard probabilistic approaches to speech recognition ( Bahl , Jelinek , and Mercer 1983 ) and tagging ( Church 1988 ) .\n\nContext after:\nIt maximizes the probability of getting the entire DA sequence correct, but it does not necessarily find the DA sequence that has the most DA labels correct (Dermatas and Kokkinakis 1995). To minimize the total number of utterance labeling errors, we need to maximize the probability of getting each DA label correct individually, i.e., we need to maximize P(U11E) for each i = 1,. . . ,n. We can compute the per-utterance posterior DA probabilities by summing: where the summation is over all sequences U whose ith element matches the label in question.",
"role": "user"
},
{
"content": "CompareOrContrast",
"role": "assistant"
}
] |
science.anat_em_ner
|
science.anat_em_ner.511
|
[
{
"content": "Given this abstract, identify all unique entities of these types: [\"AnatomicalEntity\"].\n\nOnly output the JSON object, no other text.\n\nAbstract:\nEffect of the deletion of IRE1alpha on the liver.\n(A) HE-stained sections of the liver tissue (scale bar: 50 mum). (B) Comparison of the serum AST and ALT levels between the IRE1alpha CKO mice and the control mice. Data are expressed as mean +/- S.E.M (n = 5). (C) Quantitative PCR analysis of lipid synthesis genes in the liver of mice fed normal or high-fructose feed. Columns indicate mean and error bars denote S.E.M (n = 3). All the data were obtained from 20 weeks old male mice.",
"role": "user"
},
{
"content": "{\"AnatomicalEntity\": [\"serum\", \"sections\", \"liver tissue\", \"liver\"]}",
"role": "assistant"
}
] |
science.chemprot_ner
|
science.chemprot_ner.250
|
[
{
"content": "Extract entities of these types from the text: [\"Chemical\", \"Protein\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values.\n\nText:\nA novel SCN5A arrhythmia mutation, M1766L, with expression defect rescued by mexiletine.\nOBJECTIVE: Mutations in the cardiac sodium channel gene, SCN5A, cause congenital long QT syndrome (LQT3), Brugada syndrome, idiopathic ventricular fibrillation, and conduction disease by distinct cellular and clinical electrophysiological phenotypes. METHODS: Postmortem molecular analysis of SCN5A was conducted on an infant who presented shortly after birth with self-terminating torsades de pointes. The infant was treated with lidocaine, propranolol, and mexiletine and was stable for 16 months manifesting only a prolonged QT interval. The infant collapsed suddenly following presumed viral gastroenteritis, was found in 2:1 AV block, and was subsequently declared brain dead. Genomic DNA was subjected to SCN5A mutational analyses and DNA sequencing revealing a novel, spontaneous germline missense mutation, M1766L. The M1766L mutation was engineered into the hH1a clone by site-directed mutagenesis, transfected into embryonic kidney cells (HEK-293), and studied by voltage clamp. RESULTS: The M1766L mutation caused a significant decrease in the sodium channel expression. Co-expression with beta1 subunit, incubation at low temperature, and most effectively incubation with mexiletine partially 'rescued' the defective expression. In addition to this pronounced loss of function, M1766L also showed a 10-fold increase in the persistent late sodium current. CONCLUSIONS: These findings suggest that M1766L-SCN5A channel dysfunction may contribute to the basis of lethal arrhythmias, displays an overlapping electrophysiological phenotype, and represents the first sodium channelopathy rescued by drug.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"sodium\", \"mexiletine\", \"propranolol\", \"lidocaine\"], \"Protein\": [\"SCN5A\", \"M1766L\"]}",
"role": "assistant"
}
] |
science.genia_ner
|
science.genia_ner.1294
|
[
{
"content": "Extract all unique entities of these types from the biomedical abstract: [\"CellLine\", \"DNA\", \"Protein\", \"CellType\", \"RNA\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities found for a type, use [].\n\nAbstract:\n\nCD2 signalling induces phosphorylation of CREB in primary lymphocytes. Promoter sequences responsive to cyclic AMP (cAMP) are found in a number of cellular genes, and bind transcription factors of the cAMP response element binding protein (CREB) / activating transcription factor-1 (ATF-1) family. We have used a human T-lymphotropic virus type 1 (HTLV-1) model of cAMP response element (CRE) transcription to investigate the influence of lymphocyte activation on transcription from homologous regions in the viral promoter. We previously demonstrated increased HTLV-1 transcription following CD2 but not CD3 receptor cross-linking. We hypothesized that this increased viral transcription was mediated, in part, through the phosphorylation of CREB. Therefore, we investigated CD2 and CD3 receptor-mediated signalling in primary human peripheral blood mononuclear cells (PBMC). CD2, but not CD3, cross-linking increased cAMP detected by competitive enzyme-linked immunosorbent assay (ELISA) approximately fourfold. CD2 cross-linking concurrently increased phosphorylation of CREB detected by immunoblot assay eightfold. Consistent with post-translational regulation, no change in total level of CREB protein was observed. Phosphorylation of CREB occurred through a herbimycin A and Rp-cAMP-sensitive pathway, suggesting phosphorylation required antecedent activation of both protein tyrosine kinases (PTK) and protein kinase A (PKA). Both CD2 and CD3 cross-linking increased binding of nuclear proteins to a radiolabelled CRE oligonucleotide probe in electrophoretic mobility shift assays suggesting that lymphocyte activation enhances binding independently of phosphorylation of CREB at serine 133. These data indicate specific modulation of the CREB / ATF-1 family of transcription factors by the CD2 signalling pathway and suggest CD2 receptor modulation of CRE-mediated transcription following ligand engagement (e. g. cell-to-cell contact).",
"role": "user"
},
{
"content": "{\"CellLine\": [], \"CellType\": [\"primary human peripheral blood mononuclear cells\", \"primary lymphocytes\", \"PBMC\"], \"DNA\": [\"CRE\", \"cAMP response element\", \"cellular genes\", \"viral promoter\"], \"Protein\": [\"CD3 receptor\", \"nuclear proteins\", \"PTK\", \"CD2\", \"CREB) / activating transcription factor - 1 (ATF - 1) family\", \"PKA\", \"protein tyrosine kinases\", \"protein kinase A\", \"CREB / ATF - 1 family\", \"transcription factors\", \"CREB\", \"cAMP response element binding protein\", \"CD3\"], \"RNA\": []}",
"role": "assistant"
}
] |
science.acl_arc_intent_classification
|
science.acl_arc_intent_classification.678
|
[
{
"content": "Classify the intent of this citation from an NLP research paper. \n\nYour answer must be one word from: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. No other text allowed.\n\nSection Title:\nNone\n\nContext before:\nA number of speech understanding systems have been developed during the past fifteen years (Barnett et al. 1980, Dixon and Martin 1979, Erman et al. 1980, Haton and Pierrel 1976, Lea 1980, Lowerre and Reddy 1980, Medress 1980, Reddy 1976, Walker 1978, and Wolf and Woods 1980).\n\nCitation:\nA number of speech understanding systems have been developed during the past fifteen years ( Barnett et al. 1980 , Dixon and Martin 1979 , Erman et al. 1980 , Haton and Pierrel 1976 , Lea 1980 , Lowerre and Reddy 1980 , Medress 1980 , Reddy 1976 , Walker 1978 , and Wolf and Woods 1980 ) .\n\nContext after:\nMost of these efforts concentrated on the interaction between low level information sources from a speech recognizer and a natural language processor to discover the meaning of an input sentence. While some of these systems did exhibit expectation capabilities at the sentence level, none acquired dialogues of the kind described here for the sake of dialogue level expectation and error correction. A detailed description of the kinds of expectation mechanisms appearing in these systems appears in Fink (1983). The problem of handling ill-formed input has been studied by Carbonell and Hayes (1983), Granger (1983), Jensen et al. (1983), Kwasny and Sondheimer (1981), Riesbeck and Schank (1976), Thompson (1980), Weischedel and Black (1980), and Weischedel and Sondheimer (1983).",
"role": "user"
},
{
"content": "CompareOrContrast",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.2695
|
[
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nAdult height in short children born SGA treated with growth hormone and gonadotropin releasing hormone analog : results of a randomized , dose-response GH trial . CONTEXT GH treatment is effective in improving height in short children born small for gestational age ( SGA ) . GH is thought to have limited effect when started during adolescence . OBJECTIVE The aim of this study was to investigate GH treatment efficacy in short SGA children when treatment was started during adolescence ; to assess whether GH 2 mg/m ( 2 ) · d during puberty improves adult height ( AH ) compared with 1 mg/m ( 2 ) · d ; and to assess whether an additional 2-yr postponement of puberty by GnRH analog ( GnRHa ) improves AH in children who are short at the start of puberty ( < 140 cm ) , with a poor AH expectation . PATIENTS AND DESIGN In this longitudinal , randomized , dose-response GH trial , we included 121 short SGA children ( 60 boys ) at least 8 yr of age . We performed intention-to-treat analyses on all children and uncensored case analyses on 84 children who reached AH . Besides , we evaluated growth during 2 yr of combined GH/GnRHa and subsequent GH treatment until AH in a subgroup of 40 pubertal children with a height of less than 140 cm at the start . RESULTS Short SGA children started treatment at a median age of 11.2 yr , when 46 % had already started puberty . Median height increased from -2.9 at start to -1.7 sd score ( SDS ) at AH ( P < 0.001 ) . Treatment with GH 2 vs. 1 mg/m ( 2 ) · d during puberty resulted in significantly better AH ( P = 0.001 ) , also after correction for gender , age at start , height SDS at start , treatment years before puberty , and target height SDS . AH was similar in children who started puberty at less than 140 cm and received GH/GnRHa , compared with children who started puberty greater than 140 cm and received GH only ( P = 0.795 ) . CONCLUSION When started in adolescence , GH treatment significantly improves AH in short SGA children , particularly with GH 2 mg/m ( 2 ) · d during puberty . When SGA children are short at the start of puberty , they can benefit from combined GH/GnRHa treatment .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"growth hormone\", \"gonadotropin releasing hormone analog\", \"GH\"], \"Outcome\": [\"efficacy\"], \"Participant\": [\"short children born small for gestational age ( SGA )\", \"SGA\", \"children\", \"Adult\"]}",
"role": "assistant"
}
] |
science.healthver_entailment
|
science.healthver_entailment.5062
|
[
{
"content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: there is SARS-CoV-2 RNA in various clinical specimens, suggesting other transmission routes for this virus besides respiratory secretions \n\nAbstract:\nWe remain largely without effective prophylactic/therapeutic interventions for COVID-19.\nAlthough many human clinical trials are ongoing, there remains a deficiency of supportive preclinical drug efficacy studies.\nHere we assessed the prophylactic/therapeutic efficacy of hydroxychloroquine (HCQ), a drug of interest for COVID-19 management, in two animal models.\nWhen used for prophylaxis or treatment neither the standard human malaria dose (6.5 mg/kg) nor a high dose (50 mg/kg) of HCQ had any beneficial effect on clinical disease or SARS-CoV-2 kinetics (replication/shedding) in the Syrian hamster disease model.\nSimilarly, HCQ prophylaxis/treatment (6.5 mg/kg) did not significantly benefit clinical outcome nor reduce SARS-CoV-2 replication/shedding in the upper and lower respiratory tract in the rhesus macaque disease model.\nIn conclusion, our preclinical animal studies do not support the use of HCQ in prophylaxis/treatment of COVID-19.",
"role": "user"
},
{
"content": "{\"verdict\": \"NEI\", \"evidence\": []}",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.435
|
[
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nThe effects of physical and emotional status on adherence to a low-fat dietary pattern in the Women 's Health Initiative . OBJECTIVE To examine whether the effects of physical and emotional status on adherance to a low-fat ( 20 % energy ) dietary pattern are mediated by participation in an intervention program ( attending sessions and self-monitoring ) . DESIGN The Baron and Kenny mediator model , a series of 4 regression analyses , was used to evaluate whether : a ) physical and emotional status predicted program participation , b ) program participation predicted dietary adherence , c ) physical and emotional status factors predicted dietary adherence , and , ultimately d ) the effects of physical and emotional status on dietary adherence were mediated by program participation . SUBJECTS/SETTING Data from 13,277 postmenopausal women randomly assigned to the low-fat intervention arm of the Women 's Health Initiative Dietary Modification Trial . INTERVENTION The nutrition goals for women randomly assigned to the low-fat intervention were to reduce total fat intake to 20 % or less of energy from fat and to consume 5 or more fruit/vegetable servings daily and 6 or more grain servings daily . MAIN OUTCOME MEASURES Year 1 program participation ( degree of attending group sessions and submitting fat scores ) and adherence to the low-fat dietary pattern ( percent energy from fat ) as predicted by baseline physical and emotional status ( eight SF-36 Health Survey subscales ) . RESULTS Participating in the dietary intervention program reduced ( mediated ) the negative effect of poorer mental health on dietary adherence by 15 % . Additional findings included that a 10 % increase in physical functioning increased session attendance by 0.4 % ( P < .001 ) and a 10 % increase in mental health predicted a decrease in percent energy from fat of 0.3 % ( P < .001 ) . Program participation had a marked effect on dietary adherence : a 10 % increase in session attendance predicted a 1.2 % decrease in percent energy from fat ( P < .001 ) . APPLICATIONS/CONCLUSIONS Understanding and using instruments to assess the physical and emotional status of a target population will help dietetic professionals promote healthful dietary change and maintenance .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"dietary adherence\", \"physical and emotional status\", \"reduce total fat intake to 20 % or less of energy from fat and to consume 5 or more fruit/vegetable servings daily and 6 or more grain servings daily\", \"low-fat intervention\", \"low-fat dietary pattern\", \"intervention program ( attending sessions and self-monitoring )\", \"low-fat ( 20 % energy ) dietary pattern\", \"dietary intervention program\"], \"Outcome\": [\"effect of poorer mental health\", \"dietary adherence\", \"physical functioning\", \"mental health\", \"energy from fat\", \"session attendance\", \"Year 1 program participation ( degree of attending group sessions and submitting fat scores\", \"adherence to the low-fat dietary pattern ( percent energy from fat )\"], \"Participant\": [\"postmenopausal\", \"13,277\", \"women\", \"low-fat ( 20 % energy ) dietary pattern\", \"Women\"]}",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.12466
|
[
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: The main contributions of the paper are: (i) we present an unsupervised image generation framework that uses\n\nKeyphrases: image generation\n\nDataset descriptions:\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).\nWikiCREM: An unsupervised dataset for co-reference resolution. Presented in the publication: Kocijan et.\nImage and Video Advertisements: The Image and Video Advertisements collection consists of an image dataset of 64,832 image ads, and a video dataset of 3,477 ads. The data contains rich annotations encompassing the topic and sentiment of the ads, questions and answers describing what actions the viewer is prompted to take and the reasoning that the ad presents to persuade the viewer (\"What should I do according to this ad, and why should I do it?\nLLAMAS: The unsupervised Labeled Lane MArkerS dataset (LLAMAS) is a dataset for lane detection and segmentation. It contains over 100,000 annotated images, with annotations of over 100 meters at a resolution of 1276 x 717 pixels.\n\nOptions: A: CIFAR-10 B: WikiCREM C: Image and Video Advertisements D: LLAMAS",
"role": "user"
},
{
"content": "CIFAR-10",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.50722
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: AutoML: A Survey of the State-of-the-Art \nChapter Title: A. Low fidelity \n1. Abstract of Cited Paper (BIB001): Developing neural network image classification models often requires significant architecture engineering. In this paper, we study a method to learn the model architectures directly on the dataset of interest. As this approach is expensive when the dataset is large, we propose to search for an architectural building block on a small dataset and then transfer the block to a larger dataset. The key contribution of this work is the design of a new search space (the \"NASNet search space\") which enables transferability. In our experiments, we search for the best convolutional layer (or \"cell\") on the CIFAR-10 dataset and then apply this cell to the ImageNet dataset by stacking together more copies of this cell, each with their own parameters to design a convolutional architecture, named \"NASNet architecture\". We also introduce a new regularization technique called ScheduledDropPath that significantly improves generalization in the NASNet models. On CIFAR-10 itself, NASNet achieves 2.4% error rate, which is state-of-the-art. On ImageNet, NASNet achieves, among the published works, state-of-the-art accuracy of 82.7% top-1 and 96.2% top-5 on ImageNet. Our model is 1.2% better in top-1 accuracy than the best human-invented architectures while having 9 billion fewer FLOPS - a reduction of 28% in computational demand from the previous state-of-the-art model. When evaluated at different levels of computational cost, accuracies of NASNets exceed those of the state-of-the-art human-designed models. For instance, a small version of NASNet also achieves 74% top-1 accuracy, which is 3.1% better than equivalently-sized, state-of-the-art models for mobile platforms. Finally, the learned features by NASNet used with the Faster-RCNN framework surpass state-of-the-art by 4.0% achieving 43.1% mAP on the COCO dataset. \n2. Abstract of Cited Paper (BIB002): The effort devoted to hand-crafting neural network image classifiers has motivated the use of architecture search to discover them automatically. Although evolutionary algorithms have been repeatedly applied to neural network topologies, the image classifiers thus discovered have remained inferior to human-crafted ones. Here, we evolve an image classifier— AmoebaNet-A—that surpasses hand-designs for the first time. To do this, we modify the tournament selection evolutionary algorithm by introducing an age property to favor the younger genotypes. Matching size, AmoebaNet-A has comparable accuracy to current state-of-the-art ImageNet models discovered with more complex architecture-search methods. Scaled to larger size, AmoebaNet-A sets a new state-of-theart 83.9% top-1 / 96.6% top-5 ImageNet accuracy. In a controlled comparison against a well known reinforcement learning algorithm, we give evidence that evolution can obtain results faster with the same hardware, especially at the earlier stages of the search. This is relevant when fewer compute resources are available. Evolution is, thus, a simple method to effectively discover high-quality architectures. \n3. Abstract of Cited Paper (BIB003): While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation suboptimal. Likewise, we demonstrate that the common practice of using very few epochs during the main NAS and much larger numbers of epochs during a post-processing step is inefficient due to little correlation in the relative rankings for these two training regimes. To combat both of these problems, we propose to use a recent combination of Bayesian optimization and Hyperband for efficient joint neural architecture and hyperparameter search. \n4. Abstract of Cited Paper (BIB004): Automatic machine learning (AutoML) aims at automatically choosing the best configuration for machine learning tasks. However, a configuration evaluation can be very time consuming particularly on learning tasks with large datasets. This limitation usually restrains derivative-free optimization from releasing its full power for a fine configuration search using many evaluations. To alleviate this limitation, in this paper, we propose a derivative-free optimization framework for AutoML using multi-fidelity evaluations. It uses many lowfidelity evaluations on small data subsets and very few highfidelity evaluations on the full dataset. However, the lowfidelity evaluations can be badly biased, and need to be corrected with only a very low cost. We thus propose the Transfer Series Expansion (TSE) that learns the low-fidelity correction predictor efficiently by linearly combining a set of base predictors. The base predictors can be obtained cheaply from down-scaled and experienced tasks. Experimental results on real-world AutoML problems verify that the proposed framework can accelerate derivative-free configuration search significantly by making use of the multi-fidelity evaluations.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Since the training time is highly related to the dataset and model size, we can accelerate model evaluation from different perspectives. On the one hand, we can reduce the number of images or the resolution of images (for image classification tasks). For example, FABOLAS BIB001 trains the model on a subset of the training set to accelerate model estimation. In , ImageNet64×64 and its variants 32×32, 16×16 are provided, at the same time these lower resolution dataset can remain the similar characteristics of the origin ImageNet dataset. Figure 14 : Validation error of each configuration generated on different budgets during the whole HPO procedure. For example, each grey point represents the validation error of the corresponding network whose configuration is obtained with a 400-second search. At last, the networks that take 3600 seconds (orange points) to search performs as well as one that takes 10800 seconds (red points). On the other hand, low fidelity model evaluation can be realized by reducing the model size, such as training with less number of filters per layer BIB002 , BIB003 . Similar to ensemble learning, BIB005 propose the Transfer Series Expansion (TSE) that constructs an ensemble estimator by linearly combining a series of base low fidelity estimators, hence it solves the problem that a single low fidelity estimator can be badly biased. Furthermore, Zela et al. BIB004 empirically demonstrate that there is a weak correlation between the performance after short and long training time, hence we do not need to spend too much time searching network configurations (see Fig. 14) .",
"role": "assistant"
}
] |
science.qasa_abstractive_qa
|
science.qasa_abstractive_qa.901
|
[
{
"content": "Read this passage from a research paper and answer the question.\n\nContext: As noted in Table 1, a self-attention layer connects all positions with a constant number of sequentially executed operations, whereas a recurrent layer requires O(n) sequential operations.In terms of computational complexity, self-attention layers are faster than recurrent layers when the sequence length n is smaller than the representation dimensionality d, which is most often the case with sentence representations used by state-of-the-art models in machine translations, such as word-piece (wu2016google, ) and byte-pair (sennrich2015neural, ) representations.To improve computational performance for tasks involving very long sequences, self-attention could be restricted to considering only a neighborhood of size r in the input sequence centered around the respective output position. This would increase the maximum path length to O(n/r). We plan to investigate this approach further in future work.\n\nQuestion: How could restricting self attention to some window with size r be useful with long term dependencies?",
"role": "user"
},
{
"content": "Restricting self attention to some window with size r does improve computational performance but its effect on long term dependencies have not been explored in the paper.",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.7214
|
[
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nAn overview of the work the approach taken by the Anna Freud National Centre for Children and Families in the rapid transition to remote working in response to the coronavirus lockdown. We outline some of the challenges of remote working and how we are seeking to mitigate them, informed by the over-riding principle that individual relationships and the experiences of the child, young person and family must remain the central concern. The importance of maintaining a mentalising stance in remote working is discussed. We argue that a mentalising relationship which generates epistemic trust is possible in remote working, but this will require particular thought and effort on the part of the therapist. In particular, it is suggested that mentalising processes can be supported in remote working through, in the absence of the more implicit communications that are possible in face-to-face work, more explicit communications about mental states.",
"role": "user"
},
{
"content": "[\"Prevention\"]",
"role": "assistant"
}
] |
science.data_reco_mcq_mc
|
science.data_reco_mcq_mc.475
|
[
{
"content": "Based on the dataset descriptions below, which datasets would be suitable for the following research question? Your response should be a JSON array.\n\nQuestion: The robustness of RoBERTa, XLNet, and BERT under stress tests for NLI\n\nKeywords: nli qa text\n\nDataset descriptions:\nFarsTail: Natural Language Inference (NLI), also called Textual Entailment, is an important task in NLP with the goal of determining the inference relationship between a premise p and a hypothesis h. It is a three-class problem, where each pair (p, h) is assigned to one of these classes: \"ENTAILMENT\" if the hypothesis can be inferred from the premise, \"CONTRADICTION\" if the hypothesis contradicts the premise, and \"NEUTRAL\" if none of the above holds. There are large datasets such as SNLI, MNLI, and SciTail for NLI in English, but there are few datasets for poor-data languages like Persian.\nMultiNLI: The Multi-Genre Natural Language Inference (MultiNLI) dataset has 433K sentence pairs. Its size and mode of collection are modeled closely like SNLI.\nOpenWebText: OpenWebText is an open-source recreation of the WebText corpus. The text is web content extracted from URLs shared on Reddit with at least three upvotes.\nDreaddit: Consists of 190K posts from five different categories of Reddit communities.\nSQuAD: The Stanford Question Answering Dataset (SQuAD) is a collection of question-answer pairs derived from Wikipedia articles. In SQuAD, the correct answers of questions can be any sequence of tokens in the given text.\n\nOptions: A: FarsTail B: MultiNLI C: OpenWebText D: Dreaddit E: SQuAD",
"role": "user"
},
{
"content": "[\"MultiNLI\", \"SQuAD\"]",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.2055
|
[
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nComparison of laser photocoagulation for diabetic retinopathy using 532-nm standard laser versus multispot pattern scan laser . PURPOSE The purpose of this study was to compare the efficacy , collateral damage , and convenience of panretinal photocoagulation for proliferative diabetic retinopathy or severe nonproliferative diabetic retinopathy using a 532-nm solid-state green laser ( GLX ) versus a multispot 532-nm pattern scan laser ( PASCAL ) . METHODS This study was a prospective randomized clinical trial . Sixty patients with bilaterally symmetrical proliferative diabetic retinopathy or severe nonproliferative diabetic retinopathy participated . Each patient underwent panretinal photocoagulation : one eye with GLX and the other with PASCAL , two sittings per eye . Grade 3 burns with a 200-mum spot size were placed with both modalities . The fluence , pain using the visual analog scale , time , laser spot spread with infrared images , and retinal sensitivity were compared . RESULTS Pattern scan laser and GLX required an average fluence of 40.33 vs 191 J/cm ( 2 ) , respectively . Average time required per sitting was 1.43 minutes with PASCAL and 4.53 minutes with GLX . Average visual analog scale reading for GLX was 4.6 , whereas that for PASCAL was 0.33 . Heidelberg retinal angiography images showed the spot spread as being 430 versus 310 microm at 3 months with GLX and PASCAL . The eyes treated with PASCAL showed higher average retinal sensitivity in the central 15 degrees and 15 degrees to 30 degrees zones ( 25.08 and 22.08 dB , respectively ) than the eyes treated with GLX ( 23.16 and 17.14 dB ) , respectively . CONCLUSION Pattern scan laser showed lesser collateral damage and similar regression of retinopathy compared with GLX . Pattern scan laser treatment was less time consuming and less painful for the patient compared with GLX .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"multispot 532-nm pattern scan laser\", \"PASCAL\", \"solid-state green laser ( GLX )\", \"laser photocoagulation\", \"one eye with GLX\"], \"Outcome\": [\"time\", \"retinal sensitivity\", \"fluence , pain using the visual analog scale\", \"average retinal sensitivity\", \"average fluence\", \"Average time required per sitting\", \"Average visual analog scale reading\", \"regression of retinopathy\", \"spot spread\", \"laser spot spread\"], \"Participant\": [\"proliferative diabetic retinopathy or severe nonproliferative diabetic retinopathy\"]}",
"role": "assistant"
}
] |
science.qasa_abstractive_qa
|
science.qasa_abstractive_qa.572
|
[
{
"content": "Read this passage from a research paper and answer the question.\n\nContext: performance in all metrics related to task accomplishment. However, they also show that GPT-Critic takes longer dialogue turn for the task accomplishment because GPT-Critic is trained by maximizing the success rate without considering the dialogue turn.\n\nQuestion: Why does the proposed algorithm not outperforms in turn metric in the results of ConvLab experiments?",
"role": "user"
},
{
"content": "Since a proposed method is trained by maximizing the success rate without considering the dialogue turn, the proposed algorithm does not outperforms in turn metric in the results.",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.10037
|
[
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: A comprehensive survey of RDF dataset profiling methods, tools and vocabularies.\n\nKeyphrases: rdf dataset profiling datasets\n\nDataset descriptions:\nQM9: QM9 provides quantum chemical properties for a relevant, consistent, and comprehensive chemical space of small organic molecules. This database may serve the benchmarking of existing methods, development of new methods, such as hybrid quantum mechanics/machine learning, and systematic identification of structure-property relationships.\nDBpedia: DBpedia (from \"DB\" for \"database\") is a project aiming to extract structured content from the information created in the Wikipedia project. DBpedia allows users to semantically query relationships and properties of Wikipedia resources, including links to other related datasets.\nGSL: Dataset Description The Greek Sign Language (GSL) is a large-scale RGB+D dataset, suitable for Sign Language Recognition (SLR) and Sign Language Translation (SLT). The video captures are conducted using an Intel RealSense D435 RGB+D camera at a rate of 30 fps.\nBanglaWriting: The BanglaWriting dataset contains single-page handwritings of 260 individuals of different personalities and ages. Each page includes bounding-boxes that bounds each word, along with the unicode representation of the writing.\n\nOptions: A: QM9 B: DBpedia C: GSL D: BanglaWriting",
"role": "user"
},
{
"content": "DBpedia",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.49188
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Survey of Smart Grid Concepts and Technological Demonstrations Worldwide Emphasizing on the Oman Perspective \nChapter Title: ICT Infrastructure for Advance Protection System \n1. Abstract of Cited Paper (BIB001): Increasing complexity of power grids, growing demand, and requirement for greater reliability, security and efficiency as well as environmental and energy sustainability concerns continue to highlight the need for a quantum leap in harnessing communication and information technologies. This leap toward a ?smarter? grid is widely referred to as ?smart grid.? A framework for cohesive integration of these technologies facilitates convergence of acutely needed standards, and implementation of necessary analytical capabilities. This paper critically reviews the reliability impacts of major smart grid resources such as renewables, demand response, and storage. We observe that an ideal mix of these resources leads to a flatter net demand that eventually accentuates reliability challenges further. A gridwide IT architectural framework is presented to meet these challenges while facilitating modern cybersecurity measures. This architecture supports a multitude of geographically and temporally coordinated hierarchical monitoring and control actions over time scales from milliseconds and up. \n2. Abstract of Cited Paper (BIB002): Recently, there has been an increased focus and a sense of urgency in developing standards for Power Grid systems centered on the need for interoperability. Given the threat against these systems an important goal is the development of effective cyber security standards. However, past experience shows that security protocols are prone to design errors. Focusing on authentication protocols, in this work we discuss key design principles and engineering practices that we believe can help ensure the correctness and effectiveness of standards for authentication in Power Grid protocols; e.g., DNP3. This work builds on past work in the area of principles of authentication in Internet protocols but focuses the discussion on the constraints of the Power Grid; in particular, the need for efficient and highly available systems. \n3. Abstract of Cited Paper (BIB003): The development of a trustworthy smart grid requires a deeper understanding of potential impacts resulting from successful cyber attacks. Estimating feasible attack impact requires an evaluation of the grid's dependency on its cyber infrastructure and its ability to tolerate potential failures. A further exploration of the cyber-physical relationships within the smart grid and a specific review of possible attack vectors is necessary to determine the adequacy of cybersecurity efforts. This paper highlights the significance of cyber infrastructure security in conjunction with power application security to prevent, mitigate, and tolerate cyber attacks. A layered approach is introduced to evaluating risk based on the security of both the physical power applications and the supporting cyber infrastructure. A classification is presented to highlight dependencies between the cyber-physical controls required to support the smart grid and the communication and computations that must be protected from cyber attack. The paper then presents current research efforts aimed at enhancing the smart grid's application and infrastructure security. Finally, current challenges are identified to facilitate future research efforts. \n4. Abstract of Cited Paper (BIB004): This panel session paper outlines one of the research thrust areas in the Power System Engineering Research Center's (PSERC) new initiative funded by the US Department of Energy (DOE) to investigate requirements for a systematic transformation of today's electric grid to enable high penetrations of sustainable energy systems. The proposed research under this thrust area aims at defining and determining the feasibility of wide area control and protection that will be needed in the future.\n\nLiterature Review:",
"role": "user"
},
{
"content": "The SG protection is expected to respond not only grid infrastructure faults such as the failure in equipment and natural catastrophe, but also unplanned cyber-attacks. A layer-based ICT infrastructure is required to incorporate into SG system in order to avoid illegal access, and allows the system resiliency during a cyber-attack BIB004 . Three coordinated layers, such as predictive, inherent adaptive and corrective protections, based ICT infrastructure has been proposed in reference BIB001 . The ICT infrastructure must have the ability to address the malicious attacks on transmitted information in the SG. The consequences of the malicious attacks include delay in information transmission corrupt data, or make the network inaccessible to exchange information. In the data integrity attacks, attempts are made to purposely modify or corrupt data in the SG. Whereas, in the information privacy attacks attempts are made to spy on communications to obtain the targeted data such as customer's account information BIB002 BIB001 . Smart protections along with layer-based ICT infrastructure have been proposed by several researchers in order to address malicious attack BIB005 BIB003 . ICT infrastructure of smart grid is represented in Figure 8 .",
"role": "assistant"
}
] |
science.nlmgene_ner
|
science.nlmgene_ner.250
|
[
{
"content": "Find all entities of these types in the text: [\"Gene\"].\n\nOutput a JSON object.\n\nText:\nOverexpression of human selenoprotein H in neuronal cells enhances mitochondrial biogenesis and function through activation of protein kinase A, protein kinase B, and cyclic adenosine monophosphate response element-binding protein pathway. Mitochondrial biogenesis is activated by nuclear encoded transcription co-activator peroxisome proliferator-activated receptor γ coactivator-1α (PGC-1α), which is regulated by several upstream factors including protein kinase A and Akt/protein kinase B. We have previously shown that selenoprotein H enhances the levels of nuclear regulators for mitochondrial biogenesis, increases mitochondrial mass and improves mitochondrial respiratory rate, under physiological condition. Furthermore, overexpression of selenoprotein H protects neuronal HT22 cells from ultraviolet B irradiation-induced cell damage by lowering reactive oxygen species production, and inhibiting activation of caspase-3 and -9, as well as p53. The objective of this study is to identify the cell signaling pathways by which selenoprotein H initiates mitochondrial biogenesis. We first confirmed our previous observation that selenoprotein H transfected HT22 cells increased the protein levels of nuclear-encoded mitochondrial biogenesis factors, peroxisome proliferator-activated receptor γ coactivator-1α, nuclear respiratory factor 1 and mitochondrial transcription factor A. We then observed that total and phosphorylation of protein kinase A, Akt/protein kinase B and cyclic adenosine monophosphate response element-binding protein (CREB) were significantly increased in selenoprotein H transfected cells compared to vector transfected HT22 cells. To verify whether the observed stimulating effects on mitochondrial biogenesis pathways are caused by selenoprotein H and mediated through CREB, we knocked down selenoprotein H mRNA level using siRNA and inhibited CREB with napthol AS-E phosphate in selenoprotein H transfected cells and repeated the measurements of the aforementioned biomarkers. Our results revealed that silencing of selenoprotein H not only decreased the protein levels of PGC-1α, nuclear respiratory factor 1 and mitochondrial transcription factor A, but also decreased the total and phosphorylation levels of protein kinase A, protein kinase B, and CREB. Similarly, CREB inhibition reduced CREB activation and PGC-1α protein levels in selenoprotein H transfected cells. Moreover, selenoprotein H transfection increased the activity of mitochondrial complexes and prevented the ultraviolet B induced fall of mitochondrial membrane potential. We conclude that the effects of selenoprotein H on mitochondrial biogenesis and mitochondrial function are probably mediated through protein kinase A-CREB-PGC-1α and Akt/protein kinase B-CREB-PGC-1α pathways.",
"role": "user"
},
{
"content": "{\"Gene\": [\"PGC-1\\u03b1\", \"cyclic adenosine monophosphate response element-binding protein\", \"peroxisome proliferator-activated receptor \\u03b3 coactivator-1\\u03b1\", \"nuclear respiratory factor 1\", \"selenoprotein H\", \"protein kinase A\", \"caspase-3 and -9\", \"peroxisome proliferator-activated receptor \\u03b3 coactivator-1\\u03b1,\", \"Akt\", \"CREB\", \"p53\", \"nuclear encoded transcription co-activator peroxisome proliferator-activated receptor \\u03b3 coactivator-1\\u03b1\", \"protein kinase B\", \"mitochondrial transcription factor A\"]}",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_pubmed
|
science.scientific_papers_summarization_single_doc_pubmed.14449
|
[
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\nspontaneous cerebrospinal fluid ( csf ) fistula of the skull base is an uncommon condition associated with multiple etiologies and can have a variable presentation . of note , obese , middle - aged , and multiparous women\nmost commonly develop this condition.1 \n 2 intractable , watery discharge from the nose ( rhinorrhea ) that tests positive for 2-transferrin is pathognomonic.1 however , the quality and quantity of discharge may result in misdiagnosis as allergic rhinitis or sinusitis and delay treatment , particularly if the condition presents with atypical complications .\nwe present the first known case of spontaneous csf rhinorrhea complicated by chronic pneumonitis secondary to csf aspiration , which was successfully resolved by endoscopic endonasal repair , and discuss the relevant literature associated with the complications of spontaneous csf rhinorrhea .\na 44-year - old woman presented with 4 months of progressive cough , exertional dyspnea , hoarseness , and intermittent fluid drainage from the right nostril .\nshe was initially evaluated by a pulmonologist , who noted that she was otherwise healthy besides being obese ( body mass index : 36.5 kg / m ) and having diminished lung sounds bilaterally at the bases . computed tomography ( ct ) imaging of the chest ( fig .\nshe was also prescribed codeine , formoterol / budesonide , prednisone , albuterol , montelukast , and fluticasone in various unsuccessful attempts to alleviate her pulmonary symptoms . \n\npreoperative ct image of the paranasal sinuses ( a ) showing meningocele with fluid collection in the right ethmoid sinus ( arrows ) and of the chest ( b ) showing lung opacities ( circles ) .\nct , computed tomography . because of the persistent pneumonitis , she was referred to a thoracic surgeon for further evaluation . due to the uncertain , persistent , and the progressive nature of her lung findings , a thoracoscopic wedge resection of the superior right upper lobe\nthe specimen showed acute bronchopneumonia , a 1.5-mm chemodectoma , and acute on chronic inflammation , but no further etiology was determined .\nshe was then referred to an otolaryngologist for evaluation of the persistent nasal drainage and postnasal drip , which was a major stimulant of her cough and severe enough to force her to sleep upright .\nthe nasal fluid was more pronounced during a forward tilt test , and was collected and tested positive for 2-transferrin .\nthis was an unexpected finding , as a spontaneous csf fistula with chronic aspiration has not been previously recognized as a cause of lung disease .\nthe patient was referred to our otolaryngology and neurosurgery services for evaluation of her spontaneous csf rhinorrhea .\nendoscopic evaluation of her nasal cavity in the clinic setting did not identify a site of csf leakage .\n1 ) showed bony dehiscence of the skull base and a meningocele extending into the right ethmoid sinus .\nalthough the cause of her spontaneous csf leak and skull base defect was unknown , it was likely related to her body habitus and idiopathic intracranial hypertension .\nfollowing administration of intrathecal fluorescein through a lumbar drain , a small bony defect and brisk csf fistula were identified in the region of the right fovea ethmoidalis .\nthe bony and dural defects were repaired using a two - layer reconstruction with autologous fascia lata ( fascial apposition method ) followed by a pedicled nasal - septal flap .\nthe lumbar drain was removed on postoperative day 3 . following surgery , her pneumonitis resolved and she remained free of any pulmonary symptoms at 11-month follow - up .\npostoperative ct imaging of the chest showing resolution of the lung opacities ( circles ) .\na 44-year - old woman presented with 4 months of progressive cough , exertional dyspnea , hoarseness , and intermittent fluid drainage from the right nostril .\nshe was initially evaluated by a pulmonologist , who noted that she was otherwise healthy besides being obese ( body mass index : 36.5 kg / m ) and having diminished lung sounds bilaterally at the bases . computed tomography ( ct ) imaging of the chest ( fig .\nshe was also prescribed codeine , formoterol / budesonide , prednisone , albuterol , montelukast , and fluticasone in various unsuccessful attempts to alleviate her pulmonary symptoms . \n\npreoperative ct image of the paranasal sinuses ( a ) showing meningocele with fluid collection in the right ethmoid sinus ( arrows ) and of the chest ( b ) showing lung opacities ( circles ) .\nct , computed tomography . because of the persistent pneumonitis , she was referred to a thoracic surgeon for further evaluation . due to the uncertain , persistent , and the progressive nature of her lung findings , a thoracoscopic wedge resection of the superior right upper lobe\nthe specimen showed acute bronchopneumonia , a 1.5-mm chemodectoma , and acute on chronic inflammation , but no further etiology was determined .\nshe was then referred to an otolaryngologist for evaluation of the persistent nasal drainage and postnasal drip , which was a major stimulant of her cough and severe enough to force her to sleep upright .\nthe nasal fluid was more pronounced during a forward tilt test , and was collected and tested positive for 2-transferrin .\nthis was an unexpected finding , as a spontaneous csf fistula with chronic aspiration has not been previously recognized as a cause of lung disease .\nthe patient was referred to our otolaryngology and neurosurgery services for evaluation of her spontaneous csf rhinorrhea .\nendoscopic evaluation of her nasal cavity in the clinic setting did not identify a site of csf leakage .\n1 ) showed bony dehiscence of the skull base and a meningocele extending into the right ethmoid sinus .\nalthough the cause of her spontaneous csf leak and skull base defect was unknown , it was likely related to her body habitus and idiopathic intracranial hypertension .\nthe csf leak was repaired via a right endoscopic endonasal approach . following administration of intrathecal fluorescein through a lumbar drain ,\na small bony defect and brisk csf fistula were identified in the region of the right fovea ethmoidalis .\nthe bony and dural defects were repaired using a two - layer reconstruction with autologous fascia lata ( fascial apposition method ) followed by a pedicled nasal - septal flap .\nthe lumbar drain was removed on postoperative day 3 . following surgery , her pneumonitis resolved and she remained free of any pulmonary symptoms at 11-month follow - up .\npostoperative ct imaging of the chest showing resolution of the lung opacities ( circles ) .\ndiagnosis and treatment of spontaneous csf rhinorrhea are straightforward , but can be delayed significantly if it presents with atypical complications . upon review of the literature ,\nthe most common and clinically relevant complications are meningitis and pneumocephalus.3 \n 4 meningitis is of primary concern for all csf leaks regardless of origin .\nnasopharyngeal csf leaks are especially prominent sources of meningitis , as pneumococci are responsible for greater than 80% of csf leak - related meningitis.5 other complications , such as intermittent herniation , empty sella syndrome , and spontaneous intracranial hypotension are much rarer.6 \n 7 \n 8 our report of chronic pneumonitis due to csf aspiration is the first reported instance of this significant and clinically relevant complication .\nwhile our case did not present this issue , difficulties with identifying the skull base defect on standard neuroimaging studies can also result in treatment delay.9 ct imaging is standard and magnetic resonance imaging can be used if ct results are nondiagnostic.10 however , it remains that some scans will not clearly identify the responsible skull base defect.11 regardless of imaging , 2-transferrin positive nasal discharge is sufficient cause for endoscopic endonasal exploration and repair1 ; use of intrathecal fluorescein dye will help identify the leak under direct visualization.10 \n once the location of the csf fistula is accurately identified , multiple surgical repair options exist .\nautologous fat and fascial grafting is commonly used to fill in any dead space and create a dural reconstruction , respectively .\nmethod , in which the first fascial layer is inserted as a dural inlay and the second is placed in apposition as a dural overlay and bony inlay.12 we prefer not to use a rigid buttress unless the defect is exceptionally large , but routinely prepare and rotate a pedicled nasal - septal flap for broad coverage of the defect as described by hadad et al,13 and popularized by kassam et al.14 lumbar drainage may be utilized conservatively to temporarily reduce csf pressure for 2 to 3 days following the operation along with facilitating intraoperative intrathecal fluorescein administration . in this case , the increased diagnostic complexity related to the pronounced pulmonary complications resulted in unnecessary interventions and treatment delays .\nthis is a meaningful example of why prompt recognition of spontaneous csf leaks by practitioners of all types is essential to prevent potentially harmful complications including meningitis , pneumocephalus , and even lung disease caused by chronic csf aspiration .",
