Article

Gene identity, not variant effect, dominates ClinVar benchmarks of missense pathogenicity predictors

2026-08-24

Abstract excerpt

Missense pathogenicity predictors are routinely benchmarked against ClinVar, whose labels are strongly structured by gene: genes under diagnostic scrutiny accumulate pathogenic submissions while incidentally sequenced genes accumulate benign ones. We asked how much of a benchmark score this structure alone can produce. On 197,904 ClinVar missense variants validated against UniProt canonical sequences, a null model...

Topics

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

Identifiers and source

Literature Corpus work: 8fc5329c-7405-59c2-9705-02ba9c94e869
DOI: 10.64898/2026.08.21.746180

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Gene identity, not variant effect, dominates ClinVar benchmarks of missense pathogenicity predictorsDOI 10.64898/2026.08.21.746180Read

An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer driversSemantic proximity Read

AnnotateMissense: a genome-wide annotation and benchmarking framework for missense pathogenicity predictionSemantic proximity Read

Critical assessment of missense variant effect predictors on disease-relevant variant dataSemantic proximity Read

Benchmarking of variant pathogenicity prediction methods using a population genetics approachSemantic proximity Read

Systematic benchmarking of 32 in silico tools for pathogenicity prediction of missense variants in genes associated with female infertility and differences in sex developmentSemantic proximity Read

Variant annotation across homologous proteins (“Paralogue Annotation”) identifies disease-causing missense variants with high precision, and is widely applicable across protein familiesSemantic proximity Read

REPRODUCIBLE AND SHAREABLE QUANTIFICATIONS OF PATHOGENICITY.Semantic proximity Read

Variant annotation across homologous proteins (“Paralogue Annotation”) identifies disease-causing missense variants with high precision, and is widely applicable across protein familiesSemantic proximity Read

Toward Advanced Quantitative Prediction of Missense Variant EffectsSemantic proximity Read

A fine-tuned genomic language model captures nucleotide-level information overlooked by missense variant impact predictorsSemantic proximity Read

P-KNN: Maximizing variant classification evidence through joint calibration of multiple pathogenicity prediction toolsSemantic proximity Read

A benchmark study of scoring methods for non-coding mutations.Semantic proximity Read