AUTHOR=Vinje H. , Brustad H. K. , Heggli A. , Sevillano C. A. , Van Son M. , Gangsei L. E. 

TITLE=Classification of breed combinations for slaughter pigs based on genotypes—modeling DNA samples of crossbreeds as fuzzy sets from purebred founders

JOURNAL=Frontiers in Genetics

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2023.1289130

DOI=10.3389/fgene.2023.1289130

ISSN=1664-8021

ABSTRACT=In pig production, the production animals are generally three- or four-way crossbreds. Reliable information regarding the breed of origin of slaughtered pigs might be useful, even a prerequisite, for a number of purposes, e.g. evaluating potential breed effects on carcass grading. Genetic data from slaughtered pigs can easily be extracted and used for crossbreed classification.
In the current study four classification methods, Random Forest (RF), ADMIXTURE, Partial Least Squares Regression (PLSR) and Partial Least Squares - Quadratic discriminant analysis (PLS-QDA) were evaluated on simulated (n = 7500) genomic data of crossbreeds. The derivation of the theory behind PLS-QDA is a major part of the current study, whereas RF and ADMIXTURE are known and well described in literature. Classification success rate (CS), square loss (SL) and Kullback–Leibler divergence loss (KL) for the simulated data were used to compare methods. Overall, PLS-QDA performed best with $99\%/0.0018/0.002$ (CS/SL/KL) vs. $97\%/0.0084/0.051$, $97\%/0.0087/0.0623$ and $17\%/0.068/0.39$ for PLSR, ADMIXTURE and RF respectively. PLS-QDA and ADMIXTURE, as the most relevant methods, were used on a real data set (n = 1013) from Norway where the two largest classes contained 532 and 192 (PLS-QDA) and 531 and 193 (ADMIXTURE) individuals respectively. These two classes were expected to be dominating a priori. The Bayesian nature of PLS-QDA enables inclusion of desirable features like a separate class "unknown breed combination", and informative priors for crossbreeds making this a preferable method for classification of breed combination in the industry.