Datasets:

---

kejian

/

SciRIFF-4096-0214-v2

like 0

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nAfrican languages are numerous, complex and low-resourced. The datasets required for machine translation are difficult to discover, and existing research is hard to reproduce. Minimal attention has been given to machine translation for African languages so there is scant research regarding the problems that arise when using machine translation techniques. To begin addressing these problems, we trained models to translate English to five of the official South African languages (Afrikaans, isiZulu, Northern Sotho, Setswana, Xitsonga), making use of modern neural machine translation techniques. The results obtained show the promise of using neural machine translation techniques for African languages. By providing reproducible publicly-available data, code and results, this research aims to provide a starting point for other researchers in African machine translation to compare to and build upon.\n\nCited Works Summary:\n[1]: Translation is an indispensable process for socioeconomic and cultural development in a multilingual society. The use of translation tools such as translation memories and machine translation systems can be beneficial in supporting the human translator. Unfortunately, the availability of these tools is limited for resource-scarce languages. In this paper, we introduce the Autshumato Integrated Translation Environment that facilitates a comprehensive set of translation tools, including machine translation and translation memory. The Autshumato Integrated Translation Environment is specifically developed for translation between the official South African languages, but it is in essence languageindependent and can therefore be used to translate between any language pair.", "role": "user" }, { "content": "trained Transformer models for English to Setswana on the parallel Autshumato dataset [1] . Data was not cleaned nor was any additional data used. This is the only study reviewed that released datasets and code. performed statistical phrase-based translation for English to Setswana translation. This research used linguistically-motivated pre- and post-processing of the corpus in order to improve the translations. The system was trained on the Autshumato dataset and also used an additional monolingual dataset.", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nOnline learning with limited information feedback (bandit) tries to solve the problem where an online learner receives partial feedback information from the environment in the course of learning. Under this setting, [8] extended Zinkevich's classical Online Gradient Descent (OGD) algorithm [29] by proposing the Online Gradient Descent with Expected Gradient (OGDEG) algorithm. Specifically, it uses a simple trick to approximate the gradient of the loss function @math by evaluating it at a single point and bounds the expected regret as @math [8], where the number of rounds is @math . Meanwhile, past research efforts have shown that compared with the first-order algorithms, second-order online learning algorithms such as Online Newton Step (ONS) [11] can significantly accelerate the convergence rate of traditional online learning algorithms. Motivated by this, this paper aims to exploit the second-order information to speed up the convergence of the OGDEG algorithm. In particular, we extend the ONS algorithm with the trick of expected gradient and develop a novel second-order online learning algorithm, i.e., Online Newton Step with Expected Gradient (ONSEG). Theoretically, we show that the proposed ONSEG algorithm significantly reduces the expected regret of OGDEG algorithm from @math to @math in the bandit feedback scenario. Empirically, we further demonstrate the advantages of the proposed algorithm on multiple real-world datasets.\n\nCited Works Summary:\n[1]: Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially generated convex loss functions, while only observing the value of each function at a single point. In some cases, the minimax regret of these problems is known to be strictly worse than the minimax regret in the corresponding full information setting. We introduce the multi-point bandit setting, in which the player can query each loss function at multiple points. When the player is allowed to query each function at two points, we prove regret bounds that closely resemble bounds for the full information case. This suggests that knowing the value of each loss function at two points is almost as useful as knowing the value of each function everywhere. When the player is allowed to query each function at d+1 points (d being the dimension of the space), we prove regret bounds that are exactly equivalent to full information bounds for smooth functions.\n\n[2]: \n\n[3]: We introduce the general and powerful scheme of predicting information re-use in optimization algorithms. This allows us to devise a computationally efficient algorithm for bandit convex optimization with new state-of-the-art guarantees for both Lipschitz loss functions and loss functions with Lipschitz gradients. This is the first algorithm admitting both a polynomial time complexity and a regret that is polynomial in the dimension of the action space that improves upon the original regret bound for Lipschitz loss functions, achieving a regret of @math . Our algorithm further improves upon the best existing polynomial-in-dimension bound (both computationally and in terms of regret) for loss functions with Lipschitz gradients, achieving a regret of @math .\n\n[4]: We consider the adversarial convex bandit problem and we build the first @math -time algorithm with @math -regret for this problem. To do so we introduce three new ideas in the derivative-free optimization literature: (i) kernel methods, (ii) a generalization of Bernoulli convolutions, and (iii) a new annealing schedule for exponential weights (with increasing learning rate). The basic version of our algorithm achieves @math -regret, and we show that a simple variant of this algorithm can be run in @math -time per step at the cost of an additional @math factor in the regret. These results improve upon the @math -regret and @math -time result of the first two authors, and the @math -regret and @math -time result of Hazan and Li. Furthermore we conjecture that another variant of the algorithm could achieve @math -regret, and moreover that this regret is unimprovable (the current best lower bound being @math and it is achieved with linear functions). For the simpler situation of zeroth order stochastic convex optimization this corresponds to the conjecture that the optimal query complexity is of order @math .\n\n[5]: The problem of stochastic convex optimization with bandit feedback (in the learning community) or without knowledge of gradients (in the optimization community) has received much attention in recent years, in the form of algorithms and performance upper bounds. However, much less is known about the inherent complexity of these problems, and there are few lower bounds in the literature, especially for nonlinear functions. In this paper, we investigate the attainable error regret in the bandit and derivative-free settings, as a function of the dimension d and the available number of queries T . We provide a precise characterization of the attainable performance for strongly-convex and smooth functions, which also imply a non-trivial lower bound for more general problems. Moreover, we prove that in both the bandit and derivative-free setting, the required number of queries must scale at least quadratically with the dimension. Finally, we show that on the natural class of quadratic functions, it is possible to obtain a \"O(1=T ) error rate in terms of T , under mild assumptions, even without having access to gradients. To the best of our knowledge, this is the rst such rate in a derivative-free stochastic setting, and holds despite previous\n\n[6]: Bandit Convex Optimization (BCO) is a fundamental framework for decision making under uncertainty, which generalizes many problems from the realm of online and statistical learning. While the special case of linear cost functions is well understood, a gap on the attainable regret for BCO with nonlinear losses remains an important open question. In this paper we take a step towards understanding the best attainable regret bounds for BCO: we give an efficient and near-optimal regret algorithm for BCO with strongly-convex and smooth loss functions. In contrast to previous works on BCO that use time invariant exploration schemes, our method employs an exploration scheme that shrinks with time.\n\n[7]: The study of online convex optimization in the bandit setting was initiated by Kleinberg (2004) and (2005). Such a setting models a decision maker that has to make decisions in the face of adversarially chosen convex loss functions. Moreover, the only information the decision maker receives are the losses. The identities of the loss functions themselves are not revealed. In this setting, we reduce the gap between the best known lower and upper bounds for the class of smooth convex functions, i.e. convex functions with a Lipschitz continuous gradient. Building upon existing work on selfconcordant regularizers and one-point gradient estimation, we give the first algorithm whose expected regret is O(T ), ignoring constant and logarithmic factors.", "role": "user" }, { "content": "For some specifical classes of nonlinear convex losses, several methods have been proposed [2]1 [4] [3] [2] [2]3 . Under the assumption of strongly convex loss, [1] attained an upper bound of @math . The follow-up work of Saha [2]1 showed that for convex and smooth loss functions, one can run FTRL with a self-concordant barrier as regularization and sample around the Dikin ellipsoid to attain regret bound of @math . In a recent paper, Hazan and Levy investigated the bandit convex optimization setting by assuming that the adversary is limited to inflicting strongly convex and smooth loss functions and the player may choose points from a constrained set. In this setting, they devised an algorithm that achieves a regret bound of @math . While a recent paper by [5] shows that the lower bound of regret has to be @math even with the strongly convex and smooth assumptions.", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nOxaprozin versus diclofenac in NSAID-refractory periarthritis pain of the shoulder . OBJECTIVE To evaluate the efficacy and safety of oxaprozin in comparison with diclofenac in patients with periarthritis pain of the shoulder previously unsuccessfully treated with nonsteroidal anti-inflammatory drugs other than diclofenac and oxaprozin . METHODS In this open , multicentre , randomised , controlled study , eligible patients with periarthritis of the shoulder were randomised to receive either oxaprozin 1200 mg once daily ( n = 49 ) or diclofenac 50 mg three times daily ( n = 47 ) . The treatment period was 15 +/- 1 days . The study was planned on a hypothesis of equivalence between the two study drugs . The primary study endpoint was the change from baseline at day 15 in the patient-assessed shoulder pain score . Secondary efficacy variables included investigator-assessed shoulder function , patient-assessed quality of life on the Short-Form-36 ( SF-36 ) Acute Health Survey and both patients ' and investigators ' overall assessment of efficacy . RESULTS At day 15 , the mean changes in shoulder pain score from baseline in the oxaprozin and diclofenac groups were -5.85 +/- SD 4.62 and -5.54 +/- SD 4.41 , respectively . The difference between the two groups was not statistically significant , confirming the hypothesis of the study that oxaprozin is as effective as diclofenac . Investigator-assessed shoulder function improved in both groups but more so in the oxaprozin group ( p = 0.028 at day 15 ) . Quality of life as measured by SF-36 total score was also improved in both treatment groups , with a trend toward greater improvement in the oxaprozin group . Furthermore , a significantly more favourable effect on the SF-36 'mental health ' item was observed in oxaprozin compared with diclofenac-treated patients at day 15 ( p = 0.0202 ) . As assessed by investigators , the overall efficacy of oxaprozin was superior to that for diclofenac at visit 3 ( 8 +/- 1 days ) ( p = 0.0067 ) . Patients also assessed the overall efficacy of oxaprozin as superior to that of diclofenac at visits 3 ( 8 +/- 1 days ) ( p = 0.0235 ) and 4 ( 15 +/- 1 days ) ( p = 0.0272 ) . Only six adverse events , all of which were mild or moderate in intensity and occurred in four diclofenac recipients , were observed in the study . CONCLUSIONS As expected , once-daily oxaprozin proved to be as effective as diclofenac three times daily in reducing the primary efficacy variable of patient-assessed shoulder pain score in patients with periarthritis of the shoulder refractory to previous treatments with other NSAIDs . Oxaprozin was shown to be superior to diclofenac in improving shoulder function and was considered by investigators and patients to have greater overall efficacy than diclofenac . In addition , oxaprozin showed a trend toward superior results in improving patients ' quality of life compared with diclofenac . A trend towards better tolerability results for oxaprozin compared with diclofenac was also noted .", "role": "user" }, { "content": "{\"Intervention\": [\"diclofenac\", \"oxaprozin\", \"Oxaprozin\"], \"Outcome\": [\"Investigator-assessed shoulder function\", \"Quality of life as measured by SF-36 total score\", \"shoulder pain score\", \"patient-assessed shoulder pain score\", \"shoulder function\", \"tolerability results\", \"adverse events\", \"effect\", \"difference\", \"SF-36 \\u0027mental health \\u0027 item\", \"quality of life\", \"change from baseline at day 15 in the patient-assessed shoulder pain score\", \"efficacy\"], \"Participant\": [\"periarthritis\", \"SF-36\", \"eligible patients with periarthritis of the shoulder\", \"Short-Form-36\", \"shoulder pain\"]}", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nInsummary,whereasisochronicexpressionofEWS-Pea3promotedtheestablishmentofproprioceptiveafferentprojectionsintotheventralspinalcord,precociousexpressionofthesameETSsignalingfactorinDRGneuronsinterferedwithestablishmentofprojectionsintothespinalcordaswellastoperipheraltargets.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: Does heat prevent COVID-19? No, Absolutely not\n\nResearch Abstract:\nAirborne transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) via air-conditioning systems poses a significant threat for the continued escalation of the current coronavirus disease (COVID-19) pandemic.\nConsidering that SARS-CoV-2 cannot tolerate temperatures above 70 °C, here we designed and fabricated efficient air disinfection systems based on heated nickel (Ni) foam to catch and kill SARS-CoV-2.\nVirus test results revealed that 99.8% of the aerosolized SARS-CoV-2 was caught and killed by a single pass through a Ni-foam-based filter when heated up to 200 °C.\nAdditionally, the same filter was also used to catch and kill 99.9% of Bacillus anthracis, an airborne spore.\nThis study paves the way for preventing transmission of SARS-CoV-2 and other highly infectious airborne agents in closed environments.\nOne Sentence Summary Heated Ni-foam filters are capable of effectively catching and killing airborne SARS-CoV-2 and Bacillus anthracis spores.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nFavipiravir is an investigational antiviral drug that is being tested for use against the novel coronavirus disease, COVID-19. No information is available on the use of favipiravir during breastfeeding or its excretion into breastmilk. Favipiravir is a small molecule that is about 60% protein bound in plasma, so it would be expected to appear in breastmilk and be absorbed by the infant, probably in small amounts. In clinical trials, favipiravir has been well tolerated, but has caused liver enzyme abnormalities, gastrointestinal symptoms, and serum uric acid elevations.[1-3] If favipiravir is used in a nursing mother, these parameters should be monitored in the breastfed infant.", "role": "user" }, { "content": "[\"Treatment\"]", "role": "assistant" } ]

[ { "content": "Evaluate the following claim concerning COVID-19 using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"verdict\": Decide if the abstract supports or contradicts the claim.\n- \"evidence\": List sentences from the abstract that justify your decision.\n\nClaim: Functional myeloid-derived suppressor cells expand in blood but also airways of covid-19 patients and predict disease severity\n\nResearch Abstract:\nThe immunopathology of COVID-19 remains enigmatic, exhibiting immunodysregulation and T cell lymphopenia.\nMonocytic myeloid-derived suppressor cells (M-MDSC) are T cell suppressors that expand in inflammatory conditions, but their role in acute respiratory infections remains unclear.\nWe studied blood and airways of COVID-19 patients across disease severity at multiple timepoints.\nM-MDSC frequencies were elevated in blood but not in nasopharyngeal or endotracheal aspirates of COVID-19 patients compared to controls.\nM-MDSCs isolated from COVID-19 patients suppressed T cell proliferation and IFNg production partly via an arginase-1 (Arg-1) dependent mechanism.\nFurthermore, patients showed increased Arg-1 and IL-6 plasma levels.\nCOVID-19 patients had fewer T cells, and displayed downregulated expression of the CD3ζ chain.\nOrdinal regression showed that early M-MDSC frequency predicted subsequent disease severity.\nIn conclusion, M-MDSCs expand in blood of COVID-19 patients, suppress T cells and strongly associate with disease severity, suggesting a role for M-MDSCs in the dysregulated COVID-19 immune response.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"In conclusion, M-MDSCs expand in blood of COVID-19 patients, suppress T cells and strongly associate with disease severity, suggesting a role for M-MDSCs in the dysregulated COVID-19 immune response.\"]}", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nFace restoration from low resolution and noise is important for applications of face analysis recognition. However, most existing face restoration models omit the multiple scale issues in face restoration problem, which is still not well-solved in research area. In this paper, we propose a Sequential Gating Ensemble Network (SGEN) for multi-scale noise robust face restoration issue. To endow the network with multi-scale representation ability, we first employ the principle of ensemble learning for SGEN network architecture designing. The SGEN aggregates multi-level base-encoders and base-decoders into the network, which enables the network to contain multiple scales of receptive field. Instead of combining these base-en decoders directly with non-sequential operations, the SGEN takes base-en decoders from different levels as sequential data. Specifically, it is visualized that SGEN learns to sequentially extract high level information from base-encoders in bottom-up manner and restore low level information from base-decoders in top-down manner. Besides, we propose to realize bottom-up and top-down information combination and selection with Sequential Gating Unit (SGU). The SGU sequentially takes information from two different levels as inputs and decides the output based on one active input. Experiment results on benchmark dataset demonstrate that our SGEN is more effective at multi-scale human face restoration with more image details and less noise than state-of-the-art image restoration models. Further utilizing adversarial training scheme, SGEN also produces more visually preferred results than other models under subjective evaluation.\n\nCited Works Summary:\n[1]: In video surveillance, the faces of interest are often of small size. Image resolution is an important factor affecting face recognition by human and computer. In this paper, we propose a new face hallucination method using eigentransformation. Different from most of the proposed methods based on probabilistic models, this method views hallucination as a transformation between different image styles. We use Principal Component Analysis (PCA) to fit the input face image as a linear combination of the low-resolution face images in the training set. The high-resolution image is rendered by replacing the low-resolution training images with high-resolution ones, while retaining the same combination coefficients. Experiments show that the hallucinated face images are not only very helpful for recognition by humans, but also make the automatic recognition procedure easier, since they emphasize the face difference by adding more high-frequency details.\n\n[2]: Face image super-resolution has attracted much attention in recent years. Many algorithms have been proposed. Among them, sparse representation (SR)-based face image super-resolution approaches are able to achieve competitive performance. However, these SR-based approaches only perform well under the condition that the input is noiseless or has small noise. When the input is corrupted by large noise, the reconstruction weights (or coefficients) of the input low-resolution (LR) patches using SR-based approaches will be seriously unstable, thus leading to poor reconstruction results. To this end, in this paper, we propose a novel SR-based face image super-resolution approach that incorporates smooth priors to enforce similar training patches having similar sparse coding coefficients. Specifically, we introduce the fused least absolute shrinkage and selection operator-based smooth constraint and locality-based smooth constraint to the least squares representation-based patch representation in order to obtain stable reconstruction weights, especially when the noise level of the input LR image is high. Experiments are carried out on the benchmark FEI face database and CMU+MIT face database. Visual and quantitative comparisons show that the proposed face image super-resolution method yields superior reconstruction results when the input LR face image is contaminated by strong noise.\n\n[3]: \n\n[4]: Sparse representation-based face hallucination approaches proposed so far use fixed l1 norm penalty to capture the sparse nature of face images, and thus hardly adapt readily to the statistical variability of underlying images. Additionally, they ignore the influence of spatial distances between the test image and training basis images on optimal reconstruction coefficients. Consequently, they cannot offer a satisfactory performance in practical face hallucination applications. In this paper, we propose a weighted adaptive sparse regularization (WASR) method to promote accuracy, stability and robustness for face hallucination reconstruction, in which a distance-inducing weighted lq norm penalty is imposed on the solution. With the adjustment to shrinkage parameter q , the weighted lq penalty function enables elastic description ability in the sparse domain, leading to more conservative sparsity in an ascending order of q . In particular, WASR with an optimal q > 1 can reasonably represent the less sparse nature of noisy images and thus remarkably boosts noise robust performance in face hallucination. Various experimental results on standard face database as well as real-world images show that our proposed method outperforms state-of-the-art methods in terms of both objective metrics and visual quality.", "role": "user" }, { "content": "To overcome the drawback of global face-based restoration methods, local patch-based restoration methods decompose face image into small patches, which can capture more facial details. Local patch-based restoration methods assume that LR and HR face patch manifolds are locally isometric. Therefore, once obtaining the representation of the input LR patch with the LR training patches, we can reconstruct the target HR patch by transforming the reconstruction weights to corresponding HR training patch. The work in [1] proposed a least squares representation (LSR) framework that restores images using all the training patches, which incorporates more face priors. Due to the un-stability of LSR, [4] introduced a weighted sparse representation (SR) with sparsity constraint for face super-resolution. However, one main drawback of SR based methods is its sensitivity to noise. Accordingly, [3] [2] introduced to reconstruct noise corrupted LR images with weighted local patch, namely locality-constrained representation (LcR).", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nCurrent state-of-the-art models for sentiment analysis make use of word order either explicitly by pre-training on a language modeling objective or implicitly by using recurrent neural networks (RNNs) or convolutional networks (CNNs). This is a problem for cross-lingual models that use bilingual embeddings as features, as the difference in word order between source and target languages is not resolved. In this work, we explore reordering as a pre-processing step for sentence-level cross-lingual sentiment classification with two language combinations (English-Spanish, English-Catalan). We find that while reordering helps both models, CNNS are more sensitive to local reorderings, while global reordering benefits RNNs.\n\nCited Works Summary:\n[1]: Scarcity of annotated corpora for many languages is a bottleneck for training finegrained sentiment analysis models that can tag aspects and subjective phrases. We propose to exploit statistical machine translation to alleviate the need for training data by projecting annotated data in a source language to a target language such that a supervised fine-grained sentiment analysis system can be trained. To avoid a negative influence of poor-quality translations, we propose a filtering approach based on machine translation quality estimation measures to select only high-quality sentence pairs for projection. We evaluate on the language pair German English on a corpus of product reviews annotated for both languages and compare to in-target-language training. Projection without any filtering leads to 23 F1 in the task of detecting aspect phrases, compared to 41 F1 for in-target-language training. Our approach obtains up to 47 F1. Further, we show that the detection of subjective phrases is competitive to in-target-language training without filtering.\n\n[2]: Semantic word spaces have been very useful but cannot express the meaning of longer phrases in a principled way. Further progress towards understanding compositionality in tasks such as sentiment detection requires richer supervised training and evaluation resources and more powerful models of composition. To remedy this, we introduce a Sentiment Treebank. It includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality. To address them, we introduce the Recursive Neural Tensor Network. When trained on the new treebank, this model outperforms all previous methods on several metrics. It pushes the state of the art in single sentence positive negative classification from 80 up to 85.4 . The accuracy of predicting fine-grained sentiment labels for all phrases reaches 80.7 , an improvement of 9.7 over bag of features baselines. Lastly, it is the only model that can accurately capture the effects of negation and its scope at various tree levels for both positive and negative phrases.\n\n[3]: Sentiment analysis is the natural language processing task dealing with sentiment detection and classification from texts. In recent years, due to the growth in the quantity and fast spreading of user-generated contents online and the impact such information has on events, people and companies worldwide, this task has been approached in an important body of research in the field. Despite different methods having been proposed for distinct types of text, the research community has concentrated less on developing methods for languages other than English. In the above-mentioned context, the present work studies the possibility to employ machine translation systems and supervised methods to build models able to detect and classify sentiment in languages for which less no resources are available for this task when compared to English, stressing upon the impact of translation quality on the sentiment classification performance. Our extensive evaluation scenarios show that machine translation systems are approaching a good level of maturity and that they can, in combination to appropriate machine learning algorithms and carefully chosen features, be used to build sentiment analysis systems that can obtain comparable performances to the one obtained for English.\n\n[4]: Although research in other languages is increasing, much of the work in subjectivity analysis has been applied to English data, mainly due to the large body of electronic resources and tools that are available for this language. In this paper, we propose and evaluate methods that can be employed to transfer a repository of subjectivity resources across languages. Specifically, we attempt to leverage on the resources available for English and, by employing machine translation, generate resources for subjectivity analysis in other languages. Through comparative evaluations on two different languages (Romanian and Spanish), we show that automatic translation is a viable alternative for the construction of resources and tools for subjectivity analysis in a new target language.", "role": "user" }, { "content": "Cross-lingual approaches to sentiment analysis attempt to leverage available sentiment annotations in a high-resource language for target languages which lack annotated data. This is especially important when the cost of annotating a high-quality sentiment dataset, such as the Stanford Sentiment Treebank [2] , can be prohibitive (215,154 phrases, each annotated by 3 annotators, at 10 cents an annotation would be 64,546€!). Therefore, it is preferable to make use of those datasets that already exist. Although most approaches to cross-lingual sentiment analysis rely on Machine Translation [4] [3] [1] , this requires large amounts of parallel data, making it less helpful for under-resourced languages.", "role": "assistant" } ]

[ { "content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nSynthesis of poly(disulfide)s with narrow molecular weight distributions <i>via</i> lactone ring-opening polymerization\n\nContent Extracts:\nIntroduction\n<p>The disulde bond is oen regarded as a dynamic covalent bond with conditional reactivity or meta-stability. 1 It can sufficiently maintain molecular integrity, being a reasonably strong bond with typical bond dissociation energies of 60 kcal mol À1 . On the other hand, it can be easily cleaved and exchanged with other bonds in the presence of physical (i.e. light, 2 heat, 3 mechanical force, 4 etc.) or chemical (i.e. radicals, 5 nucleophiles, 6 etc.) stimuli overcoming the dissociation energy barrier. In particular, the reversibility of oxidative coupling and reductive degradation between a disulde and two thiols is a key factor in the structural integrity and controlled reactivity of proteins. 7,8 The intriguing properties of disuldes have been popularly studied for application in the elds of polymer and materials science. Disulde acts as a cross-linker between polymeric chains to improve the stiffness of polymeric networks, as shown in vulcanized rubber 9 or disulde-based hydrogels. 10 Various pharmaceuticals can be conjugated to polymers or proteins via disulde bonds for drug delivery. 11, 12 When appropriate signals are applied to the disulde-based materials in a spatiotemporal manner, the disulde bonds degrade either to disintegrate the polymer network structure or to release the active pharmaceuticals from the delivery carrier. UV-responsive self-healing gels, 13 nanogels, 14 and antibody-drug conjugates 12 responding to high glutathione concentrations around cancerous tissues or in the cytosol are all on the frontier of materials and pharmaceutical sciences.</p><p>Notwithstanding the recent rapid progress in polymer science, the synthesis of ne polymers containing disulde backbones is very limited, probably due to the vulnerability of disulde bonds under most polymerization conditions. Oxidative coupling of disulydryl monomers, 15 condensation polymerization of disulde-pre-containing monomers 16 and copolymerization of dihalide-containing monomers with sodium disulde 17 are representative strategies for the synthesis of poly(disulde)s. However, the aforementioned step-growth polymerization methods inevitably lead to polymers only with a broad distribution of molecular weights (polydispersity index (PDI) > 2). Chain-growth polymerization has been attempted to obtain poly(disulde)s with more narrow molecular weight distributions (MWDs), but only with limited improvement. For instance, ring-opening polymerization of strained disulde monomers via thiol-disulde exchange oen produced mixtures of linear and cyclic polymers and even catenanes with broad MWDs. [18][19][20][21][22] The formation of these complex product mixtures may be attributed to the limited selectivity of the thiol-disulde exchange between disuldes in the monomer and the polymer backbone. Various reaction conditions were examined to overcome this problem and obtain linear polymers as a major product, but undesired cyclic oligomers were still present with PDI > 1.4. 22 Ring-opening metathesis polymerization (ROMP), which is orthogonal with the thiol-disulde exchange reaction, was also applied for the synthesis of poly(disulde)s. However, undesirable interactions between the ruthenium catalyst and disuldes caused not only a large PDI > 1.5 but also a failure in homopolymerization of the disulde monomer. 23 From the previous results, we inferred that it is critical to choose polymerization conditions where unwanted thiol-disulde exchange and catalyst-disulde interactions are inhibited for obtaining ne poly(disulde)s with narrow MWDs.</p>\n\nResults and discussion\n<p>In this research work, we selected lactone polymerization for the synthesis of poly(disulde)s since numerous catalysts for the controlled polymerization of poly(lactone)s have already been established. 24,25 As for the monomer, we designed 1,4,5oxadithiepan-2-one (OTP), an analogue of 3-caprolactone (3CL), where two of the ve methylene groups are replaced with a disulde. We reasoned that the 7-membered ring structure may provide sufficient ring strain for polymerization (Scheme 1). OTP was prepared from the catalytic intramolecular oxidation 26 of an a,u-disulydryl ester formed from 2-mercaptoethanol and 2-thioglycolic acid (see the ESI †). We have screened various catalysts ranging from bases to Lewis and Brønsted acids for the OTP polymerization, but the disulde bonds were vulnerable under most of the reaction conditions, as the catalysts induced undesirable nucleophilic attack on disuldes by enhancing the electrophilicity of disuldes or nucleophilicity of nucleophiles. Among them, diphenylphosphate (DPP), a Brønsted acid with a pK a of 3.88 in DMSO, 27 showed remarkable tolerance to disuldes but strong catalytic activity for the polymerization of OTP. Therefore, we used DPP as the catalyst in all the polymerization reactions below.</p><p>The polymerization of OTP was carried out with catalytic DPP and benzyl alcohol (BnOH) as the initiator (I) at various [OTP]/[I] ratios (from [OTP]/[I] ¼ 20 to 180). The general procedure for the polymerization is described in detail in the ESI. † We chose chloroform as the reaction solvent due to the solubility issue of the OTP polymer with a high sulfur content of approximately 43% (w/w). The MWDs were examined by size exclusion chromatography (SEC) (Table 1 and S1, ESI †). Surprisingly, the polymers (P1-P5) were found to have very narrow MWDs (PDI < 1.1) throughout the wide range of the monomer (M) to initiator ratio. The PDI values of poly(OTP)s are even smaller than those of poly(3CL) or poly(d-valerolactone) in previous reports where the same catalyst was utilized. 25 M n values from the SEC analysis were in reasonable agreement with the target M n . Additionally, we could conrm the preservation of a well-oriented head-to-tail backbone without disulde exchange and delity of the terminal benzyl group in poly(OTP)s by MALDI-MS and 1 H NMR study (Fig. S7 and S13-S17, ESI †).</p><p>To widen the applicability of our method, we investigated various alcohols for initiation. Propargyl alcohol also produced poly(OTP) (P6) with desired molecular weights and a narrow PDI (Fig. S2, ESI †), which gives access to future end group functionalization via the alkyne-azide click reaction. 28 Next, when we utilized 2-propanol as the initiator, we could still obtain a narrow MWD (P7, PDI ¼ 1.05) (Fig. S3, ESI †) although secondary alcohols are generally recognized to be unsuitable for rapid initiation. 29 We assumed that the initiation rate of OTP, even by secondary alcohols, is signicantly faster than the propagation rate, thus leading to the low PDI. Furthermore, umethoxy-capped polyethylene oxide (mPEO) was also used as a macroinitiator for the synthesis of a block copolymer. The polymerization resulted in mPEO-b-poly(OTP) with narrow MWDs (P8 and P9) (Fig. S4 and S5, ESI †). These well-dened amphiphilic block copolymers with narrow MWDs would We then examined whether OTP is polymerized in a living/ controlled manner. The polymerization kinetics of poly(OTP) were measured by 1 H NMR and SEC (Fig. 1). We could observe a linear relationship between M n versus the conversion ratio and a decrease in the PDI (M w /M n ) as the reaction progressed. Also, by plotting Àln([M]/[M] 0 ) versus reaction time, we could obtain a strict linear relationship, which suggests that the polymerization rate is proportional to the OTP concentration in the rst order.</p><p>We also performed one-pot post-polymerization with additional OTP feed to prove the livingness of the polymeric end group. First, we conducted polymerization at a [M]/[I] ratio of 25 for 24 h, where the full conversion of the monomer was conrmed by 1 H NMR. The solution was further stirred without quenching for an additional 24 h. There was still no sign of backbiting or peak broadening in the SEC chromatogram even aer 24 h from monomer depletion (Fig. 2a, black curve). Then, we added the second monomer solution feed ([M]/[I] ¼ 25) to the unquenched polymer solution and stirred the mixture for an additional 48 h. We conrmed the second full consumption of the monomer by 1 H NMR. The SEC chromatogram clearly showed the peak shi with an almost 2-fold increase of M n from 3.63 kDa to 6.56 kDa, as well as the maintenance of the low PDI < 1.05 (Fig. 2a, red curve), which implies that the chain end of poly(OTP) is still \"living\".</p><p>The results above encouraged us to attempt a successive ring-opening polymerization of 3CL and OTP in a one-pot manner for the preparation of poly(3CL)-b-poly(OTP). Aer the rst polymerization of the poly(3CL) block at a [3CL]/[I] ratio of 30 for 24 h, where the full conversion of 3CL was conrmed by 1 H NMR, the second OTP monomer was injected rapidly at an</p><p>[OTP]/[I] ratio of 30. Aer the second polymerization proceeded for 48 h, we could observe that the SEC peak had shied from the initial peak of poly(3CL) and that M n showed an increase of 4.5 kDa (Fig. 2b). The PDI value was also maintained below 1.09 during the successive one-pot polymerization. In addition, the peak corresponding to the methylene proton at the chain end (-CH 2 OH) of poly(3CL) at 3.65 ppm (ref. 25) shied to 4.15 ppm corresponding to those next to ester (-CH 2 OOC-) in the 1 H NMR spectrum aer the polymerization (see the ESI †), implying the successful one-pot post-polymerization with OTP from poly(3CL).</p><p>The disulde backbone of poly(OTP) is expected to have degradability responding to various chemical and physical stimuli. As a representative chemical stimulus to trigger the disulde metathesis in poly(OTP), we chose D,L-dithiothreitol (DTT), a reagent well known to induce thiol-disulde exchange reactions by forming a stable intramolecular cyclic disulde while reducing other disulde substrates. 30 P3 (M n ¼ 11.2 kDa) was dissolved in chloroform and DTT was added to the solution at a molar ratio of 1 : 1 relative to the disulde content of P3. Aer incubation at ambient temperature for 24 h, the backbone of poly(OTP) was almost completely degraded to oligomers, as shown in the SEC chromatogram in Fig. 3a. Poly(OTP) showed the characteristic degradability of disulde polymers responding to the reducing conditions. Then, we also examined the backbone degradation of poly(OTP) by UV irradiation, which is known to facilitate disulde metathesis by generating thiyl radicals via the homolytic cleavage of disulde. 2 Aer irradiation with UV light (l max ¼ 357 nm, 5 W cm À2 ), the initial peak of P2 (M n ¼ 5.71 kDa) in the SEC chromatogram gradually decreased in intensity with an increase in retention time, while small peaks appeared with increasing intensity in the oligomer region (Fig. 3b). The results clearly exhibit the UVresponsive degradability of the poly(OTP) backbone. In addition, the disulde bonds in the poly(OTP) backbone are quite stable even at 100 C, where the broadening of the MWD was observed probably due to transesterication, but start to show exchange reactions to produce a mixture of head-to-head, headto-tail and tail-to-tail disulde bonds with larger broadening of the MWD at 120 C (Fig. S11 and S12, ESI †).</p>\n\nConclusions\n<p>In summary, we have demonstrated the rst example of controlled living polymerization of disulde-backbone polymers with narrow MWDs (PDI < 1.1). We could successfully synthesize poly(OTP)s from various alcohol initiators and their block copolymers with PEO and poly(3CL) through the combination of a newly designed 7-membered disulde-containing lactone, OTP, and a lactone-activating catalyst unreactive to disuldes. The poly(OTP)s showed characteristic degradability of disulde-bearing compounds under exposure to thiols and UV irradiation. Thanks to the simple introduction of a poly(-disulde) backbone with a controlled length, the OTP polymerization can be a very useful tool for the development of smart materials with stimuli-responsive reversible degradability, especially in the biomedical elds. More importantly, we believe that poly(OTP)s can be applicable to supramolecular chemistry for formation of delicate nanostructures requiring narrow MWDs of the components, where the application of poly(disulde)s with attractive stimuli-responsiveness has been difficult due to broad MWDs until now.</p>\n\nConflicts of interest\n<p>There are no conicts to declare.</p>", "role": "user" }, { "content": "We report the first example of controlled polymerization of poly(disulfide)s with narrow molecular weight distributions. 1,4,5-oxadithiepan-2-one (OTP), a disulfide-containing 7-membered ring lactone, was polymerized by using the diphenylphosphate (DPP) catalyzed lactone ring-opening polymerization method. The polymerization proceeded in a living manner, and the resulting polymers displayed very narrow polydispersity index (PDI) values below 1.1 and excellent backbone degradability responding to reducing conditions and UV irradiation.", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nUsed for simple commands recognition on devices from smart routers to mobile phones, keyword spotting systems are everywhere. Ubiquitous as well are web applications, which have grown in popularity and complexity over the last decade with significant improvements in usability under cross-platform conditions. However, despite their obvious advantage in natural language interaction, voice-enabled web applications are still far and few between. In this work, we attempt to bridge this gap by bringing keyword spotting capabilities directly into the browser. To our knowledge, we are the first to demonstrate a fully-functional implementation of convolutional neural networks in pure JavaScript that runs in any standards-compliant browser. We also apply network slimming, a model compression technique, to explore the accuracy-efficiency tradeoffs, reporting latency measurements on a range of devices and software. Overall, our robust, cross-device implementation for keyword spotting realizes a new paradigm for serving neural network applications, and one of our slim models reduces latency by 66 with a minimal decrease in accuracy of 4 from 94 to 90 .\n\nCited Works Summary:\n[1]: Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization. It also acts as a regularizer, in some cases eliminating the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.9 top-5 validation error (and 4.8 test error), exceeding the accuracy of human raters.\n\n[2]: The success of CNNs in various applications is accompanied by a significant increase in the computation and parameter storage costs. Recent efforts toward reducing these overheads involve pruning and compressing the weights of various layers without hurting original accuracy. However, magnitude-based pruning of weights reduces a significant number of parameters from the fully connected layers and may not adequately reduce the computation costs in the convolutional layers due to irregular sparsity in the pruned networks. We present an acceleration method for CNNs, where we prune filters from CNNs that are identified as having a small effect on the output accuracy. By removing whole filters in the network together with their connecting feature maps, the computation costs are reduced significantly. In contrast to pruning weights, this approach does not result in sparse connectivity patterns. Hence, it does not need the support of sparse convolution libraries and can work with existing efficient BLAS libraries for dense matrix multiplications. We show that even simple filter pruning techniques can reduce inference costs for VGG-16 by up to 34 and ResNet-110 by up to 38 on CIFAR10 while regaining close to the original accuracy by retraining the networks.\n\n[3]:", "role": "user" }, { "content": "Compressing neural networks Sparse matrix storage leads to inefficient computation and storage in general-purpose hardware; thus, inducing structured sparsity in neural networks, e.g., on entire rows and columns, has been the cornerstone of various compression techniques [2] [3] . Network slimming [2] is one such state-of-the-art approach that have been applied successfully to CNNs: first, models are trained with an @math penalty on the scale parameters in 2D batch normalization [1] layers, which encourages entire channels to approach zero. Then, a fixed percentage of smallest and hence unimportant scale parameters are removed, along with the correspondent preceding and succeeding filters in the convolution layers (see Figure ). Finally, the entire network is fine-tuned on the training set---this entire process can optionally be repeated multiple times.", "role": "assistant" } ]

[ { "content": "Analyze the given text to identify specific entities. Focus on extracting relevant data.\n\nProvide your findings in JSON format. Each category should list the entities found.\n\nText:\n\nGenomics-Guided Discovery of Thailanstatins A, B, and C As Pre-mRNA Splicing Inhibitors and Antiproliferative Agents from Burkholderia thailandensis MSMB43. Mining the genome sequence of Burkholderia thailandensis MSMB43 revealed a cryptic biosynthetic gene cluster resembling that of FR901464 (4), a prototype spliceosome inhibitor produced by Pseudomonas sp. No. 2663. Transcriptional analysis revealed a cultivation condition in which a regulatory gene of the cryptic gene cluster is adequately expressed. Consequently, three new compounds, named thailanstatins A (1), B (2), and C (3), were isolated from the fermentation broth of B. thailandensis MSMB43. Thailanstatins are proposed to be biosynthesized by a hybrid polyketide synthase-nonribosomal peptide synthetase pathway. They differ from 4 by lacking an unstable hydroxyl group and by having an extra carboxyl moiety; those differences endow thailanstatins with a significantly greater stability than 4 as tested in phosphate buffer at pH 7.4. In vitro assays showed that thailanstatins inhibit pre-mRNA splicing as potently as 4, with half-maximal inhibitory concentrations in the single to sub-μM range. Cell culture assays indicated that thailanstatins also possess potent antiproliferative activities in representative human cancer cell lines, with half-maximal growth inhibitory concentrations in the single nM range. This work provides new chemical entities for research and development and new structure-activity information for chemical optimization of related spliceosome inhibitors.", "role": "user" }, { "content": "{\"Chemical\": [\"carboxyl\", \"phosphate\", \"thailanstatins\", \"hydroxyl\", \"FR901464\", \"Thailanstatins A, B, and C\", \"Thailanstatins\"]}", "role": "assistant" } ]

