rewirebio.iobenchmarks
Source

A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML · Peer-reviewed

DOI: 10.1126/sciadv.ady9432

What this source contributed

Records in this release that cite this source. A record can cite several sources.

Results

Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.

Model or configurationMetricValueDatasetEvaluation
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Accuracy (cancers with all tumour fractions vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.536039320643375 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Accuracy (cancers with all tumour fractions vs healthy; threshold giving 95% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.646638225011025 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Accuracy (cancers with all tumour fractions vs healthy; threshold giving 98% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.652811439228354 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Accuracy (cancers with all tumour fractions vs healthy; threshold giving 99% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.634375944780108 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)AUPRC (cancers with all tumour fractions vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.866094229282759 unitlessUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)AUROC (cancers with all tumour fractions vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.642171723744025 unitlessUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)F1 (cancers with all tumour fractions vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.55202621082848 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)F1 (cancers with all tumour fractions vs healthy; threshold giving 95% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.538856450659316 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)F1 (cancers with all tumour fractions vs healthy; threshold giving 98% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.489962458316316 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)F1 (cancers with all tumour fractions vs healthy; threshold giving 99% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.417691736700955 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Precision (cancers with all tumour fractions vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.956247386598031 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Recall (cancers with all tumour fractions vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.38854678054388 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Sensitivity at 95% specificity (cancers with all tumour fractions vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.373866578876939 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Sensitivity at 98% specificity (cancers with all tumour fractions vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.327740701445065 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Sensitivity at 99% specificity (cancers with all tumour fractions vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.278751889560216 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Specificity (cancers with all tumour fractions vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.949356176091971 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, all tumour fractions
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Accuracy (cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.577107810189542 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction 0 to 0.03
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)AUPRC (cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.680211627867673 unitlessUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction 0 to 0.03
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)AUROC (cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.602893767061887 unitlessUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction 0 to 0.03
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)F1 (cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.631386059184135 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction 0 to 0.03
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Precision (cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.689961009427645 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction 0 to 0.03
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Recall (cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.582850046715552 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction 0 to 0.03
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Sensitivity at 95% specificity (cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.0576610584199779 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction 0 to 0.03
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Sensitivity at 98% specificity (cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.0220385056220232 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction 0 to 0.03
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Sensitivity at 99% specificity (cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.00445838533380332 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction 0 to 0.03
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Specificity (cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.568017064783447 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction 0 to 0.03
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Accuracy (cancers with ichorCNA tumour fraction above 0.1 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))1 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)AUPRC (cancers with ichorCNA tumour fraction above 0.1 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))1 unitlessUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)AUROC (cancers with ichorCNA tumour fraction above 0.1 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))1 unitlessUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)F1 (cancers with ichorCNA tumour fraction above 0.1 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))1 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Precision (cancers with ichorCNA tumour fraction above 0.1 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))1 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Recall (cancers with ichorCNA tumour fraction above 0.1 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))1 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Specificity (cancers with ichorCNA tumour fraction above 0.1 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))1 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Accuracy (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.906497767423801 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Accuracy (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; threshold giving 95% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.857240240218315 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Accuracy (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; threshold giving 98% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.78320751011292 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Accuracy (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; threshold giving 99% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.77500561235778 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)AUPRC (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.968101840031636 unitlessUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)AUROC (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.98326390488962 unitlessUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)F1 (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.860065940371046 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)F1 (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; threshold giving 95% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.853480374471083 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)F1 (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; threshold giving 98% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.724219409562381 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)F1 (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; threshold giving 99% specificity; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.692601030867619 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Precision (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.921731579923558 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Recall (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.807944328458772 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Sensitivity at 95% specificity (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.795750202162242 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Sensitivity at 98% specificity (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.587546671877492 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Sensitivity at 99% specificity (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.5605517652561 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026)Specificity (cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.961188465421524 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesichorCNA-TF logistic regression, ichorCNA tumour fraction above 0.03 to 0.1
UNITE XGBoost, 5' C/T motif ratio per bin (C/T) (Wang et al. 2026)Accuracy (cancers with all tumour fractions vs healthy; default classification threshold; mean of 50 outer test folds (5-fold cross-validation, 10 repeats))0.693943674019829 fractionUNITE cross-validation set: shallow WGS plasma cfDNA, 458 healthy and 1,232 cancer samplesUNITE XGBoost 5' C/T motif ratio per bin (C/T), all tumour fractions

Claims

Statements this source supports, each with where in the source it was checked.

