Configuration

UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)

Configuration as run in the cited comparison.

Overview

Configuration as run in the cited comparison.

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

Evaluations and results

4 evaluations · 24 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, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.599 accuracy fraction · higher Uncertainty: 95% CI 0.588936416184971 to 0.609600601559349. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct 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 37 (feat 'S/L', ichorcna_strat '[0, 0.03]', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.779 auprc unitless · higher Uncertainty: 95% CI 0.770845236401767 to 0.788018437449984. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct 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 33 (feat 'S/L', ichorcna_strat '[0, 0.03]', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.651 auroc unitless · higher Uncertainty: 95% CI 0.639452882852616 to 0.66268006619639. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct 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 32 (feat 'S/L', ichorcna_strat '[0, 0.03]', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.665 f1-score fraction · higher Uncertainty: 95% CI 0.653857626533397 to 0.676073921695134. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct 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 36 (feat 'S/L', ichorcna_strat '[0, 0.03]', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.644 recall fraction · higher Uncertainty: 95% CI 0.624997485019656 to 0.665046182529305. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct 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 34 (feat 'S/L', ichorcna_strat '[0, 0.03]', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.524 specificity fraction · higher Uncertainty: 95% CI 0.491459980253017 to 0.556257116511671. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction 0 to 0.03 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct 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 35 (feat 'S/L', ichorcna_strat '[0, 0.03]', .metric 'Specificity'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (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	0.78 accuracy fraction · higher Uncertainty: 95% CI 0.770290865851291 to 0.790428897301495. 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 Short/long fragment length ratio per bin (S/L), 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 73 (feat 'S/L', ichorcna_strat '(0.03, 0.1]', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (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	0.734 auprc unitless · higher Uncertainty: 95% CI 0.717503910055244 to 0.752180227311925. 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 Short/long fragment length ratio per bin (S/L), 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 69 (feat 'S/L', ichorcna_strat '(0.03, 0.1]', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (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	0.772 auroc unitless · higher Uncertainty: 95% CI 0.758037253730844 to 0.786418996254549. 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 Short/long fragment length ratio per bin (S/L), 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 68 (feat 'S/L', ichorcna_strat '(0.03, 0.1]', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (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	0.628 f1-score fraction · higher Uncertainty: 95% CI 0.609958933591513 to 0.646434670959473. 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 Short/long fragment length ratio per bin (S/L), 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 72 (feat 'S/L', ichorcna_strat '(0.03, 0.1]', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (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	0.521 recall fraction · higher Uncertainty: 95% CI 0.503599907990619 to 0.537957990970897. 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 Short/long fragment length ratio per bin (S/L), 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 70 (feat 'S/L', ichorcna_strat '(0.03, 0.1]', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (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	0.925 specificity fraction · higher Uncertainty: 95% CI 0.913963191967106 to 0.935602976434984. 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 Short/long fragment length ratio per bin (S/L), 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 71 (feat 'S/L', ichorcna_strat '(0.03, 0.1]', .metric 'Specificity'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.695 accuracy fraction · higher Uncertainty: 95% CI 0.685500131790761 to 0.702742635153258. 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 Short/long fragment length ratio per bin (S/L), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all 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 145 (feat 'S/L', ichorcna_strat 'all', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.9 auprc unitless · higher Uncertainty: 95% CI 0.896517651120383 to 0.903433551853159. 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 Short/long fragment length ratio per bin (S/L), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all 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 141 (feat 'S/L', ichorcna_strat 'all', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions 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 0.733382581932454 to 0.746581827836438. 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 Short/long fragment length ratio per bin (S/L), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all 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 140 (feat 'S/L', ichorcna_strat 'all', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.784 f1-score fraction · higher Uncertainty: 95% CI 0.774068056280059 to 0.793857101116504. 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 Short/long fragment length ratio per bin (S/L), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all 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 144 (feat 'S/L', ichorcna_strat 'all', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.762 recall fraction · higher Uncertainty: 95% CI 0.737755735909812 to 0.782526402064997. 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 Short/long fragment length ratio per bin (S/L), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all 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 142 (feat 'S/L', ichorcna_strat 'all', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.504 specificity fraction · higher Uncertainty: 95% CI 0.468317537885931 to 0.540242353080225. 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 Short/long fragment length ratio per bin (S/L), all tumour fractions ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all 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 143 (feat 'S/L', ichorcna_strat 'all', .metric 'Specificity'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.882 accuracy fraction · higher Uncertainty: 95% CI 0.87457155078618 to 0.889512156077573. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-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 109 (feat 'S/L', ichorcna_strat '(0.1, 1]', .metric 'Accuracy'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.905 auprc unitless · higher Uncertainty: 95% CI 0.897210766625781 to 0.912892976095422. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-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 105 (feat 'S/L', ichorcna_strat '(0.1, 1]', .metric 'AUPRC'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.917 auroc unitless · higher Uncertainty: 95% CI 0.910033026038962 to 0.924257173344146. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-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 104 (feat 'S/L', ichorcna_strat '(0.1, 1]', .metric 'AUROC'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.827 f1-score fraction · higher Uncertainty: 95% CI 0.817014756484173 to 0.836986028337798. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-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 108 (feat 'S/L', ichorcna_strat '(0.1, 1]', .metric 'F1'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.752 recall fraction · higher Uncertainty: 95% CI 0.736980891575468 to 0.769126936276715. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-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 106 (feat 'S/L', ichorcna_strat '(0.1, 1]', .metric 'Sensitivity'), column D 'mean'
Configuration: UNITE XGBoost, Short/long fragment length ratio per bin (S/L) (Wang et al. 2026)	Protocol: UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) Dataset: UNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samples	0.96 specificity fraction · higher Uncertainty: 95% CI 0.952653159010798 to 0.967482664471341. 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 Short/long fragment length ratio per bin (S/L), ichorCNA tumour fraction above 0.1 ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-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 107 (feat 'S/L', ichorcna_strat '(0.1, 1]', .metric 'Specificity'), column D 'mean'

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

Use this model

How it works, versions and access

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-config-wang2026-unite-xgb-sl

areas: dna-genomes
contexts: clinical_research
method types: supervised_machine_learning
reported name: S/L
foundation model eligible: false
source locator: Data file S2 sheet STATS_xgb_x1-x6 column 'feat'; Methods P49
missing metadata: version: reason: unreported; note: No UNITE release or code commit is printed for these cross-validation models
parameters: Features: Short/long fragment length ratio per bin (S/L). XGBoost with nested cross-validation (StratifiedGroupKFold, randomized grid search); keras v3.3.3 and scikit-learn v1.4.2.

Related records

Suggest a correction