[ { "content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: While the primary threat posed by COVID-19 is to people's physical health, the pandemic is also taking its toll on economies, social and cultural activities, and people's mental health.\n\nResearch Abstract:\nOBJECTIVE The socio-health emergency caused by COVID-19 may have a significant psychological impact on the population.\nFor this reason, it is necessary to identify especially vulnerable social groups and protective factors that may reduce this impact, which was the objective of this study.\nMETHODS Using snowball sampling approach, 1,596 people residing in Spain during the lockdown answered an online questionnaire that included information on sociodemographic variables, symptoms, and contact with the disease, risk perception, precautionary measures to prevent infection and coping strategies during lockdown.\nPsychological impact was assessed using the Impact of Event Scale-Revised (IES-R), and mental health status with the Goldberg's General Health Questionnaire (GHQ-12).\nSimple linear regression models were performed to analyze the associations between the study variables and the psychological impact of the pandemic and the mental health of the participants.\nRESULTS Of all respondents, 24.7% reported a moderate or severe psychological impact, and 48.8% showed mental health problems.\nWomen, students and the population with a lower level of economic income, in addition to those having less available space per person in the household presented a more significant psychological impact and worse mental health.\nLiving with someone from the high-risk vulnerable group, and anticipating the adverse economic effects of social-health crisis raised the emotional distress and psychological morbidity.\nPrecautionary measures to prevent infection did not present a connection to the psychological impact of the pandemic; however, several coping strategies did help to reduce it.\nCONCLUSIONS These findings outline the existence of especially vulnerable social groups to the impact of the pandemic, and suggest lines of action that help reduce the psychosocial consequences of COVID-19.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "You will be presented with the full text of a scientific research paper. Write an abstract summarizing the key points. Your response should contain only the abstract without any other text.\n\nArticle text:\nthe physical nature of dark matter in the universe still remains an unresolved mystery .\naxions @xcite which appear as nambu - goldstone bosons of the spontaneously broken peccei - quinn symmetry @xmath3 are one of the well - motivated candidates for the cold dark matter @xcite . in analogy to neutral pions ,\naxions generically interact with photons according to lagrangian : @xmath4 with a strength @xmath5 where @xmath6 is the energy scale of the symmetry breaking and @xmath7 is a model - dependent factor of order unity , @xmath8 is the electromagnetic field strength tensor , @xmath9 its dual , and * e * and * b * are the electric and magnetic fields , respectively ; @xmath1 is the axion field .\nexisting axion models also contain an interaction of axions with charged fermions ( usual or exotic ) : @xmath10 which automatically leads to an electromagnetic coupling of the form in eq .\n( [ eq : l - ag ] ) because of the triangle loop @xmath11amplitude @xcite . here\n@xmath12 is a dimensionless coupling constant , @xmath13 is a model dependent factor\n, @xmath14 is the fermion field with mass @xmath15 ; @xmath16 , @xmath17 are dirac @xmath18-matrices . the two - photon - axion interaction vertex allows for the axion radiative decay @xmath19 @xcite , for the primakoff conversion @xmath20 in the presence of electric or magnetic fields @xcite as well as for plasmon decay @xmath21 @xcite and coalescence @xmath22 @xcite .\nthe last two processes are kinematically possible because of the dispersion relations of electromagnetic excitations in a plasma which differ significantly from the vacuum dispersion .\nit is known that an external electromagnetic field plays the role of an active medium in its influence on particle properties . due to a nontrivial kinematics of charged particles and a photon dispersion in the external field , such axion processes as the axion decay into electron - positron pair @xmath23 @xcite , the axion cyclotron emission @xmath24\n@xcite are not only opened kinematically but also become substantial . due to a very weak interaction of axions with a matter ( the latest astrophysical data yield @xmath25 gev @xcite ) , the processes with axion emission could be of great importance in astrophysics as an additional source of star energy losses is obtained from the requirement that stars not lose too much energy by axions . ] . in the studies of processes occurring inside astrophysical objects ,\none has to take into account the influence of both components of the active medium a plasma and a magnetic field .\na situation is also possible when the field component dominates ; for example , in a supernova explosion or in a coalescence of neutron stars , a region outside the neutrino sphere of order of hundred kilometers with a strong magnetic field and a rather rarefied plasma could exist .\nin this letter we investigate a forbidden in vacuum axion decay of photon @xmath0 in an external electromagnetic field using the effective @xmath11-interaction @xcite and estimate a possible influence of this decay on the star cooling process .\nin calculating @xmath0 decay in the external field , we have to integrate over the phase space of the final particles ( photon , axion ) taking into account their non - trivial kinematics .\nthe kinematics depend substantially on the particles dispersion relations in the electromagnetic field which plays the role of an anisotropic medium .\nthe photon `` effective masses '' squared @xmath26 induced by the external field are defined as the eigenvalues of the photon polarization operator @xmath27 : @xmath28 where @xmath29 are the photon polarization vectors .\nnote that eigenmodes of two transverse photons with polarization vectors @xmath30 and @xmath31 : @xmath32 are realized in the electromagnetic field .\nhere @xmath8 is the external field tensor and @xmath33 is the photon four - momentum .\nnote that an arbitrary weak smooth field in which a relativistic particle propagates is well - described by the constant crossed field limit ( @xmath34 , @xmath35 ) .\nthus , calculations in this field possess a great extent of generality and acquire interest by themselves . below we will consider the constant crossed field as the external field . in this case\nthe dynamic parameter @xmath36 is the only field invariant .\nthe analysis of @xmath27 in one - loop approximation in the crossed field @xcite shows that the dispersion curves ( fig .\n[ fig : disp ] ) = .4 corresponding to the above - mentioned photon eigenmodes ( [ eq : polar ] ) , though being similar in their qualitative behavior , are quantitatively different .\nthe difference in values of the field - induced `` effective masses '' squared of the first- and second - photon eigenmodes makes the process of the photon splitting @xmath0 possible , where @xmath1 is an arbitrary relatively light pseudoscalar with mass @xmath37 . the field - induced contribution to the small axion mass @xcite . ]\n@xmath38 ( the real part of @xmath39 transition amplitude via the fermion loop ) is negligible : @xmath40 where @xmath41 is the model - dependent factor which determines the axion - electron coupling constant @xmath42 .\nhereafter we will take axion as a massless particle .\nthe effective axion - photon vertex was obtained in ref .\n@xcite and used to analyze the axion radiative decay @xmath19 @xcite . as in the case of @xmath19 ,\nthe main contribution to the amplitude of the photon decay @xmath0 comes from the bilinear on the external field terms of @xmath11-vertex and can be presented in the form : @xmath43 @xmath44 @xmath45 , \\nonumber \\\\\n\\eta(\\chi_1,\\chi_2 ) & = & \\big [ \\left ( x ( 1 - x ) \\chi_2 + y ( 1 - y ) \\chi_1 \\right ) ^2 \\nonumber \\\\ & - & 4 x y \\left ( x y + ( 1 - x - y ) ( x + y ) \\right ) \\chi_1 \\chi_2 \\big ] ^{-1/3 } , \\nonumber \\end{aligned}\\ ] ] where @xmath46 is the hardy - stokes function , @xmath36 , @xmath47 and @xmath48 are the dynamic parameters @xmath49 here @xmath50 and @xmath51 are the four - momenta of the initial and final photons , respectively ; @xmath52 is the axion four - momentum . the summation in eq .\n( [ eq : ampl ] ) is over the virtual fermions @xmath14 with mass @xmath15 and the relative electric charge @xmath53 ; @xmath54 is the elementary charge ; @xmath55 is the critical value of the magnetic field strength for the fermion .\nwe have neglected terms of order @xmath56 , @xmath57 in the argument of the function @xmath46 . the amplitude , eq .\n( [ eq : ampl ] ) , is significantly simplified in the case of small values of the dynamic parameters . in this case\nthe decay of the photon with the first polarization ( see fig . [ fig : disp ] ) is allowed kinematically due to the condition @xmath58 : @xmath59 with the photon polarization vectors , eq .\n( [ eq : polar ] ) , the amplitude is : @xmath60 where @xmath61 is the relative energy of the final photon .\nthe function @xmath62 defined in ( [ eq : intj ] ) has the following asymptotic behavior at small values of its arguments : @xmath63 the limit of large values of the dynamic parameter can only be realized in the central regions of astrophysical objects with the strong magnetic field where the characteristic temperatures @xmath64 .\nbut in these regions from both components of the active medium , the plasma and the magnetic field , the plasma component dominates .\nthus eq .\n( [ eq : ampl ] ) can not be used to estimate possible astrophysical applications because it does not take into account the plasma influence .\nthe probability of the photon decay in the limit of small values of dynamic parameter @xmath47 can be presented in the form : @xmath65 to illustrate a possible application of the result obtained , we calculate the contribution of this process to the axion emissivity @xmath66 , i.e. the rate of energy loss per unit volume , of the photon gas : @xmath67 where @xmath68 and @xmath69 are the planck distribution functions of the initial and final photons at temperature @xmath70 , respectively . in eq .\n( [ eq : q1 ] ) we have taken into account that the photon of only one polarization ( the first one in our case ) splits .\nnote that the dynamic parameter @xmath47 in @xmath71 depends on the photon energy @xmath72 and the angle @xmath73 between the initial photon momentum @xmath74 and the magnetic field strength * b * : @xmath75 neglecting the photon `` effective masses '' squared ( @xmath76 ) , the result of the calculation of the axion emissivity @xmath66 ( [ eq : q1 ] ) becomes : @xmath77 below we estimate the contribution of the photon decay @xmath0 into the axion luminosity @xmath78 in a supernova explosion from a region of order of hundred kilometers in size outside the neutrino sphere . in this region a rather rarefied plasma with the temperature of order of mev and the magnetic field of order @xmath79 g can exist . under these conditions\nthe estimation of the axion luminosity is : @xmath80 the comparison of eq .\n( [ eq : lum ] ) with the total neutrino luminosity @xmath81 erg / s from the neutrino sphere shows that the contribution of the photon decay to the supernova energy losses is very small and does not allow to get a new restriction on the axion - electron coupling @xmath42 .\nin this letter we have studied the field - induced photon decay @xmath0 ( @xmath1 is a light pseudoscalar particle ) . for the pseudoscalar particle , we considered the most widely discussed particle , the axion , corresponding to the spontaneous breaking of the peccei - quinn symmetry .\nthis is forbidden in vacuum process but it becomes kinematically possible because photons of different polarizations obtain different field - induced `` effective masses '' squared . at the same time an external field influence on\nthe axion mass is negligible . the process @xmath0 could be of interest as an additional source of energy losses by astrophysical objects .\nwe considered the case of small values of the dynamic parameter which can be realized , for example , in a supernova explosion .\nwhile this process and its evaluation are conceptually quite intriguing , the actual energy - loss rate appeared to be rather small in comparison with the neutrino luminosity in the conditions considered .\nthis work was partially supported by intas under grant no .\n96 - 0659 and by the russian foundation for basic research under grant no .\n98 - 02 - 16694 . the work of n.v .\nmikheev was supported under grant no . d98 - 181 by international soros science education program .\npeccei and h.r .\nquinn , _ phys .\nlett . _ * 38 * , 1440 ( 1977 ) ; _ phys .\nrev . _ * d16 * , 1791 ( 1977 ) . s. weinberg , _ phys\n. rev .\n_ * 40 * , 223 ( 1978 ) ; f. wilczek , _ ibid . _\n* 40 * , 279 ( 1978 ) .\nraffelt , _ stars as laboratories for fundamental physics _\n( university of chicago press , 1996 ) .\nraffelt , in _ proceedings of beyond the desert 1997 _ , eds .\nklapder - kleingrothaus and h. paes .\n( institute of physics pub . , 1998 ) , p. 808 ; preprint astro - ph/9707268 .\nraffelt , in _ proceedings of 1997 european school of high - energy physics _ , eds . n. ellis and m. neubert .\n( cern , geneva , 1998 ) , p. 235 ; preprint hep - ph/9712538 . d.a .\ndicus _ et al .\n. rev . _ * d18 * , 1829 ( 1978 ) .\na. pantziris and k. kang , _ phys .\nrev . _ * d33 * , 3509 ( 1986 ) .\nraffelt , _ phys .\nrev . _ * d37 * , 1356 ( 1988 ) .\nmikheev and l.a .\nvassilevskaya , _ phys .\nlett . _ * b410 * , 203 ( 1997 ) . n.v . mikheev , o.s . ovchinnikov and l.a .\nvassilevskaya , _ mod .\nlett . _ * a13 * , 321 ( 1998 ) .\na.v . borisov and v.yu .\ngrishina , _ jetp _ * 79 * , 837 ( 1994 ) ; m. kachelriess , c. wilke and g. wunner , _ phys .\nrev . _ * d56 * , 1313 ( 1997 ) .\nmikheev , g.g .\nraffelt and l.a .\nvassilevskaya , _ phys .\nrev . _ * d58 * , 055008 ( 1998 ) ; preprint hep - ph/9803486 .\nvassilevskaya , n.v .\nmikheev and a.ya .\nparkhomenko , _ phys . at .\nnucl . _ * 60 * , 2041 ( 1997 ) .\nritus , in _ issues in intense - field quantum electrodynamics _\n( nauka , 1986 ) , p. 141 .\nmikheev and l.a .\nvassilevskaya , _ phys .\n* b410 * , 207 ( 1997 ) .", "role": "user" }, { "content": "an interaction of a pseudoscalar particle with two photons induced by an external electromagnetic field is used to study the photon decay @xmath0 where @xmath1 is a pseudoscalar particle associated with the peccei - quinn @xmath2 symmetry . \n the field - induced axion emission by photon is analyzed as a possible source of energy losses by astrophysical objects . \n # 1#2", "role": "assistant" } ]

[ { "content": "Transform the following sections from a biomedical study into a simple summary for the general public. Focus on making the information accessible and easy to understand.\n\nResearch Heading: Independent Component Analysis in Spiking Neurons\nContent:\nAbstract:\nAlthough models based on independent component analysis( ICA) have been successful in explaining various properties of sensory coding in the cortex, it remains unclear how networks of spiking neurons using realistic plasticity rules can realize such computation. Here, we propose a biologically plausible mechanism for ICA-like learning with spiking neurons. Our model combines spike-timing dependent plasticity and synaptic scaling with an intrinsic plasticity rule that regulates neuronal excitability to maximize information transmission. We show that a stochastically spiking neuron learns one independent component for inputs encoded either as rates or using spike-spike correlations. Furthermore, different independent components can be recovered, when the activity of different neurons is decorrelated by adaptive lateral inhibition.\nIntroduction:\nIndependent component analysis is a well-known signal processing technique for extracting statistically independent components from high-dimensional data. For the brain, ICA-like processing could play an essential role in building efficient representations of sensory data[1]–[4]. However, although many algorithms have been proposed for solving the ICA problem[5], only few consider spiking neurons. Moreover, the existing spike-based models[6],[7] do not answer the question how this type of learning can be realized in networks of spiking neurons using local, biologically plausible plasticity mechanisms( but see[8]). Classic ICA algorithms often exploit the non-Gaussianity principle, which allows the ICA model to be estimated by maximizing some non-Gaussianity measure, such as kurtosis or negentropy[5]. A related representational principle is sparse coding, which has been used to explain various properties of V1 receptive fields[9]. Sparse coding states that only a small number of neurons are activated at the same time, or alternatively, that each individual unit is activated only rarely[10]. In the context of neural circuits, it offers a different interpretation of the goal of the ICA transform, from the perspective of metabolic efficiency. As spikes are energetically expensive, neurons have to operate under tight metabolic constraints[11], which affect the way information is encoded. Moreover, experimental evidence supports the idea that the activity of neurons in V1 is sparse. Close to exponential distributions of firing rates have been reported in various visual areas in response to natural scenes[12]. Interestingly, certain homeostatic mechanisms are thought to regulate the distribution of firing rates of a neuron[13]. These intrinsic plasticity( IP) mechanisms adjust ionic channel properties, inducing persistent changes in neuronal excitability[14]. They have been reported for a variety of systems, in brain slices and neuronal cultures[14],[15] and they are generally thought to play a role in maintaining system homeostasis. Moreover, IP has been found to occur in behaving animals, in response to learning( see[14] for review). From a computational perspective, it is believed that IP may maximize information transmission of a neuron, under certain metabolic constraints[13]. Additionally, we have previously shown for a rate neuron model that, when interacting with Hebbian synaptic plasticity, IP allows the discovery of heavy-tailed directions in the input[16]. Here, we extend these results for a network of spiking neurons. Specifically, we combine spike-timing dependent plasticity( STDP)[17]–[19], synaptic scaling[20] and an IP rule similar to[16], which tries to make the distribution of instantaneous neuronal firing rates close to exponential. We show that IP and synaptic scaling complement STDP learning, allowing single spiking neurons to learn useful representations of their inputs for several ICA problems. First, we show that output sparsification by IP together with synaptic learning is sufficient for demixing two zero mean supergaussian sources, a classic formulation of ICA. When using biologically plausible inputs and STDP, complex tasks, such as Foldiák's bars problem[21], and learning oriented receptive fields for natural visual stimuli, can be tackled. Moreover, a population of neurons learns to extract several independent components if the activity of different neurons are decorrelated by adaptive lateral inhibition. When investigating the mechanisms how learning occurs in our model, we show that IP is necessary for learning, as it enforces a sparse output, guiding learning towards heavy-tailed directions in the input. Lastly, for specific STDP implementations, we show that IP shifts the threshold between potentiation and depression, similar to a sliding threshold for Bienenstock-Cooper-Munro( BCM) learning[22]. The underlying assumption behind our approach, implicit in all standard models of V1 receptive field development, is that both input and output information are encoded in rates. In this light, one may think of our current work as a translation of the model in[16] to a spike-based version. However, the principles behind our model are more general than suggested by our work with rate neurons. We show that the same rule can be applied when inputs are encoded as spike-spike correlation patterns, where a rate-based model would fail.\nDiscussion:\nAlthough ICA and related sparse coding models have been very successful in describing sensory coding in the cortex, it has been unclear how such computations can be realized in networks of spiking neurons in a biologically plausible fashion. We have presented a network of stochastically spiking neurons that performs ICA-like learning by combining different forms of plasticity. Although this is not the only attempt at computing ICA with spiking neurons, in previous models synaptic changes were not local, depending on the activity of neighboring neurons within a population[6],[7]. In this light, our model is, to our knowledge, the first to offer a mechanistic explanation of how ICA-like computation could arise by biologically plausible learning mechanisms. In our model, IP, STDP and synaptic scaling interact to give rise to robust receptive field development. This effect does not depend on a particular implementation of STDP, but it does require an IP mechanism which enforces a sparse output distribution. Although there are very good theoretical arguments why this should be the case[11],[13],[16], the experimental evidence supporting this assumption is limited[12]. A likely explanation for this situation is the fact that it is difficult to map the experimentally observable output spikes into a probability of firing. Spike count estimates cannot be used directly, as they critically depend on the bin size. Additionally, the inter-spike interval( ISI) of an inhomogeneous Poisson process with exponentially distributed mean is indistinguishable from the ISI of a homogeneous Poisson distribution with mean. Hence, more complex statistical analyses are required for disentangling the two( see[35]). From a computational perspective, our approach is reminiscent of several by-now classic ICA algorithms. As mentioned before, IP enforces the output distribution to be heavy-tailed, like in sparse coding[9]. Our model also shares conceptual similarities to InfoMax[29], which attempts to maximize output entropy( however, at the population level) by regulating the weights and a neuron threshold parameter. Maximizing information transmission between pre- and post-synaptic spike trains under the constraint of a fixed mean postsynaptic firing rate links our method to previous work on synaptic plasticity. A spike-based synaptic rule optimizing the above criterion[23] yields a generalization of the BCM rule[22], a powerful form of learning, which is able to discover heavy-tailed directions in the input[36],[37] and to learn Gabor receptive fields[38] in linear neurons. We have shown that, sliding threshold BCM can be viewed as a particular case of IP learning, for a specific family of STDP models. It is interesting to think of the mechanism presented here in relation to projection pursuit[39], which tries to find good representations of high-dimensional spaces by projecting data on a lower dimensional space. The algorithm searches for interesting projection directions, a typical measure of interest being the non-Gaussianity of the distribution of data in the lower dimensional space. The difference here is that, although we do not explicitly define a contrast function maximizing kurtosis or other similar measure, our IP rule implicitly yields highly kurtotic output distributions. By sparsifying the neuron output, IP guides the synaptic learning towards the interesting( i. e. heavy-tailed) directions in the input. From a different perspective, we can relate our method to nonlinear PCA. It is known that, for zero mean whitened data, nonlinear Hebbian learning in a rate neuron can successfully capture higher order correlations in the input[40],[41]. Moreover, it has been suggested that the precise shape of the Hebbian nonlinearity can be used for optimization purposes, for example for incorporating prior knowledge about the sources' distribution[40]. IP goes one step further in this direction, by adapting the transfer function online, during learning. From a biological perspective, there are some advantages in adapting the neuron's excitability during computation. Firstly, IP speeds up the nonlinear decorrelation of inputs. Secondly, the system gains great robustness to changes in parameters( as demonstrated in Text S2). Additionally, IP regulation plays a homeostatic role, making constraints on the input mean or second order statistics unnecessary. In the end, all the methods we have mentioned are closely related and, though conceptually similar, our approach is another distinct solution. Our previous work was restricted to the a rate model neuron[16]. Beyond translating our results to a spiking neuron model, we have shown here that similar principles can be applied when information is encoded as spike-spike correlations, where a model relying just on firing rates would fail. It is a interesting challenge for future work to further investigate the exact mechanisms of receptive field development for different types of input encoding.", "role": "user" }, { "content": "How the brain learns to encode and represent sensory information has been a longstanding question in neuroscience . Computational theories predict that sensory neurons should reduce redundancies between their responses to a given stimulus set in order to maximize the amount of information they can encode . Specifically , a powerful set of learning algorithms called Independent Component Analysis ( ICA ) and related models , such as sparse coding , have emerged as a standard for learning efficient codes for sensory information . These algorithms have been able to successfully explain several aspects of sensory representations in the brain , such as the shape of receptive fields of neurons in primary visual cortex . Unfortunately , it remains unclear how networks of spiking neurons can implement this function and , even more difficult , how they can learn to do so using known forms of neuronal plasticity . This paper solves this problem by presenting a model of a network of spiking neurons that performs ICA-like learning in a biologically plausible fashion , by combining three different forms of neuronal plasticity . We demonstrate the model's effectiveness on several standard sensory learning problems . Our results highlight the importance of studying the interaction of different forms of neuronal plasticity for understanding learning processes in the brain .", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nWith the rise of the Internet of Things (IoT), fog computing has emerged to help traditional cloud computing in meeting scalability demands. Fog computing makes it possible to fulfill real-time requirements of applications by bringing more processing, storage, and control power geographically closer to edge devices. However, since fog computing is a relatively new field, there is no standard platform for research and development in a realistic environment, and this dramatically inhibits innovation and development of applications suitable for the fog. In response to these challenges, we propose the FDK: A Fog Development Kit for software-defined edge-fog systems. By providing high-level interfaces for allocating computing and networking resources, the FDK abstracts the complexities of fog computing from developers and enables rapid development of edge-fog systems. Also, the FDK supports the utilization of virtualized devices to create a highly realistic emulation environment, allowing fog application prototypes to be built with zero additional costs and enabling portability to a physical infrastructure. We evaluate the resource allocation performance of the FDK using a testbed, including eight edge devices, four fog nodes, and five OpenFlow switches. Our evaluations show that the delay of resource allocation and deallocation is less than 279ms and 256ms for 95 of edge-fog transactions, respectively. Besides, we demonstrate that resource allocations are appropriately enforced and guaranteed, even amidst extreme network congestion.\n\nCited Works Summary:\n[1]: Production datacenters operate under various uncertainties such as traffic dynamics, topology asymmetry, and failures. Therefore, datacenter load balancing schemes must be resilient to these uncertainties; i.e., they should accurately sense path conditions and timely react to mitigate the fallouts. Despite significant efforts, prior solutions have important drawbacks. On the one hand, solutions such as Presto and DRB are oblivious to path conditions and blindly reroute at fixed granularity. On the other hand, solutions such as CONGA and CLOVE can sense congestion, but they can only reroute when flowlets emerge; thus, they cannot always react timely to uncertainties. To make things worse, these solutions fail to detect handle failures such as blackholes and random packet drops, which greatly degrades their performance. In this paper, we introduce Hermes, a datacenter load balancer that is resilient to the aforementioned uncertainties. At its heart, Hermes leverages comprehensive sensing to detect path conditions including failures unattended before, and it reacts using timely yet cautious rerouting. Hermes is a practical edge-based solution with no switch modification. We have implemented Hermes with commodity switches and evaluated it through both testbed experiments and large-scale simulations. Our results show that Hermes achieves comparable performance to CONGA and Presto in normal cases, and well handles uncertainties: under asymmetries, Hermes achieves up to 10 and 20 better flow completion time (FCT) than CONGA and CLOVE; under switch failures, it outperforms all other schemes by over 32 .\n\n[2]: Most datacenters still use Equal Cost Multi-Path (ECMP), which performs congestion-oblivious hashing of flows over multiple paths, leading to an uneven distribution of traffic. Alternatives to ECMP come with deployment challenges, as they require either changing the tenant VM network stacks (e.g., MPTCP) or replacing all of the switches (e.g., CONGA). We argue that the hypervisor provides a unique point for implementing load-balancing algorithms that are easy to deploy, while still reacting quickly to congestion. We propose Clove, a scalable load-balancer that (i) runs entirely in the hypervisor, requiring no modifications to tenant VM networking stacks or physical switches, and (ii) works on any topology and adapts quickly to topology changes and traffic shifts. Clove relies on standard ECMP in physical switches, discovers paths using a novel traceroute mechanism, uses software-based flowlet-switching, and continuously learns congestion (or path utilization) state using standard switch features. It then manipulates packet-header fields in the hypervisor switch to direct traffic over less congested paths. Clove achieves 1.5 to 7 times smaller flow-completion times at 70 network load than other load-balancing algorithms that work with existing hardware. Clove also captures some 80 of the performance gain of best-of-breed hardware-based load-balancing algorithms like CONGA that require new equipment.", "role": "user" }, { "content": "Typically, network resource management is accomplished using a load balancer, which attempts to find a suitable path to one or more destinations while optimally spreading traffic throughout the network to avoid congestion. In many cases, Equal-Cost Multi-Path (ECMP) routing is used to manage network resources by distributing traffic throughout the network. However, several authors, such as Katta [2] and Zhang [1] , suggest that ECMP's performance is far from optimal and that it is known to result in unevenly distributed network flows and poor performance. In response, Katta proposed Clove [2] , a congestion-aware load balancer that works alongside ECMP by modifying encapsulation packet header fields to manipulate flow paths, ultimately providing lower Flow Completion Times (FCT) than ECMP. Similarly, Zhang proposed Hermes [1] , a distributed load balancing system, which offers up to 10 Clove can handle link failures and topology asymmetry, Hermes can handle more advanced and complex uncertainties in the network such as packet black-holes and switch failures.", "role": "assistant" } ]

[ { "content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nThe systemic nature of this disease is reflected in the involvement of multiple organ systems, including skin, lungs, and vasculature as well as diffuse tissue inflammation and increased risk of atherosclerosis (1).", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nSynthesis of isoprenoid bisphosphonate ethers through C–P bond formations: Potential inhibitors of geranylgeranyl diphosphate synthase\n\nContent Extracts:\nIntroduction\n<p>Several enzymes of the isoprenoid biosynthesis pathways are the targets of widely prescribed drugs. For example, hydroxymethylglutaryl CoA reductase (HMGCoA) is viewed as the first committed step of isoprenoid and steroid biosynthesis, and is the target of the statin class of cholesterol-lowering agents including lovastatin (1, Figure 1) and pravastatin (2) [1]. The downstream enzyme farnesyl diphosphate synthase (FDPS) is the target of the nitrogenous bisphosphonates including risedronate (3) and zoledronate (4), which are widely used for treat-ment of osteoporosis [2]. It can be argued that the success of these drugs is due at least in part to the central roles that isoprenoids play in mammalian metabolism, which suggests that other enzymes in these pathways also may have value as drug targets.</p><p>One of our interests in isoprenoid biosynthesis has been the enzyme geranylgeranyl diphosphate synthase (GGDPS), which mediates the reaction of the C 15 compound farnesyl diphos- phate (FPP) with the C 5 isopentenyl diphosphate to form the C 20 isoprenoid geranylgeranyl diphosphate (GGPP) (Figure 2) [3]. Geranylgeranylation is an important posttranslational modification, especially among proteins in the Ras superfamily of small GTPases that are involved in a variety of signaling pathways [4]. Based on the premise that inhibition of GGDPS should reduce cellular levels of GGPP and thus diminish protein geranylgeranylation, one might expect that inhibitors of this enzyme would interfere with essential cell signaling pathways and demonstrate antiproliferative activity. Several years ago we reported the synthesis of digeranyl bisphosphonate (DGBP, 5, Figure 3) [5], and determined that this compound was an inhibitor of GGDPS (IC 50 ~ 200 nM), competitive with FPP, and yet showed much less activity against FDPS (IC 50 > 10 μM) in enzyme assays [6]. Furthermore, despite the high degree of negative charge on DGBP at physiological pH, Western blot analyses of K562 cells (a human-derived, myeloid leukemia cell line) treated with this compound make clear that it penetrates the cell membrane at a concentration sufficient to impact GGPP levels. For example in the presence of micromolar DGBP, Rap1a which is normally found to be fully geranylgeranylated through posttranslational processing, instead is only partially modified [5]. Preparation of a prodrug form of DGBP does increase the impact of the drug by nearly an order of magnitude [7], but masking the negative charges of DGBP is not essential for observation of cellular activity. Following our reports on the activity of DGBP, a beautiful set of crystallographic analyses from the Oldfield group attributed the activity of this compound and a number of others in part to a V-like shape [8]. This shape allows one geranyl group to occupy the enzyme channel where FPP enters the active site of GGDPS, while at the same time the second isoprenoid chain can fit nicely in the groove where the product GGPP normally departs from the active site. To continue efforts [9] to increase the potency of GGDPS inhibitors, we sought a new set of isoprenoid bisphosphonates as represented by structure 6 (Figure 3). This O,C-digeranyl geminal bisphosphonate was expected to preserve a V-like structure very similar to that of DGBP. However, the presence of an oxygen substituent on the geminal carbon should lower the pK a of bisphosphonate 6 relative to that of compound 5, which might enhance its similarity to an isoprenoid diphosphate. In both monophosphonates [10] and bisphosphonates [11] introduction of an alpha hydroxy group has been reported to increase biological activity significantly. In bisphosphonates even a small change in pK a3 may be important because it lies in a range close to physiological pH [12]. If an ether substituent on this template had a comparable impact, it could significantly increase the activity relative to DGBP itself [13]. Furthermore, one binding model suggests that the hydroxy group itself, so prominent in the clinically used bisphosphonates, contributes only modestly to binding with the bone surface [14], and there- fore might be a site appropriate for further modification. Thus we decided to pursue compounds of the general structure 6. We report here the synthesis of some isoprenoid bisphosphonate ethers in this family and our initial studies of their biological activity.</p>\n\nResults and Discussion\n<p>Of the different routes one might consider to prepare geminal bisphosphonate ethers, some can be readily dismissed. For example, while several routes to hydroxybisphosphonates are known [15], any attempt to incorporate an ether linkage through the corresponding alkoxide after formation of the bisphosphonate would face the strong possibility of phosphonate-phosphate rearrangement [15][16][17]. However, diethyl hydroxymethylphosphonate (7, Scheme 1) is known to react with a base and geranyl bromide to afford the ether 8 in good yield [18]. With compound 8 in hand, formation of the second C-P bond occurred readily upon treatment with base and diethyl chlorophosphate [19][20][21][22][23] to give the bisphosphonate ether 9 in modest yield. Alkylation of ether 9 with geranyl bromide proceeded under conditions similar to those we have reported for the preparation of dialkyl bisphosphonate 5, and gave the desired tetraethyl O,C-digeranylbisphosphonate 10. Hydrolysis of the phosphonate esters proceeded under standard McKenna conditions [24], but only a limited amount of the product 6 was recovered after precipitation from acetone/water. A parallel hydrolysis of bisphosphonate 9 gave compound 11, also in modest yield. Because the 31 P NMR spectra of the reaction mixtures showed a single resonance in both cases, it is quite likely that the low yield results from low recovery of the bisphosphonate salts.</p><p>Compound 6 should preserve the V-shape that would allow one isoprenoid chain to nestle within the FPP site while the other occupies the GGPP site [8]. It would not be readily apparent however, if one site is occupied preferentially by the O-geranyl group, or whether this group is randomly distributed between the two possibilities. In an initial effort to distinguish between random binding and differential binding, we have prepared the two isomeric bisphosphonate salts 16 and 20 through variations on the strategy used to prepare the digeranyl compound 6. As shown in Scheme 2, reaction of phosphonate 7 with base and prenyl bromide gave the known phosphonate 12 [25]. Treatment of this phosphonate with base and diethyl chlorophosphate gave the desired bisphosphonate ester 13. This ester was converted to the corresponding salt under standard conditions to obtain compound 14. Alternatively, reaction of ester 13 with base and geranyl bromide gave the tetraethyl ester 15 and hydrolysis in this case afforded the desired phosphonate 16. In a similar manner, reaction of the bisphosphonate ester 13 with base and prenyl bromide gave the O,C-diprenyl product 17, and standard hydrolysis gave the salt 18. To prepare the isomeric O-geranyl-C-prenyl compounds, the geranyl ether 9 was treated with base and prenyl bromide under parallel reaction conditions to afford compound 19. Standard hydrolysis of this ester then gave the desired phosphonate salt 20.</p><p>Scheme 2: Synthesis of prenyl/geranyl bisphosphonate isomers.</p><p>To gauge the generality of this approach to bisphosphonate ethers while still maintaining isoprenoid substructures, preparation of a citronellal series was examined. Alkylation of phosphonate 7 with (S)-(+)-citronellyl bromide occurred under the standard conditions, albeit in lower yield (Scheme 3). The resulting ether 21 was converted to the corresponding bisphosphonate 22 through formation of the anion and reaction with diethyl chlorophosphate. Alkylation of this bisphosphonate with geranyl bromide also proved feasible, and gave the expected tetraethyl ester 23. Hydrolysis of compound 23 under standard conditions gave the desired salt 24. In contrast, efforts to alkylate the O-geranyl bisphosphonate 9 with citronellyl bromide under parallel conditions went unrewarded, which might be attributed to the lower reactivity of this alkyl bromide vis-à-vis the allylic geranyl and prenyl bromides used above. Alternate strategies for preparation of compound 25 have not yet been explored, pending determination of the biological activity of the compounds in hand.</p><p>Preliminary evaluation of the biological activity of the dialkyl bisphosphonates was based on their ability to inhibit the enzymes GGDPS and FDPS [26]. The two prenyl bisphosphonate ethers, compounds 18 and 14, showed little or no activity in these assays, as might be expected given their minimal isoprenoid chains [27]. However the compounds bearing longer alkyl chains were more interesting. As shown in Table 1, a range of activities was observed for these bisphosphonates. Under the specific conditions employed for the enzyme assays, compound 5 had an IC 50 of 210 nM, which is very comparable to the value initially observed [6]. The O,C-digeranyl compound 6 was similar to this value which was disappointing, but the O-geranyl compound 11 could be considered surprisingly potent given the limited activity previously reported for geranyl bisphosphonate (10 μM) [27]. The two prenyl-geranyl isomers, compounds 16 and 20 differed by a factor of ~2.5 with one roughly as potent and one ~3 fold less potent than the digeranyl compound 5. Our hypothesis was that random placement of the two isoprenoid chains should result in nearly identical biological activity for these isomeric compounds, while if placement of the isoprenoid chains were ordered then the two isomers might well show different biological activity. The observed difference is intriguing and may support the concept of an ordered binding. However, the most interesting result was observed with the citronellyl derivative 24. This compound displayed an IC 50 of 82 nM, which is ~2.6 fold more potent than the DGBP control (5). Furthermore, compound 24 displayed no activity in assays with FDPS, suggesting that its inhibition is highly selective.</p>\n\nConclusion\n<p>In conclusion, we have prepared a family of bisphosphonate ethers that incorporated terpenoid elements designed to enhance their ability to inhibit the enzyme GGDPS. The increased potency observed with the citronellyl ether 24 versus compounds prepared earlier, as well as the difference in activity between the two prenyl-geranyl isomers, encourage a more extensive investigation of the biological activity of these compounds [28]. Such studies are ongoing and will be reported in due course.</p>", "role": "user" }, { "content": "A set of bisphosphonate ethers has been prepared through sequential phosphonylation and alkylation of monophosphonate ethers. After formation of the corresponding phosphonic acid salts, these compounds were tested for their ability to inhibit the enzyme geranylgeranyl diphosphate synthase (GGDPS). Five of the new compounds show IC 50 values of less than 1 μM against GGDPS with little to no activity against the related enzyme farnesyl diphosphate synthase (FDPS). The most active compound displayed an IC 50 value of 82 nM when assayed with GGDPS, and no activity against FDPS even at a 10 μM concentration.", "role": "assistant" } ]

