Combining MAVEs and computational predictors improves variant classification across ancestries in hereditary cancer genes
4 affiliations
- 1Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore
- 2MRC Human Genetics Unit, Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, UK
- 3Center for Systems Biology Dresden, Dresden, Germany
- 4Cancer Genetics Service, Division of Medical Oncology, National Cancer Centre Singapore, Singapore, Singapore
Abstract
Background: Many commonly used computational tools for variant effect prediction exhibit ancestry-related bias because they are trained on clinical or population datasets that under-represent global diversity, leading to uneven and sometimes unfair variant classification across ancestries. Multiplexed assays of variant effect (MAVEs) and population-free variant effect predictors (VEPs) instead offer alternatives that are unbiased with respect to human ancestry, providing classification evidence that generalises across populations.
Methods: Here, we evaluate MAVE- and VEP-based classification across five cancer-associated genes with high-quality MAVE datasets, focusing primarily on three leading population-free VEPs: GEMME, EVE, and CPT-1.
Results: We find that MAVEs are more conservative and decisive in classification, assigning fewer variants to the pathogenic category while yielding fewer indeterminate classifications when calibrated to ACMG/AMP guidelines. Although MAVEs show heightened sensitivity in functionally assayed regions, VEPs identify a broader range of pathogenic variants overall. By combining clinical evidence strengths from MAVEs and VEPs, we reclassify over 90% of variants of uncertain significance across the SG10K_Health and Mexico City Prospective Study reference datasets as at least likely benign or likely pathogenic. We further isolate variants where MAVE- and VEP-based classifications are discordant, highlighting method-specific limitations.
Conclusions: Together, these findings clarify the complementary strengths of experimental and computational classification approaches and provide a path to less biased and more equitable variant interpretation in clinical genomics, helping to mitigate disparities in diagnosis across ancestries.
Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s13073-026-01799-4.
Related
- Iterative computational bioprospecting of hydroxymethylfurfural oxidases combining molecular simulation and machine learning
- Explainable computational framework for subtype classification and biomarker identification in head and neck squamous cell carcinoma using machine learning
- A Computational Re-evaluation of Spatial Trials for Zoonotic Tuberculosis Control: Model Misspecification, Diagnostic Miss-classification, and the Illusion of Wildlife Culling Efficacy
- Neurodegenerative disease risk associated with gene expression in peripheral monocytes across ancestries
- Computational alternative to cardiac biopsy in multiple myeloma: utilizing the shape of routine laboratory data for the classification of AL cardiac amyloidosis
BibTeX
@article{bora2026combining,
title = {{Combining MAVEs and computational predictors improves variant classification across ancestries in hereditary cancer genes}},
author = {Nikita Bora and Mihaly Badonyi and Ankit K. Pathak and Rutharra Ghayadthri Manisekaran and SG10K_Health Consortium and Joseph A. Marsh and Joanne Ngeow},
journal = {Genome Medicine},
year = {2026},
month = oct,
doi = {10.1186/s13073-026-01799-4},
url = {https://doi.org/10.1186/s13073-026-01799-4},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Combining MAVEs and computational predictors improves variant classification across ancestries in hereditary cancer genes
AU - Nikita Bora
AU - Mihaly Badonyi
AU - Ankit K. Pathak
AU - Rutharra Ghayadthri Manisekaran
AU - SG10K_Health Consortium
AU - Joseph A. Marsh
AU - Joanne Ngeow
PY - 2026
DA - 2026/10/18
JO - Genome Medicine
DO - 10.1186/s13073-026-01799-4
UR - https://doi.org/10.1186/s13073-026-01799-4
AB - Background: Many commonly used computational tools for variant effect prediction exhibit ancestry-related bias because they are trained on clinical or population datasets that under-represent global diversity, leading to uneven and sometimes unfair variant classification across ancestries. Multiplexed assays of variant effect (MAVEs) and population-free variant effect predictors (VEPs) instead offer alternatives that are unbiased with respect to human ancestry, providing classification evidence that generalises across populations. Methods: Here, we evaluate MAVE- and VEP-based classification across five cancer-associated genes with high-quality MAVE datasets, focusing primarily on three leading population-free VEPs: GEMME, EVE, and CPT-1. Results: We find that MAVEs are more conservative and decisive in classification, assigning fewer variants to the pathogenic category while yielding fewer indeterminate classifications when calibrated to ACMG/AMP guidelines. Although MAVEs show heightened sensitivity in functionally assayed regions, VEPs identify a broader range of pathogenic variants overall. By combining clinical evidence strengths from MAVEs and VEPs, we reclassify over 90% of variants of uncertain significance across the SG10K_Health and Mexico City Prospective Study reference datasets as at least likely benign or likely pathogenic. We further isolate variants where MAVE- and VEP-based classifications are discordant, highlighting method-specific limitations. Conclusions: Together, these findings clarify the complementary strengths of experimental and computational classification approaches and provide a path to less biased and more equitable variant interpretation in clinical genomics, helping to mitigate disparities in diagnosis across ancestries. Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s13073-026-01799-4.
SN - 1756-994X
ER -