claim · source checked
Reported AUC for DNABERT2-Enhancer
Sources and history
Release 2026-09-16-d74d282221a9 · Record review: source checked
- Utilizing a deep learning model based on BERT for identifying enhancers and their strength · Original source · journal full text in PMC
Technical metadata and extraction receipts
Stable ID: claim-b2-dnabert2-enhancer-2025
- areas
- dna-genomes
- tasks
- enhancer recognition
- field
- attributes.printed_value
- value
- 0.965
- source locator
- Table 4, first-layer DNABERT2-Enhancer row, AUC column
- review
- method: independent_ai_table_review; reviewer: Codex secondary table review; reviewed at: 2026-09-16T10:38:57.558204+00:00; notes: Resolved the first-layer row group. DNABERT2-Enhancer AUC is 0.965, whereas second-layer AUC is 0.933. The caption explicitly describes 5-fold cross-validation on Liu training data, not an independent held-out test.