[ { "content": "Transform the following sections from a biomedical study into a simple summary for the general public. Focus on making the information accessible and easy to understand.\n\nResearch Heading: A Polycomb Group Protein Is Retained at Specific Sites on Chromatin in Mitosis\nContent:\nAbstract:\nEpigenetic regulation of gene expression, including by Polycomb Group( PcG) proteins, may depend on heritable chromatin states, but how these states can be propagated through mitosis is unclear. Using immunofluorescence and biochemical fractionation, we find PcG proteins associated with mitotic chromosomes in Drosophila S2 cells. Genome-wide sequencing of chromatin immunoprecipitations( ChIP–SEQ) from mitotic cells indicates that Posterior Sex Combs( PSC) is not present at well-characterized PcG targets including Hox genes in mitosis, but does remain at a subset of interphase sites. Many of these persistent sites overlap with chromatin domain borders described by Sexton et al.( 2012), which are genomic regions characterized by low levels of long range contacts. Persistent PSC binding sites flank both Hox gene clusters. We hypothesize that disruption of long-range chromatin contacts in mitosis contributes to PcG protein release from most sites, while persistent binding at sites with minimal long-range contacts may nucleate re-establishment of PcG binding and chromosome organization after mitosis.\nIntroduction:\nEpigenetic mechanisms, including those used by the essential PcG proteins, mediate stable inheritance of gene expression patterns through mitotic divisions. During mitosis, chromosomes undergo dramatic structural and biochemical changes and transcription is repressed. Binding of many transcription factors and chromatin regulators is disrupted in mitosis through post-translational modification of the proteins or their chromatin substrate[1]–[3]. Some transcription factors and chromatin proteins have been shown to persist on mitotic chromosomes to facilitate reactivation or prevent derepression of genes in G1, in a phenomenon termed “mitotic bookmarking”[4]–[9]. In most cases, however, how gene regulatory information is preserved through mitosis is not understood. PcG proteins are required to maintain gene silencing during development and in differentiated cells( reviewed in[10]–[15]). These proteins assemble into multiprotein complexes with an array of enzymatic and structural effects on chromatin( for detailed reviews on the biochemistry of PcG proteins, see[16],[17]). Genes regulated by the PcG thus likely have unique chromatin features including histone and protein modifications, tightly bound PcG proteins, and a locally altered chromatin structure. In Drosophila, Polycomb Response Elements( PREs), functional binding sites for PcG proteins[18], also participate in long range interactions, which are disrupted when PcG proteins are depleted[19],[20]. Long range interactions are influenced by insulator sequences, which are found near many well-studied PREs[21]–[24]. Insulator sequences restrict enhancer-promoter interactions, and delineate chromatin loops and large-scale domains[25]. Insulators function by binding several proteins, including CTCF, BEAF, Su( HW), Mod( mgd4) and CP190[25]. The status of long range interactions in mitosis is not known. The extensive biochemical characterization of PcG proteins has not yet elucidated how regulation by these proteins can be maintained through mitosis. One model is that PcG proteins remain bound to mitotic chromosomes. An alternative model is that most PcG proteins are released from mitotic chromosomes but certain proteins or chromatin features mark their binding sites through mitosis to direct re-establishment of PcG protein binding after mitosis[26]. In Drosophila, immunofluorescence and live cell imaging studies have provided evidence for loss of PcG proteins from mitotic chromosomes, and, in some cases, for retention of some PcG proteins[27]–[30]. Here, we use immunofluorescence, biochemical fractionation and ChIP to analyze PcG protein localization to chromatin in mitosis in Drosophila S2 cells. We describe persistent association of PcG proteins with mitotic chromosomes but loss at most specific binding sites. A class of PcG binding sites that persists in mitosis is described, which we hypothesize has unique functions in chromatin organization and heritable gene regulation.\nDiscussion:\nWe set out to determine whether PcG-dependent repression might be propagated through mitosis in Drosophila cells by persistent binding of PcG proteins( Model 1, Figure 10A), or whether binding needs to be re-established after mitosis( Model 2, Figure 10B). Using three different methods( immunofluorescence, biochemical fractionation, and ChIP-SEQ), we show that PcG proteins are associated with mitotic chromosomes. ChIP-SEQ analysis, however, indicates that PSC and likely PH binding is retained at only a subset of interphase sites. Thus, the mitotic behavior of PcG proteins displays features of both Models 1 and 2, prompting consideration of new models( Figure 10C). By immunofluorescence, we observe PSC, PC, and dR associated with mitotic chromosomes, although at reduced levels compared with interphase cells( Figure 1). These results are consistent with some studies[51],[28], and at odds with the conclusions of other investigators for PSC and PC[27]. Details in how material was prepared and quantified, as well as which cell types and developmental stages were analyzed may account for these differences. We therefore used an independent method, biochemical fractionation, to confirm that PcG proteins including PSC are associated with mitotic chromosomes( Figure 2). Our ChIP-SEQ results also demonstrate persistence of PSC on mitotic chromosomes( Figure 4). The amount of PSC retained on mitotic chromosomes as determined by ChIP is lower than by the other methods. Based on comparisons of sequenced reads, it is only a few per cent of that bound to chromatin in control cells( Figure 4B). We cannot rule out the possibility that the condensation of chromatin reduces accessibility to the antibodies and thus decreases the signal in ChIP experiments, although H3 ChIP at PRES where PSC is lost is unchanged between control and mitotic cells( Figure 3E). Nevertheless, we think it is quite possible that much of the chromosome-associated PcG protein we detect by immunofluorescence and fractionation is not bound to specific sites. These PcG proteins may travel with mitotic chromosomes to ensure equal segregation to both new cells, or to keep to the local concentration of PcG proteins near the DNA high to facilitate rebinding after mitosis. A recent live cell imaging study of two types of cells in Drosophila expressing transgenic GFP-PC or GFP-PH found that only a small fraction( 0. 4–2%) of each of these proteins was bound in metaphase( compared with 10–20% for GFP-PC and 30–70% for GFP-PH in interphase)[30]. Interestingly, PC, and in one cell type PH, was more tightly bound in metaphase than interphase. It is possible that this tightly bound protein is the protein we detect bound to specific sites by ChIP-SEQ. Our ChIP-SEQ data indicate that PSC binding sites can be grouped into two classes: dynamic sites that lose binding of PSC in mitosis, and persistent sites, at which these proteins are reduced but clearly still present. The dynamic sites include well-characterized PREs controlling expression of important PcG targets like the Hox genes. Our data thus provide clear evidence that propagation of PcG-dependent repression of most genes through mitosis does not involve persistent binding of PSC to PREs near these genes as predicted by Model 1. Our ChIP data on G2/M cells also indicates that it is unlikely that any of the PcG proteins we tested( PHO, PC, SU( Z) 12) persist at Hox PREs in mitosis( Figure 9). In contrast, our data suggest H3K27me3 levels are unchanged in G2/M cells relative to controls, and thus that H3K27me3 is a candidate “epigenetic mark” at these sites in mitosis, as predicted in Model 2. Based on the overlap between persistent PSC binding sites, chromatin domain borders and insulator proteins, and the finding that some of these sites flank PcG targets such as the Hox gene clusters( Figure 7), a possible model for the function of persistent sites is that they function as nucleation sites for re-establishment of PcG protein binding after mitosis( Figure 10). From these loading sites, PcG proteins could spread into the chromatin domain to PREs that are marked with H3K27me3 and possibly other persistent chromatin features( Figure 10). A similar model has been proposed for establishing binding of the Male Specific Lethal( MSL) dosage compensation complexes on the Drosophila male X-chromosome during development[52],[53]. MSL complexes are recruited to high affinity sites on the X chromosome from which they spread across the X chromosome. MSL complexes do not coat the X chromosome but preferentially spread to actively transcribed genes, at least in part through recognition of H3K36me3. MSL complexes associate stably with the X chromosome in mitosis[54], so that it is not clear if this process needs to be repeated each cell cycle. This model predicts that the mechanisms of recruitment to persistent and dynamic sites may be different, a prediction which has not yet been tested. Perhaps interactions between insulator proteins and PcG proteins are important for binding at persistent sites; it will be interesting to determine whether insulator proteins are retained at these sites in mitosis. Recently, Van Bortle et al.( 2012) carried out ChIP-SEQ analysis of H3K27me3 in Kc cells in which dCTCF was depleted by RNAi, and found a decrease in H3K27me3 in PcG domains in cells with depleted dCTCF[55]. This is consistent with a role for insulator proteins in maintaining PcG domains, as are earlier observations that PcG( or TrxG) mutations disrupt insulator bodies in Drosophila cells[56]. The paucity of long range interactions at border sites relative to other PcG sites such as those in the Hox clusters[19],[57],[46],[44] may contribute to the difference in PcG protein behavior at them. Perhaps disruption of long range interactions as cells enter mitosis, which might be important to allow chromatin condensation, contributes to loss of PcG proteins from sites within domains. Regions of the chromosome that are not extensively networked with distal sites( i. e. border sites) might be less disrupted by mitotic chromatin condensation, possibly allowing PcG proteins to remain bound. An alternative model for the function of persistent PSC binding sites at chromatin domain borders is that they reflect an independent role of PcG proteins in demarcating large scale chromatin domains through mitosis. PcG proteins and their functions are widely conserved. In mammalian cells, immunofluorescence studies report some PcG protein and H3K27me3 associated with mitotic chromosomes[48],[58]. PcG proteins, including EZH2, the enzyme responsible for H3K27 methylation, are phosphorylated in a cell cycle dependent manner[59]–[64]. Cell-cycle dependent CDK-mediated phosphorylation of EZH2, which peaks in G2/M is important for maintaining PRC2( the complex formed by EZH2) at target genes, possibly because it increases the affinity of PRC2 for non-coding RNAs. PRC2 also interacts and co-localizes with CTCF[24],[65]. Interestingly, a careful study of PcG proteins through the cell cycle in mammalian cells found that PcG bodies, which are thought to be sites of long range interactions among PcG proteins in Drosophila[44], are reformed in G1 although some PcG proteins and H3K27me3 persist on chromosomes through mitosis[48]. It will therefore be interesting to compare ChIP-SEQ analysis of PcG proteins in mammalian mitotic cells with the observations presented here. While this paper was being revised, a paper describing mitotic ChIP-SEQ for the transcription factor GATA-1 in FACS-sorted mammalian cells was published[66]. Persistent GATA1 binding was observed at about 10% of interphase sites in mitosis. Degradation of GATA1 in mitosis led to slower transcriptional activation of some genes with mitotic GATA1 binding and loss of repression at other targets where GATA1 is involved in negative regulation[66]. Thus, GATA1 seems to function similarly to previously described mitotic bookmarking factors[8],[9] to ensure timely regulation of gene expression on mitotic exit. We do not know if PcG proteins carry out a bookmarking function at persistent sites, but our data indicate that at important PcG targets such as the Hox genes, PSC does not function as a bookmark. In summary, we found that a key PcG protein, PSC, is lost from most sites, including well-characterized PREs, in mitosis. PSC is retained at specific sites, many of which overlap chromatin borders. We hypothesize that the persistent binding sites are important for re-establishing PcG-dependent chromatin structures and/or large scale chromatin domains after mitosis and may contribute to propagation of silencing.", "role": "user" }, { "content": "Gene expression profiles must be maintained through the cell cycle in many situations during development . How gene expression profiles are maintained through mitosis by transcriptional regulators like the Polycomb Group ( PcG ) proteins is not well understood . Here we find that PcG proteins remain associated with mitotic chromatin , and a small subset of PcG binding sites throughout the genome is maintained between interphase and mitosis . These persistent binding sites preferentially overlap borders of chromatin domains . These results suggest a model in which PcG proteins retained at border sites may nucleate re-binding of PcG protein within domains after mitosis .", "role": "assistant" } ]

[ { "content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\n(Unfortunately, many later references to Trivers (1971) do not clearly distinguish reciprocal helping from cooperation in the narrow sense and from exchange among not particularly needy individuals.)", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: Control Allocation- A Survey \nChapter Title: Mobile robots \n1. Abstract of Cited Paper (BIB001): This paper proposes new robust control allocation method of redundantly actuated variable structure systems. The original system is divided into two subsystems by factorizing the input matrix. Then all system uncertainties can be treated with the virtual control input. The control strategy has two steps. At the first step the virtual control input is found with sliding mode control with perturbation estimation method (SMCPE) considering system uncertainties then at the second step the real control input is calculated by using the Quadratic Optimization method. The simulation is conducted with the redundantly actuated leg-wheel hybrid structures which have 4 actuators and 3DOFs. The state-space model is derived from the dynamic equation with kinematic and dynamic constraints. The effect of kinematic error is also studied. \n2. Abstract of Cited Paper (BIB002): Eccentric centroid is one of the most serious problems of omni-directional mobile robot design. The reason is the limited precision in producing causes. Nowadays, most control approaches are studied basing on ideal models with regular centroid. Thus extra energy is needed to adjust difference between ideal centroid and actual centroid. In this paper, we propose an approach with eccentric centroid to analyze the distribution of traction on each wheel in this condition and get an optimization solution set of this traction with linear programming algorithm. We conducted simulation experiments to demonstrate the algorithm is of positive effect in reducing cost of extra energy.\n\nReview Chapter:", "role": "user" }, { "content": "Traction control for mobile robots that operate off-road is considered in BIB001 . Based on the geometry of the problem, several simple (unconstrained) closed-form computationally efficient control allocation strategies for wheeled and legged mobile robots with active suspension are derived and compared in BIB001 , while pseudo-inverse type control allocation strategies are studied in BIB002 . A linear programming solution to control allocation for wheeled mobile robots is presented in BIB003 . Nonlinearities, uncertainty and additional complexity in these approaches is to a large extent handled in the low-level controllers at each actuator/effector.", "role": "assistant" } ]

[ { "content": "Evaluate the following claim concerning COVID-19 using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"verdict\": Decide if the abstract supports or contradicts the claim.\n- \"evidence\": List sentences from the abstract that justify your decision.\n\nClaim: High sars-cov-2 viral load is associated with a higher clinical outcome of covid-19 disease.\n\nResearch Abstract:\nThe relationship between SARS-CoV-2 viral load and risk of disease progression remains largely undefined in coronavirus disease 2019 (COVID-19).\nHere, we quantify SARS-CoV-2 viral load from participants with a diverse range of COVID-19 disease severity, including those requiring hospitalization, outpatients with mild disease, and individuals with resolved infection.\nWe detected SARS-CoV-2 plasma RNA in 27% of hospitalized participants, and 13% of outpatients diagnosed with COVID-19.\nAmongst the participants hospitalized with COVID-19, we report that a higher prevalence of detectable SARS-CoV-2 plasma viral load is associated with worse respiratory disease severity, lower absolute lymphocyte counts, and increased markers of inflammation, including C-reactive protein and IL-6.\nSARS-CoV-2 viral loads, especially plasma viremia, are associated with increased risk of mortality.\nOur data show that SARS-CoV-2 viral loads may aid in the risk stratification of patients with COVID-19, and therefore its role in disease pathogenesis should be further explored.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"Amongst the participants hospitalized with COVID-19, we report that a higher prevalence of detectable SARS-CoV-2 plasma viral load is associated with worse respiratory disease severity, lower absolute lymphocyte counts, and increased markers of inflammation, including C-reactive protein and IL-6.\", \"SARS-CoV-2 viral loads, especially plasma viremia, are associated with increased risk of mortality.\"]}", "role": "assistant" } ]

[ { "content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nSince December 2019, coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2, has given rise to emerging respiratory infections with pandemic diffusion. The vitamin D binding protein (DBP) with emphasis on its regulation of total and free vitamin D metabolite levels participate in various clinical conditions. The main goal of this study was to evaluate if there was any association between the DBP gene polymorphism at rs7041 and rs4588 loci and the prevalence of COVID-19 and its mortality rates caused among populations of 10 countries including Turkey. Positive significant correlations were found between the prevalence (per million) and mortality rates (per million), and GT genotype (P < .05) while there was a negative significant correlation between prevalence (per million) and mortality rates (per million), and TT genotype at rs7041 locus among all populations (P < .05). However, no significant correlation was found at rs4588 locus. GT genotype was found to confer this susceptibility to the populations of Germany, Mexico, Italy, Czech, and Turkey. The variations in the prevalence of COVID-19 and its mortality rates among countries may be explained by Vitamin D metabolism differed by the DBP polymorphisms of rs7041 and rs4588.", "role": "user" }, { "content": "[\"Mechanism\"]", "role": "assistant" } ]

[ { "content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nBenzil/triethylamine: a photo-reducing system for Cu2+\n\nContent Extracts:\nIntroduction\n<p>Nanomaterials have experienced a vast growth in interest over the last years. They have been utilized in fields like nonlinear optics and electric conduction [1–3]. Metallic nanoparticles have gained attention because of their remarkable chemical properties, leading to applications, e.g., for molecular imaging [4] or catalysis [5].</p><p>A key point for producing nanoparticles is the reduction of metal salts to elemental metals in a controlled way. Chemical, thermal, radiation-chemical, sonochemical, and photochemical methods have been followed in this context [6–9]. However, many of these approaches require expensive reagents, hazardous reaction conditions, and long reaction times combined with difficult isolation procedures [7, 10]. Photochemical methods offer a valuable access to metal reductions allowing temporal and spatial control [11–18]. In such procedures, organic radical anions, produced by photochemical reduction, act as mediators, reducing metal cations to elementary metals [16, 19].</p><p>A group of reagents often employed in photo-reductions of metal salts include ketones such as acetophenone [11], acetone [20], and benzophenone [21]. The use of ketones combined with hydrocarbons, alcohols, ethers, and amines has been reported [22, 23]. In such reactions, highly reactive ketyl radicals or ketyl radical anions are formed as intermediates. A substantial requirement for the reducing species is their oxidation potential, since it has to match the potential for the reduction of the metal cation. In terms of metals, the generation of Cu nanoparticles from Cu2+ salts has been of prominent interest because of the favorable availability of Cu salts and the activity of Cu as catalyst, in photovoltaics, electronics, and optics [24–27].</p><p>The aim of our investigation is to inspect if benzil (1,2-diphenylethane-1,2-dione, 1) can be utilized for the photo-reduction of Cu2+ salts. Benzil is one of the most common (and low cost) diketones and its photochemistry has been well characterized [28, 29]; nevertheless, benzil has yet only seen limited use in photo-induced redox reactions with metal salts.</p><p>While the photo-reduction of ketones and diketones in the presence of donor systems, e.g., amines, and the intermediate formation of ketyl radicals are well understood, there are still remaining questions with regard to the mechanism of metal reduction. The mechanisms depicted in Scheme 1 have been suggested for the photo-reduction of metal salts. Here, either ketyl radicals [11, 12, 17, 21] or the ketyl radical anions [30] act as electron donors.</p><p>In this publication, we report on the reaction of photo-excited benzil (1) and triethylamine (2) as a model donor with Cu2+ salts. We followed the reactions by steady-state photolysis (SSP), continuous-wave electron paramagnetic resonance (cw-EPR) spectroscopy, and laser-flash photolysis (LFP).</p>\n\n\n<p>UV–Vis spectrum obtained upon photolysis of 1/2 and CuSO4 (a) or CuCl2 (b); the arrows represent the irradiation wavelength (365 nm)</p><p>Time trace of the formation of colloidal copper monitored at 515 nm and 620 nm upon photolysis of the 1/2 system and CuCl2 or CuSO4</p><p>cw-EPR spectrum of 1·− obtained on the reaction of 1/2 in CH3CN under continuous irradiation; experimental (left) and simulation (right)</p><p>Hyperfine coupling constants of 1·− in CH3CN/2</p>\n\nContinuous-wave electron paramagnetic resonance\n<p>The radical cation of 2·+, formed together with 1·−, is not detected in the EPR spectrum. It is well established that radical cations of amines undergo follow-up reactions, leading to both diamagnetic and paramagnetic species [23, 37, 46, 47] (Scheme 4). Besides parent 2, the α-aminoalkyl radical 4 may serve as an electron-donating species [17, 37, 48]. Therefore, an additional reduction of Cu2+ by 4 should be considered when discussing the redox reactions in this system [48]. However, it was shown that 2·+ can undergo rapid follow-up reactions leading to the formation of diamagnetic species [37, 49, 50]. Additionally, product analysis by 1H NMR after irradiation (see Supporting Information) reveals formation of N,N-diethylethenamine (5), further rationalizing that the electron transfer from triethylamine-derived radicals only plays a minor role in this system.</p>\n\n\n<p>Transient absorption spectra of radicals produced by photolysis of 1 in CH3CN (left) and CH3CN/2 0.2 µs after the laser pulse. See text for the assignment of the absorption bands</p>\n\nConclusions\n<p>Our spectroscopic investigation shows that benzil acts as an efficient photo-reducing agent for copper salts in the presence of an amine donor. The efficiency and the rate of the photo-reduction are markedly influenced by the counterions of the copper salts. We have demonstrated the intermediate formation of the benzil radical anion by cw-EPR and LFP. From our experiments, we conclude that 1·−, formed upon photolysis in the presence of 2, is highly redox active and can reduce Cu2+ to Cu0. In addition, no indication that the corresponding radical cation of 2 takes part in the reduction of Cu2+ to Cu0 could be found. This is presumably due to the fast follow-up reaction of 2+·, leading to the formation of diamagnetic products that are not redox active.</p><p>In future work, this cost-effective and simple approach for the photo-induced reduction of Cu2+ to elemental copper could be used for the production of copper nanoparticles by employing different irradiation times as well as characterization methods such as transmission electron microscopy (TEM) to form nanoparticles with defined shape and size [16, 55, 56].</p>\n\nExperimental\n<p>Benzil (1, Fluka), triethylamine (2, Sigma-Aldrich), copper(II) sulfate (Roth), copper(II) chloride (Riedel-de Haën), and acetonitrilie (Riedel-de Haën) were obtained at the highest purity available and employed as received.</p>\n\nSteady-state photolysis\n<p>UV–Vis spectra were recorded on a fiber optic diode array spectrometer (J&M Analytik AG). Photolysis was conducted using a Hamamatsu Lightingcure LC4 (Hg–Xe lamp, 3500 mW/cm2, λmax = 365 nm). The concentrations of 1, CuSO4, and CuCl2 were 5 mM for all measurements. The concentration of 2 was 100 mM in all measurements. Polyvinylpyrrolidone (10 mg) was added to all samples to help solubilize the copper salts and precipitate the formed Cu0.</p>\n\nEPR spectroscopy\n<p>Cw-EPR spectra were recorded on a Bruker X-band spectrometer (EMX, 100 kHz field modulation) at room temperature with 0.025 mT field modulation amplitude. The signals correspond to the steady-state concentration of radicals accumulated in the flow system (0.4 mm quartz flat cell) under continuous irradiation The concentrations of 1 and 2 were 100 and 500 mM, respectively.</p>\n\nLaser-flash photolysis\n<p>LFP experiments were carried out with an LKS80 spectrometer (Applied Photophysics). The excitation of the samples was carried out with the light of a frequency triplet Spitlight Compact 100 (Innolas) Nd:YAG laser at 355 nm (8 ns pulse duration; 10 mJ/pulse energy). The concentration of 1 in solution was adjusted to achieve absorbance of around 0.5 at the excitation wavelength. The concentration of 2 was 100 mM in all measurements.</p>\n\n1H NMR experiments\n<p>1H NMR spectra (32 scans) were recorded on a 200 MHz Bruker Avance DPX spectrometer. Chemical shifts (δ) are reported in ppm relative to tetramethylsilane (TMS) using the residual undeuterated solvent as an internal reference (acetonitrile-d3, δH = 1.94 ppm).</p>\n\n\n<p>Supplementary material 1 (DOCX 233 kb)</p><p>Electronic supplementary material</p><p>The online version of this article (10.1007/s00706-017-2085-7) contains supplementary material, which is available to authorized users.</p>", "role": "user" }, { "content": "AbstractWe have investigated the photo-induced reduction of Cu2+–Cu0 using benzil/triethylamine mixtures. The formation of elemental Cu is indicated by the appearance of its characteristic plasmon absorption peaks at 515 nm and 620 nm. Importantly, the nature of the counterion of the Cu2+ salt affects the reduction process. In the presence of Cl−, the reduction proceeds faster than with SO42-. Photo-induced electron transfer between excited benzil and triethylamine leads to the benzil radical anion, which acts as the reducing agent for Cu2+ and generates Cu0.Graphical abstract Electronic supplementary materialThe online version of this article (10.1007/s00706-017-2085-7) contains supplementary material, which is available to authorized users.", "role": "assistant" } ]

[ { "content": "Analyze the given text and respond to the inquiry. Choose from: \"YES\", \"NO\", or \"MAYBE\".\n\nText:\n(BACKGROUND) Some of the disagreements on the perception of dyspnea (PD) during bronchoconstriction in asthma patients could depend on the interrelationships among the following: (1) the influence of baseline airflow obstruction on the patient's ability to detect any further increase in airway resistance; (2) the effect of eosinophilic inflammation on the airway; (3) bronchial hyperresponsiveness (BHR); and (4) the effect of inhaled corticosteroids (ICSs).\n(OBJECTIVE) We hypothesized that if the inflammation of the airway wall influences to some extent and in some way the PD in asthma patients, ICSs reverse the effect of airway inflammation on the PD.\n(METHODS) We studied 100 asthma patients who were divided into the following four groups: patients with obstruction who were either ICS-naive (group I) or were treated with ICSs (group II); and nonobstructed patients who were either ICS-naive (group III) or were treated with ICSs (group IV). PD on the visual analog scale (VAS) was assessed during a methacholine-induced FEV(1) decrease and specifically was quantified as the VAS slope and score at an FEV(1) decrease of 5 to 20%. BHR was assessed in terms of the provocative concentration of methacholine causing a 20% fall in FEV(1) (PC(20)). Eosinophil counts in induced sputum samples also were performed. Regression analysis, univariate analysis of variance, and factor analysis were applied for statistical evaluation.\n(RESULTS) For a 5 to 20% fall in FEV(1) from the lowest point after saline solution induction, VAS score was lowest in group II, slightly higher in group I, slightly higher still in group IV, and the highest in group III. In the patients as a whole, BHR related to PD, but age, clinical score, duration of the disease, and presence of baseline airway obstruction did not. In patients with obstruction who were treated with ICSs, eosinophil counts related to PD negatively. Factor analysis yielded the following four factors that accounted for 70% of the variance in the data: ICS; eosinophil counts; FEV(1); and PC(20) loaded on separated factors with PD loading on the same factors as PC(20). The post hoc analysis carried out dividing the patients into ICS-treated and ICS-naive, showed that in the former group eosinophil counts and BHR proved to be factors negatively associated with PD, while in the latter group eosinophil counts were positively associated with PD.\n\nInquiry:\nDo inhaled corticosteroids affect perception of dyspnea during bronchoconstriction in asthma?\n\nResponse:", "role": "user" }, { "content": "YES", "role": "assistant" } ]

[ { "content": "Analyze the given text to identify specific entities. Focus on extracting relevant data.\n\nProvide your findings in JSON format. Each category should list the entities found.\n\nText:\n\nIs poor research the cause of the declining productivity of the pharmaceutical industry? An industry in need of a paradigm shift. For the past 20 years target-based drug discovery has been the main research paradigm used by the pharmaceutical industry and billions of dollars have been invested into this approach. However, recent industry data strongly indicate that the target-based approach is not an effective drug discovery paradigm and is likely to be the cause of the productivity crisis the industry is experiencing. However, from a theoretical and scientific perspective the target-based approach appears sound, so why is it not more successful? The purpose of this paper is first to analyse the real-life implementation of the target-based approach to identify possible reasons for the high failure rate and second to suggest changes to the drug discovery approach, which can improve productivity.", "role": "user" }, { "content": "{\"Chemical\": []}", "role": "assistant" } ]

[ { "content": "Analyze the given research paper excerpts and address the question provided. Extract the necessary information directly from the text. Your answer should be formatted as a JSON object with the following structure:\n\n\"answer\": A list of text segments from the paper that directly respond to the question.\n\"evidence\": A list of text segments from the paper where the answer can be found.\n\nIf the question cannot be answered with the given text, return \"null\".\n\nDocument: Mind Your Language: Abuse and Offense Detection for Code-Switched Languages\n\nIn multilingual societies like the Indian subcontinent, use of code-switched languages is much popular and convenient for the users. In this paper, we study offense and abuse detection in the code-switched pair of Hindi and English (i.e. Hinglish), the pair that is the most spoken. The task is made difficult due to non-fixed grammar, vocabulary, semantics and spellings of Hinglish language. We apply transfer learning and make a LSTM based model for hate speech classification. This model surpasses the performance shown by the current best models to establish itself as the state-of-the-art in the unexplored domain of Hinglish offensive text classification.We also release our model and the embeddings trained for research purposes\n\nIntroduction\nWith the penetration of internet among masses, the content being posted on social media channels has uptaken. Specifically, in the Indian subcontinent, number of Internet users has crossed 500 mi, and is rising rapidly due to inexpensive data. With this rise, comes the problem of hate speech, offensive and abusive posts on social media. Although there are many previous works which deal with Hindi and English hate speech (the top two languages in India), but very few on the code-switched version (Hinglish) of the two BIBREF0 . This is partially due to the following reasons: (i) Hinglish consists of no-fixed grammar and vocabulary. It derives a part of its semantics from Devnagari and another part from the Roman script. (ii) Hinglish speech and written text consists of a concoction of words spoken in Hindi as well as English, but written in the Roman script. This makes the spellings variable and dependent on the writer of the text. Hence code-switched languages present tough challenges in terms of parsing and getting the meaning out of the text. For instance, the sentence, “Modiji foreign yatra par hai”, is in the Hinglish language. Somewhat correct translation of this would be, “Mr. Modi is on a foriegn tour”. However, even this translation has some flaws due to no direct translation available for the word ji, which is used to show respect. Verbatim translation would lead to “Mr. Modi foreign tour on is”. Moreover, the word yatra here, can have phonetic variations, which would result in multiple spellings of the word as yatra, yaatra, yaatraa, etc. Also, the problem of hate speech has been rising in India, and according to the policies of the government and the various social networks, one is not allowed to misuse his right to speech to abuse some other community or religion. Due to the various difficulties associated with the Hinglish language, it is challenging to automatically detect and ban such kind of speech.\nThus, with this in mind, we build a transfer learning based model for the code-switched language Hinglish, which outperforms the baseline model of BIBREF0 . We also release the embeddings and the model trained.\n\nMethodology\nOur methodology primarily consists of these steps: Pre-processing of the dataset, training of word embeddings, training of the classifier model and then using that on HEOT dataset.\n\nPre-Processing\nIn this work, we use the datasets released by BIBREF1 and HEOT dataset provided by BIBREF0 . The datasets obtained pass through these steps of processing: (i) Removal of punctuatios, stopwords, URLs, numbers, emoticons, etc. This was then followed by transliteration using the Xlit-Crowd conversion dictionary and translation of each word to English using Hindi to English dictionary. To deal with the spelling variations, we manually added some common variations of popular Hinglish words. Final dictionary comprised of 7200 word pairs. Additionally, to deal with profane words, which are not present in Xlit-Crowd, we had to make a profanity dictionary (with 209 profane words) as well. Table TABREF3 gives some examples from the dictionary.\n\nTraining Word Embeddings\nWe tried Glove BIBREF2 and Twitter word2vec BIBREF3 code for training embeddings for the processed tweets. The embeddings were trained on both the datasets provided by BIBREF1 and HEOT. These embeddings help to learn distributed representations of tweets. After experimentation, we kept the size of embeddings fixed to 100.\n\nClassifier Model\nBoth the HEOT and BIBREF1 datasets contain tweets which are annotated in three categories: offensive, abusive and none (or benign). Some examples from the dataset are shown in Table TABREF4 . We use a LSTM based classifier model for training our model to classify these tweets into these three categories. An overview of the model is given in the Figure FIGREF12 . The model consists of one layer of LSTM followed by three dense layers. The LSTM layer uses a dropout value of 0.2. Categorical crossentropy loss was used for the last layer due to the presence of multiple classes. We use Adam optimizer along with L2 regularisation to prevent overfitting. As indicated by the Figure FIGREF12 , the model was initially trained on the dataset provided by BIBREF1 , and then re-trained on the HEOT dataset so as to benefit from the transfer of learned features in the last stage. The model hyperparameters were experimentally selected by trying out a large number of combinations through grid search.\n\nResults\nTable TABREF9 shows the performance of our model (after getting trained on BIBREF1 ) with two types of embeddings in comparison to the models by BIBREF0 and BIBREF1 on the HEOT dataset averaged over three runs. We also compare results on pre-trained embeddings. As shown in the table, our model when given Glove embeddings performs better than all other models. For comparison purposes, in Table TABREF10 we have also evaluated our results on the dataset by BIBREF1 .\n\nConclusion\nIn this paper, we presented a pipeline which given Hinglish text can classify it into three categories: offensive, abusive and benign. This LSTM based model performs better than the other systems present. We also release the code, the dictionary made and the embeddings trained in the process. We believe this model would be useful in hate speech detection tasks for code-switched languages.\n\nTable 1: Examples of word-pairs in Hinglish-English dictionary\n\nTable 2: Examples of tweets in the dataset and their translations\n\nTable 3: Comparison of accuracy scores on HEOT dataset\n\nTable 4: Comparison of accuracy scores on (Davidson et al. 2017) dataset\n\nFigure 1: LSTM based model for tweet classification\n\nInquiry: What embeddings do they use?", "role": "user" }, { "content": "{\"answer\": [\"Glove\", \"Twitter word2vec\"], \"evidence\": [\"We tried Glove BIBREF2 and Twitter word2vec BIBREF3 code for training embeddings for the processed tweets. The embeddings were trained on both the datasets provided by BIBREF1 and HEOT. These embeddings help to learn distributed representations of tweets. After experimentation, we kept the size of embeddings fixed to 100.\"]}", "role": "assistant" } ]

[ { "content": "Examine the given text from a research paper in the field of NLP. Your task is to identify the role of the citation within the context provided. Focus on understanding the intent behind the citation and classify it accordingly.\n\nSection Title:\nintroduction\n\nText Before Citation:\nIdentical to the standard perceptron proof, e.g., Collins (2002), by inserting in loss-separability for normal separability. Proof. If training is run indefinitely, then m < R2 γ2.\n\nCitation Text:\nIdentical to the standard perceptron proof , e.g. , Collins ( 2002 ) , by inserting in loss-separability for normal separability .\n\nText After Citation:\nLike the original perceptron theorem, this implies that the algorithm will converge. However, unlike the original theorem, it does not imply that it will converge to a parameter vector θ such that for all (x, y) E D, if yˆ = arg maxg θ ·`F(ˆy) then L(ˆy, y) = 0. Even if we assume for every x there exists an output with zero loss, Theorem 1 still makes no guarantees. Consider a training set with one instance (x, y).", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nRecent character and phoneme-based parametric TTS systems using deep learning have shown strong performance in natural speech generation. However, the choice between character or phoneme input can create serious limitations for practical deployment, as direct control of pronunciation is crucial in certain cases. We demonstrate a simple method for combining multiple types of linguistic information in a single encoder, named representation mixing, enabling flexible choice between character, phoneme, or mixed representations during inference. Experiments and user studies on a public audiobook corpus show the efficacy of our approach.\n\nCited Works Summary:\n[1]: We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS) system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in naturalness while training an order of magnitude faster. We scale Deep Voice 3 to dataset sizes unprecedented for TTS, training on more than eight hundred hours of audio from over two thousand speakers. In addition, we identify common error modes of attention-based speech synthesis networks, demonstrate how to mitigate them, and compare several different waveform synthesis methods. We also describe how to scale inference to ten million queries per day on a single GPU server.", "role": "user" }, { "content": "Representation mixing is closely related to the \"mixed-character-and-phoneme\" setting described in Deep Voice 3 [1] , with the primary difference being our addition of the mask embedding @math . We found utilizing a mask embedding alongside the character and phoneme embeddings further improved quality, and was an important piece in the text portion of the network. The focused user study in this paper also highlights the advantages of this kind of mixing independent of high-level architecture choices, since our larger system is markedly different from that used in Deep Voice 3.", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nWe address item relocation problems in graphs in this paper. We assume items placed in vertices of an undirected graph with at most one item per vertex. Items can be moved across edges while various constraints depending on the type of relocation problem must be satisfied. We introduce a general problem formulation that encompasses known types of item relocation problems such as multi-agent path finding (MAPF) and token swapping (TSWAP). In this formulation we express two new types of relocation problems derived from token swapping that we call token rotation (TROT) and token permutation (TPERM). Our solving approach for item relocation combines satisfiability modulo theory (SMT) with conflict-based search (CBS). We interpret CBS in the SMT framework where we start with the basic model and refine the model with a collision resolution constraint whenever a collision between items occurs in the current solution. The key difference between the standard CBS and our SMT-based modification of CBS (SMT-CBS) is that the standard CBS branches the search to resolve the collision while in SMT-CBS we iteratively add a single disjunctive collision resolution constraint. Experimental evaluation on several benchmarks shows that the SMT-CBS algorithm significantly outperforms the standard CBS. We also compared SMT-CBS with a modification of the SAT-based MDD-SAT solver that uses an eager modeling of item relocation in which all potential collisions are eliminated by constrains in advance. Experiments show that lazy approach in SMT-CBS produce fewer constraint than MDD-SAT and also achieves faster solving run-times.\n\nCited Works Summary:\n[1]: We have obtaincd some results in pebble coordination problems and the diameter of permutation groups.\n\n[2]: Abstract The so-called 15-puzzle may be generalized to a puzzle based on an arbitrary graph. We consider labelings or colorings of the vertices and the operation of switching one distinguished label with a label on an adjacent vertex. Starting from a given labeling, iterations of this operation allow one to obtain all, or exactly half, of the labelings on a non-separable graph (with the polygons and one other graph as exceptions).\n\n[3]: The problem of cooperative path-finding is addressed in this work. A set of agents moving in a certain environment is given. Each agent needs to reach a given goal location. The task is to find spatial temporal paths for agents such that they eventually reach their goals by following these paths without colliding with each other. An abstraction where the environment is modeled as an undirected graph is adopted-vertices represent locations and edges represent passable regions. Agents are modeled as elements placed in the vertices while at most one agent can be located in a vertex at a time. At least one vertex remains unoccupied to allow agents to move. An agent can move into unoccupied neighboring vertex or into a vertex being currently vacated if a certain additional condition is satisfied. Two novel scalable algorithms for solving cooperative path-finding in bi-connected graphs are presented. Both algorithms target environments that are densely populated by agents. A theoretical and experimental evaluation shows that the suggested algorithms represent a viable alternative to search based techniques as well as to techniques employing permutation groups on the studied class of the problem.\n\n[4]: An abstraction of a problem of rearranging group of mobile robots is addressed in this paper (the problem of multi-robot path planning). The robots are moving in an environment in which they must avoid obstacles and each other. An abstraction where the environment is modeled as an undirected graph is adopted throughout this work. A case when the graph modeling the environment is bi-connected is particularly studied. This paper puts into a relation the well known problems of moving pebbles on graphs (sliding box puzzles) with problems of multi-robot path planning. Theoretical results gained for problems of pebble motion on graphs are utilized for the development of algorithms for multi-robot path planning. As the opti-mization variant of both problems (a shortest solution is required) is known to be computationally hard (NP-hard), we concentrate on construction of sub-optimal solving procedures. However, the quality of solution is still an objective. Therefore a process of composition of a sub-optimal solution of the problem (a plan) of the pre-calculated optimal plans for the sub-problems (macros) is suggested. The plan composition using macros was inte-grated into two existing sub-optimal solving algorithms. In both cases, substantial improvements of the quality of resulting plans were achieved in comparison to the origi-nal algorithms. The no less important result is that one of the existing algorithms was generalized by integrating macros for larger class of problems of multi-robot path planning.\n\n[5]: Cooperative path-finding can be abstracted as computing non-colliding paths for multiple agents between their start and goal locations on a graph. This paper proposes a fast algorithm that can provide completeness guarantees for a general class of problems without any assumptions about the graph's topology. Specifically, the approach can address any solvable instance where there are at most n-2 agents in a graph of size n. The algorithm employs two primitives: a \"push\" operation where agents move towards their goals up to the point that no progress can be made, and a \"swap\" operation that allows two agents to swap positions without altering the configuration of other agents. Simulated experiments are provided on hard instances of cooperative path-finding, including comparisons against alternative methods. The results are favorable for the proposed algorithm and show that the technique scales to problems that require high levels of coordination, involving hundreds of agents.\n\n[6]: Multi-robot path planning is abstracted as the problem of computing a set of non-colliding paths on a graph for multiple robots. A naive search of the composite search space, although complete, has exponential complexity and becomes computationally prohibitive for problems with just a few robots. This paper proposes an efficient and complete algorithm for solving a general class of multi-robot path planning problems, specifically those where there are at most n-2 robots in a connected graph of n vertices. This paper provides a full proof of completeness. The algorithm employs two primitives: “push”, where a robot moves toward its goal until no progress can be made, and “swap”, that allows two robots to swap positions without altering the position of any other robot. Additionally, this paper provides a smoothing procedure for improving solution quality. Simulated experiments compare the proposed approach with several other centralized and decoupled planners, and show that the proposed technique improves computation time and solution quality, while scaling to problems with 100s of robots, solving them in under 5 seconds.\n\n[7]: The 8-puzzle and the 15-puzzle have been used for many years as a domain for testing heuristic search techniques. From experience it is known that these puzzles are \"difficult\" and therefore useful for testing search techniques. In this paper we give strong evidence that these puzzles are indeed good test problems. We extend the 8-puzzle and the 15-puzzle to a nxn board and show that finding a shortest solution for the extended puzzle is NP-hard and thus computationally infeasible. We also present an approximation algorithm for transforming boards that is guaranteed to use no more than c L (SP) moves, where L (SP) is the length of the shortest solution and c is a constant which is independent of the given boards and their size n.\n\n[8]: Multi-agent Pathfinding is a relevant problem in a wide range of domains, for example in robotics and video games research. Formally, the problem considers a graph consisting of vertices and edges, and a set of agents occupying vertices. An agent can only move to an unoccupied, neighbouring vertex, and the problem of finding the minimal sequence of moves to transfer each agent from its start location to its destination is an NP-hard problem. We present Push and Rotate, a new algorithm that is complete for Multi-agent Pathfinding problems in which there are at least two empty vertices. Push and Rotate first divides the graph into subgraphs within which it is possible for agents to reach any position of the subgraph, and then uses the simple push, swap, and rotate operations to find a solution; a post-processing algorithm is also presented that eliminates redundant moves. Push and Rotate can be seen as extending Luna and Bekris's Push and Swap algorithm, which we showed to be incomplete in a previous publication. In our experiments we compare our approach with the Push and Swap, MAPP, and Bibox algorithms. The latter algorithm is restricted to a smaller class of instances as it requires biconnected graphs, but can nevertheless be considered state of the art due to its strong performance. Our experiments show that Push and Swap suffers from incompleteness, MAPP is generally not competitive with Push and Rotate, and Bibox is better than Push and Rotate on randomly generated biconnected instances, while Push and Rotate performs better on grids.\n\n[9]: An optimization variant of a problem of path planning for multiple robots is addressed in this work. The task is to find spatial-temporal path for each robot of a group of robots such that each robot can reach its destination by navigating through these paths. In the optimization variant of the problem, there is an additional requirement that the makespan of the solution must be as small as possible. A proof of the claim that optimal path planning for multiple robots is NP-complete is sketched in this short paper.\n\n[10]: We study the problem of optimal multi-robot path planning on graphs (MPP) over four distinct minimization objectives: the total arrival time, the makespan (last arrival time), the total distance, and the maximum (single-robot traveled) distance. On the structure side, we show that each pair of these four objectives induces a Pareto front and cannot always be optimized simultaneously. Then, through reductions from 3-SAT, we further establish that computation over each objective is an NP-hard task, providing evidence that solving MPP optimally is generally intractable. Nevertheless, in a related paper, we design complete algorithms and efficient heuristics for optimizing all four objectives, capable of solving MPP optimally or near-optimally for hundreds of robots in challenging setups.\n\n[11]: This paper addresses a problem of path planning for multiple robots. An abstraction where the environment for robots is modeled as an undirected graph with robots placed in its vertices is used (this abstraction is also known as the problem of pebble motion on graphs). A class of the problem with bi-connected graph and at least two unoccupied vertices is defined. A novel polynomial-time solution algorithm for this class of problem is proposed. It is shown in the paper that the new algorithm significantly outperforms the existing state-of-the-art techniques applicable to the problem. Moreover, the performed experimental evaluation indicates that the new algorithm scales up well which make it suitable for practical problem solving.", "role": "user" }, { "content": "Feasible solution of a solvable MAPF instance can be found in polynomial time [2] [1] ; precisely the worst case time complexity of most practical algorithms for finding feasible solutions is @math (asymptotic size of the solution is also @math ) [11] [4] [3] [6] [5] [8] . This is also asymtotically best what can be done as there are MAPF instances requiring @math moves. As with TSWAP, finding optimal MAPF solutions with respect to various cummulative objectives is NP-hard [7] [9] [10] .", "role": "assistant" } ]

