rewirebio.iobenchmarks
Evaluation

VEST4: PP3/BP4 score intervals (Pejaver et al. 2022)

Published calibration; transcribed, not reproduced.

Evaluation results

1 evaluation · 8 results. Different protocols are not a single leaderboard.

Protocol: PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2) · Dataset: ClinVar 2019 calibration set (Pejaver et al. 2022)

In source order. Decimals are rounded for display; each value links to the printed value and its source.

Tested configurationEvidence strength score interval (BP4 Moderate, ClinGen SVI calibration (Pejaver et al. 2022))Evidence strength score interval (BP4 Strong, ClinGen SVI calibration (Pejaver et al. 2022))Evidence strength score interval (BP4 Supporting, ClinGen SVI calibration (Pejaver et al. 2022))Evidence strength score interval (BP4 Very Strong, ClinGen SVI calibration (Pejaver et al. 2022))Evidence strength score interval (PP3 Moderate, ClinGen SVI calibration (Pejaver et al. 2022))Evidence strength score interval (PP3 Strong, ClinGen SVI calibration (Pejaver et al. 2022))Evidence strength score interval (PP3 Supporting, ClinGen SVI calibration (Pejaver et al. 2022))Evidence strength score interval (PP3 Very Strong, ClinGen SVI calibration (Pejaver et al. 2022))
VEST4 (Pejaver et al. 2022 calibration)Evaluation≤0.302–(0.302, 0.449]–[0.861, 0.965)≥0.965[0.764, 0.861)–
All 8 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: VEST4 (Pejaver et al. 2022 calibration)Protocol: PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)
Dataset: ClinVar 2019 calibration set (Pejaver et al. 2022)
≤0.302 Evidence strength score interval (BP4 Moderate, ClinGen SVI calibration (Pejaver et al. 2022))
unitless · unknown

Uncertainty: Not yet extracted: One-sided confidence intervals are in Table S1, not retrieved

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

VEST4: PP3/BP4 score intervals (Pejaver et al. 2022)

vep-uc-20261014-protocol-pejaver2022-intervals

Aggregation: Not reported

Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML) · Table 2, row 'VEST4', column 'Benign (BP4): Moderate'
Configuration: VEST4 (Pejaver et al. 2022 calibration)Protocol: PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)
Dataset: ClinVar 2019 calibration set (Pejaver et al. 2022)
– Evidence strength score interval (BP4 Strong, ClinGen SVI calibration (Pejaver et al. 2022))
unitless · unknown

Uncertainty: Not applicable: Strength not reached

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

VEST4: PP3/BP4 score intervals (Pejaver et al. 2022)

vep-uc-20261014-protocol-pejaver2022-intervals

Aggregation: Not reported

Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML) · Table 2, row 'VEST4', column 'Benign (BP4): Strong'
Configuration: VEST4 (Pejaver et al. 2022 calibration)Protocol: PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)
Dataset: ClinVar 2019 calibration set (Pejaver et al. 2022)
(0.302, 0.449] Evidence strength score interval (BP4 Supporting, ClinGen SVI calibration (Pejaver et al. 2022))
unitless · unknown

Uncertainty: Not yet extracted: One-sided confidence intervals are in Table S1, not retrieved

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

VEST4: PP3/BP4 score intervals (Pejaver et al. 2022)

vep-uc-20261014-protocol-pejaver2022-intervals

Aggregation: Not reported

Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML) · Table 2, row 'VEST4', column 'Benign (BP4): Supporting'
Configuration: VEST4 (Pejaver et al. 2022 calibration)Protocol: PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)
Dataset: ClinVar 2019 calibration set (Pejaver et al. 2022)
– Evidence strength score interval (BP4 Very Strong, ClinGen SVI calibration (Pejaver et al. 2022))
unitless · unknown

Uncertainty: Not applicable: Strength not reached

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

VEST4: PP3/BP4 score intervals (Pejaver et al. 2022)

vep-uc-20261014-protocol-pejaver2022-intervals

Aggregation: Not reported

Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML) · Table 2, row 'VEST4', column 'Benign (BP4): Very Strong'
Configuration: VEST4 (Pejaver et al. 2022 calibration)Protocol: PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)
Dataset: ClinVar 2019 calibration set (Pejaver et al. 2022)
[0.861, 0.965) Evidence strength score interval (PP3 Moderate, ClinGen SVI calibration (Pejaver et al. 2022))
unitless · unknown

Uncertainty: Not yet extracted: One-sided confidence intervals are in Table S1, not retrieved

