Association of Single Nucleotide Polymorphism and Phenotypes in Type 2 Diabetes Mellitus Using Genetic Algorithm and CatBoost

Unique biological features in precision medicine derive from multiple data omics, including pharmacogenomics. Pharmacogenomic data can help the process of diagnosis and treatment of patients who have complex diseases, such as Type 2 Diabetes Mellitus (T2DM), by selecting the right drug and dosage. Single nucleotide polymorphism (SNP) data together with phenotype data can be used to improve the diagnosis of specific diseases. This study aims to determine the association between SNP and phenotype of T2DM using Genetic Algorithms and CatBoost. This association study produced 4 SNPs with an MSE value of 0.06335. These SNPs are located in their respective genes, namely ABCC8, AFF3, CAP2, and FAF1. Based on MGI information and literature studies, AFF3 and CAP2 do not have any relationship with T2DM. AFF3 is associated with T1DM disease, whereas CAP2 is associated with abnormalities in adipocytes that are at risk of causing T2DM.