[ { "content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nSynthesis and applications of highly functionalized 1-halo-3-substituted bicyclo[1.1.1]pentanes\n\nContent Extracts:\nIntroduction\n<p>Bioisosteres are important motifs in drug design, 1 enabling the expansion of chemical and intellectual property space 2 while also improving biological proles relative to the parent functionality. Bicyclo[1.1.1]pentanes (BCPs) have shown particularly impressive results in this eld as surrogates for 1,4-disubstituted arenes, tertbutyl, and alkyne groups, imparting desirable properties such as membrane permeability, solubility and metabolic stability. 3,4 Examples include BCP analogues of the g-secretase inhibitor BMS-708, 163 (1, Fig. 1a) 5 and resveratrol (2), 6 in which the BCP serves as a bioisostere for a p-substituted arene due to its comparable positioning of substituents; and of the pulmonary arterial hypertension agent bosentan (3, Fig. 1b), where a monosubstituted BCP replaces a tert-butyl group. 7,8 Despite these favourable attributes, access to carbon-substituted BCPs remains a challenge. Their synthesis typically relies on multistep sequences from a small number of available precursors, 9 or requires relatively harsh conditions, 10 necessitating early-stage introduction of the BCP and limiting functional group tolerance.</p><p>The BCP system is most commonly accessed through 'strain release' 11 reactions of tricyclo[1.1.1.0 1,3 ]pentane 4 (TCP), 12 where in addition to classical approaches, 3,13 recent work has seen the development of elegant methods for the synthesis of heteroatom-substituted BCPs. 11,14 The insertion of TCP into C-X bonds would offer an appealing entry to carbon-substituted BCPs, as well as the opportunity for further functionalization of the halide product (5, Fig. 1c). 15 To date however, this process has only been achieved using highly activated reagents (e.g. CF 3 I), 13 or by mercury lamp irradiation of an alkyl or aryl halide, 10d,e or methyllithium-promoted alkyl halide addition. 10b Despite the importance of these contributions, all display limitations in substrate scope, functional group compatibility, or scalability, due to the constraints of the reaction conditions.</p><p>Atom transfer radical addition (ATRA) reactions using chemical initiators are an attractive alternative for TCP ring opening, but previously required a large excess of the radical precursor, or suffered from the formation of oligomeric 'staffane' byproducts due to multiple insertions into TCP. 10d,13 Building on our studies of radical-mediated nucleoside alkynylation, 16 we questioned whether triethylborane could serve as an effective initiator 17 for the synthesis of 1-halo-3-substituted bicyclopentanes (Fig. 1c). Here we report the development of this method as an efficient and highly functional group tolerant route to halogenated BCPs, the utility of which are illustrated through various derivatizations. Importantly, the mild conditions of this chemistry allow the synthesis of bicyclopentanes that could not be accessed using other methods, and open up opportunities for the late-stage functionalization of more complex molecules.</p>\n\nResults and discussion\n<p>We began our studies using ethyl iodoacetate 7a, and were delighted to observe complete reaction in just 15 min at room temperature using 1.3 equivalents of TCP and 10 mol% triethylborane (1 M in hexane), with the product iodide 5a isolated in 83% yield (Table 1, entry 1). A mild exotherm was observed on addition of triethylborane to the reaction, which could be avoided by reducing the temperature (entry 2). The amount of initiator could be decreased to 1 mol% without detriment (entries 2-5), and the quantity of TCP could also be lowered (to 1.1 equiv.), affording 5a in 92% yield (entry 6). Successful reaction was similarly observed using TCP as a solution in dibutyl ether (0.19 M), which is signicant for industrial applications (entry 7). The presence of triethylborane proved crucial, as reactions run in its absence failed to reach completion in the dark or light (entries 8 and 9). 18 Importantly, no staffane byproducts were observed under the optimized conditions (entry 6).</p><p>Use of the equivalent bromoacetate 8a led to incomplete conversion, or signicant staffane formation (entry 10). 19 However, we were pleased to nd that 2-bromo-2-nitropropane 8b underwent rapid reaction with 1.3 equivalents of TCP to afford 6b in 67% yield (entry 11). 20 As with 7a, full conversion was maintained on cooling the reaction to 0 C (73%, entry 12); however, lowering the quantity of triethylborane resulted in incomplete reaction (entry 13). The success of substrate 8b presumably reects a more efficient bromine atom abstraction by the bicyclopentyl radical in the propagation step compared to ester 8a, due to the greater stability of the tertiary nitrosubstituted radical.</p><p>The scope of the triethylborane-initiated ATRA was next explored using organohalides featuring a variety of functional groups (Fig. 2). 21 While the optimized conditions (Table 1, entry 6) translated smoothly to ethyl diuoroiodoacetate, giving bench-stable BCP 5b in 98% yield, 22 incomplete reactions were observed in other cases. To ensure consistency, the substrate screen was therefore conducted using 10 mol% BEt 3 and 1.3-2.0 equivalents of TCP at either 0 C or room temperature, according to the requirements of the substrate. Alkyl iodides showed excellent reactivity, tolerating groups such as hydroxyls and carbamates (5c-e). a-Iodoketones gave high yields across a range of substrates, including heteroaromatics (5f-k). Other electron-withdrawing groups such as amides and sulfones also proved viable (5l-5n), 20 including the sensitive but potentially valuable aldehyde 5o. The formation of 5p is particularly notable due to the potential utility of BCP analogues of amino acids; 23 no racemization was observed in this reaction. Even chloroiodomethane was found to be a suitable substrate, delivering chloromethyl BCP 5q in good yield. Benzyl halides also underwent smooth reaction, providing electronwithdrawing substituents were present on the arene (which presumably accelerates the halide abstraction step from the intermediate BCP radical, 5r-5u). 20 The involvement of radical intermediates was supported by the use of (iodomethyl)cyclopropane, which exclusively gave the ring-opened product 5v.</p><p>Finally, other electron-decient bromides proved suitable partners, affording products 6c-f in short reaction times; for these substrates, the presence of two electron-withdrawing groups proved essential for efficient bromine atom abstraction. While the BCP iodide products are stable towards storage at À20 C (particularly if crystalline), in some cases gradual coloration was observed at ambient temperature. Deiodination was expected to enhance BCP stability, and would simultaneously access the parent phenyl/tert-butyl bioisostere. We questioned whether triethylborane could again be used as initiator for this C-I bond reduction; pleasingly, the use of 1.3 equivalents of tris(trimethylsilyl)silane (TTMSS) as a non-toxic hydrogen atom source 24 and 10 mol% BEt 3 effected smooth deiodination of various BCP iodides (Scheme 1a), giving amide 9l, a BCP analogue of phenylalanine (9p), and triuoroacetate salt 9e, the free base of the latter being a BCP equivalent of the monoaminergic neuromodulator phenethylamine. Given the use of the same initiator for both radical processes, a one-pot reaction sequence was also performed in which BCP 9a was prepared directly from 7a in a single operation (64%). Transformation of the iodide into substituents other than hydrogen was also explored (Scheme 1b): lithiation of 5s, 10b followed by reaction of the resulting organolithium 10 with benzaldehyde or ethyl formate, gave alcohol 11 and aldehyde 12 respectively. Alternatively, transmetalation to the organozinc and crosscoupling with 2-bromopyridine afforded pyridyl BCP 13 (64%). 10a,b Pleasingly, the synthesis of a phenol bioisostere 6 (14) could also be accomplished by a borylation quench, followed by oxidation with sodium perborate.</p><p>The high functional group tolerance and mild reaction conditions suggested that this methodology could be exploited in the functionalization of more complex organic molecules. For example, 2 0 -iodouridine derivative 7w (Scheme 2a) underwent successful ATRA reaction to generate 5w (75%, 5 : 1 dr), with deiodination delivering the 2 0 -deoxy-2 0 -BCP nucleoside 9w (73%). More generally, the availability of iodides from hydroxyl groups provides a multitude of opportunities for bioisostere installation: Appel reaction of the aspartate-serine dipeptide 15 (Scheme 2b) afforded iodide 5x, which on ATRA reaction and subsequent TTMSS reduction generated BCP-functionalized dipeptide 9x. This sequence corresponds to a three step conversion of a serine residue to a potential phenylalanine equivalent, and here delivers a BCP analogue of aspartame. Finally, we targeted application of the methodology to the opioid receptor agonist fentanyl (16, Scheme 2c). Synthesis of its BCP analogue 17 was accomplished from iodotosylate 7y where, pleasingly, the primary alkyl tosylate was tolerated in the initial high-yielding TCP ring-opening (87%). TTMSS-mediated reduction of the iodide product 5y afforded the useful BCP building block 9y, which underwent alkylation with norfentanyl 18 to afford fentanyl analogue 17 (53%). 20 While the mechanism of this C-X addition reaction likely involves a radical pathway, not least due to the cyclopropane ring fragmentation observed in the formation of 5v (Fig. 2), it is not immediately obvious why reaction propagation via halogen atom abstraction should proceed so efficiently, with avoidance of formation. To explore this, we examined the reaction of a-iodoand a-bromomethyl acetate with TCP from a theoretical perspective at the ROM062x/def2tzvp level 25 (Fig. 3, in vacuo). 26 Exergonic addition of the a-carbonyl radical to TCP (A) was found to proceed via transition state AB ‡ (DG ‡ ¼ 12.5 kcal mol À1 ). Reaction of the resultant bicyclopentyl radical B with a-iodoor a-bromomethyl acetate (iodine/bromine atom transfer, BI ‡ /BBr ‡ ), or with TCP (leading to a staffane radical, BS ‡ ), was computed. Predicted activation barriers of 7.3 and 13.3 kcal mol À1 for iodine atom abstraction and TCP capture respectively suggest that the former productive propagation step is signicantly favoured over oligomerization (DDG ‡ ¼ 6.1 kcal mol À1 ). In contrast, a barrier of 12.9 kcal mol À1 for bromine atom abstraction indeed suggests staffane formation to be competitive (DDG ‡ ¼ 0.4 kcal mol À1 ), which is consistent with experimental observations (Table 1), and reects the inuence of C-X bond strength in the propagation phase of the reaction.</p>\n\nConclusions\n<p>In conclusion, we have developed an efficient triethylboranepromoted radical-based method to synthesize 1-halo-3substituted bicyclo[1.1.1]pentanes from readily available iodide and bromide starting materials. The reaction displays broad substrate scope, and functional group compatibility that is not achievable using other methods, enabling application to the functionalization of complex substrates such as nucleosides, peptides and drug-like molecules. The carbon-halogen bond is easily reduced under similarly mild conditions to reveal the parent bioisostere, or functionalized via methods such as Negishi cross-coupling or oxidation. In addition to offering a new entry to highly-functionalized bicyclopentanes, the C-X bond offers much potential for subsequent transformations; investigations to this end are underway.</p>\n\nConflicts of interest\n<p>There are no conicts to declare.</p>", "role": "user" }, { "content": "Bicyclo[1.1.1]pentanes (BCPs) are important bioisosteres of 1,4-disubstituted arenes, tert-butyl and acetylenic groups that can impart physicochemical benefits on drug candidates. Here we describe the synthesis of BCPs bearing carbon and halogen substituents under exceptionally mild reaction conditions, via triethylborane-initiated atom-transfer radical addition ring-opening of tricyclo[1.1.1.0 1,3 ]pentane (TCP) with alkyl halides. This chemistry displays broad substrate scope and functional group tolerance, enabling application to BCP analogues of biologically-relevant targets such as peptides, nucleosides, and pharmaceuticals. The BCP halide products can be converted to the parent phenyl/tert-butyl surrogates through triethylborane-promoted dehalogenation, or to other derivatives including carbonyls, alcohols, and heterocycles.", "role": "assistant" } ]

[ { "content": "Analyze the provided clinical trial criteria. Identify and extract distinct entities from the text.\n\nReturn the results as a JSON structure. Ensure the output is strictly in JSON format without any additional commentary.\n\nCriteria Text:\n\n(1) cases of infertility, older than 20 years of age and not older than 40 years.\n(2) Body mass index (BMI):20-29.\n(3) women have experienced two or more implantation failure attributed to inadequate endometrial development.", "role": "user" }, { "content": "{\"Condition\": [\"infertility\", \"inadequate endometrial development\"], \"Device\": [], \"Drug\": [], \"Measurement\": [\"BMI\", \"Body mass index\"], \"Mood\": [\"attributed to\"], \"Multiplier\": [\"two or more\"], \"Negation\": [], \"Observation\": [], \"Person\": [\"women\", \"age\"], \"Procedure\": [\"implantation\"], \"Qualifier\": [\"failure\"], \"ReferencePoint\": [], \"Scope\": [], \"Temporal\": [], \"Value\": [\"20-29\", \"older than 20 years\", \"not older than 40 years\"], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Analyze the provided clinical trial criteria. Identify and extract distinct entities from the text.\n\nReturn the results as a JSON structure. Ensure the output is strictly in JSON format without any additional commentary.\n\nCriteria Text:\n\nLeft main disease\nKnown hypersensitivity or contraindication to any of the following medications: Heparin, aspirin, clopidogrel, sirolimus, siptagliptin and statin\nCongestive heart failure (patients with LVEF <30% or cardiogenic shock)\nUncontrolled myocardial ischemia (repeated chest pain or dyspnea after revascularization)\nUncontrolled ventricular arrhythmia\nHistory of malignancy with chemotherapy\nSerious hematologic disease (e.g. CML, MDS)\nCurrent infectious disease needs antibiotics therapy\nCreatinine level >1.5 mg/dL or dependence on dialysis\nOther severe concurrent illness (e.g. active infection, malignancy).\nLife expectancy of less than one year\nPregnancy or women with potential childbearing\nType I DM\nTreatment with insulin\nHistory of pancreatitis\nWho cannot read the informed consent form (e.g. illiteracy, foreigner)", "role": "user" }, { "content": "{\"Condition\": [\"hypersensitivity\", \"active infection\", \"malignancy\", \"CML\", \"dyspnea\", \"myocardial ischemia\", \"chest pain\", \"cardiogenic shock\", \"pancreatitis\", \"Left main disease\", \"illness\", \"Type I DM\", \"hematologic disease\", \"ventricular arrhythmia\", \"contraindication\", \"Congestive heart failure\", \"infectious disease\", \"MDS\"], \"Device\": [], \"Drug\": [\"clopidogrel\", \"antibiotics\", \"siptagliptin\", \"insulin\", \"aspirin\", \"statin\", \"sirolimus\", \"Heparin\"], \"Measurement\": [\"Creatinine level\", \"LVEF\"], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [\"ife expectancy\"], \"Person\": [], \"Procedure\": [\"revascularization\", \"chemotherapy\", \"dialysis\"], \"Qualifier\": [\"concurrent\", \"repeated\", \"severe\", \"Uncontrolled\", \"Serious\"], \"ReferencePoint\": [\"revascularization\"], \"Scope\": [\"Heparin, aspirin, clopidogrel, sirolimus, siptagliptin and statin\", \"chest pain or dyspnea\", \"VEF \\u003c30% or cardiogenic shock\", \"active infection, malignancy\", \"CML, MDS\", \"hypersensitivity or contraindication\"], \"Temporal\": [\"after revascularization\"], \"Value\": [\"\\u003e1.5 mg/dL\", \"less than one year\", \"\\u003c30%\"], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: Feed-forward convolutional neural networks are state-of-the-art for object classification tasks such as\n\nKeywords: object classification images\n\nDataset Information:\nTHEODORE: Recent work about synthetic indoor datasets from perspective views has shown significant improvements of object detection results with Convolutional Neural Networks(CNNs). In this paper, we introduce THEODORE: a novel, large-scale indoor dataset containing 100,000 high- resolution diversified fisheye images with 14 classes.\nImageNet: The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection.\nNVGesture: The NVGesture dataset focuses on touchless driver controlling. It contains 1532 dynamic gestures fallen into 25 classes.\nANLI: The Adversarial Natural Language Inference (ANLI, Nie et al.) is a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure.\n\nAvailable Datasets: A: THEODORE B: ImageNet C: NVGesture D: ANLI", "role": "user" }, { "content": "ImageNet", "role": "assistant" } ]

[ { "content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nA 31-year-old man developed diarrhea, fatigue, and intermittent fever for 2 weeks. The past few days he had experienced increasing dyspnea and dry cough. Ambulatory reverse transcriptase-polymerase chain reaction testing was positive for SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2). Because of elevated D-dimer (1.5 mg/L), a lung scintigraphy (V/Q scan) was performed as SPECT/CT. Ventilation SPECT showed reduced ventilation with central nuclide deposition, whereas perfusion SPECT was inconspicuous, excluding pulmonary embolism. However, the low-dose CT revealed bilateral ground-glass opacities as previously described in COVID-19. This case highlights the procedure and findings of V/Q scanning (without embolism) in COVID-19.", "role": "user" }, { "content": "[\"Case Report\"]", "role": "assistant" } ]

[ { "content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nScientists hypothesized that drugs such as ibuprofen or renin-angiotensin system (RAS) blockers could exacerbate the novel coronavirus disease COVID-19 by upregulating the angiotensin-converting enzyme 2 (ACE2), which serves as an entry receptor for the coronavirus SARS-CoV-2. This hypothesis was taken up by the lay press and led to concerns among doctors and patients whether the use of these drugs was still safe and justified against the background of the pandemic spread of SARS-CoV-2 with an increasing number of cases and deaths. In this article, we summarize what is known about the effect of RAS blockers or non-steroidal anti-inflammatory drugs (NSAIDs) on the course of COVID-19 disease. In the case of RAS inhibition, we also find evidence for the opposite hypothesis, namely, that RAS inhibition in COVID-19 could be protective. In view of the inconsistent and limited evidence and after weighing up the benefits and risks, we would not currently recommend discontinuing or switching an effective treatment with RAS blockers. NSAIDs should be used at the lowest effective dose for the shortest possible period. The choice of drug to treat COVID-19-associated fever or pain should be based on a benefit-risk assessment for known side effects (e.g., kidney damage, gastrointestinal ulceration).", "role": "user" }, { "content": "[\"Treatment\", \"Mechanism\"]", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nComparison of remifentanil with fentanyl for deep sedation in oral surgery . PURPOSE The aim of this study was to compare recovery for oral surgery patients given a deep sedation regimen of midazolam , propofol , and remifentanil with a standard control of fentanyl in place of remifentanil . MATERIALS AND METHODS This investigation was designed as a randomized , prospective , single-blinded controlled study . Group 1 , the control , received midazolam 0.03 mg/kg , fentanyl 1 microg/kg , and propofol initially at 140 microg/kg/min . Group 2 received midazolam 0.03 mg/kg , remifentanil : propofol ( 1:500 ) given at an initial propofol infusion rate of 40 microg/kg/min . Outcome measures included time to response to verbal command , Aldrete score = 9 , Postanesthesia Discharge Scoring System = 7 , and assessment by the Digit Symbol Substitution Test . RESULTS Forty-seven subjects were entered in the study . Baseline findings were homogenous between the 2 groups . Subjects in group 2 recovered earlier ( P < .005 ) and required less propofol for both the induction ( 0.8 +/- 0.4 versus 1.2 +/- 0.6 mg/kg ; mean +/- SD , P < .01 ) and maintenance of deep sedation ( 46 +/- 9 versus 131 +/- 17 microg/kg/min ; P < .005 ) . There were minor differences in vital signs . CONCLUSIONS This study demonstrated that this remifentanil regimen provided significantly more rapid recovery and used significantly less propofol compared with the fentanyl regimen .", "role": "user" }, { "content": "{\"Intervention\": [\"midazolam 0.03 mg/kg\", \"propofol\", \"remifentanil\", \"midazolam , propofol\", \"fentanyl 1 microg/kg\", \"fentanyl\", \"propofol initially at 140 microg/kg/min .\", \"midazolam 0.03 mg/kg , remifentanil : propofol ( 1:500 ) given at an initial propofol infusion rate of 40 microg/kg/min .\"], \"Outcome\": [\"rapid recovery\", \"= 9\", \"Aldrete score\", \"induction\", \"Postanesthesia Discharge Scoring System = 7\", \"maintenance of deep sedation\", \"time to response to verbal command\", \"deep sedation\", \"assessment by the Digit Symbol Substitution Test\"], \"Participant\": [\"oral surgery patients\", \"Forty-seven subjects were entered in the study .\"]}", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nRelativetranscriptlevelswereestimatedusingreal-timePCRaccordingtoAppliedBiosystems'protocols,withmagnesiumconcentration,primerpairandfluorescentprobegiveninAdditionaldatafile2.", "role": "user" }, { "content": "[\"magnesium\", \"fluorescent probe\"]", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nProlonged sirolimus administration after allogeneic hematopoietic cell transplantation is associated with decreased risk for moderate-severe chronic graft-versus-host disease . Effective pharmacological strategies employed in allogeneic hematopoietic cell transplantation should prevent serious chronic graft-versus-host disease and facilitate donor-recipient immune tolerance . Based on demonstrated pro-tolerogenic activity , sirolimus ( rapamycin ) is an agent with promise to achieve these goals . In a long-term follow-up analysis of a randomized phase II trial comparing sirolimus/tacrolimus versus methotrexate/tacrolimus for graft-versus-host disease prevention in matched sibling or unrelated donor transplant , we examined the impact of prolonged sirolimus administration ( ≥ 1 year post-transplant ) . Median follow-up time for surviving patients at time of this analysis was 41 months ( range 27-60 ) for sirolimus/tacrolimus and 49 months ( range 29-63 ) for methotrexate/tacrolimus . Sirolimus/tacrolimus patients had significantly lower National Institutes of Health Consensus moderate-severe chronic graft-versus-host disease ( 34 % vs. 65 % ; P=0.004 ) and late acute graft-versus-host disease ( 20 % vs. 43 % ; P=0.04 ) . While sirolimus/tacrolimus patients had lower prednisone exposure and earlier discontinuation of tacrolimus ( median time to tacrolimus discontinuation 368 days vs. 821 days ; P=0.002 ) , there was no significant difference in complete immune suppression discontinuation ( 60-month estimate : 43 % vs. 31 % ; P=0.78 ) . Prolonged sirolimus administration represents a viable approach to mitigate risk for moderate-severe chronic and late acute graft-versus-host disease . Further study of determinants of successful immune suppression discontinuation is needed .", "role": "user" }, { "content": "{\"Intervention\": [\"methotrexate/tacrolimus\", \"sirolimus ( rapamycin )\", \"sirolimus/tacrolimus\", \"sirolimus\"], \"Outcome\": [\"chronic graft-versus-host disease .\", \"lower prednisone exposure\", \"lower National Institutes of Health Consensus moderate-severe chronic graft-versus-host disease\", \"post-transplant ) .\", \"in complete immune suppression discontinuation\", \"earlier discontinuation of tacrolimus\", \"Median follow-up time for surviving patients\", \"and late acute graft-versus-host disease\"], \"Participant\": [\"allogeneic hematopoietic cell transplantation\"]}", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nWhen describing images with natural language, the descriptions can be made more informative if tuned using downstream tasks. This is often achieved by training two networks: a \"speaker network\" that generates sentences given an image, and a \"listener network\" that uses them to perform a task. Unfortunately, training multiple networks jointly to communicate to achieve a joint task, faces two major challenges. First, the descriptions generated by a speaker network are discrete and stochastic, making optimization very hard and inefficient. Second, joint training usually causes the vocabulary used during communication to drift and diverge from natural language. We describe an approach that addresses both challenges. We first develop a new effective optimization based on partial-sampling from a multinomial distribution combined with straight-through gradient updates, which we name PSST for Partial-Sampling Straight-Through. Second, we show that the generated descriptions can be kept close to natural by constraining them to be similar to human descriptions. Together, this approach creates descriptions that are both more discriminative and more natural than previous approaches. Evaluations on the standard COCO benchmark show that PSST Multinomial dramatically improve the recall@10 from 60 to 86 maintaining comparable language naturalness, and human evaluations show that it also increases naturalness while keeping the discriminative power of generated captions.\n\nCited Works Summary:\n[1]: \n\n[2]: We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.\n\n[3]: Providing systems the ability to relate linguistic and visual content is one of the hallmarks of computer vision. Tasks such as image captioning and retrieval were designed to test this ability, but come with complex evaluation measures that gauge various other abilities and biases simultaneously. This paper presents an alternative evaluation task for visual-grounding systems: given a caption the system is asked to select the image that best matches the caption from a pair of semantically similar images. The system's accuracy on this Binary Image SelectiON (BISON) task is not only interpretable, but also measures the ability to relate fine-grained text content in the caption to visual content in the images. We gathered a BISON dataset that complements the COCO Captions dataset and used this dataset in auxiliary evaluations of captioning and caption-based retrieval systems. While captioning measures suggest visual grounding systems outperform humans, BISON shows that these systems are still far away from human performance.", "role": "user" }, { "content": "Beyond the naturalness of communication, several studies looked into the problem of generating captions that allow discriminating an image from other similar images. [2] showed how captions can take into account a distractor image at inference time and create a caption that discriminates a target image from a distractor image. A similar approach was taken earlier by [1] . [3] recently described a dataset that contains pairs of closely similar images, that can be used as hard-negatives for evaluating image retrieval tasks.", "role": "assistant" } ]

[ { "content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: Smart Cities: A Survey on Security Concerns \nChapter Title: IoT \n1. Abstract of Cited Paper (BIB001): At present, \"Smart Grid\" emerged to be one of the best advanced energy supply chain. This paper looks into the security system of Smart Grid via Smart Planet system. The scope focused onto information security criteria that impacts consumer trust and satisfaction. The importance of information security criteria is the main aspect perceived to impact customer trust towards the entire smart grid system. On one hand, it also focused on the selection of the model in developing information security criteria on smart grid. \n2. Abstract of Cited Paper (BIB002): Based on the “digital city”, “smart city” is widely used in daily livelihood, environmental protection, public security, city services and other fields. In this paper, we mainly focus on recent research and the concept of “smart city”, summarizing the relationship between \"smart city\" and \"digital city\", putting forward the main content of application systems as well as the importance and difficulty of the construction of “smart city”, and making a brief statement of the influence of developing smart city in China. \n3. Abstract of Cited Paper (BIB003): Throughout the evolution of cities, the very structure of what defines a city has been changing. There has been a huge amount of advancement from the ancient settlements to modern metropolitans and now the next step in the evolution of cities is here - smart cities. Smart cities have come up to counter act the ills of the industrial cities that produce a many bad side effects. Smart cities have been known to be environment friendly, better organized, have better mobility, and a more competent economy. In meeting these necessary objectives, the role of software can make the smart city more integrated and functional as a whole. But the use of smart software, as we call it, can pose problems pertaining to the security and integrity of the smart city's data and privacy. Therefore the need arises to understand and evaluate the concerns of security and privacy that come up with smart software before they can be used in full scale. This paper concentrates on these issues. \n4. Abstract of Cited Paper (BIB004): With the distributed sensors that are deployed to monitor ::: the urban environment in smart cities, the sensed data are ::: overwhelming and beyond the scope of the wireless sensor ::: networks (WSNs) capability. Due to the communication range ::: limits of the sensors, most of these data will be outsourced and ::: stored on some untrusted servers. Thus, how to maintain the ::: data confidentiality and integrity, as well as source authentication ::: and data query privacy of the outsourced data, is a challenging ::: problem. In this paper, we propose a secure searchable encryption ::: scheme, named SSE, for urban sensing and querying to address ::: the problem. Specifically, our SSE constructs a secure hidden ::: vector encryption-(HVE-) based rang query predicate. The sensed ::: data can be stored on an untrusted server in encrypted form. A ::: requester can obtain the correct ciphertexts when his authorized ::: range query matches the HVE-based encryption predicate. With ::: the help of the base station, the ciphertexts can be decrypted ::: and data integrity can be verified; then, the requester can obtain ::: the correct original data. Security analysis demonstrates that; in ::: the SSE, only the authorized requesters can obtain the query ::: results, while the data confidentiality and integrity and source ::: authentication are also preserved. \n5. Abstract of Cited Paper (BIB005): Cloud Computing and Internet of Things (IoT) are currently two of the most popular ICT paradigms that are expected to shape the next era of computing. The convergence between cloud computing and IoT has become a hot topic over the last few years because of the benefits that IoT could have from the distributed nature of cloud computing infrastructures. This paper proposes a new platform for using cloud computing capacities for provision and support of ubiquitous connectivity and real-time applications and services for smart cities' needs. We present a framework for data procured from highly distributed, heterogeneous, decentralized, real and virtual devices (sensors, actuators, smart devices) that can be automatically managed, analyzed and controlled by distributed cloud-based services. \n6. Abstract of Cited Paper (BIB006): Cities are growing steadily, and the process of urbanization is a common trend in the world. Although cities are getting bigger, they are not necessarily getting better. With the aim to provide citizens with a better place to live, a new concept of a city was born: the smart city. The real meaning of smart city is not strictly defined, but it has gained much attention, and many cities are taking action in order to be considered 'smart'. These smart cities, founded on the use of information and communication technologies, aim at tackling many local problems, from local economy and transportation to quality of life and e-governance. Although technology helps to solve many of these local problems, their ability to gather unprecedented amounts of information could endanger the privacy of citizens. In this article we identify a number of privacy breaches that can appear within the context of smart cities and their services. We leverage some concepts of previously defined privacy models and define the concept of citizens' privacy as a model with five dimensions: identity privacy, query privacy, location privacy, footprint privacy and owner privacy. By means of several examples of smart city services, we define each privacy dimension and show how existing privacy enhancing technologies could be used to preserve citizens' privacy. \n7. Abstract of Cited Paper (BIB007): The possibility of so-called 'smart' technologies to improve city life has filled both pages of concern and PR leaflets. While the corporations driving these developments have emphasized how smart technologies can improve efficiency, critics have warned against the risks associated with the proliferation of smart surveillance. However, a critical discourse about the potential, limits and risks of the proliferation of smart technologies has not yet emerged, and in most instances public officials and decision-makers are ill-equipped to judge both the value and the externalities of the technologies being sold under the label 'smart cities'. This paper presents a summary of smart solutions and definitions, and draws on the surveillance literature to address issues and risks related to the global drive to outsmart competing cities in a context of global governance. Using a multi-faceted and multi-disciplinary approach, it aims to provide a starting point for a public debate that involves policy-makers, developers and academics. Copyright The Author 2013. Published by Oxford University Press. All rights reserved. For Permissions, please email: [email protected], Oxford University Press. \n8. Abstract of Cited Paper (BIB008): ‘Smart cities’ is a term that has gained traction in academia, business and government to describe cities that, on the one hand, are increasingly composed of and monitored by pervasive and ubiquitous computing and, on the other, whose economy and governance is being driven by innovation, creativity and entrepreneurship, enacted by smart people. This paper focuses on the former and, drawing on a number of examples, details how cities are being instrumented with digital devices and infrastructure that produce ‘big data’. Such data, smart city advocates argue enables real-time analysis of city life, new modes of urban governance, and provides the raw material for envisioning and enacting more efficient, sustainable, competitive, productive, open and transparent cities. The final section of the paper provides a critical reflection on the implications of big data and smart urbanism, examining five emerging concerns: the politics of big urban data, technocratic governance and city development, corporatisation of city governance and technological lock-ins, buggy, brittle and hackable cities, and the panoptic city. \n9. Abstract of Cited Paper (BIB009): The world is experiencing an evolution of Smart Cities. These emerge from innovations in information technology that, while they create new economic and social opportunities, pose challenges to our security and expectations of privacy. Humans are already interconnected via smart phones and gadgets. Smart energy meters, security devices and smart appliances are being used in many cities. Homes, cars, public venues and other social systems are now on their path to the full connectivity known as the “Internet of Things.” Standards are evolving for all of these potentially connected systems. They will lead to unprecedented improvements in the quality of life. To benefit from them, city infrastructures and services are changing with new interconnected systems for monitoring, control and automation. Intelligent transportation, public and private, will access a web of interconnected data from GPS location to weather and traffic updates. Integrated systems will aid public safety, emergency responders and in disaster recovery. We examine two important and entangled challenges: security and privacy. Security includes illegal access to information and attacks causing physical disruptions in service availability. As digital citizens are more and more instrumented with data available about their location and activities, privacy seems to disappear. Privacy protecting systems that gather data and trigger emergency response when needed are technological challenges that go hand-in-hand with the continuous security challenges. Their implementation is essential for a Smart City in which we would wish to live. We also present a model representing the interactions between person, servers and things. Those are the major element in the Smart City and their interactions are what we need to protect. \n10. Abstract of Cited Paper (BIB010): Smart cities accumulate and process large amount of data streams which raise security and privacy concerns at individual and community levels. Sizeable attempts have made to ensure security and privacy of inhabitants' data. However, security and privacy issues of smart cities are not confined to inhabitants only, service provider and local government have their own reservations -- service provider trust, reliability of the sensed data, and data ownership, to name a few. In this research work we identified a comprehensive list of stakeholders and model their involvement in smart cities by using Onion Model approach. Based on the stakeholder model we presented a security and privacy framework for secure and privacy-aware service provisioning in smart cities. Our framework aims to provide end-to-end security and privacy features for trustable data acquisition, transmission, processing and legitimate service provisioning. As a proof of concept we tested core functionalities of authentication protocol for data acquisition and service provisioning using Scyther automated verification tool that demonstrated that the proposed framework mitigates security and privacy concerns of different stakeholders identified in the stakeholder model.\n\nReview Chapter:", "role": "user" }, { "content": "A very important factor that plays key role in developing a smart city is \"big data\". The production of large data sets in a smart city is an inevitable phenomenon including national consensuses, government records, and other information about the citizens BIB009 . From such data, the smart cities can extract very important information helping real time analysis and ubiquitous computing. The author in paper elaborates that though the big data provides various opportunities for smarter life, still it brings challenges of security and privacy. The challenges include lack of tools for management of big data, third party data sharing, threats in growing public databases, data leakage and concerns on digital security. In another paper, the cyber security challenges are addressed BIB010 . Here the authors focus on two main challenges, security and privacy. They present a mathematical model depicting the interaction between people, IoT, and servers which are vulnerable to information security threats. Though the mathematical and graphical model for the IoT, people and servers is given stating that it will help in locating the problems in security and privacy, but the methodology to do so is not discussed. Moreover, Bohli et al propose a distributed framework for IoT applications, which promises security, trust and privacy in information delivery. As IoT applications play a key role on building the smarter city, so some information security issues in a smart city can be addressed through the distributive framework. The identification and classification of stakeholders of a smart city help in addressing the security problems in smart city in a better way. In this paper BIB011 all the concerned stakeholders regarding the security and privacy of information are identified by using onion model approach. The authors proposed that by identifying all the stakeholders, the security requirements and issues are identified in a better way. They also propose a comprehensive framework to deal with these issues. In BIB004 the role of smart software is discussed in context of information security. The role of smart software in developing a smarter city is discussed specifically throwing light upon limitations regarding security issues. Certain security software models are also discussed. Another paper discusses the issue of security problems in sensing and querying in urbanization BIB005 . The authors propose an encryption scheme to deal with the issues of data integrity and privacy. Smart grids are considered an important component of a smart city as they provide the services of very novel and efficient energy supply chain and information management BIB001 . In BIB002 the authors discuss the information security issues in a smart grid. The requirements of information security are identified by the authors and various models are discussed and compared regarding the concerned issues with methodologies. Sanjay Goel in his paper discuss the relationship between anonymity and security thus proving that there is a need of balance between anonymity and security in smart grids. The author then proposes a new idea for designing Internet in a way that security issues are dealt in a better way. The restructuring of Internet seems an interesting idea as author believes that redesigning and creation of multiple Internets with attempt to have a balance and anonymity can create a difference. The paper BIB003 describes the main application systems for a smart city, and discuss various problem issues in constructing a smart city, particularly in China. Though the authors have discussed many hurdles in developing a smart city, but the information security issue has been overlooked and not been discussed by authors specifically. Suciu et al BIB006 propose that by defining the platform of cloud computing and IoT properly for a smart city, better security can be achieved. For that, they have proposed a framework for the information that can be automatically be managed by the distributed cloud computing services. The privacy concerns of a common citizen of a smart city also need to be discussed. For example in BIB007 the privacy issues of citizens of a smart city are analyzed. This includes five dimensions according to the authors: identity privacy, query privacy, location privacy, footprint privacy and owner privacy. They propose a 5D model that addresses these five issues. The authors conclude that by following the model, privacy aware smart city is achievable. The credibility of a smart city is questioned by GaldonClavell and Gemma BIB008 particularly on various problem areas in the implementation of smart cities, including security and privacy in context of individuals as well as institutions and governments. They describe the smart solutions and elaborate the issues regarding the implementation of such solutions. They propose is that by understanding the problem areas efficiently, smarter cities can be built. The issue of privacy is also discussed in where the authors provide the issues and problem areas in trace analysis and mining for the smart cities. They conclude that though data mining and trace analysis play a key role in smart cities, still it is a challenging task to be done keeping in mind the privacy concerns and usage of limited and relevant data only.", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\na 76-year - old female presented to the emergency department with the main complaint of 7 days of dyspnea and 1 day of dysarthria and dizziness .\nauscultation findings showed an irregular heart beat with a diastolic rumbling murmur in the apical region and crackles in both lower lung fields .\ntransthoracic echocardiography showed a moderate degree of aortic regurgitation with left ventricular ( lv ) ejection fraction of 70.8% and a 1.631.31-cm complex , echogenic , round , mass - like lesion attached to the left atrial side of the interatrial septum .\ntransesophageal echocardiography revealed the same mass finding with prominent spontaneous echo contrast in the left atrium and decreased emptying velocity of the left atrial appendage ( fig .\n2 ) . the diagnostic coronary angiogram revealed a round , movable mass lesion in the left atrium with feeding arteries originating from the conus branch and atrioventricular nodal artery of the right coronary artery and no significant stenosis in either coronary artery ( fig .\n3 ) . the patient was transferred to cardiac surgery and underwent removal of the mass and a maze operation .\nmacroscopic findings were compatible with myxoma , and the microscopic findings revealed an acid mucopolysaccharide - rich stroma composed of a myxoid matrix and polygonal cells with scant eosinophilic cytoplasm scattered throughout the matrix ( fig .\n4 ) . after surgery , the atrial fibrillation was abolished and an electrocardiogram showed a normal sinus rhythm .\nfollow - up transthoracic echocardiography was performed after surgery and no remnant mass was observed in the left atrium ( fig .\n, the patient is admitted to outpatient department regularly and has taken aspirin and angiotensin receptor blocker steadily without specific problems .\nthe presence of possible tumor vessels originating from coronary arteries may be helpful in the decision on an operative strategy for cardiac myxoma . about 52% of cardiac myxoma is visualized by coronary angiograms according to previous reports , but catheterization of the chamber from which the tumor arises carries the risk of tumor embolization .", "role": "user" }, { "content": "a 76-year - old female present to the emergency department with dysarthria , dizziness , dyspnea . \n the patient had hypertension and atrial fibrillation . \n brain mri revealed right cerebellar infarction . \n transthoracic echocardiography showed a large round mass in the left atrium . \n transesophageal echocardiography showed large complex echogenic round mass lesion attached on left atrial side of interatrial septum . \n coronary angiogram revealed round movable mass lesion in left atrium with feeding arteries originated from right coronary artery . \n she underwent removal of mass and maze operation , and pathologic finding was compatible with myxoma .", "role": "assistant" } ]

