AUROC (ClinVar pathogenic vs benign SNVs, 5' UTR) of DNABERT-2 117M, CLS embedding L2 distance (Lu et al. 2025) on Lu et al. 2025 ClinVar benchmark: 5' UTR (Figure 1)
0.414 AUROC (ClinVar pathogenic vs benign SNVs, 5' UTR)
Methods
- Tested configuration
- DNABERT-2 117M, CLS embedding L2 distance (Lu et al. 2025)
- Protocol
- ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)
- Dataset subset
- Lu et al. 2025 ClinVar benchmark: 5' UTR (Figure 1)
- Procedure
- ClinVar pathogenic versus benign SNVs within variant type, AUROC (Lu et al. 2025)
- Evaluation
- DNABERT2 on ClinVar 5' UTR SNVs (Lu et al. 2025 Figure 1)
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not reported by the source
- Evidence
- Independent external evaluation · source checkedGenomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2) · Figure 1 (page 8), column 2, panel 1 '5' UTR (N=2,471, %P=2.38%)', row 'DNABERT2', bar label
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
- None: zero-shot or precomputed scores
- Adaptation
- None
- Scoring implementation
- AUROC on scores oriented so higher means more pathogenic
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 0.414 Individual claims | Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2) Figure 1 (page 8), column 2, panel 1 '5' UTR (N=2,471, %P=2.38%)', row 'DNABERT2', bar label Version: bioRxiv preprint version 2, posted 2025-09-10 (version 1 posted 2025-09-08); full-text PDF (21 pages) | source checked ["source-hash-verification","rendered-source-visual-check","independent-cell-check"] · 2026-11-01 independent paper Audit detailsCompared every bar label, row order, N and %P with an independent 300 dpi render of page 8 (column 3 also at 400 dpi) or a 150 dpi render of page 21 of a 2026-11-01 retrieval. The 2026-11-01 retrieval is stamped differently from the pinned bytes (different SHA-256); re-running the extractor on it, with only the hash assertion relaxed, reproduced batch.jsonl byte for byte. Verdict in docs/reviews/2026-11-01-alphagenome-atlas-lu-brandes.md. Field: Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF on each download: a second retrieval at 2026-10-19T12:31:50Z had the same length (1,100,277 bytes), SHA-256 1a1aa1135ad8aa59bdb949bf8df75262eb6feba51b47f49439dbb819c426fbdd, differed in 32 bytes (ModDate) and had an identical pdftotext -layout text layer. Extraction artifact SHA-256: |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
1 source record and release history
- Genomic heterogeneity inflates the performance of variant pathogenicity predictions (Lu, Liu, Lin and Brandes, bioRxiv 2025, v2) · Original source · bioRxiv preprint version 2, posted 2025-09-10 (version 1 posted 2025-09-08); full-text PDF (21 pages)
Technical metadata and extraction receipts
Stable ID: lu-hetero-20261019-result-utr5-dnabert2-auroc
- metric
- auroc
- metric direction
- higher
- unit
- unitless
- printed value
- 0.414
- numeric value
- 0.414
- metric qualifier
- ClinVar pathogenic vs benign SNVs, 5' UTR
- source locator
- Figure 1 (page 8), column 2, panel 1 '5' UTR (N=2,471, %P=2.38%)', row 'DNABERT2', bar label
- missing metadata
- uncertainty: reason: unreported
- review
- method: source-hash-verification; rendered-source-visual-check; independent-cell-check; method note: Bar label transcribed from a 400 dpi render of page 8 (the figure has no text layer); row order asserted in extract/build_batch.py.; reviewer: claude; reviewer note: Independent Claude review agent for PR #214, 2026-11-01; did not extract this batch; no human review claimed.; date: 2026-11-01; artifact sha256: 5b8e939257000811a6eaddd90d9de3e03bf1ac0e9015a38769df887ee01f9bf2; retrieval url: https://www.biorxiv.org/content/10.1101/2025.09.05.674459v2.full.pdf; note: Compared every bar label, row order, N and %P with an independent 300 dpi render of page 8 (column 3 also at 400 dpi) or a 150 dpi render of page 21 of a 2026-11-01 retrieval. The 2026-11-01 retrieval is stamped differently from the pinned bytes (different SHA-256); re-running the extractor on it, with only the hash assertion relaxed, reproduced batch.jsonl byte for byte. Verdict in docs/reviews/2026-11-01-alphagenome-atlas-lu-brandes.md.