Protocol

OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10)

Accuracy, sensitivity, specificity, PPV and NPV of 17 predictors using default categorical calls.

Overview

Accuracy, sensitivity, specificity, PPV and NPV of 17 predictors using default categorical calls.

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

17 recorded evaluations, 85 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

17 evaluations · 85 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: CanDrA (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.49 accuracy fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CanDrA on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), B18; Algorithm 'CanDrA'; column 'Accuracy (±2σ)'
Configuration: CanDrA (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.46 negative-predictive-value fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CanDrA on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), F18; Algorithm 'CanDrA'; column 'NPV (±2σ)'
Configuration: CanDrA (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.49 precision fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CanDrA on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), E18; Algorithm 'CanDrA'; column 'PPV (±2σ)'
Configuration: CanDrA (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.8 recall fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CanDrA on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), C18; Algorithm 'CanDrA'; column 'Sensitivity (±2σ)'
Configuration: CanDrA (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.17 specificity fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CanDrA on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), D18; Algorithm 'CanDrA'; column 'Specificity (±2σ)'
Configuration: DEOGEN2 (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.7 accuracy fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DEOGEN2 on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), B2; Algorithm 'DEOGEN2'; column 'Accuracy (±2σ)'
Configuration: DEOGEN2 (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.79 negative-predictive-value fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DEOGEN2 on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), F2; Algorithm 'DEOGEN2'; column 'NPV (±2σ)'
Configuration: DEOGEN2 (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.65 precision fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DEOGEN2 on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), E2; Algorithm 'DEOGEN2'; column 'PPV (±2σ)'
Configuration: DEOGEN2 (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.87 recall fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DEOGEN2 on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), C2; Algorithm 'DEOGEN2'; column 'Sensitivity (±2σ)'
Configuration: DEOGEN2 (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.51 specificity fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DEOGEN2 on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), D2; Algorithm 'DEOGEN2'; column 'Specificity (±2σ)'
Configuration: FATHMM-disease (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.52 accuracy fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-disease on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), B17; Algorithm 'FATHMM-disease'; column 'Accuracy (±2σ)'
Configuration: FATHMM-disease (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.53 negative-predictive-value fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-disease on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), F17; Algorithm 'FATHMM-disease'; column 'NPV (±2σ)'
Configuration: FATHMM-disease (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.51 precision fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-disease on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), E17; Algorithm 'FATHMM-disease'; column 'PPV (±2σ)'
Configuration: FATHMM-disease (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.63 recall fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-disease on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), C17; Algorithm 'FATHMM-disease'; column 'Sensitivity (±2σ)'
Configuration: FATHMM-disease (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.42 specificity fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-disease on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), D17; Algorithm 'FATHMM-disease'; column 'Specificity (±2σ)'
Configuration: FATHMM-MKL (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.6 accuracy fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-MKL on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), B11; Algorithm 'FATHMM-MKL'; column 'Accuracy (±2σ)'
Configuration: FATHMM-MKL (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.93 negative-predictive-value fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-MKL on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), F11; Algorithm 'FATHMM-MKL'; column 'NPV (±2σ)'
Configuration: FATHMM-MKL (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.56 precision fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-MKL on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), E11; Algorithm 'FATHMM-MKL'; column 'PPV (±2σ)'
Configuration: FATHMM-MKL (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.98 recall fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-MKL on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), C11; Algorithm 'FATHMM-MKL'; column 'Sensitivity (±2σ)'
Configuration: FATHMM-MKL (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.21 specificity fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-MKL on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), D11; Algorithm 'FATHMM-MKL'; column 'Specificity (±2σ)'
Configuration: FATHMM-XF (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.66 accuracy fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-XF on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), B4; Algorithm 'FATHMM-XF'; column 'Accuracy (±2σ)'
Configuration: FATHMM-XF (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.85 negative-predictive-value fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-XF on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), F4; Algorithm 'FATHMM-XF'; column 'NPV (±2σ)'
Configuration: FATHMM-XF (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.6 precision fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-XF on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), E4; Algorithm 'FATHMM-XF'; column 'PPV (±2σ)'
Configuration: FATHMM-XF (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.93 recall fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-XF on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), C4; Algorithm 'FATHMM-XF'; column 'Sensitivity (±2σ)'
Configuration: FATHMM-XF (Chen et al. 2020)	Protocol: OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020 Additional file 10) Dataset: OncoKB-annotated somatic missense mutations (oncogenic, likely oncogenic and likely neutral)	0.39 specificity fraction · higher Uncertainty: Not yet extracted: Printed as 'mean (lower-upper)' under the column header '(±2σ)': per Methods, the mean and two standard deviations over 100 random draws. That is not a confidence interval, and the schema's standard_deviation type would need a standard deviation derived from rounded bounds, so no structured uncertainty is recorded. The printed range is kept in printed_source_cell; every range is symmetric about the mean to rounding. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source FATHMM-XF on OncoKB benchmark (positive set not stated), default categorical calls (Chen et al. 2020) somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default Aggregation: Not reported Comprehensive assessment of computational algorithms in predicting cancer driver mutations; Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Additional file 10 (sheet 'Additional_file_10'), D4; Algorithm 'FATHMM-XF'; column 'Specificity (±2σ)'

Source checking is not independent reproduction. Release 2026-10-10-7fcc3e48a123.

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.

Author-reported evaluations: 1
External evaluations: 16

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 2026-10-10-7fcc3e48a123. 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 2026-10-10-7fcc3e48a123
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 2026-10-10-7fcc3e48a123 · Record review: source checked

3 source records and release history

Comprehensive assessment of computational algorithms in predicting cancer driver mutations · Original source · Genome Biology 21:43, published 2020-02-20; PMC7033911 full-text XML
Chen et al. 2020, Additional file 10: Performance metrics of 17 algorithms, default categories, benchmark 2 (OncoKB) · Original source · 13059_2020_1954_MOESM10_ESM.xlsx
Chen et al. 2020, Additional file 1: Default prediction categories of 17 algorithms · Original source · 13059_2020_1954_MOESM1_ESM.xlsx

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: somatic-oncogenicity-20261009-protocol-chen2020-oncokb-default

areas: dna-genomes
contexts: clinical_research
protocol: Binary predictions by default categorical calls (categories in Additional file 1) compared with the truth labels with reportROC; 400 positives and 400 negatives sampled 100 times; mean and two standard deviations reported.
version: Additional file 10
metric: accuracy
limitations: Binary metrics are means over 100 random draws of 400 positives and 400 negatives; the bracketed range is the mean plus or minus two standard deviations, not a confidence interval.; Predictor scores date from dbNSFP v4.0 and 2019 web servers; current releases (for example AlphaMissense, CHASMplus, BoostDM) are not included.; Only 17 algorithms provide default categories, mostly germline deleteriousness tools; cancer-specific tools other than CanDrA and FATHMM-disease are absent.; OncoKB annotations are biased towards known, often actionable cancer genes (Discussion).; Some predictors were trained on known cancer mutations, so performance on literature-curated drivers may be inflated.; The OncoKB set has 421 or 497 likely neutral negatives (Methods and Results disagree) and 400 are drawn per repeat, so the draws overlap heavily and the spread understates sampling uncertainty. Results and Methods also disagree on the positive counts, and which positive set fed the binary metrics is not stated.; Two authors (H. Liang, G.B. Mills) co-developed CanDrA (reference 7), and the cell viability labels come from the same group's assays; CanDrA rows are author_reported.
source locator: Additional file 10; Methods 'Calculation of five evaluation metrics based on categorical predictions'

Related records

Suggest a correction