Scoring disease-microRNA associations by integrating disease hierarchy into graph convolutional networks. (September 2020)

• Record Type: Journal Article
• Authors: Pan, Xiaoyong; Shen, Hong-Bin
• Is Part Of: Pattern recognition. Volume 105(2020:Sep.)
• Publication Date: 2020-09
• Subjects: microRNAs -- Protein coding genes -- Interaction network -- Graph convolutional network -- Disease hierarchy; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107385
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Inferring disease-associated miRNAs using graph convolutional network under an interaction network. The newly presented method is superior to state-of-the-art methods for predicting unseen diseasemiRNA associations. Ablation analysis demonstrates that introducing disease hierarchy into model training improves prediction performance. Case studies on three diseases shows our proposed methods can identify verified associated miRNAs. Abstract: In this study, we present an updated predictor DimiG 2.0, which uses a semi-supervised multi-label graph convolutional network (GCN) to infer disease-associated microRNAs (miRNAs) on an interaction network between protein coding genes (PCGs) and miRNAs using disease-PCG associations. DimiG 2.0 benefits from integrating the hierarchy of diseases into the GCN. DimiG 2.0 has the following updates: 1) It incorporates the hierarchy of diseases to regularize the GCN, encouraging diseases in the hierarchy to share similar miRNAs. 2) It integrates the PCGs with interacting partners but without associated diseases into model training, these unlabeled PCGs increase the size of the constructed interaction network. 3) It is able to predict associated miRNAs for 1017 diseases (updated from 248). 4) It updates expression data across tissues from the latest GTEx v7, and the expression values are quantified in Transcripts Per Million (TPM). Our results show that DimiG 2.0 outperforms state-of-the-art semi-supervised and supervised methods on the constructed benchmarked sets.