Calibrated Variant Effect Prediction at the Residue Level Using Conditional Score Distributions
Passi, G.; Amittai, S.; Schneidman-Duhovny, D.
Show abstract
Effective clinical use of variant effect prediction (VEP) requires models that are both accurate and well-calibrated. Calibration refers to a models ability to produce meaningful and reliable probability estimates. Here, we propose a practical path toward robust VEP calibration by calibrating at the residue-level rather than using global or per-protein schemes. We identify variant subgroups that benefit from targeted calibration and show that, while VEPs appear well calibrated on average, they remain markedly miscalibrated within these subgroups. Leveraging these insights, we develop RaCoon (Residue-aware Calibration via Conditional distributions), implemented on ESM1b, which provides multicalibrated and interpretable predictions across diverse variant subgroups and significantly improves performance across multiple benchmarks. Targeted residue-level calibration not only improves overall calibration but, for most models, also yields gains in global AUROC. Specifically, RaCoon increases AUCROC from 0.912 to 0.924. Our calibration strategy, guided by model-specific feature distributions, is readily transferable to other VEPs.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- PreMode predicts mode-of-action of missense variants by deep graph representation learning of protein sequence and structural context 96%
- A probabilistic graphical model for estimating selection coefficient of nonsynonymous variants from human population sequence data 96%
- Generalizable and scalable protein stability prediction with rewired protein generative models 96%
Similar papers in this journal
Similar papers in this journal
- Variant-resolved prediction of context-specific isoform variation with a graph-based attention model 95%
- Meta-analysis fine-mapping is often miscalibrated at single-variant resolution 95%
- Binding domain mutations provide insight into CTCF's relationship with chromatin and its contribution to gene regulation 94%
Similar papers in this journal
- Benchmarking of deep neural networks for predicting personal gene expression from DNA sequence highlights shortcomings 95%
- Linking regulatory variants to target genes by integrating single-cell multiome methods and genomic distance 95%
- Genotyping sequence-resolved copy number variationusing pangenomes reveals paralog-specific global diversityand expression divergence of duplicated genes 95%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.