Showing papers on "Interaction network published in 2020"

RNAInter in 2020: RNA interactome repository with increased coverage and annotation

Abstract: Research on RNA-associated interactions has exploded in recent years, and increasing numbers of studies are not limited to RNA-RNA and RNA-protein interactions but also include RNA-DNA/compound interactions. To facilitate the development of the interactome and promote understanding of the biological functions and molecular mechanisms of RNA, we updated RAID v2.0 to RNAInter (RNA Interactome Database), a repository for RNA-associated interactions that is freely accessible at http://www.rna-society.org/rnainter/ or http://www.rna-society.org/raid/. Compared to RAID v2.0, new features in RNAInter include (i) 8-fold more interaction data and 94 additional species; (ii) more definite annotations organized, including RNA editing/localization/modification/structure and homology interaction; (iii) advanced functions including fuzzy/batch search, interaction network and RNA dynamic expression and (iv) four embedded RNA interactome tools: RIscoper, IntaRNA, PRIdictor and DeepBind. Consequently, RNAInter contains >41 million RNA-associated interaction entries, involving more than 450 thousand unique molecules, including RNA, protein, DNA and compound. Overall, RNAInter provides a comprehensive RNA interactome resource for researchers and paves the way to investigate the regulatory landscape of cellular RNAs.

Channel Interaction Networks for Fine-Grained Image Categorization

Abstract: Fine-grained image categorization is challenging due to the subtle inter-class differences. We posit that exploiting the rich relationships between channels can help capture such differences since different channels correspond to different semantics. In this paper, we propose a channel interaction network (CIN), which models the channel-wise interplay both within an image and across images. For a single image, a self-channel interaction (SCI) module is proposed to explore channel-wise correlation within the image. This allows the model to learn the complementary features from the correlated channels, yielding stronger fine-grained features. Furthermore, given an image pair, we introduce a contrastive channel interaction (CCI) module to model the cross-sample channel interaction with a metric learning framework, allowing the CIN to distinguish the subtle visual differences between images. Our model can be trained efficiently in an end-to-end fashion without the need of multi-stage training and testing. Finally, comprehensive experiments are conducted on three publicly available benchmarks, where the proposed method consistently outperforms the state-of-the-art approaches, such as DFL-CNN(Wang, Morariu, and Davis 2018) and NTS(Yang et al. 2018).

Bi-Directional Interaction Network for Person Search

Abstract: Existing works have designed end-to-end frameworks based on Faster-RCNN for person search. Due to the large receptive fields in deep networks, the feature maps of each proposal, cropped from the stem feature maps, involve redundant context information outside the bounding boxes. However, person search is a fine-grained task which needs accurate appearance information. Such context information can make the model fail to focus on persons, so the learned representations lack the capacity to discriminate various identities. To address this issue, we propose a Siamese network which owns an additional instance-aware branch, named Bi-directional Interaction Network (BINet). During the training phase, in addition to scene images, BINet also takes as inputs person patches which help the model discriminate identities based on human appearance. Moreover, two interaction losses are designed to achieve bi-directional interaction between branches at two levels. The interaction can help the model learn more discriminative features for persons in the scene. At the inference stage, only the major branch is applied, so BINet introduces no additional computation. Extensive experiments on two widely used person search benchmarks, CUHK-SYSU and PRW, have shown that our BINet achieves state-of-the-art results among end-to-end methods without loss of efficiency.

Predicting human microbe-drug associations via graph convolutional network with conditional random field.

Abstract: MOTIVATION: Human microbes play critical roles in drug development and precision medicine How to systematically understand the complex interaction mechanism between human microbes and drugs remains a challenge nowadays Identifying microbe-drug associations can not only provide great insights into understanding the mechanism, but also boost the development of drug discovery and repurposing Considering the high cost and risk of biological experiments, the computational approach is an alternative choice However, at present, few computational approaches have been developed to tackle this task RESULTS: In this work, we leveraged rich biological information to construct a heterogeneous network for drugs and microbes, including a microbe similarity network, a drug similarity network and a microbe-drug interaction network We then proposed a novel graph convolutional network (GCN)-based framework for predicting human Microbe-Drug Associations, named GCNMDA In the hidden layer of GCN, we further exploited the Conditional Random Field (CRF), which can ensure that similar nodes (ie microbes or drugs) have similar representations To more accurately aggregate representations of neighborhoods, an attention mechanism was designed in the CRF layer Moreover, we performed a random walk with restart-based scheme on both drug and microbe similarity networks to learn valuable features for drugs and microbes, respectively Experimental results on three different datasets showed that our GCNMDA model consistently achieved better performance than seven state-of-the-art methods Case studies for three microbes including SARS-CoV-2 and two antimicrobial drugs (ie Ciprofloxacin and Moxifloxacin) further confirmed the effectiveness of GCNMDA in identifying potential microbe-drug associations AVAILABILITY AND IMPLEMENTATION: Python codes and dataset are available at: https://githubcom/longyahui/GCNMDA SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online

