AUROC (task: promoter all 70 bps) of DNABERT-2 (Promoter All 70 bps classification) on Feng Promoter All 70 bps dataset
0.831 AUROC (task: promoter all 70 bps)
Methods
- Tested configuration
- DNABERT-2 (Promoter All 70 bps classification)
- Protocol
- Feng Promoter All 70 bps sequence classification
- Dataset
- Feng Promoter All 70 bps dataset
- Procedure
- Table 1, frozen embeddings + task-specific random forest classifier
- Evaluation
- DNABERT-2 Promoter All 70 bps evaluation
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not reported by the source: Table 1 prints point AUCs only.
- Evidence
- Independent external evaluation · source checkedBenchmarking DNA foundation models for genomic and genetic tasks · Table 1, row 'Promoter All 70 bps', column 'DNABERT-2'.
A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.
Reproduction
- Split
- 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 unless the source states an exception. Random forest hyperparameters tuned by fivefold cross-validation. No whole-chromosome holdout (Methods). Supplementary Data 6: 41437 training and 17759 test sequences.
- Adaptation
- Frozen pretrained representation plus a supervised random-forest classifier head fitted for this exact task
- Scoring implementation
- Not reported
No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.
Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.
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.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 0.8311 Individual claims | Benchmarking DNA foundation models for genomic and genetic tasks Table 1, row 'Promoter All 70 bps', column 'DNABERT-2'. Version: PMC12663285.1 | source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-13T14:40:00Z independent paper Audit detailsExtracted by extract/extract_feng.py (deterministic parse of the XML table cells). Independent review: value, metric and identity match the source. Field: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. Extraction artifact SHA-256: |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
1 source record and release history
Download this release (gzip)Technical metadata and extraction receipts
Stable ID: feng-dna-fm-20261013-result-t1-promoter-all-70-bps-dnabert-2-auc
- metric
- auroc
- metric direction
- higher
- unit
- unitless
- printed value
- 0.8311
- numeric value
- 0.8311
- metric qualifier
- task: promoter all 70 bps
- source locator
- Table 1, row 'Promoter All 70 bps', column 'DNABERT-2'.
- missing metadata
- uncertainty: reason: unreported; note: Table 1 prints point AUCs only.
- review
- method: source-hash-verification; deterministic-table-parse; independent-cell-check; method note: Re-downloaded the Europe PMC XML and matched the pinned SHA-256. Parsed Tables 1 and 4 with a separate ElementTree parser (review/signoff.py) and checked printed value, numeric value, metric, qualifier, unit, direction, locator (including bold marking) and the linked configuration and protocol.; reviewer: claude; reviewer note: Independent Claude (Opus 5.5) review agent, separate from the extraction agent feng-19 that built this batch. Automated review only; no human review claimed. Transcription, not reproduction.; reviewed at: 2026-10-13T14:40:00Z; artifact sha256: 5d8ca9bcf88cc1b38ad667906a2e4699b1aefa6d31c6f49259784930353f3202; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12663285/fullTextXML; note: Extracted by extract/extract_feng.py (deterministic parse of the XML table cells). Independent review: value, metric and identity match the source.
Related records
- evaluation: DNABERT-2 Promoter All 70 bps evaluation