Evaluating sequence-to-function deep learning models for ancestry-stratified regulatory variant effect prediction using multi-ancestry blood eQTLs.

Background: Sequence-to-function (S2F) deep learning models are increasingly used to prioritize non-coding regulatory variants, but their behavior across ancestrally diverse populations remains unclear. Because both training data and reference resources are heavily European-centered, multi-ancestry benchmarks are needed to determine whether S2F scores capture regulatory effects consistently across populations with different allele-frequency and LD patterns. Methods: We evaluated Borzoi and AlphaGenome using whole blood eQTL data from the MAGENTA cohort, including African American (AA; Results: Both models showed weak agreement with nominal eQTL effect sizes across ancestries and TSS-distance bins ( Conclusions: Borzoi and AlphaGenome showed limited agreement with nominal eQTL effect sizes, but better distinguished high-confidence fine-mapped eQTLs from low-PIP variants. These results support using S2F scores as prioritization evidence for fine-mapped regulatory variants, especially promoter-proximal high-PIP variants, rather than as standalone predictors of eQTL effect size. The strongest discrimination was observed for the AA high-PIP variant set. Overall, the AA result is best interpreted as stronger separation of high-PIP variants from lower-PIP comparison variants, shaped by fine-mapping resolution, LD, the choice of comparison variants, and annotation composition.