BACKGROUND: Extraction of drug drug interactions from biomedical literature and other textual data is an important component to monitor drug-safety and this has attracted attention of many researchers in healthcare. Existing works are more pivoted around relation extraction using bidirectional long short-term memory networks (BiLSTM) and BERT model which does not attain the best feature representations.RESULTS: Our proposed DDI (drug drug interaction) prediction model provides multiple advantages: (1) The newly proposed attention vector is added to better deal with the problem of overlapping relations, (2) The molecular structure information of drugs is integrated into the model to better express the functional group structure of drugs, (3) We also added text features that combined the T-distribution and chi-square distribution to make the model more focused on drug entities and (4) it achieves similar or better prediction performance (F-scores up to 85.16%) compared to state-of-the-art DDI models when tested on benchmark datasets.CONCLUSIONS: Our model that leverages state of the art transformer architecture in conjunction with multiple features can bolster the performances of drug drug interation tasks in the biomedical domain. In particular, we believe our research would be helpful in identification of potential adverse drug reactions. <<<

Konrad J Karczewski, Matthew Solomonson, Katherine R Chao, Julia K Goodrich, Grace Tiao, Wenhan Lu, Bridget M Riley-Gillis, Ellen A Tsai, Hye In Kim, Xiuwen Zheng, Fedik Rahimov, Sahar Esmaeeli, A Jason Grundstad, Mark Reppell, Jeff Waring, Howard Jacob, David Sexton, Paola G Bronson, Xing Chen, Xinli Hu, Jacqueline I Goldstein, Daniel King, Christopher Vittal, Timothy Poterba, Duncan S Palmer, Claire Churchhouse, Daniel P Howrigan, Wei Zhou, Nicholas A Watts, Kevin Nguyen, Huy Nguyen, Cara Mason, Christopher Farnham, Charlotte Tolonen, Laura D Gauthier, Namrata Gupta, Daniel G MacArthur, Heidi L Rehm, Cotton Seed, Anthony A Philippakis, Mark J Daly, J Wade Davis, Heiko Runz, Melissa R Miller, Benjamin M Neale <<<

Genome-wide association studies have successfully discovered thousands of common variants associated with human diseases and traits, but the landscape of rare variations in human disease has not been explored at scale. Exome-sequencing studies of population biobanks provide an opportunity to systematically evaluate the impact of rare coding variations across a wide range of phenotypes to discover genes and allelic series relevant to human health and disease. Here, we present results from systematic association analyses of 4,529 phenotypes using single-variant and gene tests of 394,841 individuals in the UK Biobank with exome-sequence data. We find that the discovery of genetic associations is tightly linked to frequency and is correlated with metrics of deleteriousness and natural selection. We highlight biological findings elucidated by these data and release the dataset as a public resource alongside the Genebass browser for rapidly exploring rare-variant association results. <<<

We apply previously developed Chu space and Channel Theory methods, focusing on the construction of Cone-Cocone Diagrams (CCCDs), to study the role of epistemic feelings, particularly feelings of confidence, in dual process models of problem solving. We specifically consider "Bayesian brain" models of probabilistic inference within a global neuronal workspace architecture. We develop a formal representation of Process-1 problem solving in which a solution is reached if and only if a CCCD is completed. We show that in this representation, Process-2 problem solving can be represented as multiply iterated Process-1 problem solving and has the same formal solution conditions. We then model the generation of explicit, reportable subjective probabilities from implicit, experienced confidence as a simulation-based, reverse engineering process and show that this process can also be modeled as a CCCD construction. <<<

Carolina Villarroya-Beltri , Ana Osorio , Raúl Torres-Ruiz , David Gómez-Sánchez , Marianna Trakala , Agustin Sánchez-Belmonte , Fátima Mercadillo , Borja Pitarch , Almudena Hernández-Núñez , Antonio Gómez-Caturla , Daniel Rueda , José Perea , Sandra Rodríguez-Perales , Marcos Malumbres , Miguel Urioste <<<

