Protocol

BRCA1 MAVE LoF discrimination at the PP3 threshold (Ramadane-Morchadi et al. 2025 Table 2)

Sensitivity, specificity, PPV, NPV and accuracy for discriminating LoF from FUNC BRCA1 missense variants at one threshold per tool.

6 evaluations · 30 results

Overview

Sensitivity, specificity, PPV, NPV and accuracy for discriminating LoF from FUNC BRCA1 missense variants at one threshold per tool.

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

6 recorded evaluations, 30 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

6 evaluations · 30 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: AlphaMissense, BP4 ≤0.65 and PP3 ≥0.75 (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	87.2% accuracy percent · higher Uncertainty: 95% CI 85.4 to 88.8 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaMissense ≥0.75, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'AM' group, row '≥0.75', column 'Accuracy'
Configuration: AlphaMissense, BP4 ≤0.65 and PP3 ≥0.75 (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	95.2% negative-predictive-value percent · higher Uncertainty: 95% CI 93.8 to 96.2 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaMissense ≥0.75, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'AM' group, row '≥0.75', column 'NPV'
Configuration: AlphaMissense, BP4 ≤0.65 and PP3 ≥0.75 (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	66.7% precision percent · higher Uncertainty: 95% CI 63.0 to 70.1 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaMissense ≥0.75, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'AM' group, row '≥0.75', column 'PPV'
Configuration: AlphaMissense, BP4 ≤0.65 and PP3 ≥0.75 (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	84.3% recall percent · higher Uncertainty: 95% CI 79.9 to 88.0 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaMissense ≥0.75, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'AM' group, row '≥0.75', column 'Sensitivity'
Configuration: AlphaMissense, BP4 ≤0.65 and PP3 ≥0.75 (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	88% specificity percent · higher Uncertainty: 95% CI 86.0 to 89.8 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaMissense ≥0.75, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'AM' group, row '≥0.75', column 'Specificity'
Configuration: BayesDel, BP4 ≤0.15 and PP3 ≥0.28 (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	85.6% accuracy percent · higher Uncertainty: 95% CI 83.7 to 87.3 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BayesDel ≥0.28, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'BD' group, row '≥0.28', column 'Accuracy'
Configuration: BayesDel, BP4 ≤0.15 and PP3 ≥0.28 (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	93.8% negative-predictive-value percent · higher Uncertainty: 95% CI 92.5 to 94.9 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BayesDel ≥0.28, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'BD' group, row '≥0.28', column 'NPV'
Configuration: BayesDel, BP4 ≤0.15 and PP3 ≥0.28 (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	64.1% precision percent · higher Uncertainty: 95% CI 60.3 to 67.6 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BayesDel ≥0.28, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'BD' group, row '≥0.28', column 'PPV'
Configuration: BayesDel, BP4 ≤0.15 and PP3 ≥0.28 (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	79.8% recall percent · higher Uncertainty: 95% CI 75.1 to 84.0 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BayesDel ≥0.28, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'BD' group, row '≥0.28', column 'Sensitivity'
Configuration: BayesDel, BP4 ≤0.15 and PP3 ≥0.28 (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	87.2% specificity percent · higher Uncertainty: 95% CI 85.2 to 89.1 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BayesDel ≥0.28, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'BD' group, row '≥0.28', column 'Specificity'
Configuration: FoldX5.0 ΔΔG on AlphaFold2 models, BP4 ≤+1.0 and PP3 ≥+3.0 (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	86.6% accuracy percent · higher Uncertainty: 95% CI 84.6 to 88.4 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on AlphaFold2 models ≥+3, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/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 '≥+3', column 'Accuracy'
Configuration: FoldX5.0 ΔΔG on AlphaFold2 models, BP4 ≤+1.0 and PP3 ≥+3.0 (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	96.6% negative-predictive-value percent · higher Uncertainty: Sources conflict: Printed interval (92.3-97.5) is inconsistent with the estimate: an NPV of 96.6% over about 1,050 predicted-FUNC variants gives roughly 95.4 to 97.6, and every other Table 2 interval is close to symmetric. The lower bound is probably misprinted; the interval is kept in printed_source_cell only. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on AlphaFold2 models ≥+3, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/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 '≥+3', column 'NPV'
Configuration: FoldX5.0 ΔΔG on AlphaFold2 models, BP4 ≤+1.0 and PP3 ≥+3.0 (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	64% precision percent · higher Uncertainty: 95% CI 60.2 to 67.6 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on AlphaFold2 models ≥+3, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/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 '≥+3', column 'PPV'
Configuration: FoldX5.0 ΔΔG on AlphaFold2 models, BP4 ≤+1.0 and PP3 ≥+3.0 (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	89.1% recall percent · higher Uncertainty: 95% CI 84.9 to 92.5 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on AlphaFold2 models ≥+3, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/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 '≥+3', column 'Sensitivity'
Configuration: FoldX5.0 ΔΔG on AlphaFold2 models, BP4 ≤+1.0 and PP3 ≥+3.0 (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	85.9% specificity percent · higher Uncertainty: 95% CI 83.5 to 88.0 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on AlphaFold2 models ≥+3, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/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 '≥+3', column 'Specificity'
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	83.7% accuracy percent · higher Uncertainty: 95% CI 81.7 to 85.4 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on AlphaFold2 models ≥+2.5, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/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'
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	94.1% negative-predictive-value percent · higher Uncertainty: 95% CI 92.8 to 95.3 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on AlphaFold2 models ≥+2.5, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/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 'NPV'
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	59.5% precision percent · higher Uncertainty: 95% CI 56.1 to 62.8 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on AlphaFold2 models ≥+2.5, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/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 'PPV'
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	81.6% recall percent · higher Uncertainty: 95% CI 77.1 to 85.6 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on AlphaFold2 models ≥+2.5, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/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 'Sensitivity'
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	84.2% specificity percent · higher Uncertainty: 95% CI 81.2 to 86.2 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on AlphaFold2 models ≥+2.5, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/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 'Specificity'
Configuration: FoldX5.0 ΔΔG on experimental PDB structures, BP4 ≤+1.0 and PP3 ≥+3.0 (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	86.3% accuracy percent · higher Uncertainty: 95% CI 84.2 to 88.3 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on experimental PDB structures ≥+3, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'ΔΔG PDB a' group, row '≥+3', column 'Accuracy'
Configuration: FoldX5.0 ΔΔG on experimental PDB structures, BP4 ≤+1.0 and PP3 ≥+3.0 (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	96.1% negative-predictive-value percent · higher Uncertainty: 95% CI 94.7 to 97.2 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on experimental PDB structures ≥+3, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'ΔΔG PDB a' group, row '≥+3', column 'NPV'
Configuration: FoldX5.0 ΔΔG on experimental PDB structures, BP4 ≤+1.0 and PP3 ≥+3.0 (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	63.7% precision percent · higher Uncertainty: 95% CI 59.7 to 67.6 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on experimental PDB structures ≥+3, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'ΔΔG PDB a' group, row '≥+3', column 'PPV'
Configuration: FoldX5.0 ΔΔG on experimental PDB structures, BP4 ≤+1.0 and PP3 ≥+3.0 (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	87.7% recall percent · higher Uncertainty: 95% CI 83.1 to 91.4 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on experimental PDB structures ≥+3, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'ΔΔG PDB a' group, row '≥+3', column 'Sensitivity'
Configuration: FoldX5.0 ΔΔG on experimental PDB structures, BP4 ≤+1.0 and PP3 ≥+3.0 (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	85.9% specificity percent · higher Uncertainty: 95% CI 83.4 to 88.2 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FoldX5.0 ΔΔG on experimental PDB structures ≥+3, BRCA1 MAVE LoF discrimination (Ramadane-Morchadi et al. 2025) brca-20261009-protocol-ramadane2025-binary Aggregation: Not reported ACMG/AMP interpretation of BRCA1 missense variants: Structure-informed scores add evidence strength granularity to the PP3/BP4 computational evidence · Table 2, 'ΔΔG PDB a' group, row '≥+3', column 'Specificity'