[ { "content": "Consider the following research inquiry and associated key terms. Review the dataset summaries provided and determine which datasets are suitable for addressing the research question. Base your decision on your understanding of machine learning datasets.\nProvide your answer as a JSON list. For example, for the inquiry \"Semi supervised image classification\", a possible response could be: [\"CIFAR-10\", \"CIFAR-100\"]. Ensure the response contains only the dataset names in JSON format.\n\nResearch Inquiry: I want to study biases in the [DATASET] dataset and propose a\n\nKey Terms: visual question answering videos, subtitles, scripts\n\nDataset Summaries:\nTVQA: The TVQA dataset is a large-scale vido dataset for video question answering. It is based on 6 popular TV shows (Friends, The Big Bang Theory, How I Met Your Mother, House M.D., Grey's Anatomy, Castle).\nDialogueFairness: The Dialogue Fairness dataset is used to evaluate and understand fairness in dialogue models, focusing on gender and racial biases.\nFGADR: This dataset has 1,842 images with pixel-level DR-related lesion annotations, and 1,000 images with image-level labels graded by six board-certified ophthalmologists with intra-rater consistency. The proposed dataset will enable extensive studies on DR diagnosis.\nMovieQA: The MovieQA dataset is a dataset for movie question answering. to evaluate automatic story comprehension from both video and text.\nI-HAZE: The I-Haze dataset contains 25 indoor hazy images (size 2833×4657 pixels) training. It has 5 hazy images for validation along with their corresponding ground truth images.\nOpenEDS: OpenEDS (Open Eye Dataset) is a large scale data set of eye-images captured using a virtual-reality (VR) head mounted display mounted with two synchronized eyefacing cameras at a frame rate of 200 Hz under controlled illumination. This dataset is compiled from video capture of the eye-region collected from 152 individual participants and is divided into four subsets: (i) 12,759 images with pixel-level annotations for key eye-regions: iris, pupil and sclera (ii) 252,690 unlabelled eye-images, (iii) 91,200 frames from randomly selected video sequence of 1.5 seconds in duration and (iv) 143 pairs of left and right point cloud data compiled from corneal topography of eye regions collected from a subset, 143 out of 152, participants in the study.\nBAR: Biased Action Recognition (BAR) dataset is a real-world image dataset categorized as six action classes which are biased to distinct places. The authors settle these six action classes by inspecting imSitu, which provides still action images from Google Image Search with action and place labels.\n\nDataset Options: A: TVQA B: DialogueFairness C: FGADR D: MovieQA E: I-HAZE F: OpenEDS G: BAR", "role": "user" }, { "content": "[\"TVQA\", \"MovieQA\"]", "role": "assistant" } ]

[ { "content": "Examine the provided text and determine the interactions between chemical entities and genes. Focus on identifying any connections present.\n\nPresent your findings in a structured JSON format. Each relationship should be represented as an array entry. If no interactions are detected, return an empty array.\n\nText Content:\n\n[ Psychopharmacological profile of venlafaxine ]. Venlafaxine is an antidepressant which blocks reuptake of noradrenaline and serotonin and, to a lesser extent, dopamine. These data have been confirmed by behavioral tests. It has been shown that by decreasing the overall cerebral quantity of 5-HT and NA, venlafaxine continued to have an antidepressant action in animal models. In addition, the drug has been shown to act preferentially on 5-HT1A and 5-HT1B receptors.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Analyze the provided paragraph from a scientific document. Your goal is to identify and extract relevant entities.\n\nFormat your findings as a JSON object, where each key represents a category of entities, and the corresponding value is a list of entities identified in that category. If no entities are found for a category, return an empty list.\n\nFocus on precision and ensure that the output is strictly in JSON format.\n\nDocument:\n\nThe bumper technique for advancing a large profile microcatheter Operators commonly encounter difficulty maneuvering a microcatheter beyond the distal lip of wide neck aneurysms and aneurysms in challenging locations. Few techniques have been described to guide operators in these particular situations. In this case report of a 56- year -old woman with a 16 mm ophthalmic artery aneurysm, the microcatheter continually snagged the distal aneurysm lip, preventing delivery of a flow diverter into the distal parent vessel. In troubleshooting this obstacle, a second microguidewire was introduced alongside the microcatheter and was used to cover the distal lip of the aneurysm to prevent further snagging. The second guidewire successfully deflected the microcatheter into the distal vessel, a technique that we have aptly dubbed the ' bumper technique '.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"vessel\", \"parent vessel\"], \"Bacterium\": [], \"BiologicFunction\": [\"aneurysms\", \"aneurysm\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"obstacle\"], \"Food\": [], \"HealthCareActivity\": [\"maneuvering\"], \"InjuryOrPoisoning\": [\"snagged\"], \"IntellectualProduct\": [\"case report\"], \"MedicalDevice\": [\"flow diverter\", \"guidewire\", \"microcatheter\", \"microguidewire\"], \"Organization\": [], \"PopulationGroup\": [\"woman\", \"operators\", \"Operators\"], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [], \"SpatialConcept\": [\"distal\", \"locations\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Review the provided biomedical excerpts and respond to the question concisely. Ensure your answer is derived solely from the given context and avoid adding any extraneous information.\n\nQuestion: What is the function of TALENs?\n\nExcerpts: Transcription activator-like effector nucleases (TALENs) are programmable nucleases that join FokI endonuclease with the modular DNA-binding domain of TALEs", "role": "user" }, { "content": "These chimeric enzymes can be used to introduce a double strand break at a specific genomic site which then can become the substrate for error-prone non-homologous end joining (NHEJ), generating mutations at the site of cleavage. Artificial transcription activator-like effector nucleases (TALENs) provide a powerful new approach for targeted zebrafish genome editing and functional genomic applications. Transcription Activator-Like Effector Nucleases (TALENs) consist of a nuclease domain fused to a DNA binding domain which is engineered to bind to any genomic sequence. Transcription activator-like effector nucleases (TALENs) are programmable nucleases that join FokI endonuclease with the modular DNA-binding domain of TALEs.", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nThe effect of lowering LDL cholesterol on vascular access patency : post hoc analysis of the Study of Heart and Renal Protection . BACKGROUND AND OBJECTIVES Reducing LDL cholesterol ( LDL-C ) with statin-based therapy reduces the risk of major atherosclerotic events among patients with CKD , including dialysis patients , but the effect of lowering LDL-C on vascular access patency is unclear . DESIGN , SETTING , PARTICIPANTS , & MEASUREMENTS The Study of Heart and Renal Protection ( SHARP ) randomized patients with CKD to 20 mg simvastatin plus 10 mg ezetimibe daily versus matching placebo . This study aimed to explore the effects of treatment on vascular access occlusive events , defined as any access revision procedure , access thrombosis , removal of an old dialysis access , or formation of new permanent dialysis access . RESULTS Among 2353 SHARP participants who had functioning vascular access at randomization , allocation to simvastatin plus ezetimibe resulted in a 13 % proportional reduction in vascular access occlusive events ( 355 [ 29.7 % ] for simvastatin/ezetimibe versus 388 [ 33.5 % ] for placebo ; risk ratio [ RR ] , 0.87 ; 95 % confidence interval [ 95 % CI ] , 0.75 to 1.00 ; P=0.05 ) . There was no evidence that the effects of treatment differed for any of the separate components of this outcome . To test the hypothesis raised by SHARP , comparable analyses were performed using the AURORA ( A Study to Evaluate the Use of Rosuvastatin in Subjects on Regular Hemodialysis : An Assessment of Survival and Cardiovascular Events ) trial cohort . AURORA did not provide independent confirmation ( vascular access occlusive events : 352 [ 28.9 % ] for rosuvastatin versus 337 [ 27.6 % ] for placebo ; RR , 1.06 , 95 % CI , 0.91 to 1.23 ; P=0.44 ) . After combining the two trials , the overall effect of reducing LDL-C with a statin-based regimen on vascular access occlusive events was not statistically significant ( 707 [ 29.3 % ] with any LDL-C-lowering therapy versus 725 [ 30.5 % ] with placebo ; RR , 0.95 , 95 % CI , 0.85 to 1.05 ; P=0.29 ) . CONCLUSIONS Exploratory analyses from SHARP suggest that lowering LDL-C with statin-based therapy may improve vascular access patency , but there was no evidence of benefit in AURORA . Taken together , the available evidence suggests that any benefits of lowering LDL-C on vascular access patency are likely to be modest .", "role": "user" }, { "content": "{\"Intervention\": [\"statin-based therapy\", \"placebo\", \"20 mg simvastatin plus 10 mg ezetimibe daily\", \"simvastatin/ezetimibe\"], \"Outcome\": [\"any access revision procedure\", \"access thrombosis\", \"LDL-C\", \"removal of an old dialysis access\", \"formation of new permanent dialysis access\", \"reduction in vascular access occlusive events\"], \"Participant\": [\"patients with CKD , including dialysis patients\", \"CKD\", \"who had functioning vascular access\", \"2353\"]}", "role": "assistant" } ]

[ { "content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: There is no evidence that viruses can spread to people or other animals from a pet's skin, fur or hair.\n\nResearch Abstract:\nSevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2)--the virus that causes coronavirus disease (COVID-19)--has been detected in domestic dogs and cats, raising concerns of transmission from, to, or between these animals.\nThere is currently no indication that feline- or canine-to-human transmission can occur, though there is rising evidence of the reverse.\nTo explore the extent of animal-related transmission, we aggregated 17 case reports on confirmed SARS-CoV-2 infections in animals as of 15 May 2020.\nAll but two animals fully recovered and had only mild respiratory or digestive symptoms.\nUsing data from probable cat-to-cat transmission in Wuhan, China, we estimated the basic reproduction number R0 under this scenario at 1.09 (95% confidence interval: 1.05, 1.13).\nThis value is much lower than the R0 reported for humans and close to one, indicating that the sustained transmission between cats is unlikely to occur.\nOur results support the view that the pet owners and other persons with COVID-19 in close contact with animals should be cautious of the way they interact with them.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"There is currently no indication that feline- or canine-to-human transmission can occur, though there is rising evidence of the reverse.\", \"Using data from probable cat-to-cat transmission in Wuhan, China, we estimated the basic reproduction number R0 under this scenario at 1.09 (95% confidence interval: 1.05, 1.13).\", \"This value is much lower than the R0 reported for humans and close to one, indicating that the sustained transmission between cats is unlikely to occur.\"]}", "role": "assistant" } ]

[ { "content": "Examine the given text from a research paper in the field of NLP. Your task is to identify the role of the citation within the context provided. Focus on understanding the intent behind the citation and classify it accordingly.\n\nSection Title:\nNone\n\nText Before Citation:\nIn a log-linear parameterization, for example, a prior that penalizes feature strengths far from 1 can be used to do feature selection and avoid overfitting (Chen and Rosenfeld, 1999). Maximum-posterior estimation tries to maximize P(0)·Hi fθ(xi, yi) where P(0) is a prior probability. Maximum-likelihood estimation guesses 0ˆ to be the 0 maximizing Hi fθ(xi, yi).\n\nCitation Text:\nIn a log-linear parameterization , for example , a prior that penalizes feature strengths far from 1 can be used to do feature selection and avoid overfitting ( Chen and Rosenfeld , 1999 ) .\n\nText After Citation:\nThe EM algorithm (Dempster et al., 1977) can maximize these functions. Roughly, the E step guesses hidden information: if (xi, yi) was generated from the current fθ, which FST paths stand a chance of having been the path used? (Guessing the path also guesses the exact input and output.) The M step updates 0 to make those paths more likely.", "role": "user" }, { "content": "Uses", "role": "assistant" } ]

[ { "content": "Analyze the provided paragraph from a scientific document. Your goal is to identify and extract relevant entities.\n\nFormat your findings as a JSON object, where each key represents a category of entities, and the corresponding value is a list of entities identified in that category. If no entities are found for a category, return an empty list.\n\nFocus on precision and ensure that the output is strictly in JSON format.\n\nDocument:\n\nPredominance of Clostridium difficile Ribotypes 017 and 078 among Toxigenic Clinical Isolates in Southern Taiwan Ribotypes and toxin genotypes of clinical C. difficile isolates in Taiwan are rarely reported. A prospective surveillance study from January 2011 to January 2013 was conducted at the medical wards of a district hospital in southern Taiwan. Of the first toxigenic isolates from 120 patients, 68 (56.7%) of 120 isolates possessed both tcdA and tcdB. Of 52 (43.3%) with tcdB and truncated tcdA (tcdA-/tcdB+), all were ribotype 017 and none had binary toxin or tcdC deletion. Eighteen (15%) toxigenic isolates harbored binary toxins (cdtA and cdtB) and all had tcdC deletion, including Δ39 (C184T) deletion (14 isolates), Δ18 in-frame deletion (3 isolates), and Δ18 (Δ117A) deletion (1 isolate). Eleven of 14 isolates with Δ39 (C184T) deletion belonged to the ribotype 078 family, including ribotype 127 (6 isolates), ribotype 126 (4 isolates), and ribotype 078 (1 isolate). Among 8 patients with consecutive C. difficile isolates, these isolates from 6 (75%) patients were identical, irrespective of the presence or absence of diarrhea, suggestive of persistent fecal carriage or colonization. In conclusion in southern Taiwan, ribotype 017 isolates with a tcdA-/tcdB+ genotype were not uncommon and of C. difficile isolates with binary toxin, the ribotype 078 family was predominant.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [\"C. difficile\", \"Clostridium difficile\"], \"BiologicFunction\": [\"\\u039418 in-frame deletion\", \"\\u039439 (C184T) deletion\", \"\\u039418 (\\u0394117A) deletion\", \"deletion\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"Clinical Isolates\", \"isolate\", \"binary toxin\", \"binary toxins\", \"isolates\", \"toxin\", \"toxigenic\", \"Toxigenic\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"078\", \"Ribotypes\", \"colonization\", \"persistent fecal carriage\", \"ribotype 078\", \"Ribotypes 017\", \"diarrhea\", \"presence\", \"ribotype 127\", \"ribotype 126\", \"ribotype 017\"], \"Food\": [], \"HealthCareActivity\": [], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [\"district hospital\", \"medical wards\"], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [], \"SpatialConcept\": [\"Taiwan\", \"southern\", \"Southern\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: A survey of the current status of research on quantum games \nChapter Title: C. Quantum Game Applications \n1. Abstract of Cited Paper (BIB001): The digital revolution of the information age and in particular the sweeping changes of scientific communication brought about by computing and novel communication technology, potentiate global, high grade scientific information for free. The arXiv for example is the leading scientific communication platform, mainly for mathematics and physics, where everyone in the world has free access on. While in some scientific disciplines the open access way is successfully realized, other disciplines (e.g. humanities and social sciences) dwell on the traditional path, even though many scientists belonging to these communities approve the open access principle. In this paper we try to explain these different publication patterns by using a game theoretical approach. Based on the assumption, that the main goal of scientists is the maximization of their reputation, we model different possible game settings, namely a zero sum game, the prisoners’ dilemma case and a version of the stag hunt game, that show the dilemma of scientists belonging to “non-open access communities”. From an individual perspective, they have no incentive to deviate from the Nash Equilibrium of traditional publishing. By extending the model using the quantum game theory approach it can be shown, that if the strength of entanglement exceeds a certain value, the scientists will overcome the dilemma and terminate to publish only traditionally in all three settings. \n2. Abstract of Cited Paper (BIB002): Most game-theoretic studies of strategic interaction assume independent individual strategies as the basic unit of analysis. This paper explores the effects of non-independence on strategic interaction. Two types of non-independence effects are considered. First, the paper considers subjective non-independence at the level of the individual actor by looking at how choice ambivalence shapes the decision-making process. Specifically, how do alternative individual choices superpose with one another to “constructively/destructively” shape each other's role within an actor's decision-making process? This process is termed as quantum superposition of alternative choices. Second, the paper considers how inter-subjective non-independence across actors engenders collective strategies among two or more interacting actors. This is termed as quantum entanglement of strategies. Taking into account both types of non-independence effect makes possible the emergence of a new collective equilibrium, without assuming signaling, prior “contract” agreement or third-party moderation, or even “cheap talk”. I apply these ideas to analyze the equilibrium possibilities of a situation wherein N actors play a quantum social game of cooperation. I consider different configurations of large-N quantum entanglement using the approach of density operator. I specifically consider the following configurations: star-shaped, nearest-neighbors, and full entanglement. \n3. Abstract of Cited Paper (BIB003): The last financial and economic crisis demonstrated the dysfunctional long-term effects of aggressive behaviour in financial markets. Yet, evolutionary game theory predicts that under the condition of strategic dependence a certain degree of aggressive behaviour remains within a given population of agents. However, as the consequences of the financial crisis exhibit, it would be desirable to change the 'rules of the game' in a way that prevents the occurrence of any aggressive behaviour and thereby also the danger of market crashes. The paper picks up this aspect. Through the extension of the in literature well-known Hawk-Dove game by a quantum approach, we can show that dependent on entanglement, also evolutionary stable strategies can emerge, which are not predicted by classical evolutionary game theory and where the total economic population uses a non aggressive quantum strategy. \n4. Abstract of Cited Paper (BIB004): In recent years, Chinese service industry is developing rapidly. Compared with developed countries, service quality should be the bottleneck for Chinese service industry. On the background of three major telecommunications service providers in China, the functions of customer perceived utilities are established. With the goal of consumer’s perceived utility maximization, the classic Nash equilibrium solution and quantum equilibrium solution are obtained. Then a numerical example is studied and the changing trend of service quality and customer perceived utility is further analyzed by the influence of the entanglement operator. Finally, it is proved that quantum game solution is better than Nash equilibrium solution.\n\nReview Chapter:", "role": "user" }, { "content": "Some papers study how to apply quantum game theory into society research. Based on the assumption that the main goal of scientists is the maximization of their reputation, Hanauske has performed modeling work for different possible game settings, namely a zero sum game, the prisoners' dilemma case and a version of the stag hunt game, which demonstrates the dilemma of scientists belonging to \"non-open access communities\". By extending the model using the quantum game theory approach, it can be seen that if the power of entanglement exceeds a certain value, the scientists will overcome the dilemma and terminate to publish only traditionally in all three settings BIB002 .Through the extension of the well-known hawk-dove game by a quantum approach, Hanauske et al. show that, depending on entanglement, evolutionary stable strategies also can emerge, which are not predicted by the classical evolutionary game theory and when the total economic population uses a nonaggressive quantum strategy BIB004 . After proposing a quantum-like description of markets and economics, Piotrowski further presents a simple but nontrivial class of the quantum strategies in buying-selling games . The Giffen paradoxes in quantum game model formalism is discussed by Sladkowski BIB001 . Badredine explores the effects of non-independence on strategic interaction, where two types of non-independence effects are considered. The first one is the subjective nonindependence at the level of the individual actor by looking at how choice ambivalence shapes the decision-making process. The other is how inter-subjective non-independence across actors engenders collective strategies among two or more interacting actors BIB003 . Based on the fact that service quality is the bottleneck for Chinese service industry, with the goal of consumer's perceived utility maximization, a classic game model and a quantum game model are proposed and established by Zhang and Xing. Through the research, their results show that the quantum game expands the strategy space of the firms, and can help them to obtain a superior equilibrium solution or better decision-making value than the classic game BIB005 .", "role": "assistant" } ]

[ { "content": "Analyze the following collection of medical RCT summaries. Your goal is to craft a concise synthesis of the findings. Focus on the core insights and present them succinctly. Only include the synthesis in your response. Below are the RCT summaries:\n\n\n\nReport 1:\nTitle: Cost-effectiveness of ranibizumab and bevacizumab for age-related macular degeneration: 2-year findings from the IVAN randomised trial\nSummary: Objective To assess the incremental cost and cost-effectiveness of continuous and discontinuous regimens of bevacizumab ( Avastin ) and ranibizumab ( Lucentis ) for neovascular age-related macular degeneration ( nAMD ) from a UK National Health Service ( NHS ) perspective . Design A within-trial cost-utility analysis with a 2-year time horizon , based on a multicentre factorial , non-inferiority r and omised controlled trial . Setting 23 hospital ophthalmology clinics . Participants 610 patients aged ≥50 years with untreated nAMD in the study eye . Interventions 0.5 mg ranibizumab or 1.25 mg bevacizumab given continuously ( monthly ) or discontinuously ( as-needed ) for 2 years . Main outcome measures Quality -adjusted life-years ( QALYs ) . Results Total 2-year costs ranged from £ 3002/patient ( $ 4700 ; 95 % CI £ 2601 to £ 3403 ) for discontinuous bevacizumab to £ 18 590/patient ( $ 29 106 ; 95 % CI £ 18 258 to £ 18 922 ) for continuous ranibizumab . Ranibizumab was significantly more costly than bevacizumab for both continuous ( + £ 14 989/patient ( $ 23 468 ) ; 95 % CI £ 14 522 to £ 15 456 ; p<0.001 ) and discontinuous treatment ( + £ 8498 ( $ 13 305 ) ; 95 % CI £ 7700 to £ 9295 ; p<0.001 ) , with negligible difference in QALYs . Continuous ranibizumab would only be cost-effective compared with continuous bevacizumab if the NHS were willing to pay £ 3.5 million ( $ 5.5 million ) per additional QALY gained . Patients receiving continuous bevacizumab accrued higher total costs ( + £ 599 ( $ 938 ) ; 95 % CI £ 91 to £ 1107 ; p=0.021 ) than those receiving discontinuous bevacizumab , but also accrued non-significantly more QALYs ( + 0.020 ; 95 % CI −0.032 to 0.071 ; p=0.452 ) . Continuous bevacizumab therefore cost £ 30 220 ( $ 47 316 ) per QALY gained versus discontinuous bevacizumab . However , bootstrapping demonstrated that if the NHS is willing to pay £ 20 000/QALY gained , there is a 37 % chance that continuous bevacizumab is cost-effective versus discontinuous bevacizumab . Conclusions Ranibizumab is not cost-effective compared with bevacizumab , being substantially more costly and producing little or no QALY gain . Discontinuous bevacizumab is likely to be the most cost-effective of the four treatment strategies evaluated in this UK trial , although there is a 37 % chance that continuous bevacizumab is cost-effective . Trial registration number IS RCT N92166560\n\n\nReport 2:\nTitle: Alternative treatments to inhibit VEGF in age-related choroidal neovascularisation: 2-year findings of the IVAN randomised controlled trial\nSummary: BACKGROUND Bevacizumab has been suggested to have similar effectiveness to ranibizumab for treatment of neovascular age-related macular degeneration . The Inhibition of VEGF in Age-related choroidal Neovascularisation ( IVAN ) trial was design ed to compare these drugs and different regimens . Here , we report the findings at the prespecified 2-year timepoint . METHODS In a multicentre , 2 × 2 factorial , non-inferiority r and omised trial , we enrolled adults aged at least 50 years with active , previously untreated neovascular age-related macular degeneration and a best corrected distance visual acuity ( BCVA ) of at least 25 letters from 23 hospitals in the UK . Participants were r and omly assigned ( 1:1:1:1 ) to intravitreal injections of ranibizumab ( 0·5 mg ) or bevacizumab ( 1·25 mg ) in continuous ( every month ) or discontinuous ( as needed ) regimens , with monthly review . Study participants and clinical assessors were masked to drug allocation . Allocation to continuous or discontinuous treatment was masked up to 3 months , at which point investigators and participants were unmasked . The primary outcome was BCVA at 2 years , with a prespecified non-inferiority limit of 3·5 letters . The primary safety outcome was arterial thrombotic event or hospital admission for heart failure . Analyses were by modified intention to treat . This trial is registered , number IS RCT N92166560 . FINDINGS Between March 27 , 2008 , and Oct 15 , 2010 , 628 patients underwent r and omisation . 18 were withdrawn ; 610 received study drugs ( 314 ranibizumab ; 296 bevacizumab ) and were included in analyses . 525 participants reached the visit at 2 years : 134 ranibizumab in continuous regimen , 137 ranibizumab in discontinuous regimen , 127 bevacizumab in continuous regimen , and 127 bevacizumab in discontinuous regimen . For BCVA , bevacizumab was neither non-inferior nor inferior to ranibizumab ( mean difference -1·37 letters , 95 % CI -3·75 to 1·01 ; p=0·26 ) . Discontinuous treatment was neither non-inferior nor inferior to continuous treatment ( -1·63 letters , -4·01 to 0·75 ; p=0·18 ) . Frequency of arterial thrombotic events or hospital admission for heart failure did not differ between groups given ranibizumab ( 20 [ 6 % ] of 314 participants ) and bevacizumab ( 12 [ 4 % ] of 296 ; odds ratio [ OR ] 1·69 , 95 % CI 0·80 - 3·57 ; p=0·16 ) , or those given continuous ( 12 [ 4 % ] of 308 ) and discontinuous treatment ( 20 [ 7 % ] of 302 ; 0·56 , 0·27 - 1·19 ; p=0·13 ) . Mortality was lower with continuous than discontinuous treatment ( OR 0·47 , 95 % CI 0·22 - 1·03 ; p=0·05 ) , but did not differ by drug group ( 0·96 , 0·46 - 2·02 ; p=0·91 ) . INTERPRETATION Ranibizumab and bevacizumab have similar efficacy . Reduction in the frequency of retreatment result ed in a small loss of efficacy irrespective of drug . Safety was worse when treatment was administered discontinuously . These findings highlight that the choice of anti-VEGF treatment strategy is less straightforward than previously thought . FUNDING UK National Institute for Health Research Health Technology Assessment programme\n\n\nReport 3:\nTitle: Comparing the effectiveness and costs of Bevacizumab to Ranibizumab in patients with Diabetic Macular Edema: a randomized clinical trial (the BRDME study)\nSummary: Background The effectiveness of ranibizumab in the treatment of diabetic macular edema has been proven with large clinical trials . For bevacizumab only two clinical trials have been published and a head-to-head comparison is lacking to date . However , if proved non-inferior to ranibizumab , use of the off-label bevacizumab could reduce costs enormously without a loss in visual acuity . A cost-effectiveness study has been design ed to substantiate this hypothesis . Aim To compare the effectiveness and costs of 1.25 mg of bevacizumab to 0.5 mg ranibizumab given as monthly intravitreal injections during 6 months in patients with diabetic macular edema . It is hypothesized that bevacizumab is non-inferior to ranibizumab regarding its effectiveness . Design This is a r and omized , controlled , double masked , clinical trial in 246 patients in seven academic trial centres in The Netherl and s. Outcomes The primary outcome measure is the change in best-corrected visual acuity ( BCVA ) in the study eye from baseline to month 6 . Secondary outcomes are the proportions of patients with a gain or loss of 15 letters or more or a BCVA of 20/40 or more at 6 months , the change in leakage on fluorescein angiography and the change in foveal thickness by optical coherence tomography at 6 months , the number of adverse events in 6 months , and the costs per quality adjusted life-year of the two treatments\n\n\nReport 4:\nTitle: Ranibizumab and bevacizumab for neovascular age-related macular degeneration.\nSummary: BACKGROUND Clinical trials have established the efficacy of ranibizumab for the treatment of neovascular age-related macular degeneration ( AMD ) . In addition , bevacizumab is used off-label to treat AMD , despite the absence of similar supporting data . METHODS In a multicenter , single-blind , noninferiority trial , we r and omly assigned 1208 patients with neovascular AMD to receive intravitreal injections of ranibizumab or bevacizumab on either a monthly schedule or as needed with monthly evaluation . The primary outcome was the mean change in visual acuity at 1 year , with a noninferiority limit of 5 letters on the eye chart . RESULTS Bevacizumab administered monthly was equivalent to ranibizumab administered monthly , with 8.0 and 8.5 letters gained , respectively . Bevacizumab administered as needed was equivalent to ranibizumab as needed , with 5.9 and 6.8 letters gained , respectively . Ranibizumab as needed was equivalent to monthly ranibizumab , although the comparison between bevacizumab as needed and monthly bevacizumab was inconclusive . The mean decrease in central retinal thickness was greater in the ranibizumab-monthly group ( 196 μm ) than in the other groups ( 152 to 168 μm , P=0.03 by analysis of variance ) . Rates of death , myocardial infa rct ion , and stroke were similar for patients receiving either bevacizumab or ranibizumab ( P>0.20 ) . The proportion of patients with serious systemic adverse events ( primarily hospitalizations ) was higher with bevacizumab than with ranibizumab ( 24.1 % vs. 19.0 % ; risk ratio , 1.29 ; 95 % confidence interval , 1.01 to 1.66 ) , with excess events broadly distributed in disease categories not identified in previous studies as areas of concern . CONCLUSIONS At 1 year , bevacizumab and ranibizumab had equivalent effects on visual acuity when administered according to the same schedule . Ranibizumab given as needed with monthly evaluation had effects on vision that were equivalent to those of ranibizumab administered monthly . Differences in rates of serious adverse events require further study . ( Funded by the National Eye Institute ; Clinical Trials.gov number , NCT00593450 . )\n\n\nReport 5:\nTitle: Seven-year outcomes in ranibizumab-treated patients in ANCHOR, MARINA, and HORIZON: a multicenter cohort study (SEVEN-UP).\nSummary: PURPOSE To assess long-term outcomes 7 to 8 years after initiation of intensive ranibizumab therapy in exudative age-related macular degeneration ( AMD ) patients . DESIGN Multicenter , noninterventional cohort study . PARTICIPANTS Sixty-five AMD patients originally treated with ranibizumab in the phase 3 Anti-VEGF Antibody for the Treatment of Predominantly Classic Choroidal Neovascularization in AMD ( ANCHOR ) trial , Minimally Classic/Occult Trial of the Anti-VEGF Antibody Ranibizumab in the Treatment of Neovascular AMD ( MARINA ) trial , and Open-Label Extension Trial of Ranibizumab for Choroidal Neovascularization Secondary to Age-Related Macular Degeneration ( HORIZON ) . METHODS Fourteen clinical trial sites recruited their original subjects for a return evaluation . Individual subject comparisons were obtained from the ANCHOR , MARINA , and HORIZON data bases . MAIN OUTCOME MEASURES The primary end point was percentage with best-corrected visual acuity ( BCVA ) of 20/70 or better ; secondary outcomes included mean change in letter score compared with previous time points and anatomic results on fluorescein angiography , spectral-domain ocular coherence tomography ( OCT ) , and fundus autofluorescence ( FAF ) . RESULTS At a mean of 7.3 years ( range , 6.3 - 8.5 years ) after entry into ANCHOR or MARINA , 37 % of study eyes met the primary end point of 20/70 or better BCVA , with 23 % achieving a BCVA of 20/40 or better . Thirty-seven percent of study eyes had BCVA of 20/200 or worse . Forty-three percent of study eyes had a stable or improved letter score ( ≥0-letter gain ) compared with ANCHOR or MARINA baseline measurements , whereas 34 % declined by 15 letters or more , with overall a mean decline of 8.6 letters ( P<0.005 ) . Since exit from the HORIZON study , study eyes had received a mean of 6.8 anti-vascular endothelial growth factor ( VEGF ) injections during the mean 3.4-year interval ; a subgroup of patients who received 11 or more anti-VEGF injections had a significantly better mean gain in letter score since HORIZON exit ( P<0.05 ) . Active exudative disease was detected by spectral-domain OCT in 68 % of study eyes , and 46 % were receiving ongoing ocular anti-VEGF treatments . Macular atrophy was detected by FAF in 98 % of eyes , with a mean area of 9.4 mm(2 ) ; the area of atrophy correlated significantly with poor visual outcome ( P<0.0001 ) . CONCLUSIONS Approximately 7 years after ranibizumab therapy in the ANCHOR or MARINA trials , one third of patients demonstrated good visual outcomes , whereas another third had poor outcomes . Compared with baseline , almost half of eyes were stable , whereas one third declined by 15 letters or more . Even at this late stage in the therapeutic course , exudative AMD patients remain at risk for substantial visual decline", "role": "user" }, { "content": "A third drug , bevacizumab ( Avastin ) , is only licensed for colorectal cancer , and therefore , use in the eye is ‘ off label’.1 Yet , all three are effective .", "role": "assistant" } ]

[ { "content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nOBJECTIVES: The SARS-CoV-2 outbreak has imposed considerable restrictions on people's mobility, which affects the referral of chronically ill patients to health care structures. The emerging need for alternative ways to follow these patients up is leading to a wide adoption of telemedicine. We aimed to evaluate the feasibility of this approach for our cohort of patients with CTDs, investigating their attitude to adopting telemedicine, even after the pandemic. METHODS: We conducted a telephonic survey among consecutive patients referred to our CTD outpatients' clinic, evaluating their capability and propensity for adopting telemedicine and whether they would prefer it over face-to-face evaluation. Demographical and occupational factors were also collected, and their influence on the answers has been evaluated by a multivariate analysis. RESULTS: A total of 175 patients answered our survey (M/F = 28/147), with a median age of 62.5 years [interquartile range (IQR) 53-73]. About 80% of patients owned a device allowing video-calls, and 86% would be able to perform a tele-visit, either alone (50%) or with the help of a relative (36%). Telemedicine was considered acceptable by 78% of patients and 61% would prefer it. Distance from the hospital and patient's educational level were the strongest predictive factors for the acceptance of telemedicine (P < 0.05), whereas age only affected the mastering of required skills (P < 0.001). CONCLUSION: Telemedicine is a viable approach to be considered for routine follow-up of chronic patients, even beyond the pandemic. Our data showed that older patients would be willing to use this approach, although a proper guide for them would be required.", "role": "user" }, { "content": "[\"Prevention\"]", "role": "assistant" } ]

[ { "content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nIn addition, more than three quarters of 97% OTUs in these proteobacterial classes contain SSU rRNA genes detected in PCR-based studies and appear in the SILVA database [12].", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Analyze the given text to identify specific entities. Focus on extracting relevant data.\n\nProvide your findings in JSON format. Each category should list the entities found.\n\nText:\n\nA 90-day feeding study of glyphosate-tolerant maize with the G2-aroA gene in Sprague-Dawley rats. Maize is not only a staple food crop but also an important raw material for feed and industry; however, the threat of weeds leads to a serious decline in its output and quality. The G2-aroA gene confers glyphosate herbicide tolerance to crops. In this study, the food safety of genetically modified (GM), glyphosate-tolerant maize with the G2-aroA gene was evaluated in a 90-day feeding study in Sprague-Dawley (SD) rats. Maize grain from GM or non-GM isogenic control lines were separately formulated into rodent diets at concentrations of 12.5% (low level), 25% (middle level), and 50% (high level). An additional group of rats were fed a commercialized diet as a control. The toxicological response variables, including body weights, food consumption, serum biochemistry, hematology, and absolute and relative organ weights, were compared between rats fed GM maize and those fed non-GM maize after consumption of test diets for 90days. In addition, gross and microscopic pathology were conducted among treatment groups. No adverse effects related to the consumption of GM maize were detected in the subchronic feeding study. These results indicated that the GM glyphosate-tolerant maize was as safe and nutritious as conventional maize.", "role": "user" }, { "content": "{\"Chemical\": [\"glyphosate\"]}", "role": "assistant" } ]

[ { "content": "Examine the provided biomedical text and determine the answer to the question. Your response should be either \"yes\" or \"no\" based on the information given.\n\nQuestion: Is Otolin-1 a matrix protein?\n\nText: otoconia matrix protein, otolin-1\nOtolin-1 is a collagen-like protein expressed in the inner ear of vertebrates.\nMammalian Otolin: a multimeric glycoprotein specific to the inner ear that interacts with otoconial matrix protein Otoconin-90 and Cerebellin-1\nbinds to otolin-1 and forming matrix protein architectures", "role": "user" }, { "content": "yes", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: In this paper, we investigate the fault tolerance of the yeast interactome\n\nKeywords: gene essentiality prediction protein-protein physical interaction network\n\nDataset Information:\nMIMII: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection (MIMII) is a sound dataset of industrial machine sounds.\nPhotoBook: A large-scale collection of visually-grounded, task-oriented dialogues in English designed to investigate shared dialogue history accumulating during conversation.\nAVE: To investigate three temporal localization tasks: supervised and weakly-supervised audio-visual event localization, and cross-modality localization.\nBioGRID: BioGRID is a biomedical interaction repository with data compiled through comprehensive curation efforts. The current index is version 4.2.192 and searches 75,868 publications for 1,997,840 protein and genetic interactions, 29,093 chemical interactions and 959,750 post translational modifications from major model organism species.\n\nAvailable Datasets: A: MIMII B: PhotoBook C: AVE D: BioGRID", "role": "user" }, { "content": "BioGRID", "role": "assistant" } ]

