Predicting miRNA-disease associations using a hybrid feature representation in the heterogeneous network

摘要

MicroRNAs(miRNAs) are a kind of small single-stranded endogenous non-coding RNAs with a length about 22 nucleotides, which play an important role in regulating the gene expression during the post-transcriptional level [1, 2]. Many studies have shown that the dysregulation of miRNAs is involved in multiple human diseases like cancers [3], cardiovascular diseases [4] and Alzheimer’s diseases [5] etc., and the prediction of miRNAs-diseases associations is crucial to understand the diseases pathogenesis [6]. Furthermore, George Adrian, et al. found that the miR15 and miR16 are deleted in a lot B cell chronic lymphocytic leukemias (B-CLL) [7], T. Sredni et al. demonstrated that miR-129 and miR-25 express abnormally in all pediatric brain tumor types [8]. Besides, Jun Lu et al. successfully classified poorly differentiated tumours using miRNA expression profiles [9], which demonstrated the potential of miRNAs as biomarkers. Therefore, Predicting miRNA-disease associations is very meaningful. However, a lot of miRNA-disease associations remain unknown and experimental approaches for predicting the associations are time-consuming and expensive. Therefore, a lot computational methods have been developed to predict the miRNA-disease associations.