Benchmark

ClinGen SVI calibration of computational predictors for PP3/BP4

Local posterior probability calibration of missense predictor scores to ACMG/AMP evidence strengths (PP3 for pathogenicity, BP4 for benignity), on ClinVar missense variants with a prior probability of pathogenicity estimated from gnomAD.

Results are recorded on the linked protocols, tasks or configurations listed below. Their settings and evaluations are kept separate.

4 protocols with results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Results on linked records

This benchmark has no results of its own in this release. 4 linked records have results. They are not assigned to the underlying benchmark: each record keeps its own settings and evaluations, and its scores are on its own page.

PP3/BP4 score intervals on the points scale (Bergquist et al. 2025 Table 1) Protocol · part of this benchmark · 7 evaluations · 63 results
Share of gnomAD variants called pathogenic at developer thresholds (Pejaver et al. 2022 Table 3) Protocol · part of this benchmark · 3 evaluations · 3 results
Local likelihood ratio at developer-recommended thresholds (Pejaver et al. 2022 Table 3) Protocol · part of this benchmark · 3 evaluations · 3 results
PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2) Protocol · part of this benchmark · 13 evaluations · 104 results

Methods and evaluation design

Procedure, tasks and evaluated configurations

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 8 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

Baseline status by linked protocol

PP3/BP4 score intervals on the points scale (Bergquist et al. 2025 Table 1) · 0/2 roles measured
Share of gnomAD variants called pathogenic at developer thresholds (Pejaver et al. 2022 Table 3) · 0/2 roles measured
Local likelihood ratio at developer-recommended thresholds (Pejaver et al. 2022 Table 3) · 0/2 roles measured
PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2) · 0/2 roles measured

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this benchmark. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Strengths, limitations and unresolved questions

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

2 source records and release history

Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML) · Original source · PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Bergquist et al. 2025, Genet Med 27:101402 (PMC author manuscript) · Original source · PMC12208618, NIH author manuscript of Genet Med 2025;27(6):101402

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: vep-uc-20261014-benchmark-clingen-svi-calibration

areas: dna-genomes
contexts: clinical_research
entity level: suite
version: Pejaver et al. 2022 (13 tools) and Bergquist et al. 2025 (3 further tools, point-based intervals)
task: Calibrate predictor score thresholds to ACMG/AMP evidence strengths for missense variants
scope note: Calibration on the ClinVar 2019 set (11,834 missense variants, 1,914 genes, rare in gnomAD, training variants of the tools removed where available); prior probability of pathogenicity 4.41% from the gnomAD set by DistCurve; thresholds where the one-sided 95% bootstrap bound of the local positive likelihood ratio reaches 2.406, 5.790, 33.53 and 1,124 (Supporting to Very Strong).
source locator: Pejaver et al. 2022 Methods and Table 1; Bergquist et al. 2025 Materials and Methods
limitations: Genome-wide calibration; evidence strength varies between genes (Tejura et al. 2024).; Several authors of Pejaver et al. 2022 developed calibrated tools: B.-J. Feng (BayesDel; reference 13 is Feng's PERCH paper), V. Pejaver, K.A. Pagel, S.D. Mooney and P. Radivojac (MutPred2, reference 19), V. Pejaver (REVEL, reference 23), R. Karchin (VEST4, reference 25) and A. O'Donnell-Luria (MPC, reference 18).
review: reviewer: claude; reviewer note: Claude review agent; no human review claimed. Independent Claude (Opus 5.5) review agent, separate from the extraction agent that built this batch. Automated review only. Transcription, not reproduction.; reviewed at: 2026-10-14T16:00:00Z; artifact sha256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC9748256/fullTextXML; method: source-hash-verification; ai-assisted-source-review; method note: Checked against the Methods, table captions and author lists of the pinned sources.; note: Checked; see the dated review for rulings on origin and carried-over rows.

Related records

Suggest a correction