An efficient methodology for discovering both of gene-environment interactions and gene-gene interactions causing genetic diseases

Abstract

Genetic diseases are one of the most critical diseases facing human societies, their risk lies in the transmission of genetic characteristics from one generation to another, where the imbalance of these characteristics leads to an unhealthy offspring, which negatively affects the effort of this offspring and its services to society. Genetic disease is caused by a mutation in the Deoxyribonucleic Acid (DNA), these genetic mutations are generated by nonlinear interactions between two or more genes and / or environmental exposures. The aim of this paper is to discover both of gene-environment interactions and gene-gene interactions causing a genetic disease, the proposed methodology is based on both of the filter and wrapper feature selection methods, it uses the filter method using a Relief algorithm to detect the gene-environment interactions, wrapper method using genetic algorithm to discover gene-gene interactions, and classification decision tree algorithm to generate the conditional rules of gene-gene interactions. It has been evaluated using many different classifier models on four benchmark databases, and compared its performance with an Apriori algorithm for generating rules of gene-gene interactions, the proposed methodology achieved the highest performance and better classification accuracy on all databases containing patients affected by gene-environment interactions or gene-gene interactions or both of gene-environment and gene-gene interactions.