An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation
medRxiv version 1, posted 2026-07-29 · Preprint
DOI: 10.64898/2026.07.26.26358979
Two authors (University of Southern California; MicroTrace BioAI, Inc.) who did not develop CpGPT. They fine-tuned the published CpGPT Cancer-100M checkpoint and built the classical baselines themselves. Not peer reviewed.
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.
Claims
Statements this source supports, each with where in the source it was checked.
- Evidence summary: plasma ctDNA methylation detection workflows: Summary Six bounded sources compare cfDNA methylation methods. None is a prospective screening study and none measures clinical benefit. Jamshidi et al. 2022 (Cancer Cell), by the GRAIL developers, compared prototype cfDNA classifiers on the same CCGA substudy 1 participants at a 98% specificity threshold set post hoc within each set. On the validation set of 464 cancers and 362 non-cancers, analysed double-blinded, the whole-genome bisulfite methylation classifier detected 34% of cancers (95% CI 30% to 39%; 158 of 464), against 33% for variants with white-blood-cell correction, 30% for copy number with that correction, 27% for copy number, 16% for uncorrected variants and 2.6% for clinical risk factors alone; only the gap to the corrected variant classifier was not marked as significant. Among 127 validation cancers detected by all three representative classifiers, a methylation origin classifier developed after unblinding assigned the correct tissue for 75% (95 of 127), against 41% for copy number and 35% for corrected variants, with 'other' counted as correct for six cancer types. These are case-control results from the assay developer, not screening performance. Sun et al. 2024 (Genome Biology), an independent benchmark whose authors did not develop the tools, deconvolved real plasma with five methods and reported the ROC-AUC of a random forest trained on the estimated cell-type fractions; the paper does not state how the random forest was validated, so the AUCs may be in-sample. For 24 liver cancer patients and 32 healthy individuals (WGBS), AUCs were 0.96 (CelFEER), 0.93 (CelFiE), 0.91 (MethAtlas), 0.77 (cfNOMe) and 0.72 (UXM). On cfMethyl-Seq plasma (30 to 67 patients per cancer type, each against the same 193 healthy individuals), AUCs ranged from 0.72 (UXM, lung squamous cell carcinoma) to 0.93 (CelFiE, gastric cancer), and no method was highest for every cancer type. Giuili et al. 2025, a bioRxiv preprint not yet peer reviewed, ran ten reference-based tools inside the authors' DecoNFlow pipeline on in silico mixtures of tumour tissue or cell-line reads in healthy plasma reads. CelFiE had the lowest overall median tumour-fraction limit of detection in each dataset: 0.0070 (WGBS-TT), 0.0100 (RRBS-TT) and 0.0010 (RRBS-CL). CIBERSORT and EpiDISH had overall medians of 0.1000 to 0.2500 on WGBS-TT and RRBS-TT. For five tools the RRBS-CL values disagree between the supplementary table and Figure 4A and are not shown. Nguyen et al. 2023 (eLife), by the developers of the SPOT-MAS assay at Gene Solutions, compared three tissue-of-origin classifiers on combined methylation, fragment-length, copy-number and end-motif features from cancer patients only. In the validation cohort of 239 patients, overall accuracy was 0.53 (random forest), 0.69 (deep neural network) and 0.69 (graph convolutional network); the graph network was trained with the validation samples in its graph. Zeng et al. 2026 (Nature Cancer), by the cfMeDIP-seq developers, compared a cfMeDIP-seq methylation classifier with fragmentomic features of the same reads and their combinations, reporting means over 10 fold models. In cross-validation on 356 cancers and 64 healthy donors, methylation alone reached AUC 0.986 and detected 0.949 of cancers at 99% specificity; on an independent validation set its sensitivity at 99% specificity was 0.633, against 0.766 for methylation combined with fragment ratios. These sensitivities are read on few healthy controls (six or seven per cross-validation fold and 17 in the validation set), so 99% specificity there allows no false positive among them, and Li-Fraumeni syndrome carriers without current cancer count as cancers in the validation sensitivities. The Source Data give the methylation-only validation AUC as 0.694 and the text as 0.674, so that value is not shown. Xu and Feng 2026, a medRxiv preprint not yet peer reviewed, by authors who did not develop CpGPT, fine-tuned the CpGPT methylation foundation model on public targeted bisulfite cfDNA data from 254 gastrointestinal cancers and 46 non-cancer controls and built four classical classifiers themselves. On three train/validation/test splits with test partitions of about 30 samples, mean test AUROC was 0.9904 for CpGPT against 0.9573 (SVM), 0.9420 (elastic net), 0.8460 (gradient boosting) and 0.8408 (random forest); the candidate CpGs were selected using all 300 samples, including the test partitions. Neither study reports performance in a screening population. Tissue-of-origin evidence here comes from two developer studies, one methylation-only classifier scored on already detected cancers and one multimodal workflow, and neither classifies people without cancer. (ctdnameth-20261009-source-sun2024-additional-file-1: Table S7 I4:M4, M8, J9; ctdnameth-20261009-source-sun2024: Methods P30; ctdnameth-20261009-source-giuili2025-supp-table-3: sheet B B3:D4, B7:C7; ctdnameth-20261009-source-nguyen2023-supp-file-1: Table S9 B19:E19; 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.4a-Fig.4d; ctdnalit-20261011-cpgpt2026-source-preprint: Table 3; Methods; Results)
- Relevance of ctdnalit-20261011-cpgpt2026-protocol-dmr-informed-split-runs to "Which measured methylation workflow detects tumour-derived plasma DNA and, where separately supported, identifies tissue of origin?": Assessed by Xu and Feng 2026: GI cancer vs non-cancer on GSE149438, three train-validation-test split-runs, DMR-informed CpG features (ctdnalit-20261011-cpgpt2026-source-preprint: Table 3; Methods; Results)
Models, benchmarks and other records
Methods (2)
Configurations (5)
Protocols (1)
Datasets (1)
Evaluations (5)
- CpGPT on GSE149438 DMR-informed split-runs (Xu and Feng 2026)
- Elastic Net on GSE149438 DMR-informed split-runs (Xu and Feng 2026)
- GBM on GSE149438 DMR-informed split-runs (Xu and Feng 2026)
- Random Forest on GSE149438 DMR-informed split-runs (Xu and Feng 2026)
- SVM radial on GSE149438 DMR-informed split-runs (Xu and Feng 2026)
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.
