398. Combination of SNP markers for discrimination of a target chicken population using machine learning algorithms

Abstract

Identifying target populations using genetic information is a necessary aspect for the conservation of pure breed and discrimination of chickens in the market scenario. In this study, the optimal combination of single nucleotide polymorphism (SNP) markers for discriminating the target chicken breed (the Yeonsan Ogye breed) was presented using high-density SNP chip data. SNP markers specific to the target population were discovered through case-control genome-wide association study (GWAS) and filtered out based on the linkage disequilibrium blocks, and optimal SNP markers were selected by applying a machine learning algorithm. Through the machine learning approach, the identification power of the 38 optimal SNP marker combination for the specific chicken population was confirmed, and the marker combination demonstrated complete accuracies. Hence, the GWAS and machine learning models used in this study can be efficiently utilized to find out the optimal combination of markers that can discriminate target populations using multiple SNP markers.