Protocol

CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv)

AUROC and average precision (labelled AUPRC) of 49 predictor and conservation scores on oncogenes (gain of function).

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.

49 recorded evaluations, 98 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

49 evaluations · 98 results. Different protocols are not a single leaderboard.

Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) · Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels

Sorted by AUROC (CGC missense, oncogenes (gain of function)) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	AUROC (CGC missense, oncogenes (gain of function))	Average precision (CGC missense, oncogenes (gain of function))
popEVE rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.9 (best in column)	0.834 (best in column)
VARITY_R rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.894	0.804
VARITY_R_LOO rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.891	0.798
ClinPred rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.888	0.789
MetaRNN rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.887	0.793
VARITY_ER rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.886	0.78
AlphaMissense rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.885	0.804
VARITY_ER_LOO rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.884	0.775
BayesDel_addAF rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.878	0.764
MutScore rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.877	0.809
MutPred2 rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.876	0.773
MutationTaster rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.868	0.779
gMVP rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.86	0.739
DEOGEN2 rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.858	0.732
PHACTboost rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.85	0.745
MisFit_D rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.846	0.723
REVEL rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.843	0.739
MPC rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.842	0.716
ESM1b rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.841	0.719
VEST4 rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.84	0.713
BayesDel_noAF rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.827	0.688
CADD_raw rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.821	0.642
Polyphen2_HVAR rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.82	0.602
PrimateAI rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.817	0.618
MVP rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.815	0.657
PROVEAN rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.813	0.646
fathmm-XF_coding rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.81	0.644
Eigen-raw_coding rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.809	0.633
Polyphen2_HDIV rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.805	0.541
MisFit_S rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.803	0.695
Eigen-PC-raw_coding rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.795	0.607
SIFT4G rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.786	0.572
M-CAP rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.775	0.544
MutationAssessor rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.769	0.604
MutFormer rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.768	0.582
phyloP100way_vertebrate rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.766	0.567
MetaSVM rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.766	0.563
SIFT rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.764	0.52
LIST-S2 rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.756	0.562
MetaLR rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.75	0.543
DANN rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.749	0.468
phyloP470way_mammalian rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.714	0.437
phastCons17way_primate rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.68	0.405
phastCons100way_vertebrate rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.671	0.357
GERP_92_mammals rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.662	0.333
GERPpp_RS rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.658	0.349
phastCons470way_mammalian rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.636	0.33
phyloP17way_primate rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.592	0.294
bStatistic rank score, dbNSFP 5.3.1a (Lee 2026)Evaluation	0.425	0.245

All 98 result rows with coverage, uncertainty and sources

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 rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.804 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaMissense on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'AlphaMissense', group 'oncogene', column 'AUPRC'
Configuration: AlphaMissense rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.885 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaMissense on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'AlphaMissense', group 'oncogene', column 'AUROC'
Configuration: BayesDel_addAF rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.764 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BayesDel_addAF on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'BayesDel_addAF', group 'oncogene', column 'AUPRC'
Configuration: BayesDel_addAF rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.878 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BayesDel_addAF on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'BayesDel_addAF', group 'oncogene', column 'AUROC'
Configuration: BayesDel_noAF rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.688 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BayesDel_noAF on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'BayesDel_noAF', group 'oncogene', column 'AUPRC'
Configuration: BayesDel_noAF rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.827 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BayesDel_noAF on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'BayesDel_noAF', group 'oncogene', column 'AUROC'
Configuration: bStatistic rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.245 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source bStatistic on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'bStatistic', group 'oncogene', column 'AUPRC'
Configuration: bStatistic rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.425 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source bStatistic on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'bStatistic', group 'oncogene', column 'AUROC'
Configuration: CADD_raw rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.642 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source CADD_raw on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'CADD_raw', group 'oncogene', column 'AUPRC'
Configuration: CADD_raw rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.821 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source CADD_raw on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'CADD_raw', group 'oncogene', column 'AUROC'
Configuration: ClinPred rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.789 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ClinPred on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'ClinPred', group 'oncogene', column 'AUPRC'
Configuration: ClinPred rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.888 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ClinPred on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'ClinPred', group 'oncogene', column 'AUROC'
Configuration: DANN rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.468 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DANN on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'DANN', group 'oncogene', column 'AUPRC'
Configuration: DANN rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.749 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DANN on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'DANN', group 'oncogene', column 'AUROC'
Configuration: DEOGEN2 rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.732 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DEOGEN2 on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'DEOGEN2', group 'oncogene', column 'AUPRC'
Configuration: DEOGEN2 rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.858 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DEOGEN2 on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'DEOGEN2', group 'oncogene', column 'AUROC'
Configuration: Eigen-PC-raw_coding rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.607 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Eigen-PC-raw_coding on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'Eigen-PC-raw_coding', group 'oncogene', column 'AUPRC'
Configuration: Eigen-PC-raw_coding rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.795 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Eigen-PC-raw_coding on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'Eigen-PC-raw_coding', group 'oncogene', column 'AUROC'
Configuration: Eigen-raw_coding rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.633 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Eigen-raw_coding on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'Eigen-raw_coding', group 'oncogene', column 'AUPRC'
Configuration: Eigen-raw_coding rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.809 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Eigen-raw_coding on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'Eigen-raw_coding', group 'oncogene', column 'AUROC'
Configuration: ESM1b rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.719 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM1b on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'ESM1b', group 'oncogene', column 'AUPRC'
Configuration: ESM1b rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.841 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM1b on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'ESM1b', group 'oncogene', column 'AUROC'
Configuration: fathmm-XF_coding rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.644 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source fathmm-XF_coding on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'fathmm-XF_coding', group 'oncogene', column 'AUPRC'
Configuration: fathmm-XF_coding rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.81 AUROC (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source fathmm-XF_coding on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'fathmm-XF_coding', group 'oncogene', column 'AUROC'
Configuration: GERP_92_mammals rank score, dbNSFP 5.3.1a (Lee 2026)	Protocol: CGC missense oncogenicity, oncogenes (gain of function) (Lee 2026, OncoCal tool_performance.tsv) Dataset: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels	0.333 Average precision (CGC missense, oncogenes (gain of function)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GERP_92_mammals on CGC missense, oncogenes (gain of function) (Lee 2026) somatic-oncogenicity-20261009-protocol-lee2026-oncogene Aggregation: Not reported An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers; OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · OncoCal tables/tool_performance.tsv at commit 40b7770f2a76, row tool 'GERP_92_mammals', group 'oncogene', column 'AUPRC'

