Dataset

SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)

Cancer cases of the SPOT-MAS discovery cohort used for tissue-of-origin classification.

Research readiness

These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.

Release 2026-10-09-8cc1db47c7f9 · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
metric replay: verification is missing

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
metric replay: verification is missing
annotations: verification is missing
dependence: verification is missing

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
recipe pinned: verification is missing
resource estimate: verification is missing

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
independent validation: verification is missing
overlap checked: verification is missing

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Read reviewed discrepancy investigations

Evaluation results

3 evaluations · 66 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: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.62 accuracy fraction · higher Uncertainty: Not reported by the source Coverage: 499 cancer patients scored (n printed in cell B10)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', D10; Discovery block; row 'All cancer'; column 'DNN' under 'All stage' (n in B10)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.67 recall fraction · higher Uncertainty: Not reported by the source Coverage: 156 cancer patients scored (n printed in cell B5)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', D5; Discovery block; row 'Breast'; column 'DNN' under 'All stage' (n in B5)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.54 recall fraction · higher Uncertainty: Not reported by the source Coverage: 106 cancer patients scored (n printed in cell B6)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', D6; Discovery block; row 'CRC'; column 'DNN' under 'All stage' (n in B6)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.65 recall fraction · higher Uncertainty: Not reported by the source Coverage: 11 cancer patients scored (n printed in cell F6)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', H6; Discovery block; row 'CRC'; column 'DNN' under 'Stage I' (n in F6)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.66 recall fraction · higher Uncertainty: Not reported by the source Coverage: 41 cancer patients scored (n printed in cell J6)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', L6; Discovery block; row 'CRC'; column 'DNN' under 'Stage II' (n in J6)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.44 recall fraction · higher Uncertainty: Not reported by the source Coverage: 41 cancer patients scored (n printed in cell N6)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', P6; Discovery block; row 'CRC'; column 'DNN' under 'Stage III' (n in N6)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.53 recall fraction · higher Uncertainty: Not reported by the source Coverage: 13 cancer patients scored (n printed in cell R6)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', T6; Discovery block; row 'CRC'; column 'DNN' under 'Non-metastasis with unknown stage' (n in R6)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.45 recall fraction · higher Uncertainty: Not reported by the source Coverage: 67 cancer patients scored (n printed in cell B7)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', D7; Discovery block; row 'Gastric'; column 'DNN' under 'All stage' (n in B7)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.5 recall fraction · higher Uncertainty: Not reported by the source Coverage: 4 cancer patients scored (n printed in cell F7)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', H7; Discovery block; row 'Gastric'; column 'DNN' under 'Stage I' (n in F7)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.75 recall fraction · higher Uncertainty: Not reported by the source Coverage: 12 cancer patients scored (n printed in cell J7)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', L7; Discovery block; row 'Gastric'; column 'DNN' under 'Stage II' (n in J7)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.43 recall fraction · higher Uncertainty: Not reported by the source Coverage: 23 cancer patients scored (n printed in cell N7)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', P7; Discovery block; row 'Gastric'; column 'DNN' under 'Stage III' (n in N7)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.5 recall fraction · higher Uncertainty: Not reported by the source Coverage: 28 cancer patients scored (n printed in cell R7)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', T7; Discovery block; row 'Gastric'; column 'DNN' under 'Non-metastasis with unknown stage' (n in R7)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.79 recall fraction · higher Uncertainty: Not reported by