Abstract: The present disclosure provides methods, systems, and media for determining a pigmentation phenotype of a canine subject. In an aspect, the present disclosure provides a computer-implemented method for determining a pigmentation phenotype of a canine subject. The method may comprise (a) receiving genotype data for the canine subject, wherein the genotype data comprises quantitative values of each of a plurality of genetic markers, wherein the plurality of genetic markers comprises genetic variants; (b) applying a trained machine learning classifier to the genotype data to determine a predicted pigmentation phenotype based at least in part on the quantitative values of the plurality of genetic variants; and (c) identifying the canine subject as having the predicted pigmentation phenotype with an accuracy of at least about 70%.