Zeng et al. 2026 SE 10% hold-out set: cancer vs healthy
Fold models from the SE training set applied to the 39-sample hold-out set of the same study.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
3 recorded evaluations, 6 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
3 evaluations · 6 results. Different protocols are not a single leaderboard.
Protocol: Zeng et al. 2026 SE 10% hold-out set: cancer vs healthy · Dataset: Zeng et al. 2026 single-end 10% hold-out set (39 samples)
Sorted by AUROC (cancer vs healthy, SE 10% hold-out set, mean over 10 fold models) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
| Tested configuration | AUROC (cancer vs healthy, SE 10% hold-out set, mean over 10 fold models) | Sensitivity at 99% specificity (cancer vs healthy, SE 10% hold-out set, mean over 10 fold models) |
|---|---|---|
| Zeng et al. 2026 classifier: Combined Motif + Methylation (1%)Evaluation | 0.986 (best in column) | 0.93 (best in column) |
| Zeng et al. 2026 classifier: End MotifsEvaluation | 0.983 | 0.893 |
| Zeng et al. 2026 classifier: MethylationEvaluation | 0.921 | 0.727 |
All 6 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Zeng et al. 2026 classifier: End Motifs | Protocol: Zeng et al. 2026 SE 10% hold-out set: cancer vs healthy Dataset: Zeng et al. 2026 single-end 10% hold-out set (39 samples) | 0.983 AUROC (cancer vs healthy, SE 10% hold-out set, mean over 10 fold models) unitless · higher Uncertainty: SD 0.005. Figure 4 legend: error bars in a, c, e and g are ±1 s.d. across cross-validation folds (n = 10). Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEnd Motifs on se validation (Zeng et al. 2026) ctdnalit-20261011-zeng2026-protocol-se-validation Aggregation: Not reported A pan-cancer compendium of 1,294 plasma cell-free DNA methylomes and fragmentomes enabling multicancer detection; Zeng et al. 2026, Source Data Fig. 4 (classifier AUC and sensitivity summaries) · Source Data Fig. 4, sheet Fig.4g, row 3 'End Motifs', column B 'mean_auc' |
| Configuration: Zeng et al. 2026 classifier: End Motifs | Protocol: Zeng et al. 2026 SE 10% hold-out set: cancer vs healthy Dataset: Zeng et al. 2026 single-end 10% hold-out set (39 samples) | 0.893 Sensitivity at 99% specificity (cancer vs healthy, SE 10% hold-out set, mean over 10 fold models) fraction · higher Uncertainty: ± 0.0344265186329548 (type not stated). Source Data columns are headed sd_sens99 and the sheets' text column prints 'Sensitivity=x ± y'; the Figure 4 legend says the error bars in panels b, d, f and h are s.e. Methods P61 says error bars denote across-fold s.d. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceEnd Motifs on se validation (Zeng et al. 2026) ctdnalit-20261011-zeng2026-protocol-se-validation Aggregation: Not reported A pan-cancer compendium of 1,294 plasma cell-free DNA methylomes and fragmentomes enabling multicancer detection; Zeng et al. 2026, Source Data Fig. 4 (classifier AUC and sensitivity summaries) · Source Data Fig. 4, sheet Fig.4h, row 3 'End Motifs', column B 'mean_sens99' |
| Configuration: Zeng et al. 2026 classifier: Methylation | Protocol: Zeng et al. 2026 SE 10% hold-out set: cancer vs healthy Dataset: Zeng et al. 2026 single-end 10% hold-out set (39 samples) | 0.921 AUROC (cancer vs healthy, SE 10% hold-out set, mean over 10 fold models) unitless · higher Uncertainty: SD 0.019. Figure 4 legend: error bars in a, c, e and g are ±1 s.d. across cross-validation folds (n = 10). Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMethylation on se validation (Zeng et al. 2026) ctdnalit-20261011-zeng2026-protocol-se-validation Aggregation: Not reported A pan-cancer compendium of 1,294 plasma cell-free DNA methylomes and fragmentomes enabling multicancer detection; Zeng et al. 2026, Source Data Fig. 4 (classifier AUC and sensitivity summaries) · Source Data Fig. 4, sheet Fig.4g, row 4 'Methylation', column B 'mean_auc' |