[ { "content": "Transform the following sections from a biomedical study into a simple summary for the general public. Focus on making the information accessible and easy to understand.\n\nResearch Heading: DAF-18/PTEN signals through AAK-1/AMPK to inhibit MPK-1/MAPK in feedback control of germline stem cell proliferation\nContent:\nAbstract:\nUnder replete growth conditions, abundant nutrient uptake leads to the systemic activation of insulin/IGF-1 signalling( IIS) and the promotion of stem cell growth/proliferation. Activated IIS can stimulate the ERK/MAPK pathway, the activation of which also supports optimal stem cell proliferation in various systems. Stem cell proliferation rates can further be locally refined to meet the resident tissue’s need for differentiated progeny. We have recently shown that the accumulation of mature oocytes in the C. elegans germ line, through DAF-18/PTEN, inhibits adult germline stem cell( GSC) proliferation, despite high systemic IIS activation. We show here that this feedback occurs through a novel cryptic signalling pathway that requires PAR-4/LKB1, AAK-1/AMPK and PAR-5/14-3-3 to inhibit the activity of MPK-1/MAPK, antagonize IIS, and inhibit both GSC proliferation and the production of additional oocytes. Interestingly, our results imply that DAF-18/PTEN, through PAR-4/LKB1, can activate AAK-1/AMPK in the absence of apparent energy stress. As all components are conserved, similar signalling cascades may regulate stem cell activities in other organisms and be widely implicated in cancer.\nIntroduction:\nStem cells can divide symmetrically to generate more copies of themselves or asymmetrically to produce one stem cell and a daughter cell destined for differentiation. Whether a stem cell will proliferate or differentiate is governed by niche signaling, which locally prevents differentiation[1]. Stem cell proliferation rates on the other hand, are largely controlled by growth factors that act in parallel to niche signaling to stimulate stem cell activity independent of fate[2–9]. Some of these growth factors are systemically controlled, such as insulin/IGF-1 signalling( IIS), which relays nutrient uptake information to cell growth/proliferation, largely through stimulating protein synthesis by activating the mTOR complex[10–12]. In C. elegans( Ce), activated IIS stimulates germline stem cell( GSC) proliferation throughout postembryonic life[2, 3, 9]. Genetic inactivation of IIS during early larval development leads to entry into a developmentally-arrested stage called dauer in which GSCs are fully quiescent[2, 13], while IIS inactivation at later stages of development or adulthood dramatically slows GSC proliferation rates[3, 9]. Dauer entry is naturally promoted by food deprivation, which causes energy stress and leads to a down-regulation of IIS and activation the AMP-activated protein kinase AAK( Ce AMPK)[14], a master intracellular energy-stress sensor[15]. In this context, the proper establishment of GSC quiescence downstream of insulin receptor inactivation requires DAF-18( Ce PTEN), PAR-4( Ce LKB1; an AMPK-activating kinase[15]), as well as germline AAK activity[2, 14]. In addition to being subject to systemic growth factor regulation, the proliferation rates of certain stem cell populations are also affected by the demand for their differentiated progeny. This was first demonstrated in Drosophila intestinal stem cells, the proliferation of which can be stimulated by cytokines released by damaged intestinal epithelial cells[5]. In Drosophila hematopoietic progenitor cells, proliferation was found to be inhibited by differentiated hemocytes through an adenosine deaminase growth factor A( Adgf-A) signal[16]. In mammals, hair follicle stem cell proliferation is stimulated by their transit-amplifying progeny once these begin producing Sonic hedgehog( Shh)[17]. Interactions between stem cells and their differentiated progeny is thus a conserved phenomenon that is likely to be involved in the regulation of diverse types of stem cells. Recently, we found that the proliferation rates of the C. elegans GSCs were negatively influenced by oocyte accumulation in sperm-less or sperm-depleted hermaphrodites[9]. C. elegans hermaphrodites produce a finite number of sperm during larval development, then switch to oocyte production during adult life, which continues until sperm stores are depleted. Sperm constitutively secrete major sperm proteins( MSPs) that activate cAMP signaling in the proximal somatic gonad. cAMP leads to activation of OMA-1 and OMA-2 in the proximal-most oocyte, triggering oocyte maturation( i. e. the transition between diakinesis and metaphase of meiosis I, which is accompanied by nuclear envelope breakdown, rearrangement of the cortical cytoskeleton, and meiotic spindle assembly) and ovulation[18–21]. Thus, when sperm is absent or depleted, oocytes do not mature and begin to accumulate in the proximal gonad, eventually leading to the inhibition of further oocyte production, as well as the inhibition of GSC proliferation at the distal end[9, 19, 22]. Indeed, the GSCs of sperm-less or sperm-depleted hermaphrodites enter G2/M quiescence with stochastic transient bouts of proliferation, leading to an overall drastically reduced mitotic index( MI)[9, 23]. Feedback inhibition of GSC proliferation by oocyte accumulation requires DAF-18 activity, which acts to locally antagonize systemic IIS information and block GSC proliferation, specifically in the gonad arm that is sperm-depleted and has accumulated oocytes. In this situation, DAF-18 does not block GSC proliferation by directly inhibiting IIS through antagonizing AGE-1( Ce PI3K) activity because the transcription factor that AGE-1 eventually inhibits, DAF-16( Ce FOXO), remains inactivated in sperm-less animals and is dispensable for feedback GSC regulation[9]. Thus, we reasoned that DAF-18 was inhibiting GSC proliferation in parallel to IIS via another, yet unidentified, signalling mechanism. Our work here demonstrates how DAF-18 negatively regulates MPK-1( Ce MAPK) function through activating PAR-4 and AAK-1( Ce AMPK α1-catalytic subunit), in the absence of any apparent stress, to locally couple GSC proliferation rates to the need for their differentiated progeny.\nDiscussion:\nOur results uncover a novel signalling pathway that links, in two sequential steps, oocyte needs to the regulation of GSC proliferation in C. elegans adult hermaphrodites( Fig 6). We previously demonstrated that DAF-18 was required to inhibit GSC proliferation downstream of sperm depletion, and that in the absence of sperm in these animals, unfertilized oocytes spontaneously activated and were ovulated[9]. Here, we demonstrate that the lack of PAR-4, AAK-1 or PAR-5 causes a similar phenotype, disrupting oocyte quiescence and feedback regulation of GSC proliferation. Preventing oocyte activation in a feedback-defective mutant also revealed an additional coupling step, this time between oocyte maturation and oocyte production. In aak-1; oma-1; oma-2 triple mutants, loss of OMA-1 and OMA-2 prevents oocyte maturation, triggering their accumulation, while the loss of AAK-1 blocks feedback signalling to the rest of the germ line. In this case, neither GSC proliferation nor oocyte maturation is blocked and we observe hyper-accumulation of oocytes. Thus, in feedback-defective animals, the accumulation of diakinesis-arrested oocytes cannot block GSC proliferation or oocyte production. This rules out the possibility that oocyte accumulation is physically sufficient to promote GSC quiescence, in which case the accumulated oocytes in aak-1; oma-1; oma-2 triple mutants would have been expected to promote GSC quiescence. We favor the possibility that oocyte accumulation indirectly promotes GSC quiescence through first causing an arrest in oocyte production, by blocking pachytene progression upstream in the germ line. Stalling of germ cell progression through meiosis would concomitantly inhibit GSC proliferation further upstream, in a chain of interdependent retrograde events, as we previously proposed[9]. In this scenario, AAK-1 would act as the gear that couples oocyte accumulation to the arrest of oocyte production( and other feedback steps). The newly demonstrated involvement of mpk-1 in feedback GSC regulation fits well such a mode of operation. Indeed, our results( combined with those of others[9, 19, 30, 40]) are consistent with a model in which sperm depletion blocks oocyte maturation and ovulation, causing their accumulation. After oocytes have accumulated up to a certain point, levels of dpMPK-1 in the pachytene zone of the germ line drop, blocking meiotic progression and the production of additional oocytes. Our results indicate that this inactivation of MPK-1 in pachytene-stage germ cells following oocyte accumulation requires DAF-18, PAR-4, AAK-1 and PAR-5 activities, and that ectopic activation of mpk-1 signalling prevents oocyte accumulation from blocking GSC proliferation. Lastly, we found that inactivation of mpk-1 suppressed the effects of a daf-18 null allele on GSC proliferation, indicating that MPK-1 functions downstream of, or in parallel to, DAF-18. Thus, we propose that following oocyte accumulation, DAF-18 activity leads to MPK-1 downregulation in pachytene-stage germ cells through activation of PAR-4 and AAK-1( PAR-4 can directly phosphorylate and activate AAK-1/AMPK[14, 15]), followed by AAK-1 phosphorylation of yet unidentified targets and their recognition by PAR-5, to inhibit MPK-1 signalling( Fig 6). How this inactivation of MPK-1 exactly inhibits GSC proliferation remains to be elucidated and is a focus for future investigation. However, our analysis of GSC proliferation in tumorous animals that lack differentiated germ cells imply that mpk-1 activity may promote GSC proliferation partly in the soma and/or GSCs, as well as in differentiated germ cells in the adult, possibly in zone I. Despite their anticipated germline requirement, the precise site( s) of PAR-4/LKB1 and AAK-1/AMPK action in feedback control of GSC proliferation remains to be determined. Our results indicate that the regulation of larval and adult GSC proliferation is mechanistically distinct. Feedback regulation of GSC proliferation by oocyte accumulation requires PAR-4/LKB1 and AAK-1/AMPK. These genes are also required for inhibition of GSC proliferation during dauer development but in this context they function downstream of insulin and/or TGF-β signals[2]. Our work reveals that PAR-4 and AAK-1 control GSC proliferation upon oocyte accumulation in the absence of changes in IIS during adulthood. The molecular context of feedback regulation of GSC proliferation by oocyte accumulation is thus mechanistically distinct from inhibition of GSC proliferation during dauer development, despite some overlap in gene requirements. Our results suggest that the inhibition of MPK-1 signalling in differentiated germ cells by AAK-1 may be an adult-specific mechanism through which GSC proliferation is controlled. While this mechanism must permit localized regulation of GSC proliferation, it appears to function only in animals that have activated IIS, perhaps because the inhibition of IIS also inactivates MPK-1 in germline zone I[30]. The involvement of AAK-1/AMPK in this feedback signal is particularly interesting because AMPK has been historically predominantly implicated in cellular stress response, typically inhibiting cell growth and proliferation in response to nutrient stress[2, 15, 25]. Hormones that increase intracellular Ca2+ can however activate AMPK in the absence of stress via phosphorylation by the calmodulin-dependent protein kinase CaMKKβ, but this is independent of PAR-4/LKB1[25, 41–43]. To our knowledge, the feedback mechanism that we herein report is thus the first documented occurrence of AMPK activation in a PAR-4/LKB1-dependent context in the absence of any apparent stress, but in response to a specific signal. Although we did not provide molecular evidence of AAK-1/AMPK activation, we assume it is the case due to the concomitant requirement for the upstream AMPK activating kinase PAR-4/LKB1. As for the regulation of lipid reserves in dauer larvae[44], only one of the two catalytic subunit isoforms is sufficient to fulfill this function. Thus, an emerging role of AAK-1/AMPK is its function as a signalling molecule downstream of DAF-18/PTEN and PAR-4/LKB1 to inhibit stem cell proliferation through PAR-5/14-3-3-dependent MPK-1/MAPK inhibition. Cancer is emerging as being a disease of the stem cells. For instance, cancer incidence was proposed to be related to the frequency of stem cell divisions[45], suggesting it is the stem cells themselves that can turn ill after going through a number of divisions and become tumorigenic. Understanding how stem cell division rates are regulated in vivo is thus immediately relevant to cancer biology. In this regard, our results reveal that some tumour suppressor genes, such as PTEN and LKB1, may prevent cancer by limiting stem cell divisions when these divisions are not needed. Indeed, defective feedback inhibition of intestinal stem cells may well underlie the growth of the related benign hamartomas in Cowden’s and Peutz-Jegher’s syndromes, which are caused in humans by germline mutations in PTEN and LKB1, respectively[46–48]. As such, we predict that the mechanisms we have identified in feedback GSC regulation in C. elegans may underlie cancer development in humans.", "role": "user" }, { "content": "Adult stem cell proliferation rates respond to the needs for their differentiated progeny . For example , the lung stem cells of a smoker will divide more frequently than those of a non-smoker to constantly replenish smoke-damaged tissues . Molecularly , stem cell proliferation rates vary according to growth factor levels , some of which , such as insulin , are regulated systemically . What remains unclear is whether and how a more or less rapid turnover of differentiated cells interferes with growth factor signalling to ultimately set the stem cells’ proliferative rate . We show here that this is accomplished though a novel cryptic signalling pathway that locally antagonizes the effects of insulin through inactivating a more locally-acting growth factor pathway ( ERK/MAPK signalling ) . Interestingly , a ubiquitous protein kinase ( AMPK ) that has primarily been implicated in energy stress response constitutes an integral part of this feedback mechanism . This suggests that an abundance of differentiated cells is molecularly interpreted as being similar to energy stress at the level of the stem cells , likewise leading to the inhibition of their growth and proliferation .", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nIn recent years, the distinctive advancement of handling huge data promotes the evolution of ubiquitous computing and analysis technologies. With the constantly upward system burden and computational complexity, adaptive coding has been a fascinating topic for pattern analysis, with outstanding performance. In this work, a continuous hashing method, termed continuous random hashing (CRH), is proposed to encode sequential data stream, while ignorance of previously hashing knowledge is possible. Instead, a random selection idea is adopted to adaptively approximate the differential encoding patterns of data stream, e.g., streaming media, and iteration is avoided for stepwise learning. Experimental results demonstrate our method is able to provide outstanding performance, as a benchmark approach to continuous hashing.\n\nCited Works Summary:\n[1]: In this article, we give an overview of efficient algorithms for the approximate and exact nearest neighbor problem. The goal is to preprocess a dataset of objects (e.g., images) so that later, given a new query object, one can quickly return the dataset object that is most similar to the query. The problem is of significant interest in a wide variety of areas.\n\n[2]: This paper introduces a product quantization-based approach for approximate nearest neighbor search. The idea is to decompose the space into a Cartesian product of low-dimensional subspaces and to quantize each subspace separately. A vector is represented by a short code composed of its subspace quantization indices. The euclidean distance between two vectors can be efficiently estimated from their codes. An asymmetric version increases precision, as it computes the approximate distance between a vector and a code. Experimental results show that our approach searches for nearest neighbors efficiently, in particular in combination with an inverted file system. Results for SIFT and GIST image descriptors show excellent search accuracy, outperforming three state-of-the-art approaches. The scalability of our approach is validated on a data set of two billion vectors.\n\n[3]: We propose a method for learning similarity-preserving hash functions that map high-dimensional data onto binary codes. The formulation is based on structured prediction with latent variables and a hinge-like loss function. It is efficient to train for large datasets, scales well to large code lengths, and outperforms state-of-the-art methods.\n\n[4]: We present a novel Locality-Sensitive Hashing scheme for the Approximate Nearest Neighbor Problem under lp norm, based on p-stable distributions.Our scheme improves the running time of the earlier algorithm for the case of the lp norm. It also yields the first known provably efficient approximate NN algorithm for the case p<1. We also show that the algorithm finds the exact near neigbhor in O(log n) time for data satisfying certain \"bounded growth\" condition.Unlike earlier schemes, our LSH scheme works directly on points in the Euclidean space without embeddings. Consequently, the resulting query time bound is free of large factors and is simple and easy to implement. Our experiments (on synthetic data sets) show that the our data structure is up to 40 times faster than kd-tree.", "role": "user" }, { "content": "Similarity search, as the basic issue of most information systems, addresses the problem of learning the similar data from buckets with respect to a given query data point [4] [1] . It is also known as (ANN) search [2] in large data sets with an identical demand. Generally, it is required to learn the compact binary codes of data, and then retrieval and recall of information can be implemented with codes matching [3] .", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nWe present a novel approach to reconstruct large or featureless scenes. Our method jointly estimates camera poses and a room layout from a set of partial reconstructions due to camera tracking interruptions when scanning a large or featureless scene. Unlike the existing methods relying on feature point matching to localize the camera, we exploit the 3D \"box\" structure of a typical room layout that meets the Manhattan World property. We first estimate a local layout for each partial scan separately and then combine these local layouts to form a globally aligned layout with loop closure. We validate our method quantitatively and qualitatively on real and synthetic scenes of various sizes and complexities. The evaluations and comparisons show superior effectiveness and accuracy of our method.\n\nCited Works Summary:\n[1]: This paper presents an approach for automatically aligning the non-overlapping interior and exterior parts of a 3D building model computed from image based 3D reconstructions. We propose a method to align the 3D reconstructions by identifying corresponding 3D structures that are part of the interior and exterior model (e.g. openings like windows). In this context, we point out the potential of using 3D line segments to enrich the information of point clouds generated by SfMs and show how this can be used for interpreting the scene and matching individual reconstructions.\n\n[2]: \n\n[3]: \n\n[4]: \n\n[5]: We introduce a novel RGB-D patch descriptor designed for detecting coplanar surfaces in SLAM reconstruction. The core of our method is a deep convolutional neural net that takes in RGB, depth, and normal information of a planar patch in an image and outputs a descriptor that can be used to find coplanar patches from other images.We train the network on 10 million triplets of coplanar and non-coplanar patches, and evaluate on a new coplanarity benchmark created from commodity RGB-D scans. Experiments show that our learned descriptor outperforms alternatives extended for this new task by a significant margin. In addition, we demonstrate the benefits of coplanarity matching in a robust RGBD reconstruction formulation.We find that coplanarity constraints detected with our method are sufficient to get reconstruction results comparable to state-of-the-art frameworks on most scenes, but outperform other methods on standard benchmarks when combined with a simple keypoint method.\n\n[6]: \n\n[7]: In this paper, we propose a novel method to jointly solve scene layout estimation and global registration problems for accurate indoor 3D reconstruction. Given a sequence of range data, we first build a set of scene fragments using KinectFusion and register them through pose graph optimization. Afterwards, we alternate between layout estimation and layout-based global registration processes in iterative fashion to complement each other. We extract the scene layout through hierarchical agglomerative clustering and energy-based multi-model fitting in consideration of noisy measurements. Having the estimated scene layout in one hand, we register all the range data through the global iterative closest point algorithm where the positions of 3D points that belong to the layout such as walls and a ceiling are constrained to be close to the layout. We experimentally verify the proposed method with the publicly available synthetic and real-world datasets in both quantitative and qualitative ways.\n\n[8]: \n\n[9]: We present 3DLite1, a novel approach to reconstruct 3D environments using consumer RGB-D sensors, making a step towards directly utilizing captured 3D content in graphics applications, such as video games, VR, or AR. Rather than reconstructing an accurate one-to-one representation of the real world, our method computes a lightweight, low-polygonal geometric abstraction of the scanned geometry. We argue that for many graphics applications it is much more important to obtain high-quality surface textures rather than highly-detailed geometry. To this end, we compensate for motion blur, auto-exposure artifacts, and micro-misalignments in camera poses by warping and stitching image fragments from low-quality RGB input data to achieve high-resolution, sharp surface textures. In addition to the observed regions of a scene, we extrapolate the scene geometry, as well as the mapped surface textures, to obtain a complete 3D model of the environment. We show that a simple planar abstraction of the scene geometry is ideally suited for this completion task, enabling 3DLite to produce complete, lightweight, and visually compelling 3D scene models. We believe that these CAD-like reconstructions are an important step towards leveraging RGB-D scanning in actual content creation pipelines.\n\n[10]: RGB-D scanning of indoor environments is important for many applications, including real estate, interior design, and virtual reality. However, it is still challenging to register RGB-D images from a hand-held camera over a long video sequence into a globally consistent 3D model. Current methods often can lose tracking or drift and thus fail to reconstruct salient structures in large environments (e.g., parallel walls in different rooms). To address this problem, we propose a fine-to-coarse global registration algorithm that leverages robust registrations at finer scales to seed detection and enforcement of new correspondence and structural constraints at coarser scales. To test global registration algorithms, we provide a benchmark with 10,401 manually-clicked point correspondences in 25 scenes from the SUN3D dataset. During experiments with this benchmark, we find that our fine-to-coarse algorithm registers long RGB-D sequences better than previous methods.\n\n[11]: \n\n[12]: We present an algorithm for calibrated camera relative pose estimation from lines. Given three lines with two of the lines parallel and orthogonal to the third we can compute the relative rotation between two images. We can also compute the relative translation from two intersection points. We also present a framework in which such lines can be detected. We evaluate the performance of the algorithm using synthetic and real data. The intended use of the algorithm is with robust hypothesize-and-test frameworks such as RANSAC. Our approach is suitable for urban and indoor environments where most lines are either parallel or orthogonal to each other.", "role": "user" }, { "content": "In addition to the MW assumption, indoor scenes have plentiful lines and planes which provide strong cues for many tasks. Elqursh and Elgammal [11]0 present a line-based camera pose estimation method, while Koch al [1] use 3D line segments to align the non-overlapping indoor and outdoor reconstructions. Planar patch detection and matching [9] [4] [2] [11] [6] [8] [3] are extensively used strategies to improve the reconstruction quality. Some works [9] [4] [2] [11] exploit plane correspondence to solve for frame-to-frame camera poses. Shi al [5] use a CNN to learn a feature descriptor for planar patches in RGB-D images. Halber al [5]9 and Lee al [7] perform global registration leveraging structural constraints to elevate the scan accuracy. These approaches all hinge on the success of feature matching at the overlapping areas, as opposed to the scenario in this paper.", "role": "assistant" } ]

[ { "content": "Examine the text below and extract disease-related entities. Present your findings in a structured JSON format.\n\nYour response should be a JSON object with keys as entity types and values as lists of entities. If no entities are found, return an empty list for that type.\n\nContent:\n\nMicrodeletions at chromosome bands 1q32-q41 as a cause of Van der Woude syndrome. Van der Woude syndrome (VWS) is an autosomal dominant disorder comprising cleft lip and/or cleft palate and lip pits. We reported previously a family whose underlying mutation is a 500-800 kb deletion localized to chromosome bands 1q32-q41 [Sander et al., 1994 Hum Mol Genet 3 576-578]. Along with cleft lip/palate and lip pits, affected relatives exhibit developmental delays, suggesting that the function of a gene nearby may also be disrupted. To further localize the VWS gene we searched for other deletions that cause VWS. An allele loss assay was performed using a novel highly polymorphic marker, D1S3753. From a panel of 37 unrelated individuals, we detected an allele loss in one family, indicating the presence of a deletion. In this family, the phenotype in three generations of affected individuals was confined to the cardinal signs of VWS. Surprisingly, mapping of the new deletion showed that it extended 0. 2-1 Mb beyond the proximal breakpoint for the deletion described previously. No deletions were detected in seven cases of popliteal pterygia syndrome, 76 cases of mixed syndromic forms of cleft lip and palate, and 178 cases of nonsyndromic cleft lip and palate.", "role": "user" }, { "content": "{\"Disease\": [\"VWS\", \"cleft palate\", \"Van der Woude syndrome\", \"lip pits\", \"cleft lip/palate\", \"nonsyndromic cleft lip and palate\", \"popliteal pterygia syndrome\", \"autosomal dominant disorder\", \"syndromic forms of cleft lip and palate\", \"developmental delays\", \"cleft lip\"]}", "role": "assistant" } ]

[ { "content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: A review of dynamic vehicle routing problems \nChapter Title: Solution Methods \n1. Abstract of Cited Paper (BIB001): Real-time decision problems are playing an increasingly important role in the economy due to advances in communication and information technologies that now allow realtime information to be quickly obtained and processed (Seguin et al., 1997). Among these, dynamic vehicle routing and dispatching problems have emerged as an intense area of research in the operations research community. Numerous examples may be found in Haines and Wolfe (1982), Powell, Jaillet and Odoni (1995) and Psaraftis (1995). In these problems, a set of vehicles is routed over a particular time horizon (typically, a day) while new service requests are occuring in real-time. With each new request, the current solution may be reconfigured to better service the new request, as well as those already assigned to a route. \n2. Abstract of Cited Paper (BIB002): Abstract In real-time fleet management, vehicle routes are built in an on-going fashion as vehicle locations, travel times and customer requests are revealed over the planning horizon. To deal with such problems, a new generation of fast on-line algorithms capable of taking into account uncertainty is required. Although several articles on this topic have been published, the literature on real-time vehicle routing is still disorganized. In this paper the research in this field is reviewed and some issues that have not received attention so far are highlighted. A particular emphasis is put on parallel computing strategies. \n3. Abstract of Cited Paper (BIB003): An important, but seldom investigated, issue in the field of dynamic vehicle routing and dispatching is how to exploit information about future events to improve decision making. In this paper, we address this issue in a real-time setting with a strategy based on probabilistic knowledge about future request arrivals to better manage the fleet of vehicles. More precisely, the new strategy introduces dummy customers (representing forecasted requests) in vehicle routes to provide a good coverage of the territory. This strategy is assessed through computational experiments performed in a simulated environment. \n4. Abstract of Cited Paper (BIB004): This paper reviews and classifies the work done in the field of dynamic vehicle routing. We focus, in particular, on problems where the uncertainty comes from the occurrence of new requests. Problem-solving approaches are investigated in contexts where consolidation of multiple requests onto the same vehicle is allowed and addressed through the design of planned routes. Starting with pure myopic approaches, we then review in later sections the issues of diversion and anticipation of future requests \n5. Abstract of Cited Paper (BIB005): In the past 30 years, commercial transport traffic has more than doubled in both Europe and North America. Asian commercial transport traffic over this period of time has likely increased even more. Traffic jams are routine and they can happen in any segment of the highway system at any time. Moreover, manufacturing companies increasingly apply just-in-time practices in order to cut down inventory costs. As any mismatch between supply and demand can result into significant disturbances of manufacturing processes, just-in-time practices necessitate punctual, reliable, and flexible transportation. Emerging technologies in real-time communications systems provide the means for commercial vehicle operators to meet the increasingly complex customer expectations in a highly dynamic environment with unreliable traffic conditions. FLEET TELEMATICS: Real-Time Management and Planning of Commercial Vehicle Operations combines wireless telematics systems with dynamic vehicle routing algorithms and vehicle-positioning systems to produce a telematics-enabled information system that can be employed by commercial fleet operators for real-time monitoring, control, and planning. The book presents a Messaging & Fleet Monitoring System that automatically identifies deviations between the planned and the current state of the transportation system and a Dynamic Planning System (DPS) that provides real-time decision support considering the current state of the transportation system. The DPS uses newly developed dynamic vehicle routing algorithms to find high-quality solutions and adjust schedules and routes immediately. \n6. Abstract of Cited Paper (BIB006): We consider online Vehicle Routing Problems (VRPs). The problems are online because the problem instance is revealed incrementally. After providing motivations for the consideration of such online problems, we first give a detailed summary of the most relevant research in the area of online VRPs. We then consider the online Traveling Salesman Problem (TSP) with precedence and capacity constraints and give an online algorithm with a competitive ratio of at most 2. We also consider an online version of the TSP with m salesmen and we give an online algorithm that has a competitive ratio of 2, a result that is best possible. We also study polynomial-time algorithms for these problems. Finally, we introduce the notion of disclosure dates, a form of advanced notice which allows for more realisticcompetitive ratios. \n7. Abstract of Cited Paper (BIB007): This chapter examines the evolution of research on dynamic vehicle routing problems (DVRP). We de?ne the DVRP and show how it is di?erent from the traditional static vehicle routing problem. We then illustrate the technological environment required. Next, we discuss important characteristics of the problem, including the degree of dynamism, elements relevant for the system objective, and evaluation methods for the performance of algorithms.The chapter then summarizes research prior to 2000 and focuses on developments from 2000 to present. Finally, we o?er our conclusions and suggest directions for future research. \n8. Abstract of Cited Paper (BIB008): This paper presents a methodology for classifying the literature of the Vehicle Routing Problem (VRP). VRP as a field of study and practice is defined quite broadly. It is considered to encompass all of the managerial, physical, geographical, and informational considerations as well as the theoretic disciplines impacting this ever emerging-field. Over its lifespan the VRP literature has become quite disjointed and disparate. Keeping track of its development has become difficult because its subject matter transcends several academic disciplines and professions that range from algorithm design to traffic management. Consequently, this paper defines VRP's domain in its entirety, accomplishes an all-encompassing taxonomy for the VRP literature, and delineates all of VRP's facets in a parsimonious and discriminating manner. Sample articles chosen for their disparity are classified to illustrate the descriptive power and parsimony of the taxonomy. Moreover, all previously published VRP taxonomies are shown to be relatively myopic; that is, they are subsumed by what is herein presented. Because the VRP literature encompasses esoteric and highly theoretical articles at one extremum and descriptions of actual applications at the other, the article sampling includes the entire range of the VRP literature.\n\nReview Chapter:", "role": "user" }, { "content": "Few research was conducted on dynamic routing between the work of Psaraftis BIB001 in 1980 and the late 1990s. However, the last decade has seen a renewed interest for this class of problems BIB009 , with solution techniques ranging from linear programming to metaheuristics. This section presents the major contributions in this field, and the reader is referred to the reviews, books, and special issues by Gendreau and Potvin BIB002 , Ghiani et al. BIB003 , Goel BIB006 , Ichoua , Ichoua et al. BIB004 BIB005 , Jaillet and Wagner BIB007 , Larsen et al. BIB008 , and Zeimpekis et al. , to complement our review.", "role": "assistant" } ]

[ { "content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nCoronavirus causes a disease with high infectivity and pathogenicity, especially SARS in 2003, MERS in 2012, and COVID-2019 currently. The spike proteins of these coronaviruses are critical for host cell entry by receptors. Thus, searching for broad-spectrum anti-coronavirus candidates, such as spike protein inhibitors, is vital and desirable due to the mutations in the spike protein. In this study, a combination of computer-aided drug design and biological verification was used to discover active monomers from traditional Chinese medicine. Surface plasmon resonance (SPR) assays and NanoBit assays were used to verify the predicated compounds with their binding activities to spike proteins and inhibitory activities on the SARS-CoV-2 RBD/ACE2 interaction, respectively. Furthermore, an MTT assay was used to evaluate the cell toxicities of active compounds. As a result, glycyrrhizic acid (ZZY-44) was found to be the most efficient and nontoxic broad-spectrum anti-coronavirus molecule in vitro, especially, the significant effect on SARS-CoV-2, which provided a theoretical basis for the study of the pharmacodynamic material basis of traditional Chinese medicine against SARS-CoV-2 and offered a lead compound for further structural modification in order to obtain more effective candidate drugs against SARS-CoV-2.", "role": "user" }, { "content": "[\"Treatment\", \"Mechanism\"]", "role": "assistant" } ]

[ { "content": "Given the following biomedical passages, answer the question succinctly. Ensure your response is precise and limited to the answer only.\n\nQuestion: Which molecule is targeted by Camrelizumab?\n\nPassages: Camrelizumab (SHR-1210) is a humanised anti-programmed death-1 (anti PD-1) antibody.\nThe PD-1 antibody camrelizumab was well tolerated in patients with nasopharyngeal carcinoma.\nAs decitabine is known to boost T-cell function, we assessed the safety and efficacy of anti-PD-1 camrelizumab alone versus decitabine-primed camrelizumab in patients with relapsed/refractory cHL.\nCamrelizumab (SHR-1210) is a humanised anti-programmed death-1 (anti PD-1) antibody.\nDecitabine plus camrelizumab may reverse resistance to PD-1 inhibitors in patients with relapsed/refractory cHL.\nAddition of Low-Dose Decitabine to Anti-PD-1 Antibody Camrelizumab in Relapsed/Refractory Classical Hodgkin Lymphoma.\nCONCLUSION CR rate in patients with relapsed/refractory cHL who were clinically naïve to PD-1 blockade was significantly higher with decitabine plus camrelizumab than with camrelizumab alone.\nAs decitabine is known to boost T-cell function, we assessed the safety and efficacy of anti-PD-1 camrelizumab alone versus decitabine-primed camrelizumab in patients with relapsed/refractory cHL.\nRecent phase 1-2 trials reported manageable safety profiles and promising antitumor activities of anti-PD-1 drugs (pembrolizumab, nivolumab, camrelizumab and JS001) with/without chemotherapy in recurrent/metastatic nasopharyngeal carcinoma (RM-NPC), however head-to-head comparison among these regimens is lacking.\nCamrelizumab (SHR-1210) is a humanised anti-programmed death-1 (anti PD-1) antibody.\nAs decitabine is known to boost T-cell function, we assessed the safety and efficacy of anti-PD-1 camrelizumab alone versus decitabine-primed camrelizumab in patients with relapsed/refractory cHL.\nRecent phase 1-2 trials reported manageable safety profiles and promising antitumor activities of anti-PD-1 drugs (pembrolizumab, nivolumab, camrelizumab and JS001) with/without chemotherapy in recurrent/metastatic nasopharyngeal carcinoma (RM-NPC), however head-to-head comparison among these regimens is lacking.\nHere, we represent preliminary evidence for the comparative safety and efficacy of existing anti-PD-1 agents with/without chemotherapy in RM-NPC, which indicated that camrelizumab has the least toxicity profile and merits future investigation.\nCamrelizumab (AiRuiKa™), a programmed cell death 1 (PD-1) inhibitor being developed by Jiangsu Hengrui Medicine Co.\nLactate dehydrogenase and baseline markers associated with clinical outcomes of advanced esophageal squamous cell carcinoma patients treated with camrelizumab (SHR-1210), a novel anti-PD-1 antibody.\nAll patients were administered intravenous camrelizumab (SHR-1210), a novel anti-PD-1 antibody, at doses of 60 mg, 200 mg, or 400 mg (4-week interval after first dose followed by a 2-week schedule) until disease progression or intolerable toxicity.\nHere we describe a case of a novel pattern of RRP induced by anti-PD-1 blockade Camrelizumab 2 years after radiotherapy, with some focus on further understanding of this phenomenon.\nAfter 15 months, due to tumor progression and brain metastasis, he started with administration of anti-PD-1 blockade Camrelizumab (200 mg q2w) and stereotactic radiosurgery (SRS).\nWe aimed to assess efficacy and safety of the anti-PD-1 antibody camrelizumab versus investigator's choice of chemotherapy in previously treated patients.\nThis study aimed to assess the antitumour activity and safety of the anti-PD-1 inhibitor camrelizumab in pretreated patients with advanced hepatocellular carcinoma.\nIn our present report, we described a newly diagnosed non-small-cell lung cancer patient who suffered from focal vitiligo for approximately ten years and was treated with the anti-programmed cell death-1 receptor antibody camrelizumab (SHR-1210), which accelerated the aggravation of depigmentation of the skin over the whole body in just half a year.\nPATIENTS AND METHODS: In this open-label, single-arm, phase II study, the safety and efficacy of combined regimen of chemotherapy consisting of gemcitabine, vinorelbine, and pegylated liposomal doxorubicin (GVD) plus anti-PD-1 antibody camrelizumab was assessed in rrPMBCL.\nApatinib plus camrelizumab (anti-PD1 therapy, SHR-1210) for advanced osteosarcoma (APFAO) progressing after chemotherapy: a single-arm, open-label, phase 2 trial.\nWe further benchmarked the dissociation kinetics for three clinically approved PD-1 blockade mAbs (Nivolumab, Pembrolizumab, and Camrelizumab), intriguingly correlating well with the objective response rates in the hepatocellular carcinoma second-line treatment.\nPurpose: Camrelizumab inhibits PD-1 in non-clinical models and showed typical non-clinical pharmacokinetic (PK) and safety profiles for an IgG4 monoclonal antibody.\nCamrelizumab is a programmed cell death protein 1 inhibitor.\nsions: Our findings suggest that (I) PD-1 targeted immunotherapy with toripalimab, camrelizumab, or sintilimab yielded a promising outcome in Chinese HBV patients with HCC and that (II) immunotherapy was well tolerated generally and had manageable side effects. This\nately, the tumors dramatically shrank after one cycle of camrelizumab, an anti-programmed cell death-1 (PD-1) antibody developed by Chinese Hengrui Medicine. In concl\nWe report a case of a 68-year-old man diagnosed with pulmonary pleomorphic carcinoma who showed partial response after a single treatment with camrelizumab (PD1 monoclonal antibody)\nJECTIVE: To evaluate the immune-related adverse events (irAEs) induced by Camrelizumab, an anti-PD-1 antibody in a patient with gastric cancer.C\nRT OPINION: Camrelizumab is a selective, humanized, high-affinity IgG4 kappa mAb against PD-1. Ca\nINTRODUCTION: Camrelizumab (also known as SHR-1210), a humanized monoclonal antibody against PD-1, has been shown to block the binding of PD-1 to PD-L1 and consequently inhibit the immune escape of tumor cells\nThe structure of the camrelizumab/PD-1 complex reveals that camrelizumab mainly utilizes its heavy chain to bind to PD-1, while the light chain sterically inhibits the binding of PD-L1 to PD-1.\nHere, we demonstrate varied N-glycan composition in PD-1, and show that the binding affinity of camrelizumab, a recently approved PD-1-specific MAb, to non-glycosylated PD-1 proteins from E. coli is substantially decreased compared with glycosylated PD-1.\nThis study aimed to assess the antitumour activity and safety of the anti-PD-1 inhibitor camrelizumab in pretreated patients with advanced hepatocellular carcinoma.M\nINTRODUCTION: Camrelizumab (also known as SHR-1210), a humanized monoclonal antibody against PD-1, has been shown to block the binding of PD-1 to PD-L1 and consequently inhibit the immune escape o\nPurpose: Camrelizumab inhibits PD-1 in non-clinical models and showed typical non-clinical pharmacokinetic (PK) and safety profiles for an IgG4 monoclonal\nCamrelizumab (AiRuiKa™), a programmed cell death 1 (PD-1) inhibitor being developed by Jiangsu Hengrui Medicine Co. Ltd, recently received conditional approval in China for the treatment of relapsed or refractory classical Hodgkin lymphoma.\nThe PD-1 antibody camrelizumab plus the VEGFR2 inhibitor apatinib had efficacy in a phase II trial.\nPURPOSE: We assessed the efficacy and safety of camrelizumab (an anti-PD-1 monoclonal antibody) plus apatinib (a vascular endothelial growth factor [VEGFR]-2 tyrosine kinase inhibitor) in patients with advanced hepatocellular carcinoma (HCC).\nHowever, all three patients responded to low-dose decitabine, an epigenetic drug, in combination with camrelizumab (anti-PD-1 antibody), with only controllable adverse events, indicating that low-dose decitabine can sensitize PD-1/PD-L1 inhibitors.\nBackground: Camrelizumab is a promising anti-programmed cell death-1 agent for non-small cell lung cancer (NSCLC) and induces reactive capillary hemangiomas (RCHs).\nCamrelizumab is a programmed cell death protein 1 inhibitor; however, current evidence of its efficacy in PSC is lacking.\nCamrelizumab is a programmed death receptor-1 inhibitor originally developed in China for the treatment of refractory lymphoma.\nRecent phase 1-2 trials reported manageable safety profiles and promising antitumor activities of anti-PD-1 drugs (pembrolizumab, nivolumab, camrelizumab and JS001) with/without chemotherapy in recurrent/metastatic nasopharyngeal carcinoma (RM-NPC), however head-to-head comparison among these regimens is lacking.\nCamrelizumab, a programmed cell death 1 (PD-1) inhibitor, has been approved for the treatment of patients with relapsed or refractory classical Hodgkin lymphoma, nasopharyngeal cancer and non-small cell lung cancer.\nPURPOSE: Camrelizumab is an antibody against programmed death protein 1.\nAll patients were administered intravenous camrelizumab (SHR-1210), a novel anti-PD-1 antibody, at doses of 60 mg, 200 mg, or 400 mg (4-week interval after first dose followed by a 2-week schedule) until disease progression or intolerable toxicity.\nTherefore, we explored the efficacy and safety of a PD-1 checkpoint inhibitor camrelizumab in advanced or metastatic solid tumour with dMMR/MSI-H.\nAim: The present study evaluated the safety and efficacy of camrelizumab (a programmed death-1 antibody) in combination with microwave ablation (MWA) in advanced non-small cell lung cancer (NSCLC).", "role": "user" }, { "content": "programmed death-1", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nFinally,PGC-1alpha-/-micedonotrespondnormallytoavarietyofphysiologicanddietarystressesknowntoincreaseoxidativeenergydemands.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Examine the provided biomedical text and determine the answer to the question. Your response should be either \"yes\" or \"no\" based on the information given.\n\nQuestion: Is alternative splicing of apoptotic genes playing a role in the response to DNA or mitochondrial damage?\n\nText: Apoptosis promoted by UV in cells lacking p53 is prevented when the change in AS of the apoptotic gene bcl-x is reverted, confirming the relevance of this mechanism.\nWe demonstrate that E2F1 requires SC35 to switch the alternative splicing profile of various apoptotic genes such as c-flip, caspases-8 and -9 and Bcl-x, towards the expression of pro-apoptotic splice variants. Finally, we provide evidence that E2F1 upregulates SC35 in response to DNA-damaging agents and show that SC35 is required for apoptosis in response to these drugs.\nThis analysis revealed that DNA damage resulted in changes in splicing activity that modified the splicing pattern of Fas, a key pro-apoptotic, p53-inducible death receptor.\nBortezomib induces mitochondrial damage in native cells and also activates the UPR by splicing of Xbp-1 and induction of CHOP, which is significantly reduced by silencing of MUC4.\nThe tumour-suppressor protein p53 is an important activator of apoptosis. Although p53-deficient cancer cells are less responsive to chemotherapy, their resistance is not complete, which suggests that other apoptotic pathways may exist. A p53-related gene, p73, which encodes several proteins as a result of alternative splicing, can also induce apoptosis.\nInduction of apoptosis was significantly reduced in P388/SPR cells, as indicated by minimal DNA fragmentation. Analysis of oncogenes regulating apoptotic cell death revealed a marked decrease of bcl-2 in combination with a moderate reduction of bax protein, but a striking overexpression of the long form of the bcl-X protein.", "role": "user" }, { "content": "yes", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: I want to detect objects from images.\n\nKeywords: object detection images\n\nDataset Information:\nMiddlebury: The Middlebury Stereo dataset consists of high-resolution stereo sequences with complex geometry and pixel-accurate ground-truth disparity data. The ground-truth disparities are acquired using a novel technique that employs structured lighting and does not require the calibration of the light projectors.\nCOCO-Tasks: Comprises about 40,000 images where the most suitable objects for 14 tasks have been annotated.\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.\nOccludedPASCAL3D+: The OccludedPASCAL3D+ is a dataset is designed to evaluate the robustness to occlusion for a number of computer vision tasks, such as object detection, keypoint detection and pose estimation. In the OccludedPASCAL3D+ dataset, we simulate partial occlusion by superimposing objects cropped from the MS-COCO dataset on top of objects from the PASCAL3D+ dataset.\n\nAvailable Datasets: A: Middlebury B: COCO-Tasks C: COVERAGE D: OccludedPASCAL3D+", "role": "user" }, { "content": "Middlebury", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nantibiotic therapy directed against multiresistent bacteria is a significant cost driver in clinical medicine . due to various reasons ,\nthe costs of new antibiotics are comparatively high and some multiresistant bacteria can or should only be treated with new antibiotics .\nmoreover , most complicated bacterial infections requiring long treatment durations occur in the hospital setting , often in intensive care units .\nit is a well established notion that prolonged length of stay in the hospital ( los ) , the time spent in intensive care units ( icu days ) and the hours of mechanical ventilation ( hmv ) are the main cost drivers in this setting [ 1 - 6 ] .\nthe evaluation of the economical effectiveness of pharmacological therapies is gaining more and more importance .\nwhile most of these pharmacoeconomical analyses are intended to show effectiveness of a new drug versus the current standard - of - care from a healthcare system perspective ( cost - effectiveness studies , prospective modelling , using quality - adjusted - lifeyears ( qualys ) and other parameters ) , these studies do not necessarily answer the budget - related questions of clinicians or even the administrators in a hospital [ 7 - 10 ] .\nfinally , in most developed countries so - called diagnosis - related groups ( drg ) are used for hospital budgeting , reimbursement or resource allocation .\ndrgs are payment groups that determine the reimbursement for a certain type of patient group that was found to be economically homogenous .\nfor example , the germany system provides drg - directed payment for respiratory tract infections with or without \" complications or comorbidities ( cc ) \" .\nthe following table gives an overview of drgs for respiratory tract infections , their cost - weights , their payment ( assuming a base price for cost weight 1.0 of 2,900.- ) and the related length of stay ( los ) in hospital , see table 1 .\noverview of drg e77 - respiratory tract infections drgs are common instruments for hospital reimbursement or budget allocation in most developed countries in the world .\nnearly every country in europe has drg - systems in use . without drilling too deep into the complicated german drg system and translating all the drg - denominators , we point out , that drg payments for one particular set of conditions - like respiratory tract infections - vary according to various cost - modifiers . one of these factors is the occurence of multiresistent bacteria ( see bold letters in the table ) . however , the payment for a given drg is fixed at a certain amount .\nthe german costing study includes annually calculated average costs in a matrix of cost types ( such as staff , pharmaceuticals , etc . ) and cost centers ( such as normal ward , or , icu , etc . ) .\nthis results in a costing matrix with up to 100 so - called cost modules .\nmoreover a national los \" benchmark \" is available , and these data are published in the internet ( for each drg ) . after the introduction of drgs , optimizing\nthe los has turned out as an important lever to achieve higher profitability . yet , this notion has not yet been fully acknowledged by everyone in the medical community . as an example , table 2 shows the cost matrix of e77b - respiratory infections with complex diagnosis or catastrophic cc , w / o complex intensive care for children , with treatment of multiresistent bacteria , hospital stay longer than 72 hrs cost matrix for drg e77b based on the known \" limits \" that must be observed to avoid losing money in drg - reimbursed treatments , analyses can be done on an individual hospital 's data to determine whether the current treatment strategies in a hospital lead to a sustainable balance of cost and medical need . coming from this idea ,\nthe development of a drg - based approach to the analysis of infections and the prove - of - concept were the major questions to be dealt with in this publication .\nas in drg - based payment systems , the coding of diagnoses as primary ( the reason why the patient got admission to the hospital ) and secondary ( relevant complications and comorbidities that caused resource consumption ) diagnoses is the cornerstone of finding the correct drg , we assumed that the coding quality in terms of completeness and accuracy pretty well reflects the clinically relevant situation , especially in case of infections .\nwe developed an algorithm that contains over 100 icd - codes representing infections and/or bacterial pathogens .\nhospital - acquired versus community - acquired infections were assumed to be represented by the assignment as \" primary \" ( or main ) diagnosis or \" secondary \" diagnosis .\nmoreover , we tried to rule out coding errors such as the implausible use of the same icd code as primary and secondary diagnosis .\nhospital acquired pneumonias ( hap ) may be indicated by a special icd - code ( u69.00 ! ) used to distinguish between community acquired pneumonia ( cap ) and hap in the german system . using the minimal basic dataset ( mbds ) of a country - in germany\n21-data - for one hospital or a set of hospitals , it is possible to \" decode \" infections from the drg data .\ntable 3 displays the basic data model used to retrieve information on infections and bacterial pathogens from coded icd-10 data . entity relationship model of the \" decoding infections \" database as in some cases , bacterial pathogens are part of the icd - code of the infections , counting infections and the bacteria involved respect this fact by listing some icd - codes as infections and as bacteria . see table 4 for an example .\nassociation of bacterial pathogens and icd - codes using this methodology , we were able to decode infections from routine drg data .\nafter implementation of these data in a business information warehouse ( bi ) software , it is now possible to answer the following questions : - which infections caused by which bacteria occur in the hospitals ? - which los is associated to which infection and does it imply a risk of losing reimbursement for the hospital ? - which drgs are the ones most likely impacted by infections ? once identified , the drgs with a high number of infections or those patients that cause the highest loss in drg - reimbursement due to infections may be further analyzed . in peer reviews , the antibiotic therapy strategy for each case may be compared against the expected cost average in the respective drg , the actual cost and the potential cost outcome achieved by using a different therapeutic strategy .\ndifferences in length of stay that cause inefficiency can be detected and assigned to various types of infections .\ntable 5 shows an overview of certain infections and the los of patients having these infections compared to the los of patients being in the hospital without an infection .\nlos with and without infections without infections : 7,3 days ( green block line ) with hospital acquired pneumonia ( hap ) 21 - 28 days ( pink line ) if the los is higher with an infection , this does not necessarily imply that there is an economic loss for the hospital , as expensive cases usually also entail more revenue . by knowing that los is the key cost driver in a drg - based system\n, an analysis can be performed how many patients meet the average los ( alos ) of the drg - as defined by the national benchmark - and how many patients stay longer .\nthose patients staying longer are the patients that cost more than the hospital is reimbursed for . tables 6 and 7 display los curves ( absolute = red curve , cumulative = brown curve ) for 1 ) all patients in a hospital and 2 ) patients having a postoperative infection such as wound infections , peritonitis or other or - related infections : los for all patients of a hospital - good result : 76% of all patients can be discharged before reaching the alos ( mvd in the figure ) los distribution for patients with postoperative infections although the national alos of these drgs is 21.9 days ( indicating that the drg - reimbursement is higher than the hospital average ) only 50% of these patients can be discharged before alos .\nthat means half of the patients cost presumably more than the hospital is being reimbursed for . using individual patient cases for analysis ,\nthe individual drg may be used and the actual antibiotic therapy strategy may be compared versus an optimum setting .\nquite often it is possible to show that a state - of - the art therapy causes less cost .\ntable 8 shows a case simulation for a given drg - result ( a13e - mechanical ventilation 95 - 250 hrs ) . by examining the medical record ,\nthe reviewers found that by optimizing antibiotic therapy ( i.e. starting the eventually effective therapy with tigecycline 3 days earlier ) the icu - stay and the los could have been 2 days shorter .\nmoreover , by starting the adequate therapy earlier , three days of ineffective and expensive therapy ( in this case meropenem plus ciprofloxacin ) could have been avoided . in the end\n, the hospital would have had small gain in this drg rather than a loss as in the original situation .\ncomparing national standard cost ( section \" inek - daten \" in the picture ) with actual cost ( section \" ist - situation \" ) shows that the hospital spends more than it is reimbursed ( -1,881.23 ) . by simulating the case with the optimized therapy option ( section \" variante \" in the picture ) the economic result shows a surplus of 1,223.10.\ndrg and individual case - based simulation of optimized antibiotic therapy strategies the findings of other studies and the results from the data easily can be reproduced also in the results of individual case reviews .\nthe main cost drivers are : - length of stay in hospital possible reason : delayed start of effective antibiotic therapy - complications related to antibiotic therapy most frequent : renal failure - use of inadequate antibiotics that turn out to be in effective - prolonged duration of mechanical ventilations\ndecoding infections from drg routine data is feasible , comparatively easy and can be done with little effort of time and expenses as the data are easily available for each hospital .\nvalidations in several hospitals were done by using the results and reviewing selected medical records to verify whether the \" decoded \" infection was actually mentioned in the record .\nvery little variances were found to be due to coding variations . while germany has coding standards for diagnoses and procedures , errors may still occur .\nthe actual accuracy of the coding is very good . according to the medical services of the statuary health insurance in germany ( mds ) 11% of all hospital drg reimbursements\nare claimed to be wrong and in 40% of the claims actual errors are found .\nthat means that nearly 96% of the coding is correct , as no claim is issued or no error is found .\nit is clearly possible to identify cases that are more expensive than the drg system recommends . in many of these cases\n, sound medical reasons caused the extended los , but there is a substantial part of the reviewed cases that suggest opportunities to optimize the antibiotic therapy strategy .\nanalysis on the basis of drg routine data is an easy way to \" decode \" infections in a hospital setting and directly connect them to economic results .\nestablishing a peer review of the medical records of cases producing financial loss may identify opportunities to optimize treatment strategies .\nlos , number of complications , icu - days and hours of mechanical ventilation are good endpoints to be used in the assessment of the economical effects of individual antibiotics .\nalos : average length of stay in a given drg , basis for determining whether a patient causes more costs than reimbursement ; cap : community acquired pneumonia ; cc : complications and comorbidities , conditions ( like secondary diagnoses ) that cause higher resource consumption ; drg : diagnoses related groups , systems to classify patients based on their resource consumptions ; hap : hospital acquired pneumonia ; hmv : hours of mechanical ventilation ; icu - days : treatment days on an intensive care unit ; los : length of stay in hospital ; mds : medical services of the statuary health insurance in germany ; qaly : quality adjusted life years ; w : with ; w / o : without .", "role": "user" }, { "content": "the cost of treatments especially in conditions where multiresistant bacteria are involved are a major issue in times where in most developed countries in the world payment systems based on diagnoses - related - groups ( drg ) are in place . \n there is great evidence that especially the length of stay in hospital ( los ) , the time in the intensive care unit ( icu - days ) and the hours of mechanical ventilation ( hmv ) are major cost drivers.while established methods of pharmacoeconomical analyses focus on the efficiency of drugs from healthcare system perspective , these data are often not sufficient for improving treatment strategies in a given hospital context.we developed a system that allows the analysis of patients with severe infections on the basis of routine data that is also used for reimbursement . \n these data contain a lot of information concerning the clinical conditions . by using the icd - coding we developed an algorithm which allows the detection of patients with infections and gives information on the potential financial outcome of these patients . by using the analysis it is possible to identify subsets of infections and the patient records that had a potentially negative drg - result , i.e. the costs are higher than the reimbursement . \n when identified the patient records undergo a peer review , where the clinical situation and the antibiotic therapy are reviewed by medical experts . in case simulations it is possible to find out if a different therapeutic approach , e.g. by different choices in initial ( empirical ) antibiotic treatment would have caused other outcomes.data driven analyses together with peer reviews of patient records are a useful tool to examine antibiotic treatment strategies and to establish changes that again can be reviewed on a regular basis . doing this a continous improvement process \n can be established in hospitals which can lead to a better balance of clinical and economical outcomes in patients with severe infections . \n moreover these analyses are helpful in assessing the literature on economical benefits of new therapies .", "role": "assistant" } ]

