Weighted Graph Constraint and Group Centric Non-negative Matrix Factorization for gene-phenotype association prediction

Abstract

Gene-phenotype association prediction can be applied to reveal the inherited basis of human diseases and help drug development. Gene-phenotype associations are related to complex biological process and influenced by various factors, such as relationship between phenotypes and that among genes. While due to sparseness of curated gene-phenotype associations, existing approaches are limited to prediction accuracy. In this paper, we propose a novel method by exploiting weighted graph constraint learned from hierarchical structures of phenotype data and group prior information among genes by inheriting advantages of Non-negative Matrix Factorization (NMF), called Weighted Graph Constraint and Group Centric Non-negative Matrix Factorization (GC2NMF). Specifically, firstly we introduce the depth of parent-child relationships between two adjacent phenotypes in hierarchal phenotypic data as weighted graph constraint for a better phenotype understanding. Secondly, we utilize intra-group correlation among genes in a gene group as group constraint for gene understanding. Such information provides us an intuitive priori that genes in a group probably result in similar phenotypes. The model allows not only to achieve a high prediction performance but also jointly to learn interpretable representation of genes and phenotypes to handle future biological analysis. Experimental results on biological gene-phenotype association datasets of mouse and human demonstrate that GC2NMF can obtain superior prediction accuracy and good understandability for biological explanation over other state-of-the-art methods.