Protocol

Feng C.Elegans 4mC sequence classification

Table 3 sequence classification; Feng et al. 2025 source-reported protocol.

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.

5 recorded evaluations, 5 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

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

Protocol: Feng C.Elegans 4mC sequence classification · Dataset: Feng C.Elegans 4mC dataset

Sorted by AUROC (task: c.elegans 4mc) (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 (task: c.elegans 4mc)
NT-v2 (C.Elegans 4mC classification)Evaluation	0.649 (best in column)
GROVER (C.Elegans 4mC classification)Evaluation	0.606
DNABERT-2 (C.Elegans 4mC classification)Evaluation	0.599
Caduceus-Ph (C.Elegans 4mC classification)Evaluation	0.596
HyenaDNA (C.Elegans 4mC classification)Evaluation	0.596

All 5 result rows with coverage, uncertainty and sources

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: Caduceus-Ph (C.Elegans 4mC classification)	Protocol: Feng C.Elegans 4mC sequence classification Dataset: Feng C.Elegans 4mC dataset	0.596 AUROC (task: c.elegans 4mc) unitless · higher Uncertainty: Not reported by the source: Table 3 prints point AUCs only. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus-Ph C.Elegans 4mC evaluation Table 3, frozen embeddings + task-specific random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, row 'C.Elegans 4mC', column 'Caduceus-Ph'.
Configuration: DNABERT-2 (C.Elegans 4mC classification)	Protocol: Feng C.Elegans 4mC sequence classification Dataset: Feng C.Elegans 4mC dataset	0.599 AUROC (task: c.elegans 4mc) unitless · higher Uncertainty: Not reported by the source: Table 3 prints point AUCs only. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2 C.Elegans 4mC evaluation Table 3, frozen embeddings + task-specific random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, row 'C.Elegans 4mC', column 'DNABERT-2'.
Configuration: GROVER (C.Elegans 4mC classification)	Protocol: Feng C.Elegans 4mC sequence classification Dataset: Feng C.Elegans 4mC dataset	0.606 AUROC (task: c.elegans 4mc) unitless · higher Uncertainty: Not reported by the source: Table 3 prints point AUCs only. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GROVER C.Elegans 4mC evaluation Table 3, frozen embeddings + task-specific random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, row 'C.Elegans 4mC', column 'GROVER'. Printed in bold (table footnote: 'Bolded: higher than at least two other AUCs, p < 0.01.').
Configuration: HyenaDNA (C.Elegans 4mC classification)	Protocol: Feng C.Elegans 4mC sequence classification Dataset: Feng C.Elegans 4mC dataset	0.596 AUROC (task: c.elegans 4mc) unitless · higher Uncertainty: Not reported by the source: Table 3 prints point AUCs only. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HyenaDNA C.Elegans 4mC evaluation Table 3, frozen embeddings + task-specific random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, row 'C.Elegans 4mC', column 'HyenaDNA'.
Configuration: NT-v2 (C.Elegans 4mC classification)	Protocol: Feng C.Elegans 4mC sequence classification Dataset: Feng C.Elegans 4mC dataset	0.649 AUROC (task: c.elegans 4mc) unitless · higher Uncertainty: Not reported by the source: Table 3 prints point AUCs only. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT-v2 C.Elegans 4mC evaluation Table 3, frozen embeddings + task-specific random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, row 'C.Elegans 4mC', column 'NT-v2'. Printed in bold (table footnote: 'Bolded: higher than at least two other AUCs, p < 0.01.').

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

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.

External evaluations: 5

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Training-set class prior where supervised fitting is permitted

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

Regularised classifier on simple permitted features, or protocol's conventional reference

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 2026-11-02-a7f03c9e55a5. 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

Claims, original sources and review scope · Release 2026-11-02-a7f03c9e55a5
Property and statement	Original source and location	Review and provenance

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

How to read the evidence

Sources and history

Release 2026-11-02-a7f03c9e55a5 · Record review: source checked

2 source records and release history

Benchmarking DNA foundation models for genomic and genetic tasks · Original source · PMC12663285.1
Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Data 1-6 · Original source · Nature Communications 16, 10780 (2025); Supplementary Data 1-6 workbook (MOESM3, .xlsm)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: feng-dna-fm-20261014-protocol-t3-c-elegans-4mc

areas: dna-genomes
contexts: research
scope note: Frozen last-layer mean token embeddings from each pretrained model, scored by a supervised random forest classifier fitted for this exact task (not label-free prediction). Original predefined split retained where clearly defined; otherwise a random 70:30 train/test split. DNABERT-2/NT-v2 benchmark datasets are re-split 70:30 keeping class proportions. Random forest hyperparameters tuned by fivefold cross-validation. No whole-chromosome holdout (Methods, 'Sequence classification benchmark').
task: C.Elegans 4mC sequence classification (AUC)
version: Table 3
metric: auroc
metric direction: higher
comparison limit: Within-row comparison only: rows differ in source dataset, species, sequence length and split.

Related records

subject: reported_finding: feng-dna-fm-20261014-protocol-t3-c-elegans-4mc
assessment: Caduceus-Ph C.Elegans 4mC evaluation
assessment: DNABERT-2 C.Elegans 4mC evaluation
assessment: GROVER C.Elegans 4mC evaluation
assessment: HyenaDNA C.Elegans 4mC evaluation
assessment: NT-v2 C.Elegans 4mC evaluation

Suggest a correction