Semi-Supervised Machine Learning Method for Predicting Homogeneous Ancestry Groups To Assess Hardy-Weinberg Equilibrium in Diverse Whole-Genome Sequencing Studies

Authors

Derek Shyr
Rounak Dey
Xihao Li
Hufeng Zhou
Eric Boerwinkle
Steve Buyske
Mark Daly
Richard A Gibbs
Ira Hall
Tara Matise
Catherine Reeves
Nathan O Stitziel
Michael Zody
Benjamin M Neale
Xihong Lin

Language

English

Publication Date

10-3-2024

Journal

American Journal of Human Genetics

DOI

10.1016/j.ajhg.2024.08.018

PMID

39270648

PMCID

PMC11480788

PubMedCentral® Posted Date

9-12-2024

PubMedCentral® Full Text Version

Post-print

Abstract

Large-scale, multi-ethnic whole-genome sequencing (WGS) studies, such as the National Human Genome Research Institute Genome Sequencing Program's Centers for Common Disease Genomics (CCDG), play an important role in increasing diversity for genetic research. Before performing association analyses, assessing Hardy-Weinberg equilibrium (HWE) is a crucial step in quality control procedures to remove low quality variants and ensure valid downstream analyses. Diverse WGS studies contain ancestrally heterogeneous samples; however, commonly used HWE methods assume that the samples are homogeneous. Therefore, directly applying these to the whole dataset can yield statistically invalid results. To account for this heterogeneity, HWE can be tested on subsets of samples that have genetically homogeneous ancestries and the results aggregated at each variant. To facilitate valid HWE subset testing, we developed a semi-supervised learning approach that predicts homogeneous ancestries based on the genotype. This method provides a convenient tool for estimating HWE in the presence of population structure and missing self-reported race and ethnicities in diverse WGS studies. In addition, assessing HWE within the homogeneous ancestries provides reliable HWE estimates that will directly benefit downstream analyses, including association analyses in WGS studies. We applied our proposed method on the CCDG dataset, predicting homogeneous genetic ancestry groups for 60,545 multi-ethnic WGS samples to assess HWE within each group.

Keywords

Humans, Whole Genome Sequencing, Supervised Machine Learning, Genome, Human, Genetics, Population, Ethnicity, Genome-Wide Association Study, Polymorphism, Single Nucleotide, Genotype

Published Open-Access

yes

Recommended Citation

Shyr, Derek; Dey, Rounak; Li, Xihao; et al., "Semi-Supervised Machine Learning Method for Predicting Homogeneous Ancestry Groups To Assess Hardy-Weinberg Equilibrium in Diverse Whole-Genome Sequencing Studies" (2024). Faculty, Staff and Student Publications. 1072.
https://digitalcommons.library.tmc.edu/uthsph_docs/1072