A Data-Driven Graph Generative Model for Temporal Interaction Networks

Abstract: Deep graph generative models have recently received a surge of attention due to its superiority of modeling realistic graphs in a variety of domains, including biology, chemistry, and social science. Despite the initial success, most, if not all, of the existing works are designed for static networks. Nonetheless, many realistic networks are intrinsically dynamic and presented as a collection of system logs (i.e., timestamped interactions/edges between entities), which pose a new research direction for us: how can we synthesize realistic dynamic networks by directly learning from the system logs? In addition, how can we ensure the generated graphs preserve both the structural and temporal characteristics of the real data? To address these challenges, we propose an end-to-end deep generative framework named TagGen. In particular, we start with a novel sampling strategy for jointly extracting structural and temporal context information from temporal networks. On top of that, TagGen parameterizes a bi-level self-attention mechanism together with a family of local operations to generate temporal random walks. At last, a discriminator gradually selects generated temporal random walks, that are plausible in the input data, and feeds them to an assembling module for generating temporal networks. The experimental results in seven real-world data sets across a variety of metrics demonstrate that (1) TagGen outperforms all baselines in the temporal interaction network generation problem, and (2) TagGen significantly boosts the performance of the prediction models in the tasks of anomaly detection and link prediction.

Robustness and lethality in multilayer biological molecular networks.

Abstract: Robustness is a prominent feature of most biological systems. Most previous related studies have been focused on homogeneous molecular networks. Here we propose a comprehensive framework for understanding how the interactions between genes, proteins and metabolites contribute to the determinants of robustness in a heterogeneous biological network. We integrate heterogeneous sources of data to construct a multilayer interaction network composed of a gene regulatory layer, a protein–protein interaction layer, and a metabolic layer. We design a simulated perturbation process to characterize the contribution of each gene to the overall system’s robustness, and find that influential genes are enriched in essential and cancer genes. We show that the proposed mechanism predicts a higher vulnerability of the metabolic layer to perturbations applied to genes associated with metabolic diseases. Furthermore, we find that the real network is comparably or more robust than expected in multiple random realizations. Finally, we analytically derive the expected robustness of multilayer biological networks starting from the degree distributions within and between layers. These results provide insights into the non-trivial dynamics occurring in the cell after a genetic perturbation is applied, confirming the importance of including the coupling between different layers of interaction in models of complex biological systems. Robustness is a prominent feature of most biological systems, but most of the current efforts have been focused on studying homogeneous molecular networks. Here the authors propose a comprehensive framework for understanding how the interactions between genes, proteins, and metabolites contribute to the determinants of robustness.

SkipGNN: predicting molecular interactions with skip-graph networks.

Abstract: Molecular interaction networks are powerful resources for molecular discovery. They are increasingly used with machine learning methods to predict biologically meaningful interactions. While deep learning on graphs has dramatically advanced the prediction prowess, current graph neural network (GNN) methods are mainly optimized for prediction on the basis of direct similarity between interacting nodes. In biological networks, however, similarity between nodes that do not directly interact has proved incredibly useful in the last decade across a variety of interaction networks. Here, we present SkipGNN, a graph neural network approach for the prediction of molecular interactions. SkipGNN predicts molecular interactions by not only aggregating information from direct interactions but also from second-order interactions, which we call skip similarity. In contrast to existing GNNs, SkipGNN receives neural messages from two-hop neighbors as well as immediate neighbors in the interaction network and non-linearly transforms the messages to obtain useful information for prediction. To inject skip similarity into a GNN, we construct a modified version of the original network, called the skip graph. We then develop an iterative fusion scheme that optimizes a GNN using both the skip graph and the original graph. Experiments on four interaction networks, including drug-drug, drug-target, protein-protein, and gene-disease interactions, show that SkipGNN achieves superior and robust performance. Furthermore, we show that unlike popular GNNs, SkipGNN learns biologically meaningful embeddings and performs especially well on noisy, incomplete interaction networks.

Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platform.

