Inferring lncRNA Functional Similarity Based on Integrating Heterogeneous Network Data

摘要

Although lncRNAs lack the potential to be translated into proteins directly, their complicated and diversiform functions make them as a window into decoding the mechanisms of human physiological activities. Accumulating experiment studies have identified associations between lncRNA dysfunction and many important complex diseases. However, known experimentally confirmed lncRNA functions are still very limited. It is urgent to build effective computational models for rapid predicting of unknown lncRNA functions on a large scale. To this end, valid similarity measure between known and unknown lncRNAs plays a vital role. In this paper, a novel model was developed to calculate functional similarities between lncRNAs by integrating heterogeneous networks, in which an integrated network was constructed based on four single lncRNA functional similarity networks (miRNA-based similarity network, disease-based similarity network, GTEx expression-based networks and NONCODE expression-based network). Using the lncRNA pairs that share the target mRNA as the benchmark, the results show that this integrated network is more effective than single networks with an AUC of 0.736 in the cross validation, while the AUC of four single networks were 0.703, 0.733, 0.611 and 0.602. To implement our model, a web server named IHNLncSim was constructed for inferring lncRNA functional similarity based on integrating heterogeneous networks. Moreover, the modules of network visualization and disease-based lncRNA function enrichment analysis were added into IHNLncSim. It is anticipated that IHNLncSim could be an effective bioinformatics tool for the research of lncRNA regulation function studies. IHNLncSim is freely available at http://www.lirmed.com/ihnlncsim.