Source checking is not independent reproduction. Release 2026-10-10-84341e0b121f.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

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

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

External evaluations: 6

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

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

Coverage is derived from release 2026-10-10-84341e0b121f. 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 protocol. 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 2026-10-10-84341e0b121f
Property and statement	Original source and location	Review and provenance

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

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-protocol-ramadane2025-binary

areas: dna-genomes
contexts: clinical_research
protocol: Each score is dichotomised at its PP3 threshold; predicted LoF is compared with the MAVE LoF or FUNC class.
version: Table 2
metric: recall
limitations: LoF and FUNC functional classes (Findlay et al. 2018 saturation genome editing) stand in for pathogenic and benign; 119 intermediate variants are excluded.; The AlphaMissense 0.65/0.75 and ΔΔG 1.5/2.5 thresholds were chosen by a trade-off process on the same 1,519 variants (Results), so those rows are not held-out estimates; the 0.60/0.80 and 1.0/3.0 alternatives are shown alongside without a stated origin. The AlphaMissense 0.34/0.56 thresholds are the developers' and the BayesDel 0.15/0.28 thresholds are the BRCA1 VCEP's.; The BRCA1 VCEP BayesDel thresholds were calibrated by ENIGMA on functional reference labels in the same domains (existing ENIGMA judgements); overlap with this dataset is possible but not stated.; BRCA1 RING and BRCT domains only.; Three authors are employees of Ambry Genetics, a commercial testing laboratory (Declaration of interests); none of the compared tools is from the authors.; The same saturation genome editing data are the BRCA1 truth set in Cubuk et al. 2021; agreement between these studies is not independent replication.; Each row is a single binary cut at the PP3 threshold; variants below it count as predicted FUNC, so this does not describe the three-category use in Table 1.; Intervals were computed with the MedCalc online calculator; the NPV interval for ΔΔG(AlphaFold2) at +3 or more is probably misprinted and not recorded.
denominator: 1519
source locator: Table 2; Material and methods paragraph 4; Results paragraph 11

Related records

Suggest a correction