"role": "user"
},
{
"content": "spontaneous cerebrospinal fluid ( csf ) rhinorrhea due to a skull base defect requires prompt diagnosis and treatment . \n multiple surgical options are available for repairing the fistula , including the two - layer fascial apposition method and use of a pedicled nasal - septal flap . \n a 44-year - old obese woman presented with 4 months of progressive cough , exertional dyspnea , hoarseness , and intermittent fluid drainage from the right nostril . \n chest computed tomography ( ct ) imaging and bronchoscopy showed chronic pneumonitis , which was confirmed by pulmonary wedge resection . \n ct and magnetic resonance imaging of the skull base , as well as laboratory analysis of the nasal fluid for 2-transferrin , confirmed a skull base defect causing csf rhinorrhea . during surgery , \n insertion of a lumbar drain with the intrathecal fluorescein administration was performed , followed by endoscopic endonasal repair using an autologous fascial apposition graft and pedicled nasal - septal flap . \n both the csf leak and the pulmonary complications resolved following the operation with no symptoms at 11-month follow - up . \n this is the first reported case of spontaneous csf rhinorrhea complicated by chronic aspiration and pneumonitis . \n increased diagnostic complexity due to chronic pulmonary complications resulted in unnecessary interventions and treatment delays . \n prompt recognition of spontaneous csf leaks is essential to prevent potentially harmful complications .",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.18968
|
[
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nPURPOSE OF REVIEW: Present a review of relevant literature and suggest a framework for discussion of the considerations affecting the evolution and adoption of Telerobotic Support and Telerobotic Collaboration in the practice of cardiac procedural medicine. RECENT FINDINGS: Recent medical practice has undergone remarkable transformation in the adoption of telemedicine. This evolution has been accelerated by the COVID-19 (SARS-CoV-2) pandemic and has largely been focused on outpatient medicine. Clinical studies and opinion articles have highlighted benefits including reduced costs, increased patient engagement, and saved time, while also raising concerns regarding privacy, care quality and data security. Early and current efforts implementing remote procedural medicine have not only demonstrated technical success but also highlighted the many issues that must be resolved before acceptance as a major aspect of everyday patient care. SUMMARY: It is inevitable that remote technologies will play an increasing role in procedural medicine as they have in outpatient clinical medicine. Thoughtful participation by physicians in the evolution of these technologies and their modes of use will be necessary to maximize the benefits to our patients and healthcare systems.",
"role": "user"
},
{
"content": "[\"Prevention\"]",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.5053
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nWe present a novel compact point cloud representation that is inherently invariant to scale, coordinate change and point permutation. The key idea is to parametrize a distance field around an individual shape into a unique, canonical, and compact vector in an unsupervised manner. We firstly project a distance field to a @math D canonical space using singular value decomposition. We then train a neural network for each instance to non-linearly embed its distance field into network parameters. We employ a bias-free Extreme Learning Machine (ELM) with ReLU activation units, which has scale-factor commutative property between layers. We demonstrate the descriptiveness of the instance-wise, shape-embedded network parameters by using them to classify shapes in @math D datasets. Our learning-based representation requires minimal augmentation and simple neural networks, where previous approaches demand numerous representations to handle coordinate change and point permutation.\n\nCited Abstract(s):\n[1]: Although RGB-D sensors have enabled major break-throughs for several vision tasks, such as 3D reconstruction, we have not attained the same level of success in high-level scene understanding. Perhaps one of the main reasons is the lack of a large-scale benchmark with 3D annotations and 3D evaluation metrics. In this paper, we introduce an RGB-D benchmark suite for the goal of advancing the state-of-the-arts in all major scene understanding tasks. Our dataset is captured by four different sensors and contains 10,335 RGB-D images, at a similar scale as PASCAL VOC. The whole dataset is densely annotated and includes 146,617 2D polygons and 64,595 3D bounding boxes with accurate object orientations, as well as a 3D room layout and scene category for each image. This dataset enables us to train data-hungry algorithms for scene-understanding tasks, evaluate them using meaningful 3D metrics, avoid overfitting to a small testing set, and study cross-sensor bias.\n\n[2]: We present ShapeNet: a richly-annotated, large-scale repository of shapes represented by 3D CAD models of objects. ShapeNet contains 3D models from a multitude of semantic categories and organizes them under the WordNet taxonomy. It is a collection of datasets providing many semantic annotations for each 3D model such as consistent rigid alignments, parts and bilateral symmetry planes, physical sizes, keywords, as well as other planned annotations. Annotations are made available through a public web-based interface to enable data visualization of object attributes, promote data-driven geometric analysis, and provide a large-scale quantitative benchmark for research in computer graphics and vision. At the time of this technical report, ShapeNet has indexed more than 3,000,000 models, 220,000 models out of which are classified into 3,135 categories (WordNet synsets). In this report we describe the ShapeNet effort as a whole, provide details for all currently available datasets, and summarize future plans.",
"role": "user"
},
{
"content": "With the advances in deep learning techniques and more datasets [1] [2] becoming available, classifying shapes from point clouds is quickly becoming a major task in computer vision. Most methods focus on finding a ''convolution-friendly'' representation that can be used as input to convolutional neural networks. Common approaches are voxel-based, image rendering-based, cross-section-based, and point-based methods. Table shows the common approaches and the invariance and robustness they achieve.",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.23856
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A survey of numerical methods for IVPs of ODEs with discontinuous right-hand side \nChapter Title: Event location procedure \n1. Abstract of Cited Paper (BIB001): Abstract An initial value problem for y′ = f(t, y) may have an associated event function g(t, y). An event is said to occur at t∗ when g(t∗, y(t∗)) = 0 . We consider problems for which the definition of f(t, y) changes at the time of an event. A number of solvers locate events and restart the integration there so as to deal with the changes in f, but there is little theoretical support for what is done. Here we prove that with reasonable assumptions about the problem and the solver, the error of the numerical solution is qualitatively the same whether or not events occur. Numerical results obtained with a wide range of solvers confirm the theory developed here. \n2. Abstract of Cited Paper (BIB002): Abstract Numerical integration of dynamical equations of mechanical systems with impacts still poses many open problems. On the one hand there exist powerful integration codes with embedded root Þnding capabilities. However, for these codes, the issues of (1) efÞciency, (2) reliability and (3) stability of time progression through events still are not solved satisfactorily. In this paper, we present the implementation of a special approach for solving impact problems, in which we combine a Runge-Kutta method of order 4/5 with the Dormand coefÞcients for continuous extension dense output and a polynomial root detection algorithm. The method has been intensively tested for mechanical systems and displays robust behavior for non-stiff systems \n3. Abstract of Cited Paper (BIB003): The main purpose of the book is to introduce the readers to the numerical integration of the Cauchy problem for delay differential equations (DDEs). Peculiarities and differences that DDEs exhibit with respect to ordinary differential equations are preliminarily outlined by numerous examples illustrating some unexpected, and often surprising, behaviours of the analytical and numerical solutions. The effect of various kinds of delays on the regularity of the solution is described and some essential existence and uniqueness results are reported. The book is centered on the use of Runge-Kutta methods continuously extended by polynomial interpolation, includes a brief review of the various approaches existing in the literature, and develops an exhaustive error and well-posedness analysis for the general classes of one-step and multistep methods. The book presents a comprehensive development of continuous extensions of Runge-Kutta methods which are of interest also in the numerical treatment of more general problems such as dense output, discontinuous equations, etc. Some deeper insight into convergence and superconvergence of continuous Runge-Kutta methods is carried out for DDEs with various kinds of delays. The stepsize control mechanism is also developed on a firm mathematical basis relying on the discrete and continuous local error estimates. Classical results and a unconventional analysis of \"stability with respect to forcing term\" is reviewed for ordinary differential equations in view of the subsequent numerical stability analysis. Moreover, an exhaustive description of stability domains for some test DDEs is carried out and the corresponding stability requirements for the numerical methods are assessed and investigated. Alternative approaches, based on suitable formulation of DDEs as partial differential equations and subsequent semidiscretization are briefly described and compared with the classical approach. A list of available codes is provided, and illustrative examples, pseudo-codes and numerical experiments are included throughout the book. Series Editors: G. H. Golub (Stanford University) C. Schwab (ETH Zurich) W. A. Light (University of Leicester) E. Suli (University of Oxford) Recent developments in the field of numerical analysis have radically changed the nature of the subject. Firstly, the increasing power and availability of computer workstations has allowed the widespread feasibility of complex numerical computations, and the demands of mathematical modelling are expanding at a corresponding rate. In addition to this, the mathematical theory of numerical mathematics itself is growing in sophistication, and numerical analysis now generates research into relatively abstract mathematics. Oxford University Press has had an established series Monographs in Numerical Analysis, including Wilkinson's celebrated treatise The Algebraic Eigenvalue Problem. In the face of the developments in the field this has been relaunched as the Numerical Mathematics and Scientific Computation series. As its name suggests, the series will now aim to cover the broad subject area concerned with theoretical and computational aspects of modern numerical mathematics. Available in OSO: http://www.oxfordscholarship.com/oso/public/content/maths/9780198506546/toc.html \n4. Abstract of Cited Paper (BIB004): Systems of implicit delay differential equations, including state-dependent problems, neutral and differential-algebraic equations, singularly perturbed problems, and small or vanishing delays are considered. The numerical integration of such problems is very sensitive to jump discontinuities in the solution or in its derivatives (so-called breaking points). In this article we discuss a new strategy – peculiar to implicit schemes – that allows codes to detect automatically and then to compute very accurately those breaking points which have to be inserted into the mesh to guarantee the required accuracy. In particular for state-dependent delays, where breaking points are not known in advance, this treatment leads to a significant improvement in accuracy. As a theoretical result we obtain a general convergence theorem which was missing in the literature (see Bellen and Zennaro, Numerical Methods for Delay Differential Equations, Oxford University Press, Oxford, 2003). Furthermore, as a useful by-product, we design strategies that are able to detect points of non-uniqueness or non-existence of the solution so that the code can terminate when such a situation occurs. A new version of the code RADAR5 together with drivers for some real-life problems is available on the homepages of the authors. \n5. Abstract of Cited Paper (BIB005): Abstract The interpolation polynomial in the k -step Adams–Bashforth method may be used to compute the numerical solution at off grid points. We show that such a numerical solution is equivalent to the one obtained by the Nordsieck technique for changing the step size. We also provide an application of this technique to the event location in discontinuous differential systems.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Event location arises naturally in many models as a way of dealing with discontinuous behaviors. A nice survey of methods that have been proposed for dealing with it may be found in [38] . The task also arises in the solution of delay differential equations because of discontinuities that are induced by a lack of smoothness and propagated by the delays BIB005 . Even the popular ODESUITE of Matlab codes provides event detection as an option. When an event function h(x) exists, in order to derive an effective procedure, the routine which locates the discontinuity pointξ should be inexpensive but very accurate. For instance, in the simplified Newton method (3.2), the evaluation of χ 1 (ξ i ) needs additional evaluations of the vector field f 1 , and this could lead to an expensive procedure with a large number of function evaluations. An interpolation or a continuous extension of the numerical solution given by a one-step method can be used to locate the discontinuity pointx in the discontinuity interval (t k , t k+1 ). For instance, consider a s-stage Runge-Kutta method (of order p) given by the Butcher array s and its continuous extension: where: with p * ≤ p. Thus, in order to locateξ we may find a root of h(x k+1 (σ )). Such a continuous extension does not require additional function evaluations, but it must provide a point on Σ with an error which preserves the accuracy of the underlying one-step method, that is of order O(τ p ); this means that p * has to be equal to p (see for instance BIB001 BIB003 ). The theory of continuous Runge-Kutta methods tells us that for explicit Runge-Kutta methods of order up to p = 3 there is a continuous extension of the same order requiring no additional function evaluations (e.g., see BIB004 ). Often, in the context of linear multistep methods a continuous approximation of the numerical solution derives directly from the numerical scheme, which is based on polynomial interpolation of the vector field values; e.g., see the Adams formulas. So, in these cases, if an event function exists, it is possible to use such a continuous numerical solution to find the event point in the discontinuity interval without additional function evaluations (see BIB002 ). Fig. 9 . Two event points in the discontinuity interval. For instance, if the discontinuity interval is (t k , t k+1 ), then the m-step Adams-Bashforth method (AB), which is a method of order p = m, reads: where ). Thus, if we need to approximate the solution at t k + σ τ , for σ ∈ (0, 1), it is natural to use the following continuous approximation: where Table 1 for the first few γ i (σ ) functions). The numerical method in (6.2) may be interpreted as a variable stepsize AB method where the size of the interpolation grid is constant and equal to τ , except in the last step, when it is equal to σ τ . It is easy to see that the local truncation error of the numerical solution (6.2) is O(τ m+1 ) for every σ ∈ (0, 1). Thus, an event point may be computed as a root of the scalar polynomial (of degree m) H(σ ) = h(x k+1 (σ τ )). Of course, evaluation of (6.2) at a value σ ∈ (0, 1) does not require additional function evaluations with respect to the ones need to compute x k+1 as noted in BIB006 . We conclude this discussion on event detection by cautioning that several critical situations can appear in the detection of the discontinuity points. For instance, an event may occur as a double root, or multiple events can occur if the discontinuity interval [t k , t k + τ ] is not sufficiently small. In such cases the numerical method may fail to notice that an event has occurred because there is no change sign for h(x) (see Fig. 9 ); because of this, the assumption that events are isolated is a more serious matter in practice than it might at first seem. From the practical and mathematical points of view, one could very small time steps or require some form of monotonicity for the numerical solution on the discontinuity interval in order to guarantee only one intersection with Σ. In , Carver suggests an interesting approach to event location: to add the differential to the original differential system. This way, the stepsize will be selected not only to take into account changes in the solution",
"role": "assistant"
}
] |
science.scicite_classification
|
science.scicite_classification.1968
|
[
{
"content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: out mainly in rural areas of Tenerife [2], along with the high prevalence of P.",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.11518
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nAbstract We address the problem of transferring the style of a headshot photo to face images. Existing methods using a single exemplar lead to inaccurate results when the exemplar does not contain sufficient stylized facial components for a given photo. In this work, we propose an algorithm to stylize face images using multiple exemplars containing different subjects in the same style. Patch correspondences between an input photo and multiple exemplars are established using a Markov Random Field (MRF), which enables accurate local energy transfer via Laplacian stacks. As image patches from multiple exemplars are used, the boundaries of facial components on the target image are inevitably inconsistent. The artifacts are removed by a post-processing step using an edge-preserving filter. Experimental results show that the proposed algorithm consistently produces visually pleasing results.\n\nCited Abstract(s):\n[1]: Headshot portraits are a popular subject in photography but to achieve a compelling visual style requires advanced skills that a casual photographer will not have. Further, algorithms that automate or assist the stylization of generic photographs do not perform well on headshots due to the feature-specific, local retouching that a professional photographer typically applies to generate such portraits. We introduce a technique to transfer the style of an example headshot photo onto a new one. This can allow one to easily reproduce the look of renowned artists. At the core of our approach is a new multiscale technique to robustly transfer the local statistics of an example portrait onto a new one. This technique matches properties such as the local contrast and the overall lighting direction while being tolerant to the unavoidable differences between the faces of two different people. Additionally, because artists sometimes produce entire headshot collections in a common style, we show how to automatically find a good example to use as a reference for a given portrait, enabling style transfer without the user having to search for a suitable example for each input. We demonstrate our approach on data taken in a controlled environment as well as on a large set of photos downloaded from the Internet. We show that we can successfully handle styles by a variety of different artists.",
"role": "user"
},
{
"content": ": A local method that transfers the face style of an exemplar to the input face image is proposed in [1] . It first generates dense correspondence between an input photo and one selected exemplar. Then it decomposes each image into a Laplacian stack before transferring the local energy in each image frequency subband within each layer. Finally all the stacks are aggregated to generate the output image. Since the style represented by the local energy is precisely transferred in multiple layers, it has the advantage to handle detailed facial components. Compared to the holistic methods, local approaches can better capture the region details and thus facilitate face stylization . However, if the components appeared in the exemplars and the input photos are significantly different, the resulting images are likely to contain undesired effects. In this work, we use multiple exemplars to solve this problem.",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.1455
|
[
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: A semi-adversarial convolutional autoencoder to extend gender privacy to\n\nKeyphrases: privacy extension face images\n\nDataset descriptions:\nCelebA: CelebFaces Attributes dataset contains 202,599 face images of the size 178×218 from 10,177 celebrities, each annotated with 40 binary labels indicating facial attributes like hair color, gender and age.\nWikiLarge: WikiLarge comprise 359 test sentences, 2000 development sentences and 300k training sentences. Each source sentences in test set has 8 simplified references\nPA-HMDB51: The Privacy Annotated HMDB51 (PA-HMDB51) dataset is a video-based dataset for evaluating pirvacy protection in visual action recognition algorithms. The dataset contains both target task labels (action) and selected privacy attributes (skin color, face, gender, nudity, and relationship) annotated on a per-frame basis.\nPersonalDialog: PersonalDialog is a large-scale multi-turn dialogue dataset containing various traits from a large number of speakers. The dataset consists of 20.83M sessions and 56.25M utterances from 8.47M speakers.\n\nOptions: A: CelebA B: WikiLarge C: PA-HMDB51 D: PersonalDialog",
"role": "user"
},
{
"content": "CelebA",
"role": "assistant"
}
] |
science.mslr2022_cochrane_multidoc_summarization
|
science.mslr2022_cochrane_multidoc_summarization.1044
|
[
{
"content": "Based on the RCT reports below, write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article.\n\n\n\nTitle 1:\nMolluscum contagiosum effectively treated with a topical acidified nitrite, nitric oxide liberating cream.\nAbstract 1:\nA double-blind, group-sequential clinical trial of acidified nitrite was performed to demonstrate the efficacy of this nitric oxide donor in treating molluscum contagiosum. Subjects received either 5% sodium nitrite co-applied with 5% salicylic acid under occlusion, or identical cream with 5% salicylic acid, omitting sodium nitrite. Active and control treatment groups were well matched for the number and duration of lesions and made a similar number of applications. We found a 75% cure rate in the active treatment group and 21% cure with control treatment (P = 0.01). The mean time to cure was 1.83 months. Staining of the skin and irritation were frequent side-effects but did not prevent successful treatment.\n\n\nTitle 2:\nEssential oil of Australian lemon myrtle (Backhousia citriodora) in the treatment of molluscum contagiosum in children.\nAbstract 2:\nMolluscum contagiosum is a common viral illness of childhood and is increasingly found as a sexually transmitted disease in sexually active young adults. Current treatment options are invasive, requiring tissue destruction and attendant discomfort. Thirty-one children (mean age 4.6 +/- 2.1 years) with the diagnosis of molluscum contagiosum (mean length of time with condition 8.6 +/- 5.3 months) were treated with once daily topical application of a 10% solution (v/v) of essential oil of Australian lemon myrtle (Backhousia citriodora) or vehicle (olive oil). At the end of 21 days, there was greater than 90% reduction in the number of lesions in 9/16 children treated with lemon myrtle oil, while 0/16 children met the same criteria for improvement in the vehicle group (P < 0.05). No adverse events were reported.\n\n\nTitle 3:\nA prospective randomized trial comparing the efficacy and adverse effects of four recognized treatments of molluscum contagiosum in children.\nAbstract 3:\nMolluscum contagiosum is a common viral disease of childhood presenting as small, firm, dome-shaped umbilicated papules. Although benign and generally self-limited, this condition is contagious and can lead to complications such as inflammation, pruritus, dermatitis, bacterial superinfection, and scars. No consensus has been established concerning the management of this condition. We conducted a prospective randomized study comparing four common treatments for molluscum contagiosum in 124 children aged 1 to 18 years. One group was treated with curettage, a second with cantharidin, a third with a combination of salicylic acid and lactic acid, and a fourth with imiquimod. Patients needing, respectively, one, two, or three visits for treatment of their mollusca were: 80.6%, 16.1%, and 3.2% for curettage, 36.7%, 43.3%, and 20.0% for cantharidin, 53.6%, 46.4%, and 0% for salicylic acid and glycolic acid, and 55.2%, 41.4%, and 3.4% for imiquimod. The rate of side effects was 4.7% for group 1, 18.6% for group 2, 53.5% for group 3, and 23.3% for group 4. Curettage was found to be the most efficacious treatment and had the lowest rate of side effects. It must be performed with adequate anesthesia and is a time-consuming procedure. Cantharidin is a useful bloodless alternative particularly in the office setting, but has moderate complications due to blisters and necessitated more visits in our experience. The topical keratolytic used was too irritating for children. Topical imiquimod holds promise but the optimum treatment schedule has yet to be determined. Finally, we believe that the ideal treatment for mollusca depends on the individual patient preference, fear, and financial status, distance from the office, and whether they have dermatitis or blood-borne infections.\n\n\nTitle 4:\nDouble-blind, randomized, placebo-controlled trial of the use of topical 10% potassium hydroxide solution in the treatment of molluscum contagiosum.\nAbstract 4:\nMolluscum contagiosum is a common viral infection of the skin that frequently affects children. Lesions take between 6 and 18 months to resolve spontaneously and are a source of great embarrassment to both caretakers and children, often affecting attendance at school and limiting social activity. Treatment options to date have been poorly tolerated by children but recent studies have suggested that potassium hydroxide may be beneficial. This double-blind, randomized, placebo-controlled study compared 10% potassium hydroxide with placebo (normal saline). Twenty patients, aged 2 to 12 years, were recruited. Parents applied a solution twice daily to lesional skin until signs of inflammation appeared. Children were examined by the same observer on days 0, 15, 30, 60, and 90. Seventy percent of children receiving topical potassium hydroxide cleared, compared with 20% in the placebo group. Further dosing studies are required to identify whether weaker concentrations of potassium hydroxide are as efficacious, with less irritancy.",
"role": "user"
},
{
"content": "No single intervention has been shown to be convincingly effective in the treatment of molluscum contagiosum. The update identified six new studies, most of them reporting on interventions not included in the original version. However, the conclusions of the review did not change.",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.10732
|
[
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nOBJECTIVE: No guidelines exist for the management of massive pulmonary embolism (PE) in COVID-19. We present a COVID-19 patient with refractory acute respiratory syndrome (ARDS), and life-threatening PE who underwent successful thrombolysis. CASE PRESENTATION: A previously healthy 47 year old male was admitted to our hospital due to severe COVID-19 pneumonia [confirmed by Real-Time-Polymerase-Chain-Reaction (RT-PCR)]. He had rapidly evolving ARDS [partial arterial pressure of oxygen to fractional inspired concentration of oxygen ratio: 175], and sepsis. Laboratory results showed lymphocytopenia, and increased D-dimer levels (7.7 mug/ml; normal: 0-0.5 mug/ml). The patient was treated in the intensive care unit. On day-1, ARDS-net/prone positioning ventilation, and empiric anti-COVID treatment integrating prophylactic anticoagulation was administered. On hospital day-2, the patient developed shock with worsening oxygenation. Point-of-care-ultrasound depicted a large thrombus migrating from the right atrium to the pulmonary circulation. Intravenous alteplase (100 mg over 2 h) was administered as rescue therapy. The patient made an uneventful recovery, and was discharged to home isolation (day-20) on oral rivaroxaban. CONCLUSION: Thrombolysis may have a critical therapeutic role for massive PE in COVID-19; however the risk of potential bleeding should not be underestimated. Point-of-care ultrasound has a pivotal role in the management of refractory ARDS in COVID-19.",
"role": "user"
},
{
"content": "[\"Case Report\"]",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_plos_single_doc_summ
|
science.scientific_lay_summarisation_plos_single_doc_summ.4009
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Cell-Cycle Dependence of Transcription Dominates Noise in Gene Expression\nArticle:\nAbstract:\nThe large variability in mRNA and protein levels found from both static and dynamic measurements in single cells has been largely attributed to random periods of transcription, often occurring in bursts. The cell cycle has a pronounced global role in affecting transcriptional and translational output, but how this influences transcriptional statistics from noisy promoters is unknown and generally ignored by current stochastic models. Here we show that variable transcription from the synthetic tetO promoter in S. cerevisiae is dominated by its dependence on the cell cycle. Real-time measurements of fluorescent protein at high expression levels indicate tetO promoters increase transcription rate ∼2-fold in S/G2/M similar to constitutive genes. At low expression levels, where tetO promoters are thought to generate infrequent bursts of transcription, we observe random pulses of expression restricted to S/G2/M, which are correlated between homologous promoters present in the same cell. The analysis of static, single-cell mRNA measurements at different points along the cell cycle corroborates these findings. Our results demonstrate that highly variable mRNA distributions in yeast are not solely the result of randomly switching between periods of active and inactive gene expression, but instead largely driven by differences in transcriptional activity between G1 and S/G2/M.\nIntroduction:\nAt the single-cell level, mRNA and protein levels of regulable genes are often found to be highly variable[1]–[5]. The resulting long-tailed mRNA and protein distributions are well-described by stochastic models[1],[5]–[7] of transcriptional bursting, where a promoter undergoes random and intermittent periods of highly active transcription. Real-time observations of transcription in multiple organisms appear consistent with this behavior[5],[8]–[14]. Thus, both static and dynamic views attribute much of the observed mRNA variability to the stochastic nature of reactions intrinsic to transcription. Consequently, the standard stochastic model of gene expression has been widely used to infer steady-state dynamics[1],[2],[15]–[17]. However, earlier studies examining the origin of variability in protein expression found such variability is not solely due to stochasticity in reactions intrinsic to gene expression, but also extrinsic factors. This was done by looking for correlations in expression between identical copies of one promoter[18]–[20] and/or between that promoter and a global or pathway-specific gene[21],[22]. Not only is the importance of extrinsic factors clear, without time-series measurements the intrinsic noise measured by these techniques may not completely be ascribed to stochastic reactions in gene expression[23],[24]. While global extrinsic factors have been suggested to largely impact translation[1], their influence on transcription and transcriptional bursting is unclear. The cell cycle has global effects on total protein and RNA synthesis that should play a role in transcription[12],[20],[25]. With few exceptions[20], most deterministic and stochastic models of gene regulation do not account for cell cycle variability. Using both dynamic real-time protein and static single molecule mRNA measurements in single cells, we show that much of the variability in a synthetic tetO promoter typical of noisy genes in yeast is driven by differences in transcription rate between G1 and S/G2/M.\nDiscussion:\nTranscriptional bursting, whereby a promoter occasionally transitions from a long-lived inactive to a short-lived active state that produces a burst of mRNA, is commonly invoked to explain the observed single-cell variability in mRNA numbers[1] of noisy genes. In contrast, we demonstrate that large differences in transcriptional activity between G1 and S/G2 that go beyond gene dosage effects drive much of the observed single-cell variability in mRNA numbers. Genome-wide studies in yeast[3],[35] have identified noisy promoters as those associated with strong TATA boxes and highly regulated by chromatin remodeling factors. The tetO promoters, whose core region is derived from the native CYC1 promoter[36], have similar characteristics. Likewise, constitutive, housekeeping promoters and highly expressed tetO promoters previously associated with low expression variability[2],[3],[31] exhibit only ∼2-fold changes in transcription throughout the cell cycle consistent with gene dosage effects. None of these promoters are classified as cell-cycle regulated[37]. While the cell cycle has been appreciated to be an important source of extrinsic noise, our findings suggest there may be a specific role beyond gene dosage for noisy genes that have not been associated with cell-cycle regulation. Transcriptional bursting may still occur, but it is not needed to explain most of the variability in mRNA levels given the variability in timing of the G1 to S transition[38],[39]. The heretofore unexplored connection between noisy gene expression and large differences in G1 and S/G2 transcriptional activity raises fundamental questions concerning its origin and prevalence amongst noisy genes in various organisms and its implications in stable gene network regulation. Studies monitoring transcripts in synchronized yeast cells with tiling microarrays identify ∼10% of genes that exhibit cell-cycle-dependent expression[37]. The mechanistic basis of their cycling, through regulation by cyclin-dependent transcription factors, is well-understood. The CYC1 gene, whose core promoter is present in the tetO promoters, is not part of this class. Because we observed cycle-dependent basal expression for tetO promoters in the absence of any tTA, the CYC1 gene might be expected to behave similarly. If we surmise that this cycle-dependent expression occurs at a majority of the ∼20% of genes whose expression has been identified in genome-wide studies as noisy[35], why has not previous work, which monitors expression in populations of synchronized cells, identified these genes? First, normalized microarray data represent a mole fraction of mRNA species in the population. As such, they will never identify, say, two-fold changes in mRNA abundance due to replication when normalized to the concurrent rise in total mRNA[40]. Second, we see large differences in transcription rate between G1 and S/G2 but because of the finite mRNA lifetime, differences in mRNA abundance are smaller. The discrepancies are much more pronounced with slower growth conditions( as the mRNA reaches the new steady-state in each growth phase), but the microarray studies were done in fast growth conditions. Third, under conditions with the largest cell-cycle phase-dependent differences in transcription, S/G2 transcription is a probabilistic event. Microarray experiments measure the population average mRNA mole fraction in each phase, and hence the relative difference between S/G2 and G1 will be quite low on average. Therefore, monitoring expression in single living cells through multiple cell cycles is crucial to observing cell-cycle-dependent transcription. Single-cell studies do not suffer from the averaging effects of microarray analysis. Still, our data alters the interpretation of static single-cell studies where mRNA/protein distributions are fit to stochastic models of gene expression to infer steady-state dynamics[1],[2],[15],[17]. This difficulty of using static data to pinpoint origins of variability has been anticipated[5],[23] although here we have shown that even static mRNA FISH data can reveal additional dynamic information by disaggregating mRNA distributions by cell-cycle phase. Consistent with our observations, control measurements made in a study examining cycle-dependent mRNA degradation kinetics using mRNA FISH show an approximately 2-fold increase in mRNA levels as cells progress through S/G2/M for the ADH1 and DOA1 promoters[25]. Our results suggest that burst sizes and burst frequencies obtained from fitting static mRNA distributions to a negative binomial distribution may be of limited use beyond the fact that they describe the first two moments of the distribution( and hence its noise). If we titrate tTA levels and infer burst statistics from the aggregate distribution, it appears that burst size increases at low expression levels, then burst frequency increases at high expression levels. This transition roughly corresponds to moving from little or no transcription in G1( with a burst frequency corresponding to one cell cycle) to robust G1 expression( Quinn, Maheshri, unpublished results). Because of the ease of grossly classifying cell-cycle phase in yeast, an exciting and straightforward exercise would be to reanalyze existing mRNA FISH datasets published from multiple labs to determine the prevalence of cycle-dependent expression. Morphological measurements might also be combined with two-color FISH measurements using a second transcript with known cell-cycle regulation[41]. Such an approach with high abundance transcripts has already revealed independent cell and metabolic cycles[42]. Recent real-time single-cell measurements of transcription may not have seen the cycle-dependent transcription we report for various reasons. In the one yeast study, mRNA expression of a housekeeping gene was measured in real-time with no accounting for cell-cycle phase[12]. In mammalian cells[14], transcriptional bursts with a refractory period were inferred from real-time measurements of luciferase protein levels expressed by multiple promoters, but again there was no accounting for cell-cycle phase. The bursts occurred on time scales much shorter than cell-cycle transitions, but revisiting the data still may reveal a cell-cycle phase dependence. Interestingly, real-time measurements of mRNA expression from two housekeeping promoters in undifferentiated single Dictyostelium cells do show a weak cell-cycle dependence, with the frequency of transcriptional burst or pulses dropping 2–3 fold from the beginning to the end of the cell cycle[43]. However, Dictyostelium lack a G1 period and have an extended G2[44],[45]; the reduction in expression later in the cell cycle might be due to mitotic repression of transcription, which is a well-established phenomenon in mammalian cells[46]. It remains unclear how widespread cycle-dependent transcription is in other organisms and awaits further study. What might be the mechanistic basis for the large differences in G1 and S/G2 transcriptional activity? At low expression tetO promoters exhibit transcriptional pulses that originate around the G1 to S transition when DNA replication occurs. S phase progression has been suggested to affect transcription[47] and has been established as important to( de) silence gene loci in a manner that either requires replication fork progression[48],[49] or not[50],[51]. Replication-dependent transcriptional activation of viral genes has been reported in transient transfection assays, and depends on trans activators that bind to either the proximal promoter or and enhancer region[52],[53]. In these cases, there does not appear to be cycle-dependent changes in the activity of the trans activators. Furthermore, in an in vitro system replication potentiates Gal4-VP16 transcriptional activation during S phase[54]. In our case, cycle-dependent activity of tTA can be ruled out because we observe the phenomenon even in the absence of tTA( Fig. 4A&B). In S phase, activity of the Cdc28 kinase leads to upregulation of the basal transcriptional machinery which has been shown to lead to similarly timed pulses of transcription in ∼200 yeast genes not classified as cycle-dependent, but these are enriched in housekeeping genes and CYC1 did not exhibit this behavior[55]. Therefore, we favor the hypothesis that temporary disruption of a repressed promoter's chromatin architecture during DNA replication could explain the pulse timing( Fig. 3B) and the increased tendency of tetO promoters to not activate until the G1 to S transition even when Pho4-tetR enters the nucleus in G1( Fig. 5H).( We observe a similar cycle-dependence at the native PHO5 promoter where gene activation tends to occur in early S/G2 – Zopf, Maheshri, unpublished results.) Because nucleosomes that are deposited following passage of the replication fork consist of an equivalent mixture of maternal and newly synthesized histones[56], as this chromatin matures there may exist a period permissive for transcription. Even if this permissive period is short-lived, once activated, transcription-mediated deposition of histone marks could maintain an active transcription state[57]. The return to inactive state in G1 might be brought about during mitosis. Repressive modifications in general transcriptional machinery, changes in histone marks, and chromatin condensation all contribute to mitotic repression of RNA transcription in higher eukaryotes[58]. In budding yeast, transcription was originally proposed to occur throughout mitosis as total RNA synthesis appeared to increase at and after nuclear migration[59], but recent work shows Cdc14 inhibiting RNA Pol I transcription during anaphase[60]. Still, mitotic repression of RNA Pol II transcription remains unclear, and we did observe an increased number of nascent spots of transcription in cells with large buds indicative of late G2 or M phase( Fig. S9). Exploring genetic and chemical perturbations in the activity of factors involved in chromatin maturation during DNA replication and mitosis for their effect on the cycle-dependent transcription pattern should aid in elucidating precise mechanisms. Our results should spur the development of new models that incorporate cell-cycle linked pulses of transcription and analyze its effects on the dynamics and function of genetic regulatory networks. Global extrinsic factors influence the behavior[22] and previous work identifies two important roles of cell division: in the stochastic partitioning of cellular contents[24] and in setting the timescale at which extrinsic fluctuations decay[61]. The latter especially has been incorporated in models of global extrinsic fluctuations[62]. Revised models in light of our results may be particularly exciting to develop in networks containing positive feedback loops, where switching from an OFF to ON state relies heavily on the statistics of transcription at low expression. Because here transcription appears prohibited in G1, this would introduce a sizeable refractory period to switching. Finally, since poorer nutrient conditions increase cell division time by extending G1 in yeast, prohibited G1 transcription may alter the dynamics of regulatory networks in cells in different growth conditions in unexpected ways.",
"role": "user"
},
{
"content": "There is an astonishing amount of variation in the number of mRNA and protein molecules generated from particular genes between genetically identical single cells grown in the same environment . Particularly for mRNA , the large variation seen from these “noisy” genes is consistent with the idea of transcriptional bursting where transcription occurs in random , intermittent periods of high activity . There is considerable experimental support for transcriptional bursting , and it is a primary feature of stochastic models of gene expression that account for variation . Still , it has long been recognized that variation , especially in protein levels , can occur because of global differences between genetically identical cells . We show that in budding yeast , mRNA variation is driven to a large extent by differences in the transcriptional activity of a noisy gene between different phases of the cell cycle . These differences are not because of specific cell-cycle regulation , and in some cases transcription appears restricted to certain phases , leading to pulses of mRNA production . These results raise new questions about the origins of transcriptional bursting and how the statistics of gene expression are regulated in a global way by the cell cycle .",
"role": "assistant"
}
] |
science.scicite_classification
|
science.scicite_classification.315
|
[
{
"content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: This validation can be readily done using a specific PCR and PCR product sequencing, for which miR-RACE can be prefered method due to its effectiveness in the validation of precise sequences, especially both ends of miRNAs [19,36].",
"role": "user"
},
{
"content": "Method",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.822
|
[
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: A region-based approach for fast object detection in videos.\n\nKeyphrases: object detection video\n\nDataset descriptions:\nCOVERAGE: COVERAGE contains copymove forged (CMFD) images and their originals with similar but genuine objects (SGOs). COVERAGE is designed to highlight and address tamper detection ambiguity of popular methods, caused by self-similarity within natural images.\nDoMSEV: The Dataset of Multimodal Semantic Egocentric Video (DoMSEV) contains 80-hours of multimodal (RGB-D, IMU, and GPS) data related to First-Person Videos with annotations for recorder profile, frame scene, activities, interaction, and attention.\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.\nYouTubeVIS: YouTubeVIS is a new dataset tailored for tasks like simultaneous detection, segmentation and tracking of object instances in videos and is collected based on the current largest video object segmentation dataset YouTubeVOS.\n\nOptions: A: COVERAGE B: DoMSEV C: COCO D: YouTubeVIS",
"role": "user"
},
{
"content": "COCO",
"role": "assistant"
}
] |
science.craftchem_ner
|
science.craftchem_ner.999
|
[
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Thevesicleformationgoesalongwithseveralotherchangesintheredbloodcelllikecytoskeletalrearrangementsandchangesinthephospholipidorientationinthecellularmembrane.",
"role": "user"
},
{
"content": "[\"phospholipid\"]",
"role": "assistant"
}
] |
science.ddi_ner
|
science.ddi_ner.428
|
[
{
"content": "Extract entities of these types from the text: [\"Drug\", \"Brand\", \"DrugGroup\", \"UnapprovedDrug\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nNo formal drug interaction studies have been performed with RAPTIVA. RAPTIVA should not be used with other immunosuppressive drugs. Acellular, live and live-attenuated vaccines should not be administered during RAPTIVA treatment. Drug/Laboratory Test Interactions Increases in lymphocyte counts related to the pharmacologic mechanism of action are frequently observed during RAPTIVA treatment.",
"role": "user"
},
{
"content": "{\"Brand\": [\"RAPTIVA\"], \"Drug\": [], \"DrugGroup\": [\"Acellular vaccines\", \"live-attenuated vaccines\", \"immunosuppressive drugs\", \"live vaccines\"], \"UnapprovedDrug\": []}",
"role": "assistant"
}
] |
science.scicite_classification
|
science.scicite_classification.6759
|
[
{
"content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: The patients were neurologically evaluated at baseline and at follow-up with the recently validated Scale for Assessment and Rating of Ataxia (SARA) [33].",
"role": "user"
},
{
"content": "Method",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.21414
|
[