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

VEST4: PP3/BP4 score intervals (Pejaver et al. 2022)

vep-uc-20261014-protocol-pejaver2022-intervals

Aggregation: Not reported

Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML) · Table 2, row 'VEST4', column 'Pathogenic (PP3): Moderate'
Configuration: VEST4 (Pejaver et al. 2022 calibration)Protocol: PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)
Dataset: ClinVar 2019 calibration set (Pejaver et al. 2022)
≥0.965 Evidence strength score interval (PP3 Strong, ClinGen SVI calibration (Pejaver et al. 2022))
unitless · unknown

Uncertainty: Not yet extracted: One-sided confidence intervals are in Table S1, not retrieved

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

VEST4: PP3/BP4 score intervals (Pejaver et al. 2022)

vep-uc-20261014-protocol-pejaver2022-intervals

Aggregation: Not reported

Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML) · Table 2, row 'VEST4', column 'Pathogenic (PP3): Strong'
Configuration: VEST4 (Pejaver et al. 2022 calibration)Protocol: PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)
Dataset: ClinVar 2019 calibration set (Pejaver et al. 2022)
[0.764, 0.861) Evidence strength score interval (PP3 Supporting, ClinGen SVI calibration (Pejaver et al. 2022))
unitless · unknown

Uncertainty: Not yet extracted: One-sided confidence intervals are in Table S1, not retrieved

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

VEST4: PP3/BP4 score intervals (Pejaver et al. 2022)

vep-uc-20261014-protocol-pejaver2022-intervals

Aggregation: Not reported

Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML) · Table 2, row 'VEST4', column 'Pathogenic (PP3): Supporting'
Configuration: VEST4 (Pejaver et al. 2022 calibration)Protocol: PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)
Dataset: ClinVar 2019 calibration set (Pejaver et al. 2022)
– Evidence strength score interval (PP3 Very Strong, ClinGen SVI calibration (Pejaver et al. 2022))
unitless · unknown

Uncertainty: Not applicable: Strength not reached

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

VEST4: PP3/BP4 score intervals (Pejaver et al. 2022)

vep-uc-20261014-protocol-pejaver2022-intervals

Aggregation: Not reported

Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML) · Table 2, row 'VEST4', column 'Pathogenic (PP3): Very Strong'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-10-22-1b7cf027e4f6 · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified
  • Sample annotations are recorded: not yet verified
  • Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • A pinned run recipe exists: not yet verified
  • Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Independent validation data exist: not yet verified
  • Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Evaluation procedure

PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)

Configuration
VEST4 (Pejaver et al. 2022 calibration)
Protocol
PP3/BP4 score intervals per evidence strength (Pejaver et al. 2022 Table 2)
Dataset
ClinVar 2019 calibration set (Pejaver et al. 2022)
origin
Author-reported evaluation
configuration
Not reported
dataset version
ClinVar December 2019, filtered (Figure 1A)
split
Whole calibration set
population
11,834 missense variants from 1,914 genes; prior probability of pathogenicity 4.41% (gnomAD set)
inputs
Precomputed or author-generated scores of the tool for each variant
adaptation
None; thresholds fitted to the tool's scores
metric implementation
Local posterior probability of pathogenicity estimated in a sliding score window on the ClinVar 2019 set with prior 0.0441; a threshold is the most lenient score at which the one-sided 95% bootstrap bound (10,000 iterations) of the local positive likelihood ratio still reaches the cut-off for that strength (2.406, 5.790, 33.53, 1,124; reciprocals for BP4)
aggregation
Pooled over variants in all genes
budget
Not reported
protocol id
vep-uc-20261014-protocol-pejaver2022-intervals

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split
Whole calibration set
Adaptation
None; thresholds fitted to the tool's scores
Scoring implementation
Local posterior probability of pathogenicity estimated in a sliding score window on the ClinVar 2019 set with prior 0.0441; a threshold is the most lenient score at which the one-sided 95% bootstrap bound (10,000 iterations) of the local positive likelihood ratio still reaches the cut-off for that strength (2.406, 5.790, 33.53, 1,124; reciprocals for BP4)

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

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.

