rewirebio.iobenchmarks
Configuration

Fragmentia-AI WGS, high-TF-only fine-tuning

Fragmentia-AI WGS, high-TF-only fine-tuning: DNABERT-2 backbone with LoRA on Wqkv, gated-attention MIL pooling and MLP; high-TF-only fine-tuning on ichorCNA tumour-fraction strata of the training cohort.

2 evaluations · 5 results

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.

Model Capabilities & Hardware Requirements

Deployment facts recorded for Fragmentia-AI WGS, high-TF-only fine-tuning. Fields the record does not carry are marked not recorded.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessNot recorded
LicenseNot recorded

Evaluations and results

2 evaluations · 5 results. Different protocols are not a single leaderboard.

Sorted by AUROC (all cancers vs non-cancer) (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 configurationProtocol and datasetAUROC (all cancers vs non-cancer)AUROC (high-TF (> 5%) cancers vs non-cancer)AUROC (high-TF cancers vs non-cancer (training cohort contains only high-TF cancers for this scheme))AUROC (low-TF (< 3%) cancers vs non-cancer)AUROC (medium-TF (3-5%) cancers vs non-cancer)
Fragmentia-AI WGS, high-TF-only fine-tuningEvaluationFragmentia-AI WGS paper: Internal validation cohort by ichorCNA tumour fraction, Fragmentia-AI WGS internal validation cohort (2,043 samples, 0.1x ULP-WGS)0.7690.988Not reported0.6520.905
Fragmentia-AI WGS, high-TF-only fine-tuningEvaluationFragmentia-AI WGS paper: Training cohort (resubstitution), Fragmentia-AI WGS training cohort (3,695 samples, 0.1x ULP-WGS)Not reportedNot reported0.982Not reportedNot reported
All 5 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: Fragmentia-AI WGS, high-TF-only fine-tuningProtocol: Fragmentia-AI WGS paper: Training cohort (resubstitution)
Dataset: Fragmentia-AI WGS training cohort (3,695 samples, 0.1x ULP-WGS)
0.982 AUROC (high-TF cancers vs non-cancer (training cohort contains only high-TF cancers for this scheme))
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high-TF-only fine-tuning on the training cohort (resubstitution)

ctdnalit-20261011-fragmentiawgs2026-protocol-train

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P13, sentence 1
Configuration: Fragmentia-AI WGS, high-TF-only fine-tuningProtocol: Fragmentia-AI WGS paper: Internal validation cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS internal validation cohort (2,043 samples, 0.1x ULP-WGS)
0.988 AUROC (high-TF (> 5%) cancers vs non-cancer)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high-TF-only fine-tuning on the internal validation cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-validation

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P13, sentence 2
Configuration: Fragmentia-AI WGS, high-TF-only fine-tuningProtocol: Fragmentia-AI WGS paper: Internal validation cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS internal validation cohort (2,043 samples, 0.1x ULP-WGS)
0.652 AUROC (low-TF (< 3%) cancers vs non-cancer)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high-TF-only fine-tuning on the internal validation cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-validation

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P13, sentence 2
Configuration: Fragmentia-AI WGS, high-TF-only fine-tuningProtocol: Fragmentia-AI WGS paper: Internal validation cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS internal validation cohort (2,043 samples, 0.1x ULP-WGS)
0.905 AUROC (medium-TF (3-5%) cancers vs non-cancer)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high-TF-only fine-tuning on the internal validation cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-validation

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P13, sentence 2
Configuration: Fragmentia-AI WGS, high-TF-only fine-tuningProtocol: Fragmentia-AI WGS paper: Internal validation cohort by ichorCNA tumour fraction
Dataset: Fragmentia-AI WGS internal validation cohort (2,043 samples, 0.1x ULP-WGS)
0.769 AUROC (all cancers vs non-cancer)
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Fragmentia-AI WGS high-TF-only fine-tuning on the internal validation cohort by ichorcna tumour fraction

ctdnalit-20261011-fragmentiawgs2026-protocol-validation

Aggregation: Not reported

Generalizable cancer detection from ultra-low-pass WGS via deep contextual modeling of cfDNA sequences; Fragmentia-AI WGS paper, Supplementary Material 1 (Tables S1-S4, Figures S1-S9) · Results P13, sentence 2

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

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

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance

No evidence rows match these filters. Choose another scope or clear the search.

Sources and history

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

2 source records and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID ctdnalit-20261011-fragmentiawgs2026-config-high-tf.

Source locator: Results P8, P13-P14; Methods P47-P60

Related records

How to cite

Fragmentia-AI WGS, high-TF-only fine-tuning. Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/ctdnalit-20261011-fragmentiawgs2026-config-high-tf/

Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.

The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence

Suggest a correction