Inference of population structure using multilocus genotype data: dominant markers and null alleles

Abstract

Dominant markers such as amplified fragment length polymorphisms (AFLPs) provide an economical way of surveying variation at many loci. However, the uncertainty about the underlying genotypes presents a problem for statistical analysis. Similarly, the presence of null alleles and the limitations of genotype calling in polyploids mean that many conventional analysis methods are invalid for many organisms. Here we present a simple approach for accounting for genotypic ambiguity in studies of population structure and apply it to AFLP data from whitefish. The approach is implemented in the program structure version 2.2, which is available from http://pritch.bsd.uchicago.edu/structure.html.

Fig. 1

Comparison of estimated gene frequencies p and admixture proportions q with true values, for simulated data from two closely related populations. Black points show estimates for codominant markers. Grey points show estimates where allele 1 is dominant over allele 0. p represents the frequency of allele 1.

Fig. 2

Ancestry of whitefish from Cliff Lake estimated using structure. (a) Ancestry estimates based on naïve clustering. Ancestry from the inferred dwarf and normal gene pools are shown in dark and light grey, respectively. (b) Likely ancestry of each individual, estimated using phenotypic information. White: full ancestry from observed ecotype. Light grey: one great grandparent with other ecotype. Grey: one grand parent with other ecotype. Dark grey: one parent with other ecotype. Black: both parents from other ecotype. See text for model details.