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nInflammation is implicated in the development and severity of the coronavirus disease 2019 (COVID-19), as well as in the pathophysiology of diabetes. Diabetes, especially when uncontrolled, is also recognized as an important risk factor for COVID-19 morbidity and mortality. Furthermore, certain inflammatory markers [i.e. C-reactive protein (CRP), interleukin-6 (IL-6) and ferritin] were reported as strong predictors of worse outcomes in COVID-19 positive patients. The same biomarkers have been associated with poor glycemic control. Therefore, achieving euglycemia in patients with diabetes is even more important in the era of the COVID-19 pandemic. Based on the above, it is clinically interesting to elucidate whether antidiabetic drugs may reduce inflammation, thus possibly minimizing the risk for COVID-19 development and severity. The present narrative review discusses the potential anti-inflammatory properties of certain antidiabetic drugs (i.e. metformin, pioglitazone, sitagliptin, linagliptin, vildagliptin, alogliptin, saxagliptin, liraglutide, dulaglutide, exenatide, lixisenatide, semaglutide, empagliflozin, dapagliflozin, canagliflozin), with a focus on CRP, IL-6 and ferritin.",
"role": "user"
},
{
"content": "[\"Treatment\"]",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_elife_single_doc_summ
|
science.scientific_lay_summarisation_elife_single_doc_summ.421
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Mapping global environmental suitability for Zika virus\nArticle:\nAbstract:\nZika virus was discovered in Uganda in 1947 and is transmitted by Aedes mosquitoes, which also act as vectors for dengue and chikungunya viruses throughout much of the tropical world. In 2007, an outbreak in the Federated States of Micronesia sparked public health concern. In 2013, the virus began to spread across other parts of Oceania and in 2015, a large outbreak in Latin America began in Brazil. Possible associations with microcephaly and Guillain-Barré syndrome observed in this outbreak have raised concerns about continued global spread of Zika virus, prompting its declaration as a Public Health Emergency of International Concern by the World Health Organization. We conducted species distribution modelling to map environmental suitability for Zika. We show a large portion of tropical and sub-tropical regions globally have suitable environmental conditions with over 2. 17 billion people inhabiting these areas.\nIntroduction:\nZika virus( ZIKV) is an emerging arbovirus carried by mosquitoes of the genus Aedes( Musso et al., 2014). Although discovered in Uganda in 1947( Dick et al., 1952; Dick, 1953) ZIKV was only known to cause sporadic infections in humans in Africa and Asia until 2007( Lanciotti et al., 2008), when it caused a large outbreak of symptomatic cases on Yap island in the Federated States of Micronesia( FSM), followed by another in French Polynesia in 2013–14 and subsequent spread across Oceania( Musso et al., 2015a). In the 2007 Yap island outbreak, it was estimated that approximately 20% of ZIKV cases were symptomatic. While indigenous transmission of ZIKV to humans was reported for the first time in Latin America in 2015( Zanluca et al., 2015; World Health Organisation, 2015), recent phylogeographic research estimates that the virus was introduced into the region between May and December 2013( Faria et al., 2016). This recent rapid spread has led to concern that the virus is following a similar pattern of global expansion to that of dengue and chikungunya( Musso et al., 2015a). ZIKV has been isolated from 19 different Aedes species( Haddow et al., 2012; Grard et al., 2014), but virus has been most frequently found in Ae. aegypti( Monlun et al., 1992; Marchette et al., 1969; Smithburn, 1954; Pond, 1963; Faye et al., 2008; Foy et al., 2011b; WHO Collaborating Center for Reference and Research on Arboviruses and Hemorrhagic Fever Viruses: Annual Report, 1999). These studies were based upon ancestral African strains of ZIKV, but the current rapid spread of ZIKV in Latin America is indicative of this highly efficient arbovirus vector( Marcondes and Ximenes, 2015). The relatively recent global spread of Ae. albopictus( Benedict et al., 2007; Kraemer et al., 2015c) and the rarity of ZIKV isolations from wild mosquitoes may also partially explain the lower frequency of isolations from Ae. albopictus populations. Whilst virus transmission by Ae. albopictus and other minor vector species has normally resulted in only a small number of cases( Kutsuna et al., 2015; Roiz et al., 2015), these vectors do pose the threat of limited transmission( Grard et al., 2014). The wide geographic distribution of Ae. albopictus combined with the frequent virus introduction via viraemic travellers( McCarthy 2016; Bogoch et al., 2016; Morrison et al., 2008; Scott and Takken, 2012), means the risk for ZIKV infection via this vector must therefore also be considered in ZIKV mapping. The fact that ZIKV reporting was limited to a few small areas in Africa and Asia until 2007 means that global risk mapping has not, until recently, been a priority( Pigott et al., 2015b). Recent associations with Guillain-Barré syndrome in adults and microcephaly in infants born to ZIKV-infected mothers( World Health Organisation, 2015; Martines et al., 2016) have revealed that ZIKV could lead to more severe complications than the mild rash and flu-like symptoms that characterize the majority of symptomatic cases( Gatherer and Kohl, 2016). Considering these potentially severe complications and the rapid expansion of ZIKV into previously unaffected areas, the global public health community needs information about those areas that are environmentally suitable for transmission of ZIKV to humans. Being a closely related flavivirus to DENV, there is furthermore the potential for antigen-based diagnostic tests to exhibit cross-reactivity when IgM ELISA is used for rapid diagnosis. Although ZIKV-specific serologic assays are being developed by the U. S. Centers for Disease Control, currently the only method of confirming ZIKV infection is by using PCR on acute specimens( Lanciotti et al., 2008, Faye et al., 2008). Awareness of suitability for transmission is essential if proper detection methods are to be employed. In this paper, we use species distribution modelling techniques that have been useful for mapping other vector-borne diseases such as dengue( Bhatt et al., 2013), Leishmaniasis( Pigott et al., 2014b), and Crimean-Congo Haemorrhagic Fever( Messina et al., 2015b) to map environmental suitability for ZIKV. The environmental niche of a disease can be identified according to a combination of environmental conditions supporting its presence in a particular location, with statistical modelling then allowing this niche to be described quantitatively( Kraemer et al., 2016). Niche modelling uses records of known disease occurrence alongside hypothesized environmental covariates to predict suitability for disease transmission in regions where it has yet to be reported( Elith and Leathwick, 2009). Contemporary high spatial-resolution global data representing a variety of environmental conditions allows for these predictions to be made at a global scale( Hay et al., 2006).\nDiscussion:\nIn this study, we produced the first global high spatial-resolution map of environmental suitability for ZIKV transmission to humans using an assembly of known records of ZIKV occurrence and environmental covariates in a species distribution modelling framework. While it is clear that much remains to be understood about ZIKV, this first map serves as a baseline for understanding the change in the geographical distribution of this globally emerging arboviral disease. Knowledge of the potential distribution can encourage more vigilant surveillance in both humans and Aedes mosquito populations, as well as help in the allocation of limited resources for disease prevention. Public health awareness campaigns and advice for mitigation of individual risk can also be focused in the areas we have predicted to be highly suitable for ZIKV transmission, particularly during the first wave of infection in a population. The maps we have presented may also inform existing travel advisories for pregnant women and other travellers. The maps and underlying data are freely available online via figshare( http://www. figshare. com).",
"role": "user"
},
{
"content": "Zika virus is transmitted between humans by mosquitoes . The majority of infections cause mild flu-like symptoms , but neurological complications in adults and infants have been found in recent outbreaks . Although it was discovered in Uganda in 1947 , Zika only caused sporadic infections in humans until 2007 , when it caused a large outbreak in the Federated States of Micronesia . The virus later spread across Oceania , was first reported in Brazil in 2015 and has since rapidly spread across Latin America . This has led many people to question how far it will continue to spread . There was therefore a need to define the areas where the virus could be transmitted , including the human populations that might be risk in these areas . Messina et al . have now mapped the areas that provide conditions that are highly suitable for the spread of the Zika virus . These areas occur in many tropical and sub-tropical regions around the globe . The largest areas of risk in the Americas lie in Brazil , Colombia and Venezuela . Although Zika has yet to be reported in the USA , a large portion of the southeast region from Texas through to Florida is highly suitable for transmission . Much of sub-Saharan Africa ( where several sporadic cases have been reported since the 1950s ) also presents an environment that is highly suitable for the Zika virus . While no cases have yet been reported in India , a large portion of the subcontinent is also suitable for Zika transmission . Over 2 billion people live in Zika-suitable areas globally , and in the Americas alone , over 5 . 4 million births occurred in 2015 within such areas . It is important , however , to recognize that not all individuals living in suitable areas will necessarily be exposed to Zika . We still lack a great deal of basic epidemiological information about Zika . More needs to be known about the species of mosquito that spreads the disease and how the Zika virus interacts with related viruses such as dengue . As such information becomes available and clinical cases become routinely diagnosed , the global evidence base will be strengthened , which will improve the accuracy of future maps .",
"role": "assistant"
}
] |
science.gnormplus_ner
|
science.gnormplus_ner.337
|
[
{
"content": "Extract all unique entities of these types from the text: [\"Gene\"].\n\nOutput a JSON object of the format: {\"Gene\": [\"SSX\", ...]}.\n\nText:\nRarity of IgH translocations in Waldenstrom macroglobulinemia. Comparatively little is known of the cytogenetics of Waldenstrom macroglobulinemia (WM). This is primarily due to the low proliferation of the clonal B cells, which precludes conventional karyotyping in many cases. Translocations involving the immunoglobulin heavy chain (IGH) gene at 14q32 are characteristic of many B-cell lymphomas and myelomas. Initial reports suggested that the t(9;14) was characteristic of lymphoplasmacytic lymphoma (the underlying pathological diagnosis in WM), but subsequent studies have failed to confirm the uniqueness of the translocation. To clarify this, we examined 69 cases of WM with interphase fluorescence in situ hybridization and failed to demonstrate an IgH translocation in 67 (97%). We conclude that IGH translocations are not a feature of WM, and the implications of this finding are discussed.",
"role": "user"
},
{
"content": "{\"Gene\": [\"IGH\", \"immunoglobulin heavy chain\", \"IgH\"]}",
"role": "assistant"
}
] |
science.acl_arc_intent_classification
|
science.acl_arc_intent_classification.382
|
[
{
"content": "Classify the intent of this citation from an NLP research paper. \n\nYour answer must be one word from: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. No other text allowed.\n\nSection Title:\nexperiments\n\nContext before:\nMany provide graphical user interfaces (GUI) for manual annotation (e.g. General Architecture for Text Engineering (GATE) (Cunningham et al., 1997) and the Alembic Workbench (Day et al., 1997)) as well as NLP tools and resources that can be manipulated from the GUI. There are a number of generalised NLP systems in the literature.\n\nCitation:\nMany provide graphical user interfaces ( GUI ) for manual annotation ( e.g. General Architecture for Text Engineering ( GATE ) ( Cunningham et al. , 1997 ) and the Alembic Workbench ( Day et al. , 1997 ) ) as well as NLP tools and resources that can be manipulated from the GUI .\n\nContext after:\nFor instance, GATE currently provides a POS tagger, named entity recogniser and gazetteer and ontology editors (Cunningham et al., 2002). GATE goes beyond earlier systems by using a component-based infrastructure (Cunningham, 2000) which the GUI is built on top of. This allows components to be highly configurable and simplifies the addition of new components to the system. A number of stand-alone tools have also been developed.",
"role": "user"
},
{
"content": "Background",
"role": "assistant"
}
] |
science.bioasq_general_qa
|
science.bioasq_general_qa.766
|
[
{
"content": "Answer the following question using the provided context. Only provide the answer without any additional text.\n\nQuestion: What is epitranscriptomics?\nContext: Here we provide a perspective on necessary and expected developments in the fast expanding area of RNA modifications, termed epitranscriptomics.",
"role": "user"
},
{
"content": "Epitranscriptomics is the fast expanding area of RNA modifications.",
"role": "assistant"
}
] |
science.ddi_ner
|
science.ddi_ner.140
|
[
{
"content": "Extract entities of these types from the text: [\"Drug\", \"Brand\", \"DrugGroup\", \"UnapprovedDrug\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nCholinergic role in alcohol's effects on evoked potentials in visual cortex of the albino rat. Photic evoked potentials were recorded from the visual cortex of chronically implanted albino rats. Since photic evoked potential components are representations of neural pathways which are activated during photic stimulation, study of the effects of alcohol on these components may help to trace pathways which are affected by alcohol. In the present study, evoked potentials were recorded at 5, 20, and 40 min following IP injections of saline, ethanol (2.0 g/kg), physostigmine (0.6 mg/kg) or atropine (15.0 mg/kg) on separate days. Ethanol depressed the amplitudes of most evoked potential components in comparison to saline administration. Component P2, however, was increased in amplitude. Physostigmine briefly reduced the amplitude of most components, including P2. In contrast, atropine increased the amplitudes of components P1 and P2, while decreasing components N1, N2 and N3 for varying durations of time. Physostigmine pretreatment augmented the depressant effect of alcohol on the early components P1 and N1, while attenuating alcohol's influence on components P2 and P3. Pretreatment with atropine likewise further reduced the amplitudes of components P1 and N1, and produced a similar effect on component N3. Atropine, either alone or in combination with alcohol, produced approximately the same degree of enhancement of component P2. In comparison to saline values, all three agents produced reliable increases in peak latency for most of the components, with only N3 showing no effects. The amplitude data from this study suggest that ethanol's augmentation of component P2 may result, at least in part, from alterations in cholinergic functions.",
"role": "user"
},
{
"content": "{\"Brand\": [], \"Drug\": [\"Physostigmine\", \"Ethanol\", \"physostigmine\", \"ethanol\", \"alcohol\", \"atropine\", \"Atropine\"], \"DrugGroup\": [], \"UnapprovedDrug\": []}",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.24784
|
[
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nGeriatric patients seem to be the most vulnerable group in COVID-19. These patients are usually characterized by impaired mobilization and malnutrition. In addition, obesity has been correlated with increased mortality rates after COVID-19 infection, highlighting the role of nutrition in prognosis of COVID-19 as well. In the past, several indices of nutritional status (GNRI) and functional status (ECOG performance status, Barthel Index, Handgrip Strength) have demonstrated a prognostic ability for hospitalized patients with influenza-like respiratory infections from coronavirus, metapneumovirus, parainfluenza and rhinovirus. Our hypothesis suggests that the previously mentioned nutritional and functional status indices, combined with the pneumonia severity index (CRB-65), could be useful in prognosis of morbidity and mortality of the elderly after the novel COVID-19 infection. Our hypothesis, is the first in the literature, which suggests a prognostic association between nutritional status of patients and COVID-19 infection, offering a quick and low-cost prognostic tool for COVID-19 in the elderly.",
"role": "user"
},
{
"content": "[\"Treatment\", \"Diagnosis\"]",
"role": "assistant"
}
] |
science.chemsum_single_document_summarization
|
science.chemsum_single_document_summarization.67527
|
[
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nThree-Coordinate and Four-Coordinate Cobalt Hydride Complexes That React with Dinitrogen\n\nPaper sections:\n\n<p>Complexes of a transition metal (defined here as a metal with a partially filled d shell) having only three bonds to the metal are interesting because the orbital energies, spin states, and reaction pathways can be different than traditional complexes.1 Isolating three-coordinate complexes invariably depends on the use of extremely bulky supporting ligands, which protect the metal center through steric effects. However, this strategy might seem to be incompatible with three-coordinate hydride complexes, because H– is the smallest possible ligand. Accordingly, no three-coordinate hydride complexes are known.2 New kinds of hydride complexes are desired because of the many roles for hydrides in organometallic chemistry and catalysis.3</p><p>Using iron complexes, we recently introduced the use of the very bulky bidentate β-diketiminate ligand L (L = 2,2,6,6-tetramethyl-3,5-bis(2,4-diisopropylphenylimido)hept-4-yl) for enabling the isolation of three-coordinate complexes in which one of the three ligands is small (e.g. halide, CH3).4 Here, we report that L can be used to stabilize the first crystallographically characterized three-coordinate hydride complex of any transition metal. We also report that this cobalt-hydride complex and another related complex react with N2 at room temperature and atmospheric pressure, through the bimetallic reductive elimination of H2.</p><p>Figure 1 shows the syntheses and structures of dimeric cobalt(II) hydride (1) and cobalt(I) hydride (2) complexes, which come from adding different amounts of KHBEt3 to toluene solutions of the three-coordinate cobalt(II) complex LCoCl under Ar.5 Addition of 1 equiv of KHBEt3 to LCoCl gives [LCo(μ-H)]2 (1) in 72% yield. Although we were not able to completely free 1 from impurities (see Supporting Information), several forms of characterization have been possible. The X-ray crystal structure of 1 reveals that it has two hydride ligands (located in the difference Fourier map) that bridge diketiminate-bound cobalt centers. The metal coordination and geometry closely resemble those for the iron(II) complex [LFe(μ-H)]26 and a dimeric β-diketiminate nickel(II) hydride complex recently reported by Limberg.7 The cobalt atoms in 1 are separated by 2.476(5) Å, which is intermediate between the metal-metal distances in the iron (2.624(2) Å) and nickel (2.3939(6) Å) analogues. The presence of the hydride ligands in 1 was confirmed through the reaction of a toluene solution of 1 with 2 equiv of cyclohexene to give the cobalt(II) cyclohexyl product LCo(C6H11), which results from [1,2]-addition of the cobalt hydride to the C-C double bond.</p><p>Reaction of LCoCl with 2 equiv of KHBEt3 under Ar gave compound 2, with presumed loss of H2, in 70% yield. Compound 2 is very unusual. Its X-ray crystal structure reveals two nearly parallel three-coordinate cobalt units related by a pseudo-inversion center. The high quality of the crystallographic data enabled refinement of the positions of the hydrogen atoms, giving Co-H distances of 1.81(3) Å. The cobalt geometry is trigonal-planar, and each H atom lies near the pseudo-mirror plane of the β-diketiminate ligand on the same cobalt atom (N-Co-H angles ranging from 128° to 134°). The two H atoms are separated by 3.02(3) Å, and the two cobalt atoms by 5.7386(7) Å, showing that there is no direct connection between the cobalt-bound atoms. Instead, the halves of the molecule are held together by K+ ions that form cation-π interactions with the aryl rings of the β-diketiminate ligands. The potassium ions are also close to the hydride ligands (K-H 2.60(2) Å and 2.67(2) Å).</p><p>The three-coordinate cobalt ions in complex 2 are high-spin cobalt(I), as shown by the paramagnetically shifted 1H NMR spectrum and the solution magnetic moment of μeff = 5.6(2) μB per dimeric molecule of 2. Complex 2 is soluble and gives similar 1H NMR spectra in cyclohexane, benzene, and THF, suggesting that the alkali metals remain bound in solution. The freezing-point depression of a solution of 2 in naphthalene indicated a molecular weight of 1140 ± 200 (3σ), supporting the dimeric formulation in solution. Seven β-diketiminate resonances are observed in its 1H NMR spectrum in C6D6 from 200-353 K (the hydrides are not observed due to fast relaxation), showing that the β-diketiminate ligands of 2 have averaged C2v symmetry in solution. Therefore, there is a low-energy mechanism that enables the molecule to reach an arrangement in which the CoN2H units are transiently coplanar, without dissociation of the molecule into halves.</p><p>Solutions of 1 and 2 in aromatic and hydrocarbon solvents show no signs of decomposition by 1H NMR when heated to 100 °C for several days under an Ar atmosphere. On the other hand, exposure of room-temperature solutions of each compound to an atmosphere of purified N2 in pentane, diethyl ether, or toluene leads to the growth of resonances in the 1H NMR spectrum that are characteristic of the analogous bimetallic dinitrogen complexes (Scheme 1). These cobalt dinitrogen complexes have been characterized separately.5b The reaction of 1 with N2 was complete in less than 1 h, giving 88% spectroscopic yield of LCoNNCoL. H2, the other product of the reaction, was detected by gas chromatography in 80% yield. The reaction of 2 with N2 gave K2[LCoNNCoL] over several hours, in 90% spectroscopic and isolated yield. In the latter reaction, H2 was detected in 83% yield. The reactions in Scheme 1 occur at roughly the same rate in the dark as in ambient light.8</p><p>The reactions to produce H2 are formal reductive eliminations: the dicobalt(II) complex 1 leads to the dicobalt(I) dinitrogen complex LCoNNCoL, and the dicobalt(I) complex 2 gives the formally dicobalt(0) dinitrogen complex K2[LCoNNCoL]. In the latter complex, the N-N distance is 1.22 Å, indicating that the dinitrogen ligand is best described as [N=N]2–.5b Thus, using this picture, the electrons from the reductive elimination of H2 end up in the π* orbital of bound N2. This is interesting in the context of N2 binding and activation.9 Although H2 reductive elimination from metastable hydride complexes has been used previously as a route to dinitrogen complexes,10,11,12,13 there is only one literature example of N2 binding directly from a crystallographically verified hydride complex.10c This H2-N2 exchange is of interest in the context of catalytic N2 reduction, because the formation of N2 complexes in this way avoids the use of harsh reducing agents.14</p><p>We explored the mechanism of H2 reductive elimination by treating a mixture of the isotopologues K2[LCo(μ-H)]2 (2) and K2[LCo(μ-D)]2 (2-D) with N2 for 2 days. H2 and D2 were present in the headspace, and no HD was detected. This result indicates that (a) 2 does not dissociate in solution at room temperature, and (b) the elimination of H2 from 2 is an intramolecular process. The analogous reaction of 1 and 1-D with N2 gave a significant amount of HD, probably through the pre-equilibration of isotopologues of 1 through monomer-dimer equilibrium.</p><p>In conclusion, we have crystallographically characterized the first three-coordinate transition-metal hydride complex, K2[LCo(μ-H)]2 (2). The hydride ligands in this species are labile, eliminating as H2 upon the addition of N2. It is surprising that 2 readily reacts with N2 but does not react at room temperature with THF or arenes, suggesting that the approach of additional donors to cobalt is sterically restricted by the potassium-bound diketiminate ligands.</p><p>Formation and structures of unsaturated cobalt hydride complexes, using 50% thermal ellipsoids. Carbon-bound hydrogen atoms are omitted for clarity. All cobalt-bound hydrogens were refined with isotropic thermal parameters. Selected bond lengths and bond angles follow; because compound 1 has three crystallographically independent dimers, ranges are listed here (details are in the Supporting Information). 1: Co-Co 2.472-2.481 Å, Co-N 1.962-1.993 Å, N-Co-N 95.4-96.5°. For 2: Co1-Co2 5.7386(7) Å, Co1-H1 1.84(2) Å, Co1-N11 1.9162(13) Å, Co1-N21 1.9164(12) Å, N11-Co1-N21 96.73(6)°, N11-Co1-H1 128.2(7)°, N21-Co1-H1 134.1(7)°, Co2-H2 1.78(2) Å, Co2-N14 1.9106(13) Å, Co2-N24 1.9121(13) Å, N14-Co2-N24 96.59(6)°, N14-Co2-H2 133.5(7)°, N24-Co2-H2 129.4(7)°.</p><p>Side view of the core of 2, showing the relative orientation of the two CoN2H planes.</p><p>Reactions of the Low-Coordinate Cobalt Hydride Complexes with Dinitrogen (R = isopropyl)</p>",
"role": "user"
},
{
"content": "We report the formation and N2 reactivity of novel cobalt hydride complexes supported by bulky \\xce\\xb2-diketiminate ligands (L). Addition of KHBEt3 to LCoCl gives [LCo(\\xce\\xbc-H)]2 (1) or K2[LCoH]2 (2), depending on the amount of borohydride used. Compound 2 is the first example of a crystallographically characterized hydride complex in which a transition metal is three-coordinate. Both 1 and 2 react with N2 at room temperature to give dinuclear N2 complexes with loss of H2.",
"role": "assistant"
}
] |
science.data_reco_mcq_mc
|
science.data_reco_mcq_mc.1528
|
[
{
"content": "Based on the dataset descriptions below, which datasets would be suitable for the following research question? Your response should be a JSON array.\n\nQuestion: We present a BERT-based model that takes as input a multimodal input and is pretrained\n\nKeywords: visual question answering images text\n\nDataset descriptions:\nVCR: Visual Commonsense Reasoning (VCR) is a large-scale dataset for cognition-level visual understanding. Given a challenging question about an image, machines need to present two sub-tasks: answer correctly and provide a rationale justifying its answer.\nOpenWebText: OpenWebText is an open-source recreation of the WebText corpus. The text is web content extracted from URLs shared on Reddit with at least three upvotes.\nICL-NUIM: The ICL-NUIM dataset aims at benchmarking RGB-D, Visual Odometry and SLAM algorithms. Two different scenes (the living room and the office room scene) are provided with ground truth.\nDAQUAR: DAQUAR (DAtaset for QUestion Answering on Real-world images) is a dataset of human question answer pairs about images.\nHDR+ Burst Photography Dataset: The dataset consists of 3640 bursts (made up of 28461 images in total), organized into subfolders, plus the results of an image processing pipeline. Each burst consists of the raw burst input (in DNG format) and certain metadata not present in the images, as sidecar files.\nFlickr30k: The Flickr30k dataset contains 31,000 images collected from Flickr, together with 5 reference sentences provided by human annotators.\n\nOptions: A: VCR B: OpenWebText C: ICL-NUIM D: DAQUAR E: HDR+ Burst Photography Dataset F: Flickr30k",
"role": "user"
},
{
"content": "[\"VCR\", \"Flickr30k\"]",
"role": "assistant"
}
] |
science.craftchem_ner
|
science.craftchem_ner.8800
|
[
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: AS,aorticsac,arrowspointtoclustersofapoptoticcellssurroundingtheaorticsac.",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.1952
|
[
{
"content": "Which dataset would be most relevant for this research query?\n\nQuery: I am doing 3D shape completion from depth maps.\n\nKeyphrases: 3d shape completion depth maps\n\nDataset descriptions:\nModelNet: The ModelNet40 dataset contains synthetic object point clouds. As the most widely used benchmark for point cloud analysis, ModelNet40 is popular because of its various categories, clean shapes, well-constructed dataset, etc.\nITOP: The ITOP dataset consists of 40K training and 10K testing depth images for each of the front-view and top-view tracks. This dataset contains depth images with 20 actors who perform 15 sequences each and is recorded by two Asus Xtion Pro cameras.\n3D Shapes Dataset: 3dshapes is a dataset of 3D shapes procedurally generated from 6 ground truth independent latent factors. These factors are floor colour, wall colour, object colour, scale, shape and orientation.\nMSR ActionPairs: This is a 3D action recognition dataset, also known as 3D Action Pairs dataset. The actions in this dataset are selected in pairs such that the two actions of each pair are similar in motion (have similar trajectories) and shape (have similar objects); however, the motion-shape relation is different.\n\nOptions: A: ModelNet B: ITOP C: 3D Shapes Dataset D: MSR ActionPairs",
"role": "user"
},
{
"content": "ModelNet",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.9255
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nThe evaluation of interactive machine learning systems remains a difficult task. These systems learn from and adapt to the human, but at the same time, the human receives feedback and adapts to the system. Getting a clear understanding of these subtle mechanisms of co-operation and co-adaptation is challenging. In this chapter, we report on our experience in designing and evaluating various interactive machine learning applications from different domains. We argue for coupling two types of validation: algorithm-centered analysis, to study the computational behaviour of the system; and human-centered evaluation, to observe the utility and effectiveness of the application for end-users. We use a visual analytics application for guided search, built using an interactive evolutionary approach, as an exemplar of our work. Our observation is that human-centered design and evaluation complement algorithmic analysis, and can play an important role in addressing the \"black-box\" effect of machine learning. Finally, we discuss research opportunities that require human-computer interaction methodologies, in order to support both the visible and hidden roles that humans play in interactive machine learning.\n\nCited Abstract(s):\n[1]: Relevance feedback has a history in information retrieval that dates back well over thirty years (c.f [SL96]). Relevance feedback is typically used for query expansion during short-term modeling of a user's immediate information need and for user profiling during long-term modeling of a user's persistent interests and preferences. Traditional relevance feedback methods require that users explicitly give feedback by, for example, specifying keywords, selecting and marking documents, or answering questions about their interests . Such relevance feedback methods force users to engage in additional activities beyond their normal searching behavior . Since the cost to the user is high and the benefits are not always apparent, it can be difficult to collect the necessary data and the effectiveness of explicit techniques can be limited.",
"role": "user"
},
{
"content": "Broadly speaking, human feedback to machine learning algorithms can be either or . The difference between these two mechanisms stems from the field of Information Retrieval (IR). In the case of implicit feedback, humans do not assess relevance for the benefit of the IR system, but rather to fulfill their own task. Besides, they are not necessarily aware that their assessment is being used for relevance feedback [1] . In contrast, for explicit feedback, humans indicate their assessment via a suitable interface, and are aware that their feedback is interpreted for relevance judgment. Whereas implicit feedback is from human interactions with the system, explicit feedback is directly provided by humans.",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_elife_single_doc_summ
|
science.scientific_lay_summarisation_elife_single_doc_summ.4102
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Mitochondrial Ca2+ and membrane potential, an alternative pathway for Interleukin 6 to regulate CD4 cell effector function\nArticle:\nAbstract:\nIL-6 plays an important role in determining the fate of effector CD4 cells and the cytokines that these cells produce. Here we identify a novel molecular mechanism by which IL-6 regulates CD4 cell effector function. We show that IL-6-dependent signal facilitates the formation of mitochondrial respiratory chain supercomplexes to sustain high mitochondrial membrane potential late during activation of CD4 cells. Mitochondrial hyperpolarization caused by IL-6 is uncoupled from the production of ATP by oxidative phosphorylation. However, it is a mechanism to raise the levels of mitochondrial Ca2+ late during activation of CD4 cells. Increased levels of mitochondrial Ca2+ in the presence of IL-6 are used to prolong Il4 and Il21 expression in effector CD4 cells. Thus, the effect of IL-6 on mitochondrial membrane potential and mitochondrial Ca2+ is an alternative pathway by which IL-6 regulates effector function of CD4 cells and it could contribute to the pathogenesis of inflammatory diseases.\nIntroduction:\nInterleukin 6( IL-6) is an inflammatory cytokine that is elevated in several autoimmune and inflammatory disorders, including rheumatoid arthritis( RA)( Kishimoto, 2005). Inhibition of IL-6 signaling by an anti-IL-6R antibody has been shown to be a highly effective therapy in treating patients with RA( Tanaka and Kishimoto, 2012). IL-6 plays crucial role in regulating CD4 T helper cell differentiation and cytokine production( Dienz and Rincon, 2009). It enhances Th2 differentiation through an auto-feedback loop by upregulating autocrine IL-4 production( Rincon et al., 1997; Diehl et al., 2002). IL-6 inhibits IFNγ production and Th1 differentiation( Diehl et al., 2000). In combination with TGFβ, IL-6 also contributes to the differentiation of Th17 cells( Bettelli et al., 2006; Ivanov et al., 2006; Zhou et al., 2007). IL-6 inhibits regulatory T cell function and downregulates Foxp3 expression( Pasare and Medzhitov, 2003; Dienz and Rincon, 2009). In addition, IL-6 alone, without the need of TGFβ, induces IL-21 expression, a mechanism by which it promotes the generation of follicular T helper( Tfh) cells( Nurieva et al., 2008; Suto et al., 2008; Dienz et al., 2009; Diehl et al., 2012). IL-6 binds to its membrane receptor, which triggers signaling through gp130, a common transducer that activates Jak/Stat3 and Ras/MAPK pathways in T cells( Boulanger et al., 2003; Heinrich et al., 2003; Kishimoto, 2005). Stat3 is a transcription factor present in cytosol but translocates to the nucleus upon stimulation where it mediates the expression of numerous genes. Stat3 has been previously implicated in the regulation of genes involved in cell survival and proliferation by directly binding to multiple survival genes, including Bcl2, Fos, Jun, Mcl1 and Fosl2( Hirano et al., 2000; Bourillot et al., 2009; Durant et al., 2010; Carpenter and Lo, 2014). Additionally, IL-6-dependent Stat3 activation plays an important role in the expression of several cytokine genes, including Il21 and Il17( Mathur et al., 2007; Zhou et al., 2007; Dienz et al., 2009). In addition to its role as a nuclear transcription factor, Stat3 has been found within mitochondria in liver, heart and some cell lines where it enhances the mitochondrial respiratory chain activity( Gough et al., 2009; Wegrzyn et al., 2009). However, no studies have addressed whether IL-6 regulates mitochondrial function through Stat3. IL-6 has for long been associated with metabolic changes and high levels of IL-6 in serum have been correlated with BMI( Mohamed-Ali et al., 1997; Fried et al., 1998; Vgontzas et al., 2000). Recent studies indicate that IL-6 is linked to glucose homeostasis in adipose tissue and it participates in the switch from white to brown fat tissue in cancer-induced cachexia( Stanford et al., 2013; Petruzzelli et al., 2014). However, it remains unclear whether IL-6 has a direct effect on the metabolism of cells. But in the context of ischemia-reperfusion injury in cardiomyocytes, IL-6 has been shown to maintain mitochondrial membrane potential( MMP) in cardiomyocytes( Smart et al., 2006). Despite the known role of IL-6 in the CD4 cell effector function, no studies have addressed whether IL-6 has an effect on mitochondrial function in CD4 cells. Here we show that IL-6 plays an important role in maintaining MMP late during CD4 cell activation in a Stat3-dependent manner. IL-6-mediated mitochondrial hyperpolarization is, however, uncoupled from the oxidative phosphorylation and ATP production. Instead, IL-6 uses the high MMP to raise mitochondrial Ca2+ and, consequently, cytosolic Ca2+ levels to promote cytokine expression late during activation. Thus we have identified a previously undescribed mechanism by which IL-6 regulates CD4 cell effector function.\nDiscussion:\nMost of the functions of IL-6 in CD4 cells have been assigned to a regulatory role on gene expression through Stat3 as a transcription factor. However, in the light of studies indicating that Stat3 localizes in mitochondria where it regulates the mitochondrial respiratory chain through association with Complex I( Gough et al., 2009; Wegrzyn et al., 2009), it was also possible that IL-6 could have an effect on mitochondria in CD4 cells. Our studies here show for the first time that IL-6 maintains mitochondrial hyperpolarization late during activation of CD4 cells and this has an impact in mitochondrial Ca2+ and, thereby cytosolic Ca2+. We also show that the effect of IL-6 on mitochondrial Ca2+ and baseline cytosolic Ca2+ requires the presence of Stat3, but it is independent of its role as transcription factor. In recent years, growing interest has been focused on mitochondrial biology in T cells. Bioenergetic profiling of T cells has revealed that T cell metabolism changes dynamically during activation( Wang and Green, 2012; Pearce et al., 2013). Naive T cells maintain low rates of glycolysis and predominantly oxidize glucose-derived pyruvate via OXPHOS, or engage fatty acid oxidation( FAO). After activation, they rapidly switch to anabolic growth and biomass accumulation. This adaption to aerobic glycolysis is specifically required for effector functions in T cells( Chang et al., 2013). IL-2 and IL-15 have been reported to regulate mitochondrial respiration and the balance between glycolysis and oxidative phosphorylation( van der Windt et al., 2012). IL-2 has been shown to support aerobic glycolysis, while IL-15 increases spared respiratory capacity and oxidative metabolism by enhancing mitochondrial biogenesis and FAO in CD8 cells( Pearce et al., 2009; van der Windt et al., 2012). IL-6 has been recently shown to regulate glucose homeostasis in myeloid cells and induce the switch from white adipose tissue to brown fat in cancer induced cachexia( Mauer et al., 2014; Petruzzelli et al., 2014). Here we show that IL-6 enhances the MMP in CD4 cells. However, this is uncoupled from oxidative phosphorylation( i. e. ATP synthesis). In addition, IL-6 does not alter the balance between glycolysis and oxidative glycolysis during activation. Instead, we show that a sustained MMP elicited by IL-6 leads to an effect on mitochondrial Ca2+. No other studies have linked cytokine effects to mitochondrial Ca2+ in CD4 cells. While endoplasmic reticulum( ER)-derived Ca2+ has been extensively studied in T cells, less is known about mitochondrial Ca2+ homeostasis in T cells. Mitochondrial Ca2+ has been previously shown to modulate store-operated calcium signaling early upon T cell activation at the immunological synapse( Hoth et al., 1997; Quintana et al., 2007). Here we show that IL-6 uses MMP to sustain elevated levels of mitochondrial Ca2+ late during activation and, consequently, elevated levels of cytosolic Ca2+. We have previously shown that the expression of IP3Rs is downregulated during the activation of CD4 cells( Nagaleekar et al., 2008). It is therefore possible that the source of Ca2+ in CD4 cells is reprogramed during activation. ER- IP3R is the main source of Ca2+ during early activation of naive CD4 cells at the synapse. However, mitochondrial Ca2+ could be the major source to sustain cytosolic Ca2+ in activated CD4 cells. Our data indicate that IL-6 sustains cytosolic Ca2+ late during activation by increasing the MMP and mitochondrial Ca2+. This provides a potential mechanism by which Tfh cells have increased free cytosolic calcium levels( Shulman et al., 2014). More importantly, we show here for the first time that mitochondrial Ca2+ plays a key role in promoting increased production of cytokine by effector CD4 cells. Although IP3R-mediated Ca2+ release is essential for the initial induction of cytokine gene expression( Feske, 2007), we have previously shown that IP3R-mediated Ca2+ is not responsible for late production of cytokines by activated CD4 cells( Nagaleekar et al., 2008). Thus, the source of Ca2+ for cytokine production is also reprogrammed during activation of CD4 cells. Although we cannot discard the effect of other transcription factors, our study shows that mitochondrial Ca2+ is required for IL-6 to keep NFATc2 in the nucleus, and that NFAT contributes to late expression of Il21 and Il4. Mitochondrial respiration has been shown to lead to ROS production caused by proton leaks and ROS can lead to oxidative injury. A number of recent studies have shown that mROS can function as signaling intermediates, and the mROS signaling is required for antigen-specific T cell activation and subsequent IL-2 production( Byun et al., 2008; Schieke et al., 2008; Sena et al., 2013). Although IL-6 increases the MMP, we did not observe an increase in the levels of mROS correlating with the effect of IL-6 facilitating the formation of respiratory SCs. The presence of ETC SCs is emerging as a novel but highly relevant aspect of the mitochondrial function( Acín-Pérez et al., 2008; Althoff et al., 2011). The function of these SCs is to facilitate the transfer of electrons between ETC complexes to minimize the risk of electron leak and, thereby, the risk of producing harmful ROS. Our study demonstrates for the first time the presence of ETC SCs in CD4 cells, and the effect that IL-6 has in promoting the formation of these SCs during activation of CD4 cells. This could be a mechanism by which IL-6 can sustain elevated MMP and Ca2+ while minimizing the production of mROS. Although the association of Stat3 with individual complexes of the ETC has been previous described in heart and cancer cells( Gough et al., 2009; Wegrzyn et al., 2009), here we show for the first time the presence of Stat3 in the ETC SCs in CD4 cells. Stat3 may also be present in mitochondrial SCs in other tissues such as heart. Thus, here we identify a novel mechanism by which IL-6 promotes the production of IL-21 and IL-4 late during the activation of CD4 cells. This new mechanism involves Stat3 but as a factor regulating MMP and Ca2+ instead of its function as mediator of transcription. Our studies also reveal a novel function of mitochondrial respiration in the control of cytokine production through its effect on mitochondrial Ca2+ homeostasis.",
"role": "user"
},
{
"content": "Inflammation is a normal part of the body's response to an infection or injury and it helps to start the healing process . However , if left unchecked , inflammation itself can damage tissues , and diseases such as rheumatoid arthritis are the result of uncontrolled inflammation . Certain immune cells release molecules that can either trigger or suppress inflammation . Interleukin 6 is an example of a ‘pro-inflammatory’ molecule , which regulates the activity of groups of immune cells collectively known as ‘CD4 cells’ . People who are overweight or obese have higher levels of interleukin 6 than people of a healthy weight . Obesity and other metabolic conditions have been linked to problems with structures called mitochondria , which make a molecule called ATP that provides cells with the energy they need to survive . But it is not known if interleukin 6 can affect the activity of mitochondria inside CD4 cells . Now , Yang et al . have discovered that interleukin 6 can affect the mitochondria inside CD4 cells and , in doing so , have identified a new way that interleukin 6 can regulate these cells' activity . Experiments involving immune cells from mice revealed that interleukin 6 triggers a cascade of signaling events that aid the formation of so-called ‘mitochondrial respiratory chain supercomplexes’ in CD4 cells . These are groups of proteins that work together in the membranes of mitochondria and are vital for the activity of these structures . The formation of these supercomplexes maintains a large voltage difference across the membrane of the mitochondria that occurs during the later stages of CD4 cell activation . Yang et al . found that this voltage difference was not linked to the production of ATP , but that it did raise the levels of calcium ions inside the mitochondria . Further experiments revealed that these increased levels of calcium ions prolong the production of other pro-inflammatory molecules in the CD4 cells . Following the discovery of a new pathway that regulates the activity of CD4 cells , the next challenge is to see if the parts of this pathway could be targeted with drugs to help treat inflammatory diseases such as rheumatoid arthritis . Moreover , because interleukin 6 plays an active role in other diseases such as cancer , further studies of this new pathway may help explain how this molecule encourages cancers to progress and/or spread around the body .",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.4817
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nIn open set learning, a model must be able to generalize to novel classes when it encounters a sample that does not belong to any of the classes it has seen before. Open set learning poses a realistic learning scenario that is receiving growing attention. Existing studies on open set learning mainly focused on detecting novel classes, but few studies tried to model them for differentiating novel classes. In this paper, we recognize that novel classes should be different from each other, and propose distribution networks for open set learning that can model different novel classes based on probability distributions. We hypothesize that, through a certain mapping, samples from different classes with the same classification criterion should follow different probability distributions from the same distribution family. A deep neural network is learned to map the samples in the original feature space to a latent space where the distributions of known classes can be jointly learned with the network. We additionally propose a distribution parameter transfer and updating strategy for novel class modeling when a novel class is detected in the latent space. By novel class modeling, the detected novel classes can serve as known classes to the subsequent classification. Our experimental results on image datasets MNIST and CIFAR10 show that the distribution networks can detect novel classes accurately, and model them well for the subsequent classification tasks.\n\nCited Abstract(s):\n[1]: Learning from a few examples remains a key challenge in machine learning. Despite recent advances in important domains such as vision and language, the standard supervised deep learning paradigm does not offer a satisfactory solution for learning new concepts rapidly from little data. In this work, we employ ideas from metric learning based on deep neural features and from recent advances that augment neural networks with external memories. Our framework learns a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types. We then define one-shot learning problems on vision (using Omniglot, ImageNet) and language tasks. Our algorithm improves one-shot accuracy on ImageNet from 87.6 to 93.2 and from 88.0 to 93.8 on Omniglot compared to competing approaches. We also demonstrate the usefulness of the same model on language modeling by introducing a one-shot task on the Penn Treebank.\n\n[2]: \n\n[3]: We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend prototypical networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.",
"role": "user"
},
{
"content": "Few-shot learning including one-shot learning, tries to do learning tasks by using very few training examples [2] [1] [3] . In OSL, when a novel class is generated, there should be very few samples in the novel class, the subsequent classification for samples in this class can be seen as few-shot learning. In our work, the model of novel class is learned from the known classes and the limited samples. The prototypical networks [3] for few-shot learning has something in common with ours. We both map the original feature space to an embedding space. The prototypical networks try to figure a prototype for each class in the embedding space for few-shot learning, while our DN try to model a distribution for each known class and to transfer the distribution parameters to unknown classes for open set learning.",
"role": "assistant"
}
] |
science.healthver_entailment
|
science.healthver_entailment.863
|
[
{