Abstract: Real-time semantic segmentation of LiDAR data is crucial for autonomously driving vehicles, which are usually equipped with an embedded platform and have limited computational resources. Approaches that operate directly on the point cloud use complex spatial aggregation operations, which are very expensive and difficult to optimize for embedded platforms. They are therefore not suitable for real-time applications with embedded systems. As an alternative, projection-based methods are more efficient and can run on embedded platforms. However, the current state-of-the-art projection-based methods do not achieve the same accuracy as point-based methods and use millions of parameters. In this paper, we therefore propose a projection-based method, called Multi-scale Interaction Network (MINet), which is very efficient and accurate. The network uses multiple paths with different scales and balances the computational resources between the scales. Additional dense interactions between the scales avoid redundant computations and make the network highly efficient. The proposed network outperforms point-based, image-based, and projection-based methods in terms of accuracy, number of parameters, and runtime. Moreover, the network processes more than 24 scans per second on an embedded platform, which is higher than the framerates of LiDAR sensors. The network is therefore suitable for autonomous vehicles.

Moment Retrieval via Cross-Modal Interaction Networks With Query Reconstruction

Abstract: Moment retrieval aims to localize the most relevant moment in an untrimmed video according to the given natural language query. Existing works often only focus on one aspect of this emerging task, such as the query representation learning, video context modeling or multi-modal fusion, thus fail to develop a comprehensive system for further performance improvement. In this paper, we introduce a novel Cross-Modal Interaction Network (CMIN) to consider multiple crucial factors for this challenging task, including the syntactic dependencies of natural language queries, long-range semantic dependencies in video context and the sufficient cross-modal interaction. Specifically, we devise a syntactic GCN to leverage the syntactic structure of queries for fine-grained representation learning and propose a multi-head self-attention to capture long-range semantic dependencies from video context. Next, we employ a multi-stage cross-modal interaction to explore the potential relations of video and query contents, and we also consider query reconstruction from the cross-modal representations of target moment as an auxiliary task to strengthen the cross-modal representations. The extensive experiments on ActivityNet Captions and TACoS demonstrate the effectiveness of our proposed method.

DiffSLC: A graph centrality method to detect essential proteins of a protein-protein interaction network

Abstract: Identification of central genes and proteins in biomolecular networks provides credible candidates for pathway analysis, functional analysis, and essentiality prediction. The DiffSLC centrality measure predicts central and essential genes and proteins using a protein-protein interaction network. Network centrality measures prioritize nodes and edges based on their importance to the network topology. These measures helped identify critical genes and proteins in biomolecular networks. The proposed centrality measure, DiffSLC, combines the number of interactions of a protein and the gene coexpression values of genes from which those proteins were translated, as a weighting factor to bias the identification of essential proteins in a protein interaction network. Potentially essential proteins with low node degree are promoted through eigenvector centrality. Thus, the gene coexpression values are used in conjunction with the eigenvector of the network's adjacency matrix and edge clustering coefficient to improve essentiality prediction. The outcome of this prediction is shown using three variations: (1) inclusion or exclusion of gene co-expression data, (2) impact of different coexpression measures, and (3) impact of different gene expression data sets. For a total of seven networks, DiffSLC is compared to other centrality measures using Saccharomyces cerevisiae protein interaction networks and gene expression data. Comparisons are also performed for the top ranked proteins against the known essential genes from the Saccharomyces Gene Deletion Project, which show that DiffSLC detects more essential proteins and has a higher area under the ROC curve than other compared methods. This makes DiffSLC a stronger alternative to other centrality methods for detecting essential genes using a protein-protein interaction network that obeys centrality-lethality principle. DiffSLC is implemented using the igraph package in R, and networkx package in Python. The python package can be obtained from git.io/diffslcpy. The R implementation and code to reproduce the analysis is available via git.io/diffslc.

Network-Based Heterogeneous Particle Swarm Optimization and Its Application in UAV Communication Coverage

Abstract: Particle swarm optimization (PSO) aims at finding the optimum point in a high-dimension solution space by simulating the swarming and flocking behaviors in nature. Recent empirical studies of reconstructing the hidden interaction networks in flocking birds and schooling fish found that individuals play different roles in group decision making. An outstanding question is whether the performance of PSO can be improved by incorporating these empirical findings. Here, we systematically explore the impact of the heterogeneity of interaction network and individual's learning strategies to find that the corresponding network-based algorithm, network-based heterogeneous particle swarm optimization (NHPSO), significantly outperforms other PSO based and non-PSO-based comparative algorithms on our experiments with 18 test functions. Our further analysis of the information exchange among the particles reveals that learning from low-degree particles in the middle period of evolution is crucial for the swarm to achieve the global optimum. These results offer a new framework to improve the performance of swarm optimization and demonstrate the applicability of network science in designing optimization algorithms. Finally, the universality of NHPSO is demonstrated on an emerging application, the unmanned aerial vehicle communication coverage.

