Genomic foundation models do not yet boost common variant discovery beyond standard functional annotations
- 1University of Cambridge
Abstract
Genomic foundation models (GFMs) use large-scale AI to model genetic sequences and their influence on molecular phenotypes. While GFMs have shown promise in rare variant analysis, their utility for common variant discovery remains untested. Using the surrogate functional false discovery rate framework for functionally informed GWAS discovery, we compared standard functional annotations (baselineLD) with annotations derived from three leading GFMs: the sequence-to-function models AlphaGenome and Borzoi, and the genomic language model GPN-Star. Across 27 UK Biobank traits, GPN-Star decreased locus discovery relative to a standard GWAS, whereas AlphaGenome and Borzoi increased discovery but by less than baselineLD (medians 1.8%, 3.8%, and 5.1%). When we combined the GFM and baselineLD annotations, there was no increase over baselineLD alone (median changes -0.1% to 0.2%), suggesting that AlphaGenome and Borzoi mostly capture information already in baselineLD. Thus, GFMs may require larger corpora or trait-specific feature engineering to improve discovery beyond standard functional annotations.
Related
- Integrating multi-omics with machine learning: from genomic variant functional annotation to pharmacogenomics and biomarker discovery
- The Genetic Discovery (GeDi) resource: Deep characterization of a multi-ancestry panel of human reference iPSCs for functional genomic studies
- Integrating Genomic Annotations and Traits Dependencies for single-nucleotide polymorphisms Prioritization with Causal Concept Bottleneck Models
- A Pipeline for Predicting Variant Associations with Complex Disorders via Functional Annotations
- Limitations of Genomic Foundation Models for Decoding Regulatory Mechanisms in ALS
BibTeX
@misc{bass2026genomic,
title = {{Genomic foundation models do not yet boost common variant discovery beyond standard functional annotations}},
author = {A. J. Bass and J. Park and S. Mukherjee and J. Whittaker and C. Wallace},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.13.758880},
url = {https://www.biorxiv.org/content/10.64898/2026.10.13.758880v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Genomic foundation models do not yet boost common variant discovery beyond standard functional annotations
AU - A. J. Bass
AU - J. Park
AU - S. Mukherjee
AU - J. Whittaker
AU - C. Wallace
PY - 2026
DA - 2026/10/13
PB - bioRxiv
DO - 10.64898/2026.10.13.758880
UR - https://www.biorxiv.org/content/10.64898/2026.10.13.758880v1
AB - Genomic foundation models (GFMs) use large-scale AI to model genetic sequences and their influence on molecular phenotypes. While GFMs have shown promise in rare variant analysis, their utility for common variant discovery remains untested. Using the surrogate functional false discovery rate framework for functionally informed GWAS discovery, we compared standard functional annotations (baselineLD) with annotations derived from three leading GFMs: the sequence-to-function models AlphaGenome and Borzoi, and the genomic language model GPN-Star. Across 27 UK Biobank traits, GPN-Star decreased locus discovery relative to a standard GWAS, whereas AlphaGenome and Borzoi increased discovery but by less than baselineLD (medians 1.8%, 3.8%, and 5.1%). When we combined the GFM and baselineLD annotations, there was no increase over baselineLD alone (median changes -0.1% to 0.2%), suggesting that AlphaGenome and Borzoi mostly capture information already in baselineLD. Thus, GFMs may require larger corpora or trait-specific feature engineering to improve discovery beyond standard functional annotations.
ER -