Genotype imputation accuracy in multiple equine breeds from medium- to high-density genotypes

Genotype imputation is now a key component of genomic analyses as it increases the density of available genotypes within a population. However, many factors can influence imputation accuracy. The aim of this study was to assess and compare the accuracy of imputation of high-density genotypes (Affymetrix Axiom Equine genotyping array, 670,806 SNPs) from two moderate-density genotypes (Illumina Equine SNP50 BeadChip, 54,602 SNPs and Illumina Equine SNP70 BeadChip, 65,157 SNPs), using single-breed or multiple-breed reference sets. Genotypes were available from five groups of horse breeds: Arab (AR, 1,207 horses), Trotteur Francais (TF, 979 horses), Selle Francais (SF, 1,979 horses), Anglo-Arab (AA, 229 horses) and various foreign sport horses (FH, 209 horses). The proportions of horses genotyped with the high-density (HD) chip in each breed group were 10% in AA, 15% in AR and FH, 30% in TF and 57% in SF. A validation set consisting of one-third of the horses genotyped with the HD chip was formed and their genotypes deleted. Two imputation strategies were compared, one in which the reference population consisted only of horses from the same breed group as in the validation set, and another with horses from all breed groups. For the first strategy, concordance rates (CRs) ranged from 97.8% (AR) to 99.0% (TF) and correlations (r(2)) from 0.94 (AR) to 0.99 (TF). For the second strategy, CR ranged from 97.4% (AR) to 98.9% (TF) and r(2) from 0.93 (AR) to 0.99 (TF). Overall, the results show a small advantage of within-breed imputation compared with multi-breed imputation. Adding horses from different breed groups to the reference population does not improve the accuracy of imputation. Imputation provides an accurate means of combining data sets from different genotyping platforms, now necessary with the increasing use of the recently developed Affymetrix Axiom Equine genotyping array.