Research Article

Prediction of disease-related microRNAs by incorporating functional similarity and common association information

Published: March 24, 2014
Genet. Mol. Res. 13 (1) : 2009-2019 DOI: 10.4238/2014.March.24.5

Abstract

The identification of human disease-related microRNAs (miRNAs) is important for understanding the pathogenesis of diseases, but to do this experimentally is a costly and time-consuming process. Computational prediction of disease-related miRNA candidates is a valuable complement to experimental studies. It is essential to develop an effective prediction method to provide reliable candidates for subsequent biological experiments. In this study, we constructed a miRNA functional similarity network based on calculation of the functional similarity between each pair of miRNAs. Here, we present a new method (DismiPred) for predicting disease-related miRNA candidates based on the network. This method incorporates functional similarity and common association information to achieve an efficient prediction performance. DismiPred has been successfully shown to recover experimentally validated disease-related miRNAs for 12 common human diseases, with an F-measure ranging from 69.49 to 91.69%. Furthermore, a case study examining breast neoplasms showed that DismiPred could uncover novel disease-related miRNAs. DismiPred is useful for further experimental studies on the involvement of miRNAs in the pathogenesis of diseases.

The identification of human disease-related microRNAs (miRNAs) is important for understanding the pathogenesis of diseases, but to do this experimentally is a costly and time-consuming process. Computational prediction of disease-related miRNA candidates is a valuable complement to experimental studies. It is essential to develop an effective prediction method to provide reliable candidates for subsequent biological experiments. In this study, we constructed a miRNA functional similarity network based on calculation of the functional similarity between each pair of miRNAs. Here, we present a new method (DismiPred) for predicting disease-related miRNA candidates based on the network. This method incorporates functional similarity and common association information to achieve an efficient prediction performance. DismiPred has been successfully shown to recover experimentally validated disease-related miRNAs for 12 common human diseases, with an F-measure ranging from 69.49 to 91.69%. Furthermore, a case study examining breast neoplasms showed that DismiPred could uncover novel disease-related miRNAs. DismiPred is useful for further experimental studies on the involvement of miRNAs in the pathogenesis of diseases.