Relevance of ctdnalit-20261011-fragmentiawgs2026-protocol-validation to "Which fragmentomics workflow detects tumour-derived plasma DNA under realistic low tumour fractions and fixed false-positive constraints?"
- Use case
- Select a plasma ctDNA fragmentomics detection workflow
- Assessed by
- Fragmentia-AI WGS paper: Internal validation cohort by ichorCNA tumour fraction
- Relevance
- Proxy evidence
- Endpoint
- AUC overall and within ichorCNA tumour-fraction strata for three fine-tuning schemes of one fragment-level model, plus sensitivity at the training-derived 98%-specificity cutoff
Shows how a fragmentomic model's discrimination changes in low ichorCNA tumour fraction and how training on low-TF samples changes it. Proxy: one developer model, AUC rather than fixed-specificity sensitivity within strata (except Table S4), and the cohort was used for model selection.
3 reviewed evaluations
- Fragmentia-AI WGS high/medium/low-TF sequential fine-tuning (final model) on the internal validation cohort by ichorcna tumour fraction
- Fragmentia-AI WGS high/medium-TF sequential fine-tuning on the internal validation cohort by ichorcna tumour fraction
- Fragmentia-AI WGS high-TF-only fine-tuning on the internal validation cohort by ichorcna tumour fraction
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.
40 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
Citation locations2 values
| Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Molecular Biomedicine, published online 2026-08-12; Europe PMC full-text JATS XML of PMC13469060 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Citation locations2 values
| Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 43556_2026_538_MOESM1_ESM.docx, publisher supplementary file | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Comparison group fragmentiawgs2026-tf-strata Context-only references | Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Molecular Biomedicine, published online 2026-08-12; Europe PMC full-text JATS XML of PMC13469060 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Comparison group fragmentiawgs2026-tf-strata Context-only references | Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 43556_2026_538_MOESM1_ESM.docx, publisher supplementary file | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Comparison title Fragmentia-AI WGS by ichorCNA tumour fraction (Molecular Biomedicine 2026) Context-only references | Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Molecular Biomedicine, published online 2026-08-12; Europe PMC full-text JATS XML of PMC13469060 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Comparison title Fragmentia-AI WGS by ichorCNA tumour fraction (Molecular Biomedicine 2026) Context-only references | Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 43556_2026_538_MOESM1_ESM.docx, publisher supplementary file | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Constraints3 values
| Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Molecular Biomedicine, published online 2026-08-12; Europe PMC full-text JATS XML of PMC13469060 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Constraints3 values
| Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 43556_2026_538_MOESM1_ESM.docx, publisher supplementary file | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Endpoint AUC overall and within ichorCNA tumour-fraction strata for three fine-tuning schemes of one fragment-level model, plus sensitivity at the training-derived 98%-specificity cutoff Context-only references | Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Molecular Biomedicine, published online 2026-08-12; Europe PMC full-text JATS XML of PMC13469060 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Endpoint AUC overall and within ichorCNA tumour-fraction strata for three fine-tuning schemes of one fragment-level model, plus sensitivity at the training-derived 98%-specificity cutoff Context-only references | Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 43556_2026_538_MOESM1_ESM.docx, publisher supplementary file | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
2 source records and release history
- Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences · Original source · Molecular Biomedicine, published online 2026-08-12; Europe PMC full-text JATS XML of PMC13469060
- Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Original source · 43556_2026_538_MOESM1_ESM.docx, publisher supplementary file
Technical metadata and extraction receipts
Stable ID: use-case-mapping-ctdna-lit-20261011-fragmentiawgs2026-validation
- field
- links:assessed_by:ctdnalit-20261011-fragmentiawgs2026-protocol-validation
- value
- ctdnalit-20261011-fragmentiawgs2026-protocol-validation
- relevance
- proxy
- endpoint
- AUC overall and within ichorCNA tumour-fraction strata for three fine-tuning schemes of one fragment-level model, plus sensitivity at the training-derived 98%-specificity cutoff
- rationale
- Shows how a fragmentomic model's discrimination changes in low ichorCNA tumour fraction and how training on low-TF samples changes it. Proxy: one developer model, AUC rather than fixed-specificity sensitivity within strata (except Table S4), and the cohort was used for model selection.
- constraints
- Inspect every linked evaluation's source locator and preserved limitations before citing a result.; Tumour-fraction strata are ichorCNA estimates; do not read them as measured ctDNA fractions.; Do not combine with other protocols' results; cohorts, depth and thresholds differ.
- limitations
- Developer study: Geneseeq employees collected and sequenced the cohorts, developed the model and report every value.; Tumour-fraction strata are ichorCNA estimates, not measured fractions; the authors chose the 3% cutoff because the ichorCNA study reported 0.03 as its lower limit for detecting tumour from ULP-WGS (Results P8), so the low stratum holds cancers whose tumour fraction ichorCNA cannot resolve.; Retrospective case-control cohorts of clinically diagnosed cancers and non-cancer controls; not a screening population.; The cutoff is set at 98% specificity in the training cohort and applied unchanged; observed specificity in other cohorts differs (0.97 in the test cohort, 0.92 in the DELFI cohort).; No comparator method is evaluated on these cohorts; only Fragmentia-AI configurations are compared.; Used for hyperparameter optimisation and model selection, so not an independent test.; The training cohort has 1,245 non-cancer controls, the same number as the ULP-WGS cohort of the Fragmentia-AI paper (Cell Reports Medicine 2026) from the same company, so the two studies may share samples; neither paper says.