Aneuploidy is a frequent feature of human tumors. Germline mutations leading to aneuploidy are very rare in humans, and their tumor-promoting properties are mostly unknown at the molecular level. We report here novel germline biallelic mutations in MAD1L1, the gene encoding the Spindle Assembly Checkpoint (SAC) protein MAD1, in a 36-year-old female with a dozen of neoplasias, including five malignant tumors. Functional studies in peripheral blood cells demonstrated lack of full-length protein and deficient SAC response, resulting in ∼30-40% of aneuploid cells as detected by cytogenetic and single-cell (sc) DNA analysis. scRNA-seq analysis of patient blood cells identified mitochondrial stress accompanied by systemic inflammation with enhanced interferon and NFkB signaling. The inference of chromosomal aberrations from scRNA-seq analysis detected inflammatory signals both in aneuploid and euploid cells, suggesting a non-cell autonomous response to aneuploidy. In addition to random aneuploidies, MAD1L1 mutations resulted in specific clonal expansions of γδ T-cells with chromosome 18 gains and enhanced cytotoxic profile, as well as intermediate B-cells with chromosome 12 gains and transcriptomic signatures characteristic of chronic lymphocytic leukemia cells. These data point to MAD1L1 mutations as the cause of a new aneuploidy syndrome with systemic inflammation and unprecedented tumor susceptibility. <<<

The ability to anticipate and flexibly plan for the future is critical for achieving goal-directed outcomes. Extant data suggest that neural and cognitive stress mechanisms may disrupt memory retrieval and restrict prospective planning, with deleterious impacts on behavior. Here, we examined whether and how acute psychological stress influences goal-directed navigational planning and efficient, flexible behavior. Our methods combined fMRI, neuroendocrinology, and machine learning with a virtual navigation planning task. Human participants were trained to navigate familiar paths in virtual environments and then (concurrent with fMRI) performed a planning and navigation task that could be most efficiently solved by taking novel shortcut paths. Strikingly, relative to non-stressed control participants, participants who performed the planning task under experimentally induced acute psychological stress demonstrated (1) disrupted neural activity critical for mnemonic retrieval and mental simulation and (2) reduced traversal of shortcuts and greater reliance on familiar paths. These neural and behavioral changes under psychological stress were tied to evidence for disrupted neural replay of memory for future locations in the spatial environment, providing mechanistic insight into why and how stress can alter planning and foster inefficient behavior. <<<

Mitchell E Fane, Yash Chhabra, Gretchen M Alicea, Devon A Maranto, Stephen M Douglass, Marie R Webster, Vito W Rebecca, Gloria E Marino, Filipe Almeida, Brett L Ecker, Daniel J Zabransky, Laura Hüser, Thomas Beer, Hsin-Yao Tang, Andrew Kossenkov, Meenhard Herlyn, David W Speicher, Wei Xu, Xiaowei Xu, Elizabeth M Jaffee, Julio A Aguirre-Ghiso, Ashani T Weeraratna <<<

Disseminated cancer cells from primary tumours can seed in distal tissues, but may take several years to form overt metastases, a phenomenon that is termed tumour dormancy. Despite its importance in metastasis and residual disease, few studies have been able to successfully characterize dormancy within melanoma. Here we show that the aged lung microenvironment facilitates a permissive niche for efficient outgrowth of dormant disseminated cancer cells-in contrast to the aged skin, in which age-related changes suppress melanoma growth but drive dissemination. These microenvironmental complexities can be explained by the phenotype switching model, which argues that melanoma cells switch between a proliferative cell state and a slower-cycling, invasive state. It was previously shown that dermal fibroblasts promote phenotype switching in melanoma during ageing. We now identify WNT5A as an activator of dormancy in melanoma disseminated cancer cells within the lung, which initially enables the efficient dissemination and seeding of melanoma cells in metastatic niches. Age-induced reprogramming of lung fibroblasts increases their secretion of the soluble WNT antagonist sFRP1, which inhibits WNT5A in melanoma cells and thereby enables efficient metastatic outgrowth. We also identify the tyrosine kinase receptors AXL and MER as promoting a dormancy-to-reactivation axis within melanoma cells. Overall, we find that age-induced changes in distal metastatic microenvironments promote the efficient reactivation of dormant melanoma cells in the lung. <<<

In this article, we discuss recent research that has arisen from theoretical and conceptual models that use a systems metaphor for understanding families. We suggest that research stimulated by such models leads social scientists in new and important directions in understanding the social and emotional development of children in their families. These models view development as resulting from the dynamic transactions across multiple levels of family systems, which regulate a child's behavior. Thus, these models are important in considering multiple influences on development and adaptation. <<<