the source Coverage: 77 cancer patients scored (n printed in cell B8)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', D8; Discovery block; row 'Liver'; column 'DNN' under 'All stage' (n in B8)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	1 recall fraction · higher Uncertainty: Not reported by the source Coverage: 4 cancer patients scored (n printed in cell F8)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', H8; Discovery block; row 'Liver'; column 'DNN' under 'Stage I' (n in F8)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.79 recall fraction · higher Uncertainty: Not reported by the source Coverage: 21 cancer patients scored (n printed in cell J8)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', L8; Discovery block; row 'Liver'; column 'DNN' under 'Stage II' (n in J8)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	1 recall fraction · higher Uncertainty: Not reported by the source Coverage: 12 cancer patients scored (n printed in cell N8)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', P8; Discovery block; row 'Liver'; column 'DNN' under 'Stage III' (n in N8)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	1 recall fraction · higher Uncertainty: Not reported by the source Coverage: 40 cancer patients scored (n printed in cell R8)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', T8; Discovery block; row 'Liver'; column 'DNN' under 'Non-metastasis with unknown stage' (n in R8)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.67 recall fraction · higher Uncertainty: Not reported by the source Coverage: 93 cancer patients scored (n printed in cell B9)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', D9; Discovery block; row 'Lung'; column 'DNN' under 'All stage' (n in B9)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.5 recall fraction · higher Uncertainty: Not reported by the source Coverage: 2 cancer patients scored (n printed in cell F9)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', H9; Discovery block; row 'Lung'; column 'DNN' under 'Stage I' (n in F9)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.45 recall fraction · higher Uncertainty: Not reported by the source Coverage: 11 cancer patients scored (n printed in cell J9)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', L9; Discovery block; row 'Lung'; column 'DNN' under 'Stage II' (n in J9)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.57 recall fraction · higher Uncertainty: Not reported by the source Coverage: 47 cancer patients scored (n printed in cell N9)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', P9; Discovery block; row 'Lung'; column 'DNN' under 'Stage III' (n in N9)
Configuration: SPOT-MAS tissue-of-origin Deep neural network (DNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.5 recall fraction · higher Uncertainty: Not reported by the source Coverage: 33 cancer patients scored (n printed in cell R9)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, DNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', T9; Discovery block; row 'Lung'; column 'DNN' under 'Non-metastasis with unknown stage' (n in R9)
Configuration: SPOT-MAS tissue-of-origin Graph convolutional neural network (GCNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.73 accuracy fraction · higher Uncertainty: Not reported by the source Coverage: 499 cancer patients scored (n printed in cell B10)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, GCNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', E10; Discovery block; row 'All cancer'; column 'GCNN' under 'All stage' (n in B10)
Configuration: SPOT-MAS tissue-of-origin Graph convolutional neural network (GCNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.87 recall fraction · higher Uncertainty: Not reported by the source Coverage: 156 cancer patients scored (n printed in cell B5)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, GCNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', E5; Discovery block; row 'Breast'; column 'GCNN' under 'All stage' (n in B5)
Configuration: SPOT-MAS tissue-of-origin Graph convolutional neural network (GCNN)	Protocol: SPOT-MAS five-class tissue of origin, discovery cohort 10-fold cross-validation Dataset: SPOT-MAS discovery cohort, 499 non-metastatic cancer patients (five cancer types)	0.71 recall fraction · higher Uncertainty: Not reported by the source Coverage: 106 cancer patients scored (n printed in cell B6)	Author-reported evaluation · Source checked Methods, coverage and source SPOT-MAS tissue of origin, GCNN (discovery) ctdnameth-20261009-protocol-nguyen2023-spotmas-too-discovery-cv Aggregation: Not reported Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization; Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Supplementary file 1, sheet 'Table S9', E6; Discovery block; row 'CRC'; column 'GCNN' under 'All stage' (n in B6)

