Population-scale drug target and variant prioritization with Varformer
- 1Queen Mary University of London
Abstract
Human genetic variation is a powerful driver of therapeutic target prioritization, yet current models struggle to aggregate variable numbers of variants per gene and are bottlenecked by the scarcity of validated targets. We present Varformer, a multimodal transformer that uses cross-modal attention to integrate contextual representations of missense variants with gene-level features. Trained via positive-unlabeled learning on clinically validated targets across four genetic ancestry groups, Varformer achieves a precision@20 of 0.95, 0.86, and 0.48 across three benchmarks of increasing difficulty. It surpasses a logistic regression ablation by 20% and DrugnomeAI by 23% on the hardest benchmark. Cross-population rank normalization isolates targets with consistent genetic support across ancestry groups. The variant encoder also scores individual variants. Across 1,164 carrier-variant pairs in Genes & Health, Varformer ranked the known pathogenic variant in the carrier's top 20 in 57% of pairs. Varformer is available as an open-source framework for unified target and variant prioritization.
Related
- Reclassification Is All You Missed: Surfacing Variant Reinterpretation Need in Online Health Communities at Population Scale
- vep-rs: high-throughput Rust variant annotation with population-scale concordance to Ensembl VEP
- miRAssist: a context-aware, evidence integration framework for interpretable miRNA-target prioritization
- Applying AlphaGenome Variant Impact for SNV Prioritization
- Proteome scale drug prioritization from AlphaFold 3 interaction confidence
BibTeX
@misc{wenteler2026populationscale,
title = {{Population-scale drug target and variant prioritization with Varformer}},
author = {A. Wenteler and V. Neduva and Genes \& Health Research Team and C. P. Cabrera and W. Wei and M. R. Barnes},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.16.759653},
url = {https://www.biorxiv.org/content/10.64898/2026.10.16.759653v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Population-scale drug target and variant prioritization with Varformer
AU - A. Wenteler
AU - V. Neduva
AU - Genes & Health Research Team
AU - C. P. Cabrera
AU - W. Wei
AU - M. R. Barnes
PY - 2026
DA - 2026/10/16
PB - bioRxiv
DO - 10.64898/2026.10.16.759653
UR - https://www.biorxiv.org/content/10.64898/2026.10.16.759653v1
AB - Human genetic variation is a powerful driver of therapeutic target prioritization, yet current models struggle to aggregate variable numbers of variants per gene and are bottlenecked by the scarcity of validated targets. We present Varformer, a multimodal transformer that uses cross-modal attention to integrate contextual representations of missense variants with gene-level features. Trained via positive-unlabeled learning on clinically validated targets across four genetic ancestry groups, Varformer achieves a precision@20 of 0.95, 0.86, and 0.48 across three benchmarks of increasing difficulty. It surpasses a logistic regression ablation by 20% and DrugnomeAI by 23% on the hardest benchmark. Cross-population rank normalization isolates targets with consistent genetic support across ancestry groups. The variant encoder also scores individual variants. Across 1,164 carrier-variant pairs in Genes & Health, Varformer ranked the known pathogenic variant in the carrier's top 20 in 57% of pairs. Varformer is available as an open-source framework for unified target and variant prioritization.
ER -