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

Abstract

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.

MDHGI: Matrix Decomposition and Heterogeneous Graph Inference for miRNA-disease association prediction

“…Proposing computational models to predict disease-related miRNAs is a worthful supplement to experiments. Researchers should spare no effort to excogitate a more accurate prediction method so that reasonable candidates can be provided for future biological experiments [ 26 ].…”

A learning-based framework for miRNA-disease association identification using neural networks

“…The basic assumption is that miRNAs associated with the same or similar diseases are more likely to be functionally related [Chen et al, 2012], and the crucial technical point is similarity computation for different kinds of pairs including miRNA-miRNA, disease-disease and miRNA-disease [Zou et al, 2015]. According to information involved in similarity computation, network-based approaches can be loosely grouped into two categories [Zou et al, 2015], local network similarity methods [Kertesz et al, 2007, Lewis et al, 2003, Wei et al, 2012, Xuan et al, 2013, Han et al, 2014 and global network similarity methods [Chen et al, 2012, Chen andYan, 2014].…”

LSGSP: a novel miRNA–disease association prediction model using a Laplacian score of the graphs and space projection federated method

“…Based on the weighted-k-most-similar-neighbour method, Xuan et al 21 proposed HDMP to predict the relationship between miRNA and disease. On the basis of the method proposed be Xuan et al, Han et al 22 proposed DismiPred, which used topology information between nodes. Chen et al 23,24 designed two KNNbased disease association ranking algorithms (RKNNMDA and BLHARMDA).…”