Genetic background shapes AI-predicted variant effects

Schilder, Brian M, Liu, Zhihan, Desmarais, John J, Laub, David, Rahimi, Fahimeh, Sethi, Palash, Pereira, Lucas A, Sun, Mengyi, Kinney, Justin B, McCandlish, David M, Zhou, Juannan, Koo, Peter K (April 2026) Genetic background shapes AI-predicted variant effects. bioRxiv. ISSN 2692-8205 (Submitted)

[thumbnail of 10.64898.2026.04.04.715328.pdf]

PDF
10.64898.2026.04.04.715328.pdf - Submitted Version
Available under License Creative Commons Attribution.
Download (6MB)

URL: https://www.ncbi.nlm.nih.gov/pubmed/41993283

DOI: 10.64898/2026.04.04.715328

Abstract

Predicting the consequences of genetic variants remains a major goal in biomedicine. Conventional approaches typically assess single-nucleotide variants in the context of a single reference genome, without accounting for genetic diversity that can modulate variant effects. Here we introduce the personalized variant effect predictor (pVEP) framework, which quantifies how genetic background across thousands of human genomes from globally diverse populations shapes computational predictions of clinical variant effects. Across deep learning models spanning protein structure, splicing, and noncoding regulation, pVEP reveals that many clinical variants exhibit heterogeneous predicted effects across haplotypes, with the same variant predicted to be pathogenic in some genetic backgrounds and benign in others. We find support for underlying molecular mechanisms, including shifts in predicted protein contacts and changes in splice-site recognition. Overall, personalized genomic context emerges as a systematically underappreciated variable in variant annotation and clinical interpretation, with particular implications for genetically diverse populations.

Item Type:	Paper
Subjects:	bioinformatics bioinformatics > genomics and proteomics
CSHL Authors:	Kinney, Justin B. McCandlish, David Koo, Peter K Desmarais, John Liu, Zhihan Schilder, Brian Sun, Mengyi
Communities:	CSHL labs > Kinney lab CSHL labs > Koo Lab CSHL labs > McCandlish lab CSHL Post Doctoral Fellows
SWORD Depositor:	CSHL Elements
Depositing User:	CSHL Elements
Date:	7 April 2026
Date Deposited:	27 Apr 2026 13:53
Last Modified:	27 Apr 2026 13:53
PMCID:	PMC13082004
Related URLs:	Publisher
URI:	https://repository.cshl.edu/id/eprint/42178

Actions (login required)

Administrator's edit/view item