Dual Path Interaction Network for Video Moment Localization

Abstract: Video moment localization aims to localize a specific moment in a video by a natural language query. Previous works either use alignment information to find out the best-matching candidate (i.e., top-down approach) or use discrimination information to predict the temporal boundaries of the match (i.e., bottom-up approach). Little research has taken both the candidate-level alignment information and frame-level boundary information together and considers the complementarity between them. In this paper, we propose a unified top-down and bottom-up approach called Dual Path Interaction Network (DPIN), where the alignment and discrimination information are closely connected to jointly make the prediction. Our model includes a boundary prediction pathway encoding the frame-level representation and an alignment pathway extracting the candidate-level representation. The two branches of our network predict two complementary but different representations for moment localization. To enforce the consistency and strengthen the connection between the two representations, we propose a semantically conditioned interaction module. The experimental results on three popular benchmarks (i.e., TACoS, Charades-STA, and Activity-Caption) demonstrate that the proposed approach effectively localizes the relevant moment and outperforms the state-of-the-art approaches.

Identification of Protein Complexes by Using a Spatial and Temporal Active Protein Interaction Network

Abstract: The rapid development of proteomics and high-throughput technologies has produced a large amount of Protein-Protein Interaction (PPI) data, which makes it possible for considering dynamic properties of protein interaction networks (PINs) instead of static properties. Identification of protein complexes from dynamic PINs becomes a vital scientific problem for understanding cellular life in the post genome era. Up to now, plenty of models or methods have been proposed for the construction of dynamic PINs to identify protein complexes. However, most of the constructed dynamic PINs just focus on the temporal dynamic information and thus overlook the spatial dynamic information of the complex biological systems. To address the limitation of the existing dynamic PIN analysis approaches, in this paper, we propose a new model-based scheme for the construction of the Spatial and Temporal Active Protein Interaction Network (ST-APIN) by integrating time-course gene expression data and subcellular location information. To evaluate the efficiency of ST-APIN, the commonly used classical clustering algorithm MCL is adopted to identify protein complexes from ST-APIN and the other three dynamic PINs, NF-APIN, DPIN, and TC-PIN. The experimental results show that, the performance of MCL on ST-APIN outperforms those on the other three dynamic PINs in terms of matching with known complexes, sensitivity, specificity, and f-measure. Furthermore, we evaluate the identified protein complexes by Gene Ontology (GO) function enrichment analysis. The validation shows that the identified protein complexes from ST-APIN are more biologically significant. This study provides a general paradigm for constructing the ST-APINs, which is essential for further understanding of molecular systems and the biomedical mechanism of complex diseases.

SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks

Abstract: Molecular interaction networks are powerful resources for the discovery. They are increasingly used with machine learning methods to predict biologically meaningful interactions. While deep learning on graphs has dramatically advanced the prediction prowess, current graph neural network (GNN) methods are optimized for prediction on the basis of direct similarity between interacting nodes. In biological networks, however, similarity between nodes that do not directly interact has proved incredibly useful in the last decade across a variety of interaction networks. Here, we present SkipGNN, a graph neural network approach for the prediction of molecular interactions. SkipGNN predicts molecular interactions by not only aggregating information from direct interactions but also from second-order interactions, which we call skip similarity. In contrast to existing GNNs, SkipGNN receives neural messages from two-hop neighbors as well as immediate neighbors in the interaction network and non-linearly transforms the messages to obtain useful information for prediction. To inject skip similarity into a GNN, we construct a modified version of the original network, called the skip graph. We then develop an iterative fusion scheme that optimizes a GNN using both the skip graph and the original graph. Experiments on four interaction networks, including drug-drug, drug-target, protein-protein, and gene-disease interactions, show that SkipGNN achieves superior and robust performance, outperforming existing methods by up to 28.8\% of area under the precision recall curve (PR-AUC). Furthermore, we show that unlike popular GNNs, SkipGNN learns biologically meaningful embeddings and performs especially well on noisy, incomplete interaction networks.

