In the recent few years, an increasing number of studies have shown that microRNAs (miRNAs) play critical roles in many fundamental and important biological processes. As one pathogenetic factors, molecular mechanisms underlying human complex diseases still not been completely understood from perspective miRNA. Predicting potential miRNA-disease associations makes contributions to understanding pathogenesis diseases, developing new drugs, formulating individualized diagnosis treatment for...

Increasing evidences have indicated that microRNAs (miRNAs) are functionally associated with the development and progression of various complex human diseases. However, roles miRNAs in multiple biological processes or diseases their underlying molecular mechanisms still not been fully understood yet. Predicting potential miRNA-disease associations by integrating heterogeneous datasets is great significance to biomedical research. Computational methods could obtain a short time, which...

Nonnegative matrix factorization (NMF)-based models possess fine representativeness of a target matrix, which is critically important in collaborative filtering (CF)-based recommender systems. However, current NMF-based CF recommenders suffer from the problem high computational and storage complexity, as well slow convergence rate, prevents them industrial usage context big data. To address these issues, this paper proposes an alternating direction method (ADM)-based nonnegative latent...

Protein-protein interactions (PPIs) play crucial roles in the execution of various cellular processes and form basis biological mechanisms. Although large amount PPIs data for different species has been generated by high-throughput experimental techniques, current PPI pairs obtained with methods cover only a fraction complete networks, further, identifying are both time-consuming expensive. Hence, it is urgent challenging to develop automated computational efficiently accurately predict...

Abstract Motivation A large number of resources have been devoted to exploring the associations between microRNAs (miRNAs) and diseases in recent years. However, experimental methods are expensive time-consuming. Therefore, computational predict potential miRNA–disease paid increasing attention. Results In this paper, we proposed a novel model Bipartite Network Projection for MiRNA–Disease Association prediction (BNPMDA) based on known associations, integrated miRNA similarity disease...

Generating highly accurate predictions for missing quality-of-service (QoS) data is an important issue. Latent factor (LF)-based QoS-predictors have proven to be effective in dealing with it. However, they are based on first-order solvers that cannot well address their target problem inherently bilinear and nonconvex, thereby leaving a significant opportunity accuracy improvement. This paper proposes incorporate efficient second-order solver into them raise accuracy. To do so, we adopt the...

Recently, microRNAs (miRNAs) have drawn more and attentions because accumulating experimental studies indicated miRNA could play critical roles in multiple biological processes as well the development progression of human complex diseases. Using huge number known heterogeneous datasets to predict potential associations between miRNAs diseases is an important topic field biology, medicine, bioinformatics. In this study, considering limitations previous computational methods, we developed...

Abstract Motivation Accumulating clinical observations have indicated that microbes living in the human body are closely associated with a wide range of noninfectious diseases, which provides promising insights into complex disease mechanism understanding. Predicting microbe–disease associations could not only boost diagnostic and prognostic, but also improve new drug development. However, little efforts been attempted to understand predict on large scale until now. Results In this work, we...

In recent years, accumulating evidences have shown that the dysregulations of lncRNAs are associated with a wide range human diseases. It is necessary and feasible to analyze known lncRNA-disease associations, predict potential provide most possible pairs for experimental validation. Considering limitations traditional Random Walk Restart (RWR), model Improved LncRNA-Disease Association prediction (IRWRLDA) was developed novel associations by integrating disease semantic similarity, various...

Nowadays, researchers have realized that microRNAs (miRNAs) are playing a significant role in many important biological processes and they closely connected with various complex human diseases. However, since there too possible miRNA-disease associations to analyze, it remains difficult predict the potential miRNAs related diseases without systematic effective method. In this study, we developed Matrix Completion for MiRNA-Disease Association prediction model (MCMDA) based on known HMDD...

Identifying the interaction between drugs and target proteins is an important area of drug research, which provides a broad prospect for low-risk faster development. However, due to limitations traditional experiments when revealing drug-protein interactions (DTIs), screening targets not only takes lot time money but also has high false-positive false-negative rates. Therefore, it imperative develop effective automatic computational methods accurately predict DTIs in postgenome era. In this...

Cancer is a well-known killer of human beings, which has led to countless deaths and misery. Anticancer peptides open promising perspective for cancer treatment, they have various attractive advantages. Conventional wet experiments are expensive inefficient finding identifying novel anticancer peptides. There an urgent need develop computational method predict In this study, we propose deep learning long short-term memory (LSTM) neural network model, ACP-DL, effectively More specifically,...

Abstract Graph is a natural data structure for describing complex systems, which contains set of objects and relationships. Ubiquitous real-life biomedical problems can be modeled as graph analytics tasks. Machine learning, especially deep succeeds in vast bioinformatics scenarios with represented Euclidean domain. However, rich relational information between biological elements retained the non-Euclidean graphs, not learning friendly to classic machine methods. representation aims embed...

Abstract Proteins interact with each other to play critical roles in many biological processes cells. Although promising, laboratory experiments usually suffer from the disadvantages of being time-consuming and labor-intensive. The results obtained are often not robust considerably uncertain. Due recently advances high-throughput technologies, a large amount proteomics data has been collected this presents significant opportunity also challenge develop computational models predict...

Abstract Identifying new indications for drugs plays an essential role at many phases of drug research and development. Computational methods are regarded as effective way to associate with indications. However, most them complete their tasks by constructing a variety heterogeneous networks without considering the biological knowledge diseases, which believed be useful improving accuracy repositioning. To this end, novel information network (HIN) based model, namely HINGRL, is proposed...

Abstract Drug–drug interactions (DDIs) are known as the main cause of life-threatening adverse events, and their identification is a key task in drug development. Existing computational algorithms mainly solve this problem by using advanced representation learning techniques. Though effective, few them capable performing tasks on biomedical knowledge graphs (KGs) that provide more detailed information about attributes drug-related triple facts. In work, an attention-based KG framework,...

Drug repositioning is a promising drug development technique to identify new indications for existing drugs. However, computational models only make use of lower-order biological information at the level individual drugs, diseases and their associations, but few them can take into account higher-order connectivity patterns presented in heterogeneous networks (HINs). In this work, we propose novel graph representation learning model, namely FuHLDR, by fusing higher information. Specifically,...

The task of predicting drug-target interactions (DTIs) plays a significant role in facilitating the development novel drug discovery. Compared with laboratory-based approaches, computational methods proposed for DTI prediction are preferred due to their high-efficiency and low-cost advantages. Recently, much attention has been attracted apply different graph neural network (GNN) models discover underlying DTIs from heterogeneous biological information (HBIN). Although GNN-based achieve...

As post-transcriptional regulators of gene expression, micro-ribonucleic acids (miRNAs) are regarded as potential biomarkers for a variety diseases. Hence, the prediction miRNA-disease associations (MDAs) is great significance an in-depth understanding disease pathogenesis and progression. Existing models mainly concentrated on incorporating different sources biological information to perform MDA task while failing consider fully utility network at motif-level. To overcome this problem, we...

Connections between circular RNAs (circRNAs) and microRNAs (miRNAs) assume a pivotal position in the onset, evolution, diagnosis treatment of diseases tumors. Selecting most potential circRNA-related miRNAs taking advantage them as biological markers or drug targets could be conducive to dealing with complex human through preventive strategies, diagnostic procedures therapeutic approaches. Compared traditional experiments, leveraging computational models integrate diverse data order infer...