Classifying genealogical origins in hybrid populations using dominant markers

In hybrid studies, potential for error is high when classifying genealogical origins of individuals (e.g., parental, F1, F2) based on their genotypic arrays. For codominant markers, previous researchers have considered the probability of misclassification by genotypic inspection and proposed alternative maximum-likelihood approaches to estimating genealogical class frequencies. Recently developed dominant marker systems may significantly increase the number of diagnostic loci available for hybrid studies. I examine probabilities of classification error based on the number of dominant loci. As in earlier studies, I assume that only parental and first- and second-generation hybrid crosses between two taxa potentially exist. Thirteen loci with dominant expression from each parental taxon (i.e., 26 total loci) are needed to reduce classification error below 5% for F2 individuals, compared to 13 codominant loci for the same error rate. Use of loci on similar numbers from both taxa most efficiently increases power to characterize all genealogical classes. In contrast, classification of backcrosses to one parental taxon is wholly dependent on loci from the other taxon. Use of dominant diagnostic markers may increase the power and expand the use of maximum-likelihood methods for evaluating hybrid mixtures.