Constructing Disease Similarity Networks Based on Disease Module Theory

Abstract: Quantifying the associations between diseases is now playing an important role in modern biology and medicine. Actually discovering associations between diseases could help us gain deeper insights into pathogenic mechanisms of complex diseases, thus could lead to improvements in disease diagnosis, drug repositioning, and drug development. Due to the growing body of high-throughput biological data, a number of methods have been developed for computing similarity between diseases during the past decade. However, these methods rarely consider the interconnections of genes related to each disease in protein-protein interaction network (PPIN). Recently, the disease module theory has been proposed, which states that disease-related genes or proteins tend to interact with each other in the same neighborhood of a PPIN. In this study, we propose a new method called ModuleSim to measure associations between diseases by using disease-gene association data and PPIN data based on disease module theory. The experimental results show that by considering the interactions between disease modules and their modularity, the disease similarity calculated by ModuleSim has a significant correlation with disease classification of Disease Ontology (DO). Furthermore, ModuleSim outperforms other four popular methods which are all using disease-gene association data and PPIN data to measure disease-disease associations. In addition, the disease similarity network constructed by MoudleSim suggests that ModuleSim is capable of finding potential associations between diseases.

Network Physiology of Cortico-Muscular Interactions.

Abstract: Skeletal muscle activity is continuously modulated across physiologic states to provide coordination, flexibility and responsiveness to body tasks and external inputs. Despite the central role the muscular system plays in facilitating vital body functions, the network of brain-muscle interactions required to control hundreds of muscles and synchronize their activation in relation to distinct physiologic states has not been investigated. Recent approaches have focused on general associations between individual brain rhythms and muscle activation during movement tasks. However, the specific forms of coupling, the functional network of cortico-muscular coordination, and how network structure and dynamics are modulated by autonomic regulation across physiologic states remains unknown. To identify and quantify the cortico-muscular interaction network and uncover basic features of neuro-autonomic control of muscle function, we investigate the coupling between synchronous bursts in cortical rhythms and peripheral muscle activation during sleep and wake. Utilizing the concept of time delay stability and a novel network physiology approach, we find that the brain-muscle network exhibits complex dynamic patterns of communication involving multiple brain rhythms across cortical locations and different electromyographic frequency bands. Moreover, our results show that during each physiologic state the cortico-muscular network is characterized by a specific profile of network links strength, where particular brain rhythms play role of main mediators of interaction and control. Further, we discover a hierarchical reorganization in network structure across physiologic states, with high connectivity and network link strength during wake, intermediate during REM and light sleep, and low during deep sleep, a sleep-stage stratification that demonstrates a unique association between physiologic states and cortico-muscular network structure. The reported empirical observations are consistent across individual subjects, indicating universal behavior in network structure and dynamics, and high sensitivity of cortico-muscular control to changes in autonomic regulation, even at low levels of physical activity and muscle tone during sleep. Our findings demonstrate previously unrecognized basic principles of brain-muscle network communication and control, and provide new perspectives on the regulatory mechanisms of brain dynamics and locomotor activation, with potential clinical implications for neurodegenerative, movement and sleep disorders, and for developing efficient treatment strategies.

An Iterative Emotion Interaction Network for Emotion Recognition in Conversations

Abstract: Emotion recognition in conversations (ERC) has received much attention recently in the natural language processing community. Considering that the emotions of the utterances in conversations are interactive, previous works usually implicitly model the emotion interaction between utterances by modeling dialogue context, but the misleading emotion information from context often interferes with the emotion interaction. We noticed that the gold emotion labels of the context utterances can provide explicit and accurate emotion interaction, but it is impossible to input gold labels at inference time. To address this problem, we propose an iterative emotion interaction network, which uses iteratively predicted emotion labels instead of gold emotion labels to explicitly model the emotion interaction. This approach solves the above problem, and can effectively retain the performance advantages of explicit modeling. We conduct experiments on two datasets, and our approach achieves state-of-the-art performance.

Drug-target interaction prediction using Multi Graph Regularized Nuclear Norm Minimization.

Abstract: The identification of potential interactions between drugs and target proteins is crucial in pharmaceutical sciences. The experimental validation of interactions in genomic drug discovery is laborious and expensive; hence, there is a need for efficient and accurate in-silico techniques which can predict potential drug-target interactions to narrow down the search space for experimental verification. In this work, we propose a new framework, namely, Multi-Graph Regularized Nuclear Norm Minimization, which predicts the interactions between drugs and target proteins from three inputs: known drug-target interaction network, similarities over drugs and those over targets. The proposed method focuses on finding a low-rank interaction matrix that is structured by the proximities of drugs and targets encoded by graphs. Previous works on Drug Target Interaction (DTI) prediction have shown that incorporating drug and target similarities helps in learning the data manifold better by preserving the local geometries of the original data. But, there is no clear consensus on which kind and what combination of similarities would best assist the prediction task. Hence, we propose to use various multiple drug-drug similarities and target-target similarities as multiple graph Laplacian (over drugs/targets) regularization terms to capture the proximities exhaustively. Extensive cross-validation experiments on four benchmark datasets using standard evaluation metrics (AUPR and AUC) show that the proposed algorithm improves the predictive performance and outperforms recent state-of-the-art computational methods by a large margin. Software is publicly available at https://github.com/aanchalMongia/MGRNNMforDTI.