Daniel Bottomly, Nicola Long, Anna Reister Schultz, Stephen E Kurtz, Cristina E Tognon, Kara Johnson, Melissa Abel, Anupriya Agarwal, Sammantha Avaylon, Erik Benton, Aurora Blucher, Uma Borate, Theodore P Braun, Jordana Brown, Jade Bryant, Russell Burke, Amy Carlos, Bill H Chang, Hyun Jun Cho, Stephen Christy, Cody Coblentz, Aaron M Cohen, Amanda d'Almeida, Rachel Cook, Alexey Danilov, Kim-Hien T Dao, Michie Degnin, James Dibb, Christopher A Eide, Isabel English, Stuart Hagler, Heath Harrelson, Rachel Henson, Hibery Ho, Sunil K Joshi, Brian Junio, Andy Kaempf, Yoko Kosaka, Ted Laderas, Matt Lawhead, Hyunjung Lee, Jessica T Leonard, Chenwei Lin, Evan F Lind, Selina Qiuying Liu, Pierrette Lo, Marc M Loriaux, Samuel Luty, Julia E Maxson, Tara Macey, Jacqueline Martinez, Jessica Minnier, Andrea Monteblanco, Motomi Mori, Quinlan Morrow, Dylan Nelson, Justin Ramsdill, Angela Rofelty, Alexandra Rogers, Kyle A Romine, Peter Ryabinin, Jennifer N Saultz, David A Sampson, Samantha L Savage, Robert Schuff, Robert Searles, Rebecca L Smith, Stephen E Spurgeon, Tyler Sweeney, Ronan T Swords, Aashis Thapa, Karina Thiel-Klare, Elie Traer, Jake Wagner, Beth Wilmot, Joelle Wolf, Guanming Wu, Amy Yates, Haijiao Zhang, Christopher R Cogle, Robert H Collins, Michael W Deininger, Christopher S Hourigan, Craig T Jordan, Tara L Lin, Micaela E Martinez, Rachel R Pallapati, Daniel A Pollyea, Anthony D Pomicter, Justin M Watts, Scott J Weir, Brian J Druker, Shannon K McWeeney, Jeffrey W Tyner <<<

Acute myeloid leukemia (AML) is a cancer of myeloid-lineage cells with limited therapeutic options. We previously combined ex vivo drug sensitivity with genomic, transcriptomic, and clinical annotations for a large cohort of AML patients, which facilitated discovery of functional genomic correlates. Here, we present a dataset that has been harmonized with our initial report to yield a cumulative cohort of 805 patients (942 specimens). We show strong cross-cohort concordance and identify features of drug response. Further, deconvoluting transcriptomic data shows that drug sensitivity is governed broadly by AML cell differentiation state, sometimes conditionally affecting other correlates of response. Finally, modeling of clinical outcome reveals a single gene, PEAR1, to be among the strongest predictors of patient survival, especially for young patients. Collectively, this report expands a large functional genomic resource, offers avenues for mechanistic exploration and drug development, and reveals tools for predicting outcome in AML. <<<

Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn universal embeddings of time series. Unlike previous works, it is scalable with respect to their length and we demonstrate the quality, transferability and practicability of the learned representations with thorough experiments and comparisons. To this end, we combine an encoder based on causal dilated convolutions with a novel triplet loss employing time-based negative sampling, obtaining general-purpose representations for variable length and multivariate time series. <<<

Multivariate time-series forecasting plays a crucial role in many real-world applications. It is a challenging problem as one needs to consider both intra-series temporal correlations and inter-series correlations simultaneously. Recently, there have been multiple works trying to capture both correlations, but most, if not all of them only capture temporal correlations in the time domain and resort to pre-defined priors as inter-series relationships. In this paper, we propose Spectral Temporal Graph Neural Network (StemGNN) to further improve the accuracy of multivariate time-series forecasting. StemGNN captures inter-series correlations and temporal dependencies \textit{jointly} in the \textit{spectral domain}. It combines Graph Fourier Transform (GFT) which models inter-series correlations and Discrete Fourier Transform (DFT) which models temporal dependencies in an end-to-end framework. After passing through GFT and DFT, the spectral representations hold clear patterns and can be predicted effectively by convolution and sequential learning modules. Moreover, StemGNN learns inter-series correlations automatically from the data without using pre-defined priors. We conduct extensive experiments on ten real-world datasets to demonstrate the effectiveness of StemGNN. Code is available at this https URL <<<

Given a multivariate time series, how can we forecast all of its variables efficiently and accurately? The multivariate forecasting, which is to predict the future observations of a multivariate time series, is a fundamental problem closely related to many real-world applications. However, previous multivariate models suffer from large model sizes due to the inefficiency of capturing complex intra-variable patterns and inter-variable correlations, resulting in poor accuracy. In this work, we propose AttnAR (attention-based autoregression), a novel approach for general multivariate forecasting which maximizes its model efficiency via separable structure. AttnAR first extracts variable-wise patterns by a mixed convolution extractor that efficiently combines deep convolution layers and shallow dense layers. Then, AttnAR aggregates the patterns by learning time-invariant attention maps between the target variables. AttnAR accomplishes the state-of-the-art forecasting accuracy in four datasets with up to 117.3 times fewer parameters than the best competitors. <<<

