Background The identification of human disease-related microRNAs (disease miRNAs) is important for further investigating their involvement in the pathogenesis diseases. More experimentally validated miRNA-disease associations have been accumulated recently. On basis these associations, it essential to predict disease miRNAs various It useful providing reliable miRNA candidates subsequent experimental studies. Methodology/Principal Findings known that with similar functions are often...

Abstract Motivation: Identifying microRNAs associated with diseases (disease miRNAs) is helpful for exploring the pathogenesis of diseases. Because miRNAs fulfill function via regulation their target genes and because current number experimentally validated targets insufficient, some existing methods have inferred potential disease based on predicted targets. It difficult these to achieve excellent performance due high false-positive false-negative rates prediction results. Alternatively,...

In multi-agent cooperation, agents share a common goal, which is evaluated through global utility function. However, an agent typically cannot observe the state of uncertain environment, and therefore they must communicate with each other in order to information needed for deciding actions take. We argue that, when communication incurs cost (due resource consumption, example), whether or not also becomes decision make. Hence, part overall problem. explicitly address this problem, we present...

Aberrant expressions of long non-coding RNAs (lncRNAs) are often associated with diseases and identification disease-related lncRNAs is helpful for elucidating complex pathogenesis. Recent methods predicting associations between integrate their pertinent heterogeneous data. However, they failed to deeply topological information network comprising lncRNAs, diseases, miRNAs. We proposed a novel method based on the graph convolutional neural network, referred as GCNLDA, infer lncRNA candidates....

Determining the target genes that interact with drugs-drug-target interactions-plays an important role in drug discovery. Identification of drug-target interactions through biological experiments is time consuming, laborious, and costly. Therefore, using computational approaches to predict candidate targets a good way reduce cost wet-lab experiments. However, known (positive samples) unknown (negative display serious class imbalance, which has adverse effect on accuracy prediction results....

Abstract Motivation Identifying and developing novel therapeutic effects for existing drugs contributes to reduction of drug development costs. Most the previous methods focus on integration heterogeneous data diseases from multiple sources predicting candidate drug–disease associations. However, they fail take prior knowledge their sparse characteristic into account. It is essential develop a method that exploits more useful information predict reliable Results We present based non-negative...

The demand for efficient scalable and cost effective mobile information access systems is rapidly growing. Radiofrequency broadcast plays a major role in computing, there need to provide service models broadcasting according users' needs. authors present model called on (BoD), which provides timely broadcasts requests from users. Compared static broadcast, this approach has different emphasis: it based driven framework, aimed at satisfying the temporal constraints of requests, uses...

Abstract Motivation: Compared with sequence and structure similarity, functional similarity is more informative for understanding the biological roles functions of genes. Many important applications in computational molecular biology require such as gene clustering, protein function prediction, interaction evaluation disease prioritization. Gene Ontology (GO) now widely used basis measuring similarity. Some existing methods combined semantic scores single term pairs to estimate whereas...

Background:The identification of human disease-related microRNAs (disease miRNAs) is important for further investigating their involvement in the pathogenesis diseases.More experimentally validated miRNA-disease associations have been accumulated recently.On basis these associations, it essential to predict disease miRNAs various diseases.It useful providing reliable miRNA candidates subsequent experimental studies.Methodology/Principal Findings: It known that with similar functions are...

A lot of studies indicated that aberrant expression long non-coding RNA genes (lncRNAs) is closely related to human diseases. Identifying disease-related lncRNAs (disease lncRNAs) critical for understanding the pathogenesis and etiology Most previous methods focus on prioritizing potential disease based shallow learning methods. The fail extract deep complex feature representations lncRNA-disease associations. Furthermore, nearly all ignore discriminative contributions similarity,...

Abstract As the abnormalities of long non-coding RNAs (lncRNAs) are closely related to various human diseases, identifying disease-related lncRNAs is important for understanding pathogenesis complex diseases. Most current data-driven methods lncRNA candidate prediction based on diseases and lncRNAs. Those methods, however, fail consider deeply embedded node attributes lncRNA–disease pairs, which contain multiple relations representations across lncRNAs, miRNAs. Moreover, low-dimensional...

Abstract Motivation The human microbiome may impact the effectiveness of drugs by modulating their activities and toxicities. Predicting candidate microbes for can facilitate exploration therapeutic effects drugs. Most recent methods concentrate on constructing prediction models based graph reasoning. They fail to sufficiently exploit topology position information, heterogeneity multiple types nodes connections, long-distance correlations among in microbe–drug heterogeneous graph. Results We...

Abstract Motivation: MicroRNAs (miRNAs) are a set of short (21–24 nt) non-coding RNAs that play significant roles as post-transcriptional regulators in animals and plants. While some existing methods use comparative genomic approaches to identify plant precursor miRNAs (pre-miRNAs), others based on the complementarity characteristics between their target mRNAs sequences. However, they can only homologous or limited complementary miRNAs. Furthermore, since pre-miRNAs quite different from...

Background MicroRNAs (miRNAs) are a set of short (19∼24 nt) non-coding RNAs that play significant roles as posttranscriptional regulators in animals and plants. The ab initio prediction methods show excellent performance for discovering new pre-miRNAs. While most these can distinguish real pre-miRNAs from pseudo pre-miRNAs, few predict the positions miRNAs. Among existing also miRNA positions, them designed mammalian miRNAs, including human mouse. Minority plant Accurate remains challenge,...

Identification of disease-associated miRNAs (disease miRNAs) is critical for understanding disease etiology and pathogenesis. Since exert their functions by regulating the expression target mRNAs, several methods based on genes were proposed to predict miRNA candidates. They achieved only limited success as they all suffered from high false-positive rate prediction results. Alternatively, other observation that with similar tend be associated diseases vice versa. The exploited information...

Predicting novel uses for approved drugs helps in reducing the costs of drug development and facilitates process. Most previous methods focused on multi-source data related to diseases predict candidate associations between diseases. There are multiple kinds similarities drugs, these reflect how similar two from different views, whereas most failed deeply integrate similarities. In addition, topology structures drug-disease heterogeneous networks constructed by using not fully exploited. We...

Identification of disease-associated miRNAs (disease miRNAs) are critical for understanding etiology and pathogenesis. Most previous methods focus on integrating similarities associating information contained in heterogeneous miRNA-disease networks. However, these establish only shallow prediction models that fail to capture complex relationships among miRNA similarities, disease associations. We propose a method the basis network representation learning convolutional neural networks predict...

The computational prediction of novel drug-target interactions (DTIs) may effectively speed up the process drug repositioning and reduce its costs. Most previous methods integrated multiple kinds connections about drugs targets by constructing shallow models. These failed to deeply learn low-dimension feature vectors for ignored distribution these vectors. We proposed a graph convolutional autoencoder generative adversarial network (GAN)-based method, GANDTI, predict DTIs. constructed...

Identifying novel indications for approved drugs can accelerate drug development and reduce research costs. Most previous studies used shallow models prioritizing the potential drug-related diseases failed to deeply integrate paths between which may contain additional association information. A deep-learning-based method predicting drug-disease associations by integrating useful information is needed. We proposed a based on convolutional neural network (CNN) bidirectional long short-term...

Predicting disease-related long non-coding RNAs (lncRNAs) can be used as the biomarkers for disease diagnosis and treatment. The development of effective computational prediction approaches to predict lncRNA-disease associations (LDAs) provide insights into pathogenesis complex human diseases reduce experimental costs. However, few existing methods use microRNA (miRNA) information consider relationship between inter-graph intra-graph in complex-graph assisting prediction.In this paper,...