Deep multiplex graph infomax: Attentive multiplex network embedding using global information

Abstract: Network embedding has recently garnered attention due to the ubiquity of the networked data in the real-world. A network is useful for representing the relationships among objects, and these network include social network, publication network, and protein–protein interaction network. Most existing network embedding methods assume that only a single type of relation exists between nodes. However, we focus on the fact that two nodes in a network can be connected by multiple types of relations; such a network is called multi-view network or multiplex network. Although several existing work consider the multiplexity of a network, they overlook node attributes, resort to node labels for training, and fail to model the global properties of a graph. In this work, we present an unsupervised network embedding method for attributed multiplex network called DMGI , inspired by Deep Graph Infomax (DGI) that maximizes the mutual information between local patches of a graph, and the global representation of the entire graph. Building on top of DGI, we devise a systematic way to jointly integrate the node embeddings from multiple graphs by introducing (1) the consensus regularization framework that minimizes the disagreements among the relation-type specific node embeddings, and (2) the universal discriminator that discriminates true samples regardless of the relation types. We also show that the attention mechanism infers the importance of each relation type, and thus can be useful for filtering unnecessary relation types as a preprocessing step. We perform comprehensive experiments not only on unsupervised downstream tasks, such as clustering and similarity search, but also a supervised downstream task, i.e., node classification, and demonstrate that DMGI outperforms the state-of-the-art methods, even though DMGI is fully unsupervised. The source code is can be found here https://github.com/pcy1302/DMGI .

An integrative framework of heterogeneous genomic data for cancer dynamic modules based on matrix decomposition.

Abstract: Cancer progression is dynamic, and tracking dynamic modules is promising for cancer diagnosis and therapy. Accumulated genomic data provide us an opportunity to investigate the underlying mechanisms of cancers. However, as far as we know, no algorithm has been designed for dynamic modules by integrating heterogeneous omics data. To address this issue, we propose an integrative framework for dynamic module detection based on regularized nonnegative matrix factorization method (DrNMF) by integrating the gene expression and protein interaction network. To remove the heterogeneity of genomic data, we divide the samples of expression profiles into groups to construct gene co-expression networks. To characterize the dynamics of modules, the temporal smoothness framework is adopted, in which the gene co-expression network at the previous stage and protein interaction network are incorporated into the objective function of DrNMF via regularization. The experimental results demonstrate that DrNMF is superior to state-of-the-art methods in terms of accuracy. For breast cancer data, the obtained dynamic modules are more enriched by the known pathways, and can be used to predict the stages of cancers and survival time of patients. The proposed model and algorithm provide an effective integrative analysis of heterogeneous genomic data for cancer progression.

Drug-target interaction prediction using semi-bipartite graph model and deep learning

Abstract: Identifying drug-target interaction is a key element in drug discovery. In silico prediction of drug-target interaction can speed up the process of identifying unknown interactions between drugs and target proteins. In recent studies, handcrafted features, similarity metrics and machine learning methods have been proposed for predicting drug-target interactions. However, these methods cannot fully learn the underlying relations between drugs and targets. In this paper, we propose anew framework for drug-target interaction prediction that learns latent features from drug-target interaction network. We present a framework to utilize the network topology and identify interacting and non-interacting drug-target pairs. We model the problem as a semi-bipartite graph in which we are able to use drug-drug and protein-protein similarity in a drug-protein network. We have then used a graph labeling method for vertex ordering in our graph embedding process. Finally, we employed deep neural network to learn the complex pattern of interacting pairs from embedded graphs. We show our approach is able to learn sophisticated drug-target topological features and outperforms other state-of-the-art approaches. The proposed learning model on semi-bipartite graph model, can integrate drug-drug and protein-protein similarities which are semantically different than drug-protein information in a drug-target interaction network. We show our model can determine interaction likelihood for each drug-target pair and outperform other heuristics.

