Machine-Learning Approaches for Classifying Haplogroup from Y Chromosome STR Data

Genetic variation on the non-recombining portion of the Y chromosome contains information about the ancestry of male lineages. Because of their low rate of mutation, single nucleotide polymorphisms (SNPs) are the markers of choice for unambiguously classifying Y chromosomes into related sets of lineages known as haplogroups, which tend to show geographic structure in many parts of the world. However, performing the large number of SNP genotyping tests needed to properly infer haplogroup status is expensive and time consuming. A novel alternative for assigning a sampled Y chromosome to a haplogroup is presented here. We show that by applying modern machine-learning algorithms we can infer with high accuracy the proper Y chromosome haplogroup of a sample by scoring a relatively small number of Y-linked short tandem repeats (STRs). Learning is based on a diverse ground-truth data set comprising pairs of SNP test results (haplogroup) and corresponding STR scores. We apply several independent machine-learning methods in tandem to learn formal classification functions. The result is an integrated high-throughput analysis system that automatically classifies large numbers of samples into haplogroups in a cost-effective and accurate manner.Author Summary: The Y chromosome is passed on from father to son as a nearly identical copy. Occasionally, small random changes occur in the Y DNA sequences that are passed forward to the next generation. There are two kinds of changes that may occur, and they both provide vital information for the study of human ancestry. Of the two kinds, one is a single letter change, and the other is a change in the number of short tandemly repeating sequences. The single-letter changes can be laborious to test, but they provide information on deep ancestry. Measuring the number of sequence repeats at multiple places in the genome simultaneously is efficient, and provides information about recent history at a modest cost. We present the novel approach of training a collection of modern machine-learning algorithms with these sequence repeats to infer the single-letter changes, thus assigning the samples to deep ancestry lineages.