"content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Children May Be Silent Carriers of COVID-19\n\nAbstract:\nDetailed data on clinical presentations and outcomes of children with COVID-19 in Europe are still lacking.\nIn this descriptive study, we report on 130 children with confirmed COVID-19 diagnosed by 28 centers (mostly hospitals), in 10 regions in Italy, during the first months of the pandemic.\nAmong these, 67 (51.5%) had a relative with COVID-19 while 34 (26.2%) had comorbidities, with the most frequent being respiratory, cardiac, or neuromuscular chronic diseases.\nOverall, 98 (75.4%) had an asymptomatic or mild disease, 11 (8.5%) had moderate disease, 11 (8.5%) had a severe disease, and 9 (6.9%) had a critical presentation with infants below 6 months having significantly increased risk of critical disease severity (OR 5.6, 95% CI 1.3 to 29.1).\nSeventy-five (57.7%) children were hospitalized, 15 (11.5%) needed some respiratory support, and nine (6.9%) were treated in an intensive care unit.\nAll recovered.\nConclusion:This descriptive case series of children with COVID-19, mostly encompassing of cases enrolled at hospital level, suggest that COVID-19 may have a non-negligible rate of severe presentations in selected pediatric populations with a relatively high rates of comorbidities.\nMore studies are needed to further understand the presentation and outcomes of children with COVID-19 in children with special needs.\nWhat is Known: ⢠There is limited evidence on the clinical presentation and outcomes of children with COVID-19 in Europe, and almost no evidence on characteristics and risk factors of severe cases.\nWhat is New: ⢠Among a case series of 130 children, mostly diagnosed at hospital level, and with a relatively high rate (26.2%) of comorbidities, about three-quarter had an asymptomatic or mild disease.\n⢠However, 57.7% were hospitalized, 11.5% needed some respiratory support, and 6.9% were treated in an intensive care unit.",
"role": "user"
},
{
"content": "{\"verdict\": \"NEI\", \"evidence\": []}",
"role": "assistant"
}
] |
science.cdr_ner
|
science.cdr_ner.432
|
[
{
"content": "Find all entities of these types in the text: [\"Chemical\", \"Disease\"].\n\nOutput a JSON object.\n\nText:\nEstrogen prevents cholesteryl ester accumulation in macrophages induced by the HIV protease inhibitor ritonavir. Individuals with HIV can now live long lives with drug therapy that often includes protease inhibitors such as ritonavir. Many patients, however, develop negative long-term side effects such as premature atherosclerosis. We have previously demonstrated that ritonavir treatment increases atherosclerotic lesion formation in male mice to a greater extent than in female mice. Furthermore, peripheral blood monocytes isolated from ritonavir-treated females had less cholesteryl ester accumulation. In the present study, we have investigated the molecular mechanisms by which female hormones influence cholesterol metabolism in macrophages in response to the HIV protease inhibitor ritonavir. We have utilized the human monocyte cell line, THP-1 as a model to address this question. Briefly, cells were differentiated for 72 h with 100 nM PMA to obtain a macrophage-like phenotype in the presence or absence of 1 nM 17beta-estradiol (E2), 100 nM progesterone or vehicle (0.01% ethanol). Cells were then treated with 30 ng/ml ritonavir or vehicle in the presence of aggregated LDL for 24 h. Cell extracts were harvested, and lipid or total RNA was isolated. E2 decreased the accumulation of cholesteryl esters in macrophages following ritonavir treatment. Ritonavir increased the expression of the scavenger receptor, CD36 mRNA, responsible for the uptake of LDL. Additionally, ritonavir treatment selectively increased the relative levels of PPARgamma mRNA, a transcription factor responsible for the regulation of CD36 mRNA expression. Treatment with E2, however, failed to prevent these increases at the mRNA level. E2 did, however, significantly suppress CD36 protein levels as measured by fluorescent immunocytochemistry. This data suggests that E2 modifies the expression of CD36 at the level of protein expression in monocyte-derived macrophages resulting in reduced cholesteryl ester accumulation following ritonavir treatment.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"ritonavir\", \"progesterone\", \"ethanol\", \"cholesteryl ester\", \"17beta-estradiol\", \"cholesteryl esters\", \"Ritonavir\", \"E2\", \"cholesterol\"], \"Disease\": [\"premature atherosclerosis\", \"atherosclerotic lesion\"]}",
"role": "assistant"
}
] |
science.bioasq_yesno_qa
|
science.bioasq_yesno_qa.1229
|
[
{
"content": "Based on the following biomedical documents, answer the question with either yes or no.\n\nQuestion: Is serotonin transported by platelets?\n\nContext: activated platelets, which carry peripheral serotonin,\nPlatelet serotonin response was measured by serotonin augmented platelet aggregation and platelet serotonin receptor density.\nSERT was studied in the 1970s and 1980s using membrane vesicles isolated from blood platelets.\nplatelet-dense granules contain neurotransmitters such as serotonin and gamma-aminobutyric acid. Molecular players controlling granule formation and secretion are\nPlatelets transport and store virtually all plasma serotonin in dense granules",
"role": "user"
},
{
"content": "yes",
"role": "assistant"
}
] |
science.chemdner_ner
|
science.chemdner_ner.1952
|
[
{
"content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nIncrease in antioxidant and anticancer effects of ginsenoside Re-lysine mixture by Maillard reaction. Ginsenosides are the main active components of Panax ginseng. Structural changes in diol type ginsenosides along with generation of Maillard reaction products (MRPs) are strongly associated with increased free radical-scavenging activities. Ginsenoside Re, one of the major triol type ginsenosides of P. ginseng, possesses a hydrophobic four-ring steroid-like structure with hydrophilic sugar moieties at carbons-3 and -20. The aim of the present study was to identify changes in the structure, antioxidant and anticancer effects of ginsenoside Re upon Maillard reaction. Ginsenoside Re was transformed into less-polar ginsenosides, namely Rg(2), Rg(6) and F(4) by heat-processing. Free radical-scavenging activity of the ginsenoside Re-lysine mixture increased upon heat processing. This improved free radical-scavenging activity mediated by antioxidant MRPs, which were generated through Maillard reaction of a glucosyl moiety separated from carbon-20 of ginsenoside Re and lysine. The increased anticancer effect of ginsenoside Re-lysine mixture upon heat processing was mainly derived from the generation of less-polar ginsenosides through the regulation of Bcl-2 and Bax, as well as caspase-dependent apoptotic pathway. These results reported here have shed significant new lights on the mechanism of increased antioxidant and anticancer effects of P. ginseng upon heat processing.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"carbon\", \"ginsenoside Re\", \"Ginsenosides\", \"sugar\", \"Ginsenoside Re\", \"glucosyl\", \"carbons\", \"diol\", \"triol\", \"lysine\", \"ginsenosides, namely Rg(2), Rg(6) and F(4)\", \"ginsenosides\"]}",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_pubmed
|
science.scientific_papers_summarization_single_doc_pubmed.5918
|
[
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\ninfantile tremor syndrome ( its ) is a clinical syndrome of acute or gradual onset of mental and psychomotor changes , pigmentary disturbances of hair and skin , pallor , and coarse tremors in malnourished children aged between 5 months and 3 years .\nit has been primarily reported from india and south east asia and has also been reported from other developing countries in asia and africa .\nvarious nutrient deficiencies ( e.g. vitamin b12 , magnesium [ mg ] , zinc [ zn ] , vitamin c , etc .\nclinically the presence of tremor has been attributed to structural and functional alterations of extrapyramidal system , but routine neuroimaging studies with computed tomography ( ct ) scan and magnetic resonance imaging in past revealed non - specific structural changes in its . here , we report a classical case of its with a rare association of thin corpus callosum . to the best of our knowledge ,\na 5.5-month - old female infant presented with pallor for 1-month , tremors of hands and feet for 2 days and delayed development .\nthere was no history suggestive of fever , bleeding , rash , lymphadenopathy , hepatosplenomegaly , jaundice , or seizures .\nthe child was born at term gestation with no antenatal , natal , or postnatal complications .\nthe child weighed 5.5 kg , had a length of 66 cm and head circumference of 41.5 cm . on physical examination , the child had sparse hair , pallor , and hyperpigmented knuckles [ figure 1 ] .\nthere were coarse tremors in all four limbs , the perioral and periorbital region in awake as well as sleep state [ video 1 ] .\nthere was increased tone in all 4 limbs , but no paresis of limbs or cranial nerve palsies .\ninvestigations revealed anemia ( hemoglobin = 6.6 g% ) , mean corpuscular volume ( mcv ) ( 103.7 fl ) , mean corpuscular hemoglobin ( mch ) ( 38 pg ) , mch concentration ( 37.4% ) , with normal leucocyte count ( 11,400/mm ) , and platelets ( 4 lakh / mm ) .\nserum b12 level was 202 pg / ml ( 200900 pg / ml ) and serum folic acid was 6.3 ng / ml ( 521 ng / ml ) .\ncerebrospinal fluid ( csf ) examination revealed no red blood cells or neutrophils , normal protein , sugar , and sterile cultures .\nct scan of the brain revealed cerebral atrophy with thin corpus callosum [ figures 2 and 3 ] .\ndull looking facial expression along with hypopigmented sparse hairs and pallor in a child of infantile tremor syndrome computed tomography scan showing diffuse cerebral atrophy computed tomography scan showing diffuse cerebral atrophy along with thin corpus callosum based on the clinical features , child was diagnosed as its .\ninitially , we have given her propranolol , b12 , mg , and multivitamins , but there was no improvement in her condition .\nthen , we started carbamazepine after 4 days and a dramatic response was observed after 7 days , as appetite improved , tremors disappeared during sleep and decreased in amplitude in the awake state .\nafter 1-month of follow - up , the child is active , gaining weight ( 6 kg ) , hemoglobin has improved ( 9.4 g% ) , and tremors stopped .\nafter 2 months of follow - up , propanol and carbamazepine have been tapered and stopped .\na classical picture of its is a plump looking infant between 6 and 18 months with the presence of malnutrition .\ndark pigmentation is present over dorsal aspects of hands , nail folds , feet , knees , ankles , buttocks , and axillae .\nthey are more prominent in distal parts of limbs , head , face , and tongue .\nthere is presence of anemia , which may be macrocytic , microcytic , or normocytic .\nmalnutrition , vitamin and mineral deficiency ( e.g. , mg and zn ) , infections , toxins , degenerative brain disease , enzyme defects ( e.g. , tyrosine ) all have been postulated as the causation of its . among various theories ,\nit is usually seen in children who are exclusively breast - fed for prolonged periods by vegetarian mothers .\nthe low levels of vitamin b12 and its transport protein transcobalamin ii ( tc ii ) in the csf maybe responsible for the neurological features of this syndrome .\nit is usual to find direct or indirect evidence of associated other nutritional deficiencies such as protein , vitamins a , d , c , and b - complex and other micronutrients .\nits is essentially a clinical diagnosis with peripheral smear suggestive of anemia ( mostly megaloblastic anemia , macrocytosis ( mcv > 95 ) , hypersegmented polymorphs , and megaloblastic bone marrow ) .\nvitamin b12 levels in the mother may also be low suggesting low levels in the breast milk .\nmost reports have shown normal neuroimaging findings or cerebral atrophy , ventricular prominence and/or prominence of the subarachnoid space , pontine myelinolysis , and cerebral hyperintensities . in our case ,\nthin corpus callosum is usually present in premature babies and is associated with poor neurological outcome and neuropsychological performance , but our case was delivered at term gestation and her antenatal , natal , and postnatal course was uneventful . to the best of our knowledge\nmultivitamins , vitamin c , iron , protein , zn , and mg supplements may also be necessary .\nif the tremors are severe , phenobarbitone or carbamazepine may be required to decrease the intensity .\ninitially , there is a gradual reduction in the amplitude and severity , and then the tremors become intermittent and finally stop . propranolol and chlorpromazine",
"role": "user"
},
{
"content": "infantile tremor syndrome ( its ) is a clinical disorder characterized by coarse tremors , anemia and regression of motor and mental milestones , presenting in malnourished children aged between 5 months and 3 years . \n few reports of neuroimaging abnormalities in children with its are present . \n the most common finding of neuroimaging in its is cerebral atrophy with ex - vacuo enlargement of ventricles and subarachnoid space , some recent reports also showed pontine myelinolysis and cerebral hyperintensities . we did not find any report of thin corpus callosum associated with its in the literature \n .",
"role": "assistant"
}
] |
science.medmentions_ner
|
science.medmentions_ner.430
|
[
{
"content": "Extract all unique entities from this biomedical abstract. Only choose entities from these types: [\"Virus\", \"MedicalDevice\", \"BodySubstance\", \"SpatialConcept\", \"BiologicFunction\", \"ResearchActivity\", \"AnatomicalStructure\", \"ProfessionalOrOccupationalGroup\", \"HealthCareActivity\", \"BiomedicalOccupationOrDiscipline\", \"Bacterium\", \"Chemical\", \"InjuryOrPoisoning\", \"IntellectualProduct\", \"Finding\", \"ClinicalAttribute\", \"Organization\", \"Eukaryote\", \"Food\", \"BodySystem\", \"PopulationGroup\"].\n\nOutput a JSON object where keys are entity types and values are lists of extracted entities. If no entities found for a type, use empty list [].\n\nAbstract: Pivotal debates and controversies on the structure and function of the avian respiratory system: setting the record straight Among the extant air-breathing vertebrates, the avian respiratory system is structurally the most complex and functionally the most efficient gas exchanger. Having been investigated for over four centuries, some aspects of its biology have been extremely challenging and highly contentious and others still remain unresolved. Here, while assessing the most recent findings, four notable aspects of the structure and function of the avian respiratory system are examined critically to highlight the questions, speculations, controversies and debates that have arisen from past research. The innovative techniques and experiments that were performed to answer particular research questions are emphasised. The features that are outlined here concern the arrangement of the airways, the path followed by the inspired air, structural features of the lung and the air and blood capillaries, and the level of cellular defence in the avian respiratory system. Hitherto, based on association with the proven efficiency of naturally evolved and human-made counter-current exchange systems rather than on definite experimental evidence, a counter-current gas exchange system was suggested to exist in the avian respiratory system and was used to explain its exceptional efficiency. However, by means of an elegant experiment in which the direction of the air - flow in the lung was reversed, a cross-current system was shown to be in operation instead. Studies of the arrangement of the airways and the blood vessels corroborated the existence of a cross-current system in the avian lung. While the avian respiratory system is ventilated tidally, like most other invaginated gas exchangers, the lung, specifically the paleopulmonic parabronchi, is ventilated unidirectionally and continuously in a caudocranial (back-to-front) direction by synchronized actions of the air sacs. The path followed by the inspired air in the lung - air sac system is now known to be controlled by a mechanism of aerodynamic valving and not by anatomical valves or sphincters, as was previously supposed. The structural strength of the air and blood capillaries is derived from: the interdependence between the air and blood capillaries; a tethering effect between the closely entwined respiratory units; the presence of epithelial - epithelial cell connections (retinacula or cross-bridges) that join the blood capillaries while separating the air capillaries; the abundance and intricate arrangement of the connective tissue elements, i.e. collagen, elastin, and smooth muscle fibres; the presence of type-IV collagen, especially in the basement membranes of the blood-gas barrier and the epithelial - epithelial cell connections; and a putative tensegrity state in the lung. Notwithstanding the paucity of free surface pulmonary macrophages, the respiratory surface of the avian lung is well protected from pathogens and particulates by an assortment of highly efficient phagocytic cells. In commercial poultry production, instead of weak pulmonary cellular defence, stressful husbandry practices such as overcrowding, force-feeding, and intense genetic manipulation for rapid weight gain and egg production may account for the reported susceptibility of birds to aerosol - transmitted diseases.",
"role": "user"
},
{
"content": "{\"AnatomicalStructure\": [\"blood capillaries\", \"pulmonary\", \"epithelial\", \"epithelial cell\", \"retinacula\", \"structure\", \"caudocranial\", \"airways\", \"connective tissue\", \"sphincters\", \"basement membranes\", \"phagocytic cells\", \"invaginated\", \"paleopulmonic parabronchi\", \"anatomical valves\", \"smooth muscle fibres\", \"air capillaries\", \"blood vessels\", \"air\", \"lung\", \"structural\", \"structurally\", \"pulmonary macrophages\"], \"Bacterium\": [], \"BiologicFunction\": [\"gas exchanger\", \"cross-current system\", \"counter-current gas exchange system\", \"diseases\", \"gas exchangers\", \"counter-current exchange systems\", \"cellular defence\", \"egg production\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [\"respiratory units\", \"system\", \"respiratory system\"], \"Chemical\": [\"type-IV collagen\", \"elastin\", \"collagen\"], \"ClinicalAttribute\": [\"susceptibility\"], \"Eukaryote\": [\"poultry\", \"avian\", \"air-breathing vertebrates\", \"birds\"], \"Finding\": [\"overcrowding\", \"weight gain\", \"findings\", \"force-feeding\"], \"Food\": [], \"HealthCareActivity\": [], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"record\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"research\", \"experiment\", \"Studies\", \"experiments\"], \"SpatialConcept\": [\"connections\", \"back-to-front\", \"surface\", \"intricate arrangement\", \"free surface\", \"blood-gas barrier\", \"direction\", \"unidirectionally\"], \"Virus\": []}",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.904
|
[
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nA randomized crossover study investigating the influence of ranitidine or omeprazole on the pharmacokinetics of cephalexin monohydrate . Limited data characterize pharmacokinetic interactions between cephalexin and ranitidine , and no data exist for an interaction with proton pump inhibitors . The purpose of this study was to investigate the effects of ranitidine or omeprazole administration on the pharmacokinetics and pharmacodynamics of cephalexin . A randomized single- and multiple-dose crossover study was conducted in healthy subjects ingesting cephalexin before and after steady-state administration of ranitidine or omeprazole . Time-concentration profiles were determined and pharmacokinetic parameters were characterized using noncompartmental methods . Pharmacokinetic data were analyzed in accordance with the two 1-sided test for bioequivalence . The percentage of time that serum concentrations remain above the MIC ( 90 ) during the dosing interval ( T > MIC ( 90 ) ) for Streptococcus pyogenes and Staphylococcus aureus associated with the pharmacokinetic profiles was calculated . The coadministration of cephalexin with ranitidine or omeprazole resulted in relatively minor changes in C ( max ) , AUC ( infinity ) , t ( 1/2 ) , or CL/F . t ( max ) was significantly prolonged when cephalexin was administered with ranitidine or omeprazole . Suboptimal T > MIC ( 90 ) was observed for cephalexin irrespective of acid suppression . Delay in absorption of cephalexin resulted in a decrease in the percentage of T > MIC ( 90 ) for certain acid-suppressive regimens and pathogen combinations . With the exception of an increase in t ( max ) , there were no significant pharmacokinetic interactions between cephalexin and ranitidine or omeprazole . Delayed t ( max ) associated with acid suppression may result in a diminished T > MIC ( 90 ) .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"cephalexin\", \"omeprazole\", \"ranitidine\"], \"Outcome\": [\"T \\u003e MIC ( 90 )\", \"Streptococcus pyogenes\", \"Suboptimal T \\u003e MIC ( 90 )\", \"pharmacokinetics and pharmacodynamics of cephalexin\", \"pharmacokinetics of cephalexin monohydrate .\", \"C ( max )\", \",\", \"pharmacokinetic parameters\", \"Time-concentration\", \"t ( 1/2 )\", \"CL/F\", \"t ( max )\", \"AUC ( infinity )\", \", or\", \"percentage of time that serum concentrations remain above the MIC ( 90 ) during the dosing interval ( T \\u003e MIC ( 90 ) )\"], \"Participant\": [\"healthy subjects ingesting cephalexin\"]}",
"role": "assistant"
}
] |
science.medmentions_ner
|
science.medmentions_ner.748
|
[
{
"content": "Extract all unique entities from this biomedical abstract. Only choose entities from these types: [\"Virus\", \"MedicalDevice\", \"BodySubstance\", \"SpatialConcept\", \"BiologicFunction\", \"ResearchActivity\", \"AnatomicalStructure\", \"ProfessionalOrOccupationalGroup\", \"HealthCareActivity\", \"BiomedicalOccupationOrDiscipline\", \"Bacterium\", \"Chemical\", \"InjuryOrPoisoning\", \"IntellectualProduct\", \"Finding\", \"ClinicalAttribute\", \"Organization\", \"Eukaryote\", \"Food\", \"BodySystem\", \"PopulationGroup\"].\n\nOutput a JSON object where keys are entity types and values are lists of extracted entities. If no entities found for a type, use empty list [].\n\nAbstract: Ventricular Effective Refraction Period and Ventricular Repolarization Analysis in Experimental Tachycardiomyopathy in Swine Swine are recognized animal models of human cardiovascular diseases. However, little is known on the CHF -associated changes in the electrophysiological ventricular parameters of humans and animals. The aim of this study was to analyze changes in the durations of ventricular effective refraction period (VERP), QT and QTc intervals of pigs with chronic tachycardia - induced tachycardiomyopathy (TIC). The study was comprised of 28 adult pigs (8 females and 20 males) of the Polish Large White breed. A one-chamber pacemaker was implanted in each of the 28 pigs. Electrocardiographic, echocardiographic and electrophysiological studies were carried out prior to the pacemaker implantation and at subsequent 4- week intervals. All electrocardiographic, echocardiographic and short electrophysiological study measurements in all swine were done under general anesthesia (propofol) after premedication with midazolam, medetomidine, and ketamine. No significant changes in the duration of QT interval and corrected QT interval (QTc) were observed during consecutive weeks of the experiment. The duration of the QTc interval of female pigs was shown to be significantly longer than that of the males throughout the whole study period. Beginning from the 12th week of rapid ventricular pacing, a significant increase in duration of VERP was observed in both male and female pigs. Males and females did not differ significantly in terms of VERP duration determined throughout the whole study period. Ventricular pacing, stimulation with 2 and 3 premature impulses at progressively shorter coupling intervals and an imposed rhythm of 130 bpm or 150 bpm induced transient ventricular tachycardia in one female pig and four male pigs. One episode of permanent ventricular tachycardia was observed. The number of induced arrhythmias increased proportionally to the severity of heart failure and duration of the experiment. However, relatively aggressive protocols of stimulation were required in order to induce arrhythmia in the studied pigs.",
"role": "user"
},
{
"content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"tachycardiomyopathy\", \"arrhythmias\", \"animal models\", \"arrhythmia\", \"cardiovascular diseases\", \"TIC\", \"Tachycardiomyopathy\", \"tachycardia\", \"CHF\", \"Ventricular Repolarization\", \"heart failure\", \"ventricular tachycardia\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"medetomidine\", \"ketamine\", \"midazolam\", \"propofol\"], \"ClinicalAttribute\": [\"QT interval\", \"QT\"], \"Eukaryote\": [\"pig\", \"humans\", \"human\", \"animals\", \"swine\", \"pigs\", \"Swine\", \"Polish Large White breed\"], \"Finding\": [\"VERP\", \"rhythm\", \"electrophysiological ventricular parameters\", \"ventricular effective refraction period\", \"Ventricular Effective Refraction Period\"], \"Food\": [], \"HealthCareActivity\": [\"general anesthesia\", \"echocardiographic\", \"stimulation\", \"electrocardiographic\", \"pacemaker implantation\", \"Ventricular pacing\", \"ventricular pacing\", \"Electrocardiographic\", \"premedication\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"protocols\"], \"MedicalDevice\": [\"one-chamber pacemaker\"], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"study\", \"experiment\", \"Analysis\"], \"SpatialConcept\": [], \"Virus\": []}",
"role": "assistant"
}
] |
science.craftchem_ner
|
science.craftchem_ner.14
|
[
{
"content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Age,timeofday,obesityanddiabeteshaveeffectsonmouseIOPsimilartothoseinhumansandotherspecies.",
"role": "user"
},
{
"content": "[]",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_pubmed
|
science.scientific_papers_summarization_single_doc_pubmed.29675
|
[
{
"content": "Write an abstract for the research paper below.\n\nPaper text:\nnkt cells are distinguished type i nkt cell and type ii nkt cells according to t cell receptor ( tcr ) usage .\ntype i nkt cells are called invariant nkt ( inkt ) cells because they express only restricted tcr chain ( v14 ) and tcr chain ( v2 , 7 and 8) , whereas type ii nkt cells express various tcr chains ( 2,3 ) .\nnkt cells can help activation of other lymphocytes such as , t , b , nk and dendritc cells ( 3 - 6 ) .\nit has been known that dedritic cells ( dcs ) play a pivotal role in antigen presentation to nkt cells ( 7 ) .\nin contrast , resting b cells are known poor immunogenic antigen presenting cells ( apcs ) to nkt cells ( 8) . however\nnkt cells provide direct and indirect help for lipid and protein - specific b cells , respectively ( 9,10 ) . direct help from inkt cells for lipid - specific b cells is dependent on il-21 secreted from inkt cells ( 11 ) .\nhigh - density -galcer loaded b cells stimulate inkt cells although the efficiency of stimulation is not comparable to dendritic cells ( 12 ) .\n-galcer / peptide loaded b cells can induce peptide - specific cytotoxic cd8 t cells and induced cytotoxic cd8 t cells eliminate various kinds of tumor ( 12,13 ) . in micro - environment of foreign antigen stimuli , dc and b cells cooperate to activate antigen - specific cytotoxic cd8 t cells ( 14 ) .\nnevertheless , it remains to be resolved unknown nkt cells response upon co - operative stimulation of b cells and dcs . in this study .\nwe found that b cells induced th1-skewed response of nkt cells in the presence of -galcer loaded dcs , regardless of exogenous antigen loading to b cells .\nwe also demonstrated that regulation of nkt cell response by b cells stimulation was dependent on cd1d expression of b cells .\nsix- to eight - week - old c57bl/6 ( b6 ) , cd1d and cd1d mice ( b6 background ) were bred in facilities at korea university .\nthe experimental protocols of this study were approved by the institutional animal care and use committee of korea university .\nmonoclonal antibodies specific for mouse tcr ( h57 ) , ifn- ( xmg-1 ) , il-4 ( 11b11 ) and nk1.1 ( pk136 ) were purchased from bd biosciences .\nb cells were isolated from splenocytes via macs by using anti - b220-conjugated magnetic beads ( miltenyi biotec ) after dc had been depleted by using anti - cd11c microbeads .\npurified b cells and dcs were loaded 10 ng / ml -galcer for 4 hr and they were washed extensively , then were co - cultured with nkt cells for 8 hr or 48 hr . after 8 hr or 48 hr , the amount of cytokines was measured by intracellular cytokine staining and elisa .\ncells were washed and blocked with an anti - fcrii / iii mab ( 2.4g2 ) for 15 min and then labeled for 30 min on ice with the appropriate mabs . for intracellular cytokine staining ,\ncells were fixed with a cytofix / cytoperm kit ( bd biosciences ) according to the manufacturer 's protocol .\nthe stained cells were analyzed with a facscalibur flow cytometer using cellquest software ( bd biosciences ) .\nstudent 's t - tests were used to determine the statistical significance of differences between the comparison groups unless otherwise stated .\nsix- to eight - week - old c57bl/6 ( b6 ) , cd1d and cd1d mice ( b6 background ) were bred in facilities at korea university .\nthe experimental protocols of this study were approved by the institutional animal care and use committee of korea university .\nmonoclonal antibodies specific for mouse tcr ( h57 ) , ifn- ( xmg-1 ) , il-4 ( 11b11 ) and nk1.1 ( pk136 ) were purchased from bd biosciences .\nb cells were isolated from splenocytes via macs by using anti - b220-conjugated magnetic beads ( miltenyi biotec ) after dc had been depleted by using anti - cd11c microbeads .\npurified b cells and dcs were loaded 10 ng / ml -galcer for 4 hr and they were washed extensively , then were co - cultured with nkt cells for 8 hr or 48 hr . after 8 hr or 48 hr , the amount of cytokines was measured by intracellular cytokine staining and elisa .\ncells were washed and blocked with an anti - fcrii / iii mab ( 2.4g2 ) for 15 min and then labeled for 30 min on ice with the appropriate mabs . for intracellular\ncytokine staining , cells were fixed with a cytofix / cytoperm kit ( bd biosciences ) according to the manufacturer 's protocol .\nthe stained cells were analyzed with a facscalibur flow cytometer using cellquest software ( bd biosciences ) .\nstudent 's t - tests were used to determine the statistical significance of differences between the comparison groups unless otherwise stated .\nto test whether b cells can affect nkt cell stimulating activity of dcs , we co - cultured wt cd11c dc with nkt cells and b cells and then assessed the ability of b cells to activate nkt cells .\nelisa analysis and intracellular staining demonstrated that ifn- from nkt cells was significantly increased , in contrast il-4 was substantially reduced upon the addition of -galcer pulsed b cells compared to the response by dcs alone ( fig .\nthe co - culture of nkt cells with -galcer un - pulsed b cells also led to a significantly higher production of ifn- and lower production of il-4 than that with -galcer pulsed dcs alone ( fig . 2a and 2b ) .\ntaken together , these results show that b cells promote th1 response of nkt cells in the presence of antigen - loaded dcs , regardless of exogenous antigen pulse to b cells .\nalthough b cells promote th1 response of nkt cells in the presence of antigen - loaded dcs , it was not clear whether nkt cells and b cells form directly cell - cell contact by cd1d - tcr interaction . to test whether cd1d expression on b cells was required to promote th1 response of nkt cells in the presence of -galcer pulsed dcs , we isolated b cells from cd1d or cd1d mice and co - cultured them with dcs to activate nkt cells .\nco - culture of nkt cells with cd1d b cells led to a significantly higher production of ifn- and lower production of il-4 than that with cd1d b cells ( fig .\nthis data show that th1-skewed response of nkt cells upon the addition of conventional b cells is dependent on cd1d expression of b cells .\nsimilarly , it had been reported that marginal zone ( mz ) b cells amplify dc mediated - nkt cell activation ( 15 ) .\nthe cytokine patterns of nkt cells upon mz b cells and dcs stimulation ( 15 ) was similar to our results , except il-4 expression was also increased when -galcer loaded mzb cells was used . however , there was a contradicting report where conventional b cells could dampen inkt cells activation in the presence of dcs ( 8) . we are not sure at the moment what made these difference in nkt cell response but the density of b cells and concentration of -galcer might be causative factor since they used much higher number of b cells and higher concentration of -galcer to activate nkt cells compared to the experimental condition in this study .\nnkt cell - mediated cytokines milieu can be influenced by pattern of cellular composition of lymphocytes in specific inflammatory site .\nfor example , nkt cells in tumor model promote th1-skewed cytokine milieu , in contrast nkt cells in asthma model promote th2-skewed cytokine milieu ( 4,6 ) . in asthma model ,\nthe administration of -galcer ameliorated or worsened the disease symptoms by how to inject -galcer ( 16 - 18 ) .\na shift from th2 to th1-response by the administration of -galcer suppressed airway hyper - responsiveness ( ahr ) ( 17,18 ) . in this study\n, we demonstrated that b cells promote th1 response of nkt cells in the presence of antigen - loaded dcs .\nthus , the administration of -galcer pulsed b cells and dcs may be a possible approach for the treatment of ahr .\neventually , the elucidation of optimal composition of apcs such as dcs and b cells to regulate finely the direction of nkt cell response will be the basis to apply nkt cell - based cell therapy .",
"role": "user"
},
{
"content": "cd1d expressing dendritic cells ( dcs ) are good glyco - lipid antigen presenting cells for nkt cells . however , resting b cells are very weak stimulators for nkt cells . \n although -galactosylceramide ( -galcer ) loaded b cells can activate nkt cells , it is not well defined whether b cells interfere nkt cell stimulating activity of dcs . \n unexpectedly , we found in this study that b cells can promote th1-skewed nkt cell response , which means a increased level of ifn- by nkt cells , concomitant with a decreased level of il-4 , in the circumstance of co - culture of dcs and b cells . remarkably , the response promoted by b cells was dependent on cd1d expression of b cells .",
"role": "assistant"
}
] |
science.bioasq_yesno_qa
|
science.bioasq_yesno_qa.335
|
[
{
"content": "Based on the following biomedical documents, answer the question with either yes or no.\n\nQuestion: Has the protein GFP been used in transgenesis for live protein imaging?\n\nContext: we review recent advancement in the functional studies of the three different GnRH neuron systems, mainly focusing on the electrophysiological analysis of the GnRH-green fluorescent protein (GFP) transgenic animals.\nfounders were found to be transgenic for GFP.\nGFP expression was detected in a wide range of murine tissues\nTransgenic Xenopus laevis for live imaging in cell and developmental biology.\nThe stable transgenesis of genes encoding functional or spatially localized proteins, fused to fluorescent proteins such as green fluorescent protein (GFP) or red fluorescent protein (RFP), is an extremely important research tool in cell and developmental biology.\nGFP-transgenic animals for in vivo imaging: rats, rabbits, and pigs.\nWe have further extended the techniques of genetic engineering to rats, rabbits, and pigs, and have created corresponding GFP-transgenic animals.\nThe results revealed that the 3.6-GFP transgenic animals provide a unique model for direct analysis of cellular and molecular mechanisms of pulp repair and tertiary dentinogenesis in vivo.\nLong-term effects of PERV-specific RNA interference in transgenic pigs.\ngreen fluorescent protein (GFP) as reporter of the vector system were consistently expressed in transgenic animals.\nThe ability to specify the expression levels of exogenous genes inserted in the genomes of transgenic animals is critical for the success of a wide variety of experimental manipulations.\nWelfare assessment in transgenic pigs expressing green fluorescent protein (GFP).\ntransgenic animals expressing GFP with wildtype animals along various stages of post natal development\nProduction of transgenic chickens expressing a tetracycline-inducible GFP gene.\ntransgenic animals can be readily created to express fluorescently tagged proteins or reporters\nThese findings suggest that mhc2dab:GFP and cd45:DsRed transgenic lines will be instrumental in elucidating the immune response in the zebrafish.\nf 33 mice born, 28 (81%) carried the transgene DNA and 15 (55.5%) were GFP-positive.\nLentiviral vectors containing the green fluorescent protein gene have been successfully used to select transgenic embryos before transfer to a surrogate mother\nTypically transgenes are generated by placing a promoter upstream of a GFP reporter gene or cDNA of interest, and this often produces a representative expression pattern.\nSurvival and immunogenicity of mesenchymal stem cells from the green fluorescent protein transgenic rat in the adult rat brain.\nThis problem has been lessened by the availability of transgenic animals that express \"reporter\" genes, such as green fluorescent protein (GFP)\nfull-length GFP fusion proteins was examined, in transgenic animals,\nTwo stable transgenic lines express GFP prior to hair-bundle formation\nwe generated two transgenic pigs by somatic cell nuclear transfer (SCNT) that express green fluorescent protein (GFP) driven by cytomegalovirus (CMV).\nFluorescent proteins such as the green fluorescent protein (GFP) have widely been used in transgenic animals as reporter genes.\nGreen Fluorescent Protein (GFP) is used extensively as a reporter for transgene expression in Drosophila and other organisms.",
"role": "user"
},
{
"content": "yes",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_plos_single_doc_summ
|
science.scientific_lay_summarisation_plos_single_doc_summ.22381
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Design of Multi-Specificity in Protein Interfaces\nArticle:\nAbstract:\nInteractions in protein networks may place constraints on protein interface sequences to maintain correct and avoid unwanted interactions. Here we describe a “multi-constraint” protein design protocol to predict sequences optimized for multiple criteria, such as maintaining sets of interactions, and apply it to characterize the mechanism and extent to which 20 multi-specific proteins are constrained by binding to multiple partners. We find that multi-specific binding is accommodated by at least two distinct patterns. In the simplest case, all partners share key interactions, and sequences optimized for binding to either single or multiple partners recover only a subset of native amino acid residues as optimal. More interestingly, for signaling interfaces functioning as network “hubs, ” we identify a different, “multi-faceted” mode, where each binding partner prefers its own subset of wild-type residues within the promiscuous binding site. Here, integration of preferences across all partners results in sequences much more “native-like” than seen in optimization for any single binding partner alone, suggesting these interfaces are substantially optimized for multi-specificity. The two strategies make distinct predictions for interface evolution and design. Shared interfaces may be better small molecule targets, whereas multi-faceted interactions may be more “designable” for altered specificity patterns. The computational methodology presented here is generalizable for examining how naturally occurring protein sequences have been selected to satisfy a variety of positive and negative constraints, as well as for rationally designing proteins to have desired patterns of altered specificity.\nIntroduction:\nProteins have evolved to operate within the context of crowded cellular milieus and complex functional networks[1]. It is not well understood how and to what extent protein sequences and structures are optimized for multiple and likely interdependent properties such as stability and efficiency of folding, low propensity for aggregation, and functional characteristics. Protein–protein interaction networks may impose particular pressures on amino acid residues in protein interfaces if each protein needs to maintain correct and avoid unwanted interactions. Not only specificity of interactions but also a defined level of promiscuity may be required, as it is known that many proteins use regions of overlapping interface residues to bind several partners at different points in time[2]. Protein design predictions offer great promise to help dissect the structural determinants of the interplay between promiscuity and specificity, as well as to create new molecules that interfere with defined cellular protein–protein interactions with high fidelity and selectivity[3]. Protein design methodologies have generally focused on choosing an amino acid sequence optimal for a specific criterion, such as protein stability or interaction energy with a single binding partner. These computational design techniques have led to several accomplishments, including the pioneering design of a complete protein[4], of novel protein folds[5, 6], the engineering of catalytic activity into an uncatalytic scaffold[7, 8], and the redesign of protein–protein interfaces[9–12]. Yet, sequences completely redesigned on a known protein fold often differ substantially from naturally occurring sequences[4], and the properties of designed proteins can be unusual. Top7, a computationally designed protein with a fold not previously seen in nature[6], has a complex folding landscape strikingly different from that of evolved small, single domain proteins[13]. Thus, if we wish to rationally design new proteins that can be expressed and function correctly in a cellular environment and in the context of many possible interaction partners, it is likely that we will need modeling procedures that are able to consider a variety of requirements defining optimal protein “fitness. ” Here we focus on the multiple constraints interaction networks may impose on protein interfaces, both to characterize the evolutionary and biophysical principles shaping these networks, and to develop computational design methods to reengineer them. Previous studies have suggested the importance of negative selection to maintain specificity for a single binding partner[14]. Havranek and Harbury developed a negative design strategy selecting against unwanted partners to predict highly specific coiled-coil interfaces[11]. We extend the idea of incorporating additional selection constraints into computational protein design by examining the inverse problem: how are multiple positive criteria, such as the binding of different partners, accommodated at multi-specific( e. g., promiscuous) protein interfaces? We perform two computational experiments on 20 multi-specific proteins. First, we optimize each multi-specific interface sequence to maintain interactions with all known structurally characterized partners( multi-constraint protocol). Second, we predict interface sequences optimal for interacting with each partner individually( single-constraint protocol). We hypothesize that, to the extent that a multi-constraint protocol is a good approximation of pressures acting on promiscuous interfaces, predicted sequences should be more “native-like” when all characterized binding partners are included in the optimization procedure than if only the interaction with a single binding partner is considered. Further, we can compare the differences in interface sequences selected by each partner alone( single-constraint) and all partners considered together( multi-constraint). If multiple pressures play a role for sequence choices, this comparison should highlight which amino acids are compromises among the various outcomes favored by each binding partner individually. We show that, overall, inclusion of multiple binding partners during optimization returns sequences closer to those found in native promiscuous interfaces. We find native interface residues predicted to be “hotspots” for each partner remain optimal in the context of optimization for single or multiple partners, while other positions may or may not undergo compromises in order to maintain binding of all partners. These trends resulted in the classification of two broad groups of multi-specific interfaces. In the first group, the number of native residues recovered as optimal was similar for optimizations performed over single or multiple partners. Here, key interactions within the interface appeared to be shared, and there was little evidence of compromise in binding preferences among all partners. In contrast, a second group of multi-specific proteins, including “hubs” such as small GTPases, ubiquitin, and actin, appeared to have optimized large fractions of their interfaces for binding multiple partners. In these cases, each partner appears to pick and choose subsets of the interface to make key interactions with, and integrating differences in the binding preferences over all partners often resulted in the native residues being the “optimal compromise” for maintaining binding of all partners. Our method thus both predicts interface sites responsible for multi-specificity and provides an estimate of the magnitude of pressure exerted on sites by each interaction partner. The method we present here can be used as a predictive tool to study how naturally occurring amino acid sequences might have been constrained by any number of positive or negative criteria—including the ability to adopt two different conformations[15]—or as a protein design tool to rationally redesign variants of native proteins to have a desired set of properties matching user-defined constraints.\nDiscussion:\nOur study uses a protein design method that can in principle be applied to computationally select amino acid sequences under any set of positive and negative constraints that can be defined by a fitness function. Here we have made comparisons between single- and multi-constraint predicted and naturally occurring sequences to quantify optimization and compromise in multi-specific interfaces. Our analysis indicates that first, the protocol presented here is able to detect optimization for multi-specificity in promiscuous interfaces, as sequences and binding scores from multi-constraint simulations are closer to native than those obtained in single-constraint optimizations. Second, we identify two distinct mechanisms for achieving multi-specificity:( 1) shared or low compromise interfaces where a small subset of interface residues have been optimized such that all binding partners utilize this set as hotspots and( 2) multi-faceted or intermediate compromise interfaces where a far larger percentage of the interface has been optimized for multi-specific binding and each partner picks and chooses a subset of interface residue interaction with which to make key interactions. Signaling proteins with large, flat interfaces fall clearly within the “multi-faceted” group II, while enzymes, motif recognition domains, and receptors with smaller, narrower binding interfaces are often found within the shared group I. We speculate that the “multi-faceted” mode might have an evolutionary advantage for signaling interfaces, as here the chance that single mutations will deleteriously affect all binding interactions is reduced. On the other hand, a single mutation may substantially alter the pattern of interaction partners by now favoring certain interactions over others. In this way, multi-faceted interfaces may be more “evolvable” for new sets of interactions. It is interesting to note that the ability to a priori predict binding sites from surface sequence conservation or surface cavity size has been shown to be easiest for proteins similar to those classified as “shared binding” by our methodology[29]. This is consistent with our observations, as in these cases there should be shared evolutionary pressure for conservation of key surface residues by all partners. In contrast, for proteins predicted to display some degree of compromise among the differing binding preferences of their multiple partners, evolutionary pressures could differ depending on which subset of binding partners is most strongly selected for over time. Further, allowing each partner to pick and choose its own subset of interface amino acids for key interactions, as in the multi-faceted case, could necessitate large, easily accessible( i. e., flat) binding surfaces with a certain degree of conformational flexibility; this mechanism could hence partly explain why flat surfaces and conformational variability are frequently seen in multi-specific signaling proteins such as G-proteins[30]. We hypothesize that there should be significant differences in the ease with which binding specificities among partners could be rationally modified and/or small molecule inhibitors could be designed for proteins exhibiting the two modes of multi-specificity described here. The patterns of varying amino acid preferences among different binding partners revealed by comparing the single- and multi-constraint protocols suggest mutations at specific interface positions that could rationally change the specificity or promiscuity seen among binding partners. However, these same factors might make drug or small molecule design toward “multi-faceted” interfaces more difficult. For the group II interfaces in our set, the different partners display varying interface residue preferences( see Figure 3C), and there may be a substantial number of constrained residues in each binding interface( see Figure 7). Hence, proteins using this mode of interaction may have fairly distributed hotspots that are difficult to interfere with by a small molecule targeted to a single region. A caveat of our study is that first, generalizations may be somewhat limited because of the restricted size of our dataset of high-resolution structures. Second, the results presented here are necessarily dependent on the quality of the scoring function used for optimizations. However, improvement in native recovery seen in multi-constraint simulations could not be directly due to energy function biases, as the same scoring function was used for all simulations. The ability of the Rosetta scoring function to predict energetically important residues has been analyzed previously[22]. We note that amino acid types for which our simulations consistently select the native residue as the best( optimal) choice for binding multiple partners include tryptophan, tyrosine, and arginine( Figure S3; the predicted amino acid frequencies for W, Y, and R closely match the native distribution), amino acid types which have previously been shown to be energetically important in binding interfaces[16, 31, 32]. Interestingly, where allowed by steric constraints( for example at the interface periphery), we observed an increased selection in our simulations of larger amino acids such as tryptophan, arginine, and histidine, and against smaller amino acids such as alanine, threonine, and valine( Tables S1–S20 and Figure S3). While this could be due to approximations in our scoring function, an alternative explanation could be that these non-native sequences would, at least in some cases, truly bind more strongly. An overrepresentation of large hydrophobic residues may have been selected against in nature to maintain protein solubility in the absence of binding partners. In addition, while our computational protocol optimizes binding score, naturally occurring transient interfaces may not necessarily have evolved for strong binding. The complexes between small GTPases and their exchange factors( GEFs) may be examples of interactions that need to be transient to fulfill their cellular function: in the case of the ARF1-Sec7 interaction, the fungal metabolite Brefeldin A inhibits signaling by stabilizing the complex[33]. It may also be a general trend that multi-specificity must come at a cost of affinity[34]. Additional constraints not explicitly considered in our current protocol, such as selection at the level of on or off rates for complex formation could also account for differences in native and computationally selected sequences. Lastly, we note that while the analysis presented here has focused on the ability of our simulations to identify the wild-type amino acid, strict conservation of a single native amino acid over evolutionary time is rare, and the tolerance for substitution to differing amino acid types can vary between sites in an interface[29]. For example, for the multi-specific protein Ras we found two instances( Table S12, positions 32Y and 67M) where we predicted the interface positions to be energetically important but failed to correctly recover the native amino acid. In both cases, the non-native amino acids selected by our multi-constraint simulations were among the evolutionarily tolerated set seen in a multiple-sequence alignment( unpublished data, generated as described in Methods). A clear extension of our method is thus not only to predict optimal but also a set of tolerated amino acid sequences for a given set of constraints( ELH and TK, unpublished data). While we have applied the multi-constraint design protocol described in this work to examine whether and how promiscuous proteins are optimized for binding multiple partners, the methodology presented here is general and can be extended to analyze how any number of enumerable constraints( both positive and negative) affects sequence selection. A logical related analysis would be to characterize the sequence determinants of conformational flexibility where the input constraints would be stability for two or more different conformations. Further, the multi-constraint protocol introduced here is not only predictive of naturally occurring amino acid sequences, but also allows for rational redesign of proteins with altered binding properties which could be instrumental toward understand the role of specificity in protein interaction networks as well as in the engineering of biosensors and new cellular pathways.",