  • Baseline: Select a plasma ctDNA fragmentomics detection workflow: Baseline ichorCNA (ctdnafrag-20261009-source-wang2026: Results (ichorCNA-TF comparator, tumour fraction as input to a logistic regression) and Fig. 4B (tumour-fraction strata))
  • Evidence summary: plasma ctDNA fragmentomics workflows: Summary Eight sources compare plasma cfDNA fragmentomic workflows on retrospective case-control cohorts. None is a prospective screening study and none measures clinical benefit. Cristiano et al. 2019, the DELFI developers, report 73% sensitivity (152 of 208 cancers) at a reported 98% specificity for DELFI in repeated cross-validation against 215 healthy individuals. Hou et al. 2024 re-implemented ten published fragmentation patterns and DELFI with one support vector machine each on the same cohort. They are independent of every pattern except IFS, which their corresponding author developed. In 10 x 10-fold cross-validation, pan-cancer AUC within open chromatin regions ranged from 0.8741 (fragment length) to 0.9736 (5' end motif), and their DELFI re-implementation reached 0.9575. Rankings changed on independent cohorts. On 46 lung cancers and 385 healthy individuals, with a model trained on 12 lung cancers, the end-motif model fell to AUC 0.5355 and sensitivity 0.0652 at 95% specificity, while fragment size distribution reached 0.9386 and 0.7174. Hou et al.'s supplementary pan-cancer and liver cancer sensitivities conflict with other tables of the same file and are not shown. Wang et al. 2026, the UNITE developers, stratified cancers by ichorCNA tumour fraction in pooled public and new 0.1x data that include samples of the DELFI and Jiang et al. cohorts used above. For cancers with an estimated tumour fraction of 3% or less, cross-validated AUC was 0.878 for all five features combined, 0.873 for fragment length, 0.857 for the SD of length counts, 0.736 for copy number, 0.715 for the C/T end-motif ratio and 0.651 for the short/long ratio, against 0.603 for a classifier using the ichorCNA tumour fraction alone, which detected 0.058 of these cancers at 95% specificity. For cancers with an estimated fraction above 3% and up to 10%, the ichorCNA classifier reached 0.983, above the combined model (0.962) and copy number alone (0.926). The extracted UNITE tables give sensitivity at a fixed specificity only for the ichorCNA comparator; the fragmentomic models' values are in a sheet not yet extracted. Jamshidi et al. 2022 (Cancer Cell), by the GRAIL developers, scored fragment length and fragment endpoint classifiers from 30x cfDNA whole-genome sequencing on the same CCGA substudy 1 participants as their methylation, copy-number and variant classifiers, at a 98% specificity threshold set post hoc within each set. On the validation set of 464 cancers and 362 non-cancers the fragment length classifier detected 29% (95% CI 25% to 34%) and the fragment endpoint classifier 18% (15% to 22%), against 34% for whole-genome methylation analysed double-blinded; both fragment classifiers were developed after the validation set had been unblinded, so these are not blinded validation results, and no tumour-fraction-stratified sensitivity is printed. Zeng et al. 2026 (Nature Cancer), by the cfMeDIP-seq developers, computed fragmentomic features from cfMeDIP-seq reads, which are enriched for methylated fragments rather than drawn from whole-genome sequencing, and report means over 10 fold models. On an independent paired-end validation set, a fragment-ratio classifier reached AUC 0.848 and detected 0.533 of cancers at 99% specificity, and fragment ratios combined with methylation reached 0.954 and 0.766. The validation set has 17 healthy controls, so its 99% specificity allows no false positive among them, and Li-Fraumeni syndrome carriers without current cancer count as cancers in its sensitivities. Three of the five classifiers that include end motifs scored below AUC 0.5 there, which the authors attribute to healthy controls processed with a different laboratory protocol, so validation results for all five are not shown. Helzer et al. 2025 (Nature Communications) compared twelve fragmentomic metrics adapted to targeted exon panels, including the authors' own fragment-size entropy metrics, their combination and Griffin, with one classifier and shared folds, on plasma from patients with metastatic cancer. The healthy-versus-cancer one-vs-rest AUROC ranged from 0.835 (open-chromatin entropy) to 0.989 (first-exon depth) in a UW cohort of 404 cancers and 27 healthy donors, with Griffin at 0.944, and from 0.951 to 1.000 in public GRAIL panel data from 151 cancers and 47 healthy donors. In a developer comparison on 0.1x whole-genome