Predicting Disease-gene Associations through Self-supervised Mutual Infomax Graph Convolution Network

Abstract

Illuminating associations between diseases and genes can help reveal the pathogenesis of syndromes and contributes to treatments, but a large number of associations still remained unexplored. To identify novel disease-gene association, many computational methods have been developed using disease and gene related prior knowledge. However, these methods remain of relatively inferior performance due to the limited external data sources and the inevitable noise among the prior knowledge. In this study, we have developed a new method, Self-Supervised Mutual Infomax Graph Convolution Network (MiGCN), to predict disease-gene associations under the guidance of external disease-disease and gene-gene collaborative graphs. The noises within the collaborative graphs were eliminated by maximizing the mutual information between nodes and neighbors through a graphical mutual infomax layer. In parallel, the node interactions were strengthened by a novel informative message passing layer to improve the learning ability of graph neural network. The extensive experiments showed that our model achieves performance improvement over the state-of-art method by more than 8% on AUC. The datasets, source codes and trained models of MiGCN are available at https://github.com/biomed-AI/MiGCN.