Result

83.7% accuracy

FoldX5.0 ΔΔG on AlphaFold2 models ≥+2.5 Accuracy

Tested configuration: FoldX5.0 ΔΔG on AlphaFold2 models, BP4 ≤+1.5 and PP3 ≥+2.5 (Ramadane-Morchadi et al. 2025)
Protocol: BRCA1 MAVE LoF discrimination at the PP3 threshold (Ramadane-Morchadi et al. 2025 Table 2)
Dataset: BRCA1 RING and BRCT missense variants with saturation genome editing functional class (Findlay et al. 2018), LoF versus FUNC
Procedure: brca-20261009-protocol-ramadane2025-binary
Evaluation: FoldX5.0 ΔΔG on AlphaFold2 models ≥+2.5, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025)
Coverage: Not reported scored / Not reported eligible
Uncertainty: 95% CI 81.7 to 85.4
Evidence: Independent external evaluation · source checkedACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'ΔΔG AF a' group, row '≥+2.5', column 'Accuracy'

A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.

Reproduction

Split: Whole dataset
Adaptation: Binary call at the PP3 threshold ≥+2.5 only
Scoring implementation: Sensitivity, specificity, PPV, NPV and accuracy with 95% CI (MedCalc)

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-10-10-84341e0b121f
Property and statement	Original source and location	Review and provenance
Reported result 83.7 Individual claims	ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence Original source ↗ Table 2, 'ΔΔG AF a' group, row '≥+2.5', column 'Accuracy' Version: American Journal of Human Genetics 112(5):993, published 2025; PMC12120176 full-text XML Retrieved: 2026-10-09T21:18:06Z	source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-09 independent paper Audit details Extracted by deterministic parse of the table in the pinned JATS XML (extract/extract_brca.py), with the caption, header rows, row labels and footnotes asserted. printed_value is the cell value without its footnote letter and interval; the whole cell is kept in printed_source_cell. Pending independent review. Independent review 2026-10-09: value and identity match the source. Field: `attributes.printed_value` Source artifact SHA-256: `cd089e7c621818f457f54f93c37cc1b9d535e531212b1aaf431fcbdd733bbda1` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `cd089e7c621818f457f54f93c37cc1b9d535e531212b1aaf431fcbdd733bbda1` Extraction artifact

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-10-84341e0b121f · Record review: source checked

1 source records and release history

ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Original source · American Journal of Human Genetics 112(5):993, published 2025; PMC12120176 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: brca-20261009-result-ramadane2025-ddg-af-1-5-2-5-binary-accuracy

metric: accuracy
metric direction: higher
unit: percent
metric qualifier: LoF versus FUNC at the tool's PP3 threshold
printed value: 83.7
numeric value: 83.7
source locator: Table 2, 'ΔΔG AF a' group, row '≥+2.5', column 'Accuracy'
review: method: source-hash-verification; deterministic-table-parse; independent-cell-check; method note: Re-downloaded the article XML and matched its SHA-256. Read Tables 1 and 2 with the reviewer's own table-wrap reader; checked printed and numeric value, interval, row, group, column, metric and the linked configuration and protocol. For Table 2, PPV, NPV and accuracy were recomputed from the printed sensitivity and specificity with 337 LoF and 1,182 FUNC variants (all within 0.3 points).; reviewer: claude; reviewer note: Separate Claude review agent, independent of the extractor; no human review claimed; date: 2026-10-09; artifact sha256: cd089e7c621818f457f54f93c37cc1b9d535e531212b1aaf431fcbdd733bbda1; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12120176/fullTextXML; note: Extracted by deterministic parse of the table in the pinned JATS XML (extract/extract_brca.py), with the caption, header rows, row labels and footnotes asserted. printed_value is the cell value without its footnote letter and interval; the whole cell is kept in printed_source_cell. Pending independent review. Independent review 2026-10-09: value and identity match the source.
printed source cell: 83.7 (81.7–85.4)
denominator: 1519
uncertainty: type: confidence_interval; level: 0.95; printed: (81.7–85.4); lower: 81.7; upper: 85.4
score category: ≥+2.5

Related records

evaluation: FoldX5.0 ΔΔG on AlphaFold2 models ≥+2.5, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025)

Suggest a correction