sequencing (Cell Reports Medicine 2026), a fragment-level language model (Fragmentia-AI) reached AUC 0.9561 on a held-out set of unstated size, against 0.9209 to 0.935 for the developers' re-implementation of DELFI features and 0.881 to 0.8863 for Griffin features under three classifiers. The same company's whole-genome model (Molecular Biomedicine 2026), on an independent test cohort of 2,952 cancers and 3,044 non-cancer controls, reached AUC 0.910 for cancers with an ichorCNA tumour fraction below 3% and detected 0.46 of them at a cutoff set to 98% specificity in training (observed test specificity 0.97); among those low-fraction cancers it detected 0.391 at stage I/II (637 of 1,628) and 0.708 at stage III/IV (345 of 487). Its tumour-fraction strata are ichorCNA estimates, no comparator was run on its cohorts, and its training cohort has the same number of non-cancer controls (1,245) as the Cell Reports Medicine cohort, so the two studies may share samples. Three of these four studies report on their authors' own method, and in the fourth the authors' own entropy metrics are among those compared. Cohorts, feature implementations, classifiers and validation designs differ, so no value is comparable across sources. (amp-20261007-ctdna-fragmentomics-source: result amp-20261007-ctdna-fragmentomics-result; ctdnafrag-20261009-source-hou2024: Table 1, P24 and P44; ctdnafrag-20261009-source-hou2024-supporting-information: Table S3; ctdnafrag-20261009-source-wang2026-data-file-s2: STATS_xgb_x1-x6 and STATS_lr; ctdnafrag-20261009-source-wang2026: Results and Methods; ctdnajam-20261010-source-jamshidi2022: Table 3 validation column and Results, cancer signal origin prediction; ctdnalit-20261011-zeng2026-source-article: Results P28-P33; ctdnalit-20261011-zeng2026-source-source-data-fig4: sheets Fig.4c and Fig.4d; ctdnalit-20261011-helzer2025-source-supplementary-information: Supplementary Tables S1 and S2, 'Normal' columns; ctdnalit-20261011-helzer2025-source-article: Results P5-P8; ctdnalit-20261011-fragmentia2026-source-document-s1: Table S5; ctdnalit-20261011-fragmentia2026-source-article: Results P39-P44; ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Tables S1 and S4)
  • ichorCNA tumour fraction with logistic regression (ichorCNA-TF, Wang et al. 2026): facets.method_types: Facets: method types ["supervised_machine_learning"] (Wang et al. 2026 Results: ichorCNA tumour fraction fed to a one-feature logistic regression (ichorCNA-TF))
  • ichorCNA: description: Description Copy-number-based tumour fraction estimation from ultra-low-pass WGS. (Record description; cited Adalsteinsson et al. 2017)
  • Relevance of ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-0-3pct to "Select a plasma ctDNA fragmentomics detection workflow": Assessed by UNITE cross-validation, cancers with ichorCNA tumour fraction 0 to 0.03 vs healthy (Wang et al. 2026) (ctdnafrag-20261009-source-wang2026: Results P9-P18; Methods P39-P49; ctdnafrag-20261009-source-wang2026-data-file-s2: Sheets STATS_xgb_x1-x6 and STATS_lr)
  • Relevance of ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-3-10pct to "Select a plasma ctDNA fragmentomics detection workflow": Assessed by UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.03 to 0.1 vs healthy (Wang et al. 2026) (ctdnafrag-20261009-source-wang2026: Results P9-P18; Methods P39-P49; ctdnafrag-20261009-source-wang2026-data-file-s2: Sheets STATS_xgb_x1-x6 and STATS_lr)
  • Relevance of ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all to "Select a plasma ctDNA fragmentomics detection workflow": Assessed by UNITE cross-validation, cancers with all tumour fractions vs healthy (Wang et al. 2026) (ctdnafrag-20261009-source-wang2026: Results P9-P18; Methods P39-P49; ctdnafrag-20261009-source-wang2026-data-file-s2: Sheets STATS_xgb_x1-x6 and STATS_lr)
  • Relevance of ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-over-10pct to "Select a plasma ctDNA fragmentomics detection workflow": Assessed by UNITE cross-validation, cancers with ichorCNA tumour fraction above 0.1 vs healthy (Wang et al. 2026) (ctdnafrag-20261009-source-wang2026: Results P9-P18; Methods P39-P49; ctdnafrag-20261009-source-wang2026-data-file-s2: Sheets STATS_xgb_x1-x6 and STATS_lr)
  • stratification: ctdnafrag-20261009-protocol-wang2026-unite-cv-tf-all: Stratification Healthy controls (n = 458) form one category; cancers are stratified by ichorCNA tumour fraction into [0, 0.03] (n = 736), (0.03, 0.1] (n = 239), (0.1, 0.2] (n = 121) and (0.2, 1] (n = 136). Models are trained and tested within each category; the [0, 0.03] category has 861 training samples (325 healthy, 536 cancer). (Results P9 and P12)