Robustness of plant quantitative disease resistance is provided by a decentralized immune network

Abstract: Quantitative disease resistance (QDR) represents the predominant form of resistance in natural populations and crops. Surprisingly, very limited information exists on the biomolecular network of the signaling machineries underlying this form of plant immunity. This lack of information may result from its complex and quantitative nature. Here, we used an integrative approach including genomics, network reconstruction, and mutational analysis to identify and validate molecular networks that control QDR in Arabidopsis thaliana in response to the bacterial pathogen Xanthomonas campestris. To tackle this challenge, we first performed a transcriptomic analysis focused on the early stages of infection and using transgenic lines deregulated for the expression of RKS1, a gene underlying a QTL conferring quantitative and broad-spectrum resistance to X. campestris. RKS1-dependent gene expression was shown to involve multiple cellular activities (signaling, transport, and metabolism processes), mainly distinct from effector-triggered immunity (ETI) and pathogen-associated molecular pattern (PAMP)-triggered immunity (PTI) responses already characterized in A. thaliana. Protein–protein interaction network reconstitution then revealed a highly interconnected and distributed RKS1-dependent network, organized in five gene modules. Finally, knockout mutants for 41 genes belonging to the different functional modules of the network revealed that 76% of the genes and all gene modules participate partially in RKS1-mediated resistance. However, these functional modules exhibit differential robustness to genetic mutations, indicating that, within the decentralized structure of the QDR network, some modules are more resilient than others. In conclusion, our work sheds light on the complexity of QDR and provides comprehensive understanding of a QDR immune network.

Impulsive Observer-Based Control in Clustered Networks of Linear Multi-Agent Systems

Abstract: This article addresses the problem of consensus in networks divided into subnetworks (also called clusters), where each node of the network graph represents an agent with linear dynamics. Each subnetwork is represented by a directed graph. Moreover, the agents in each cluster cannot communicate with agents from other clusters, except one single agent of each subnetwork, which is called a leader. These leaders interact some instant times via a fixed and strongly connected directed graph. An impulsive observer-based control protocol is proposed. Based on this proposed protocol, the collective network dynamics of multi-agent systems is described in the term of hybrid systems. The characterization of the global consensus value of this kind of networks is analyzed. Secondly, we show that the problem of consensus design for clustered networks can be indirectly solved by considering the stability of an equivalent system. Then, a sufficient condition for the asymptotical stability of this equivalent system is proposed. Finally, an algorithm properly selects the interaction network of the leaders, feedback gain, observer gain matrices, and coupling weights. This allows agents in the clustered network to enclose a prior fixed target. Simulation results are given to demonstrate the effectiveness of the theoretical results.

Dynamic rewiring of the human interactome by interferon signaling

Abstract: The type I interferon (IFN) response is an ancient pathway that protects cells against viral pathogens by inducing the transcription of hundreds of IFN-stimulated genes. Comprehensive catalogs of IFN-stimulated genes have been established across species and cell types by transcriptomic and biochemical approaches, but their antiviral mechanisms remain incompletely characterized. Here, we apply a combination of quantitative proteomic approaches to describe the effects of IFN signaling on the human proteome, and apply protein correlation profiling to map IFN-induced rearrangements in the human protein-protein interaction network. We identify > 26,000 protein interactions in IFN-stimulated and unstimulated cells, many of which involve proteins associated with human disease and are observed exclusively within the IFN-stimulated network. Differential network analysis reveals interaction rewiring across a surprisingly broad spectrum of cellular pathways in the antiviral response. We identify IFN-dependent protein-protein interactions mediating novel regulatory mechanisms at the transcriptional and translational levels, with one such interaction modulating the transcriptional activity of STAT1. Moreover, we reveal IFN-dependent changes in ribosomal composition that act to buffer IFN-stimulated gene protein synthesis. Our map of the IFN interactome provides a global view of the complex cellular networks activated during the antiviral response, placing IFN-stimulated genes in a functional context, and serves as a framework to understand how these networks are dysregulated in autoimmune or inflammatory disease.

Graph2GO: a multi-modal attributed network embedding method for inferring protein functions

Abstract: Background Identifying protein functions is important for many biological applications. Since experimental functional characterization of proteins is time-consuming and costly, accurate and efficient computational methods for predicting protein functions are in great demand for generating the testable hypotheses guiding large-scale experiments." Results Here, we propose Graph2GO, a multi-modal graph-based representation learning model that can integrate heterogeneous information, including multiple types of interaction networks (sequence similarity network and protein-protein interaction network) and protein features (amino acid sequence, subcellular location, and protein domains) to predict protein functions on gene ontology. Comparing Graph2GO to BLAST, as a baseline model, and to two popular protein function prediction methods (Mashup and deepNF), we demonstrated that our model can achieve state-of-the-art performance. We show the robustness of our model by testing on multiple species. We also provide a web server supporting function query and downstream analysis on-the-fly. Conclusions Graph2GO is the first model that has utilized attributed network representation learning methods to model both interaction networks and protein features for predicting protein functions, and achieved promising performance. Our model can be easily extended to include more protein features to further improve the performance. Besides, Graph2GO is also applicable to other application scenarios involving biological networks, and the learned latent representations can be used as feature inputs for machine learning tasks in various downstream analyses.