22 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Archive note Not archived: no reuse licence. The artifact_sha256 pins the bytes that were read. Source metadata | An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation No field-specific location recorded Version: medRxiv version 1, posted 2026-07-29 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. |
| Artifact SHA-256 369746bfe0117866d294e01f49c6ffbfc2d177e347872030d6233e2e7366961e Source metadata | An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation No field-specific location recorded Version: medRxiv version 1, posted 2026-07-29 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. |
| Artifact url https://www.medrxiv.org/content/10.64898/2026.07.26.26358979v1.full.pdf Source metadata | An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation No field-specific location recorded Version: medRxiv version 1, posted 2026-07-29 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. |
| Doi 10.64898/2026.07.26.26358979 Source metadata | An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation No field-specific location recorded Version: medRxiv version 1, posted 2026-07-29 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. |
| Extraction method pdftotext -layout (poppler 26.08.0) text layer, parsed by extract/extract_cpgpt2026.py Source metadata | An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation No field-specific location recorded Version: medRxiv version 1, posted 2026-07-29 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. |
| Hash scope artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. Source metadata | An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation No field-specific location recorded Version: medRxiv version 1, posted 2026-07-29 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. |
| Licence All rights reserved; no reuse without permission (medRxiv display licence) Source metadata | An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation No field-specific location recorded Version: medRxiv version 1, posted 2026-07-29 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. |
| Media type application/pdf Source metadata | An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation No field-specific location recorded Version: medRxiv version 1, posted 2026-07-29 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. |
| Publication status preprint Source metadata | An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation No field-specific location recorded Version: medRxiv version 1, posted 2026-07-29 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. |
| Retrieved at 2026-10-11T21:49:59Z Source metadata | An Evaluation of DMR-Informed Fine-Tuning of Tissue Array-Pretrained CpGPT for Gastrointestinal Cancer Classification Using cfDNA Targeted Methylation No field-specific location recorded Version: medRxiv version 1, posted 2026-07-29 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving. |
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
Primary source retrieved and hashed for the 2026-10-11 plasma ctDNA literature pass.
Technical metadata and extraction receipts
Stable ID: ctdnalit-20261011-cpgpt2026-source-preprint
- areas
- dna-genomes
- contexts
- clinical_research
- url
- https://doi.org/10.64898/2026.07.26.26358979
- artifact url
- https://www.medrxiv.org/content/10.64898/2026.07.26.26358979v1.full.pdf
- version
- medRxiv version 1, posted 2026-07-29
- retrieved at
- 2026-10-11T21:49:59Z
- artifact sha256
- 369746bfe0117866d294e01f49c6ffbfc2d177e347872030d6233e2e7366961e
- doi
- 10.64898/2026.07.26.26358979
- publication status
- preprint
- licence
- All rights reserved; no reuse without permission (medRxiv display licence)
- media type
- application/pdf
- source locator
- Full artifact bytes; per-record locators on each record
- archive note
- Not archived: no reuse licence. The artifact_sha256 pins the bytes that were read.
- hash scope
- artifact_sha256 describes one retrieval (2026-10-11T21:49:59Z). medRxiv regenerates this PDF: a reviewer download on 2026-10-12 had 2,761,577 bytes, SHA-256 3d37b32e8ff782201ed8ee6677a01808d4f8c86eea70350a530dde7306cab7c9 and PDF CreationDate 2026-10-11T20:08:12-07:00. The reviewer's copy's text layer matched every extracted value. The licence does not allow archiving.
- extraction method
- pdftotext -layout (poppler 26.08.0) text layer, parsed by extract/extract_cpgpt2026.py
- scope note
- Two authors (University of Southern California; MicroTrace BioAI, Inc.) who did not develop CpGPT. They fine-tuned the published CpGPT Cancer-100M checkpoint and built the classical baselines themselves. Not peer reviewed.