18 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statementOriginal source and locationReview and provenance
Comparison: adaptation
None; thresholds fitted to the tool's scores
Context-only references
Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML)

Original source ↗

Table 2, row 'VEST4'

Version: PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Retrieved: 2026-10-14T14:44:42Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b

Hash scope: Exact downloaded bytes, before optional gzip storage

Comparison: aggregation
Pooled over variants in all genes
Context-only references
Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML)

Original source ↗

Table 2, row 'VEST4'

Version: PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Retrieved: 2026-10-14T14:44:42Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b

Hash scope: Exact downloaded bytes, before optional gzip storage

Comparison: budget
Not reported
Context-only references
Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML)

Original source ↗

Table 2, row 'VEST4'

Version: PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Retrieved: 2026-10-14T14:44:42Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b

Hash scope: Exact downloaded bytes, before optional gzip storage

Comparison: dataset version
ClinVar December 2019, filtered (Figure 1A)
Context-only references
Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML)

Original source ↗

Table 2, row 'VEST4'

Version: PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Retrieved: 2026-10-14T14:44:42Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b

Hash scope: Exact downloaded bytes, before optional gzip storage

Comparison: inputs
Precomputed or author-generated scores of the tool for each variant
Context-only references
Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML)

Original source ↗

Table 2, row 'VEST4'

Version: PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Retrieved: 2026-10-14T14:44:42Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.inputs

Source artifact SHA-256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b

Hash scope: Exact downloaded bytes, before optional gzip storage

Comparison: metric implementation
Local posterior probability of pathogenicity estimated in a sliding score window on the ClinVar 2019 set with prior 0.0441; a threshold is the most lenient score at which the one-sided 95% bootstrap bound (10,000 iterations) of the local positive likelihood ratio still reaches the cut-off for that strength (2.406, 5.790, 33.53, 1,124; reciprocals for BP4)
Context-only references
Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML)

Original source ↗

Table 2, row 'VEST4'

Version: PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Retrieved: 2026-10-14T14:44:42Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.metric_implementation

Source artifact SHA-256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b

Hash scope: Exact downloaded bytes, before optional gzip storage

Comparison: population
11,834 missense variants from 1,914 genes; prior probability of pathogenicity 4.41% (gnomAD set)
Context-only references
Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML)

Original source ↗

Table 2, row 'VEST4'

Version: PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Retrieved: 2026-10-14T14:44:42Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.population

Source artifact SHA-256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b

Hash scope: Exact downloaded bytes, before optional gzip storage

Comparison: protocol id
vep-uc-20261014-protocol-pejaver2022-intervals
Context-only references
Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML)

Original source ↗

Table 2, row 'VEST4'

Version: PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Retrieved: 2026-10-14T14:44:42Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.protocol_id

Source artifact SHA-256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b

Hash scope: Exact downloaded bytes, before optional gzip storage

Comparison: split
Whole calibration set
Context-only references
Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML)

Original source ↗

Table 2, row 'VEST4'

Version: PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Retrieved: 2026-10-14T14:44:42Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.split

Source artifact SHA-256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b

Hash scope: Exact downloaded bytes, before optional gzip storage

Evidence overlap
Developer overlap: R. Karchin, an author of Pejaver et al. 2022, developed this tool.
Context-only references
Pejaver et al. 2022, Am J Hum Genet 109:2163 (Europe PMC full text XML)

Original source ↗

Table 2, row 'VEST4'

Version: PMC9748256 (Am J Hum Genet 2022;109(12):2163)
Retrieved: 2026-10-14T14:44:42Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.evidence_overlap

Source artifact SHA-256: a78c7bcaacb0ccb72291264bbe7c1f9a16867b0c6207dcbb45c3c59a14af6b3b

Hash scope: Exact downloaded bytes, before optional gzip storage

How to read the evidence

Sources and history

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

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: vep-uc-20261014-eval-pejaver2022-intervals-vest4

areas
dna-genomes
contexts
clinical_research
origin
author_reported
protocol
vep-uc-20261014-protocol-pejaver2022-intervals
comparison
dataset version: ClinVar December 2019, filtered (Figure 1A); split: Whole calibration set; population: 11,834 missense variants from 1,914 genes; prior probability of pathogenicity 4.41% (gnomAD set); inputs: Precomputed or author-generated scores of the tool for each variant; adaptation: None; thresholds fitted to the tool's scores; metric implementation: Local posterior probability of pathogenicity estimated in a sliding score window on the ClinVar 2019 set with prior 0.0441; a threshold is the most lenient score at which the one-sided 95% bootstrap bound (10,000 iterations) of the local positive likelihood ratio still reaches the cut-off for that strength (2.406, 5.790, 33.53, 1,124; reciprocals for BP4); aggregation: Pooled over variants in all genes; budget: Not reported; protocol id: vep-uc-20261014-protocol-pejaver2022-intervals
source locator
Table 2, row 'VEST4'
missing metadata
comparison.budget: reason: inapplicable; note: Calibration of precomputed scores; no compute budget
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.
evidence overlap
Developer overlap: R. Karchin, an author of Pejaver et al. 2022, developed this tool.
Related records

Suggest a correction