Source checking is not independent reproduction. Release 2026-10-09-8cc1db47c7f9.

Dataset and evaluation context

A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.

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.

16 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-09-8cc1db47c7f9
Property and statement	Original source and location	Review and provenance
attributes.assay SPOT-MAS: one plasma cfDNA bisulfite library; 450-region target capture (~52x) and shallow genome-wide fraction (~0.55x) Context-only references	Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization Original source ↗ Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: eLife 12:RP89083, version of record published 2023-10-11; PMC10567114 full-text XML Retrieved: 2026-10-09T20:04:09Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.assay` Source artifact SHA-256: `e09cfb58a6055e89ffa7b553a37539e1687f0fcb26970b7b25eb9eda8e09cfa8` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.assay SPOT-MAS: one plasma cfDNA bisulfite library; 450-region target capture (~52x) and shallow genome-wide fraction (~0.55x) Context-only references	Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) Original source ↗ Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplementary file 1 (elife-89083-supp1.xlsx) of eLife 12:RP89083, PMC open-access copy PMC10567114.1 Retrieved: 2026-10-09T20:03:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.assay` Source artifact SHA-256: `4797d7ea0fde127bfa54cf0bdf717d859092c0442ab996a0af10cc5ce17b7331` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.population 499 treatment-naive non-metastatic patients: 156 breast, 106 colorectal, 67 gastric, 77 liver, 93 lung; recruited in Vietnam Context-only references	Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization Original source ↗ Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: eLife 12:RP89083, version of record published 2023-10-11; PMC10567114 full-text XML Retrieved: 2026-10-09T20:04:09Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.population` Source artifact SHA-256: `e09cfb58a6055e89ffa7b553a37539e1687f0fcb26970b7b25eb9eda8e09cfa8` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.population 499 treatment-naive non-metastatic patients: 156 breast, 106 colorectal, 67 gastric, 77 liver, 93 lung; recruited in Vietnam Context-only references	Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) Original source ↗ Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplementary file 1 (elife-89083-supp1.xlsx) of eLife 12:RP89083, PMC open-access copy PMC10567114.1 Retrieved: 2026-10-09T20:03:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.population` Source artifact SHA-256: `4797d7ea0fde127bfa54cf0bdf717d859092c0442ab996a0af10cc5ce17b7331` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.source_locator Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Context-only references	Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization Original source ↗ Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: eLife 12:RP89083, version of record published 2023-10-11; PMC10567114 full-text XML Retrieved: 2026-10-09T20:04:09Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.source_locator` Source artifact SHA-256: `e09cfb58a6055e89ffa7b553a37539e1687f0fcb26970b7b25eb9eda8e09cfa8` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.source_locator Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Context-only references	Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) Original source ↗ Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplementary file 1 (elife-89083-supp1.xlsx) of eLife 12:RP89083, PMC open-access copy PMC10567114.1 Retrieved: 2026-10-09T20:03:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.source_locator` Source artifact SHA-256: `4797d7ea0fde127bfa54cf0bdf717d859092c0442ab996a0af10cc5ce17b7331` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.split 10-fold cross-validation within the discovery cohort Context-only references	Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization Original source ↗ Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: eLife 12:RP89083, version of record published 2023-10-11; PMC10567114 full-text XML Retrieved: 2026-10-09T20:04:09Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.split` Source artifact SHA-256: `e09cfb58a6055e89ffa7b553a37539e1687f0fcb26970b7b25eb9eda8e09cfa8` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.split 10-fold cross-validation within the discovery cohort Context-only references	Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) Original source ↗ Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplementary file 1 (elife-89083-supp1.xlsx) of eLife 12:RP89083, PMC open-access copy PMC10567114.1 Retrieved: 2026-10-09T20:03:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.split` Source artifact SHA-256: `4797d7ea0fde127bfa54cf0bdf717d859092c0442ab996a0af10cc5ce17b7331` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.total 499 Context-only references	Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization Original source ↗ Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: eLife 12:RP89083, version of record published 2023-10-11; PMC10567114 full-text XML Retrieved: 2026-10-09T20:04:09Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.total` Source artifact SHA-256: `e09cfb58a6055e89ffa7b553a37539e1687f0fcb26970b7b25eb9eda8e09cfa8` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.total 499 Context-only references	Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) Original source ↗ Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplementary file 1 (elife-89083-supp1.xlsx) of eLife 12:RP89083, PMC open-access copy PMC10567114.1 Retrieved: 2026-10-09T20:03:58Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.total` Source artifact SHA-256: `4797d7ea0fde127bfa54cf0bdf717d859092c0442ab996a0af10cc5ce17b7331` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-09-8cc1db47c7f9 · Record review: source checked

2 source records and release history

Multimodal analysis of methylomics and fragmentomics in plasma cell-free DNA for multi-cancer early detection and localization · Original source · eLife 12:RP89083, version of record published 2023-10-11; PMC10567114 full-text XML
Nguyen et al. 2023, Supplementary file 1 (Tables S1-S11) · Original source · Supplementary file 1 (elife-89083-supp1.xlsx) of eLife 12:RP89083, PMC open-access copy PMC10567114.1

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: ctdnameth-20261009-data-nguyen2023-spotmas-discovery-cancers

areas: dna-genomes
contexts: clinical_research
version: eLife 12:RP89083 (2023)
population: 499 treatment-naive non-metastatic patients: 156 breast, 106 colorectal, 67 gastric, 77 liver, 93 lung; recruited in Vietnam
split: 10-fold cross-validation within the discovery cohort
total: 499
assay: SPOT-MAS: one plasma cfDNA bisulfite library; 450-region target capture (~52x) and shallow genome-wide fraction (~0.55x)
source locator: Article Results 'Clinical characteristics' (P6-P7), 'The multimodal SPOT-MAS assay' (P9); Table 1; Supplementary file 1 Table S9

Related records

Suggest a correction