"role": "user"
},
{
"content": "Computational methods have recently led to remarkable successes in the design of molecules with novel functions . These approaches offer great promise for creating highly selective molecules to accurately control biological processes . However , to reach these goals modeling procedures are needed that are able to define the optimal “fitness” of a protein to function correctly within complex biological networks and in the context of many possible interaction partners . To make progress toward these goals , we describe a computational design procedure that predicts protein sequences optimized to bind not only to a single protein but also to a set of target interaction partners . Application of the method to characterize “hub” proteins in cellular interaction networks gives insights into the mechanisms nature has used to tune protein surfaces to recognize multiple correct partner proteins . Our study also provides a starting point to engineer designer molecules that could modulate or replace naturally occurring protein interaction networks to combat misregulation in disease or to build new sets of protein interactions for synthetic biology .",
"role": "assistant"
}
] |
science.cdr_ner
|
science.cdr_ner.231
|
[
{
"content": "Find all entities of these types in the text: [\"Chemical\", \"Disease\"].\n\nOutput a JSON object.\n\nText:\nMetamizol potentiates morphine antinociception but not constipation after chronic treatment. This work evaluates the antinociceptive and constipating effects of the combination of 3.2 mg/kg s.c. morphine with 177.8 mg/kg s.c. metamizol in acutely and chronically treated (once a day for 12 days) rats. On the 13th day, antinociceptive effects were assessed using a model of inflammatory nociception, pain-induced functional impairment model, and the charcoal meal test was used to evaluate the intestinal transit. Simultaneous administration of morphine with metamizol resulted in a markedly antinociceptive potentiation and an increasing of the duration of action after a single (298+/-7 vs. 139+/-36 units area (ua); P<0.001) and repeated administration (280+/-17 vs. 131+/-22 ua; P<0.001). Antinociceptive effect of morphine was reduced in chronically treated rats (39+/-10 vs. 18+/-5 au) while the combination-induced antinociception was remained similar as an acute treatment (298+/-7 vs. 280+/-17 au). Acute antinociceptive effects of the combination were partially prevented by 3.2 mg/kg naloxone s.c. (P<0.05), suggesting the partial involvement of the opioidergic system in the synergism observed. In independent groups, morphine inhibited the intestinal transit in 48+/-4% and 38+/-4% after acute and chronic treatment, respectively, suggesting that tolerance did not develop to the constipating effects. The combination inhibited intestinal transit similar to that produced by morphine regardless of the time of treatment, suggesting that metamizol did not potentiate morphine-induced constipation. These findings show a significant interaction between morphine and metamizol in chronically treated rats, suggesting that this combination could be useful for the treatment of chronic pain.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"metamizol\", \"naloxone\", \"morphine\", \"charcoal\", \"Metamizol\"], \"Disease\": [\"pain\", \"chronic pain\", \"constipating\", \"constipation\"]}",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.23397
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nIn light of growing attention of intelligent vehicle systems, we propose developing a driver model that uses a hybrid system formulation to capture the intent of the driver. This model hopes to capture human driving behavior in a way that can be utilized by semi- and fully autonomous systems in heterogeneous environments. We consider a discrete set of high level goals or intent modes, that is designed to encompass the decision making process of the human. A driver model is derived using a dataset of lane changes collected in a realistic driving simulator, in which the driver actively labels data to give us insight into her intent. By building the labeled dataset, we are able to utilize classification tools to build the driver model using features of based on her perception of the environment, and achieve high accuracy in identifying driver intent. Multiple algorithms are presented and compared on the dataset, and a comparison of the varying behaviors between drivers is drawn. Using this modeling methodology, we present a model that can be used to assess driver behaviors and to develop human-inspired safety metrics that can be utilized in intelligent vehicular systems.\n\nCited Abstract(s):\n[1]: We consider learning in a Markov decision process where we are not explicitly given a reward function, but where instead we can observe an expert demonstrating the task that we want to learn to perform. This setting is useful in applications (such as the task of driving) where it may be difficult to write down an explicit reward function specifying exactly how different desiderata should be traded off. We think of the expert as trying to maximize a reward function that is expressible as a linear combination of known features, and give an algorithm for learning the task demonstrated by the expert. Our algorithm is based on using \"inverse reinforcement learning\" to try to recover the unknown reward function. We show that our algorithm terminates in a small number of iterations, and that even though we may never recover the expert's reward function, the policy output by the algorithm will attain performance close to that of the expert, where here performance is measured with respect to the expert's unknown reward function.",
"role": "user"
},
{
"content": "One of the desired outcomes of this work is to identify a model that does not depend on human input and can be used in human driven or autonomous systems. Ideally, the model could be used in human-inspired driving applications. Driving styles in terms of discrete control actions were mimicked in [1] , using inverse reinforcement learning.",
"role": "assistant"
}
] |
science.scicite_classification
|
science.scicite_classification.5107
|
[
{
"content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: PKBR1, however, also becomes activated upon cAMP stimulation by phosphorylation in both the AL site by PdkA and in the HM site by TorC2 (Kamimura et al., 2008, 2010; Cai et al., 2010; Liao et al., 2010).",
"role": "user"
},
{
"content": "Method",
"role": "assistant"
}
] |
science.healthver_entailment
|
science.healthver_entailment.651
|
[
{
"content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: COVID-19 may have also returned because the patients have weaker immune systems. But there is also a chance that humans are unable to develop a natural defense against the virus after the first infection\n\nAbstract:\nRecent studies have provided insights into the pathogenesis of coronavirus disease 2019 (COVID-19)1-4.\nYet, longitudinal immunological correlates of disease outcome remain unclear.\nHere, we serially analysed immune responses in 113 COVID-19 patients with moderate (non-ICU) and severe (ICU) disease.\nImmune profiling revealed an overall increase in innate cell lineages with a concomitant reduction in T cell number.\nWe identify an association between early, elevated cytokines and worse disease outcomes.\nFollowing an early increase in cytokines, COVID-19 patients with moderate disease displayed a progressive reduction in type-1 (antiviral) and type-3 (antifungal) responses.\nIn contrast, patients with severe disease maintained these elevated responses throughout the course of disease.\nMoreover, severe disease was accompanied by an increase in multiple type 2 (anti-helminths) effectors including, IL-5, IL-13, IgE and eosinophils.\nUnsupervised clustering analysis of plasma and peripheral blood leukocyte data identified 4 immune signatures, representing (A) growth factors, (B) type-2/3 cytokines, (C) mixed type-1/2/3 cytokines, and (D) chemokines that correlated with three distinct disease trajectories of patients.\nThe immune profile of patients who recovered with moderate disease was enriched in tissue reparative growth factor signature (A), while the profile for those with worsened disease trajectory had elevated levels of all four signatures.\nThus, we identified development of a maladapted immune response profile associated with severe COVID-19 outcome and early immune signatures that correlate with divergent disease trajectories.",
"role": "user"
},
{
"content": "{\"verdict\": \"NEI\", \"evidence\": []}",
"role": "assistant"
}
] |
science.chia_ner
|
science.chia_ner.150
|
[
{
"content": "Extract all unique entities of these types from the following clinical trial criteria: [\"Negation\", \"Observation\", \"ReferencePoint\", \"Procedure\", \"Drug\", \"Measurement\", \"Value\", \"Person\", \"Multiplier\", \"Device\", \"Qualifier\", \"Mood\", \"Temporal\", \"Condition\", \"Visit\", \"Scope\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities are found for a type, use [].\n\nText:\n\nSubjects with hemoglobin SC or SB+ thalassemia \nSubjects on chronic transfusion program \nSubjects who have received RBC transfusions cannot have >15% adult hemoglobin \nKnown positive status for HIV, active hepatitis B or hepatitis C \nPregnant or breast feeding women \nIndividuals with a history of malignancy are ineligible except for the following circumstances. Individuals with a history of malignancy are eligible if they have been disease-free for at least 5 years and are deemed by the investigator to be at low risk for recurrence of that malignancy. Individuals with the following cancer are eligible if diagnosed and adequately treated within the past 5 years: cervical or breast cancer in situ, and basal cell or squamous cell carcinoma of the skin \nSubjects with a history of thrombosis or other reason (other than sickle cell disease) for enhanced thrombotic risk \nSubjects with unresolved infections \nSevere or uncontrolled medical conditions that could compromise study participation \nSubjects on fetal hemoglobin inducing agents \nSubjects on any other experimental treatment within 90 days of the first dose of study drug or who have not recovered from the side effects of such therapy \nKnown allergic reaction to a histone deacetylase inhibitor \nSubjects who have received valproic acid for treatment of epilepsy within 30 days of enrollment \nSubjects who have received any HDAC inhibitors other than valproic acid",
"role": "user"
},
{
"content": "{\"Condition\": [\"HIV\", \"malignancy\", \"disease-free\", \"breast cancer in situ\", \"hemoglobin SC\", \"thrombotic\", \"Pregnant\", \"medical conditions\", \"cervical cancer in situ\", \"basal cell carcinoma of the skin\", \"infections\", \"squamous cell carcinoma of the skin\", \"recurrence of that malignancy\", \"SB+ thalassemia\", \"hepatitis C\", \"hepatitis B\", \"epilepsy\", \"thrombosis\", \"allergic reaction\", \"sickle cell disease\", \"that malignancy\", \"thrombotic risk\"], \"Device\": [], \"Drug\": [\"HDAC inhibitors\", \"histone deacetylase inhibitor\", \"valproic acid\", \"fetal hemoglobin inducing agents\"], \"Measurement\": [], \"Mood\": [\"diagnosed\", \"low risk\", \"adequately treated\", \"enhanced risk\"], \"Multiplier\": [\"chronic\"], \"Negation\": [\"cannot have\", \"other than\", \"are eligible\"], \"Observation\": [\"breast feeding\", \"history\"], \"Person\": [\"women\"], \"Procedure\": [\"RBC transfusions\", \"treatment\", \"treated\", \"transfusion program\"], \"Qualifier\": [\"adequately\", \"unresolved\", \"chronic\", \"compromise study participation\", \"fetal\"], \"ReferencePoint\": [\"enrollment\"], \"Scope\": [], \"Temporal\": [\"within the past 5 years\", \"for at least 5 years\", \"within 30 days of enrollment\", \"active\"], \"Value\": [\"\\u003e15% adult hemoglobin\"], \"Visit\": []}",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.23687
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nCo-occurrence Data is a common and important information source in many areas, such as the word co-occurrence in the sentences, friends co-occurrence in social networks and products co-occurrence in commercial transaction data, etc, which contains rich correlation and clustering information about the items. In this paper, we study co-occurrence data using a general energy-based probabilistic model, and we analyze three different categories of energy-based model, namely, the @math , @math and @math models, which are able to capture different levels of dependency in the co-occurrence data. We also discuss how several typical existing models are related to these three types of energy models, including the Fully Visible Boltzmann Machine (FVBM) ( @math ), Matrix Factorization ( @math ), Log-BiLinear (LBL) models ( @math ), and the Restricted Boltzmann Machine (RBM) model ( @math ). Then, we propose a Deep Embedding Model (DEM) (an @math model) from the energy model in a manner. Furthermore, motivated by the observation that the partition function in the energy model is intractable and the fact that the major objective of modeling the co-occurrence data is to predict using the conditional probability, we apply the method to learn DEM. In consequence, the developed model and its learning method naturally avoid the above difficulties and can be easily used to compute the conditional probability in prediction. Interestingly, our method is equivalent to learning a special structured deep neural network using back-propagation and a special sampling strategy, which makes it scalable on large-scale datasets. Finally, in the experiments, we show that the DEM can achieve comparable or better results than state-of-the-art methods on datasets across several application domains.\n\nCited Abstract(s):\n[1]: We consider estimation methods for the class of continuous-data energy based models (EBMs). Our main result shows that estimating the parameters of an EBM using score matching when the conditional distribution over the visible units is Gaussian corresponds to training a particular form of regularized autoencoder. We show how different Gaussian EBMs lead to different autoencoder architectures, providing deep links between these two families of models. We compare the score matching estimator for the mPoT model, a particular Gaussian EBM, to several other training methods on a variety of tasks including image denoising and unsupervised feature extraction. We show that the regularization function induced by score matching leads to superior classification performance relative to a standard autoencoder. We also show that score matching yields classification results that are indistinguishable from better-known stochastic approximation maximum likelihood estimators.\n\n[2]: Recent work has shown how denoising and contractive autoencoders implicitly capture the structure of the data-generating density, in the case where the corruption noise is Gaussian, the reconstruction error is the squared error, and the data is continuous-valued. This has led to various proposals for sampling from this implicitly learned density function, using Langevin and Metropolis-Hastings MCMC. However, it remained unclear how to connect the training procedure of regularized auto-encoders to the implicit estimation of the underlying data-generating distribution when the data are discrete, or using other forms of corruption process and reconstruction errors. Another issue is the mathematical justification which is only valid in the limit of small corruption noise. We propose here a different attack on the problem, which deals with all these issues: arbitrary (but noisy enough) corruption, arbitrary reconstruction loss (seen as a log-likelihood), handling both discrete and continuous-valued variables, and removing the bias due to non-infinitesimal corruption noise (or non-infinitesimal contractive penalty).\n\n[3]: Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful intermediate representations. We introduce and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern. This approach can be used to train autoencoders, and these denoising autoencoders can be stacked to initialize deep architectures. The algorithm can be motivated from a manifold learning and information theoretic perspective or from a generative model perspective. Comparative experiments clearly show the surprising advantage of corrupting the input of autoencoders on a pattern classification benchmark suite.\n\n[4]: Denoising autoencoders have been previously shown to be competitive alternatives to restricted Boltzmann machines for unsupervised pretraining of each layer of a deep architecture. We show that a simple denoising autoencoder training criterion is equivalent to matching the score (with respect to the data) of a specific energy-based model to that of a nonparametric Parzen density estimator of the data. This yields several useful insights. It defines a proper probabilistic model for the denoising autoencoder technique, which makes it in principle possible to sample from them or rank examples by their energy. It suggests a different way to apply score matching that is related to learning to denoise and does not require computing second derivatives. It justifies the use of tied weights between the encoder and decoder and suggests ways to extend the success of denoising autoencoders to a larger family of energy-based models.",
"role": "user"
},
{
"content": "DEM is also closely related to the autoencoder [3] models, which contains two components: encoder and decoder. The encoder maps the input data to hidden states, while the decoder reconstructs the input data from the hidden states. There are also some studies to connect denoising auto encoder to generative learning [2] [4] [1] . Indeed, DEM could be also viewed as an special case of denoising autoencoder. In encoder phase, the input data is corrupted by randomly dropping one element, and is then fed into the encoder function to generate the hierarchical latent embedding vectors. Then, in the decoding phase, the missing items are reconstructed from latent vectors afterwards.",
"role": "assistant"
}
] |
science.acl_arc_intent_classification
|
science.acl_arc_intent_classification.482
|
[
{
"content": "Classify the intent of this citation from an NLP research paper. \n\nYour answer must be one word from: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. No other text allowed.\n\nSection Title:\nNone\n\nContext before:\nSemantic filters can also be used to prevent multiple versions of the same case frame (Fillmore 1968) showing up as complements. In this case, the verb has no information concerning its subject, and so it identifies it as an unbound pronoun. Finally, in the case of passive voice, the CURRENT-FOCUS slot is empty at the time the verb is proposed, because the CURRENT-FOCUS which was the surface-form subject has been moved to the float-object position.\n\nCitation:\nSemantic filters can also be used to prevent multiple versions of the same case frame ( Fillmore 1968 ) showing up as complements .\n\nContext after:\nFor instance, the set of complements [from-place], [to-place], and [at-time] are freely ordered following a movement verb such as "leave." Thus a flight can "leave for Chicago from Boston at nine," or, equivalently, "leave at nine for Chicago from Boston." If these complements are each allowed to follow the other, then in TINA an infinite sequence of [from-place's, [to-place]s and [at-time]s is possible. This is of course unacceptable, but it is straightforward to have each node, as it occurs, or in a semantic bit specifying its case frame, and, in turn, fail if that bit has already been set.",
"role": "user"
},
{
"content": "Uses",
"role": "assistant"
}
] |
science.chemdner_ner
|
science.chemdner_ner.568
|
[
{
"content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nReal-time fluorescence turn-on detection of alkaline phosphatase activity with a novel perylene probe. A tetracationic perylene probe (probe 1) was designed and synthesized. Probe 1 was used for the real-time fluorescence turn-on assay of alkaline phosphatase (ALP) activity and inhibitor screening. Probe 1 monomer fluorescence could be very efficiently quenched by ATP through the formation of an ATP/probe 1 complex. ALP triggered the degradation of ATP, the breakdown of the ATP/probe 1 complex, and the recovery of the probe 1 monomer fluorescence. In the presence of an ALP inhibitor, a decrease in fluorescence recovery was observed.",
"role": "user"
},
{
"content": "{\"Chemical\": [\"perylene\"]}",
"role": "assistant"
}
] |
science.medmentions_ner
|
science.medmentions_ner.2557
|
[
{
"content": "Extract all unique entities from this biomedical abstract. Only choose entities from these types: [\"Virus\", \"MedicalDevice\", \"BodySubstance\", \"SpatialConcept\", \"BiologicFunction\", \"ResearchActivity\", \"AnatomicalStructure\", \"ProfessionalOrOccupationalGroup\", \"HealthCareActivity\", \"BiomedicalOccupationOrDiscipline\", \"Bacterium\", \"Chemical\", \"InjuryOrPoisoning\", \"IntellectualProduct\", \"Finding\", \"ClinicalAttribute\", \"Organization\", \"Eukaryote\", \"Food\", \"BodySystem\", \"PopulationGroup\"].\n\nOutput a JSON object where keys are entity types and values are lists of extracted entities. If no entities found for a type, use empty list [].\n\nAbstract: Clinical application and outcomes of sentinel node navigation surgery in patients with early gastric cancer Sentinel node navigation surgery (SNNS) has been recognized as a minimally invasive tool for individualized lymphadenectomy in patients with early gastric cancer (EGC). The aim of this study was to compare clinicopathological factors, adverse events, and clinical outcomes between sentinel node mapping (SNM) and SN dissection (SND) groups and assess the clinical utility of SNNS in patients with EGC. The clinical data of 157 patients with EGC, diagnosed as clinical T1N0M0 with tumors ≤ 40 mm, undergoing SNNS between March 2004 and April 2016 were retrospectively reviewed. Twenty-seven patients were excluded from the analysis. In the remaining 130 patients, 59 and 71 patients underwent standard lymphadenectomy for SNM and SND, respectively. The sentinel node detection rate in the SNM and SND groups was 98.3% (58/59) and 100% (71/71), respectively. Two (3.5%), 15 (25.9%), and 41 (70.7%) patients having sentinel nodes underwent total gastrectomy, proximal gastrectomy (PG), and distal gastrectomy (DG), respectively, in the SNM group. One (1.4%), 5 (7.0%), 10 (14.1%), 39 (54.9%), and 16 (22.5%) patients underwent PG, DG, segmental gastrectomy, local resection, and endoscopic submucosal dissection, respectively, in the SND group. There was no significant difference in postoperative complications between the SNM and SND groups (P = 0.781). Survival did not differ between the both groups (P = 0.856). The present results suggest that personalized surgery with SND provides technical safety and curability related with a favorable survival outcome in patients with EGC.",
"role": "user"
},
{
"content": "{\"AnatomicalStructure\": [\"sentinel node\", \"sentinel nodes\"], \"Bacterium\": [], \"BiologicFunction\": [\"T1N0M0 with tumors\", \"adverse events\", \"EGC\", \"postoperative complications\", \"early gastric cancer\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"diagnosed\"], \"Food\": [], \"HealthCareActivity\": [\"SN dissection\", \"SNM\", \"lymphadenectomy\", \"sentinel node navigation surgery\", \"sentinel node mapping\", \"distal gastrectomy\", \"surgery\", \"SNNS\", \"gastrectomy\", \"DG\", \"endoscopic submucosal dissection\", \"Sentinel node navigation surgery\", \"SND\", \"local resection\", \"PG\", \"detection\", \"proximal gastrectomy\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"clinical data\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"study\", \"analysis\"], \"SpatialConcept\": [\"segmental\"], \"Virus\": []}",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.1968
|
[
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nEffect of device-guided breathing exercises on blood pressure in patients with hypertension : a randomized controlled trial . OBJECTIVE Hypertension is a chronic disorder with a high prevalence worldwide . Despite considerable efforts , it is sometimes hard to reach treatment goals for blood pressure ( BP ) with classical treatment options . Reducing breathing frequency has been advocated as a method to reduce BP . METHODS A randomized , single-blind , controlled trial was conducted in 30 non-diabetic patients with hypertension over a period of 9 weeks to evaluate the effect of a device that helps to slow breathing ( Resperate ) on BP and quality of life ( QoL ) . The control group listened to music and used no other therapeutic device . RESULTS There was no significant difference in change in BP between intervention and control ; BP -4.2 mmHg ( 95 % CI -12.4 to 3.9 ) /-2.6 mmHg ( 95 % CI -8.4 to 3.3 ) . This result did not alter in post hoc analyses , when patients not achieving target breathing frequency ( < 10 breaths/min ) or non-compliant patients were excluded . QoL did not change over time . CONCLUSIONS We found no effect of the Resperate on BP or QoL compared with the control group . We conclude that , at this moment , this device has no added value in the treatment of hypertension .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"device-guided breathing exercises\", \"device that helps to slow breathing ( Resperate )\", \"listened to music and used no other therapeutic device\"], \"Outcome\": [\"blood pressure\", \"slow breathing\", \"BP\", \"quality of life ( QoL )\", \"blood pressure ( BP )\", \"target breathing frequency\", \"QoL\"], \"Participant\": [\"non-diabetic patients with hypertension\", \"hypertension\", \"30\"]}",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.75513
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Offshore Country Selection Risk Management Model: Systematic Literature Review Protocol \nChapter Title: INTRODUCTION \n1. Abstract of Cited Paper (BIB001): Chapter 1. The Development of Outsourcing Theory and Practice: Taxonomy of Outsourcing Generations Chapter 2. Making Sense of the Sourcing and Shoring Maze: The Various Outsourcing and Offshoring Alternatives Chapter 3. Global Sourcing: East-West Divide or Synthesis? Chapter 4. Strategies of Outsourcing: From De-risking to Uncertainty Chapter 5. New Ethics for E-Business Offshore Outsourcing Chapter 6. Information Technology Offshore Outsourcing: A Perspective of Advanced Countries Chapter 7. Business Process Outsourcing to Emerging Markets: A Knowledge Management Approach to Models and Strategies Chapter 8. Outsourcing Decision-Making: A Review of Strategic Frameworks and Proposal of a Multi-Perspective Approach Chapter 9. Outsourcing and Offshoring: Issues and Impacts on Venture Capital Chapter 10. Outsourcing and Offshoring of Finance Activities Chapter 11. Open Source and Outsourcing: A Perspective on Software Use and Professional Practices Related to International Outsourcing Activities Chapter 12. Real Life Case Studies of Offshore Outsourced IS Projects: Analysis of Issues and Socio-Economic Paradigms Chapter 13. Growth of Outsourced IT-enabled Services in India: A Systems Dynamics Approach Chapter 14. An Overview of Service Level Agreements Chapter 15. Understanding Consumer Reactions to Offshore Outsourcing of Customer Services Chapter 16. IT Offshoring: A German Perspective Chapter 17. Information Systems/Information Technology Outsourcing in Spain: A Critical Empirical Analysis Chapter 18. Emerging Legal Challenges in Offshore Outsourcing of IT-enabled Services Chapter 19. Does Strategic Outsourcing Undermine the Innovative Capabilities of Organizations? Chapter 20. Analysis of a Largescale IT Outsourcing \"Failure\": What Lessons Can We Learn? \n2. Abstract of Cited Paper (BIB002): We studied a supplier selection problem, where a buyer, while facing random demand, is to decide ordering quantities from a set of suppliers with different yields and prices. We provided the mathematical formulation for the buyer's profit maximization problem and proposed a solution method based on a combination of the active set method and the Newton search procedure. Our computational study shows that the proposed method can solve the problem efficiently, and is able to generate interesting and insightful results that lead us to various managerial implications. Scope and purpose: In today's globally competitive environment, decision makers in supply chains face numerous challenges particularly regarding the selection of suppliers or outsourcing partners. To assist in this endeavor, we examined a double-layered supply chain where a buyer facing the end users has the option of selecting among a cohort of suppliers. The available suppliers may have different yield rates and unit costs. The buyer has to decide, given the stochastic nature of the problem's governing parameters, whether or not to order from each supplier, and if so how much. We developed a 'newsvendor-style' model for the problem, and proposed a solution algorithm for it. Numerical studies were performed to provide some insights for supplier selection and order quantity decisions. \n3. Abstract of Cited Paper (BIB003): Supplier selection and inventory control are critical decision processes in single-item multiple-supplier systems. An integer linear programming model is proposed to help managers determine the reorder level, choose the best suppliers, and place the optimum order quantities so that the total average inventory cost is minimum, and constraints of supplier ability, quality, and demand are considered. An algorithm combining the branch-bound algorithm and enumeration algorithm is developed to solve the problems. Application of the proposed model in an automobile industry shows that it is effective. \n4. Abstract of Cited Paper (BIB004): In today's global services outsourcing arena, increasing numbers of companies adopt “multisourcing,” that is, they select and combine information technology (IT) and business services from multiple providers. The literature on IT outsourcing and supply chain management has identified critical tradeoffs involved in increasing the number of suppliers and has strongly recommended focusing on a handful of strategic partners to balance these tradeoffs. Committing to a few strategic partners, however, may prevent a firm from discovering new suppliers, or even supply regions. Such missed opportunities may be particularly limiting in the context of offshoring professional services, which has exhibited rapid changes in supplier markets in the last decade. Thus, firms may want to engage in a more intensive multisourcing in services. If they do so, their success will depend on a global sourcing process that effectively addresses the critical tradeoffs involved. To explore how a global sourcing process can support multisourcing, we conducted a qualitative longitudinal case study of a large financial services institution that developed a varied global supply base to obtain offshore professional services. Our analysis results in a theory that emphasizes (i) advantages of a multiple provider strategy in rapidly changing global supply markets; (ii) the critical role of middle managers in enabling continuous innovation in the supplier structure; and (iii) the importance of the global sourcing process combining top–down and bottom–up decision making in multisourcing. \n5. Abstract of Cited Paper (BIB005): Context: Software development outsourcing is a contract-based relationship between client and vendor organisations in which a client contracts out all or part of its software development activities to a vendor, who provides agreed services for remuneration. Objective: The objective is to identify various barriers that have a negative impact on software outsourcing clients in the selection process of offshore software development outsourcing vendors. Method: We have performed a systematic literature review (SLR) process for the identification of barriers. We have performed all the SLR steps such as the protocol development, initial selection, final selection, quality assessment, data extraction and data synthesis. Results: We have identified barriers such as 'language and cultural barriers', 'country instability', 'lack of project management', 'lack of protection for intellectual property rights' and 'lack of technical capability' that generally have a negative impact on outsourcing clients. We have identified only one common frequently cited barrier in three types of organisations (i.e. small, medium and large) which is 'language and cultural barriers'. We did not identify any common frequently cited barrier in three continents (Asia, North America and Europe) and in two decades (1990-1999 and 2000-mid 2008). The results also reveal the similarities and differences in the barriers identified through different study strategies. Conclusions: Vendors should address frequently cited barriers such as 'language and cultural barriers', 'country instability', 'lack of project management', 'lack of protection for intellectual property rights' and 'lack of technical capability' in order to compete in the offshore outsourcing business.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Software development outsourcing is a contractual business relationship between client and vendor organizations in which a client(s) outsources out all or some part of its software development activities to a vendor(s) organization. The vendor organization in turn provides agreed services for certain amount of remuneration BIB006 . Offshore outsourcing also known as far shore outsourcing is like an international trade through which the nations get considerable benefits . The main reason for choosing this methodology is due to its cost effectiveness and access to leading-edge technology, huge pool of skilled labor, high quality standard software development and round the clock services BIB002 . The availability of these skilled resources and effective costs are the primary motivators for software businesses to move to software development activities offshore [4] . Software development outsourcing is becoming very complex, difficult and challenging technique in the context of software project management due to the probability of unwanted threats called risks that can have a negative impact on outsourcing project BIB004 BIB001 . The risks that mostly occur in software outsourcing are much different than the risks of local software development. Even a very small risk becomes serious catastrophic risk in software outsourcing development 9] . Software risks should be identified controlled and monitor from the start phase of software outsourcing management life cycle . To avoid threats and to reap opportunities in software outsourcing a client organization needs to explore and identify the possible risks and plan to mitigate and manage these for the effective standard software development BIB001 . There are a lot number of risks as identified in BIB003 that need to be addressed by client organizations for outsourcing success. One of the major risks, which is responsible for controlling and monitoring the quality of a product, is the criteria for the distribution of software development activities to offshore countries. So the decision of country selection and its company's evaluation around the world is a time consuming and difficult problem to be solved. However, based on the expertise, relationship, culture, productivity, skilled developers, ease of communication, languages spoken, distance and coordination, manager of a client organization can decide BIB005 . Based on the risk identification and management principle proposed in and the framework of risks associated with offshore outsourcing software development , it is very clear that in offshore outsourcing software development, risks identification and management is conducted in various phases, in which the major phase is concerned with the selection of suitable offshore country based on the nature of software development activities. In the context of OSDO, however, client organization without proper knowledge could encounter miserable performance. OCSRMM has outlined various criteria for offshore country selection that must be followed for successful offshore outsourcing. The main objective of this research is to gain an in-depth and more thoroughly understanding of the potential risks in the contexts of OCS from client's organization perspective and to develop a plan for the management of identified risks.",
"role": "assistant"
}
] |
science.chemsum_single_document_summarization
|
science.chemsum_single_document_summarization.55298
|
[
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nAmino Acid-Derived Sensors For Specific Zn2+ Detection Using Hyperpolarized 13C Magnetic Resonance Spectroscopy\n\nPaper sections:\n\n<p>Zinc (Zn2+) is the second most abundant transition metal ion in the human body and plays various structural, regulatory and catalytic functions in physiology.1,2 Multiple methods for the measurement of Zn2+ concentration have been investigated as biomarkers for human disease, including blood and tissue tests, and imaging methods.3 Existing imaging techniques include fluorescence and magnetic resonance-based approaches. Small-molecule fluorescent agents with varying Zn2+ affinities have been used to image live cells4,5,6 Magnetic resonance imaging (MRI) using Zn2+-responsive contrast agents has been proposed as an alternative imaging method that would allow non-invasive high-resolution monitoring of Zn2+ metabolism. Although there has been some success using manganese-derived probes7 and paramagnetic chemical exchange saturation transfer agents,8 most reported Zn2+-responsive MRI agents are gadolinium-based.9,10</p><p>Enabled by hyperpolarization techniques such as dynamic nuclear polarization (DNP) and parahydrogen induced polarization (PHIP),11–14 hyperpolarized (HP) probes for in vivo detection of a variety of analytes using HP 13C MRS have been developed.15,16 Hyperpolarized EDTA and EGTA were reported for multi-metal imaging.17 Here, we explored the use of HP 13C MRS for Zn2+-specific imaging. In particular, we identified L-cysteine-1-13C ([1-13C]Cys) and iminodiacetic acid-1-13C2 ([1-13C2]IDA) as candidate probes that demonstrate altered magnetic properties upon binding Zn2+, optimized their polarization parameters, and demonstrated that [1-13C]Cys can accurately measure Zn2+ using 13C HP MRS in phantoms and biological samples (Figure 1A).</p><p>We considered the requirements for a potential hyperpolarized Zn2+ imaging probe to include 1) a large change in 13C chemical shift in the presence of Zn2+, 2) good selectivity to Zn2+ over biologically abundant cations such as Ca2+ and Mg2+, 3) insensitivity to changes in pH over the physiologic range, 4) a sufficient T1 relaxation time for MRI, and 5) lack of known or predicted toxicity. We began our study by screening a variety of candidate Zn2+ ligands for their chemical shift response upon Zn2+ binding. Among the 34 tested compounds, 10 ligands demonstrated a chemical shift response to Zn2+ binding. We noted that ligands with logarithm of stability constants of Zn2+ (logK) greater than 6.9 all displayed a chemical shift response to Zn2+ binding, while ligands with logK lower than 5.2 did not have a chemical shift response to Zn2+ binding (SI Table S1). Ligands bearing a soft functional group such as pyridine tended to show a chemical shift response at lower Zn2+ stability constants while ligands with hard functional groups, such as hydroxyl showed a chemical shift response at higher stability constants. Cysteine and iminodiacetic acid were selected for further evaluation because of their large chemical shift response to Zn2+ binding (+4.6 and +7.3 ppm in the presence of equimolar Zn2+, respectively), excellent water solubility, low molecular weight, predicting a long 13C T1, and convenience for 13C labeling. 13C-labeled cysteine was commercially available, and 13C-labeled IDA was synthesized from [1-13C]glycine and [1-13C]methyl bromoacetate in 3 steps with a 32% total yield (Scheme 1). Their specificity for Zn2+ versus other abundant physiologic cations and their sensitivity to pH changes were also tested. Both probes showed excellent specificity for Zn2+ over other main physiologic cations Na+, K+, Ca2+ and Mg2+, and limited chemical shift change over the physiologic pH range of 6.5 to 7.4 (Figure 1B). These preliminary investigations suggested that [1-13C]Cys and [1-13C2]IDA would be specific and sensitive probes for detecting Zn2+ using HP 13C MRI.</p><p>A quantitative method for determining Zn2+ concentration was developed for these probes using NMR. A titration curve was plotted to show the chemical shift difference between [1-13C]Cys and internal standard urea as a function of the Zn2+ to [1-13C]Cys ratio. The peak moved linearly with increasing Zn2+ up to 0.25 equivalents of Zn2+ to [1-13C]Cys. The rate of chemical shift change decreased at higher Zn2+ concentrations (Figure 2A, 2B, SI Table S2, SI equation S1). This suggests that [1-13C]Cys may have multiple Zn2+ binding conformations, as previously reported.18,19 The manifestation of the 13C signal as a single resonance indicates that the on-off rates for Zn2+ binding are rapid, compared with the absolute frequency difference between bound/unbound 13C resonances. A linewidth change with different Zn2+/[1-13C]Cys ratios was also observed. In particular, the linewidth increased significantly at lower Zn2+ concentrations with the widest linewidth being between 0.2 eq and 0.5 eq of [1-13C]Cys, thus demonstrating exchange broadening at different Zn2+/[1-13C]Cys ratios (SI Table S3). The chemical shift change of [1-13C]Cys with equimolar Zn2+ was tested at different temperatures ranging from 20 °C to 50 °C and at various [1-13C]Cys concentrations from 1 mM to 100 mM. These studies showed that the temperature and concentration of [1-13C]Cys (in the presence of equimolar zinc) had little or no influence on the chemical shift response (SI Tables S3 and S4).</p><p>A similar titration method was utilized for IDA for quantitative determination of Zn2+ concentration. When Zn2+ was added to [1-13C2]IDA, a new resonance at a lower field appeared. The area under the peak (integration) increased linearly with increasing Zn2+ concentration from 0 to 0.5 equivalents of Zn2+ to [1-13C2]IDA, which indicates that [1-13C2]IDA binds to Zn2+ with a 2:1 probe:Zn stoichiometry, as previously reported (Figure 2C, 2D).20 Additionally, the unbound [1-13C2]IDA peak demonstrated increasing line broadening in response to Zn2+ (SI Table S5). It is worth noting that the [1-13C2]IDA:Zn complex appears as two separate peaks while the [1-13C]Cys:Zn complex appears as a single peak, indicating that the on and off rates for [1-13C2]IDA are slower than the frequency difference between bound and unbound resonances and the on and off rates for [1-13C]Cys are more rapid. These results are analogous to prior findings in 15N, 19F, and hyperpolarized 13C pH imaging probe development efforts.21–27 Overall, these data demonstrate that the chemical shift of the 1-13C NMR signal of cysteine and IDA change in a predictable and quantitative manner in response to Zn2+ concentration.</p><p>Next, we developed and optimized a hyperpolarization method for 13C labeled [1-13C]Cys and [1-13C2]IDA. For [1-13C]Cys, the optimized preparation was obtained by a mixture of 1.0 eq of [1-13C]Cys, 0.5 eq of 4N HCl and 2.65 eq of glycerol, with 20 mM OX063 radical.28 Using this method, 13.4 ± 0.6% back-calculated polarization was obtained with a polarization time constant of 1227 ± 30 (n = 3). The T1 relaxation time was 36.0 ± 1.8 seconds at a magnetic field of 3T. A Zn2+-dependent decrease in T1 of [1-13C]Cys was observed when polarized [1-13C]Cys was mixed with various equivalents of Zn2+. A T1 of 17.5 seconds was observed when 1 equivalent of Zn2+ was present (Table S6). For [1-13C2]IDA, the optimized preparation included a mixture of 1.0 eq of [1-13C2]IDA disodium salt, 14.0 eq of D2O and 1.8 eq of DMSO, with 15 mM OX063.17 Using this method, 6.6 ± 0.9% (n = 3) back-calculated polarization was obtained with the polarization time constant of 1480 ± 38 (n = 3). The T1 was 39.3 ± 1.0 seconds at 3T. The T1 of both bound and unbound [1-13C2]IDA resonances were also Zn2+ dependent, with the T1 decreasing to 16.6 seconds when 1 eq of Zn2+ was present (Figure 3, SI Table S7). We hypothesize that the decrease in T1 is due to an increase in molecular weight of the complex.29 The high percent polarization, and relatively long T1 of the Zn2+ ligands suggested feasibility for subsequent imaging experiments.</p><p>The ability of the probes to image Zn2+ concentration was tested using phantoms on a 3T MRI system. For cysteine, a copolarization method, as we have previously reported, was developed with [1-13C]urea as a chemical shift standard.23 A four-compartment phantom containing various Zn2+ concentrations in each compartment was prepared (Figure 4A, B). As in the thermal equilibrium measurements, a chemical shift change was observed in response to Zn2+ in the 13C cysteine spectrum. By using the best-fit linear model of chemical shift asFigure 3 a function of Zn2+ concentration (Figure 2B inset), hyperpolarized [1-13C]Cys was able to accurately determine the concentration over the physiologically relevant range of 0.2 – 20 mM Zn2+. At the highest tested Zn2+ concentration of 40 mM, a slight deviation was observed, possibly due to signal loss and/or line broadening.</p><p>A phantom imaging experiment to determine the sensitivity showed that HP [1-13C]Cys can detect 200 μM of Zn2+ when 4 mM of [1-13C]Cys was present (Figure 4B). When hyperpolarized [1-13C2]IDA was tested in a phantom for Zn2+ imaging, the Zn2+ bound [1-13C2]IDA peak appeared when more Zn2+ was present. The line broadening of both the Zn2+ bound and unbound peaks of [1-13C2]IDA resulted in a loss of SNR between 0.2 eq Zn2+ and 0.3 eq Zn2+ (SI Figure S2). For this reason, accurate Zn2+ concentrations could not be obtained using this probe. Overall, these phantom experiments demonstrated that hyperpolarized [1-13C]Cys is a sensitive and accurate Zn2+ biosensor over the physiologic range, while issues with line broadening and signal loss limit the applicability of [1-13C2]IDA.</p><p>Finally, we verified that HP [1-13C]Cys could accurately determine Zn2+ concentration in biological samples (Figure 5) by comparing imaging results against a commercially available fluorescence based Zn2+ quantification kit. Rat serum and prostate extracts were selected as biological samples with low and high Zn2+ concentration, respectively. In these samples, the Zn2+ concentration was accurately measured at 0.1 and 1.9 mM, respectively. The HP and kit Zn2+ measurements agreed within 0.1 mM. In order to verify that the signal change in these samples represented a specific response to Zn2+, additional tubes including serum spiked with exogenous Zn2+, and a prostate sample with additional tris(2-pyridylmethyl)amine (TPA), a high-affinity and specific chelator, were investigated.30 We found that the Zn2+ concentration was accurately measured in the spiked serum sample, and that the addition of the TPA to the prostate extract blocked the chemical shift change. These data confirm that Zn2+ is both necessary and sufficient to induce the chemical shift change in cysteine, and moreover that this probe accurately and specifically determines Zn2+ concentration in complex biological samples.</p><p>For future in vivo applications, [1-13C]Cys in particular demonstrates both possible advantages and limitations compared against existing techniques. Owing to the short lifetime of the signal, it is unlikely that it would be internalized into cells in a time course reasonable to measure intracellular zinc concentration. Therefore, this method would likely be restricted to extracellular space Zn2+ imaging. However, zinc can be secreted from tissues including pancreas and prostate in response to glucose treatment. For example, Sherry et al. have developed imaging methods to detect the release of Zn2+ ions from β-cells in response to high glucose,31 as well as to differentiate between healthy and malignant prostate tissue in mouse models.32 Such a model could applied for initial in vivo testing of these probes. An additional limitation could be metabolic transformation, which could confound interpretation of spectroscopic data. Toxicity concerns are unlikely based on the known toxicology profile of cysteine.33 The majority of Zn2+ imaging probes are gadolinium-based contrast agents, which face the concern of their deposition in brain and environment, a concern which would be avoided in this case.34 A final potential benefit of this method is the broad range of zinc concentration in serum and other tissues, potentially enabling high image contrast. Overall, these preliminary data suggest both possibilities and limitations for future in vivo applications of these methods.</p><p>Taken together, these data demonstrate that [1-13C]Cys and [1-13C2]IDA represent promising probes for imaging Zn2+ using hyperpolarized 13C MRI. The probes demonstrate large changes in signal and chemical shift in response to Zn2+, excellent selectivity over other biologically relevant cations and changes in pH, favorable T1 and polarization parameters, and can be imaged in phantom experiments. [1-13C]Cys accurately quantified Zn2+ concentration in biological samples at physiologically relevant concentrations. For this reason, [1-13C]Cys is a particularly promising probe for future in vivo hyperpolarized magnetic resonance imaging of pathologies with alterations in Zn2+ homeostasis such as prostate cancer, neurodegenerative disease, and diabetes.</p>",
