Unsupervised Clustering Enables Cohort-Specific Variant Recalibration in Crops
- 1University of Western Australia
Abstract
Genomic selection (GS) and trait discovery in crops require reliable marker datasets, yet variant discovery remains constrained by the lack of standardised, high-confidence reference resources. Publicly available plant genomic resources are often based on outdated reference genomes, heterogenous pipelines, and generic variant hard-filtering thresholds derived from human studies. Consequently, implementation of the Genome Analysis Toolkit (GATK) Best Practices framework, including machine learning-based variant quality score recalibration (VQSR), remains challenging in crop genomes. Here, we present a crop-adapted framework for unsupervised variant quality assessment and VQSR enabling advanced SNP and insertion-deletion (INDEL) discovery without predefined high-confidence reference variant sets. Using Brassica napus as a model, we use the Illumina 60k Brassica SNP array to generate a reference-specific truth set for data pre-processing and independent evaluation of an unsupervised machine-learning approach for constructing cohort-specific VQSR resources. Gaussian mixture model (GMM)-based clustering of multidimensional variant annotation profiles identifies high-, intermediate-, and low-quality variant classes, providing flexible training resources for VQSR without requiring labelled training data. We further validate the framework in diploid Brassica oleracea and hexaploid wheat (Triticum aestivum) across cohorts differing in population size, genetic diversity, and genome architecture. Despite population- and species-specific differences in variant annotation profiles, GMM-based clustering consistently identifies informative variant quality classes and enables cohort-specific recalibration of both SNPs and INDELs. Our results demonstrate that unsupervised machine learning can extend GATK Best Practices to crop species lacking comprehensive genomic resources, providing a scalable approach for generating high-quality variant datasets for crop genomics and downstream breeding applications.
Related
- Kidzoi Enables Cell-Type-Specific Regulatory Activity and Variant Effect Prediction in Kidney
- Somatic haplotype reconstruction and variant recalibration from tumor-only long-read sequencing
- Concurrent Supervised-Unsupervised Representative Subspace Clustering (CSU-RSC)
- Gene loss is measurable, relaxed selection on the genes that remain is not: a retraction and recalibration of branch-specific selection tests in ectomycorrhizal fungi
- Decoding candidemia in critically ill patients: unsupervised clustering identifies three unique phenotypes
BibTeX
@misc{bergmann2026unsupervised,
title = {{Unsupervised Clustering Enables Cohort-Specific Variant Recalibration in Crops}},
author = {T. Bergmann and T. R. MacNish and J. Batley and D. Edwards},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.07.757277},
url = {https://www.biorxiv.org/content/10.64898/2026.10.07.757277v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Unsupervised Clustering Enables Cohort-Specific Variant Recalibration in Crops
AU - T. Bergmann
AU - T. R. MacNish
AU - J. Batley
AU - D. Edwards
PY - 2026
DA - 2026/10/07
PB - bioRxiv
DO - 10.64898/2026.10.07.757277
UR - https://www.biorxiv.org/content/10.64898/2026.10.07.757277v1
AB - Genomic selection (GS) and trait discovery in crops require reliable marker datasets, yet variant discovery remains constrained by the lack of standardised, high-confidence reference resources. Publicly available plant genomic resources are often based on outdated reference genomes, heterogenous pipelines, and generic variant hard-filtering thresholds derived from human studies. Consequently, implementation of the Genome Analysis Toolkit (GATK) Best Practices framework, including machine learning-based variant quality score recalibration (VQSR), remains challenging in crop genomes. Here, we present a crop-adapted framework for unsupervised variant quality assessment and VQSR enabling advanced SNP and insertion-deletion (INDEL) discovery without predefined high-confidence reference variant sets. Using Brassica napus as a model, we use the Illumina 60k Brassica SNP array to generate a reference-specific truth set for data pre-processing and independent evaluation of an unsupervised machine-learning approach for constructing cohort-specific VQSR resources. Gaussian mixture model (GMM)-based clustering of multidimensional variant annotation profiles identifies high-, intermediate-, and low-quality variant classes, providing flexible training resources for VQSR without requiring labelled training data. We further validate the framework in diploid Brassica oleracea and hexaploid wheat (Triticum aestivum) across cohorts differing in population size, genetic diversity, and genome architecture. Despite population- and species-specific differences in variant annotation profiles, GMM-based clustering consistently identifies informative variant quality classes and enables cohort-specific recalibration of both SNPs and INDELs. Our results demonstrate that unsupervised machine learning can extend GATK Best Practices to crop species lacking comprehensive genomic resources, providing a scalable approach for generating high-quality variant datasets for crop genomics and downstream breeding applications.
ER -