Degree-Based Similarity Indexes for Identifying Potential miRNA-Disease Associations

Yajie Meng,Junlin Xu,Xianfang Tang,Min Jin

doi:10.1109/access.2020.3006998

Abstract

Identifying disease-associated miRNAs is helpful to explore the pathogenesis of diseases. However, without foreknowledge of the experimentally valid disease-associated miRNAs information, the development of promising and affordable approaches for effective treatment of human diseases is challenging. In this study, we develop DCNMDA and DJMDA, a degree-based similarity indexes methodology for identifying potential miRNAs-disease associations. We solely focused on the similarity and the degree between nodes without adopting negative samples or other external prior information beyond the miRNA-disease associations bipartite network. Trained on HMDD v2.0 and HMDD v3.0, DCNMDA achieved the highest AUCs (0.9237 and 0.9432, respectively) based on the 5-fold cross-validation and outperformed the published state-of-the-art methodologies. Moreover, case studies about breast neoplasms, lung neoplasms, and ovarian neoplasms further evaluate the reliability of the models. As a result, biological experiments can correspondingly verify 28 out of top-30 DJMDA-predicted MDAs and 29 out of top-30 DCNMDA-predicted MDAs. In summary, DCNMDA and DJMDA offer a powerful degree-based similarity index approach for identifying potential miRNAs-disease associations with superior performance.

Highlights

A large number of miRNAs have been discovered rapidly in plants, animals, green algae, and viruses. miRNAs play vital roles in many biological processes, including cell development, proliferation, differentiation, apoptosis, signal transduction, viral infection [1]
The performances of DCNMDA and DJMDA in 5-fold cross validation (CV) are significantly better than Regularized Least Squares for MiRNADisease-Associated (RLSMDA), NCPMDA, Inductive Matrix Completion for MiRNA–Disease Association prediction (IMCMDA) and LRMCMDA
Aiming at the challenge of performance for identifying novel MDAs, in this study, we developed a novel model, named DCNMDA and DJMDA, which constructed a heterogeneous network by only known miRNA-disease associations without other further and external information and utilizing two degree-based similarity indexes including common neighbor and Jaccard to identify MDAs

Summary

Introduction

A large number of miRNAs have been discovered rapidly in plants, animals, green algae, and viruses. miRNAs play vital roles in many biological processes, including cell development, proliferation, differentiation, apoptosis, signal transduction, viral infection [1]. A large number of miRNAs have been discovered rapidly in plants, animals, green algae, and viruses. The first discovered miRNA lin-4 plays a crucial regulatory role in the development of C. elegans by regulating the expression of its target genes lin-14 and lin-28 [2]. With an in-depth understanding of the function of miRNAs, plenty of studies on human disease mechanisms have extended from genes to miRNAs. An example is that miRNAs are associated with Alzheimer’s disease [3]. MiRNA-related dysregulations are closely associated with the development and progression of various cancer [4]. Many evidence shows that almost every miRNA interacts with hundreds of targets and plays the role of ‘‘oncogene’’ or ‘‘tumor suppressor miRNAs’’ in the occurrence, metastasis, proliferation, and

Methods

Results

Conclusion