Multivariate time series (MTS) forecasting is widely used in various domains, such as meteorology and traffic. Due to limitations on data collection, transmission, and storage, real-world MTS data usually contains missing values, making it infeasible to apply existing MTS forecasting models such as linear regression and recurrent neural networks. Though many efforts have been devoted to this problem, most of them solely rely on local dependencies for imputing missing values, which ignores global temporal dynamics. Local dependencies/patterns would become less useful when the missing ratio is high, or the data have consecutive missing values; while exploring global patterns can alleviate such problem. Thus, jointly modeling local and global temporal dynamics is very promising for MTS forecasting with missing values. However, work in this direction is rather limited. Therefore, we study a novel problem of MTS forecasting with missing values by jointly exploring local and global temporal dynamics. We propose a new framework øurs, which leverages memory network to explore global patterns given estimations from local perspectives. We further introduce adversarial training to enhance the modeling of global temporal distribution. Experimental results on real-world datasets show the effectiveness of øurs for MTS forecasting with missing values and its robustness under various missing ratios. <<<

In the brain, the insular cortex receives a vast amount of interoceptive information, ascending through deep brain structures, from multiple visceral organs. The unique hierarchical and modular architecture of the insula suggests specialization for processing interoceptive afferents. Yet, the biological significance of the insula's neuroanatomical architecture, in relation to deep brain structures, remains obscure. In this opinion piece, we propose the Insula Hierarchical Modular Adaptive Interoception Control (IMAC) model to suggest that insula modules (granular, dysgranular and agranular), forming parallel networks with the prefrontal cortex and striatum, are specialized to form higher order interoceptive representations. These interoceptive representations are recruited in a context-dependent manner to support habitual, model-based and exploratory control of visceral organs and physiological processes. We discuss how insula interoceptive representations may give rise to conscious feelings that best explain lower order deep brain interoceptive representations, and how the insula may serve to defend the body and mind against pathological depression. <<<

In this paper, we propose a novel Knowledge-based Embodied Question Answering (K-EQA) task, in which the agent intelligently explores the environment to answer various questions with the knowledge. Different from explicitly specifying the target object in the question as existing EQA work, the agent can resort to external knowledge to understand more complicated question such as "Please tell me what are objects used to cut food in the room?", in which the agent must know the knowledge such as "knife is used for cutting food". To address this K-EQA problem, a novel framework based on neural program synthesis reasoning is proposed, where the joint reasoning of the external knowledge and 3D scene graph is performed to realize navigation and question answering. Especially, the 3D scene graph can provide the memory to store the visual information of visited scenes, which significantly improves the efficiency for the multi-turn question answering. Experimental results have demonstrated that the proposed framework is capable of answering more complicated and realistic questions in the embodied environment. The proposed method is also applicable to multi-agent scenarios. <<<

This paper introduces a new approach for Multivariate Time Series forecasting that jointly infers and leverages relations among time series. Its modularity allows it to be integrated with current univariate methods. Our approach allows to trade-off accuracy and computational efficiency gradually via offering on one extreme inference of a potentially fully-connected graph or on another extreme a bipartite graph. In the potentially fully-connected case we consider all pair-wise interactions among time-series which yields the best forecasting accuracy. Conversely, the bipartite case leverages the dependency structure by inter-communicating the N time series through a small set of K auxiliary nodes that we introduce. This reduces the time and memory complexity w.r.t. previous graph inference methods from O(N^2) to O(NK) with a small trade-off in accuracy. We demonstrate the effectiveness of our model in a variety of datasets where both of its variants perform better or very competitively to previous graph inference methods in terms of forecasting accuracy and time efficiency. <<<

Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate time series forecasting is that its variables depend on one another but, upon looking closely, it is fair to say that existing methods fail to fully exploit latent spatial dependencies between pairs of variables. In recent years, meanwhile, graph neural networks (GNNs) have shown high capability in handling relational dependencies. GNNs require well-defined graph structures for information propagation which means they cannot be applied directly for multivariate time series where the dependencies are not known in advance. In this paper, we propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module, into which external knowledge like variable attributes can be easily integrated. A novel mix-hop propagation layer and a dilated inception layer are further proposed to capture the spatial and temporal dependencies within the time series. The graph learning, graph convolution, and temporal convolution modules are jointly learned in an end-to-end framework. Experimental results show that our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets and achieves on-par performance with other approaches on two traffic datasets which provide extra structural information. <<<