"role": "user"
},
{
"content": "Alterations in Zn2+ concentration are seen in normal tissues and in disease states, and for this reason imaging of Zn2+ is an area of active investigation. Herein, enriched [1-13C]cysteine and [1-13C2]iminodiacetic acid were developed as Zn2+-specific imaging probes using hyperpolarized 13C magnetic resonance spectroscopy. [1-13C]cysteine was used to accurately quantify Zn2+ in complex biological mixtures. These sensors can be employed to detect Zn2+ via imaging mechanisms including changes in 13C chemical shift, resonance linewidth, or T1.",
"role": "assistant"
}
] |
science.bioasq_general_qa
|
science.bioasq_general_qa.36
|
[
{
"content": "Answer the following question using the provided context. Only provide the answer without any additional text.\n\nQuestion: What is the treatment of acute pericarditis?\nContext: Recurrences develop in up to 20-50% of patients with acute pericarditis. Although different causes of recurrent pericarditis have been identified, the etiology remains obscure in most cases which are therefore labelled as idiopathic.\nA poor response to colchicine treatment and/or a steroid-dependence may be the clue to investigate TNFRSF1A mutations in patients with idiopathic recurrent pericarditis.\nintravenous infusion of inotropic agents\nmedical treatment may be changed in these patients with a slower tapering of the dosage of steroidal and non-steroidal antiinflammatory drugs.\nThe incidence of purulent pericarditis has decreased considerably since the antibiotic era. It is typically an acute and potentially lethal disease, necessitating rapid diagnosis and adequate therapy to improve prognosis. Standard treatment combines appropriate antibiotic therapy with surgical drainage.\nWe report successful treatment of a non-resolving fibrino-purulent pericardial effusion by combined intrapericardial irrigation of fibrinolytics and systemic corticosteroids administration as an alternative to pericardectomy.\nPrednisolone (20-30 mg/d) was used in addition to antituberculous chemotherapy in 11 of the 17 patients with effusive pericarditis\nantibiotic therapy has been initiated. Use of appropriate parenterally administered antibiotics, in combination with early surgical pericardial drainage or partial pericardiectomy, should minimize morbidity and mortality and prevent acute constrictive sequelae.",
"role": "user"
},
{
"content": "A multidisciplinary approach is frequently necessary to treat acute pericarditis; the most frequent treatments are: antiinflammatory steroid and non-steroid drugs, antibiotic therapy, pericardial drainage and, less frequently ,intrapericardial irrigation of fibrinolytics; antituberculous chemotherapy in presence of Tuberculous Agent",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_plos_single_doc_summ
|
science.scientific_lay_summarisation_plos_single_doc_summ.3830
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Cell Fate Regulation Governed by a Repurposed Bacterial Histidine Kinase\nArticle:\nAbstract:\nOne of the simplest organisms to divide asymmetrically is the bacterium Caulobacter crescentus. The DivL pseudo-histidine kinase, positioned at one cell pole, regulates cell-fate by controlling the activation of the global transcription factor CtrA via an interaction with the response regulator( RR) DivK. DivL uniquely contains a tyrosine at the histidine phosphorylation site, and can achieve these regulatory functions in vivo without kinase activity. Determination of the DivL crystal structure and biochemical analysis of wild-type and site-specific DivL mutants revealed that the DivL PAS domains regulate binding specificity for DivK∼P over DivK, which is modulated by an allosteric intramolecular interaction between adjacent domains. We discovered that DivL's catalytic domains have been repurposed as a phosphospecific RR input sensor, thereby reversing the flow of information observed in conventional histidine kinase( HK)-RR systems and coupling a complex network of signaling proteins for cell-fate regulation.\nIntroduction:\nCell fate decisions driven by the spatial organization of signaling proteins are a hallmark of asymmetric divisions in systems as diverse as stem cells and bacteria. Caulobacter, a model system for localization-dependent signaling network studies, divides asymmetrically yielding two distinct daughter cells: a motile swarmer cell and a replication-competent stalked cell( Figure 1). Cell division in Caulobacter is a stepwise process that includes a cytoplasmic compartmentalization stage[1] during which the inner membrane closes to form a barrier between the incipient swarmer and stalked cell compartments( Figure 1A)[2],[3]. This event segregates crucial signaling proteins[2],[4],[5] and culminates in the swarmer cell-specific activation of the global transcriptional regulator CtrA( Figure 1B)[6], which controls the expression of more than 100 genes involved in cell division and asymmetric polar organelle development[7]. The two daughter cells are distinguished by a compartment-sensing module composed of the response regulator( RR) DivK and two histidine kinases( HKs), DivJ and PleC, which differentially regulate the CtrA signaling pathway upon compartmentalization. DivJ and PleC respectively occupy the old and new cell poles( Figure 1A)[4],[5]. Prior to cell division, the cytoplasm contains a homogeneous mixture of phosphorylated( DivK∼P) and unphosphorylated DivK[8]. In pre-divisional cells, however, PleC( positioned at the new pole) functions as a DivK phosphatase, while DivJ( positioned at the old pole) functions as a DivK kinase[4],[5],[9]. In this way, compartmentalization promotes accumulation of unphosphorylated DivK in the incipient swarmer cell and DivK∼P in the incipient stalked cell[10],[11], providing unique cell-type markers. In Caulobacter, the DivK phosphorylation state provides the basis for a regulatory switch that underlies divergent cell-fates upon cell division[12]–[15]. This switch is achieved through the activity of the pseudokinase DivL, which activates the CckA-ChpT-CtrA phosphorelay pathway in the uncomplexed state and inhibits this phosphorelay when bound to DivK∼P( Figure 1B)[13]. Previous in vitro work has shown that DivL has a binding preference for DivK∼P over unphosphorylated DivK, and genetic evidence suggests that the DivL-DivK∼P interaction leads to inhibition of the hybrid-HK CckA activity[13]. Additionally, DivL appears to play a role in the regulation of CckA polar localization and autokinase activity[13],[16]. Thus, DivL functions as a critical link that couples two distinct signaling pathways( Figure 1B). DivL has a predicted domain architecture that is typical of many HKs, consisting of multiple PAS domains fused to a C-terminal HK module that contains dimerization and histidine phosphotransfer( DHp) and catalytic and ATP-binding( CA) domains( Figure 1C). In contrast to typical HKs, a conserved tyrosine( Tyr550) appears in place of the predicted phosphorylatable histidine throughout DivL homologs in α-proteobacteria[17], with the exception of the Magnetospirillum magneticum DivL that contains a non-phosphorylatable alanine( Figure 1C). Furthermore, DivL's essential functions in vivo do not require a phosphorylated DHp domain[12],[13],[16], and the CA domain is dispensable for activity[12],[18]. Divergent α-proteobacteria that lack a DivK ortholog also frequently lack the catalytic domains( DHp-CA) of their DivL orthologs( Figure 1C)[19]. The co-evolution of DivK with the DHp-CA domains of DivL suggests that DivL and DivK may work together as a regulatory module within the cell-cycle[19]. Despite the apparent connection between DivK and DivL in cell fate signaling, the molecular nature of the interaction between this unconventional HK-RR pair is poorly understood. To gain insight into this signaling system, we solved the crystal structure of the HK region of DivL at 2. 5 Å resolution and interrogated the interaction between DivL and both DivK and DivK∼P. Our results show that Caulobacter has repurposed a conserved HK as a highly specific sensor module for a phosphorylated RR∼P.\nDiscussion:\nOur structural and biochemical analysis showed that DivL lacks both kinase and phosphatase activity but still retains its ability to dimerize and bind DivK∼P specifically. The DivL mutant Y550H supports viability but impacts cell morphology, doubling time, and the subcellular localization of DivL. These defects suggest that the replacement of histidine by tyrosine is critical for optimal DivL function. We observed that DivL Y550H bound to DivK∼P with similar affinity as the wild type, indicating that the tyrosine substitution neither enhances nor diminishes DivK∼P binding. The Y550H mutation did not rescue autonomous autokinase activity in vitro, however, DivL( Y550H) autokinase activity can be stimulated by DivK∼P in the presence of ATP( Figure 6D). Thus, the H to Y substitution in DivL does not perturb HK-RR binding but abrogates kinase activity. From these studies, we propose that the DivL pseudokinase has repurposed its catalytic HK fold to function primarily as a sensory module for a phosphorylated RR. Loss of catalytic function ensures orthogonal sensor function while preventing unwanted signal modification( i. e., inter-conversion of DivK and DivK∼P) that would compromise asymmetric cell division. Previous studies of two-component systems have highlighted the critical role of the RR docking module in determining HK-RR phosphotransfer specificity[21],[41]–[45]. Consistent with these studies, we identified four point mutations within the RR docking module that disrupt DivK∼P binding to DivL( Figure 4). Thus, our results support the notion that DivL binds DivK∼P in a conserved manner similar to a canonical HK-RR pair[23],[41]–[44]. However, a key question remains: how does DivL specifically recognize DivK∼P? The tyrosine or histidine side chain at position 550 could contribute to the specific recognition of the phosphoryl group on DivK directly, by forming a hydrogen bond. However, we do note that Y550F has been previously shown to specifically bind phosphorylated DivK over unphosphorylated DivK[13]. Furthermore, the DivL RR docking surface, which includes Tyr550, may be tuned to specifically recognize structural changes in DivK that are induced by phosphorylation. Here, we observed that the PAS sensor domain plays an unexpected role in phosphospecific discrimination of DivK∼P over DivK( Figure 5). One possible role of the PAS sensor domain could be to directly sterically block unphosphorylated DivK binding while permitting DivK∼P binding, or perhaps more likely the DivL PAS domains could indirectly reconfigure the DivK binding site to promote phosphospecific binding. The PAS domain's role in phosphospecific RR binding is consistent with the finding that optimal WalK[46] and ThkA[25] phosphatase activity requires a PAS module. More generally, it appears that PAS sensor domains may regulate kinase/phosphatase activity by influencing the phosphospecific binding preference of an HK for its cognate RR. Several recent biochemical studies of HKs have revealed that HKs transmit signaling information over a long-range through large-scale conformational changes in order to regulate activity. DHp conformational rearrangements, such as “twisting”( cogwheeling or rotation) and “bending”( kinking), can produce unique functional states that are crucial for HK regulation[24],[26]–[28],[32],[47]–[50]. Our rigid-body structural analysis of DivL suggests that interhelical bending could alter the relative position of domains that regulate DivL function. Indeed, our binding studies indicate that a mutation at the interface between two rigid bodies( A601L), disrupts DivK∼P binding in a PAS-domain-dependent manner( Figure 5C). Furthermore, the A601L mutation causes a more severe phenotype than does the direct RR docking mutation Y562A. This suggests that A601L may be pleiotropic, perhaps simultaneously affecting upstream( i. e., DivK∼P binding) and downstream events( i. e., CckA inhibition). Residue Arg553 may also serve a switch-like role triggering conformational changes upon DivK∼P binding by interacting with DivK∼P in the complexed state, and in the uncomplexed state interacting with the output-helix residue Asp595( Figure 5). Taken together, this model may explain why A601L and R553A have stronger impacts on cell fitness than the Y562A variant. Additionally, DivK∼P-dependent rescue of DivL autokinase activity in the presence of Y550H suggests that DivK∼P binding triggers conformational changes in DivL that are necessary for ATP binding and autokinase activity. Thus, we propose a model in which the interaction between Tyr550 and the phosphorylation site of DivK∼P induces bending in the α1 helix of DHp, which is then propagated to the rest of the structure via rigid-body movements. As a result of the conformational change, the CA and PAS domains of DivL may re-position to allow formation of additional contacts with bound DivK∼P. In the absence of catalytic functions, we suggest that DivL exploits the underlying large-scale conformational re-arrangements of the HK-fold to function as a DivK∼P-modulated two-state molecular switch( Figure 8). Asymmetric dimers have been proposed to represent important activation intermediates[26]–[29],[51], and it is conceivable that DivL undergoes a symmetric-asymmetric conformational switch upon DivK∼P binding. However, the mechanism by which DivK∼P-dependent conformational changes in DivL impact the CckA-ChpT-CtrA phosphorelay[12],[13],[15],[39],[52] remains unclear. It is plausible that DivL interacts directly or indirectly with CckA in the multi-protein polar complex, thus allowing the structural changes in DivL induced by DivK∼P to propagate to changes in CckA activity. Future experiments will focus on dissecting DivL's essential regulation of the CckA-ChpT-CtrA pathway. A common bacterial signaling strategy is to wire two-component systems as simple orthogonal linear signaling arrays to limit cross-talk and maintain the integrity of signaling information[43],[44]. Phosphorelay pathways offer a way to branch signaling pathways in order to enable multiple signaling inputs[30] or outputs[45],[53]. Signaling directionality in the two-component systems from a kinase to a response regulator apparently limits bacterial signal processing capacity relative to more complex eukaryotic systems. Here, we demonstrated an exception to this paradigm in which loss of HK catalytic activity repurposes an output module as a phosphospecific RR input sensor, thereby reversing the flow of information observed in conventional HK-RR systems. This reversal allows DivL to couple two distinct signaling pathways by serving as an “output” for a compartment sensing pathway and an “input” for the differentiation phosphorelay( Figure 8). The extent to which nature utilizes this reversed signaling warrants further investigation. For example, it could allow transmission cytosolic stress signals to the periplasm via membrane-bound HKs. The presence of pseudokinases in two-component signaling systems therefore offers a general mechanism for coupling signaling pathways, reminiscent of complex eukaryotic signaling networks.",
"role": "user"
},
{
"content": "Across all kingdoms of life the generation of cell-type diversity is the consequence of asymmetry at the point of cell division . The bacterium Caulobacter crescentus divides asymmetrically to produce daughter cells that have distinct morphology and behavior . As in eukaryotes , an unequal distribution of signaling proteins in daughter Caulobacter cells triggers the differential read-out of identical genomes . A critical interaction between two protein molecules – a protein kinase ( DivL ) and a response regulator ( DivK ) – is known to occur exclusively in one daughter cell and to thereby regulate differentiation . However , mapping the observed signaling interconnections that drive asymmetric division has been difficult to reconcile with traditional models of bacterial signaling . Here we determine how DivL detects and processes this DivK signal . Although DivL has an architecture that is typical of histidine kinases , which normally act by regulating the phosphorylation state of the appropriate response regulator , DivL's essential functions do not require kinase activity and DivL does not add or remove phosphate from DivK . Instead we find that DivL has converted its output kinase domain into an input sensor domain that specifically detects phosphorylated DivK , and we identify key features of DivL that underlie this specificity . This novel reassignment of sensory functions reverses the conventional kinase-to-response-regulator signaling flow and logically couples linear signaling pathways into complex eukaryote-like networks to regulate cell development .",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.77485
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Review of Geometry Recovery from a Single Image Focusing on Curved Object Reconstruction \nChapter Title: Surface Representation and Topology \n1. Abstract of Cited Paper (BIB001): We propose a convex optimization framework delivering intuitive and reasonable 3D meshes from a single photograph. For a given input image, the user can quickly obtain a segmentation of the object in question. Our algorithm then automatically generates an admissible closed surface of arbitrary topology without the requirement of tedious user input. Moreover we provide a tool by which the user is able to interactively modify the result afterwards through parameters and simple operations in a 2D image space. The algorithm targets a limited but relevant class of real world objects. The object silhouette and the additional user input enter a functional which can be optimized globally in a few seconds using recently developed convex relaxation techniques parallelized on state-of-the-art graphics hardware. \n2. Abstract of Cited Paper (BIB002): We propose a novel variational formulation for generating 3D models of objects from a single view. Based on a few user scribbles in an image, the algorithm automatically extracts the object silhouette and subsequently determines a 3D volume by minimizing the weighted surface area for a fixed user-specified volume. The respective energy can be efficiently minimized by means of convex relaxation techniques, leading to visually pleasing smooth surfaces within a matter of seconds. In contrast to existing techniques for single-view reconstruction, the proposed method is based on an implicit surface representation and a transparent optimality criterion, assuring high-quality 3D models of arbitrary topology with a minimum of user input.\n\nLiterature Review:",
"role": "user"
},
{
"content": "The reconstructability of curved surfaces with arbitrary topology depends on the surface representation. Implicit representations BIB002 BIB003 are generally better suited for this task than parametric ones BIB001 , since the parameter space has to reflect the topology. The same holds for mesh-based approaches such as the one by Igarashi et al. : during modeling operations it can be tedious to keep the mesh consistent, especially during topology changes. The parametric representation by Prasad et al. BIB001 has other implications. Firstly, uniformly distributed points in the parameter space are not uniformly distributed on the surface. This property may lead to oscillations, especially in the case of higher genus. Further, the relation between points in parameter space and points on the surface is non-trivial for inexperienced users. Silhouettes Silhouettes are used by Prasad et al. BIB001 , Oswald et al. BIB002 , and Töppe et al. BIB003 for surface inference. Full silhouette consistency of the reconstruction, however, is only enforced in the latter approaches as Prasad et al. BIB001 derive merely local constraints from the silhouette. View Constraints Finally, view constraints are of practical importance. Oswald et al. BIB002 as well as Töppe et al. BIB003 assume symmetric objects. Reconstructions work best if symmetry and viewing plane are parallel. This implies that the contour generator is planar. The approach by Prasad et al. BIB001 allows for non-planar contour generators and, thus, in some cases for slightly more general view points than just a side-view.",
"role": "assistant"
}
] |
science.bc7_litcovid_topic_classification
|
science.bc7_litcovid_topic_classification.21228
|
[
{
"content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nBackground: A multi-specialty nursing team plays a crucial role in key decision making, education, prevention, screening, assessment, diagnosis, management, data collection and dissemination of best practices during the novel coronavirus disease (COVID-19) pandemic. Methods: Using examples from a large, tertiary medical center in Los Angeles, this manuscript highlights contributions made by multi-specialty nursing specialties to optimize health and safety for patients and frontline healthcare workers. Conclusion: Recognizing nurses ongoing critical role encourages and informs further collaboration and serves as a catalyst to innovation for a healthier tomorrow. The result of the COVID-19 pandemic will be felt for years to come.",
"role": "user"
},
{
"content": "[\"Prevention\"]",
"role": "assistant"
}
] |
science.anat_em_ner
|
science.anat_em_ner.222
|
[
{
"content": "Given this abstract, identify all unique entities of these types: [\"AnatomicalEntity\"].\n\nOnly output the JSON object, no other text.\n\nAbstract:\nVerrucous carcinoma of the endometrium--a unique neoplasm with long survival.\nA case of verrucous carcinoma of the endometrium with long survival is described. It represents the first of its type to be recorded in this site. The literature on verrucous carcinoma and on other cases of squamous carcinoma of the endometrium is briefly reviewed.",
"role": "user"
},
{
"content": "{\"AnatomicalEntity\": [\"endometrium\", \"site\", \"Verrucous carcinoma\", \"verrucous carcinoma\", \"neoplasm\", \"squamous carcinoma\"]}",
"role": "assistant"
}
] |
science.multixscience_multidoc_summarization
|
science.multixscience_multidoc_summarization.6631
|
[
{
"content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nDespite the fast developmental pace of new sentence embedding methods, it is still challenging to find comprehensive evaluations of these different techniques. In the past years, we saw significant improvements in the field of sentence embeddings and especially towards the development of universal sentence encoders that could provide inductive transfer to a wide variety of downstream tasks. In this work, we perform a comprehensive evaluation of recent methods using a wide variety of downstream and linguistic feature probing tasks. We show that a simple approach using bag-of-words with a recently introduced language model for deep context-dependent word embeddings proved to yield better results in many tasks when compared to sentence encoders trained on entailment datasets. We also show, however, that we are still far away from a universal encoder that can perform consistently across several downstream tasks.\n\nCited Abstract(s):\n[1]: Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models to learn such representations ignore the morphology of words, by assigning a distinct vector to each word. This is a limitation, especially for languages with large vocabularies and many rare words. In this paper, we propose a new approach based on the skipgram model, where each word is represented as a bag of character n-grams. A vector representation is associated to each character n-gram, words being represented as the sum of these representations. Our method is fast, allowing to train models on large corpora quickly and allows to compute word representations for words that did not appear in the training data. We evaluate our word representations on nine different languages, both on word similarity and analogy tasks. By comparing to recently proposed morphological word representations, we show that our vectors achieve state-of-the-art performance on these tasks.\n\n[2]: This paper explores a simple and efficient baseline for text classification. Our experiments show that our fast text classifier fastText is often on par with deep learning classifiers in terms of accuracy, and many orders of magnitude faster for training and evaluation. We can train fastText on more than one billion words in less than ten minutes using a standard multicore CPU, and classify half a million sentences among 312K classes in less than a minute.",
"role": "user"
},
{
"content": "FastText [1] is a recent method for learning word embeddings for large datasets. It can be seen as an extension of Word2Vec that treats each word as a composition of character n-grams. The sub-word representation allows fastText to represent words more efficiently, enabling the estimation of rare and out-of-vocabulary (OOV) words. In [2] the authors used fastText word representation combined with techniques such as bag of n-gram features and demonstrated that fastText obtained performance on par with deep learning methods, while being faster.",
"role": "assistant"
}
] |
science.covid_deepset_qa
|
science.covid_deepset_qa.327
|
[
{
"content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: Internal mutation theory stated that the development of FIP is due to the exposure of cat to variants of FCoV which have been mutated by gaining the ability to replicate within the macrophages [2] , while the circulating high virulent-low virulent theory explains the existence of both distinctive pathogenic and benign lineages of viruses within the cat population [3] . Study has shown that about 40-80% of cats are detected with FECV shedding in their faeces [4] . About 12% of these FECV-positive cats have developed immune-mediated fatal FIP disease [4] . The prevalence of FIP among felines is due to continual cycles of infection and reinfection of FECV and indiscernible clinical symptoms of infected cats with FECV at an early stage before the progressive development of FIPV. Vaccination against FIPV with an attenuated, temperature-sensitive strain of type II FIPV induces low antibody titre in kittens that have not been exposed to FCoV. However, there is considerable controversy on the safety and efficacy of this vaccine, since the vaccine contains type 2 strain, whereas type 1 viruses are more prevalent in the field [4] . In addition, antibodies against FIPV do not protect infected cats but enhance the infection of monocytes and macrophages via a mechanism known as Antibody-Dependent Enhancement [1] . Besides vaccines, several antiviral drugs such as ribavirin, 2 BioMed Research International interferons, and immunosuppressive drugs have been used as treatments for FIPV-infected cats, mainly to suppress the inflammatory and detrimental immune response [5] [6] [7] [8] . However, those treatments were ineffective. Hence, there is still significant unmet medical need to develop effective treatments and prophylactics for FIPV infection. Triple Helix Forming Oligonucleotide (TFO) is defined as homopyrimidine oligonucleotides, which can form a sequence-specific triple helix by Hoogsteen bonds to the major groove of a complementary homopyrimidinehomopurine stretch in duplex DNA [9] . Furthermore, double helical RNA or DNA-RNA hybrids can be targeted as a template for triple helix formation, once the strand composition on the stabilities of triple helical complexes is determined [10] . Hence, TFO has been used to impede gene expressions by transcription inhibition of viral genes or oncogenes [11] [12] [13] [14] [15] [16] . The main purpose of this study is to develop and evaluate the in vitro antiviral properties of circular TFO RNAs against FIPV replication. serotype II strain WSU 79-1146 (ATCC no. VR-1777) was grown in CRFK cells. A serial 10-fold dilution of FIPV was prepared from the working stock. Confluent 96-well plate was inoculated with 100 L of each virus dilution/well. The plate was incubated in a humidified incubator at 37 ∘ C, 5% CO 2 . Cytopathic effects (CPE) development was observed. The results were recorded after 72 hours and the virus tissue culture infective dose 50 (TCID 50 ) was calculated using Reed and Muench's method [17] . Oligonucleotide RNA. The Triple Helix Forming Oligonucleotides (TFOs) were designed based on the genome sequence of FIPV serotype II strain WSU 79-1146 (Accession no: AY994055) [18] . TFOs, which specifically target the different regions of the FIPV genome, and one unrelated TFO were constructed ( Table 1 ). The specificity of the TFOs was identified using BLAST search in the NCBI database. The designed linear TFOs were synthesized by Dharmacon Research (USA), whereby the 5 and 3 ends of the linear TFOs were modified with phosphate (PO 4 ) group and hydroxide (OH) group, respectively. These modifications were necessary for the circularization of linear TFO. The process of circularization, using the T4 RNA ligase 1 (ssRNA ligase) (New England Biolabs Inc., England), was carried out according to the manufacturer's protocol. After ligation, the circular TFO RNAs were recovered by ethanol precipitation and the purity of the circular TFO RNAs was measured using spectrophotometer. Denaturing of urea polyacrylamide gel electrophoresis was performed as described before [19] with modification. Briefly, 20% of denatured urea polyacrylamide gel was prepared and polymerized for 30 minutes . Then, the gel was prerun at 20 to 40 V for 45 minutes. Five L of TFO RNA mixed with 5 L of urea loading buffer was heated at 92 ∘ C for 2 minutes and immediately chilled on ice. It was run on the gel at 200 V for 45 minutes. Finally, the gel was stained with ethidium bromide (Sigma, USA) and viewed with a Bio-Rad Gel Doc XR system (CA, USA). (EMSA) . The target regions of the FIPV genome were synthesized by Dharmacon Research (USA) ( Table 1) . Each TFO RNA was mixed with the target region in 1X binding buffer containing 25 mM Tris-HCl, 6 mM MgCl 2 , and 10 mMNaCl in a final volume of 10 L and subsequently incubated at 37 ∘ C for 2 hours. The sample was run on 15% native polyacrylamide gel at 80 V, in cool condition. The stained gel was viewed by a Bio-Rad Gel Doc XR system. Regions. The binding strength was measured using a nano Isothermal Titration Calorimeter (ITC) (TA instruments, Newcastle, UK). The RNA sample mixtures, consisting of circular TFOs (0.0002 mM), were incubated with their respective synthetic target regions (0.015 mM) using 1X binding buffer as the diluent. The experiment was run at 37 ∘ C with 2 L/injection, for a total of 25 injections. Data was collected every 250 seconds and analyzed using the NanoAnalyze software v2.3.6 provided by the manufacturer. This experiment was conducted in CRFK cells, where 3 × 10 4 cell/well was seeded in 96-well plate to reach 80% confluency 24 hours prior to transfection. One hundred nM of TFO RNAs was separately transfected into the CRFK cells using a HiPerFect Transfection Reagent (Qiagen, Germany), as per the manufacturer's protocol. The plate was incubated at 37 ∘ C with 5% CO 2 for 6 hours. Then, the cultures were infected with 100TCID 50 of FIPV serotype II strain WSU 79-1146 for 1 hour at 37 ∘ C (100 L/well). Finally, the viral inoculum was replaced by fresh maintenance media (MEM containing 1% FBS and 1% pen/strep). Virus-infected and uninfected cells were maintained as positive and negative controls, respectively. The morphology of the cultures was recorded 72 hours after infection and samples were harvested at this time point and stored at −80 ∘ C prior to RNA extraction. Inhibition. Different concentrations of circular TFO1 RNA (25 nM, 50 nM, 100 nM, and 500 nM) were transfected into CRFK cells. The plate was incubated for 6 hours followed by virus inoculation for 1 hour at 37 ∘ C with 5% CO2. The cells were processed as described above. Madin-Darby Canine Kidney (MDCK) cell (ATCC no. CCL-34), at a concentration of 4 × 10 4 cell/well, was seeded in 96-well plate to reach 80% confluency 24 hours prior to transfection. Transfection was performed the same as before. One hundred nM of circular TFO RNA was transfected into MDCK cells. Following 6 hours \n\nORF1a/1b and 530-541\n\nORF1a/1b and 7399-7411\n\nORF1a/1b and 14048-14061\n\n- * Highlighted in bold indicated the binding region. * * Unrelated circular TFO. [20, 21] , respectively. The reverse transcriptase quantitative real-time PCR (RT-qPCR) was performed using a Bio-Rad CFX96 real-time system (BioRad, USA). The reaction was amplified in a final volume of 25 L using a SensiMix SYBR No-ROX One-Step Kit (Bioline, UK), which consisted of 12.5 L 2X SensiMix SYBR No-Rox One-\n\nStep reaction buffer, 10 M forward and reverse primers, 10 units RiboSafe RNase inhibitor, and 5 L template RNA. Absolute quantification approach was used to quantify qPCR results where a standard curve of a serial dilution of virus was plotted before the quantification. Amount of the virus in the samples was quantified based on this standard curve. Analysis. Data statistical analysis was performed using SPSS 18.0. Data were represented as mean ± SE of three independent tests. One-way ANOVA, Tukey post hoc test was used to analyze the significant level among the data. ≤ 0.05 was considered significant. genome, which play important roles in viral replication, were selected as the target binding sites for the triplex formation. The target regions were 5 untranslated region (5 UTR), Open Reading Frames (ORFs) 1a and 1b, and 3 untranslated region (3 UTR) ( Table 1 ). The TFOs were designed in duplex, as they can bind with the single stranded target region and reshape into triplex. Both ends of the duplex TFOs were ligated with a linker sequence or clamps (C-C) to construct circular TFO RNA. Denaturing PAGE assay was carried out after the ligation process to determine the formation of the circular TFO. As shown in Figure 1 , the circular TFO RNAs migrated faster than the linear TFO RNAs, when subjected to 20% denaturing PAGE. Target Region. The binding ability was determined using Electrophoretic Mobility Shift Assay (EMSA) [23] . The appearance of the slow mobility band indicates the successful hybridization of circular TFO RNA with its target region. The binding ability of different TFO RNAs (TFO1 to TFO5) against their target regions was determined by EMSA (Figure 2) . TFO1, TFO3, TFO4, and TFO5 showed slow mobility band, while TFO2 showed the lack of an upward shifted band. This indicates the possession of triplex binding ability for all circular TFO RNAs, except TFO2. TFO RNA. Study on the interaction and hybridization of TFO towards its target region is crucial, since the stronger the binding is, the more stable the triplex structure forms. As shown in supplementary Figure 1 (Table 3) . The antiviral effect of circular TFO RNAs was investigated by RT-qPCR assay at 72 hours after transfection. The results showed viral RNA genome copy numbers of 3.65 × 10 9 , 3.22 × 10 14 , 5.04 × 10 9 , 5.01 × 10 9 , 4.41 × 10 9 , and 3.96 × 10 14 in cells treated with TFO1, TFO2, TFO3, TFO4, TFO5, and TFO7, respectively. The data analyzed by one-way ANOVA, Tukey post hoc test showed significant high viral RNA genome copy number of 4.03 × 10 14 for virus inoculated cells as compared to circular TFO1, TFO3, TFO4, and TFO5 treatments ( ≤ 0.05). The viral RNA copies of circular TFO2, linear TFO3 and TFO4, and unrelated circular TFO7 RNAs transfected cells also showed high viral RNA copy numbers which did not show significant differences to the infected cells ( ≥ 0.05) ( Figure 3 ). The morphological changes of the cells were also captured 72 hours after transfection. The cells transfected with circular TFO1, TFO3, TFO4, and TFO5 appeared to be in good condition following virus inoculation, while the cells transfected with circular TFO2 and linear TFO3 and TFO4 showed visible cytopathic effect (CPE), the same as virus inoculated cells (supplementary Figure 2) . Furthermore, cells transfected with TFO only remain viable indicating that TFO treatment is generally not toxic to the cells. Hence, these results illustrated the capacity of circular TFO RNAs (except TFO2) to inhibit FIPV replication. Concentrations on FIPV Replication. Circular TFO1 was used to examine the dose-response relationship as a representative to other TFOs. The experimental conditions were identical to that of the previous experiment, except for TFO1 concentrations of 25 nM, 50 nM, 100 nM, and 500 nM. There was no significant reduction in viral RNA genome copies using the concentration of 25 nM TFO1. The other concentrations caused significant reductions in copy numbers as compared to the virus-infected cells. However, no significant difference was detected in copy numbers from all of these concentrations ( Figure 4 ). The specificity of the TFO towards FIPV was tested, using TFO1 and TFO5, as the proper representatives of TFOs, on influenza A virus H1N1 New Jersey 8/76. The analyzed data using one-way ANOVA, Tukey post hoc test did not show significant reductions in the copies of viral RNA for both TFOs compared to the influenza virus inoculated cells ( ≥ 0.05) (supplementary Figure 3 ). Complex structure G4/Cir4 Figure 2 : EMSA analysis. EMSA analysis illustrated the binding of circular TFO 1, 3, 4, and 5 to the target regions as evidenced by upward band shift. Binding of each circular TFO except circular TFO2 to its respective target forms a complex that migrates slower than unbound TFO. G1 to G5 represent the target region for circular TFO1 to TFO5 and Cir1 to Cir5 represent the circular TFO1 to TFO5, respectively. in the replication process [24] . Meanwhile, the ORF1a/1b of FIPV are translated into polyproteins that are cleaved into nonstructural proteins which assemble into replicationtranscription complexes together with other viral proteins [24] . Hence, the development of molecular therapy targeting these critical regions may provide the possibility to inhibit FIPV replication. Development of antiviral therapies against FIPV using siRNA [25] and viral protease inhibitors [26] Figure 4 : TFO1 dose-response study for inhibiting FIPV replication. The concentrations of 50 nM and higher showed significant antiviral effects.\nQuestion: For how long was the denatured polyacrylamide gel polymerized?",
"role": "user"
},
{
"content": "30 minutes",
"role": "assistant"
}
] |
science.mslr2022_ms2_multidoc_summarization
|
science.mslr2022_ms2_multidoc_summarization.7408
|
[
{
"content": "Based on the RCT reports below, write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article.\n\n\n\nTitle 1:\nOpen hearts build lives: positive emotions, induced through loving-kindness meditation, build consequential personal resources.\nAbstract 1:\nB. L. Fredrickson 's ( 1998 , 2001 ) broaden- and -build theory of positive emotions asserts that people 's daily experiences of positive emotions compound over time to build a variety of consequential personal re sources . The authors tested this build hypothesis in a field experiment with working adults ( n = 139 ) , half of whom were r and omly-assigned to begin a practice of loving-kindness meditation . Results showed that this meditation practice produced increases over time in daily experiences of positive emotions , which , in turn , produced increases in a wide range of personal re sources ( e.g. , increased mindfulness , purpose in life , social support , decreased illness symptoms ) . In turn , these increments in personal re sources predicted increased life satisfaction and reduced depressive symptoms . Discussion centers on how positive emotions are the mechanism of change for the type of mind-training practice studied here and how loving-kindness meditation is an intervention strategy that produces positive emotions in a way that outpaces the hedonic treadmill effect\n\n\nTitle 2:\nPositive psychology progress: empirical validation of interventions.\nAbstract 2:\nPositive psychology has flourished in the last 5 years . The authors review recent developments in the field , including books , meetings , courses , and conferences . They also discuss the newly created classification of character strengths and virtues , a positive complement to the various editions of the Diagnostic and Statistical Manual of Mental Disorders ( e. g. , American Psychiatric Association , 1994 ) , and present some cross-cultural findings that suggest a surprising ubiquity of strengths and virtues . Finally , the authors focus on psychological interventions that increase individual happiness . In a 6-group , r and om-assignment , placebo-controlled Internet study , the authors tested 5 purported happiness interventions and 1 plausible control exercise . They found that 3 of the interventions lastingly increased happiness and decreased depressive symptoms . Positive interventions can supplement traditional interventions that relieve suffering and may someday be the practical legacy of positive psychology\n\n\nTitle 3:\nDon't hide your happiness! Positive emotion dissociation, social connectedness, and psychological functioning.\nAbstract 3:\nIt is now clear that positive emotion leads to enhanced psychological functioning . What is less clear , however , is just why this is so . Drawing on a social-functional perspective , we argue that positive emotional behavior that accurately signals to others the individual 's internal state will enhance social connectedness . Positive emotional behavior that does not accurately signal a person 's experience -- such as a smile that is not felt -- may impede social connectedness and , in turn , psychological functioning . This perspective suggests that ( a ) the degree to which experience and behavior are dissociated during positive emotional episodes , over and above level of positive behavior , should predict worse psychological functioning and ( b ) the effect of dissociation should be mediated by social connectedness . To test these hypotheses , we conducted a short-term prospect i ve longitudinal study , with a baseline assessment of depressive symptoms and well-being at Time 1 . Six months later , at Time 2 , we used a novel within-individual laboratory paradigm to measure the degree to which positive emotional behavior was dissociated from ( vs. coherent with ) a participant 's positive emotional experience . We also assessed level of positive behavior and experience . Then , another 6 months later , we assessed social connectedness as a mediator and depressive symptoms and well-being as outcomes at Time 3 . Even when controlling for baseline functioning and for level of positive emotion behavior and experience , we found that greater positive experience-behavior dissociation at Time 2 predicted higher levels of depressive symptoms and lower levels of well-being at Time 3 . As predicted , these associations were mediated by social connectedness\n\n\nTitle 4:\nLife events, coping and depressive symptoms among young adolescents: a one-year prospective study.\nAbstract 4:\nBACKGROUND To investigate prospect ively over one year , the extent to which greater exposure to negative life events , greater use of more negative coping strategies , and less use of positive coping strategies and an optimistic thinking style , predicts the onset of depressive symptoms among adolescents . METHODS A prospect i ve longitudinal study of 5,634 adolescents ( Mean Age=13.1 , SD=0.5 ) enrolled in Year 8 at secondary school . St and ard question naires were used to assess depressive symptoms and the predictor variables . RESULTS Over a one-year period , there was an independent and statistically significant relationship between transition to a CES-D score above the recommended cut-off score and i ) greater exposure to negative life events and use of negative coping strategies , and ii ) less use of positive coping strategies and an optimistic thinking style . Among males who experienced a higher number of negative life events , the impact on depressive symptoms was greater among those who made more use of negative coping strategies . LIMITATIONS Self-report question naires completed by adolescents were employed to evaluate all the variables in the study . Only two assessment points were available . Ten percent of adolescents did not complete the follow-up assessment . CONCLUSIONS Particularly among females , early adolescence is marked by increased susceptibility to depressive symptoms . Helping young adolescents to adopt more positive coping strategies and optimistic thinking styles may reduce their risk for the onset of depressive symptoms . This may be particularly important for young males who experience high levels of adverse life events and utilise negative coping strategies\n\n\nTitle 5:\nDepressive symptoms and momentary affect: the role of social interaction variables\nAbstract 5:\nBackground : Interpersonal functioning may be one important factor in the development and course of depression symptomatology . This study used ecological momentary assessment to test the associations among depressive symptoms , social experiences and momentary affect in women . Methods : Middle‐aged women ( N=108 , M age : 41.6 years , 81 % White ) completed diary questions on h and held computers for 2 days . Diary items assessed social ( conflictive versus supportive ) and affective ( negative versus positive ) experiences at r and om times during the day . Women also completed a self‐report measure of recent depressive symptoms . Results : Multilevel modeling analyses showed that higher levels of symptoms of depression were related to higher negative affect and lower positive affect both directly and indirectly , through experiences of social conflict . Depressive symptoms were not significantly related to socially supportive interactions . In an alternative model testing the reverse association , neither positive nor negative affect significantly predicted social experiences . Generalizability is limited by the homogenous small sample and strict inclusion ary criteria ( working full‐time or part‐time , cohabitating or married , healthy ) . Due to the cross sectional nature of the data as well as the manner in which social and affective experiences were assessed , definitive conclusions regarding the temporal associations among depression symptoms , social functioning , and affect are not possible . Results are consistent with prior reports suggesting the salience of socially conflictive experiences , and the role of affect , in the etiology and maintenance of depression symptoms . Conclusions : Interventions that attempt to decrease socially conflictive experiences via cognitive‐behavioral skills training , whereas concomitantly targeting positive and negative affect , could help prevent the development of full‐blown depressive episodes in vulnerable individuals . Depression and Anxiety , 2009 . © 2009 Wiley‐Liss ,",
