pipette
ENEnglish

Genomic heterogeneity inflates the performance of variant pathogenicity predictions

B.T. Lu, Xueshen Liu, Po‐Yu Lin, Nadav Brandes

Revista con revisión por pares

En palabras de los autores

Abstract Recent studies have reported unprecedented accuracy predicting pathogenic variants across the genome, including in noncoding regions, using large deep-learning models trained on vast genomic data. To verify and understand the basis of these reports, we systematically evaluated the prediction accuracy of frontier models over single-nucleotide variants, focusing on general models capable of scoring multiple variant types across coding or noncoding regions. Our evaluations reveal that the performance of genome-wide predictions is severely inflated by mixing variant categories with different baseline prevalences of pathogenic variants. We constructed a benchmark stratified by variant type to identify the best-performing models for each genomic context, determine where reliable predictions remain out of reach, and establish rigorous standards to guide future evaluations.

Resultado principalEl resumen no menciona limitaciones.

Apareció: domingo, 1 de noviembre. Nature Communications. Revista con revisión por pares.

DOI: 10.1038/s41467-026-78623-5