- citation locators
- source id: ctdnalit-20261011-fragmentiawgs2026-source-article; locator: Results P8-P21; Methods P40-P60; source id: ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1; locator: Table S4
- source locator
- ctdnalit-20261011-fragmentiawgs2026-source-article: Results P8-P21; Methods P40-P60; ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1: Table S4
- revision
- 1
- reason
- Add the tumour-fraction-stratified results of Fragmentia-AI WGS (Molecular Biomedicine 2026), retrieved 2026-10-11. Independently reviewed in docs/reviews/use-cases/plasma-ctdna-use-cases-2026-10-12.md.
- comparison group
- fragmentiawgs2026-tf-strata
- comparison title
- Fragmentia-AI WGS by ichorCNA tumour fraction (Molecular Biomedicine 2026)
- headline metric
- auroc
- stratum label
- Internal validation cohort (model selection)
- stratum order
- 1
- review
- method: source-hash-verification; independent-cell-check; scope-review; reviewer: claude; reviewer note: Separate Claude review agent (reviewer-ctdna), independent of the extractor uc-ctdna; no human review claimed; date: 2026-10-12; note: Re-downloaded the pinned artifacts and matched their SHA-256; read Table S4 from the DOCX table XML with a separate reader written for this review (the extractor's script was not run) and checked each sensitivity against detected/total; compared the text values with Results P13, P14, P19 and P21.
- reviewed evaluations
- ctdnalit-20261011-fragmentiawgs2026-eval-validation-high-medium-low-tf; ctdnalit-20261011-fragmentiawgs2026-eval-validation-high-medium-tf; ctdnalit-20261011-fragmentiawgs2026-eval-validation-high-tf
- pins
- record id: ctdnalit-20261011-fragmentiawgs2026-eval-validation-high-medium-low-tf; fields: status; links; attributes.origin; attributes.comparison; sha256: 530b16b1183c0c14fe53735b18d0fb4645f4cef7474e3631339934e7c6de20dd; record id: ctdnalit-20261011-fragmentiawgs2026-eval-validation-high-medium-tf; fields: status; links; attributes.origin; attributes.comparison; sha256: 93294947775eacd3ec8065eced26011608e9ad2576596e8f8d86571da69086c4; record id: ctdnalit-20261011-fragmentiawgs2026-eval-validation-high-tf; fields: status; links; attributes.origin; attributes.comparison; sha256: 663ba3c55bbba9c9c8ddfc97a8ff6d5fb9eec89245efd9cb54a5d8015f28ed8b; record id: ctdnalit-20261011-fragmentiawgs2026-protocol-validation; fields: status; name; description; facets; source_ids; links; attributes; sha256: 3001b9b79897d21a0c5040f00fbe08c33ae700232552e596cf95abf7674cf956; record id: ctdnalit-20261011-fragmentiawgs2026-result-validation-high-medium-low-tf-auroc-low-tf; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 0fd7800c4a08bd6813df9f1ecc8f922d743b77e65e25f20feac7cd89e463842e; record id: ctdnalit-20261011-fragmentiawgs2026-result-validation-high-medium-low-tf-auroc-overall; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 569ad6865dbca2aaf05ff574a443f79671128eefee8d1e78cf282df3c3b70d17; record id: ctdnalit-20261011-fragmentiawgs2026-result-validation-high-medium-low-tf-sensitivity-cutoff; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 23cd5f57479ad548fb528cb1cee99d804c33a6ebf65094745dfac423be24b8fb; record id: ctdnalit-20261011-fragmentiawgs2026-result-validation-high-medium-low-tf-sensitivity-cutoff-low-tf-stage-i-ii; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 128943331fb695a7754a1f53c8d326a65b1e06ebd6c40ca7aa194d819c1c7080; record id: ctdnalit-20261011-fragmentiawgs2026-result-validation-high-medium-low-tf-sensitivity-cutoff-low-tf-stage-iii-iv; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 1460158e7609afdbe7c2c7074909c39117f553298fb369ca6d8d59dd40186388; record id: ctdnalit-20261011-fragmentiawgs2026-result-validation-high-medium-tf-auroc-low-tf; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: c0760ec8ac2a0bcaf5d2b1a8595901e9377d5e40e0935e90f223fceca0c2f1df; record id: ctdnalit-20261011-fragmentiawgs2026-result-validation-high-tf-auroc-high-tf; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 8482a8f1d2916cfc536e13d16f8695dda413c93d5c395326cc67fc92402613c6; record id: ctdnalit-20261011-fragmentiawgs2026-result-validation-high-tf-auroc-low-tf; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 5a4b3ee5f7b1c4581440c248ebe1e96e3a91acd4534627f0804e8c1304171e58; record id: ctdnalit-20261011-fragmentiawgs2026-result-validation-high-tf-auroc-medium-tf; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 5fc40d229c4b17c5219f0315de551d400760325c406c65bde17372b2b9d69f12; record id: ctdnalit-20261011-fragmentiawgs2026-result-validation-high-tf-auroc-overall; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 4802ef65ba64b48a7218611d443e6641eba302156c02de90d76a724a6da75ef0; record id: ctdnalit-20261011-fragmentiawgs2026-source-article; fields: status; attributes.artifact_sha256; sha256: c85207569268327bf692a01933c1db48952db3dbf3f66773c05fa2ee2fdfa4af; record id: ctdnalit-20261011-fragmentiawgs2026-source-supplementary-material-1; fields: status; attributes.artifact_sha256; sha256: 526f24376cdd6ae19db68d4b144f15032588f79a52e102dcdffd45bbf36f8b05; record id: use-case-plasma-ctdna-fragmentomics; fields: status; name; description; facets; attributes.question; attributes.decision; attributes.inputs; attributes.output; attributes.exclusions; attributes.setting; attributes.clinical_scope; attributes.intended_users; sha256: 01d27c2ce64a391055bddc6dec9d5db208df9bee3d5e679045dd3f4f04a0ca08