Graph Embedding Based Novel Gene Discovery Associated With Diabetes Mellitus

Abstract

Diabetes mellitus is a group of complex metabolic disorders which has affected hundreds of millions of patients world-widely. The underlying pathogenesis of various types of diabetes is still unclear, which hinders the way of developing more efficient therapies. Although many genes have been found associated with diabetes mellitus, more novel genes are still needed to be discovered towards a complete picture of the underlying mechanism. With the development of complex molecular networks, network-based disease-gene prediction methods have been widely proposed. However, most existing methods are based on the hypothesis of guilt-by-association and often handcraft node features based on local topological structures. Advances in graph embedding techniques have enabled automatically global feature extraction from molecular networks. Inspired by the successful applications of cutting-edge graph embedding methods on complex diseases, we proposed a computational framework to investigate novel genes associated with diabetes mellitus. There are three main steps in the framework: network feature extraction based on graph embedding methods; feature denoising and regeneration using stacked autoencoder; and disease-gene prediction based on machine learning classifiers. We compared the performance by using different graph embedding methods and machine learning classifiers and designed the best workflow for predicting genes associated with diabetes mellitus. Functional enrichment analysis based on Human Phenotype Ontology (HPO), KEGG, and GO biological process and publication search further evaluated the predicted novel genes.

Speos: An ensemble graph representation learning framework to predict core genes for complex diseases

“…the prior class distribution [86][87][88][89][90][91] , is unknown and most classifiers require labels for training. Motivated by the robustness and the performance of ensemble approaches such as bagging in PU learning 39,86,87 , we develop a statistical approach to separate candidate genes from non-candidate genes using an ensemble approach 87,88,92 which eliminates the need to predefine 39 or estimate 88 a prior class distribution or to choose an arbitrary cut-off 40,42 on predicted rank distributions. At the heart of Speos is the cross validation ensemble consisting of m outer folds, each containing n models.…”

“…With the uptake of graph representation learning in biomedicine 27 , novel options exist to process networks alongside the input features in a joint ML model, thus approaching an in silico representation of biological regulation. First implementations based on random-walks [28][29][30][31][32][33][34][35][36][37] or graph neural networks (GNN) [38][39][40][41][42][43] show promise in predicting 'disease genes', but are often disease specific, depend on hard-coded and partially biased input data, and do not further explore the properties of predicted (core) genes (Extended Data Fig. 2).…”