[ { "content": "Examine the provided biomedical text and determine the answer to the question. Your response should be either \"yes\" or \"no\" based on the information given.\n\nQuestion: Is p53 a transcription factor?\n\nText: As a transcription factor, p53 mainly exerts its tumor suppressive function through transcriptional regulation of many target genes.\np53 functions primarily as a sequence-specific transcription factor that controls the expression of hundreds of protein-coding genes and noncoding RNAs, including microRNAs (miRNAs) and long noncoding RNAs (lncRNAs).\np53 is a transcription factor", "role": "user" }, { "content": "yes", "role": "assistant" } ]

[ { "content": "Consider the following research inquiry and associated key terms. Review the dataset summaries provided and determine which datasets are suitable for addressing the research question. Base your decision on your understanding of machine learning datasets.\nProvide your answer as a JSON list. For example, for the inquiry \"Semi supervised image classification\", a possible response could be: [\"CIFAR-10\", \"CIFAR-100\"]. Ensure the response contains only the dataset names in JSON format.\n\nResearch Inquiry: I want to learn a method for synthesizing realistic and diverse images without paired training images.\n\nKey Terms: image-to-image translation images\n\nDataset Summaries:\nGTA5: The GTA5 dataset contains 24966 synthetic images with pixel level semantic annotation. The images have been rendered using the open-world video game Grand Theft Auto 5 and are all from the car perspective in the streets of American-style virtual cities.\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.\nDIV2K: DIV2K is a popular single-image super-resolution dataset which contains 1,000 images with different scenes and is splitted to 800 for training, 100 for validation and 100 for testing. It was collected for NTIRE2017 and NTIRE2018 Super-Resolution Challenges in order to encourage research on image super-resolution with more realistic degradation.\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.\nMuseScore: The MuseScore dataset is a collection of 344,166 audio and MIDI pairs downloaded from MuseScore website. The audio is usually synthesized by the MuseScore synthesizer.\nACDC: The goal of the Automated Cardiac Diagnosis Challenge (ACDC) challenge is to: compare the performance of automatic methods on the segmentation of the left ventricular endocardium and epicardium as the right ventricular endocardium for both end diastolic and end systolic phase instances; compare the performance of automatic methods for the classification of the examinations in five classes (normal case, heart failure with infarction, dilated cardiomyopathy, hypertrophic cardiomyopathy, abnormal right ventricle). The overall ACDC dataset was created from real clinical exams acquired at the University Hospital of Dijon.\nFaceForensics++: FaceForensics++ is a forensics dataset consisting of 1000 original video sequences that have been manipulated with four automated face manipulation methods: Deepfakes, Face2Face, FaceSwap and NeuralTextures. The data has been sourced from 977 youtube videos and all videos contain a trackable mostly frontal face without occlusions which enables automated tampering methods to generate realistic forgeries.\n\nDataset Options: A: GTA5 B: COVERAGE C: DIV2K D: CelebA E: MuseScore F: ACDC G: FaceForensics++", "role": "user" }, { "content": "[\"GTA5\", \"CelebA\"]", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: I want to train a fully supervised model for machine reading comprehension.\n\nKeywords: machine reading comprehension text paragraph-level\n\nDataset Information:\nMC-AFP: A dataset of around 2 million examples for machine reading-comprehension.\nDRCD: Delta Reading Comprehension Dataset (DRCD) is an open domain traditional Chinese machine reading comprehension (MRC) dataset. This dataset aimed to be a standard Chinese machine reading comprehension dataset, which can be a source dataset in transfer learning.\nVisualMRC: VisualMRC is a visual machine reading comprehension dataset that proposes a task: given a question and a document image, a model produces an abstractive answer. You can find more details, analyses, and baseline results in the paper, VisualMRC: Machine Reading Comprehension on Document Images, AAAI 2021.\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\nAvailable Datasets: A: MC-AFP B: DRCD C: VisualMRC D: SQuAD", "role": "user" }, { "content": "SQuAD", "role": "assistant" } ]

[ { "content": "Examine the provided biomedical abstract. Identify and list entities based on the specified categories: [\"Brand\", \"Drug\", \"DrugGroup\", \"UnapprovedDrug\"].\n\nFormat your findings as a JSON object: {\"Brand\": [\"Aspirin\", ...], \"DrugGroup\": [\"Salicylate\", ...], \"Drug\": [\"Phenobarbital\", ...], \"UnapprovedDrug\": [\"Heroin\", ...]}. Each key represents an entity type, and the corresponding value is a list of entities. If no entities are found for a type, use an empty list [].\n\nFocus solely on producing the JSON object.\n\nSource Text:\n\nTetracycline, a bacteriostatic antibiotic, may antagonize the bactericidal effect of penicillin and concurrent use of these drugs should be avoided.", "role": "user" }, { "content": "{\"Brand\": [], \"Drug\": [\"penicillin\", \"Tetracycline\"], \"DrugGroup\": [\"bacteriostatic antibiotic\"], \"UnapprovedDrug\": []}", "role": "assistant" } ]

[ { "content": "Analyze the given text and respond to the inquiry. Choose from: \"YES\", \"NO\", or \"MAYBE\".\n\nText:\n(OBJECTIVE) To determine whether prostate morphology or technique used has any effect on postoperative outcomes after holmium laser enucleation of the prostate.\n(MATERIALS AND METHODS) A retrospective review of prospectively collected data was completed for all patients undergoing a holmium laser enucleation of the prostate at our institution. Prostate morphology was classified as either \"bilobar\" or \"trilobar\" according to the cystoscopic appearance. The baseline characteristics, complications, and postoperative outcomes were collected.\n(RESULTS) A total of 304 patients with either \"bilobar\" (n = 142) or \"trilobar\" (n = 162) prostate morphology were included. The trilobar group was more likely to have longer operative times (112 vs 100 minutes, P = .04), although this difference was not significant on multivariate analysis. The postoperative outcomes were similar between the 2 groups for American Urological Association symptom score, change in American Urological Association symptom score, bother score, maximal flow rate, change in maximal flow rate, postvoid residual urine volume, and complication rate. However, the trilobar group had a significantly greater decrease in their PVR urine volume (296 vs 176 mL, P = .01), a difference that persisted on multivariate analysis. A subset analysis of the trilobar prostates revealed that performing a 2-lobe technique achieved shorter operative and enucleation times, although the difference was not significant.\n\nInquiry:\nDoes prostate morphology affect outcomes after holmium laser enucleation?\n\nResponse:", "role": "user" }, { "content": "YES", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nuterine cervical cancer is one of the most common cancers diagnosed in women of reproductive age .\nthanks to the progress of the cervical cancer screening system , the mortality rate of patients with cervical cancer has decreased in japan over the past twenty years1 . however , the number of patients with early invasive cervical cancer during reproductive age is increasing .\n, radical trachelectomy ( rt ) with pelvic lymphadenctomy has become a valuable fertility - preserving treatment option for these patients in japan2 - 4 .\nwe have already performed 20 vaginal rts with laparoscopic lymphadenectomy , and have experienced five pregnancies and four deliveries so far . as we reported before , in pregnant patients who undergo this operation , premature labor and the following occurrence of preterm premature rupture of the membrane ( pprom )\nvarious factors such as lack of a protective effect against vaginal infection or the lack of mechanical support of the residual cervix due to the dissection of the uterine cervix and the division of supplying arteries might induce such complications . on the basis of these complications , there might be reduced blood supply to the remaining uterus . furthermore ,\nif the blood supply to the uterus is reduced , it could be a cause of intrauterine growth retardation ( iugr ) or intrauterine fetal death ( iufd)5 . in this report , we studied changes of the blood supply to the uterus in two patients who experienced pregnancy and delivery .\nin the period from january 2003 through december 2009 , a total of 20 women with early - stage invasive uterine cancer underwent vaginal rt with lymphadenectomy in sapporo medical university hospital . among them , five patients became pregnant , and four of them delivered by cesarean section . in this study , we performed 3-d ct scanning for assessment of the blood supply to the uterus in two patients who had undergone vaginal rt with pelvic lymphadenectomy after delivery .\n3-d ct scanning was also performed in a woman with normal uterus after the delivery for the assessment of an intra - abdominal disease , and her picture was used as a control .\nthe clinical courses of pregnancy , fetal growth measured by ultrasonography , and results of histopathological examination of the placenta were also compared between the two patients .\nas a pap smear at a local clinic showed atypical squamous cells corresponding to cervical intraepithelial neoplasia ( cin ) 3 , she was referred to our hospital .\nshe received diagnostic laser conization , and she was diagnosed as having stage ib1 squamous cell carcinoma .\nthen she underwent vaginal rt and laparoscopic lymphadenectomy , and she became pregnant six months after the operation by artificial intrauterine insemination .\nshe was admitted to our hospital with a diagnosis of threatened abortion at 17 weeks of gestation . in spite of bed rest , disinfection therapy , and the administration of ritodrine\nshe was diagnosed as having stage ib1 cervical squamous cell carcinoma by diagnostic laser conization at a local hospital .\nshe also underwent vaginal rt and laparoscopic lymphadenectomy . at 14 months after the operation , she became pregnant without any artificial reproductive techniques .\nwe recommended her to enter our hospital early in the second trimester in spite of no signs of threatened abortion .\ndaily vaginal disinfection with popidone iodine , bed rest , and administration of ritodrine and an ulinastatin vaginal suppository were continued as a new follow - up modality for pregnant patients who received rt .\nfinally , at 35 weeks of gestation , scheduled cesarean section was performed for her .\nthe postpartum courses of the patients were not remarkable , and no signs of recurrence have been seen for either patient up to now .\nbriefly , a rim of vaginal mucosa was delineated circumferentially and excised so that the anterior and posterior mucosae could cover the cervix .\nafter these procedures , the cervix was amputated approximately 10 mm below the isthmus , a nylon suture was placed around the cervix , and a sturumdorf suture was placed to cover the surface of the cervix .\nfigures 1 and 2 show the blood vessel distribution in the uterus for both patients .\nidentification of blood vessels was performed by a radiologist ( m.t ) . in vaginal rt\n, we usually amputate the cervix at the level of the uterine artery , which corresponds to approximately 10 mm below the isthmus . in this procedure , we usually ligate and cut the descending branches of the uterine arteries and vaginal arteries\n2 show that the descending branches of uterine arteries and vaginal arteries could not be seen in either patient .\nnew arterial vascularization from the ascending branches of uterine arteries arose , and these new vessels seemed to supply blood to the remaining cervix , including the neo - cervix . on the 3-d ct scan , no ischemic areas were seen in the remaining uterus .\npatient 1 received emergent cesarean section at 24 weeks of gestation because of sudden premature rupture of the membrane .\ntherefore the birth weight of the child of patient 1 was 588 g , though she survived thanks to the efforts of neonatologists and co - workers .\nfetal growth of patient 2 was also within the normal range over the pregnancy period .\n4 shows changes of cervical length as measured by transvaginal ultrasonography in the both patients .\nthe remaining cervix of patient 1 was shorter than that of patient 2 over the pregnancy period .\nfurthermore as shown in table 1 , the placenta from patient 1 showed the existence of severe chorioamionitis , which might have been a cause of pprom ; however , no ischemic changes of the placenta were detected histopathologically .\nthe placenta of patient 2 , who delivered at 35 weeks of gestation , did not show ischemic changes either .\nin this study , we looked at changes of blood supply to the uterus after vaginal rt in two patients who experienced pregnancy .\nthe effects of blood supply on the fetal growth and the placental changes were also studied .\nrt removes the cervix of the uterus , parametrium , and upper vagina through a vaginal approach and is designed to preserve childbearing potential in young patients with cervical cancer .\nthis procedure requires ligation and cutting the descending branches of uterine arteries as well as the division of vaginal arteries .\nthe uterus has six main supplying arteries : two ovarian , two uterine , and two vaginal arteries .\nit is said that four of the six arteries are required to ensure uterine viability5 . however , almost half of the supplying arteries are cut after vaginal rt .\nreported that the blood flow reduction after ovarian artery ligation was more pronounced than after uterine artery ligation in rats , which means that the ovarian artery might be the major contributor of blood flow to the uterus . in this study , 3d ct scans also showed sufficient blood flow to the uterine body through both ovarian arteries , the remaining ascending branches of uterine arteries , and a new network of vessels .\na decrease of blood supply to the uterus can cause abortion or intrauterine growth retardation ( iugr ) of the fetus 6 . in these conditions ,\nischemic changes of the placenta include an increase of avascular villi , syncytial knots , and an immature syncytial sprout , or increased lesions of placental infarction6,7 .\nfurthermore , as we reported before , molecular biological changes such as increased expression of apoptosis - related genes are also seen8 .\nhowever , the placentas of the both patients in this study showed no such ischemic changes . furthermore , fetal growth of both patients up to delivery was within the normal range .\nthese results suggest that division of the descending branches of uterine arteries and vaginal arteries does not seem to affect fetal growth .\ndoes division of descending branches of uterine arteries and vaginal arteries affect the function of the neo - cervix ?\nlack of mechanical support of the residual cervix , ascending infection and chorioamnonitis , caused by disruption of the endocervical glands and reduced secretion of mucus , have been thought be causes of pprom .\nas we have shown in this study , the remaining cervix of patient 1 after vaginal rt was found to be shorter than that of patient 2 by transvaginal ultrasonographic assessment over the pregnancy period .\nalthough patient 1 suffered from pprom at 23 weeks of gestation , the blood supply to the lower segment of the uterus did not show any differences between the two patients .\nfor this patient , the cause of pprom might have been chorioamnionitis caused by the reasons described above .\nrt now has become an acceptable treatment modality in patients with early invasive uterine cancer who hope for preservation of fertility .\nhowever , vaginal rt is completely different from laser conization from the point of view of targeting lesions and postoperative invasiveness .\nalthough more than 300 pregnancies have been reported since dargent reported his first series of radical trachelectomies in 1994 9,10,11 , there are still few reports on pregnancy complications after rt .\nit is known that lack of a protective effect against vaginal infection or the lack of mechanical support of the residual cervix due to the dissection of the uterine cervix might be a cause of pprom , and the following occurrence of preterm premature delivery .\nfurthermore , as martin et al . reported , in patients with high risk of recurrence , adjuvant therapies such as radiation therapy or chemotherapy might be necessary after rt .\nhowever , as far as we know , effects of changes of blood supply to the uterus after rt have never been discussed . in this report\n, we looked at changes of the blood supply to the uterus in two patients who experienced pregnancy and delivery .\nhowever , we believe that the division of the descending branches of uterine arteries and vaginal arteries leads neither to a decrease of blood supply to , nor to the dysfunction of , the neo - cervix . and these procedures also do not affect the fetal growth and the placental growth . furthermore , neovascularisation of the remaining uterine cervix would have been completed relatively early after the operation because both patients became pregnant within two years .\nthus effects of changes of uterine blood flow on pregnancy courses seemed to be minimal .\nhowever , the following up of pregnancy in patients who underwent rt is still a challenge for obstetrician .\nfurther clinical investigation to prevent pregnancy - related complications in patients who underwent rt would improve the pregnancy outcome of these patients .", "role": "user" }, { "content": "background . vaginal radical trachectomy ( rt ) ligates and cuts several arteries supplying the uterus . \n changes of blood supply to the uterus in two patients who experienced pregnancy and delivery were studied by using 3-d ct scanning . \n effects of changes of blood supply to the uterus on the pregnancy courses were also examined.methods . \n vascular distribution in the uterus was studied in two patients who received vaginal rt after delivery . \n effects of changes of vascular distribution after vaginal rt were studied with respect to pregnancy courses and cervical functions.results . \n new arterial vascularization from the ascending branches of uterine arteries or other arteries occurred , and these new vessels seemed to supply blood to the remaining cervix . \n differences of fetal growth and histopathological changes in the placenta between the two patients could not be detected.conclusion . \n ligation and cutting of several supplying arteries by rt induces new areterial vascularization and it does not seem to affect fetal growth and placental function .", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nthis study was conducted in accordance with a protocol approved by an institutional animal care and use committee of the national institutes of health . all laboratory work with potentially infectious materials\nwas conducted in a biosafety level facility at the rocky mountain laboratories ( division of intramural research / national institute of allergy and infectious diseases / national institutes of health ) .\nthree cynomologus macaques were vaccinated with 1 dose of 10 pfu of vsvg / lasvgpc , a live - attenuated , recombinant viral vaccine in which the vsv surface glycoprotein has been replaced with those of lasv , by intramuscular injection as described ( 4 ) .\nanother age - matched control animal was vaccinated with an irrelevant vsv - based vaccine ( vsvg / andvgpc ) ( 5 ) . at 28 days postvaccination\n, the 4 nhps were challenged with a lethal dose of lasv ( 10 50% tissue culture infectious doses [ tcid50s ] ) ( 9 ) .\nthe control animal showed signs of lassa fever 710 days postinoculation and was euthanized 13 days postchallenge because of severity of disease .\nclassic indicators of lassa fever , including decreased total protein and albumin ; increased serum levels of alanine aminotransferase , aspartate aminotransferase , amylase , blood urea nitrogen , and alkaline phosphatase ; and hematologic abnormalities , including thrombocytopenia and lymphopenia , were apparent in this animal .\nvirus isolation conducted for select tissue samples showed lasv titers of 57 log10 tcid50/g of tissue ; blood samples collected on day 10 and at the time of euthanasia ( 5 and 6.25 log10 tcid50/ml , respectively ) showed viremia .\nin contrast , the 3 animals vaccinated with vsvg / lasvgpc resisted lethal lasv challenge and did not demonstrate any clinical signs of disease or any hematologic or biochemical indicators of lasv infection . at no point in the study was virus found in blood samples collected regularly from these 3 animals , even when tested by sensitive reverse transcription pcrs .\nan elisa with serum samples collected 45 days postchallenge demonstrated equivocal antibody titers ( 100 ) against a recombinant lasv nucleocapsid protein in 1 nhp .\nthe other 2 animals did not show seroconversion , which suggested that vaccination caused nearly sterile immunity against lasv ( table ) .\n* vsv , vesicular stomatitis virus ; vhf , viral hemorrhagic fever ; lasv , lassa virus ; gpc , glycoprotein precursor ; np , nucleocapsid protein ; ebov , ebola virus ; gp , glycoprotein ; vp40 viral protein 40 ; nd , not determined .\ntiters are indicated as reciprocal endpoint dilutions from elisas for recombinant antigens ( lasv np , ebov gp , and vp40 ) , or whole virus preparations ( vsv ) .\napproximately 90 days after the original vaccination with vsvg / lasvgpc , the 3 nhps were vaccinated with a single dose of 10 pfu of vsvg / ebovgp by intramuscular injection as described ( 3 ) .\nan additional nhp was vaccinated with a control vaccine as outlined above and served as the inoculation control . at the time of vaccination ,\nthe 3 macaques had a robust vsv - specific antibody response with titers of 25,600 , as determined by a whole virus elisa ( table ) . despite this finding\n, the 3 animals that received the vsv - based ebov vaccine mounted an efficient response to the ebov glycoprotein ( table ) and were completely protected when challenged 28 days later with a lethal dose of ebov ( 10 pfu ) ( 10 ) .\nhematologic and serum biochemistry values remained constant throughout the study , and virus was not found in blood samples collected regularly and tested by using real - time reverse transcription pcr . in contrast , severe ebov hemorrhagic fever developed in the control animal , which was characterized by increased serum concentrations of alkaline phosphatase , aspartate aminotransferase and alanine aminotransferase ; thrombocytopenia ; and viremia ( 7 log10 tcid50/ml whole blood ) beginning 36 days postchallenge .\nthis animal was euthanized 7 days postchallenge , and titration of selected tissue samples showed ebov titers of > 9 log10 tcid50/g tissue .\nan elisa conducted at the conclusion of the study ( 42 days post ebov challenge ) showed increased antibody responses to vsv ( titers = 102,400 ) and seroconversion to the ebov viral protein 40 antigen ( titers 1,6006,400 ) in the 3 surviving nhps ( table ) , which is consistent with published results ( 10 ) .\nbecause of the remote locations where vhf agents are present , an overall shortage of health care professionals and clinics in these locations , and mobility of human populations , any vaccine against these pathogens would ideally need to elicit a protective immune response after a single vaccination .\nfor this reason , replication - competent viral vectors are considered leading vhf vaccine candidates .\nas the vsvg / ebovgp vaccine heads toward clinical trials , it is necessary to clarify the potential limitations of using the vsv platform against multiple vhf agents . a major drawback for many viral vector platforms is preexisting immunity against the vector itself , which can decrease or nullify the essential protective immune response , which results in vaccine failure .\ndesign of the vsv - based vaccines , which encode and express glycoproteins from various pathogens without its own glycoprotein ( 11,12 ) , suggest that preexisting immunity would not influence protective efficacy of individual vaccinations ( 12 ) .\nresults of this study demonstrate that multiple vsv vaccines can be used in a population without any deleterious effect on overall protective efficacy .", "role": "user" }, { "content": "we demonstrated that previous vaccination with a vesicular stomatitis virus ( vsv)based lassa virus vaccine does not alter protective efficacy of subsequent vaccination with a vsv - based ebola virus vaccine . \n these findings demonstrate the utility of vsv - based vaccines against divergent viral pathogens , even when preexisting immunity to the vaccine vector is present .", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: I want to develop a new human action recognition method which outperforms the state-of-the-\n\nKeywords: human action recognition video\n\nDataset Information:\nKinetics-600: The Kinetics-600 is a large-scale action recognition dataset which consists of around 480K videos from 600 action categories. The 480K videos are divided into 390K, 30K, 60K for training, validation and test sets, respectively.\nHMDB51: The HMDB51 dataset is a large collection of realistic videos from various sources, including movies and web videos. The dataset is composed of 6,766 video clips from 51 action categories (such as “jump”, “kiss” and “laugh”), with each category containing at least 101 clips.\nTAPOS: TAPOS is a new dataset developed on sport videos with manual annotations of sub-actions, and conduct a study on temporal action parsing on top. A sport activity usually consists of multiple sub-actions and that the awareness of such temporal structures is beneficial to action recognition.\nDialogue State Tracking Challenge: The Dialog State Tracking Challenges 2 & 3 (DSTC2&3) were research challenge focused on improving the state of the art in tracking the state of spoken dialog systems. State tracking, sometimes called belief tracking, refers to accurately estimating the user's goal as a dialog progresses.\n\nAvailable Datasets: A: Kinetics-600 B: HMDB51 C: TAPOS D: Dialogue State Tracking Challenge", "role": "user" }, { "content": "HMDB51", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nan interesting problem in birational geometry is , given @xmath1 a projective variety of general type , to understand for which @xmath2 the @xmath2-th pluricanonical linear system @xmath3 yields a birational map .\n+ for varieties of _ maximal albanese dimension _\n( i.e. the albanese map @xmath4 is generically finite ) , this study brought some surprising result , since chen and hacon @xcite proved that , independently on the dimension , @xmath5 is birational for every @xmath6 .\nmore recently , it was shown by jiang @xcite , applying ideas from @xcite , that , if @xmath1 is as above , the pentacanonical map @xmath7 is birational .\nthe main result of this paper , whose proof also uses @xmath8-regularity techniques introduced by pareschi and popa in @xcite , is an improvement of chen - hacon and jiang s theorems : if @xmath1 is a complex projective smooth variety of maximal albanese dimension and general type , then the tetracanonical map @xmath9 birational .\nthe argument consists in showing that reducible divisors @xmath10 , with @xmath11,@xmath12 and @xmath13 separate points in a suitable open set of @xmath1 .\nthe crucial point is that , for all @xmath11 , the sections of @xmath14 passing trough a general point of @xmath1 have good generation properties . in order to achieve this we use pareschi - popa theory of @xmath8-regularity and continuous global generation ( @xcite ) , joint with a theorem of chen - hacon @xcite on the fact that the variety @xmath15 spans @xmath16 . + it is worth to recall that if @xmath1 is variety of maximal albanese dimension , then @xmath17 ( @xcite ) and that chen - hacon proved in @xcite that if @xmath18 then , as for curves , the tricanonical map is always birational and this is sharp , as shown by curves of genus 2 .\ntherefore our result is relevant only in the more mysterious case where @xmath19 , which appears only in dimension @xmath20 ( see @xcite ) .\nin fact the author does not know any example of varieties of maximal albanese dimension with non - birational tricanonical map and it is tempting to conjecture that the tricanonical map should be always birational for such varieties . + in the sequel , @xmath1 will always be a smooth complex variety of general type and maximal albanese dimension while @xmath21 shall denote its dualizing sheaf .\nby @xmath22 we will mean the albanese variety of @xmath1 .\ngiven @xmath23 an invertible sheaf on a projective variety @xmath24 , then @xmath25 will be the asymptotic multiplier ideal sheaf associated to the complete linear series @xmath26 ( cfr .\n@xcite ) . finally\n, if @xmath27 is a coherent sheaf on @xmath24 , then by @xmath28 we will mean @xmath29 . given a linear system @xmath30\n, we will say , with a slight abuse of notation , that it is birational if the corresponding rational map @xmath31 is birational .\ni am indebted to my advisor , g. pareschi , for many advices and valuable suggestions .\ni am also very grateful to c. hacon , and m. popa for carefully reading a first draft of this paper and suggesting many emprovements and corrections .\nmoreover , a particular thank must go to c. hacon for explaining to me how to work with some specific examples .\nfinally it is a pleasure to thank a. calabri , c. ciliberto , a. rapagnetta , g. pareschi and f. viviani for very interesting and useful discussion .\nin what follows we briefly recall some definitions about @xmath8-regular sheaves and their generation property . given a coherent sheaf @xmath27 on a smooth projective variety @xmath24\nwe denote by @xmath32 the _ non - generation locus of @xmath27 _ , i. e. the support of the cokernel of the evaluation map@xmath33 .\nif @xmath27 is a line bundle , then @xmath32 is just the base locus of @xmath27 .\n+ the _ cohomological support loci _ of @xmath27 are defined as : @xmath34 as for cohomology groups , we will occasionally suppress @xmath24 from the notation , simply writing @xmath35 .\nlet @xmath27 a sheaf on a smooth projective variety @xmath24 . 1 .\nit is said to be @xmath36 if @xmath37 for every @xmath38 . in the case\n@xmath24 is an abelian variety , @xmath36 sheaves are called _\n@xmath8-regular_. 2 . given @xmath39\n, we say that @xmath27 is _ continuously globally generated at @xmath40 _ ( in brief cgg at @xmath40 ) if the sum of the evaluation maps @xmath41 is surjective for every @xmath42 non empty open set of @xmath43 .\n[ ese ] in ( * ? ? ?\n* proposition 2.13 ) pareschi and popa proved that an @xmath8-regular sheaf on an abelian variety is cgg at every point .\nwe will prove this slightly more general statement : [ lem : effdiv ] let @xmath47 an effective divisor on an abelian variety @xmath48 .\ntake @xmath49 subtori of @xmath48 such that they generate @xmath48 as an abstract group and let @xmath50 , @xmath51 some points of @xmath48 .\nthen @xmath52 for at least one @xmath53 .\nif @xmath47 is ample , then the statement is easily seen to be true .\nthus we can suppose , without a loss of generality , that @xmath47 is not ample .\nthen there exists an abelian variety @xmath54 , a surjective homomorphism @xmath55 and an ample divisor @xmath56 on @xmath57 such that @xmath58 .\nsuppose now that @xmath47 does not intersect @xmath59 for every @xmath53 , it follows that @xmath56 does not intersect @xmath60 for every @xmath53 .\nhence , since @xmath56 is ample , the image @xmath59 through @xmath61 is a point , and therefore @xmath62 is contained in the kernel of @xmath61 for every @xmath53 .\nbut this is impossible since the @xmath62 s generate @xmath48 .\n+ let @xmath63 albanese map of @xmath1 .\nlet us state the following claim .\n+ _ claim 1 : _ for the generic @xmath64 the sheaf @xmath65 is @xmath8-regular . + before proceeding with the proof of the claim 1 let us see how it implies theorem a , this argument follows the one pareschi and popa in @xcite .\nfirst of all we simplify a bit the notation by letting @xmath66 .\nnow observe that , since the albanese morphism @xmath67 is generically finite , a well known extension of grauert - riemenschneider vanishing theorem ( see , for example ( * ? ? ?\n* proof of proposition 5.4 ) ) yields that , for any @xmath68 , the higher direct images @xmath69 vanish .\ntherefore , for every @xmath70 we get the equality @xmath71 by nadel vanishing for adymptotic multiplier ideals ( see ( * ? ? ?\n* theorem 11.2.12 ) ) the loci at the left hand side are empty when @xmath38 .\nin particular @xmath72 is @xmath8-regular on @xmath22 and hence cgg everywhere ( example [ ese ] ) . since @xmath67 is generically finite , we get that @xmath73 is cgg away from @xmath74 , the exceptional locus of @xmath67 .\nthis means by definition that the map @xmath75 is surjective for every @xmath76 and for every @xmath77 non - empty open set .\nnow we recall that the base locus of @xmath78 is contained in the base locus of @xmath79 for every @xmath44 ; hence we can consider the closed set @xmath80 .\nit follows easily from that , if @xmath81 the map @xmath82 is surjective for every @xmath83 open dense set in @xmath16 and thus @xmath14 is cgg away from @xmath84 .\n+ from now on , since we are supposing that the claim is true , we can take @xmath42 a non - empty open set of @xmath1 such that for every @xmath85 the sheaf @xmath86 is @xmath8-regular and hence cgg . again\n, it follows that @xmath87 is cgg away from @xmath74 . finally by (\n* proposition 2.12 ) @xmath88 is globally generated away from @xmath84 and therefore @xmath89 is globally generated away from @xmath90 and we can conclude that @xmath91 is very ample outside a proper subvariety of @xmath1 and hence @xmath92 is birational for every @xmath68 .\nthis prove the theorem .\n+ now we proceed with the proof claim 1 .\nrecall that , by the subtorus theorem ( ( * ? ? ?\n* theorem 0.1 ) and @xcite ) , we can write @xmath93\\ ] ] where the @xmath94 s are torsion points of @xmath16 and the @xmath95 s are subtori of @xmath16 . hence , for all @xmath53 and for all @xmath96 the line bundle @xmath97 has sections , and therefore its base locus @xmath98 is a proper subvariety of z. we take an non - empty zariski open set @xmath42 contained in the complement of @xmath99 given @xmath85 we want to prove that for every @xmath100 @xmath101 consider the following short exact sequence : @xmath102 where @xmath103 . since @xmath104 does not belong to the exceptional locus of the albanese map of @xmath1 , by pushing forward for @xmath67 we still get a short exact sequence:@xmath105 in particular @xmath106 .\nsince , as already observed , an extension of grauert - riemenschneider vanishing , yields the vanishing the @xmath107 for every @xmath108 and every @xmath103 , we have that @xmath109 for every @xmath108 and every @xmath110 .\ntherefore , for every @xmath111 @xmath112 now we look at the long cohomology sequence of the short exact sequence . by nadel vanishing we have\nthat , for every @xmath113 and @xmath103 , @xmath114 and therefore , by the loci @xmath115 are empty for every @xmath116 .\n+ it remains to see that @xmath117 . before proceeding further\nwe state the following : + _ claim 2 : _ for every @xmath118 , @xmath119)=\\emptyset.$ ] + the reader may observe that , since by a result of chen and hacon ( ( * ? ? ? * theorem 1 ) ) the @xmath95 s generate @xmath16 , this , together with lemma [ lem : effdiv ] , implies directly claim 1 . in fact\nthe locus @xmath120 is a proper subvariety of @xmath16 that can not possibly contain a divisor , hence its codimension shall be greater than 1 . by also @xmath117 . + to prove claim 2 we reason in the following way .\nfirst we remark that there is an alternative description of the locus @xmath120 : in fact by and the vanishing of @xmath121 for every @xmath110 ( again due to nadel vanishing ) we have that @xmath122 if and only if the map @xmath123 is not surjective\n. therefore we can write @xmath124 since we chose @xmath125 there exists @xmath126 a dense open set of @xmath95 such that , for every @xmath127 , @xmath104 is not in @xmath128 .\ntake @xmath129 ; the intersection @xmath130 is still a non - empty open set of @xmath95 .\nfor @xmath131 we write @xmath132 since , thanks to our choice of @xmath133 , both @xmath134 and @xmath135 are generated at @xmath104 , also the left hand side is . therefore @xmath136 .\nnow by ( * ? ? ?\n* lemma 6.3(b ) ) , the zero locus of @xmath137 is contained in the base locus of @xmath138 for every @xmath139 ; thus we have the equality @xmath140 and , consequently , @xmath141 and the claim is proved .", "role": "user" }, { "content": "we prove the birationality of the @xmath0-canonical map of smooth projective varieties of general type and maximal albanese dimension .", "role": "assistant" } ]

