Article

Calibrated Variant Effect Prediction at the Residue Level Using Conditional Score Distributions

2025-11-26

Abstract excerpt

Effective clinical use of variant effect prediction (VEP) requires models that are both accurate and well-calibrated. Calibration refers to a model’s ability to produce meaningful and reliable probability estimates. Benchmarking 24 VEPs we show that while models may appear well calibrated on average, they remain markedly miscalibrated within specific variant subgroups. We propose a practical path toward robust VEP...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: f136095e-fe77-5459-8b56-c63364b7a176
DOI: 10.1101/2025.11.24.690189

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Calibrated Variant Effect Prediction at the Residue Level Using Conditional Score DistributionsDOI 10.1101/2025.11.24.690189Read

Gene- and domain-aware calibration increases the clinical utility of variant effect predictorsSemantic proximity Read

Gene- and domain-aware calibration increases the clinical utility of variant effect predictorsSemantic proximity Read

acmgscaler: An R package and Colab for standardised gene-level variant effect score calibration within the ACMG/AMP frameworkSemantic proximity Read

Calibration of additional computational tools expands ClinGen recommendation options for variant classification with PP3/BP4 criteriaSemantic proximity Read

Toward trustable use of machine learning models of variant effects in the clinic.Semantic proximity Read

Calibration of additional computational tools expands ClinGen recommendation options for variant classification with PP3/BP4 criteria.Semantic proximity Read

Gene-based calibration of high-throughput functional assays for clinical variant classificationSemantic proximity Read

Updated benchmarking of variant effect predictors using deep mutational scanningSemantic proximity Read

Variant effect predictor correlation with functional assays is reflective of clinical classification performanceSemantic proximity Read

QAFI: A Novel Method for Quantitative Estimation of Missense Variant Impact Using Protein-Specific Predictors and Ensemble LearningSemantic proximity Read

Clinical evidence yield as a framework for evaluating computational predictors and multiplexed assays of variant effectSemantic proximity Read

Why variant effect predictors and multiplexed assays agree and disagreeSemantic proximity Read