Computational methods dedicated to diabetes identification through epistasis analysis: a review. (3rd November 2020)

• Record Type: Journal Article
• Authors: Manavalan, R.; Priya, S.
• Is Part Of: International journal of intelligent engineering informatics. Volume 8:Number 3(2020)
• Page Start: 239
• Page End: 261
• Publication Date: 2020-11-03
• Subjects: diabetes -- epistasis -- GWAS -- genome-wide association studies -- genes -- T2D -- genetic interactions -- SNP interactions -- computational approaches -- genetic variants; Artificial intelligence -- Engineering applications -- Periodicals; Engineering -- Computer programs -- Periodicals; Knowledge management -- Periodicals; 620.0028563
• Languages: English
• ISSNs: 1758-8715

Abstract

Diabetes is an acute metabolic disease that raises the amount of blood sugar. Diabetes increases the mortality rates day by day in the world. The genetic influences, environmental characters, and patient's unhealthy behaviours are the leading causes of diabetes. One gene masks the traits of one or more genes that are characterised as epistasis. Genome-wide association studies (GWAS) aid in identifying susceptive loci and Epistasis interactions for diabetes. Predicting the considerable number of genetic interactions responsible for diabetes with laboratory methods is cumbersome. Computational and machine learning designs are useful in analysing and identifying the Epistasis impacts of diabetes risk. This study seeks to explore various techniques of statistical, machine learning, optimisation techniques used to discover the Epistasis effect related to diabetes. It also focused on the experimental outcome of the different computational models with their challenges for detecting the sensitive Epistasis effect of diabetes.