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

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: 49

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 2026-11-02-a7f03c9e55a5. 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.

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 2026-11-02-a7f03c9e55a5
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 2026-11-02-a7f03c9e55a5 · Record review: source checked

2 source records and release history

An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers · Original source · bioRxiv 2026.07.16.739080 v1, posted 2026-07-23; full-text HTML page
OncoCal repository, tables/tool_performance.tsv (per-tool AUROC and AUPRC by gene role) · Original source · commit 40b7770f2a768ba800c4f4c6b48e2bfe967ed14a (2026-07-11)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: somatic-oncogenicity-20261009-protocol-lee2026-oncogene

areas: dna-genomes
contexts: clinical_research
protocol: Each dbNSFP 5.3.1a rank score is used directly to rank labelled variants; AUROC and average precision (labelled AUPRC) are computed per tool on the variants it scores, for all genes and by gene role.
version: tables/tool_performance.tsv rows with group 'oncogene'
metric: auroc
limitations: Negatives are ClinVar benign or likely benign and gnomAD common variants, that is germline-benign labels; the use case does not accept these as automatic somatic negatives.; Many supervised tools were trained on ClinVar labels, so the ClinVar-benign negatives overlap their training data.; Single-author bioRxiv preprint (v1, posted 2026-07-23), not peer reviewed; the analysis code is in the linked repository.; Scores are dbNSFP 5.3.1a rank scores; tool coverage differs, so each row has its own n and positives.; No uncertainty is printed in this table. The preprint Results give VARITY_R 0.874 and AlphaMissense 0.868, matching the table; the OncoCal section gives 0.871 and 0.870, probably on the unique protein-level set used to train OncoCal.; Gene role uses CGC gene-level roles where variant-level CIViC mechanism is missing, so some variants may be assigned the wrong mechanism.; The table cannot be regenerated from the repository alone: its script (src/evaluation/part_b.py) needs dbNSFP 5.3.1a and COSMIC v104, which are not redistributed. It was added in the first commit (b17e658d6b) and is unchanged at the pinned commit, whose message credits an AI coding assistant but does not touch the table or its script.
source locator: OncoCal tables/tool_performance.tsv at 40b7770f2a76, group 'oncogene'; preprint S1 Table and Fig 1A

Related records

uses data: Missense variants in 768 Cancer Gene Census genes with open oncogenicity labels
assessment: AlphaMissense on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: BayesDel_addAF on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: BayesDel_noAF on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: bStatistic on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: CADD_raw on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: ClinPred on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: DANN on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: DEOGEN2 on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: Eigen-PC-raw_coding on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: Eigen-raw_coding on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: ESM1b on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: fathmm-XF_coding on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: GERP_92_mammals on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: GERPpp_RS on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: gMVP on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: LIST-S2 on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: M-CAP on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MetaLR on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MetaRNN on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MetaSVM on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MisFit_D on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MisFit_S on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MPC on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MutationAssessor on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MutationTaster on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MutFormer on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MutPred2 on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MutScore on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: MVP on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: PHACTboost on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: phastCons100way_vertebrate on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: phastCons17way_primate on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: phastCons470way_mammalian on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: phyloP100way_vertebrate on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: phyloP17way_primate on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: phyloP470way_mammalian on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: Polyphen2_HDIV on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: Polyphen2_HVAR on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: popEVE on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: PrimateAI on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: PROVEAN on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: REVEL on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: SIFT on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: SIFT4G on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: VARITY_ER_LOO on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: VARITY_ER on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: VARITY_R_LOO on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: VARITY_R on CGC missense, oncogenes (gain of function) (Lee 2026)
assessment: VEST4 on CGC missense, oncogenes (gain of function) (Lee 2026)
assessed by: Assess somatic small-variant oncogenicity

Suggest a correction