Protocol

UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026)

Tumour-fraction-stratified cross-validation of fragmentomic feature sets and an ichorCNA tumour-fraction classifier.

Overview

Tumour-fraction-stratified cross-validation of fragmentomic feature sets and an ichorCNA tumour-fraction classifier.

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

7 recorded evaluations, 52 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

7 evaluations · 52 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: UNITE XGBoost, All five feature types (UNITE-XGB, model X6) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.922 accuracy fraction · higher Uncertainty: 95% CI 0.915937876140555 to 0.927509270044652. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost All five feature types (UNITE-XGB, model X6), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 43 (feat 'All', ichorcna_strat '(0.03, 0.1]', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, All five feature types (UNITE-XGB, model X6) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.952 auprc unitless · higher Uncertainty: 95% CI 0.946540275378965 to 0.957277248648428. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost All five feature types (UNITE-XGB, model X6), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 39 (feat 'All', ichorcna_strat '(0.03, 0.1]', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, All five feature types (UNITE-XGB, model X6) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.962 auroc unitless · higher Uncertainty: 95% CI 0.956864305379267 to 0.965835559427218. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost All five feature types (UNITE-XGB, model X6), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 38 (feat 'All', ichorcna_strat '(0.03, 0.1]', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, All five feature types (UNITE-XGB, model X6) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.886 f1-score fraction · higher Uncertainty: 95% CI 0.876606186107664 to 0.894600007080721. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost All five feature types (UNITE-XGB, model X6), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 42 (feat 'All', ichorcna_strat '(0.03, 0.1]', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, All five feature types (UNITE-XGB, model X6) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.85 recall fraction · higher Uncertainty: 95% CI 0.835385112660256 to 0.863737766561006. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost All five feature types (UNITE-XGB, model X6), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 40 (feat 'All', ichorcna_strat '(0.03, 0.1]', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, All five feature types (UNITE-XGB, model X6) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.962 specificity fraction · higher Uncertainty: 95% CI 0.956435237452299 to 0.968120572709345. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost All five feature types (UNITE-XGB, model X6), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 41 (feat 'All', ichorcna_strat '(0.03, 0.1]', .metric 'Specificity'), column D 'mean'
Configuration: UNITE XGBoost, Copy number aberration (CNA) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.875 accuracy fraction · higher Uncertainty: 95% CI 0.868668219763153 to 0.881448456610367. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost Copy number aberration (CNA), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 61 (feat 'CNV', ichorcna_strat '(0.03, 0.1]', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, Copy number aberration (CNA) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.914 auprc unitless · higher Uncertainty: 95% CI 0.908229150984468 to 0.918791814512549. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost Copy number aberration (CNA), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 57 (feat 'CNV', ichorcna_strat '(0.03, 0.1]', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, Copy number aberration (CNA) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.926 auroc unitless · higher Uncertainty: 95% CI 0.919865039293221 to 0.931556862075475. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost Copy number aberration (CNA), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 56 (feat 'CNV', ichorcna_strat '(0.03, 0.1]', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, Copy number aberration (CNA) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.81 f1-score fraction · higher Uncertainty: 95% CI 0.800700064201192 to 0.820051042068867. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost Copy number aberration (CNA), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 60 (feat 'CNV', ichorcna_strat '(0.03, 0.1]', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, Copy number aberration (CNA) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.748 recall fraction · higher Uncertainty: 95% CI 0.734597960409929 to 0.760801330723526. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost Copy number aberration (CNA), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 58 (feat 'CNV', ichorcna_strat '(0.03, 0.1]', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, Copy number aberration (CNA) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.946 specificity fraction · higher Uncertainty: 95% CI 0.938072044858814 to 0.952421746765391. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost Copy number aberration (CNA), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 59 (feat 'CNV', ichorcna_strat '(0.03, 0.1]', .metric 'Specificity'), column D 'mean'
Configuration: UNITE XGBoost, 5' C/T motif ratio per bin (C/T) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.725 accuracy fraction · higher Uncertainty: 95% CI 0.717657590759076 to 0.731485633857503. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost 5' C/T motif ratio per bin (C/T), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 67 (feat 'C/T', ichorcna_strat '(0.03, 0.1]', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, 5' C/T motif ratio per bin (C/T) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.676 auprc unitless · higher Uncertainty: 95% CI 0.662511511954401 to 0.687286467204416. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost 5' C/T motif ratio per bin (C/T), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 63 (feat 'C/T', ichorcna_strat '(0.03, 0.1]', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, 5' C/T motif ratio per bin (C/T) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.74 auroc unitless · higher Uncertainty: 95% CI 0.729750718606295 to 0.749105498448642. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost 5' C/T motif ratio per bin (C/T), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 62 (feat 'C/T', ichorcna_strat '(0.03, 0.1]', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, 5' C/T motif ratio per bin (C/T) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.586 f1-score fraction · higher Uncertainty: 95% CI 0.573653996289792 to 0.598196337482905. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost 5' C/T motif ratio per bin (C/T), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 66 (feat 'C/T', ichorcna_strat '(0.03, 0.1]', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, 5' C/T motif ratio per bin (C/T) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.551 recall fraction · higher Uncertainty: 95% CI 0.530124005366327 to 0.571378052986039. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost 5' C/T motif ratio per bin (C/T), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 64 (feat 'C/T', ichorcna_strat '(0.03, 0.1]', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, 5' C/T motif ratio per bin (C/T) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.822 specificity fraction · higher Uncertainty: 95% CI 0.809713939029489 to 0.834367044365908. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source UNITE XGBoost 5' C/T motif ratio per bin (C/T), ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_xgb_x1-x6, row 65 (feat 'C/T', ichorcna_strat '(0.03, 0.1]', .metric 'Specificity'), column D 'mean'
Configuration: ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.906 accuracy fraction · higher Uncertainty: 95% CI 0.901168608037274 to 0.911965346534653. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_lr, row 18 (feat 'TF', ichorcna_strat '(0.03, 0.1]', .metric 'test_acc'), column D 'mean'
Configuration: ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.857 accuracy fraction · higher Uncertainty: 95% CI 0.840986286415509 to 0.874067454143898. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_lr, row 19 (feat 'TF', ichorcna_strat '(0.03, 0.1]', .metric 'test_acc_95spe'), column D 'mean'
Configuration: ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.783 accuracy fraction · higher Uncertainty: 95% CI 0.761618480803836 to 0.802350492447195. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_lr, row 20 (feat 'TF', ichorcna_strat '(0.03, 0.1]', .metric 'test_acc_98spe'), column D 'mean'
Configuration: ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.775 accuracy fraction · higher Uncertainty: 95% CI 0.745475789378343 to 0.801318966255286. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_lr, row 21 (feat 'TF', ichorcna_strat '(0.03, 0.1]', .metric 'test_acc_99spe'), column D 'mean'
Configuration: ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.968 auprc unitless · higher Uncertainty: 95% CI 0.964339913255639 to 0.97206783946288. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_lr, row 22 (feat 'TF', ichorcna_strat '(0.03, 0.1]', .metric 'test_auprc'), column D 'mean'
Configuration: ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.983 auroc unitless · higher Uncertainty: 95% CI 0.981274508337164 to 0.985414433343808. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_lr, row 23 (feat 'TF', ichorcna_strat '(0.03, 0.1]', .metric 'test_auroc'), column D 'mean'
Configuration: ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.86 f1-score fraction · higher Uncertainty: 95% CI 0.851397137423632 to 0.869246999831996. Interval over the 50 outer test folds as printed in columns G and H Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct Aggregation: Not reported A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing; Wang et al. 2026, Data file S2 (model scores and summary statistics) · Data file S2 sheet STATS_lr, row 24 (feat 'TF', ichorcna_strat '(0.03, 0.1]', .metric 'test_f1'), column D 'mean'