Models, benchmarks and other records

Methods (2)

Configurations (7)

Protocols (4)

Datasets (1)

Evaluations (28)

Use cases (1)

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.

20 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Archive note
gzip -n -9 copy of the exact bytes in artifacts/wang2026-article.xml.gz (CC BY 4.0)
Source metadata
A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Original source ↗

No field-specific location recorded

Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Retrieved: 2026-10-09T20:27:02Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.archive_note

Source artifact SHA-256: 61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Archive sha256
7ac25165b4eb001a58f41272aa4d5b706edbcf5d8df65cc6ca41753b29630713
Source metadata
A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Original source ↗

No field-specific location recorded

Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Retrieved: 2026-10-09T20:27:02Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.archive_sha256

Source artifact SHA-256: 61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Artifact SHA-256
61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23
Source metadata
A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Original source ↗

No field-specific location recorded

Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Retrieved: 2026-10-09T20:27:02Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.artifact_sha256

Source artifact SHA-256: 61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Artifact url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13353424/fullTextXML
Source metadata
A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Original source ↗

No field-specific location recorded

Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Retrieved: 2026-10-09T20:27:02Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.artifact_url

Source artifact SHA-256: 61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Doi
10.1126/sciadv.ady9432
Source metadata
A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Original source ↗

No field-specific location recorded

Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Retrieved: 2026-10-09T20:27:02Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.doi

Source artifact SHA-256: 61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Licence
CC-BY-4.0
Source metadata
A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Original source ↗

No field-specific location recorded

Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Retrieved: 2026-10-09T20:27:02Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.licence

Source artifact SHA-256: 61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Media type
application/xml
Source metadata
A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Original source ↗

No field-specific location recorded

Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Retrieved: 2026-10-09T20:27:02Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.media_type

Source artifact SHA-256: 61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Publication status
peer_reviewed
Source metadata
A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Original source ↗

No field-specific location recorded

Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Retrieved: 2026-10-09T20:27:02Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.publication_status

Source artifact SHA-256: 61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Retrieved at
2026-10-09T20:27:02Z
Source metadata
A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Original source ↗

No field-specific location recorded

Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Retrieved: 2026-10-09T20:27:02Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.retrieved_at

Source artifact SHA-256: 61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Source location
Full artifact bytes; per-result locators on each result
Source metadata
A scalable deep-learning framework for cancer detection using cell-free DNA shallow whole-genome sequencing

Original source ↗

No field-specific location recorded

Version: Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
Retrieved: 2026-10-09T20:27:02Z

catalogued

No individual claim review recorded

Audit details

Field: attributes.source_locator

Source artifact SHA-256: 61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

Primary source retrieved and hashed for the plasma ctDNA fragmentomics use-case pass.

Release history

No supporting source is linked yet.

Read original source

Download this release (gzip)
Technical metadata and extraction receipts

Stable ID: ctdnafrag-20261009-source-wang2026

areas
dna-genomes
contexts
clinical_research
url
https://doi.org/10.1126/sciadv.ady9432
artifact url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13353424/fullTextXML
version
Science Advances 12(28):eady9432, published 2026-07-10; PMC13353424 full-text XML
retrieved at
2026-10-09T20:27:02Z
artifact sha256
61464a274501bb9529b2250eb4c112071b8768fa640e87cf13f14d7df9f6fb23
doi
10.1126/sciadv.ady9432
publication status
peer_reviewed
licence
CC-BY-4.0
media type
application/xml
source locator
Full artifact bytes; per-result locators on each result
archive sha256
7ac25165b4eb001a58f41272aa4d5b706edbcf5d8df65cc6ca41753b29630713
archive note
gzip -n -9 copy of the exact bytes in artifacts/wang2026-article.xml.gz (CC BY 4.0)
Related records

    Suggest a correction