A Novel Computational Model for Predicting microRNA-Disease Associations Based on Heterogeneous Graph Convolutional Networks.

Li Li,Liu Liu,Que Que,Hu Hu,Yao Yao

doi:10.3390/cells8090977

Li Li, Liu Liu + Show 3 more

Open Access

https://doi.org/10.3390/cells8090977

Copy DOI

Journal: Cells	Publication Date: Aug 26, 2019
Citations: 61	License type: CC BY 4.0

Affiliation: University of the Cordilleras, Xiamen University

Abstract

Identifying the interactions between disease and microRNA (miRNA) can accelerate drugs development, individualized diagnosis, and treatment for various human diseases. However, experimental methods are time-consuming and costly. So computational approaches to predict latent miRNA–disease interactions are eliciting increased attention. But most previous studies have mainly focused on designing complicated similarity-based methods to predict latent interactions between miRNAs and diseases. In this study, we propose a novel computational model, termed heterogeneous graph convolutional network for miRNA–disease associations (HGCNMDA), which is based on known human protein–protein interaction (PPI) and integrates four biological networks: miRNA–disease, miRNA–gene, disease–gene, and PPI network. HGCNMDA achieved reliable performance using leave-one-out cross-validation (LOOCV). HGCNMDA is then compared to three state-of-the-art algorithms based on five-fold cross-validation. HGCNMDA achieves an AUC of 0.9626 and an average precision of 0.9660, respectively, which is ahead of other competitive algorithms. We further analyze the top-10 unknown interactions between miRNA and disease. In summary, HGCNMDA is a useful computational model for predicting miRNA–disease interactions.

Highlights

MicroRNAs are small, non-coding RNAs that play an important role in inhibiting the expression of target mRNAs at the post-transcriptional level with vital molecular functions and participate in almost all important life processes
In this paper, taking no account of similarity, we propose the heterogeneous graph convolutional networks for miRNA–disease associations prediction (HGCNMDA) model based on the known protein–protein interactions (PPI) to integrate four biological networks: miRNA–disease, miRNA–gene, disease–gene, and the human PPI
We proposed a novel model to forecast miRNA–disease interactions in heterogeneous networks, namely miRNAs–disease networks, diseases networks, miRNAs networks and PPI networks

Summary

Introduction

MicroRNAs (miRNAs) are small, non-coding RNAs that play an important role in inhibiting the expression of target mRNAs at the post-transcriptional level with vital molecular functions and participate in almost all important life processes. MiRNAs regulate target genes and result in cleavage or translation inhibition in target mRNAs [1,2,3]. An increasing number of empirical evidence shows that it is important for disease development and progression and that miRNAs may be positive regulators at post-transcriptional level [5,6]. MiRNAs clearly have a critical impact on human diseases. Predicting the interactions between diseases and miRNAs is a vital problem [7]. Predicting diseases and miRNAs accelerates the identification of real disease-associated miRNAs. Recent human protein–protein interactions (PPI) network modeling suggests that network-based approaches offer possibilities to identify miRNA–disease interactions

Objectives

Methods

Results

Conclusion