Source checking is not independent reproduction. Release 2026-10-09-ba02f2f4a36e.

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.

Author-reported evaluations: 6
External evaluations: 1

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

Null control

Proposed control: requires review

Training-set class prior where supervised fitting is permitted

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

Regularised classifier on simple permitted features, or protocol's conventional reference

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 2026-10-09-ba02f2f4a36e. 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 2026-10-09-ba02f2f4a36e
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 2026-10-09-ba02f2f4a36e · Record review: source checked

2 source records and release history

A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing · Original source · Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Wang et al. 2026, Data file S2 (model scores and summary statistics) · Original source · ady9432_data_file_s2.xlsx inside sciadv.ady9432_data_files_s1_and_s2.zip, PMC open-access copy PMC13353424.1

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct

areas: dna-genomes
contexts: clinical_research
protocol: Restrict cancer samples to those with ichorCNA tumour fraction above 0.03 to 0.1 (healthy controls unchanged), train each model in nested cross-validation (5 outer folds, 10 repeats, StratifiedGroupKFold so no patient is in both training and test folds) and summarise each metric over the 50 outer test folds.
version: Wang et al. 2026 Data file S2 sheets STATS_xgb_x1-x6 and STATS_lr; Methods P47, P49
metric: auroc
metric direction: higher
limitations: Cross-validation within one pooled set of public and new data; not the held-out or unseen test sets.; Tumour fraction strata are defined by ichorCNA, which is also the input of the ichorCNA-TF comparator.; Author-reported by the UNITE developers; the DELFI-XGB comparator is reported only in text and figures.; All strata share the same healthy controls (325 in the cross-validation set); only the cancers change.; The cross-validation set draws 352 samples from the Cristiano et al. 2019 (DELFI) FinaleDB data and 86 from the Jiang et al. FinaleDB liver data, the cohorts of the Hou et al. evaluations and the DELFI judgement.
source locator: Data file S2 rows with ichorcna_strat '(0.03, 0.1]'; Results P12-P13, P18; Methods P47, P49

Related records

Suggest a correction