Semi-supervised prediction of human miRNA-disease association based on graph regularization framework in heterogeneous networks

MicroRNAs (miRNAs) play important roles in the various pathogenesis of diseases. However, experimental prediction of associations between microRNAs and diseases remains challenging. Furthermore, there are several critical limitations of previous computational methods in miRNA-disease network for uncovering the potential miRNA-disease associations. Some existing methods are not applicable for diseases without any known miRNA. Meanwhile, several other methods have failed to prioritize associations for all diseases simultaneously. Therefore, it is essential to develop an algorithm to solve these problems effectively, which can identify reliable disease miRNA candidates using existing miRNA-disease associations verified by biological experiment. In this study, we propose a novel semi-supervised prediction method of MiRNA-Disease Association based on Graph Regularization Framework (MDAGRF) in miRNA-disease network. Our method achieves higher average AUC and AUPR of 19 human diseases associating with at least 80 miRNAs based on five-fold cross validation. In addition, the performance of our method is not sensitive to the selections of parameters. Compared with other existing global methods, MDAGRF could obtain better prediction result for all diseases simultaneously as well. Moreover, diseases without any known miRNA could be effectively dealt by the proposed method.