"role": "user"
},
{
"content": "The studies have important relations between humor and positive emotion as well as a significant improvement in signs and symptoms of depression using differents strategies of positive psychology .\nAnother relevant aspect is the preventative character of the proposed interventions by positive psychology by the fact that increase well-being and produce elements such as resilience and coping re sources that reduce the recurrent relapses in the treatment of depression .\nThe strategies of positive psychology , such as increasing positive emotions , develop personal strengths : seeking direction , meaning and engagement for the day-to-day life of the patients , appear as potentially tools for the prophylaxis and treatment of depression , helping to reduce signs and symptoms as well as for prevention of relapses",
"role": "assistant"
}
] |
science.genia_ner
|
science.genia_ner.1066
|
[
{
"content": "Extract all unique entities of these types from the biomedical abstract: [\"CellLine\", \"DNA\", \"Protein\", \"CellType\", \"RNA\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities found for a type, use [].\n\nAbstract:\n\nOverexpression of HSF2-beta inhibits hemin-induced heat shock gene expression and erythroid differentiation in K562 cells. Acquisition of heat shock factor 2 (HSF2) DNA binding activity is accompanied by induced transcription of heat shock genes in hemin-treated K562 cells undergoing erythroid differentiation. Previous studies revealed that HSF2 consists of two alternatively spliced isoforms, HSF2-alpha and HSF2-beta, whose relative abundance is developmentally regulated and varies between different tissues. To investigate whether the molar ratio of HSF2-alpha and HSF2-beta isoforms is crucial for the activation of HSF2 and whether the HSF2 isoforms play functionally distinct roles during the hemin-mediated erythroid differentiation, we generated cell clones expressing different levels of HSF2-alpha and HSF2-beta. We show that in parental K562 cells, the HSF2-alpha isoform is predominantly expressed and HSF2 can be activated upon hemin treatment. In contrast, when HSF2-beta is expressed at levels exceeding those of endogenous HSF2-alpha, the hemin-induced DNA binding activity and transcription of heat shock genes are repressed, whereas overexpression of HSF2-alpha results in an enhanced hemin response. Furthermore, the hemin-induced accumulation of globin, known as a marker of erythroid differentiation, is decreased in cells overexpressing HSF2-beta. We suggest that HSF2-beta acts as a negative regulator of HSF2 activity during hemin-mediated erythroid differentiation of K562 cells.",
"role": "user"
},
{
"content": "{\"CellLine\": [\"K562 cells\"], \"CellType\": [], \"DNA\": [\"heat shock genes\"], \"Protein\": [\"endogenous HSF2 - alpha\", \"HSF2 - beta\", \"HSF2 - alpha isoform\", \"HSF2\", \"the HSF2 - alpha isoform\", \"hemin\", \"HSF2 - alpha\", \"globin\"], \"RNA\": []}",
"role": "assistant"
}
] |
science.scientific_papers_summarization_single_doc_arxiv
|
science.scientific_papers_summarization_single_doc_arxiv.41515
|
[
{
"content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nprogress has been made in estimating the information - theoretic capacity of the class of fiber - optic communication systems that are ( presently ) of commercial interest @xcite , but existing systems perform far from the fundamental limits of the channel .\nwhile signal processing and coded modulation techniques promise to eliminate this gap , their implementations at the speeds present in fiber - optic systems present significant challenges . many existing proposals for coded modulation in fiber - optic communication systems amount to using techniques currently used in electrical wireline and wireless communication systems .\nfor example , in @xcite , the authors propose a concatenated coding system with inner trellis - coded modulation ( for an 8-psk constellation ) and an outer product - like code , and in @xcite , the authors propose using low - density parity - check ( ldpc ) codes for coded modulation . in both cases ,\nthe proposals are verified by simulation , where the channel is assumed to be a classical additive white gaussian noise ( awgn ) , but no consideration is given to the real - world implementation challenges for the proposed systems .\nother proposals for coded modulation in fiber - optic systems consider simplified channel models , and design codes for the resulting systems .\nfor example , in @xcite , the authors design a trellis - coded polarization - shift - keying modulation system , but their channel model only considers laser phase noise , i.e. , effects related to the propagation over fiber are completely ignored . in @xcite ,\nthe authors consider a nonlinear phase noise channel model studied by @xcite , and design a multi - level coded modulation system with reed - solomon codes at each level .\nhowever , this channel model assumes a single - channel dispersion - less system , which is not of practical interest . in this paper , we take a pragmatic approach to coded modulation for fiber - optic systems , that addresses the deficiencies of the aforementioned proposals . due to the fact that product - like codes with syndrome - based decoding have efficient high - speed decoders @xcite\n, we consider systems with hard - decision decoding .\nfurthermore , the channel model for which the codes are designed is not a simplified one , but rather is derived from ( computationally intensive ) simulations of the fiber - optic systems based on the generalized nonlinear schrdinger ( gnls ) equation [ ( [ eqn : gnls ] ) , below ] , and thus accurately models the non - awgn channel that occurs in optical communication systems .\nin contrast to most classically studied communication channels , optical fiber exhibits significant nonlinearity ( in the intensity of the guided light ) @xcite .\nfurthermore , amplification acts as a source of distributed awgn , and fiber chromatic dispersion acts as a distributed linear filter .\ncomplicating matters , these three fundamental effects _ interact _ over the length of transmission . in @xcite , signal processing is performed via digital backpropagation , in order to attempt to compensate the channel impairments .\nhowever , their results do not quantify the benefits of this compensation strategy . since digital backpropagation is computationally expensive\n, one approach to reducing the computational burden is to increase the step - size of the algorithm , as in @xcite . in this paper\n, we compare the achievable rates for two extreme cases : digital backpropagation ( as in @xcite ) , and a linear equalizer ( which can be considered as a form of `` linear backpropagation '' in which the step - size is the system s length ) . in section [ sec : pre ] , we review staircase codes , the system model for a fiber - optic communication system , and digital backpropagation . in section\n[ sec : rates ] , we compare the transmission rates that can be achieved using digital backpropagation with those achievable by linear equalization . in section [ sec : cmod ] , we present the details of a pragmatic coded modulation system , and compare the performance of the system to the capacity estimates .\nstaircase codes @xcite are a family of high - rate binary error - correcting codes suitable for high - speed fiber - optic communications .\nstaircase codes can be interpreted as _ generalized _ ldpc codes , that is , sparse graph - based codes whose constraint nodes are error-_correcting _ codes , not the single - parity - check error-_detecting _ codes used in the constraint nodes of conventional ldpc codes . with such generalized ldpc codes ,\nalgebraic decoding can be applied at the constraint nodes , and the decoder can operate exclusively on syndromes . as discussed in @xcite , this significantly reduces the decoder data - flow ( relative to a message - passing ldpc decoder ) , admitting an efficient high - speed implementation .\nfurthermore , due to the error correcting capabilities of the constraint nodes , staircase codes have very low error floors , which can be estimated analytically .\nfinally , due to their structural properties , staircase codes provide superior performance to product codes .\nstaircase codes are completely characterized by the relationship between successive matrices of symbols .\nspecifically , consider the ( infinite ) sequence @xmath5 of @xmath6-by-@xmath6 matrices @xmath7 , @xmath8 .\nblock @xmath9 is initialized to a reference state known to the encoder - decoder pair , e.g. , block @xmath9 could be initialized to the all - zeros state , i.e. , an @xmath6-by-@xmath6 array of zero symbols .\nfurthermore , we select a conventional fec code ( e.g. , hamming , bch , reed - solomon , etc . ) in systematic form to serve as the _ component _ code ; this code , which we henceforth refer to as @xmath10 , is selected to have blocklength @xmath11 symbols , @xmath12 of which are parity symbols . generally , the relationship between successive blocks in a staircase code satisfies the following relation : for any @xmath13 , each of the rows of the matrix @xmath14 $ ] is a valid codeword in @xmath10 . just as in a conventional product code , any given symbol in any given block @xmath7 participates in two constraints : one to satisfy the condition that each row of @xmath15 $ ] is a codeword of @xmath10 , and one to satisfy the condition that each row of @xmath16 $ ] is a codeword of @xmath10 .\nwe consider a coherent fiber - optic communication system . between the transmitter and receiver , standard - single - mode fiber and ideal distributed raman amplification\nare assumed , but we note that the methods presented herein also apply to alternate system configurations ( e.g. , systems with inline dispersion - compensating fiber , and/or lumped amplification ) . the complex baseband representation of the signal in a single polarization at the output of the transmitter is @xmath17 , and at the input of the receiver is @xmath18 , where @xmath19 is the total system length ; note that @xmath20 represents the full field , i.e. , in general it represents co - propagating dense wavelength - division - multiplexed signals .\nthe generalized non - linear schrdinger ( gnls ) equation expresses the evolution of @xmath20 : @xmath21 since ideal distributed raman amplification is assumed , the loss term has been omitted , and @xmath22 is a circularly symmetric complex gaussian noise process with autocorrelation @xmath23 = \\alpha h v_s k_t \\delta(z - z',t - t'),\\ ] ] where @xmath24 is planck s constant , @xmath25 is the optical frequency , and @xmath26 is the phonon occupancy factor . in table\n[ tab : param ] , we provide parameter values for the system components . note that the scalar equation ( [ eqn : gnls])whose numerical solution is used to generate all of the results of this paper governs propagation of waveforms in a single polarization mode .\nthe achievable rates for a dual - polarized transmission system would be approximately ( but slightly less than ) twice as large as for the single polarization system considered here , but a more complicated vector version of ( [ eqn : gnls ] ) , taking into account the effects of fiber birefringence and coupling between the polarization modes as well as the stochastic nature of polarization mode dispersion , would need to be considered .\n.system parameter values [ cols= \" < , < \" , ] [ tab : scbicm ]\nwe showed that digital backpropagation increases the achievable spectral efficiencies relative to linear equalization by @xmath3 to @xmath4 bits / s / hz per polarization .\nwe proposed a pragmatic coded modulation system that incorporates signal shaping and exploits the excellent performance and efficient high - speed decoding architecture of staircase codes .\nreliable communication within @xmath0 bits / s / hz per polarization of the estimated capacity of a system with @xmath1 km is provided by the proposed system , with an error floor below @xmath2 .\nm. arabaci , i. b. djordjevic , r. saunders , , and r. m. marcoccia , `` non - binary quasi - cyclic ldpc based coded modulation for beyond 100 gb / s transmission , '' _ ieee photon .\n. 22 , no . 6 , pp . 434436 , mar .\ni. b. djordjevic , m. cvijetic , l. xu , and t. wang , `` using ldpc - coded modulation and coherent detection for ultra high - speed optical transmission , '' _ j. lightw\n. technol .\n_ , vol . 25 ,\n36193625 , nov .\n2007 .\ns. benedetto , g. olmo , and p. poggiolini , `` trellis coded polarization shift keying modulation for digital optical communications , '' _ ieee trans .\n_ , vol .\n2/3/4 , pp .\n15911602 , feb./mar./apr . 1995 .\nl. beygi , e. agrell , p. johannisson , and m. karlsson , `` a novel multilevel coded modulation scheme for fiber optical channel with nonlinear phase noise , '' in _ proc . global communications conference _ ,\nmiami , fl , dec .\n2010 .\no. v. sinkin , r. , j. zweck , and c. r. menyuk , `` optimization of the split - step fourier method in modeling optical - fiber communication systems , '' _ j. lightw .\n_ , vol . 21 , no . 1 ,\n6168 , jan .",
"role": "user"
},
{
"content": "a pragmatic coded modulation system is presented that incorporates signal shaping and exploits the excellent performance and efficient high - speed decoding architecture of staircase codes . \n reliable communication within @xmath0 bits / s / hz of the estimated capacity ( per polarization ) of a system with @xmath1 km is provided by the proposed system , with an error floor below @xmath2 . \n also , it is shown that digital backpropagation increases the achievable spectral efficiencies relative to linear equalization by @xmath3 to @xmath4 bits / s / hz per polarization . \n staircase codes , fiber - optic communications , digital backpropagation , forward error correction , coded modulation , channel capacity .",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.42175
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Towards Unconstrained Palmprint Recognition on Consumer Devices: a Literature Review \nChapter Title: B. Palmprint ROI Extraction based on Conventional ML Algorithms \n1. Abstract of Cited Paper (BIB001): This paper presents a contactless hand based biometric identification system using geometric and palm features. Hand images are acquired using two commercial webcams with 1200×1600 pixel resolution which are refered to as the “IR” and “visible” webcams. The IR webcam has been modified by exchanging the IR filter with a visible filter lens and reducing the gain and exposure time to improve the hand contour extraction. The hand was illuminated using 24 infra-red LEDs and 4 white light LEDs. Images acquired from the IR webcam were binarized and the normalized widths from the index to little finger were used as features. A Least Square Support Vector Machine was then used for verification. The palm features were obtained by the Orthogonal Line Ordinal Features approach applied to the image acquired by the visible webcam. The hand image from the visible webcam was segmented using an Active Shape Model guided by the hand contour from the IR webcam as an initial guest. A Hamming distance was used as verifier. More than 8000 hand images from three public databases were used in order to compare the features extraction approaches. A score level fusion of both biometrics is performed obtaining an Equal Error Rate of 0.17% with a proprietary database of 100 users acquired with the proposed device. \n2. Abstract of Cited Paper (BIB002): This paper addresses the problem of Face Alignment for a single image. We show how an ensemble of regression trees can be used to estimate the face's landmark positions directly from a sparse subset of pixel intensities, achieving super-realtime performance with high quality predictions. We present a general framework based on gradient boosting for learning an ensemble of regression trees that optimizes the sum of square error loss and naturally handles missing or partially labelled data. We show how using appropriate priors exploiting the structure of image data helps with efficient feature selection. Different regularization strategies and its importance to combat overfitting are also investigated. In addition, we analyse the effect of the quantity of training data on the accuracy of the predictions and explore the effect of data augmentation using synthesized data. \n3. Abstract of Cited Paper (BIB003): In this paper, we propose a novel contactless palmprint authentication system where the system uses a CCD camera to capture the user's hand at a distance without any restrictions and touching the device. Furthermore, a novel and high performance region of interest (ROI) extraction method which makes use of nonlinear regression and palm model to extract the ROIs with high success is proposed. Comparative results indicate that the proposed ROI extraction method gives superior performance as compared to the previously proposed point-based approaches. To show the performance of the proposed system, a novel contactless database has also been created. This database includes images captured from the users who present their hands with various hand positions and orientations in cluttered backgrounds. Furthermore, experiments show that the proposed system has achieved a recognition rate of 99.488% and equal error rate of 0.277% on the contactless database of 145 people containing 1752 hand images. Display Omitted A novel unrestricted, contactless palmprint image acquisition device is developed.A novel model-based ROI extraction method, robust to the small errors is proposed.A contactless palmprint DB is constituted by collecting 1752 images from 145 subjects.The images in DB have pose, rotation, position variations and cluttered backgrounds.The results achieved by the proposed system are encouraging: 0.277% EER and 99.488% RR.\n\nLiterature Review:",
"role": "user"
},
{
"content": "There are few approaches using ML algorithms for ROI extraction regressing either a predefined shape or a set of points. Initially, Doublet et al. BIB001 considered to fit an Active Shape Model (ASM) to a number of points describing the shape of a hand (with spread fingers). The model regressed the output of a skin segmentation step, after which the centers of the two finger valleys were used to normalize the hand's rotation. Ferrer et al. BIB002 used a similar ASM to extract the hand from the background in the GPDS-CL1 dataset. Aykut et al. BIB004 considered an Active Appearance Model (AAM), which also considered the texture information from the hand's surface. They also provided the first evaluation of predicted key-points. Because the acquisition of images was performed in a considerably constrained environment, no normalization was required relative to the palmprint's scale. Aykut et al. preferred to report the error in terms of pixels (from the ground truth points). Recently, Shao et al. employed a complex pipeline for ROI extraction for unconstrained palmprint recognition. The approach included an initial stage of palmprint region detection using Histogram of Oriented Gradients (HOG) and a sliding window providing candidate regions at several scales to a pre-trained SVM classifier for palmprint detection. A tree regressor BIB003 (initially developed for face key-point detection) was then used for the landmark regression task applied to all 14 key-points. Unfortunately, Shao et al. did not provide details regarding the performance of their ROI extraction, how its accuracy influences the recognition task, or any comparison with prior algorithms.",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.51086
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Survey on Ambient Intelligence in Healthcare \nChapter Title: F. Smart Hospitals \n1. Abstract of Cited Paper (BIB001): Although researchers have developed robust approaches for estimating, location, and user identity, estimating user activities has proven much more challenging. Human activities are so complex and dynamic that it's often unclear what information is even relevant for modeling activities. Robust approaches to recognize user activities requires identifying the relevant information to be sensed and the appropriate sensing technologies. In our effort to develop an approach for automatically estimating hospital-staff activities, we trained a discrete hidden Markov model (HMM) to map contextual information to a user activity. We trained the model and evaluated it using data captured from almost 200 hours of detailed observation and documentation of hospital workers. In this article, we discuss our approach, the results, and how activity recognition could empower our vision of the hospital as a smart environment.\n\nLiterature Review:",
"role": "user"
},
{
"content": "AmI technology can be also useful for other stakeholders such as nurses, doctors, and other health care personnel, especially for facilitating communication among them. Sanchez et al. have developed the iHospital project which provides context aware communication based on activity recognition BIB002 . Various pieces of contextual information are collected and used, including location, time, the roles of the people present, and RFID-tagged artifacts, in order to help in decision making and communication. There have been some efforts to create AmI based middleware for healthcare. Rodriguez et al BIB001 Kofod et al. also describe using AmI technology for supporting health workers cooperating in patient diagnosis and treatment by using context information, goal recognition and case based reasoning. GerAmi (Geriatric Ambient Intelligence) is another AmI hospital project which helps doctors and nurses to monitor patients and to better manage theirs tasks . For example, it keeps track of the patients' locations using RFID technology and generates alarms, if needed. It also allocates tasks to nurses based on various contextual information such as the availability of nearby nurses and their profile information.",
"role": "assistant"
}
] |
science.mslr2022_cochrane_multidoc_summarization
|
science.mslr2022_cochrane_multidoc_summarization.3663
|
[
{
"content": "Based on the RCT reports below, write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article.\n\n\n\nTitle 1:\nStandard WHO-ORS versus reduced-osmolarity ORS in the management of cholera patients.\nAbstract 1:\nThe study compared the safety and efficacy of an oral rehydration salts (ORS) solution, containing 75 mmol/L of sodium and glucose each, with the standard World Health Organization (WHO)-ORS solution in the management of ongoing fluid losses, after initial intravenous rehydration to correct dehydration. The study was conducted among patients aged 12-60 years hospitalized with diarrhoea due to cholera. One hundred seventy-six patients who were hospitalized with acute diarrhoea and signs of severe dehydration were rehydrated intravenously and then randomly assigned to receive either standard ORS solution (311 mmol/L) or reduced-osmolarity ORS solution (245 mmol/L). Intakes and outputs were measured every six hours until the cessation of diarrhoea. During maintenance therapy, stool output, intake of ORS solution, duration of diarrhoea, and the need for unscheduled administration of intravenous fluids were similar in the two treatment groups. The type of ORS solution that the patients received did not affect the mean serum sodium concentration at 24 hours after randomization and the relative risk of development of hyponatraemia. However, patients treated with reduced-osmolarity ORS solution had a significantly lower volume of vomiting and significantly higher urine output than those treated with standard WHO-ORS solution. Reduced-osmolarity ORS solution was as efficacious as standard WHO-ORS solution in the management of cholera patients. The results indicate that reduced-osmolarity ORS solution is also as safe as standard WHO-ORS solution. However, because of the limited sample size in the study, the results will have to be confirmed in trials, involving a larger number of patients.\n\n\nTitle 2:\nReduced osmolarity oral rehydration salt in Cholera.\nAbstract 2:\nIn a controlled clinical trial conducted in 34 adults with severe cholera diarrhoea, the use of a relatively dilute oral rehydration salt (ORS) solution (sodium 67, potassium 20, chloride 66, citrate 7, glucose 89 mmol/l, osmolality 249 mOsmol/kg) caused a 29% (p=0.003) reduction in stool output over the first 24 h and a 37% (p=0.001) reduction over the first 48 h compared with 29 controls who received the hyperosmolar WHO/UNICEF ORS. No controls but 3 study-group patients had marked but asymptomatic hyponatraemia (sodium <125 mmol/l) at 24 h. Twenty-four % of controls and 12% of patients receiving the dilute ORS needed unscheduled intravenous therapy for recurrence of dehydration. The ORS intake was twice the 48 h stool volume in controls and 3 times in the study group. The test ORS with a reduced glucose and sodium concentration is more efficient than the WHO/UNICEF ORS in preserving net intestinal fluid balance in severe cholera.\n\n\nTitle 3:\nEfficacy of oral hyposmolar glucose-based and rice-based oral rehydration salt solutions in the treatment of cholera in adults.\nAbstract 3:\nRecent animal experiments and clinical trials have shown that both osmolarity and rice as the organic components are important factors for net intestinal absorption of an oral rehydration salt solution.\n In a controlled clinical trial 123 male adult patients with severe cholera, after initial rehydration with intravenous Ringer's lactate solution, were randomly assigned to receive one of the four oral rehydration salt solutions: WHO ORS, ORS containing 70 mmol/l Na+ and 16.2 g/l glucose, rice ORS containing 50 g/l rice and 90 mmol/l Na+, and rice ORS containing 50 g/l rice and 70 mmol/l Na+. All patients received 300 mg of doxycycline as a single dose.\n Patients who received rice-low-sodium ORS subsequently had lower (P < 0.05) stool output, ORS consumption, and diarrhoea duration than the other three ORS groups.\n We conclude that rice-based low-sodium ORS is superior for treating adult cholera.\n\n\nTitle 4:\nEvaluation of oral hypo-osmolar glucose-based and rice-based oral rehydration solutions in the treatment of cholera in children.\nAbstract 4:\nIn a randomized controlled clinical trial, the efficacy of a low-sodium low-glucose oral rehydration solution (ORS) and a low-sodium rice-based ORS was compared with standard WHO glucose ORS in the treatment of severe cholera in children aged 2-10y. In total, 120 children were evaluated for the study, of whom 58 patients were positive for Vibrio cholerae and were included in the study. Of these 58 cases, 19 received rice-based hypo-osmolar ORS, 20 received WHO-ORS and 19 received glucose-based hypo-osmolar ORS. The clinical characteristics (age, preadmission duration of diarrhoea, frequency of stool before admission, incidence of vomiting, body weight and volume of initial fluid requirement) were comparable in the three treatment groups. All patients received tetracycline in a dose of 50 mg/kg/d of body weight in 4 divided doses for 3 d.\n Patients who received rice-based hypo-osmolar ORS had subsequently reduced (p < 0.05) stool output, ORS consumption and diarrhoea duration than the patients who received either WHO-ORS or glucose-based hypo-osmolar ORS.\n\n\nTitle 5:\nControlled trial of hypo-osmalar versus World Health Organization oral rehydration solution.\nAbstract 5:\nTo compare the safety and efficacy of a hyposmolar oral rehydration solution (H-ORS) (245 mmol/liter) with the World Health Organization oral rehydration solution (WHO ORS) in cholera and acute non-cholera diarrhea.\n Controlled clinical trial.\n Diarrhea training and treatment unit.\n Thirty-five culture proven cholera and 135 acute non-cholera diarrheal patients randomly received H-ORS or WHO-ORS. Intake and output were measured every 4 hours.\n Analysis of the total cases revealed rehydration phase (p=0.048, 95% CI 0.64-0.99) and overall (p=0.046, 95% CI 0.70-0.99) frequency of stools to be significantly less in the H-ORS group. In the severely malnourished, the rehydration phase (p=0.032, 95% CI 0.55-97), maintenance phase (p=0.035, 95% CI 0.51-0.97) and overall (p=0.011; 0.95% CI 0.55-0.93) stool frequency were significantly decreased in the H-ORS group. The amount of ORS consumed in the maintenance phase of the cholera cases was significantly (p=0.04, 95% CI 0.44-0.98) less in the H-ORS group. All other parameters, despite showing a decreasing trend, were statistically comparable in the cholera, non-cholera and total cases. The amount of intravenous fluid needed was significantly more in the noncholera and total cases on H-ORS. In the non-breastfed cases, under two years of age, the total duration of diarrhea was significantly decreased (p=0.03; 95% CI 11.07-11.45) but the need for intravenous fluids significantly increased (p=0.02; 95% CI 109.8-112.1) in the H-ORS group. The proportion of children vomiting, the weight gain, urine passed in 24 hours, serum sodium, caloric intake and failure rate were comparable.\n H-ORS is as safe and effective as the WHO-ORS and may have some additional benefits in malnourished children.\n\n\nTitle 6:\nMulticenter, randomized, double-blind clinical trial to evaluate the efficacy and safety of a reduced osmolarity oral rehydration salts solution in children with acute watery diarrhea.\nAbstract 6:\nTo compare the efficacy of a reduced osmolarity oral rehydration salts (ORS) solution (75 mmol/L of sodium [Na], 20 mmol/L of potassium [K], 65 mmol/L of chloride, 10 mmol/L of citrate, and 75 mmol/L of glucose; osmolarity, 245 mosm/L) with that of the standard World Health Organization (WHO) ORS solution.\n A multicenter, double-blind, randomized, controlled clinical trial conducted in children with acute diarrhea in 5 developing countries to measure mean stool output in the 24 hours after randomization, proportion of children who required unscheduled intravenous therapy, proportion of children who vomited in the first 24 hours, and diarrhea duration after randomization.\n A total of 675 children who ranged in age from 1 to 24 months and who had acute diarrhea and dehydration were enrolled in the trial; 341 were randomized to receive reduced osmolarity ORS solution, and 334 were randomized to receive the WHO ORS solution. The mean (SE) stool output (g/kg) in the first 24 hours (reduced osmolarity ORS solution vs WHO ORS solution = 114 [4] vs 125 [5]) and during the total study period (reduced osmolarity ORS solution vs WHO ORS solution = 320 [18] vs 331 [18]) were comparable. The proportion of children who vomited in the first 24 hours (reduced osmolarity ORS solution vs WHO ORS solution = 58% vs 62%) and the diarrhea duration in the 2 treatment groups, compared by log rank test, were similar. The proportion of children who required unscheduled intravenous therapy was significantly lower in children who received reduced osmolarity ORS solution (10%) as compared with those who received the WHO ORS solution (15%; odds ratio = 0.6, 95% confidence interval = 0.4-1.0). There was no significant difference in the incidence of hyponatremia (serum Na <130 mmol/L) at 24 hours between the 2 treatment groups (11% in reduced osmolarity ORS solution group vs 9% in the WHO ORS solution group; odds ratio = 1.3; 95% confidence interval = 0.8-2.2). The frequency of patients with serum Na <125 mmol/L at 24 hours was 13 of 341 (4%) in children who were treated with reduced osmolarity ORS solution versus 7 of 334 (2%) in children who received the WHO ORS solution.\n Treatment with reduced osmolarity ORS solution was associated with a 33% reduction in the need for unscheduled intravenous therapy and had no apparent effect on stool output and illness duration when compared with treatment with the standard WHO ORS solution. Children with acute diarrhea, therefore, may benefit from a reduced osmolarity ORS solution. The results of trials that examine the efficacy and safety of reduced osmolarity ORS solution in adult patients with cholera have to be taken into consideration before consensus on composition of oral rehydration formulation can be reached.\n\n\nTitle 7:\nEfficacy and safety of oral rehydration solution with reduced osmolarity in adults with cholera: a randomised double-blind clinical trial. CHOICE study group.\nAbstract 7:\nThe effects of oral rehydration solution (ORS) with reduced osmolarity on children with acute watery diarrhoea are known, but little is known about the effects of such ORS on adults with cholera. We aimed to compare the efficacy and safety of an ORS with reduced osmolarity with that of standard WHO ORS in adults with cholera.\n We undertook a double-blind, controlled clinical trial in adults with severe cholera at the International Centre for Diarrhoeal Disease Research, Bangladesh. Our primary outcomes were mean stool output in the 24 h after randomisation, proportion of patients who needed unscheduled intravenous therapy, and proportion of patients with biochemical hyponatraemia 24 h after randomisation.\n 147 patients received ORS with reduced osmolarity and 153 received standard WHO ORS. There was no significant difference between the two groups in terms of main outcome variables: mean initial 24 h and total stool output (reduced osmolarity vs standard WHO ORS 212 [SE 8] vs 207 [8] and 284 [13] vs 273 [13] g/kg respectively), duration of diarrhoea (46 [1.5] vs 43 [1.5]). The proportion of patients vomiting during the first 24 h and the proportion who received unscheduled intravenous infusion during the first 24 h was similar between groups. More patients on reduced osmolarity ORS than on standard WHO ORS developed hyponatraemia during the first 24 h, defined as serum sodium concentration below 130 mmol/L (29 of 142 vs 16 of 150; odds ratio 2.1 [95% CI 1.1-4.1]). However, all hyponatraemic patients in both groups were symptom-free and the proportion of patients with serum sodium concentration below 125 mmol/L was similar between groups.\n There was no difference in clinical outcome between cholera patients treated with reduced osmolarity ORS solution and those treated with standard WHO ORS. The risk of increased incidence of symptom-free hyponatraemia in patients with cholera treated with an ORS with reduced osmolarity should be further assessed by meta-analysis. The risk should be taken into account when choice of ORS is made in areas in which cholera is endemic.",
"role": "user"
},
{
"content": "In people with cholera, ORS ≤ 270 is associated with biochemical hyponatraemia when compared with ORS ≥ 310, but there are no differences in terms of other outcomes. Although this risk does not appear to be associated with any serious consequences, the total patient experience in existing trials is small. Under wider practice conditions, especially where patient monitoring is difficult, caution is warranted.",
"role": "assistant"
}
] |
science.covid_deepset_qa
|
science.covid_deepset_qa.1865
|
[
{
"content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: With the appearance of a new H2N2 pandemic\nstrain in 1957 (“Asian flu”), the direct H1N1 Viral descen-\ndants 0f the 1918 pandemic strain disappeared from human\ncirculation entirely, although the related lineage persisted\nenzootically in pigs. But in 1977, human H1N1 Viruses\nsuddenly “reemerged” from a laboratory freezer (9). They\ncontinue to circulate endemically and epidemically. \n\nThus in 2006, 2 major descendant lineages of the 1918\nH1N1 Virus, as well as 2 additional reassortant lineages,\npersist naturally: a human epidemic/endemic H1N1 line-\nage, a porcine enzootic H1N1 lineage (so-called classic\nswine flu), and the reassorted human H3N2 Virus lineage,\nwhich like the human H1N1 Virus, has led to a porcine\nH3N2 lineage. None of these Viral descendants, however,\napproaches the pathogenicity of the 1918 parent Virus. Apparently, the porcine H1N1 and H3N2 lineages uncom-\nmonly infect humans, and the human H1N1 and H3N2 lin-\neages have both been associated with substantially lower\nrates ofillness and death than the virus of 1918. In fact, cur-\nrent H1N1 death rates are even lower than those for H3N2\nlineage strains (prevalent from 1968 until the present). H1N1 Viruses descended from the 1918 strain, as well as \nH3N2 Viruses, have now been cocirculating worldwide for\n29 years and show little evidence of imminent extinction. Trying To Understand What Happened\n\nBy the early 1990s, 75 years of research had failed to\nanswer a most basic question about the 1918 pandemic:\nwhy was it so fatal? No Virus from 1918 had been isolated,\nbut all of its apparent descendants caused substantially\nmilder human disease. Moreover, examination of mortality\ndata from the 1920s suggests that within a few years after\n1918, influenza epidemics had settled into a pattern of\nannual epidemicity associated with strain drifting and sub-\nstantially lowered death rates. Did some critical Viral genet-\nic event produce a 1918 Virus of remarkable pathogenicity\nand then another critical genetic event occur soon after the\n1918 pandemic to produce an attenuated H1N1 Virus? In 1995, a scientific team identified archival influenza\nautopsy materials collected in the autumn of 1918 and\nbegan the slow process of sequencing small Viral RNA\nfragments to determine the genomic structure of the\ncausative influenza Virus (10). These efforts have now\ndetermined the complete genomic sequence of 1 Virus and\npartial sequences from 4 others. The primary data from the\nabove studies (11717) and a number of reviews covering\ndifferent aspects of the 1918 pandemic have recently been\npublished ([8720) and confirm that the 1918 Virus is the\nlikely ancestor of all 4 of the human and swine H1N1 and\nH3N2 lineages, as well as the “extinct” H2N2 lineage. No\nknown mutations correlated with high pathogenicity in\nother human or animal influenza Viruses have been found\nin the 1918 genome, but ongoing studies to map Virulence\nfactors are yielding interesting results. The 1918 sequence\ndata, however, leave unanswered questions about the ori-\ngin of the Virus (19) and about the epidemiology of the\npandemic. When and Where Did the 1918 Influenza\nPandemic Arise? Before and after 1918, most influenza pandemics\ndeveloped in Asia and spread from there to the rest of the\nworld. Confounding definite assignment of a geographic\npoint of origin, the 1918 pandemic spread more or less\nsimultaneously in 3 distinct waves during an z12-month\nperiod in 191871919, in Europe, Asia, and North America\n(the first wave was best described in the United States in\nMarch 1918). Historical and epidemiologic data are inade-\nquate to identify the geographic origin of the Virus (21),\nand recent phylogenetic analysis of the 1918 Viral genome\ndoes not place the Virus in any geographic context ([9). Although in 1918 influenza was not a nationally\nreportable disease and diagnostic criteria for influenza and\npneumonia were vague, death rates from influenza and\npneumonia in the United States had risen sharply in 1915\nand 1916 because of a major respiratory disease epidemic\nbeginning in December 1915 (22). Death rates then dipped\nslightly in 1917. The first pandemic influenza wave\nappeared in the spring of 1918, followed in rapid succes-\nsion by much more fatal second and third waves in the fall\nand winter of 191871919, respectively (Figure 1). Is it pos-\nsible that a poorly-adapted H1N1 Virus was already begin-\nning to spread in 1915, causing some serious illnesses but\nnot yet sufficiently fit to initiate a pandemic? Data consis-\ntent with this possibility were reported at the time from\nEuropean military camps (23), but a counter argument is\nthat if a strain with a new hemagglutinin (HA) was caus-\ning enough illness to affect the US national death rates\nfrom pneumonia and influenza, it should have caused a\npandemic sooner, and when it eventually did, in 1918,\nmany people should have been immune or at least partial-\nly immunoprotected. “Herald” events in 1915, 1916, and\npossibly even in early 1918, if they occurred, would be dif-\nficult to identify. The 1918 influenza pandemic had another unique fea-\nture, the simultaneous (or nearly simultaneous) infection\nof humans and swine. The Virus of the 1918 pandemic like-\nly expressed an antigenically novel subtype to which most\nhumans and swine were immunologically naive in 1918\n(12,20). Recently published sequence and phylogenetic\nanalyses suggest that the genes encoding the HA and neu-\nraminidase (NA) surface proteins of the 1918 Virus were\nderived from an avianlike influenza Virus shortly before\nthe start of the pandemic and that the precursor Virus had\nnot circulated widely in humans or swine in the few\ndecades before (12,15, 24). More recent analyses of the\nother gene segments of the Virus also support this conclu-\nsion. Regression analyses of human and swine influenza\nsequences obtained from 1930 to the present place the ini-\ntial circulation of the 1918 precursor Virus in humans at\napproximately 191571918 (20). Thus, the precursor was\nprobably not circulating widely in humans until shortly\nbefore 1918, nor did it appear to have jumped directly\nfrom any species of bird studied to date (19). In summary,\nits origin remains puzzling. Were the 3 Waves in 1918—1 919 Caused\nby the Same Virus? If So, How and Why? Historical records since the 16th century suggest that\nnew influenza pandemics may appear at any time of year,\nnot necessarily in the familiar annual winter patterns of\ninterpandemic years, presumably because newly shifted\ninfluenza Viruses behave differently when they find a uni-\nversal or highly susceptible human population. Thereafter,\nconfronted by the selection pressures of population immu-\nnity, these pandemic Viruses begin to drift genetically and\neventually settle into a pattern of annual epidemic recur-\nrences caused by the drifted Virus variants. Figure 1. Three pandemic waves: weekly combined influenza and\npneumonia mortality, United Kingdom, 1918—1919 (21). In the 1918-1919 pandemic, a first or spring wave\nbegan in March 1918 and spread unevenly through the\nUnited States, Europe, and possibly Asia over the next 6\nmonths (Figure 1). Illness rates were high, but death rates\nin most locales were not appreciably above normal. A sec-\nond or fall wave spread globally from September to\nNovember 1918 and was highly fatal. In many nations, a\nthird wave occurred in early 1919 (21). Clinical similari-\nties led contemporary observers to conclude initially that\nthey were observing the same disease in the successive\nwaves. The milder forms of illness in all 3 waves were\nidentical and typical of influenza seen in the 1889 pandem-\nic and in prior interpandemic years. In retrospect, even the\nrapid progressions from uncomplicated influenza infec-\ntions to fatal pneumonia, a hallmark of the 191871919 fall\nand winter waves, had been noted in the relatively few\nsevere spring wave cases. The differences between the\nwaves thus seemed to be primarily in the much higher fre-\nquency of complicated, severe, and fatal cases in the last 2\nwaves. But 3 extensive pandemic waves of influenza within 1\nyear, occurring in rapid succession, with only the briefest\nof quiescent intervals between them, was unprecedented. The occurrence, and to some extent the severity, of recur-\nrent annual outbreaks, are driven by Viral antigenic drift,\nwith an antigenic variant Virus emerging to become domi-\nnant approximately every 2 to 3 years. Without such drift,\ncirculating human influenza Viruses would presumably\ndisappear once herd immunity had reached a critical\nthreshold at which further Virus spread was sufficiently\nlimited. The timing and spacing of influenza epidemics in\ninterpandemic years have been subjects of speculation for\ndecades. Factors believed to be responsible include partial\nherd immunity limiting Virus spread in all but the most\nfavorable circumstances, which include lower environ-\nmental temperatures and human nasal temperatures (bene-\nficial to thermolabile Viruses such as influenza), optimal\nhumidity, increased crowding indoors, and imperfect ven-\ntilation due to closed windows and suboptimal airflow. However, such factors cannot explain the 3 pandemic\nwaves of 1918-1919, which occurred in the spring-sum-\nmer, summer—fall, and winter (of the Northern\nHemisphere), respectively. The first 2 waves occurred at a\ntime of year normally unfavorable to influenza Virus\nspread. The second wave caused simultaneous outbreaks\nin the Northern and Southern Hemispheres from\nSeptember to November. Furthermore, the interwave peri-\nods were so brief as to be almost undetectable in some\nlocales. Reconciling epidemiologically the steep drop in\ncases in the first and second waves with the sharp rises in\ncases of the second and third waves is difficult. Assuming\neven transient postinfection immunity, how could suscep-\ntible persons be too few to sustain transmission at 1 point,\nand yet enough to start a new explosive pandemic wave a\nfew weeks later? Could the Virus have mutated profoundly\nand almost simultaneously around the world, in the short\nperiods between the successive waves? Acquiring Viral\ndrift sufficient to produce new influenza strains capable of\nescaping population immunity is believed to take years of\nglobal circulation, not weeks of local circulation. And hav-\ning occurred, such mutated Viruses normally take months\nto spread around the world. At the beginning of other “off season” influenza pan-\ndemics, successive distinct waves within a year have not\nbeen reported. The 1889 pandemic, for example, began in\nthe late spring of 1889 and took several months to spread\nthroughout the world, peaking in northern Europe and the\nUnited States late in 1889 or early in 1890. The second\nrecurrence peaked in late spring 1891 (more than a year\nafter the first pandemic appearance) and the third in early\n1892 (21 ). As was true for the 1918 pandemic, the second\n1891 recurrence produced of the most deaths. The 3 recur-\nrences in 1889-1892, however, were spread over >3 years,\nin contrast to 191871919, when the sequential waves seen\nin individual countries were typically compressed into\nz879 months. What gave the 1918 Virus the unprecedented ability to\ngenerate rapidly successive pandemic waves is unclear. Because the only 1918 pandemic Virus samples we have\nyet identified are from second-wave patients ([6), nothing\ncan yet be said about whether the first (spring) wave, or for\nthat matter, the third wave, represented circulation of the\nsame Virus or variants of it. Data from 1918 suggest that\npersons infected in the second wave may have been pro-\ntected from influenza in the third wave. But the few data\nbearing on protection during the second and third waves\nafter infection in the first wave are inconclusive and do lit-\ntle to resolve the question of whether the first wave was\ncaused by the same Virus or whether major genetic evolu-\ntionary events were occurring even as the pandemic\nexploded and progressed. Only influenza RNAipositive\nhuman samples from before 1918, and from all 3 waves,\ncan answer this question. What Was the Animal Host\nOrigin of the Pandemic Virus? Viral sequence data now suggest that the entire 1918\nVirus was novel to humans in, or shortly before, 1918, and\nthat it thus was not a reassortant Virus produced from old\nexisting strains that acquired 1 or more new genes, such as\nthose causing the 1957 and 1968 pandemics. On the con-\ntrary, the 1918 Virus appears to be an avianlike influenza\nVirus derived in toto from an unknown source (17,19), as\nits 8 genome segments are substantially different from\ncontemporary avian influenza genes.\nQuestion: When did the Swine Flu (Spanish Influenza) virus reappear in humans?",
"role": "user"
},
{
"content": "But in 1977, human H1N1 Viruses\nsuddenly “reemerged” from a laboratory freezer (9). They\ncontinue to circulate endemically and epidemically.",
"role": "assistant"
}
] |
science.scireviewgen_multidoc_summarization
|
science.scireviewgen_multidoc_summarization.27388
|
[
{
