Published October 7, 2026 | Version v1

Ancestry bias in variant effect predictors

Authors/Creators

Description

Variant effect predictors (VEPs) have become increasingly important for clinical variant interpretation. However, many widely used methods are trained using clinically curated or population-derived variant datasets that disproportionately represent individuals of European descent. To test whether this imbalance leads to ancestry-associated differences in predictor output, we evaluated the scoring patterns of 55 missense VEPs across variants from 14 ancestry groups. We observed striking disparities, with several VEPs predicting a markedly higher proportion of damaging variants in underrepresented populations compared to individuals of European ancestry. In contrast, VEPs developed without direct exposure to clinical or human population variants predicted more consistent pathogenicity burdens across populations. These discrepancies closely tracked differences in ancestry representation in variant resources, implicating biased training data as a major contributor. Our findings underscore the urgent need to adopt tools that minimise ancestry bias, ensuring more accurate variant effect prediction and genetic diagnosis for all populations.

Files

analysis.ipynb

Files (801.3 MB)

Name Size
md5:82f7910e3d8cdb53b96a9bd7124d27e7
19.5 MB Preview Download
md5:458d5218dbdba8e704d60b4afef3c107
781.7 MB Preview Download
md5:88b05c8c95fed75d9c97cd46b3c1c590
3.1 kB Preview Download