Identification of Target Chicken Populations by Machine Learning Models Using the Minimum Number of SNPs

A marker combination capable of classifying a specific chicken population could improve commercial value by increasing consumer confidence with respect to the origin of the population. This would facilitate the protection of native genetic resources in the market of each country. In this study, a total of 283 samples from 20 lines, which consisted of Korean native chickens, commercial native chickens, and commercial broilers with a layer population, were analyzed to determine the optimal marker combination comprising the minimum number of markers, using a 600 k high-density single nucleotide polymorphism (SNP) array. Machine learning algorithms, a genome-wide association study (GWAS), linkage disequilibrium (LD) analysis, and principal component analysis (PCA) were used to distinguish a target (case) group for comparison with control chicken groups. In the processing of marker selection, a total of 47,303 SNPs were used for classifying chicken populations: 96 LD-pruned SNPs (50 SNPs per LD block) served as the best marker combination for target chicken classification. Moreover, 36, 44, and 8 SNPs were selected as the minimum numbers of markers by the AdaBoost (AB), Random Forest (RF), and Decision Tree (DT) machine learning classification models, which had accuracy rates of 99.6%, 98.0%, and 97.9%, respectively. The selected marker combinations increased the genetic distance and fixation index (Fst) values between the case and control groups, and they reduced the number of genetic components required, confirming that efficient classification of the groups was possible by using a small number of marker sets. In a verification study including additional chicken breeds and samples (12 lines and 182 samples), the accuracy did not significantly change, and the target chicken group could be clearly distinguished from the other populations. The GWAS, PCA, and machine learning algorithms used in this study can be applied efficiently, to determine the optimal marker combination with the minimum number of markers that can distinguish the target population among a large number of SNP markers.