Overview of Machine Learning Methods for Genome-Wide Association Analysis

Abstract

Genome-wide association studies (GWAS) is an effective way to reveal the pathogenic genes of complex diseases by analyzing the genotype information and related disease phenotype information on the SNP loci of the whole genome of a large number of living organisms. Machine learning (ML) is a method that allows computers to simulate human cognitive processes to solve problems. The advantage of using machine learning methods to carry out genome-wide association analysis research is that it does not require false anchor points or gene-gene interaction models in advance Instead of exhaustive search, computer algorithms that simulate human cognitive processes can learn from a large amount of data to discover the ability of nonlinear high-dimensional gene-gene interactions. In recent years, a large number of machine learning methods have been used in the study of genome-wide association analysis. This article will briefly introduct these methods.