Answers are grounded in this paper and cite their sources.
Comprehensive assessment reveals inflated predictive accuracy in AI models for pathogenic variants, suggesting need for better benchmarks.
Recent studies have reported unprecedented accuracy predicting pathogenic variants across the genome, including in noncoding regions, using large AI models trained on vast genomic data. We present a comprehensive evaluation of these frontier models, showing that performance is inflated by differences in the prevalence of pathogenic variants across genomic contexts. We identify the best-performing models for each variant type and establish a benchmark to guide future progress.
No takes yet. Share an insight, caveat, or question.
Lu et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: