Single nucleotide polymorphism marker combinations for classifying Yeonsan Ogye chicken using a machine learning approach

Genetic analysis has great potential as a tool to differentiate between different species and breeds of livestock. In this study, the optimal combinations of single nucleotide polymorphism (SNP) markers for discriminating the Yeonsan Ogye chicken (Gallus gallus domesticus) breed were identified using high-density 600K SNP array data. In 3,904 individuals from 198 chicken breeds, SNP markers specific to the target population were discovered through a case-control genome-wide association study (GWAS) and filtered out based on the linkage disequilibrium blocks. Significant SNP markers were selected by feature selection applying two machine learning algorithms: Random Forest (RF) and AdaBoost (AB). Using a machine learning approach, the 38 (RF) and 43 (AB) optimal SNP marker combinations for the Yeonsan Ogye chicken population demonstrated 100% accuracy. Hence, the GWAS and machine learning models used in this study can be efficiently utilized to identify the optimal combination of markers for discriminating target populations using multiple SNP markers.

Discrimination of the commercial Korean native chicken population using microsatellite markers

Background

Korean native chicken (KNC) is a well-known breed due to its superior meat taste. This breed, however, owing to a low growth rate, has a high market price. In order to overcome this disadvantage, the National Institute of Animal Science (NIAS) in Korea developed a commercial KNC breed, named Woorimatdag version 2 (WM2), an upgraded version of the Woorimatdag (WM1) breed and the WM2 was created by crossing the KNC with meat type breeds. This study aims to discriminate between WM2 and other chicken breeds using microsatellite (MS) markers.

Methods

A total of 302 individuals from eight Korean chicken populations were examined. The genetic diversity and population structure analysis were investigated using Cervus, API-CALC, STRUCTURE, PowerMarker programs.

Results

Based on heterozygosity and polymorphic information content (PIC) values, 30 MS markers were initially selected from 150 markers. The identified average number of alleles (Na), expected heterozygosity, and PIC values for the WM2 samples were 7.17, 0.741, and 0.682, respectively. Additionally, the paternity of individuals was assigned with a success rate of greater than 99% using 12 markers, the best minimum number of markers. The 12 selected markers contained heterozygosity and PIC values above 0.7 and probability of identity values around zero. Using these markers, the determined probability of identity (PI), PI_half-sibs, and PI_sibs values were 3.23E-33, 5.03E-22, and 8.61E-08, respectively.

Conclusions

WM2 is well differentiated with respect to other chicken breeds based on estimated genetic distances. The results presented here will contribute to the identification of commercial WM2 chicken in the market.

Electronic supplementary material

The online version of this article (doi:10.1186/s40781-015-0044-6) contains supplementary material, which is available to authorized users.