The positive-negative axis of emotional valence has long been recognized as fundamental to adaptive behavior, but its origin and underlying function have largely eluded formal theorizing and computational modeling. Using deep active inference, a hierarchical inference scheme that rests on inverting a model of how sensory data are generated, we develop a principled Bayesian model of emotional valence. This formulation asserts that agents infer their valence state based on the expected precision of their action model-an internal estimate of overall model fitness ("subjective fitness"). This index of subjective fitness can be estimated within any environment and exploits the domain generality of second-order beliefs (beliefs about beliefs). We show how maintaining internal valence representations allows the ensuing affective agent to optimize confidence in action selection preemptively. Valence representations can in turn be optimized by leveraging the (Bayes-optimal) updating term for subjective fitness, which we label affective charge (AC). AC tracks changes in fitness estimates and lends a sign to otherwise unsigned divergences between predictions and outcomes. We simulate the resulting affective inference by subjecting an in silico affective agent to a T-maze paradigm requiring context learning, followed by context reversal. This formulation of affective inference offers a principled account of the link between affect, (mental) action, and implicit metacognition. It characterizes how a deep biological system can infer its affective state and reduce uncertainty about such inferences through internal action (i.e., top-down modulation of priors that underwrite confidence). Thus, we demonstrate the potential of active inference to provide a formal and computationally tractable account of affect. Our demonstration of the face validity and potential utility of this formulation represents the first step within a larger research program. Next, this model can be leveraged to test the hypothesized role of valence by fitting the model to behavioral and neuronal responses. <<<

Over the last 10 to 15 years, active inference has helped to explain various brain mechanisms from habit formation to dopaminergic discharge and even modelling curiosity. However, the current implementations suffer from an exponential (space and time) complexity class when computing the prior over all the possible policies up to the time-horizon. Fountas et al. (2020) used Monte Carlo tree search to address this problem, leading to impressive results in two different tasks. In this paper, we present an alternative framework that aims to unify tree search and active inference by casting planning as a structure learning problem. Two tree search algorithms are then presented. The first propagates the expected free energy forward in time (i.e., towards the leaves), while the second propagates it backward (i.e., towards the root). Then, we demonstrate that forward and backward propagations are related to active inference and sophisticated inference, respectively, thereby clarifying the differences between those two planning strategies. <<<

Most proteins in cells are composed of multiple folding units (or domains) to perform complex functions in a cooperative manner. Relative to the rapid progress in single-domain structure prediction, there are few effective tools available for multi-domain protein structure assembly, mainly due to the complexity of modeling multi-domain proteins, which involves higher degrees of freedom in domain-orientation space and various levels of continuous and discontinuous domain assembly and linker refinement. To meet the challenge and the high demand of the community, we developed I-TASSER-MTD to model the structures and functions of multi-domain proteins through a progressive protocol that combines sequence-based domain parsing, single-domain structure folding, inter-domain structure assembly and structure-based function annotation in a fully automated pipeline. Advanced deep-learning models have been incorporated into each of the steps to enhance both the domain modeling and inter-domain assembly accuracy. The protocol allows for the incorporation of experimental cross-linking data and cryo-electron microscopy density maps to guide the multi-domain structure assembly simulations. I-TASSER-MTD is built on I-TASSER but substantially extends its ability and accuracy in modeling large multi-domain protein structures and provides meaningful functional insights for the targets at both the domain- and full-chain levels from the amino acid sequence alone. <<<

While many multi-robot coordination problems can be solved optimally by exact algorithms, solutions are often not scalable in the number of robots. Multi-Agent Reinforcement Learning (MARL) is gaining increasing attention in the robotics community as a promising solution to tackle such problems. Nevertheless, we still lack the tools that allow us to quickly and efficiently find solutions to large-scale collective learning tasks. In this work, we introduce the Vectorized Multi-Agent Simulator (VMAS). VMAS is an open-source framework designed for efficient MARL benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of twelve challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface. We demonstrate how vectorization enables parallel simulation on accelerated hardware without added complexity. When comparing VMAS to OpenAI MPE, we show how MPE's execution time increases linearly in the number of simulations while VMAS is able to execute 30,000 parallel simulations in under 10s, proving more than 100x faster. Using VMAS's RLlib interface, we benchmark our multi-robot scenarios using various Proximal Policy Optimization (PPO)-based MARL algorithms. VMAS's scenarios prove challenging in orthogonal ways for state-of-the-art MARL algorithms. The VMAS framework is available at this https URL. A video of VMAS scenarios and experiments is available at this https URL}{here}\footnote{\url{this https URL. <<<