Machine learning approaches to genome-wide association studies

Genome-wide Association Studies (GWAS) are conducted to identify single nucleotide polymorphisms (variants) associated with a phenotype within specific population. These variants diseases have complex molecular aetiology which they cause the disease phenotype. The genotyping data generated from subjects of study is high dimensionality, challenge. problem that dataset has large number features and relatively smaller sample size. However, statistical testing standard approach being applied these influence interest. wide applications abilities Machine Learning (ML) algorithms promise understand effects better. aim this work discuss future trends ML in GWAS towards understanding population genetic variant. It was discovered such as classification, regression, ensemble, neural networks been for further discussed comprehensively including their application areas. identification significant (SNP), risk assessment & prediction, detection epistatic non-linear interaction, integrated other omics sets. This comprehensive review highlighted areas sheds light on innovating machine learning into computational pipeline genome-wide association studies. will be beneficial better how affected by biology same can developing particular favourable natural selection.