"content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Survey on Time-aware Business Process Modeling \nChapter Title: How this verification is proceeded? \n1. Abstract of Cited Paper (BIB001): The degree of flexibility of workflow management systems heavily influences the way business processes are executed. Constraint-based models are considered to be more flexible than traditional models because of their semantics: everything that does not violate constraints is allowed. Although constraint-based models are flexible, changes to process definitions might be needed to comply with evolving business domains and exceptional situations. Flexibility can be increased by run-time support for dynamic changes - transferring instances to a new model - and ad-hoc changes - changing the process definition for one instance. In this paper we propose a general framework for a constraint-based process modeling language and its implementation. Our approach supports both ad-hoc and dynamic change, and the transfer of instances can be done easier than in traditional approaches. \n2. Abstract of Cited Paper (BIB002): The diffusion of clinical guidelines to describe the proper way to deal with patients' situations is spreading out and opens new issues in the context of modeling and managing (temporal) information about medical activities. Guidelines can be seen as processes describing the sequence of activities to be executed, and thus approaches proposed in the business context can be used to model them. In this paper, we propose a general conceptual workflow model, considering both activities and their temporal properties, and focus on the representation of clinical guidelines by the proposed model. \n3. Abstract of Cited Paper (BIB003): Interorganizational workflows are a major step in automating B2B electronic commerce and to support collaborations of organizations on the technical level. Process views are an important conceptual modelling approach for interorganizational workflows as they allow interaction and communication while internal and private parts of the process can be hidden. However, it is essential to guarantee that an interorganizational workflow is free of conflicts and the overall quality assurances of the whole workflow can be achieved. This paper proposes an approach for checking temporal consistency of interorganizational workflows crossing boundaries of organizations. \n4. Abstract of Cited Paper (BIB004): Web service composition is a new way for implementing business processes. In particular, a choreography supports modeling and enactment of interorganizational business processes consisting of autonomous organizations. Temporal constraints are important quality criteria. We propose a technique for modeling temporal constraints in choreographies and orchestrations, checking whether the orchestrations satisfy the temporal constraints of a choreography and compute internal deadlines for the activities in an interorganizational workflow. \n5. Abstract of Cited Paper (BIB005): Current Web service composition approaches and languages such as WS-BPEL do not allow to define temporal constraints in a declarative and separate way. Also it is not possible to verify if there are contradictions between the temporal constraints implemented in the composition. These limitations lead to maintainability and correctness problems. In this paper, we tackle these problems through a novel approach to temporal constraints in Web service compositions, which combines formal methods and aspect-oriented programming. In this approach, we use a powerful and expressive formal language, called XTUS-Automata, for specifying time-related properties and we introduce specification patterns that ease the definition of such constraints. The formal specifications are translated automatically into AO4BPEL aspects, which ensure the runtime monitoring of the temporal constraints. Our approach enables a declarative, separate, and verifiable specification of temporal properties and it generates automatically modular enforcement code for those properties. \n6. Abstract of Cited Paper (BIB006): We describe a relative-timed semantic model for Business Process Modelling Notation (BPMN). We define the semantics in the language of Communicating Sequential Processes (CSP). This model augments our untimed model by introducing the notion of relative time in the form of delays chosen non-deterministically from a range. We illustrate the application by an example. We also show some properties relating the timed semantics and BPMN's untimed process semantics by exploiting CSP refinement. Our timed semantics allows behavioural properties of BPMN diagrams to be mechanically verified via automatic model-checking as provided by the FDR tool. \n7. Abstract of Cited Paper (BIB007): Workflow technology has emerged as one of the leading technologies in modelling, redesigning, and executing business processes. Currently available workflow management systems (WfMS ) and research prototypes offer a very limited support for the definition, detection, and management of temporal constraints over business processes. In this paper, we propose a new advanced workflow conceptual model for expressing time constraints in business processes and, in particular, we introduce and discuss the concept of controllability for workflow schemata and its evaluation at process design time. Controllability refers to the capability of executing a workflow for any possible duration of tasks. Since in several situations durations of tasks cannot be decided by WfMSs , even tough the minimum and the maximum durations for each task are known, checking controllability is stronger than verifying the consistency of the workflow temporal constraints. \n8. Abstract of Cited Paper (BIB008): The integration of time constraints in Inter-Organizational Workflows (IOWs) is an important issue in the workflow research field. Since each partner exposes a limited version of his business process, some information is kept hidden and not visible to all partners. The inter-enterprise business process, however, is obtained by joining all activities and control flows that have relevant roles within the context of the global operation. It should be noted that this composition process does not intrinsically guarantee the satisfaction of any critical deadline constraints that may be imposed by the partners. Obviously, expressing and satisfying time deadlines is important for modern business processes that need to be optimized for efficiency and extreme competitiveness. In this paper, we propose a temporal extension to CoopFlow, an existing approach for designing and modeling IOW, based on Time Petri Net models. A method for expressing and publishing sensible time deadlines, by the partners, is given. We also give a systematic method assuring the verification and the consistency of the published time constraints within the context of the global business process, while maintaining the core advantage of CoopFlow, that each partner can keep the critical part of his business process private. \n9. Abstract of Cited Paper (BIB009): The Business Process Modeling Notation (BPMN) is a standard for modeling business processes in the early phases of systems development. Model verification is an important means to guarantee the trustiness of composite services. The verification of model, especially the model with strict time constraints, is a challenge in the field of trust composite services. Whether a model is trustworthy depends not only on the model structure but also on quantitative properties such as time properties. In this paper, we propose a mapping from BPMN to time Petri nets, and use the verification techniques on the basis. The algorithm we present can be used to check the model structure and the time choreography. \n10. Abstract of Cited Paper (BIB010): The correctness of business process models is critical for IT system development. The properties of business processes need to be analyzed when they are designed. In particular, business processes usually have various constraints on time and resources, which may cause serious problems like bottlenecks and deadlocks. In this paper, we propose an approach based on the model checking technique for verifying business process models with temporal and resource constraints. First, we extend Business Process Modeling Notation (BPMN) to handle these constraints. Then, we provide a mapping of the business process models described with this extended BPMN onto timed automata that can be verified by the UPPAAL model checker. This approach helps to eliminate various problems with time and resources in the early phase of development, and enables the quality assurance of business process models. \n11. Abstract of Cited Paper (BIB011): Current methods that deal with concurrent workflow temporal violations only focus on checking whether there are any temporal violations. They are not able to point out the path where the temporal violation happens and thus cannot provide specific solutions. This paper presents an approach based on a sprouting graph to find out the temporal violation paths in concurrent workflow processes as well as possible solutions to resolve the temporal violations. First, we model concurrent workflow processes with time workflow net and a sprouting graph. Second, we update the sprouting graph at the checking point. Finally, we find out the temporal violation paths and provide solutions. We apply the approach in a real business scenario to illustrate its advantages: 1) It can dynamically check temporal constraints of multiple concurrent workflow processes with resource constraints; 2) it can give the path information in the workflow processes where the temporal violation happens; and 3) it can provide solution to the temporal violation based on the analysis. \n12. Abstract of Cited Paper (BIB012): Current logistics methods are more focused on strategic goals and do not deal with short term objectives, such as, reactivity and real-time constraints. Automated logistics management systems tend to facilitate information sharing between companies, in order to support cooperative strategies, improve productivity, control service quality and reduce administrative costs. In this paper, we discuss the application of Inter-Organizational Workflows (IOW) for automating logistic procedures in a collaborative context. A case study of healthcare process is presented, and focuses on the negotiations aspects of temporal constraints in critical situations. We show how our proposed temporal extension of the CoopFlow approach, brings advantages to automating logistics operational procedures, by providing real-time data knowledge and decision routing for the case of emergency healthcare. \n13. Abstract of Cited Paper (BIB013): In this paper, we propose an approach for analyzing and validating a composition of services with respect to real time properties. We consider services defined using an extension of the Business Process Execution Language (BPEL) where timing constraints can be associated to the execution of an activity or define delays between events. The goal is to check whether a choreography of timed services satisfies given complex real time requirements. Our approach is based on a formal interpretation of timed choreographies in the Fiacre verification language that defines a precise model for the behavior of services and their timed interactions. We also rely on a logic-based language for property definition to formalize complex real-time requirements and on specific tooling for model-checking Fiacre specifications.\n\nLiterature Review:",
"role": "user"
},
{
"content": "Eg. model checker tools, algorithms, etc. Based on the above observations, we identified that most of the already studied constraints include the temporal perspective. The temporal constraints are usually correlated with other constraints such as data and resource constraints BIB011 BIB012 . Consequently, there are been several attempts to model the different constraints in the business process diagram itself using the defacto industrial standard for business process modeling, BPMN (Gagné and Trudel, 2009; BIB014 . The use of a graph-based modeling approach of business processes as BPMN, is a competitive advantage. Indedeed, the visual appeal of the graph-based modeling approaches makes them useful for all kinds of workflow designers since no technical background is required. Similarly, other research efforts BIB009 BIB013 BIB006 BIB012 BIB010 opted for formal specification languages with modeling capabilities such as Petri nets and Timed Automata. Whereas, other approaches like BIB007 ) opted for CSP as a process algebra language, which lacks for graphical support. The approach followed by BIB002 is somewhat different from the others since it models the constraints apart from the business process model (eg. by LTL formulas). When considering the business process model itself, there are works specifying different constraints for one business process. Others take into account the cooperation between more than one business process both in the web service composition field and in the interorganizational business process field. When addressing the issue of IOBP, it is inevitable to reason about the migration of the different constraints between the private and the public workflows. There are several ideas for further research especially in the IOBP field. We can, first focus on elaborating a generic modeling approach which supports different constraint modeling such as temporal constraints and other associated constraints, namely, resource and data constraints. When dealing with temporal constraints, we remarked the lack of absolute time constraints in the majority of the works. In addition to that, just one work has modeled time points obtained from the execution phase BIB006 . We propose to deal with sequence, choice and concurrency structures and thus adopting best and worst cases of execution. We now turn our attention to the temporal requirements verification problem. Temporal verification mechanisms are of paramount importance since they enable to detect, early on, possible temporal conflicts and to react to them effectively. In this context, although many efforts confound the time conflict verification of the model (i.e. the violation of some temporal requirements) with the structure verification (i.e. the analysis of dead tasks, bottlenecks, deadlocks and loops) BIB006 BIB011 , there are some works which have tried to differentiate the two verification processes BIB010 BIB012 . BIB010 Time Petri nets dead task + deadlock +infinite loops the reachability graph of the Petri nets the time conflicts of the model the time choreography verification algorithm BIB012 Time workflow nets duration between two activitie Algorithms (TWF-net) less than s time units + UPAAL model checker BIB001 Web Service Timed deadlock model checker NuSMV State Transition Systems (WSTTS) + maximal and minimal duration of the process BIB006 XTUS-Automata deadlock UPAALmodel checker Timed Automata compatibility analysis of the web Algorithms service choreography deadlock UPAAL model checker BIB004 Timed activity graphs Temporal consistency Algorithms BIB005 + Time conformance BIB009 Time Petri nets Time conformance TINA model checker and LPT (Makni et al., 2011) (Guermouche and BIB014 A modeling environment the absence constraint with delay inspired from BPMN + the response constraint with delay TINA model checker The Fiacre specification Temporal Constraint with Granularity the consistency Algorithms (TCG) graph BIB003 A proposed conceptual The controllability checking Algorithms BIB008 workflow model BIB007 Communicating Sequential Time compatibility FDR model checker Processes (CSP) To cope with the time conflict verification, there are some works which have neglected the intra-activity temporal requirements (eg. the duration of the modeled activities) . On the other hand, there are some approaches which have neglected the inter-activity temporal dependencies BIB011 BIB010 . Besides, the approach detailed in BIB012 has tried to include the two different temporal requirements. Additionally, there are some efforts concentrating on verifying other issues such as time conformance BIB005 BIB009 , the absence constraint BIB014 , and controllability BIB008 . Once the verification process is conducted and a possible violation is detected, only few approaches BIB012 tried to detect erroneous paths and to propose solutions. So far, the approach detailed in BIB012 has proposed the modification of the duration of some activities as solution to the temporal violation in concurrent workflow processes with resource constraints. Additionnally, the author in (Guermouche, 2010) has considered the use of mediators when dealing with the compatibility analysis of the web service choreography. The idea of mediators proposed in sounds very promising since it has succeeded in resolving a large set of temporal violations in an efficient manner. Typically, researchers in the field of time management in the business process field are invited to widen the set of possible solutions to temporal constraints violations. From the research directions that have to be considered, we can notice the modification of the allocation policy of the shared resources and the change of the overall business process structure arriving at the substitution of some activities. Finally, we can proceed by monitoring or enforcing of the different constraints in the execution phase. Another line of research is to study constraint-based business process models which offer design decisions at the execution time and enable different process variants.",
"role": "assistant"
}
] |
science.medmentions_ner
|
science.medmentions_ner.577
|
[
{
"content": "Extract all unique entities from this biomedical abstract. Only choose entities from these types: [\"Virus\", \"MedicalDevice\", \"BodySubstance\", \"SpatialConcept\", \"BiologicFunction\", \"ResearchActivity\", \"AnatomicalStructure\", \"ProfessionalOrOccupationalGroup\", \"HealthCareActivity\", \"BiomedicalOccupationOrDiscipline\", \"Bacterium\", \"Chemical\", \"InjuryOrPoisoning\", \"IntellectualProduct\", \"Finding\", \"ClinicalAttribute\", \"Organization\", \"Eukaryote\", \"Food\", \"BodySystem\", \"PopulationGroup\"].\n\nOutput a JSON object where keys are entity types and values are lists of extracted entities. If no entities found for a type, use empty list [].\n\nAbstract: The Effect of Image Review before Patient Discharge on Study Completeness and Sonographer Job Satisfaction in a Pediatric Echocardiographic Laboratory Incomplete echocardiographic assessment accounts for approximately 10% of preventable diagnostic errors and may place children at risk for adverse outcomes or increased testing. The aim of this study was to determine if physician review of images improves study completeness. A prospective quality improvement (QI) study initiated physician review of first-time echocardiographic studies for completeness before patient discharge. Studies were incomplete if not all anatomic structures were diagnostically demonstrated. QI examinations were compared with controls obtained before study initiation. Demographic and clinical information and duration of scan were collected during the control and QI periods. An anonymous survey was administered to the sonographers to assess perceptions of the intervention. There were no differences between the QI (n = 63) and control (n = 63) groups in age, height, weight, and technical barriers. After study completion, 35% of control scans versus 5% of QI scans were incomplete (P < .001). In the QI group, the sonographer, physician, or both returned to scan in 12 (19%), nine (14%), and two (3%) studies, respectively. QI studies were longer than control studies (44 vs 36 min, P = .003) before review. Physician review added a median of 6 min (range, 1-28 min). The majority of sonographers believed that immediate review improved communication, and 50% believed that it improved their job satisfaction. Review of initial outpatient echocardiographic examinations before patient discharge significantly improves study completeness. Review adds a nominal amount of time to total study duration, improves sonographer - physician communication, and may prevent unnecessary testing, potentially reducing the cost of care.",
"role": "user"
},
{
"content": "{\"AnatomicalStructure\": [\"anatomic structures\"], \"Bacterium\": [], \"BiologicFunction\": [\"job satisfaction\", \"Job Satisfaction\", \"perceptions\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"adverse outcomes\"], \"Food\": [], \"HealthCareActivity\": [\"echocardiographic\", \"scans\", \"intervention\", \"Pediatric Echocardiographic\", \"assessment\", \"patient discharge\", \"Patient Discharge\", \"scan\", \"examinations\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"survey\", \"Image\", \"images\", \"clinical information\"], \"MedicalDevice\": [], \"Organization\": [\"Laboratory\"], \"PopulationGroup\": [\"group\"], \"ProfessionalOrOccupationalGroup\": [\"physician\", \"Physician\", \"Sonographer\", \"sonographers\", \"sonographer\"], \"ResearchActivity\": [\"Study\", \"Studies\", \"studies\", \"study\", \"control studies\"], \"SpatialConcept\": [], \"Virus\": []}",
"role": "assistant"
}
] |
science.pico_ner
|
science.pico_ner.3457
|
[
{
"content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nOxytocin increases eye contact during a real-time , naturalistic social interaction in males with and without autism . Autism spectrum conditions ( autism ) affect ~1 % of the population and are characterized by deficits in social communication . Oxytocin has been widely reported to affect social-communicative function and its neural underpinnings . Here we report the first evidence that intranasal oxytocin administration improves a core problem that individuals with autism have in using eye contact appropriately in real-world social settings . A randomized double-blind , placebo-controlled , within-subjects design is used to examine how intranasal administration of 24 IU of oxytocin affects gaze behavior for 32 adult males with autism and 34 controls in a real-time interaction with a researcher . This interactive paradigm bypasses many of the limitations encountered with conventional static or computer-based stimuli . Eye movements are recorded using eye tracking , providing an objective measurement of looking patterns . The measure is shown to be sensitive to the reduced eye contact commonly reported in autism , with the autism group spending less time looking to the eye region of the face than controls . Oxytocin administration selectively enhanced gaze to the eyes in both the autism and control groups ( transformed mean eye-fixation difference per second=0.082 ; 95 % CI:0.025-0.14 , P=0.006 ) . Within the autism group , oxytocin has the most effect on fixation duration in individuals with impaired levels of eye contact at baseline ( Cohen 's d=0.86 ) . These findings demonstrate that the potential benefits of oxytocin in autism extend to a real-time interaction , providing evidence of a therapeutic effect in a key aspect of social communication .",
"role": "user"
},
{
"content": "{\"Intervention\": [\"placebo-controlled\", \"intranasal oxytocin\", \"Oxytocin\"], \"Outcome\": [], \"Participant\": [\"males\", \"with and without autism\", \"Autism spectrum conditions ( autism )\", \"32\", \"autism\", \"individuals with autism\"]}",
"role": "assistant"
}
] |
science.scientific_lay_summarisation_plos_single_doc_summ
|
science.scientific_lay_summarisation_plos_single_doc_summ.3998
|
[
{
"content": "Summarize the article in an uncomplicated manner.\n\nTitle: Quantitative single cell analysis uncovers the life/death decision in CD95 network\nArticle:\nAbstract:\nCD95/Fas/APO-1 is a member of the death receptor family that triggers apoptotic and anti-apoptotic responses in particular, NF-κB. These responses are characterized by a strong heterogeneity within a population of cells. To determine how the cell decides between life and death we developed a computational model supported by imaging flow cytometry analysis of CD95 signaling. Here we show that CD95 stimulation leads to the induction of caspase and NF-κB pathways simultaneously in one cell. The related life/death decision strictly depends on cell-to-cell variability in the formation of the death-inducing complex( DISC) on one side( extrinsic noise) vs. stochastic gene expression of the NF-κB pathway on the other side( intrinsic noise). Moreover, our analysis has uncovered that the stochasticity in apoptosis and NF-kB pathways leads not only to survival or death of a cell, but also causes a third type of response to CD95 stimulation that we termed ambivalent response. Cells in the ambivalent state can undergo cell death or survive which was subsequently validated by experiments. Taken together, we have uncovered how these two competing pathways control the fate of a cell, which in turn plays an important role for development of anti-cancer therapies.\nIntroduction:\nApoptosis is a program of cell death, which is essential for all multicellular organisms[1]. The crosstalk between apoptotic and anti-apoptotic pathways plays a key role in shaping life/death decisions in the cell. Furthermore, the success of anti-cancer therapies strongly depends on the efficiency of cell death induction in a single cell. However, a number of apoptotic stimuli are well known to activate strong anti-apoptotic response, which naturally might prevent apoptosis by upregulation of anti-apoptotic genes and, hence, counteract the effect of anti-cancer therapies[2, 3]. In particular, members of the death receptor( DR) family have been reported to activate both apoptotic as well as anti-apoptotic responses[1, 4]. The DR family is a subfamily of TNFR-superfamily, which includes TNF-R1, CD95/Fas and TRAIL-R1/2[5]. Triggering of the DR family with the cognate death ligands results in the formation of high molecular weight complexes, which induce cell death pathways and anti-apoptotic responses including activation of the transcription factor NF-κB[6–9]. The induction of a particular pathway in the DR system is a rather complex process, which is highly context dependent and multifactorial[8, 10]. Importantly, molecular mechanisms underlying the intricate details of the cross-talk between apoptotic and anti-apoptotic pathways have not been established yet. The complexity of the response to DR activation stems from the fact that it is often heterogeneous within a population of cells[11–13]. The sources of the heterogeneity include genetic variations within cells, cell cycle effects, and stochastic effects from gene translation/transcription, which cumulatively might lead to different initial abundances of proteins within different cells[10, 13]. For deciphering the multifactorial nature of cell death decisions in single cells, computational modeling paired with new experimental technologies providing a large number of data for the protein expression levels from individual cells are of indispensable value[12, 14–16]. Of particular importance in this regard, is the cutting edge technology of imaging flow cytometry( IFC), which combines microscopy and flow cytometry in one measurement enabling quantitative analysis of endogenous cellular protein levels estimated from a large number of cells simultaneously[17, 18]. This feature of IFC is a strong advantage compared to confocal imaging that is mostly based on the application of artificially overexpressed activity probes, which might be often misleading. Furthermore, IFC in combination with machine learning provides a unique platform to quantitatively assign single cell events over a large number of cells and thereby has a strong advantage over confocal microscopy, which often needs manual analysis. In this study we addressed the interplay of apoptotic and anti-apoptotic pathways in single cells by analyzing the signaling network of the exemplified member of the DR family CD95. CD95 stimulation leads to formation of the CD95 death-inducing signaling complex( DISC)[1]. The DISC comprises CD95, the adaptor protein FADD, the initiator procaspase-8a/b( p55/p53), procaspase-10 and c-FLIP( S1A Fig). After recruitment to the DISC, procaspase-8 builds death effector domain( DED) chains/filaments, formed via homotypic interactions between the DEDs of individual procaspase-8 molecules[19–21]. This provides the platform for homodimerization of procaspase-8 molecules, subsequent activation of procaspase-8 homodimers, and their processing with formation of the active caspase-8 heterotetramers p102-p182( S1A Fig). The activation of caspase-8 might be blocked by c-FLIP proteins, which incorporate into the DED chains and form heterodimers with procaspase-8[21–23]. Interestingly, c-FLIP proteins act not only as inhibitors of CD95-induced apoptosis but are also essential for NF-κB activation[22, 24]. Namely, the c-FLIP cleavage products p43-FLIP and p22-FLIP( S1A Fig), have been reported to induce NF-κB[24–26]. The p43-FLIP cleavage product has been shown to play an essential role for CD95-mediated NF-κB activation[22]. The classical NF-κB activation pathway involves degradation of the NF-κB bound inhibitors of kappa B( IκBs), which are phosphorylated by the IκB kinase( IKK)-complex containing two catalytic subunits( IKKα and IKKβ) and the regulatory subunit NF-κB essential modulator( NEMO). Consequently, the NF-κB dimer( p65/RelA and p50) is released to enter the nucleus, where activation of the transcription of the target genes takes place[27]. The intricate regulation of cell fate upon induction of CD95-mediated apoptosis vs. NF-κB at the single cell level remains largely unknown. Recently, a number of studies have highlighted the importance of the caspase-8 activation rate in single cells for the initiation of CD95-mediated apoptosis or survival[12, 16]. However, the role of CD95-induced crosstalk of apoptosis with the anti-apoptotic signaling pathways such as NF-κB in the cell fate has so far only been addressed at the population level and never at the single cell level[24, 28]. In this study we have investigated the regulation of these competing pathways in single cells using computational modeling, cutting edge technology of IFC and quantitative western blot. We show that cell-to-cell variability in the apoptotic phenotype does not result from NF-κB related stochasticity, but from heterogeneities in the composition of DED chains at the CD95 DISC.\nDiscussion:\nA number of models addressing apoptosis and cell fate in single cells have been created[10, 12, 13]. However, single cell modeling of the interplay between apoptosis and anti-apoptosis pathways, which is a key feature of this model, has been missing so far. The understanding of this interplay at the single cell level is very important in the context of creation of efficient anti-cancer therapies specifically inducing apoptosis in every single cell. To understand the behavior of these competing pathways, we connected the strength of the apoptotic vs. NF-κB response with the stoichiometry of the DISC/DED chains using in silico analysis and single cell experimental data. Most of the models describing single cell behavior use experimental data that are generated with artificially overexpressed caspase activity probes or tagged NF-κB proteins that might be influencing activation of this pathway. In contrast, our study is entirely focused on the analysis of endogenous proteins at the single cell level which is deemed possible due to the state of the art high throughput IFC analysis. Furthermore, IFC provides a platform to quantitatively assign single cell events over a large number of single cells using machine learning[42]. The latter potentially provides an enormous asset for building computational models and our study presents one of the first models of apoptosis and anti-apoptosis pathways implementing IFC data. Among contemporary approaches there are several powerful single cell technologies that attract a major attention and allow to quantify endogenous proteins at the single cell level, in particular, IFC and single cell proteomics. Due to limited imaging channels in IFC this technology allows to follow only a limited number of proteins( up to 10) and is limited to the availability of suitable antibodies and dyes. In contrast to this, single cell proteomic approaches allow following a higher number of proteins. The advantage of IFC is that it allows following selected proteins. Therefore, in particular, with respect to quantitative biology and modeling signaling pathways IFC is undoubtedly the technology of choice. In this study apoptosis and anti-apoptosis pathways in single cells upon DR stimulation were analyzed using a stochastic model. Strikingly, the model shows that NF-κB activation is highly variable around 1 ng/ml CD95L, whereas it becomes relatively robust at a higher CD95L stimulation strength starting from 5 ng/ml. In contrast, caspase-3 dynamics are highly variable for all dose ranges. Heterogeneity in caspase-3 activation is directly linked to the chain configuration at the DISC. The two distinct types of stochastic behavior of caspase-3 and NF-κB activation at a dose range of 5 to 10 ng/ml, lead to the fact that both scenarios of life or death are possible within this concentration range. This in turn creates a dose range of ‘ambivalent' response. Hence, we concluded that the major source of ambivalent response upon 5 to 10 ng/ml CD95L stimulation is heterogeneity in DED chain configuration, which results from extrinsic noise. To more closely link our mathematical model of caspase-3 and NF-κB dynamics to experimental data, we introduced a parameter that determines the life/death decision in the cell and the threshold for apoptosis, the TOS/TOD ratio. Using this parameter could give a plausible explanation of the ultimate apoptotic response mechanism and its dose-dependent variability. In particular, the TOS/TOD ratio provides a clear explanation to the events occurring in the ambivalent response region between 5 and 10 ng/ml. In particular, even though both pathways are active upon stimulation above 5 ng/ml CD95L, cells can ‘fight’ apoptosis, resulting from the possibility of late activation of apoptotic downstream targets( TOS/TOD>rcrit). For dosages around 5 ng/ml CD95L the chain configuration may in rare cases induce a quick response in caspase-3( TOS/TOD<rcrit) and the cell might undergo apoptosis( Fig 5B). Interestingly, if the TOS/TOD curve were steeper( Fig 5B), the ambivalent response range would decrease, whereas a more flat TOS/TOD curve increases the dose range of ambivalent response. We validated this behavior experimentally by inhibiting IKK and caspases, which fully confirmed TOS/TOD model predictions. From our results we further conclude that on a single cell level, a life/death decision is very much dependent on the current state of the cell and the level of expression of anti-apoptotic vs. apoptotic proteins. For high stimulation strengths, the apoptotic decision prevails, whereas low stimulation strengths can also result in an anti-apoptotic response. The latter fits well to the recent findings by Roux et al. who have demonstrated that for low rates of DR-induced caspase-8 activity the cells might survive, which might be connected to the induction of the NF-κB pathway as we show in this study[12]. Here, we reason that this can be caused by dose/timing effects of two key signaling molecules related to life( NF-κB) and death( caspase-3). From our computational model we observed that activation of NF-κB is insensitive to stimulation dose variations above 5 ng/ml CD95L. This stems from the fact that NF-κB activation has a binary character owing to a time scale separation effect( signaling vs. gene expression time scale). Consequently, the stochastic gene expression related to NF-κB does not seem to be the main source of heterogeneity in the life/death decision. Rather, from our TOS/TOD ratio hypothesis, variations in the chain configuration and related caspase-3 fluctuations seem to be the dominant source of variability in the life/death response. Defining the optimal strength of cell death induction leading to the eradication of cancer cells is a key step in anti-tumor therapy. The dynamics of cell death induction is often neglected despite its very important role in defining the life/death outcome. Furthermore, as we can conclude from analyzing the dynamics of CD95 signaling, the cross-talk between apoptotic and non-apoptotic pathways has to be considered for predicting the outcome of DR stimulation. The future challenge will be to define the dynamics of cell death responses in cancer vs. normal cells supported by powerful computational modeling in order to develop efficient anti-tumor therapies.",
"role": "user"
},
{
"content": "Activation of death receptor ( DR ) family has been reported to activate both apoptotic as well as anti-apoptotic responses . Molecular mechanisms underlying the intricate details of this crosstalk have not been established yet . Here we show that these pathways are triggered simultaneously in one cell . Furthermore , using stochastic computational modeling we uncovered how an individual cell undergoes apoptosis , while other cells survive upon the same DR activation conditions . This was only possible by combination of computational modeling supported by experimental validation based on the state of the art single cell analysis . The latter included cutting edge technology of imaging flow cytometry , which combines microscopy and flow cytometry in one measurement circuit enabling quantitative analysis of endogenous cellular protein levels estimated from a large number of cells simultaneously . This allowed to shed the light on the question how a single cell possibly avoids apoptosis , which is a highly actual topic in the field of cancer research and development of efficient anti-cancer therapies .",
"role": "assistant"
}
] |
science.chemsum_single_document_summarization
|
science.chemsum_single_document_summarization.72335
|
[
{
"content": "Write an abstract for this chemistry paper.\n\nTitle:\nNew access to the synthesis of 1,1,4,4-tetracyanobuta-1,3-diene-based push-pull chromophores using tetracyanoethylene oxide via [3+2] cycloaddition-ring opening reactions\n\nPaper sections:\nIntroduction\n<p>The continuous generation of new organic push-pull chromophores has overwhelmed researchers from across the globe for about a past decade. Because of their immense applications in material fabrications, 1 designing soft molecular device-optoelectronics, 2 as fluorescence sensors, 3 in bio-imaging, 4 sensitizer in dye-sensitized solar cells, 5 piezochromic materials, 6 frequency-upconverted lasing, 7 and photorefractive organic materials, 8 etc. The exciting features of all the chromophores arise due to their encounter with the UV/Vis/NIRradiations. 9 Interaction of organic push-pull chromophores with light can be easily tuned upon modulating the design of the donor and acceptor groups. This is feasible primarily because of the control by the donor and acceptor groups over the intramolecular charge transfer (ICT) process. Even small structural variation in donor-and acceptor-parts of push-pull chromophores bring a complete transformation in the properties of molecules. 10 Cyano (CN) 2 group as an acceptor and amines as the donor has secured a prominent place owing to their strong push-pull nature. Synthetic methodology for exploring new acceptors and donors in the push-pull systems is possible with ease thanks to the well-established method pioneered by Diederich and co-workers based on the formal [2+2] cycloaddition−retroelectrocyclization (CA−RE) reaction between alkynes substituted with an electron-donating group (EDG) and electron-deficient olefin yielding EDG-substituted 1,1,4,4-tetracyanobuta-1,3-dienes (Figure 1a). 11 The click-type [2+2] CA−RE is a robust method for the preparation of nonplanar, πconjugated, donor-acceptor (D-A) chromophores that exhibit intense intramolecular chargetransfer (CT) bands with lower energy. 12 Some of them have found applications in devices for all-optical switching, 2a organic field-effect transistor, 13 light-emitting diodes, 14 holetransporting materials in solar cell, 15 and has also shown remarkable third-order nonlinear optical properties. 9b In general, the previous works reported on the synthesis of TCBDs based push-pull chromophores have mostly changed the donor moiety on the alkyne part, such as metal ylides, 16 thiophenes, 17 amines, 11 ferrocene and TTF, 18 azulene, 19 pyrroles, 20 carbazole, 21 ynamide, 22 and recently urea. 23 Whereas, in the case of the acceptor part, CN derivatives especially tetracyanoethene (TCNE) has been predominantly used as benchmark starting material. 11c Though another functional group such as carboxylic ester group has been used as acceptor but they act as a mild accepting unit and show less reactivity. 24 To expand the chemical space for TCBD based push-pull chromophores, it is imperative to look for more tools to synthesize TCBDs apart from the conventional [2+2] CA-RE reaction as the only choice.</p><p>We envisaged exploring tetracyanoethylene oxide (TCNEO, 1) as an alternative to TCNE because the oxirane ring would bring completely different reaction pathways. Further, it is also commercially available and easy to prepare on a large scale. 25 In 1965, it has been reported by Linn and Benson that TCNEO undergoes [3+2] cycloaddition (CA) with alkenes as well as alkynes to provide the corresponding cycloadducts of tetracyanotetrahydrofuran and tetracyanodihydrofuran (TCDHF) derivatives, respectively (Figure 1b). 26 This cycloaddition reaction occurs by the temperature (³100 o C) assisted formation of carbonyl ylide due to the cleavage of the C-C bond of the epoxide ring of TCNEO. 27 Recently, this chemistry has been successfully applied to fabricate graphene-TCNEO adduct and has been found to manipulate the electronic properties of graphene. 28 However, it should be noted that the previously reported TCNEO and alkynes having no EDG gave exclusively TCDHF derivatives which were found to be very stable (Figure 1b). 26 We hypothesized that incorporating the EDG group in the alkyne part would lead to subsequent ring-opening reactions as indicated in Figure 1c, thus possible to obtain some interesting new and useful products, for example, TCBD. With this hypothesis, we started to explore TCNEO as a potential precursor for the organic acceptor to undergo [3+2] CA reaction with electronrich alkynes such as N,N′-dimethylamino (DMA)-substituted phenylacetylenes and the results are presented herein.</p>\n\nResults and Discussion\n<p>Initially, we investigated the reactivity of TCNEO with mono-substituted alkyne such as 4ethynyl-N,N′-dimethylaniline 1 and explored its synthetic paths under different solvents and temperatures (Table 1). As we wish to check and identify whether the more useful TCBD 2 4 would form under this condition, an authentic sample was prepared according to the literature procedure and compared. 11b First, the reaction was conducted in CH2Cl2 at ambient condition (entries 1-3, Table 1), as indicated by the thin-layer chromatography (TLC) that the reaction occurred even without heating and showed not so clean with multiple spots (Figures S1-S3, Supporting Information (SI)). We were pleased to see that a trace amount of purple color spot appeared and matched with the authentic sample. This suggests that unlike the EDG-free alkyne which gives the stable [3+2] cycloadduct of TCDHF derivatives, 26 this adduct with EDG undergoes further reaction paths leading to a complex mixture of products. Further, to improve the yield of TCBD 2 instead of an equimolar (equiv) amount of TCNEO, 2 equiv was reacted and found significant product formation of TCBD up to 10% yield (entries 2-3, Table 1). Changing the solvent from non-polar to polar and also the high temperature resulted in a low yield of TCBD 2. It has been reported by Diederich et al. that additive such as LiClO4 assists similar reactions like [3+2] cycloaddition-rearrangement and sometimes different reactivity. 29,24b The addition of Lewis acid LiClO4 also did not improve the reaction and resulted in a more complex reaction mixture. Various attempts to improve the 1 2 TCNEO 5 yield of TCBD were failed including changing the strong EDG (-NMe2) into weaker EDG (-OMe) group such as 4-ethynyl anisole, though the TCNEO consumption occurs at high temperature and gave complex mixture. We infer that the over-reactions could be ascribed to the unsubstituted dicyanovinyl group in the 2-substituted 1,1,4,4-tetracyanobuta-1,3-dienes over 2,3-disubstituted 1,1,4,4-tetracyanobuta-1,3-dienes which is not stabilized by the EDG group. 30 Hence, we turned our attention to synthesize bis-DMA-substituted alkynes 3 and 5 derivatives to further investigate its effect on TCNEO and possible generation of TCBD chromophores (Scheme 1). While using compounds 3 and 5 as donor alkynes and two equiv of TCNEO, we had observed the almost complete transformation of alkynes into the corresponding TCBDs 4 and 6 with a yield of 90 and 95%, respectively without the use of any additives.</p><p>Scheme 1. Synthesis of 2,3-disubstituted TCBDs using TCNEO and bis-substituted alkynes via [3+2] CA followed by RO reactions.</p><p>The following observations were noticed upon screening for the best conditions.</p><p>Regardless of TCNEO equivalents, only the TCBD products were formed and no [3+2] cycloadduct of tetracyanodihydrofuran was observed by TLC. Also, we found that 2 equiv of TCNEO was the optimum amount for the formation of TCBD products. Further, increasing more equiv of TCNEO did not significantly improve the yield. While chlorinated solvent CH2Cl2 provided the best yield for 4, the slightly lower yield was obtained for 6 (85% yield), whereas the polar solvents such as CH3CN and N,N'-dimethylformamide provided a better yield of 95% for 6. Though the reaction can be performed without the inert atmosphere the presence of air leads to a ~20% decrease in the TCBD yield.</p><p>It was known that alkyne attached with TCBD tends to undergo a second CA-RE reaction at high temperature to provide the octacyano [4]dendralenes as a new class of cyanorich non-planar organic acceptor. 31 Compound 6 was subjected to further reaction with TCNEO to test whether the 6 having similar features would undergo additional [3+2] CA-RO reaction and provide the corresponding octacyano [4]dendralene i.e., 3,4-Bis(dicyanomethylidene)-2,5bis [4-(dimethylamino)phenyl]hexa-1,5-diene-1,1,6,6-tetracarbonitrile. However, both TLC and LC-MS have confirmed that such octacyano [4]dendralene did not form (Figures S4 and S5, SI). Nevertheless, a new blue-colored compound formed as major and its structural identity with different chemistry needs to be established with a greater detailed investigation which will be reported elsewhere.</p><p>The identity of the compounds was checked against the authentic sample of respective product formation in the reaction mixture using silica TLC prepared using TCNE, since all the TCBD products were already known through the showing triclinic lattice with P1 # space group (CCDC deposition number 56338). 11a The comparison table of these two polymorphs is provided in Table S1, SI. The protocol established in the previous study shows that TCNEO acts as 1,3-dipolar species at above 100 o C and the generated carbonyl ylide undergoes [3+2] CA reaction with EDG-free alkyne to give stable TCDHF product under relatively harsher condition (Figure 3a). 26,27 The mechanistic proposal for the present reaction is outlined in Figure 3b In conclusion, we demonstrated for the first time that EDG-substituted TCBDs can be synthesized from an unconventional method using TCNEO as the precursor instead of TCNE via [3+2] CA-RO reaction. Though mono-substituted alkynes gave very poor yield due to overreaction, di-substituted EDG-alkynes underwent smooth conversion under simpler conditions. Overall, the procedure is much simpler, greener, additive-free, and gives access to useful TCBDs in just a single step with excellent yields for di-substituted alkynes. The presence of EDG in the alkyne is the key to the successful synthesis of TCBDs which facilitated the RO reaction following the first step [3+2] CA reaction. A mechanism is proposed for the deoxygenation from the tetracyanodihydrofuran derivative is driven by the nucleophilic</p>\n\nExperimental section\n<p>General procedure. A solution of TCNEO (0.14 mmol) in an appropriate anhydrous degassed solvent (10 mL) was either cooled to 0 °C or at 25 °C, treated dropwise EDG-alkyne 3 or 5 (0.07 mmol), in a degassed appropriate solvent (10 mL) stirred at the same temperature for completion of reaction time upon monitoring the reaction by TLC (SiO2). The solution color changes occur approximately after 3 h. After evaporation of the solvent, CH2Cl2 and water were mixed and extracted with CH2Cl2 (3× 10 mL). The combined organic layers were washed with brine, dried over anhydrous Na2SO4, and evaporated. The crude product was columned using silica (hexane/CH2Cl2 7:3) and recrystallized by slow diffusion of hexane into CH2Cl2 solution to afford the pure product.</p>\n\nConflicts of interest\n<p>The authors declare no competing financial interest. *Corresponding Author Email: [email protected]. (medium), and w (weak). Single-crystal X-ray diffraction data were collected using a Rigaku</p>\n\nTable of Contents\n<p>XtaLABmini Xray diffractometer equipped with a Mercury charge-coupled device detector with graphite monochromatic Mo Kα radiation (λ = 0.71073 Å) at 100.0 (2) K using ω scans.</p><p>The data were reduced using CrysAlisPro 1.171.38.46, and the space group determination was done using Olex2.37 The crystal structures were solved by using ShelXT38 and were refined using ShelXL39 through Olex2 suite. All of the hydrogen atoms were geometrically fixed and refined using the riding model. Absorption correction was done by a multiscan method. All of the packing and interaction diagrams have been generated using Mercury. Liquid chromatography (LC) was performed on a Waters ACQUITY UPLC M-Class LC instrument The crystal structure obtained in the previous study using TCNE is called here as polymorph I 1a and in this study using TCNEO is called polymorph II.</p>",
"role": "user"
},
{
"content": "Herein we report a new way to access the synthesis of established invaluable pushpull chromophores based on 1,1,4,4-tetracyanobuta-1,3-dienes (TCBDs) using tetracyanoethylene oxide (TCNEO) upon reaction with alkynes substituted with an electrondonating group (EDG) via [3+2] cycloaddition (CA) followed by ring-opening (RO) reactions.Further, we uncovered that the facile [3+2] CA-RO reaction under simpler reaction condition is possible due to the presence of EDG group, otherwise, even the formation of [3+2] cycloadduct without EDG requires harsher condition and does not lead to TCBD as reported earlier in 1965 by Linn and Benson.",
"role": "assistant"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.