[ { "content": "Review the provided sections from a computer science paper and distill the primary contribution into a single sentence. Provide only the summary sentence.\n\nSections:\n\nMany irregular domains such as social networks, financial transactions, neuron connections, and natural language structures are represented as graphs.\nIn recent years, a variety of graph neural networks (GNNs) have been successfully applied for representation learning and prediction on such graphs.\nHowever, in many of the applications, the underlying graph changes over time and existing GNNs are inadequate for handling such dynamic graphs.\nIn this paper we propose a novel technique for learning embeddings of dynamic graphs based on a tensor algebra framework.\nOur method extends the popular graph convolutional network (GCN) for learning representations of dynamic graphs using the recently proposed tensor M-product technique.\nTheoretical results that establish the connection between the proposed tensor approach and spectral convolution of tensors are developed.\nNumerical experiments on real datasets demonstrate the usefulness of the proposed method for an edge classification task on dynamic graphs.\nGraphs are popular data structures used to effectively represent interactions and structural relationships between entities in structured data domains.\nInspired by the success of deep neural networks for learning representations in the image and language domains, recently, application of neural networks for graph representation learning has attracted much interest.\nA number of graph neural network (GNN) architectures have been explored in the contemporary literature for a variety of graph related tasks and applications (Hamilton et al., 2017; Seo et al., 2018; Zhou et al., 2018; Wu et al., 2019) .\nMethods based on graph convolution filters which extend convolutional neural networks (CNNs) to irregular graph domains are popular (Bruna et al., 2013; Defferrard et al., 2016; Kipf and Welling, 2016) .\nMost of these GNN models operate on a given, static graph.\nIn many real-world applications, the underlining graph changes over time, and learning representations of such dynamic graphs is essential.\nExamples include analyzing social networks (Berger-Wolf and Saia, 2006) , predicting collaboration in citation networks (Leskovec et al., 2005) , detecting fraud and crime in financial networks (Weber et al., 2018; Pareja et al., 2019) , traffic control (Zhao et al., 2019) , and understanding neuronal activities in the brain (De Vico Fallani et al., 2014) .\nIn such dynamic settings, the temporal interdependence in the graph connections and features also play a substantial role.\nHowever, efficient GNN methods that handle time varying graphs and that capture the temporal correlations are lacking.\nBy dynamic graph, we mean a sequence of graphs (V, A (t) , X (t) ), t ∈ {1, 2, . . . , T }, with a fixed set V of N nodes, adjacency matrices A (t) ∈ R N ×N , and graph feature matrices X (t) ∈ R N ×F where X (t) n: ∈ R F is the feature vector consisting of F features associated with node n at time t.\nThe graphs can be weighted, and directed or undirected.\nThey can also have additional properties like (time varying) node and edge classes, which would be stored in a separate structure.\nSuppose we only observe the first T < T graphs in the sequence.\nThe goal of our method is to use these observations to predict some property of the remaining T − T graphs.\nIn this paper, we use it for edge classification.\nOther potential applications are node classification and edge/link prediction.\nIn recent years, tensor constructs have been explored to effectively process high-dimensional data, in order to better leverage the multidimensional structure of such data (Kolda and Bader, 2009) .\nTensor based approaches have been shown to perform well in many image and video processing ap- plications Martin et al., 2013; Zhang et al., 2014; Zhang and Aeron, 2016; Lu et al., 2016; Newman et al., 2018) .\nA number of tensor based neural networks have also been investigated to extract and learn multi-dimensional representations, e.g. methods based on tensor decomposition (Phan and Cichocki, 2010), tensor-trains (Novikov et al., 2015; Stoudenmire and Schwab, 2016) , and tensor factorized neural network (Chien and Bao, 2017) .\nRecently, a new tensor framework called the tensor M-product framework (Braman, 2010; Kilmer and Martin, 2011; Kernfeld et al., 2015) was proposed that extends matrix based theory to high-dimensional architectures.\nIn this paper, we propose a novel tensor variant of the popular graph convolutional network (GCN) architecture (Kipf and Welling, 2016), which we call TensorGCN.\nIt captures correlation over time by leveraging the tensor M-product framework.\nThe flexibility and matrix mimeticability of the framework, help us adapt the GCN architecture to tensor space.\nFigure 1 illustrates our method at a high level: First, the time varying adjacency matrices A (t) and feature matrices X (t) of the dynamic graph are aggregated into an adjacency tensor and a feature tensor, respectively.\nThese tensors are then fed into our TensorGCN, which computes an embedding that can be used for a variety of tasks, such as link prediction, and edge and node classification.\nGCN architectures are motivated by graph convolution filtering, i.e., applying filters/functions to the graph Laplacian (in turn its eigenvalues) (Bruna et al., 2013) , and we establish a similar connection between TensorGCN and spectral filtering of tensors.\nExperimental results on real datasets illustrate the performance of our method for the edge classification task on dynamic graphs.\nElements of our method can also be used as a preprocessing step for other dynamic graph methods.\nWe have presented a novel approach for dynamic graph embedding which leverages the tensor Mproduct framework.\nWe used it for edge classification in experiments on four real datasets, where it performed competitively compared to state-of-the-art methods.\nFuture research directions include further developing the theoretical guarantees for the method, investigating optimal structure and learning of the transform matrix M, using the method for other prediction tasks, and investigating how to utilize deeper architectures for dynamic graph learning.", "role": "user" }, { "content": "We propose a novel tensor based method for graph convolutional networks on dynamic graphs", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nfor decades , joint replacement has been a procedure with major impact on the quality of life in elderly patients with joint degenerative diseases or traumatic injuries .\nunfortunately , some patients develop symptoms after surgical intervention . in the majority of patients , aseptic loosening due to biochemical reaction of the bone\nboth entities have a very similar clinical appearance , but require different therapeutic approaches due to different pathophysiological substrates ( 1 ) .\nlack of a single imaging modality that could clearly differentiate between infections and loosening makes this problem a challenge in the routine workup of these patients .\nlaboratory analysis , including white blood cell count , erythrocyte sedimentation rate ( esr ) and c - reactive protein ( crp ) are not specific enough .\ncanner et al . found that out of fifty - two patients who had an infection following joint arthroplasty , only eight ( 15% ) had leukocytosis ( 2 ) .\nthe esr may remain elevated for months after an uncomplicated total hip replacement ( 3 ) .\ncrp levels increase in a non - specific manner as a result of infectious , inflammatory or neoplastic disorders .\nconventional imaging methods are helpful in some situations when complications arise ( 4 , 5 ) , but their diagnostic potential in distinguishing loosening and inflammation are limited .\nct is superior to radiography in imaging soft tissue abscesses ( 6 ) ; however , not a recommended diagnostic tool due to significant artifacts on the images at the location of the prosthesis that hamper the optimal interpretation of the results .\nthus , non - attenuation - corrected images must be interpreted to avoid false - positive results if pet / ct is used for the evaluation of painful prosthesis ( 7 ) .\naspiration biopsy of the joint was regarded as a gold standard , but it is not convenient for the patient and may not always be helpful in distinguishing the two above - mentioned pathological entities . a positive result can confirm infection , but a negative result can not exclude it ( 8) .\nnuclear medicine modalities offer several diagnostic methods that are dedicated to the diagnosis of infection and are not affected by orthopedic implants .\nthree - phase bone scintigraphy ( tpbs ) is widely accepted for the diagnosis of different pathological processes of the musculoskeletal system including detection of infection with a high sensitivity and limited specificity in the diagnosis of infected joint prostheses ( 9 ) .\nit is noticeable that reported results of different studies dealing with the problem of painful joint prosthesis show variation , which is mostly due to different interpretation criteria applied ( 10 , 11 ) .\ntpbs , with an accuracy of about 50 - 70% can be performed as the modality of primary choice in these patients , but it should be combined with other diagnostic modalities ( 12 ) .\nwhite blood cell ( wbc ) scintigraphy labeled with 99mtc hmpao or 111in - oxine or anti - granulocyte scintigraphy using 99mtc - labeled monoclonal antibodies ( moab ) or their fragments are frequently used nuclear medicine imaging modalities in the detection of infection and inflammation , but it is important to emphasize that neither of these imaging methods can reliably differentiate sterile inflammation from infection ( 13 ) .\nsignificant decrease in the accuracy of wbc imaging is caused by the fact that labeled leukocytes are accumulating both in infected tissue and in bone marrow ( 10 ) . a combined study consisting of wbc imaging and complementary bone marrow ( bm ) imaging performed with radiolabeled sulphur colloid\nis based on the fact that both radiopharmaceuticals accumulate in marrow ; whereas , wbcs accumulate in infection , but sulfur colloid does not .\nalthough the combination of these two modalities increases the accuracy in the diagnosis of osteomyelitis up to 90% , pitfalls that could affect the results are not negligible ( 14 ) .\n18f - fdg - pet is a promising imaging modality for the evaluation of a variety of infectious and inflammatory processes ( 15 ) .\nin addition , there are reports indicating that in the evaluation of inflammation or infection , 18f - fdg - pet is even more accurate than conventional nuclear medicine procedures ( 16 ) . these features of 18f - fdg - pet diagnostic modalities encouraged many professionals to perform research on its applicability in patients with painful prostheses .\nhowever , the results of the studies dealing with the role of 18f - fdg - pet are so far rather inconclusive and need to be more clearly defined ( 12 ) . according to chacko et al . , the intensity of uptake is not useful for separating the infected from the aseptically loosened device ( 17 ) .\nthe periprosthetic glucose metabolism could also be enhanced to certain degrees in normal cases , which have been addressed in another study ( 18 ) , and could hamper the interpretation of the examination .\nthe reason for this shortcoming is to our opinion the unawareness of physiological remodelling processes that could be seen in asymptomatic patients .\nthe aim of this study was to demonstrate this physiological pattern and discuss the findings in the literature .\nin the present study , we aim to delineate different metabolic patterns in asymptomatic patients with hip prostheses and to improve the specificity of 18f - fdg - pet in patients with suspected septic loosening of hip prosthesis .\ntwelve patients , ( 6 males , 6 females ) ; mean age , 73 7 ( range , 58 - 91 ) years were enrolled prospectively into the study .\nnone of the patients expressed any symptoms in regard to their implanted prosthesis and none of them had hematological malignancies or any metabolic bone manifestation of the primary tumor .\nthe pet studies were performed on a full ring pet - scanner ( siemens exact , knoxville , usa ) as described in earlier studies ( 19 ) .\nthe results are summarized in table 1 . with findings related to periprosthetic enhanced uptake ,\nfigure 1 demonstrates a case of a patient with asymptomatic hip prosthesis on both sides with enhanced uptake in the left neck region .\nt = trochanter , n = neck , m = male , f = female , l = left , r = right\none of the largest samples of patients with hip prosthesis examined with 18f - fdg - pet was reported by reinartz and colleagues who compared pet with tpbs .\nthe authors concluded that 18f - fdg - pet is a highly accurate diagnostic procedure to differentiate reliably between aseptic loosening and periprosthetic infection ( 18 ) .\nthey described , by a qualitative analysis , the different patterns of periprosthetic 18f - fdg uptake in different conditions , from normal to septic loosening 6 months after arthroplasty .\n18f - fdg - pet has great potential in detecting the infection , but in cases of increased aseptic loosening , periprosthetic uptake of 18f - fdg could be caused by wear - induced polyethylene particles and the subsequent growth of aggressive granulomatous tissue ( 16 ) .\nnon - infectious inflammatory reactions around the neck of the prosthesis are common findings months or even years after surgery and they should not be interpreted as a finding suggestive of infection ( 21 ) .\napplication of suv ( standard uptake value ) as a semiquantitative parameter is usually a very important tool in the interpretation of oncological pet images , but it can not be applied as a reliable criterion in inflammatory pathology due to low specificity , particularly not as a single criterion ( 10 ) . knowing the limitations of 18f - fdg - pet alone and taking into account the mechanism of its uptake in malignant tissues , leukocytes were labeled with 18f - fdg in order to increase its affinity to the inflamed tissue .\nalthough the first results were promising , it was found that 18f - fdg was rapidly released from the leukocytes .\nit has been suggested that the amount of increased 18f - fdg uptake is less important than the location of increased 18f - fdg uptake when this technique is used to diagnose periprosthetic infection in patients who had undergone prior hip arthroplasty ( 16 ) .\nuptake pattern seems to be of essential importance in the diagnosis of infection and is defined as very suggestive of infection if the 18f - fdg uptake between the bone and prosthesis at the level of the midshaft portion of the prosthesis is present ( 23 , 24 ) .\nthis suggests that more standardized criteria for the interpretation of the 18f - fdg scan for the diagnosis of infection on the prosthesis placement should be defined and applied in practice .\ndepending on the type of prosthesis and on other factors , hip prosthesis can show different metabolic patterns . keeping in mind different metabolic patterns of periprosthetic 18f - fdg uptake in different conditions and the reliability of periprosthetic suv - measurement with the new pet / ct devices\n, it seems to be of the utmost importance to find visual criteria that could be applied in these cases ( 18 ) . in this study\n, we could demonstrate ( table 1 ) this pattern of hypermetabolic areas that could be defined more likely as normal and not caused by septic or aseptic loosening only on the neck and/or trochanteric area .\ntwo patients who showed enhanced periprosthetic uptake in two regions , had a history of re - implantation in one case and a period longer than 10 years after the surgery in the second case .\ninterestingly , we could not observe focal enhanced glucose metabolism in the stem or tip region in any patient .\nthese findings are also of importance to rule out a suspected infection , as it was shown in a recent study where fdg - pet had a sensitivity of 100% and a negative predictive value of 100% ( 25 ) .\nthe study is limited by the fact that the patients could not provide information regarding the type of prosthesis , particularly whether they were cemented or not .\nno patient had a leukocytosis , but 8/12 patients -- with or without periprosthetic - enhanced uptake -- had an elevated crp . since they were all referred for oncological reasons , data was not taken into consideration .\nthe results of this study demonstrate a non - specific pattern of enhanced 18f - fdg - uptake in asymptomatic patients in the neck or trochanteric region after arthroplasty , which should be taken into consideration for correct interpretation of metabolic studies in patients with suspected septic loosening of the hip prosthesis .", "role": "user" }, { "content": "background : joint replacement is a procedure with a major impact on the quality of life of patients with joint degenerative disease or traumatic injuries . \n however , some patients develop symptoms after the intervention caused by mechanical loosening or infection . \n metabolic imaging by 18f - fdg - pet investigated in these patients isoften hampered by low specificity for diagnosis of possible septic vs. mechanical loosening . \n the reason for this shortcoming is to our opinion the unawareness of physiological remodeling processes that could be seen in asymptomatic patients.objectives:in order to overcome this drawback , we aimed to find out the physiological metabolic functional pattern in asymptomatic patients with implanted hip prosthesispatients and methods : twelve patients ( 6 males , 6 females ) ; mean age 73 7 ( range 58 - 91 ) years were prospectively enrolled in the study . \n the patients were admitted to our department for oncological referral with implanted hip prostheses . \n all patients explained no symptoms with regard to their implanted prosthesis . \n the attenuation corrected images were used for analysis.results:fourteen hip prostheses in 12 patients were visually analyzed . \n seven out of 14 prostheses among 12 patients showed focal periprosthetic enhanced metabolism , two of which showed two sites of enhanced uptake ; whereas , the remaining five prostheses showed singular hypermetabolic areas within the periprosthetic site . \n the remaining seven prostheses in the other five patients showed no periprosthetic - enhanced uptake.conclusion:of the asymptomatic patients investigated , 58% showed focal enhanced periprosthetic glucose metabolism . \n this finding should be taken into consideration as a more probable unspecific metabolic pattern for correct interpretation of 18f - fdg - pet studies in patients with suspected septic loosening of the hip prosthesis .", "role": "assistant" } ]

[ { "content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nQuantum numerical control for particles at matter surface\n\nContent Extracts:\n\n<p>quite curious: what is the difference of control particles occurred at surface than control free particles? whether one can develop a suit of theory or methodology for quantum surface control? It is certainly expected to connect theoretical control, to numerical or computational control, and to experimental control as carrying out quantum system control of particles on the surface. It is desired that quantum control theory (QCT) for quantum dot at surface would be evidenced in visualization method, and attained confidential verification in the guidance of real-time computer-aided experiments in the viewpoint of chemistry and physics.</p>\n\nHistory of study on particles at surface\n<p>In the studying of particles at the matter surface, initial consideration is reported on the 2009 ACS meeting for quantum control of quantum dot at surface. 1 That is a work for theoretical and computational control to Klein-Gordon-Schrödinger (KGS) equation for 1 and 2 dimensions cases. At the year 2014 ACS meetings, 2,3 nano-particles control had been treated using the density function theory (DFT) for the motion of electrons surrounding the particles at surface. Theoretic result is obtained for multi-particles cases. 4,6-11,13 Lasting the survey on DFT, 12 this work is manipulating one particle at matter surface in the aspect of numerical approach. The interesting thing is to evidence that control theory is worked for DFT, computational control can be performed for a time-depended Schrödinger equation at real physics gauges. 5 The significant difference of KGS system and DFT: one is aim at wave function of a particle, and another is aim at electron density of a particle. As perspective research, numerical control in high dimensions for nano-particles at matter surface could be a considerable direction in the future.</p>\n\nGeneral density function theory\n<p>For a particle at surface, introduce density functional theory as preparation. Let Ω be an open bounded set of R 3 at spherical polar coordinate r ∈ (0, ∞), vector r as in Figure 1, and Q = (0, T ) × Ω for T > 0, (t, r) ∈ Q. The ground state energy density of electron is denoted Figure 1</p><p>as η(t, r), r is the displacement of electron from centre of a particle, E(t, r) is electronic field.</p><p>Then time-dependent density functional theory has the form of Schödinger equation</p><p>In here, η(t, r) is wave function of the particle, represent the probability function at time t.</p><p>E xc (η(t, r)) is exchange correction function. For unified scattered field E s (t, r), the Hamiltonian of particle in the presence of incident field E 0 (t) at time-depended density functional theory (TDDFT) lead the form of</p>\n\nTime depended Schrödinger equation\n<p>For N particles at surface, n(t, r ) =</p><p>term of TFDW theory is in the form of gradient expression as m (∇n) 1/2 (r) 2 dr. h, is (reduced) Planck constant, m is electron mass.</p>\n\nMathematical setting\n<p>To do mathematical setting for time-depended Schrödinger equation ( 1) in the framework of variational method. For the particle at matter or metal surface, consider complex space for wave function η i (t, r) on variable t and r, take real Hilbert space for variational theory. In system (1), g(t) is external force of electron, as control input of particle P i . Control function g(t) at incident electric field E 0 (t) is only depended on time t, and independent of spatial variable vector r.</p><p>To usual spaces L 2 (Ω) and H 1 0 (Ω), define the complex solution space L 2 (Ω) and H 1 0 (Ω).</p><p>For complex-valued function η i (t, r), denote two complex Hilbert spaces H = L 2 (Ω) and</p><p>.</p><p>, then the inner product of L 2 (Ω) can be defined by</p><p>For the space η i = η i1 + iη i2 ∈ H 1 0 (Ω), define its norm as</p><p>If</p><p>, then the inner product of space H 1 0 (Ω) is defined as</p><p>The definition is equivalent to</p><p>. Definition. The Hilbert space W (0, T ) is called solution space, defined by</p><p>Then the norm of W (0, T ) can be defined as</p><p>If η i , n i ∈ W (0, T ), then the definition of its inner product is given by</p><p>Denotes the continuous functions set C(0, T ; H), and spaces L 2 (0, T ; H), L 2 (0, T ; V), L 2 (0, T ; V ). Further, V is the complex conjugate space of V. Certainly, (V, H) is also a Gelfand triple spaces V → H → V , in which two embeddings are continuous, dense and compact.</p>\n\nSolution of nonlinear Schrödinger equation\n<p>Definition 2. A function η i is said as weak solution of system in the form of time-depended Schrödinger equation ( 1) for i-th particle</p><p>where ∀σ i ∈ D (0, T ) by the means of distribution space, σ i ∈ C 1 (0, T ; V) and σ i (T ) = 0.</p><p>, then there exists a unique solution η i (t, r) ∈ W (0, T ) for time-depended Schrödinger system (1).</p><p>Proof. Faedo-Galerkin method is using to construct an approximate solution for system (1). From Gelfand triple spaces, V → H is compact, then there exists an orthogonal basis of H, {w j } ∞ j=1 consisting of eigenfunctions of A = −∆, such that Aw j = λ j w j for all j, |η i (t, r)| 2 to get expansion of ẽ(t, r) and Ṽ (t, r) of e(t, r) and V (t, r) using {w j }. Taking σ i = w j at weak form (4), then approximate solution ηij (t) satisfy ordinary differential equation as</p><p>Substitute ηij as approximate form in (5), from standard theory of ODE, ensure a unique local solution {η ij }, i = 1, 2, • • • , N for approximate system (5). For ηij 0 , there exists a</p><p>Take analogous argument for {η ij }, there exist a function ηi ∈ V, that ηij − ηi V → 0 as j → ∞. That is, approximate solution ηij is bounded in L ∞ (0, T ; V). Suppose that {η ij } and {η jj } are two solutions of equation (1) for initial guess η i 0 and</p><p>There exist</p><p>There exist C (t) such that</p><p>Denote r as norm of vector r , hence, from weak form (4) to get 1 2</p><p>H , Gronwall inequality yield that</p><p>Therefore, ηij 0 → ηjj 0 implied ηij → ηjj in L 2 (0, T ; H) as j → ∞, and same argument to L 2 (0, T ; V) as j → ∞ from ( 6). Taking ηjj = η i to find that ηij → η i in C(0, T ; H). Thus, the inclusion C(0, T ; H) ⊂ W (0, T ) to ensure Theorem 1.</p><p>From existence theorem of weak solution to get estimate η i 2 H + η i 2 V is bounded for η i of i-th particle P i . For control g k , from boundedness of G ad that</p><p>Setting η i * = η i (g * ), there exist a subsequence {η i (g k )} of {η i (g k )}, and a η i * ∈ W (0, T ) such that</p><p>and get the convergences for η i (g k ) as</p><p>as k → ∞. Set η ik = η i (g k ), η ik 0 = η i 0 , therefore, for i-th particle P i , by taking test function w j = σ i in (5), by the definition of weak form (4) to find</p><p>If using (8), (9), and taking k → ∞ to yield that</p><p>It inferred that ηi is a solution of (1) in the sense of distribution D (0, T ) on (0, T ). From uniqueness of weak solution for system (1) to attain ηi = η i (g * ). That is, for η i to get two convergences as</p><p>as k → ∞. Since the norm • L 2 (Ω) are lower semi-continuous in weak topology of L 2 (Ω), for i-th particle P i lim inf</p><p>H . Vice versa, from weak convergence (8) that lim inf</p><p>J i (g * ), and J i (g * ) = inf g∈G ad J i (g). That is, g * is quantum optimal control of time-depended Schrödinger system (1) subject to criteria function (7). It is Theorem 4. Theorem 5. For η i 0 ∈ V of control problem for system (1) to cost function (7), if G ad is closed convex (bounded) admissible subset of G, then quantum optimal control g * is characterized by Eular-Lagrange system as</p><p>In here, n i (t, r) ∈ W (0, T ) is solution of adjoint system corresponding to η i (t, r) of timedepended Schrödinger system (1). ( 10) is necessary optimality condition for quantum optimal control g * of i-th particle P</p><p>Numerical approach for one particle at matter surface</p><p>For N = 1 one particle case, the interactions of particles are disappeared, and first term The polar plot of g 0 (t) is in the Figure 2.</p>\n\nConclusions and discussions\n<p>In this work, we investigate theoretical and computational quantum control for particles at matter surface using density function theory. For time-depended Schrödinger equation of particles, control theory is applied to consider the quantum control of electron motion surrounding particles. For one particle case in 3D, numerical control is executed for TF model at real physical scale. In comprising to existing results of physical experiments to conclude that: i). optimal control theory is worked to manipulate the particles appeared at matter surface. ii). density function theory (DFT) as a fresh tool can be using to do control at scale of molecule, atom and nuclei. Future work is for computational experiment control of multi-particles, poly-atoms, and large number of particles at surface.</p>", "role": "user" }, { "content": "In this work, time-depended Schrödinger equation described particles at matter (crystal, catalysis, metal) surface could be considered as propose of numerical control of quantum system. Accessing existing physical experimental results on the motion of particles (molecules, atoms) at surface, based on variational method of quantum control theory in Hilbert space, using density function theory (DFT), time-depended Schrödinger equation to proceed the investigation of computational approach. To do quantum calculation at surface, physically, first needs a concept as control goal: such as breaking a chemical bond as target; reducing energy of high intensity shaped laser pulse. Particles at surface is a kind of constrain control for spatial variable. Optimal control is to find and characterize the quantum optima for minimizing or maximizing the cost functional. Control methods contain selecting chemical reagent, designing chemical reaction, making control scope for a quantized system: time varying Schrödinger equation.Precisely, for general quadratic cost function, in two or three dimensional cases, a semidiscrete (time continuous, spatial discrete) algorithm consisting of finite element method and conjugate gradient method, would be utilized for solving a numerical solution of state system, and obtaining quantum optimal control from a initial guess of control input.", "role": "assistant" } ]

[ { "content": "Analyze the following text to identify specific entities. Focus on the categories provided: [\"Chemical\", \"Protein\"].\n\nDeliver your findings as a JSON structure: {\"Chemical\": [\"ExampleChemical\", ...], \"Protein\": [\"ExampleProtein\", ...]}. Each key represents an entity type, and the associated list contains the entities found. \n\nEnsure the response is strictly the JSON format without any extra text.\n\nSource:\n\nMutations in the follicle-stimulating hormone-beta (FSH beta) and FSH receptor genes in mice and humans.\nFollicle-stimulating hormone (FSH), a dimeric glycoprotein synthesized in the anterior pituitary gland, is important for the production of sex steroids and gametes. FSH-beta (FSH beta) and FSH receptor (FSHR) knockout mice display impaired ovarian follicular development and infertility in females and small testes, oligospermia, and fertility in males. Humans with FSH beta gene mutations tend to have a more severe phenotype than those with FSHR gene mutations, although infertility and varying degrees of impaired sex steroid production occur in both types of mutations. Data from human and mouse mutations in the FSH beta and FSHR genes suggest that FSH is necessary for normal pubertal development and fertility in males and females.", "role": "user" }, { "content": "{\"Chemical\": [\"steroids\", \"steroid\"], \"Protein\": [\"FSH\", \"FSH beta\", \"follicle-stimulating hormone-beta\", \"FSH-beta\", \"FSH receptor\", \"Follicle-stimulating hormone\", \"FSHR\"]}", "role": "assistant" } ]

[ { "content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nJoint based generators use a two-step pipeline [4,14]; or applying a joint model for both tasks [19,22].", "role": "user" }, { "content": "Method", "role": "assistant" } ]

[ { "content": "Transform the following sections from a biomedical study into a simple summary for the general public. Focus on making the information accessible and easy to understand.\n\nResearch Heading: An Alteration in ELMOD3, an Arl2 GTPase-Activating Protein, Is Associated with Hearing Impairment in Humans\nContent:\nAbstract:\nExome sequencing coupled with homozygosity mapping was used to identify a transition mutation( c. 794T>C; p. Leu265Ser) in ELMOD3 at the DFNB88 locus that is associated with nonsyndromic deafness in a large Pakistani family, PKDF468. The affected individuals of this family exhibited pre-lingual, severe-to-profound degrees of mixed hearing loss. ELMOD3 belongs to the engulfment and cell motility( ELMO) family, which consists of six paralogs in mammals. Several members of the ELMO family have been shown to regulate a subset of GTPases within the Ras superfamily. However, ELMOD3 is a largely uncharacterized protein that has no previously known biochemical activities. We found that in rodents, within the sensory epithelia of the inner ear, ELMOD3 appears most pronounced in the stereocilia of cochlear hair cells. Fluorescently tagged ELMOD3 co-localized with the actin cytoskeleton in MDCK cells and actin-based microvilli of LLC-PK1-CL4 epithelial cells. The p. Leu265Ser mutation in the ELMO domain impaired each of these activities. Super-resolution imaging revealed instances of close association of ELMOD3 with actin at the plasma membrane of MDCK cells. Furthermore, recombinant human GST-ELMOD3 exhibited GTPase activating protein( GAP) activity against the Arl2 GTPase, which was completely abolished by the p. Leu265Ser mutation. Collectively, our data provide the first insights into the expression and biochemical properties of ELMOD3 and highlight its functional links to sound perception and actin cytoskeleton.\nIntroduction:\nMany molecular components that are necessary for the development and maintenance of hearing have been discovered by identifying the genes that underlie hearing impairment in humans and mice[1]–[4]. Hearing requires the precise and efficient functioning of intricately structured mechanosensory hair cells and supporting cells in the inner ear[3]. One of the key structures in the mechanotransduction process is the hair cell stereocilium. Protruding from the apical surface of the hair cells, stereocilia are organized in three rows of decreasing height in a staircase pattern. Each stereocilium is composed of an actin core that contains cross-linked and bundled γ- and β-actin microfilaments that are uniformly polarized, with the barbed( positive) ends localized at the tip. At the tapered end of the stereocilium, the actin filaments form a rootlet that has been proposed to anchor the structure in the actin-rich meshwork of the cuticular plate[5]. Interestingly, among the identified hearing loss-associated genes, nineteen encode proteins that interact with actin[6],[7]. Numerous studies have demonstrated that actin cytoskeleton-associated proteins are involved in the development, maintenance and stabilization of the stereocilia( for review, see[6]). Continuous depolymerization of actin filaments at the base and polymerization at the barbed end, termed treadmilling, is thought to be critical to the maintenance of the length of stereocilia[8],[9]. However, a recent study demonstrated a rapid turnover of the actin filaments only at the tip of the stereocilia, without a treadmilling process[10], emphasizing the specific role of proteins at the stereocilia tip in the regulation of actin filaments. Regardless of the precise site, it is quite clear that the proper regulation of actin dynamics is critical to the generation and maintenance of stereocilia as sensory structures. The Rho/Rac/Cdc42 family of GTPases is well known as a regulator of actin. Rho and Rac in the inner ear are involved in the morphogenesis and growth of the otocyst[11],[12]. The depletion of Rac1 or both Rac1 and Rac3 in the murine inner ear leads to a shorter cochlear duct with an abnormal sensory epithelium. Rac may participate in cell adhesion, proliferation, and movements during otic development[11],[12]. Several studies have suggested that the activation/inhibition of Rho pathways control the actin depolymerization rate in the outer hair cells[13],[14]. Although best known for their roles in the regulation of membrane traffic, there is growing evidence that GTPases in the Arf family can also act via changes in actin.[15]. Here, we report the identification of a new deafness gene, which encodes an ELMO/CED 12 domain containing protein, ELMOD3. Our biochemical studies demonstrated that ELMOD3 possesses GAP activity against a small GTPase in the Arf family, Arl2, providing a functional link between Arf family signaling pathways and stereocilia actin-based cytoskeletal architecture. GAPs are regulators and effectors of the Ras superfamily of GTPases, which are increasingly recognized as providing specificity as well as temporal and spatial regulation to GTPase signaling[16]. Thus, we believe that the identification of ELMOD3 role in the inner ear provides new insights into signaling processes that are important to hearing in humans.\nDiscussion:\nOur study revealed that ELMOD3 is important for hearing in humans as a missense mutation in the gene leads to profound hearing impairment. ELMOD3 belongs to the engulfment and cell motility( ELMO) protein family, which includes six known members in mammals( ELMO1-3 and ELMOD1-3). Our ex vivo studies reveal that fluorescently tagged ELMOD3 localized with the actin-based microvilli of LLC-PK1-CL4 epithelial cells, in the stereocilia of sensory hair cells of mouse organ of Corti explants, and to a lesser extent to the actin cytoskeleton of MDCK cells, whereas the deafness-associated allele( p. Leu265Ser) was deficient in each case. Similarly, we show that human ELMOD3 possesses Arl2 GAP activity but the mutant has at least a 10-fold loss in activity. While ELMOD3 antibody reactivity was detected in outer hair cells stereocilia at P02, more pronounced accumulation of ELMOD3 immunoreactivity was detected in rat cochlear inner hair cell stereocilia only by P12, which is when hair bundles are in the late phase of maturation. During this period, the inner hair cell stereocilia undergo a rapid elongation[30]. The observed staining suggests that ELMOD3 might be necessary for the initial development of the outer hair cell stereocilia or the organization of the bundle in a staircase pattern but may play a different role in the stereocilia of inner hair cells. Nevertheless, it is tempting to speculate that ELMOD3 may play a role in the maturation or maintenance of the cochlear stereociliary bundle. Recently, two spontaneous mutations( rda and rda2J) in mouse Elmod1 were shown to result in profound deafness and vestibular dysfunction[7], demonstrating that the function of ELMOD1 is essential for regulating the shape and maintenance of inner ear hair cell stereocilia in mice[7]. Elmod1 has been shown to be part of a large cluster of genes expressed in the developing inner ear, while Elmod3 level was below the detectable range[31]. These observations are consistent with findings from other studies, like the SHIELD database, which demonstrated that the level of Elmod3 mRNA is ∼100-fold lower than that of Elmod1 in the developing inner ear( P0–P1). Besides stereocilia bundles, immunoreactivity for ELMOD3 was also detected along the kinocilium in developing cochlear hair cells. Recently, it has been shown that ELMO1 can act at the interface between the actin-cytoskeleton and microtubule network by interacting with ACF7( Actin crosslinking family 7)[32]. Moreover, microtubule polymerization depends on Arl2 activity[33], and we have shown that ELMOD3 exhibits a GAP activity against Arl2. Therefore, ELMOD3 expression in the kinocilium might have a role in the assembly of the kinocilium architecture and in pathways regulating planar cell polarity. The ELMO family proteins are functionally poorly characterized, and more information is currently available for the ELMOs than for the ELMODs, with no structural information available for any of them. So far, only one activity has been ascribed to ELMOD proteins: we previously reported that recombinant human ELMOD1 and ELMOD2 display in vitro Arl2 GAP activity, whereas ELMOD3 and bacterially expressed ELMO1-3 did not[29]. More recently, we performed additional phylogenetic and functional analyses of the ELMO domain that led us to re-examine whether ELMOD3 shares the Arl2 GAP activity of ELMOD1 and ELMOD2. Our data contrast with the earlier-published claim that ELMOD3 lacks Arl2 GAP activity; we determined that it does indeed possess this activity, albeit at a substantially lower specific activity than that of its two closest human paralogs. The large differences in specific activities observed in the Arl2 GAP assay may be due to differences in the specificities of ELMODs as GAPs for different GTPases, including the lack of one or more binding partners( e. g., one that is perhaps analogous to Dock180 binding to ELMO1 or a co-activator for activity such as has been proposed for COP-I and ArfGAP1[34]), and/or the lack of post-translational modification. Our in vitro experiment revealed that ELMOD3 harboring the p. Leu265Ser mutation, unlike ELMOD3, has no or few GAP activity against Arl2. The lack of Arl2 GAP activity of the mutant may suggest a reduced affinity for the Arl2 GTPase, which may play an important role in ELMOD3 localization. Elmod3 and Arl2 are expressed in developing mouse cochlear tissues and weakly in vestibular tissues( Figure S10). Even though ELMOD3 is active and has been defined as “Arl2 GAPs”, we expect it to be active against other GTPases in the Arf family as well. We therefore speculate that ELMOD3 functions as a GAP for Arl2 and perhaps other GTPases that participate in actin organization, polymerization or depolymerization in the cochlear hair bundles. If ELMOD3 is an active GAP for other GTPases, these GTPases are likely to be part of the Arf family given that GAPs are not known to cross family boundaries within the Ras superfamily. However, it is plausible that ELMOD3 functions in a signaling pathway that includes Arl2( or an Arf family GTPase), Rac, Rho, and, ultimately, affects the actin cytoskeleton. Future studies will address the specific roles of ELMOD3 in the development of the inner ear sensory epithelium, cytoskeletal organization, and ELMOD3-mediated signaling pathways. Revealing the interacting partners, substrate specificities for its GAP activities, as well as the means of regulation of ELMOD3 and other ELMO family proteins, will shed light on the overlapping functions of the Ras superfamily in the inner ear. These fundamental functions of this unique protein family are likely to be important in all eukaryotic cells.", "role": "user" }, { "content": "Autosomal recessive nonsyndromic hearing loss is a genetically heterogeneous disorder . Here , we report a severe-to-profound mixed hearing loss locus , DFNB88 on chromosome 2p12-p11 . 2 . Exome enrichment followed by massive parallel sequencing revealed a c . 794T>C transition mutation in ELMOD3 that segregated with DFNB88-associated hearing loss in a large Pakistani family . This transition mutation is predicted to substitute a highly invariant leucine residue with serine ( p . Leu265Ser ) in the engulfment and cell motility ( ELMO ) domain of the protein . No biological activity has been described previously for the ELMOD3 protein . We investigated the biochemical properties and ELMOD3 expression to gain mechanistic insights into the function of ELMOD3 in the inner ear . In rodent inner ears , ELMOD3 immunoreactivity was observed in the cochlear and vestibular hair cells and supporting cells . However , ELMOD3 appears most pronounced in the stereocilia of cochlear hair cells . Ex vivo , ELMOD3 is associated with actin-based structures , and this link is impaired by the DFNB88 mutation . ELMOD3 exhibited GAP activity against Arl2 , a small GTPase , providing a potential functional link between Arf family signaling and stereocilia actin-based cytoskeletal architecture . Our study provides new insights into the molecules that are necessary for the development and/or function of inner ear sensory cells .", "role": "assistant" } ]