A Novel Approach Based on a Weighted Interactive Network to Predict Associations of MiRNAs and Diseases.

Haochen Zhao,Linai Kuang,Quan Zou,Xiang Fen,Lei Wang

doi:10.3390/ijms20010110

Abstract

Accumulating evidence progressively indicated that microRNAs (miRNAs) play a significant role in the pathogenesis of diseases through many experimental studies; therefore, developing powerful computational models to identify potential human miRNA–disease associations is vital for an understanding of the disease etiology and pathogenesis. In this paper, a weighted interactive network was firstly constructed by combining known miRNA–disease associations, as well as the integrated similarity between diseases and the integrated similarity between miRNAs. Then, a new computational method implementing the newly weighted interactive network was developed for discovering potential miRNA–disease associations (WINMDA) by integrating the T most similar neighbors and the shortest path algorithm. Simulation results show that WINMDA can achieve reliable area under the receiver operating characteristics (ROC) curve (AUC) results of 0.9183 ± 0.0007 in 5-fold cross-validation, 0.9200 ± 0.0004 in 10-fold cross-validation, 0.9243 in global leave-one-out cross-validation (LOOCV), and 0.8856 in local LOOCV. Furthermore, case studies of colon neoplasms, gastric neoplasms, and prostate neoplasms based on the Human microRNA Disease Database (HMDD) database were implemented, for which 94% (colon neoplasms), 96% (gastric neoplasms), and 96% (prostate neoplasms) of the top 50 predicting miRNAs were confirmed by recent experimental reports, which also demonstrates that WINMDA can effectively uncover potential miRNA–disease associations.

Highlights

Increasing studies indicated that non-coding RNAs play an extensive and important role in many biological processes such as cell differentiation, ontogenesis, and disease development [1,2,3]
94%, 96%, and 96% of the top 50 predicting miRNAs were confirmed by dbDEMC [16], miR2Disease [18], and recently published experimental studies. These results demonstrate that was developed for discovering potential miRNA–disease associations (WINMDA) can effectively predict potential miRNA–disease associations
We evaluated the predictive performance of WINMDA through the following experiments: we firstly compared WINMDA with four state-of-the-art methods, namely BNPMDA [34], PBMDA [29], within and between Score for miRNA–disease association (WBSMDA) [27], and regularized least squares for miRNA–disease association (RLSMDA) [26] in the framework of leave-one-out cross-validation (LOOCV)

Summary

Introduction

Increasing studies indicated that non-coding RNAs (ncRNAs) play an extensive and important role in many biological processes such as cell differentiation, ontogenesis, and disease development [1,2,3]. Various miRNA-related heterogeneous biological databases were established and were extended to various fields of miRNA-related research, such as miRBase [15], Database of Differentially Expressed miRNAs in Human Cancers (dbDEMC) [16], Human microRNA Disease Database (HMDD) [17], miR2Disease [18], etc Based on these datasets, different computational prediction methods were developed to predict potential miRNA–disease associations [19,20,21,22,23,24]. In 2018, Chen et al developed a novel computational model named MDHGI to predict potential miRNA–disease associations using a sparse learning method to decompose the original adjacency matrix and combing the miRNA functional similarities network, the disease semantic similarities network, the Gaussian interaction profile kernel similarities network, and the new adjacency matrix into a heterogeneous graph [31]. Chen et al proposed a rating-integrated bipartite network recommendation-based prediction method named BNPMDA for predicting potential miRNA–disease association using agglomerative hierarchical clustering [34]

Methods

Results

Discussion

Conclusion