LNRLMI: Linear neighbour representation for predicting lncRNA-miRNA interactions

Abstract: LncRNA and miRNA are key molecules in mechanism of competing endogenous RNAs(ceRNA), and their interactions have been discovered with important roles in gene regulation. As supplementary to the identification of lncRNA-miRNA interactions from CLIP-seq experiments, in silico prediction can select the most potential candidates for experimental validation. Although developing computational tool for predicting lncRNA-miRNA interaction is of great importance for deciphering the ceRNA mechanism, little effort has been made towards this direction. In this paper, we propose an approach based on linear neighbour representation to predict lncRNA-miRNA interactions (LNRLMI). Specifically, we first constructed a bipartite network by combining the known interaction network and similarities based on expression profiles of lncRNAs and miRNAs. Based on such a data integration, linear neighbour representation method was introduced to construct a prediction model. To evaluate the prediction performance of the proposed model, k-fold cross validations were implemented. As a result, LNRLMI yielded the average AUCs of 0.8475 ± 0.0032, 0.8960 ± 0.0015 and 0.9069 ± 0.0014 on 2-fold, 5-fold and 10-fold cross validation, respectively. A series of comparison experiments with other methods were also conducted, and the results showed that our method was feasible and effective to predict lncRNA-miRNA interactions via a combination of different types of useful side information. It is anticipated that LNRLMI could be a useful tool for predicting non-coding RNA regulation network that lncRNA and miRNA are involved in.

Disease Module Identification Based on Representation Learning of Complex Networks Integrated From GWAS, eQTL Summaries, and Human Interactome.

Abstract: The study of disease-relevant gene modules is one of the main methods to discover disease pathway and potential drug targets. Recent studies have found that most disease proteins tend to form many separate connected components and scatter across the protein-protein interaction network. However, most of the research on discovering disease modules are biased toward well-studied seed genes, which tend to extend seed genes into a single connected subnetwork. In this paper, we propose N2V-HC, an algorithm framework aiming to unbiasedly discover the scattered disease modules based on deep representation learning of integrated multi-layer biological networks. Our method first predicts disease associated genes based on summary data of Genome-wide Association Studies (GWAS) and expression Quantitative Trait Loci (eQTL) studies, and generates an integrated network on the basis of human interactome. The features of nodes in the network are then extracted by deep representation learning. Hierarchical clustering with dynamic tree cut methods are applied to discover the modules that are enriched with disease associated genes. The evaluation on real networks and simulated networks show that N2V-HC performs better than existing methods in network module discovery. Case studies on Parkinson's disease and Alzheimer's disease, show that N2V-HC can be used to discover biological meaningful modules related to the pathways underlying complex diseases.

Chemically Interpretable Graph Interaction Network for Prediction of Pharmacokinetic Properties of Drug-like Molecules

Abstract: Solubility of drug molecules is related to pharmacokinetic properties such as absorption and distribution, which affects the amount of drug that is available in the body for its action. Computational or experimental evaluation of solvation free energies of drug-like molecules/solute that quantify solubilities is an arduous task and hence development of reliable computationally tractable models is sought after in drug discovery tasks in pharmaceutical industry. Here, we report a novel method based on graph neural network to predict solvation free energies. Previous studies considered only the solute for solvation free energy prediction and ignored the nature of the solvent, limiting their practical applicability. The proposed model is an end-to-end framework comprising three phases namely, message passing, interaction and prediction phases. In the first phase, message passing neural network was used to compute inter-atomic interaction within both solute and solvent molecules represented as molecular graphs. In the interaction phase, features from the preceding step is used to calculate a solute-solvent interaction map, since the solvation free energy depends on how (un)favorable the solute and solvent molecules interact with each other. The calculated interaction map that captures the solute-solvent interactions along with the features from the message passing phase is used to predict the solvation free energies in the final phase. The model predicts solvation free energies involving a large number of solvents with high accuracy. We also show that the interaction map captures the electronic and steric factors that govern the solubility of drug-like molecules and hence is chemically interpretable.