Predicting the Influence of MicroRNAs on Drug Therapeutic Effects by Random Walking

Abstract

The emergence of drug resistance is one of the main reasons for the failure of disease treatment. More and more studies have shown that miRNAs are associated with the resistance or sensitivity of certain therapeutic drugs by regulating target genes. However, only a few associations have been reported between miRNAs and drug resistance or sensitivity. In this study, we first constructed a heterogeneous network by integrating the miRNA similarity network, drug similarity network and miRNA-drug effect associations network. Subsequently, we predicted the potential miRNA-drug effect associations by the Bi-Random walk (BiRW) algorithm. The cross-validation and De novo validation methods were applied to verify the prediction performance. Results show that the proposed method can effectively predict potential miRNA-drug effect associations. This study will enhance our understanding of the important roles of miRNAs in drug therapeutic effects and provide a valuable resource for designing effective therapeutic strategies.