Evaluating sequence-to-function deep learning models for ancestry-stratified regulatory variant effect prediction using multi-ancestry blood eQTLs
Xinyu Sun, Makaela Mews, Nicholas R. Wheeler, Penelope H. Benchek, Tianjie Gu, Lissette Gomez, Yousef Mustafa, L Wang, Yuk Yee Leung, Gerard D. Schellenberg, Margaret Ann Pericak‐Vance, Jonathan L. Haines, Anthony J. Griswold, William S. Bush
This study evaluates two sequence-to-function models for predicting regulatory variant effects across ancestries using blood eQTL data, finding better performance for high-confidence variants in African American populations.
bioRxiv · Jun 26, 2026 · PreprintBioinformatics