Research On Prediction Of MiRNA-disease Association Based On Bipartite Network Projection

Recently,increasing number of biological experiments have indicated that micro RNAs(miRNAs)play critical role in exploring the pathogenesis of various human diseases,and the excavation of related miRNA have a significant meaning for the treatment of diseases.Since traditional experimental methods for miRNA-disease associations detection are costly and time-consuming,it is difficult to conduct large number of experiments in short period of time.Thus,scientists started to use computers to develop efficient and robust computational techniques for undiscovered associations identification,providing valuable results for biological experiments in a much lower cost of time and money.For now,methods for miRNA-disease association prediction can be summarized into two categories,complex network based methods and machine learning based methods.Complex network based methods identify potential miRNA-disease pairs by extracting information from the known miRNA-disease association network;machine learning methods employ machine learning algorithm to infer novel miRNA-disease associations,the prediction result is given by constructing supervised or semi-supervised classifiers based on known data sets,but a high-confidence negative sample set is required,and the problem of feature extraction needs to be solved.These methods utilize the known miRNA-disease association information to construct a biological network to identify associations with higher potential,providing scientists candidate miRNA-disease associations based on the result of the prediction.In this paper,based on the bipartite network recommendation algorithm from complex network methods,we proposed a computational framework named weighted bipartite network projection for miRNA-disease association prediction(WBNPMD).In this method,transfer weights were constructed by combining the known miRNA and disease similarities,and the initial information of every node was properly configured.Then the two-step bipartite network algorithm was implemented to infer potential miRNA-disease associations.The proposed WBNPMD was applied to the known miRNA-disease association data,and leave-one-out cross validation(LOOCV)and five-fold cross validation were implemented to evaluate the performance of WBNPMD.AS a result,our method achieved the AUCs of 0.9321 and 0.9173±0.0005 in LOOCV and five-fold cross validation,and outperformed other four state-of-the-art methods.We also carried out two kinds of case studies on prostate neoplasm,colorectal neoplasm,and lung neoplasm,and most of the top 50 predicted miRNAs were confirmed to have an association with the corresponding diseases based on db DEMC,miR2 Disease,and HMDD v3.0 databases.The experimental results demonstrate that WBNPMD can accurately infer potential miRNA-disease associations.We anticipated that the proposed WBNPMD could serve as a powerful tool for miRNA-disease associations prediction.