Independent E. coli sigma70 test dataset
Evaluation results
Release 2026-09-16-d74d282221a9 · 2 evaluations · 2 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Eco70PromBERT: E. coli sigma70 promoter prediction Model: Eco70PromBERT · Benchmark: E. coli sigma70 promoter prediction · Dataset: Independent E. coli sigma70 test dataset BERT-base with 1bp tokenizer; 110 promoters and 108 non-promoters. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.91 Promoter-class F1 Unit: unitless · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedTSSNote-CyaPromBERT: Development of an integrated platform for highly accurate promoter prediction and visualization of Synechococcus sp. and Synechocystis sp. through a state-of-the-art natural language processing model BERT · TABLE 3, Eco70PromBERT (BERT-base + 1bp tokenizer) row, F1 score Promoter column Source checking is not independent reproduction. |
| iPro70-FMWin: E. coli sigma70 promoter prediction Model: iPro70-FMWin · Benchmark: E. coli sigma70 promoter prediction · Dataset: Independent E. coli sigma70 test dataset Compared on the same independent test dataset; 110 promoters and 108 non-promoters. Independent external evaluation · Evaluation metadata: needs review | ||
| 0.90 Promoter-class F1 Unit: unitless · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedTSSNote-CyaPromBERT: Development of an integrated platform for highly accurate promoter prediction and visualization of Synechococcus sp. and Synechocystis sp. through a state-of-the-art natural language processing model BERT · TABLE 3, iPro70-FMWin row, F1 score Promoter column Source checking is not independent reproduction. |
Sources and history
Release 2026-09-16-d74d282221a9 · Record review: needs review
- TSSNote-CyaPromBERT: Development of an integrated platform for highly accurate promoter prediction and visualization of Synechococcus sp. and Synechocystis sp. through a state-of-the-art natural language processing model BERT · Original source · version of record
Technical metadata and extraction receipts
Stable ID: reported-dataset-a1da4a37eb46a5
- areas
- microbes-communities
- version
- Not reported
- split
- independent test
- missing metadata
- version: not_reported_in_legacy_extract; accession: not_reported_in_legacy_extract