| Configuration: Zeng et al. 2026 classifier: Methylation | Protocol: Zeng et al. 2026 SE 10% hold-out set: cancer vs healthy Dataset: Zeng et al. 2026 single-end 10% hold-out set (39 samples) | 0.727 Sensitivity at 99% specificity (cancer vs healthy, SE 10% hold-out set, mean over 10 fold models) fraction · higher Uncertainty: ± 0.230213813660258 (type not stated). Source Data columns are headed sd_sens99 and the sheets' text column prints 'Sensitivity=x ± y'; the Figure 4 legend says the error bars in panels b, d, f and h are s.e. Methods P61 says error bars denote across-fold s.d. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMethylation on se validation (Zeng et al. 2026) ctdnalit-20261011-zeng2026-protocol-se-validation Aggregation: Not reported A pan-cancer compendium of 1,294 plasma cell-free DNA methylomes and fragmentomes enabling multicancer detection; Zeng et al. 2026, Source Data Fig. 4 (classifier AUC and sensitivity summaries) · Source Data Fig. 4, sheet Fig.4h, row 4 'Methylation', column B 'mean_sens99' |
| Configuration: Zeng et al. 2026 classifier: Combined Motif + Methylation (1%) | Protocol: Zeng et al. 2026 SE 10% hold-out set: cancer vs healthy Dataset: Zeng et al. 2026 single-end 10% hold-out set (39 samples) | 0.986 AUROC (cancer vs healthy, SE 10% hold-out set, mean over 10 fold models) unitless · higher Uncertainty: SD 0.007. Figure 4 legend: error bars in a, c, e and g are ±1 s.d. across cross-validation folds (n = 10). Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCombined Motif + Methylation (1%) on se validation (Zeng et al. 2026) ctdnalit-20261011-zeng2026-protocol-se-validation Aggregation: Not reported A pan-cancer compendium of 1,294 plasma cell-free DNA methylomes and fragmentomes enabling multicancer detection; Zeng et al. 2026, Source Data Fig. 4 (classifier AUC and sensitivity summaries) · Source Data Fig. 4, sheet Fig.4g, row 2 'Combined Motif + Methylation (1%)', column B 'mean_auc' |
| Configuration: Zeng et al. 2026 classifier: Combined Motif + Methylation (1%) | Protocol: Zeng et al. 2026 SE 10% hold-out set: cancer vs healthy Dataset: Zeng et al. 2026 single-end 10% hold-out set (39 samples) | 0.93 Sensitivity at 99% specificity (cancer vs healthy, SE 10% hold-out set, mean over 10 fold models) fraction · higher Uncertainty: ± 0.0399072999912621 (type not stated). Source Data columns are headed sd_sens99 and the sheets' text column prints 'Sensitivity=x ± y'; the Figure 4 legend says the error bars in panels b, d, f and h are s.e. Methods P61 says error bars denote across-fold s.d. Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCombined Motif + Methylation (1%) on se validation (Zeng et al. 2026) ctdnalit-20261011-zeng2026-protocol-se-validation Aggregation: Not reported A pan-cancer compendium of 1,294 plasma cell-free DNA methylomes and fragmentomes enabling multicancer detection; Zeng et al. 2026, Source Data Fig. 4 (classifier AUC and sensitivity summaries) · Source Data Fig. 4, sheet Fig.4h, row 2 'Combined Motif + Methylation (1%)', column B 'mean_sens99' |
Source checking is not independent reproduction. Release 2026-11-21-adc15377fab2.
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
- 3
Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.
Null control
Proposed control: requires review
Select a task-valid null control after reviewing inputs and metric
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Conventional reference
Proposed control: requires review
Select an upstream conventional reference after reviewing the full protocol
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)
Coverage is derived from release 2026-11-21-adc15377fab2. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.
Run instructions
No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-21-adc15377fab2 · Record review: source checked
2 source records and release history
- A pan-cancer compendium of 1,294 plasma cell-free DNA methylomes and fragmentomes enabling multicancer detection · Original source · Nature Cancer, published online 2026-02-19; Europe PMC full-text JATS XML of PMC12948677
- Zeng et al. 2026, Source Data Fig. 4 (classifier AUC and sensitivity summaries) · Original source · 43018_2026_1116_MOESM6_ESM.xlsx (Source Data Fig. 4), publisher supplementary file
Technical metadata and record identifiers
Technical metadata for this record is tracked under stable ID ctdnalit-20261011-zeng2026-protocol-se-validation.
Source locator: Results P33; Fig. 4g-h legend; Extended Data Fig. 10e legend; Methods P60
Related records
- uses data: Zeng et al. 2026 single-end 10% hold-out set (39 samples)
- assessment: End Motifs on se validation (Zeng et al. 2026)
- assessment: Methylation on se validation (Zeng et al. 2026)
- assessment: Combined Motif + Methylation (1%) on se validation (Zeng et al. 2026)
- assessed by: Select a plasma ctDNA methylation detection workflow