Graph embedding and ensemble learning for predicting gene-disease associations

Abstract

The discovery of gene-disease associations is important for preventing, diagnosing, and treating diseases. In this paper, we propose two heterogeneous network-based methods that enhance gene-disease association prediction by using graph embedding and ensemble learning, abbreviated as 'HNEEM' and 'HNEEM-PLUS'. We integrate gene-disease associations, gene-chemical associations, gene-gene associations and disease-chemical associations to construct a heterogeneous network, and adopt six graph embedding methods respectively to learn the representative vectors of genes and diseases from the network. We build individual prediction models using each graph embedding representation and random forest, and then combine them by average scoring to construct the ensemble model HNEEM. To increase the diversity of base predictors, we further introduce the multilayer perceptron as an additional classifier and generate more base predictors, and thus propose an extended method named 'HNEEM-PLUS'. Computational experiments show that HNEEM has better results than individual methods and HNEEM-PLUS makes more improvement than HNEEM.