Considering the extensive data sets and statistical techniques, animal breeding embodies a branch of machine learning that has a constantly increasing impact on breeding. In our study, information regarding the potential of machine learning and data mining within a large set of horses and breeds is presented. The individual assignment methods and factors influencing the success rate of the procedure are compared at the Czech population scale. The fixation index values ranged from 0.057 (HMS1) to 0.144 (HTG6), and the overall genetic differentiation amounted to 8.9% among the breeds. The highest genetic divergence (FST = 0.378) was established between the Friesian and Equus przewalskii; the highest degree of gene migration was obtained between the Czech and Bavarian Warmblood (Nm = 14,302); and the overall global heterozygote deficit across the populations was 10.4%. The eight standard methods (Bayesian, frequency, and distance) using GeneClass software and almost all mainstream classification algorithms (Bayes Net, Naive Bayes, IB1, IB5, KStar, JRip, J48, Random Forest, Random Tree, PART, MLP, and SVM) from the WEKA machine learning workbench were compared by utilizing 314,874 real allelic data sets. The Bayesian method (GeneClass, 89.9%) and Bayesian network algorithm (WEKA, 84.8%) outperformed the other techniques. The breed genomic prediction accuracy reached the highest value in the cold-blooded horses. The overall proportion of individuals correctly assigned to a population depended mainly on the breed number and genetic divergence. These statistical tools could be used to assess breed traceability systems, and they exhibit the potential to assist managers in decision-making as regards breeding and registration.

Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Technická 3082 12 616 00 Brno Czech Republic

Laboratory of Agrogenomics Department of Morphology Physiology and Animal Genetics Faculty of Agronomy Mendel University in Brno Zemědělská 1665 1 613 00 Brno Czech Republic

See more in PubMed

Genetics. 1999 Dec;153(4):1989-2000 PubMed

Anim Genet. 2002 Aug;33(4):264-70 PubMed

Anim Genet. 2003 Aug;34(4):297-301 PubMed

J Hered. 2004 Nov-Dec;95(6):536-9 PubMed

Bioinformatics. 2005 May 1;21(9):2128-9 PubMed

Mol Ecol. 2006 Oct;15(11):3157-73 PubMed

Mol Ecol. 2007 Mar;16(5):1099-106 PubMed

Mol Ecol Resour. 2008 Jan;8(1):103-6 PubMed

Anim Genet. 2011 Dec;42(6):627-33 PubMed

Meat Sci. 2008 Oct;80(2):389-95 PubMed

BMC Genet. 2013 Dec 09;14:118 PubMed

Anim Genet. 2014 Dec;45(6):898-902 PubMed

J Anim Breed Genet. 2017 Apr;134(2):85-86 PubMed

Evolution. 1984 Nov;38(6):1358-1370 PubMed

J Anim Breed Genet. 2018 Feb;135(1):73-83 PubMed

Proc Natl Acad Sci U S A. 1973 Dec;70(12):3321-3 PubMed

Am J Hum Genet. 1967 May;19(3 Pt 1):233-57 PubMed

J Mol Evol. 1983;19(2):153-70 PubMed

Proc Natl Acad Sci U S A. 1995 Jul 18;92(15):6723-7 PubMed

Mol Ecol. 1995 Jun;4(3):347-54 PubMed

Proc Natl Acad Sci U S A. 1997 Aug 19;94(17):9197-201 PubMed

Anim Genet. 1997 Dec;28(6):397-400 PubMed