Datasets
Promoter annotations from PPD and species-matched negative sequence collections.
Task
Multi-species prokaryotic promoter detection
Multi-species promoter classification uses curated positives and genomic-background negatives.
Sources
iPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72Overview
Metrics
Sensitivity, specificity, accuracy, MCC and ROC-AUC.
Allowed inputs
DNA sequence windows.
Sources
iPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72Evaluation procedure diagram
How it worksComputational evaluation flow
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Sources
iPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
2 evaluations · 2 results. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: iPro-MP | Task: Multi-species prokaryotic promoter detection Dataset: 23 independent prokaryotic promoter test sets | 0.935 Mean AUC unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceiPro-MP: Multi-species prokaryotic promoter detection Average over independent testing sets. Aggregation: Not reported iPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Table 2, iPro-MP row, AUC column |
| Configuration: Prompt | Task: Multi-species prokaryotic promoter detection Dataset: 23 independent prokaryotic promoter test sets | 0.835 Mean AUC unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcePrompt: Multi-species prokaryotic promoter detection Average over the same independent testing sets. Aggregation: Not reported iPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Table 2, Prompt row, AUC column |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
Methods and evaluation design
Procedure, tasks and evaluated configurations
How it works
Evaluation methodology
Promoter annotations from PPD and species-matched negative sequence collections. Five-fold cross-validation is used for fitting and an independent collection for comparison. Sensitivity, specificity, accuracy, MCC and ROC-AUC. The source describes CD-HIT redundancy filtering for both classes. The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim.
Sources
iPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72Recorded evaluations
Each evaluation records what was tested and under which conditions.
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Strengths, limitations and unresolved questions
Strengths and limitations
Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
Limitations and conditions
- Within-species independent tests and cross-species transfer matrices are separate evaluation conditions; their aggregate scores must not be interchanged.
Sources
iPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72
Profile review details
Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.
Stable record: reported-task-a1151e386a3d3fSpecifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Datasets | Promoter annotations from PPD and species-matched negative sequence collections.SourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 |
| Splits | Five-fold cross-validation is used for fitting and an independent collection for comparison.SourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 |
| Metrics | Sensitivity, specificity, accuracy, MCC and ROC-AUC.SourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 |
| Baselines | Generic classifiers are random forest, XGBoost, logistic regression and LSTM, trained with five-fold cross-validation. Tool comparisons use Prompt, PromoterLCNN and iPro-WAEL on the same species-specific independent tests; a separate repeat uses their official five-fold training protocols.SourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Results: Tables 1–2; comparison with baseline classifiers and existing tools; cached paragraphs 29–37 |
| Leakage controls | The source describes CD-HIT redundancy filtering for both classes.SourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 |
| Uncertainty | The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. · Not reported in inspected sourcesSourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 |
| Entity type | Paper-specific computational evaluation protocol.SourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 |
| Organisms | Multiple prokaryotic species in PPD.SourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 |
| Assays | Promoter annotations and species-matched negatives.SourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 |
| Allowed inputs | DNA sequence windows.SourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 |
| Adaptation | Supervised promoter classification with cross-validation and an independent collection.SourcesiPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 |
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Papers and result coverage
Last literature check: 2026-09-17. Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
| Paper or primary resource | Version | Reference |
|---|---|---|
| iPro-MP: a BERT-based model to predict multiple prokaryotic promoters | version of record | Read source DOI: 10.1186/s13059-025-03819-9 |
Historical gaps recorded on 2026-09-17
The catalogue now holds 2 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.
- iPro-MP's first four scores duplicate across Tables 1–2; one result with two source occurrences.
- Species-averaged accuracy/AUROC/AUPRC/MCC differ from pooled sample scores; retain source aggregation.
- Runtime is seconds, lower-is-better, and hardware-dependent.
Search and extraction details
primary comparison table screened
Searches
- "PMC12516880"
Evidence locations
- Tables 1–3
- Methods: Data collection and preprocessing; Performance evaluation
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.
17 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims | iPro-MP: a BERT-based model to predict multiple prokaryotic promoters Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Diagram steps
| iPro-MP: a BERT-based model to predict multiple prokaryotic promoters Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | iPro-MP: a BERT-based model to predict multiple prokaryotic promoters Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets Promoter annotations from PPD and species-matched negative sequence collections. Individual claims | iPro-MP: a BERT-based model to predict multiple prokaryotic promoters Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits Five-fold cross-validation is used for fitting and an independent collection for comparison. Individual claims | iPro-MP: a BERT-based model to predict multiple prokaryotic promoters Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Supervised promoter classification with cross-validation and an independent collection. Individual claims | iPro-MP: a BERT-based model to predict multiple prokaryotic promoters Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics Sensitivity, specificity, accuracy, MCC and ROC-AUC. Individual claims | iPro-MP: a BERT-based model to predict multiple prokaryotic promoters Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines Generic classifiers are random forest, XGBoost, logistic regression and LSTM, trained with five-fold cross-validation. Tool comparisons use Prompt, PromoterLCNN and iPro-WAEL on the same species-specific independent tests; a separate repeat uses their official five-fold training protocols. Individual claims | iPro-MP: a BERT-based model to predict multiple prokaryotic promoters Results: Tables 1–2; comparison with baseline classifiers and existing tools; cached paragraphs 29–37 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls The source describes CD-HIT redundancy filtering for both classes. Individual claims | iPro-MP: a BERT-based model to predict multiple prokaryotic promoters Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. Individual claims | iPro-MP: a BERT-based model to predict multiple prokaryotic promoters Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72 Version: version of record | unreported automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: needs review
2 source records and release history
- iPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Original source · version of record
- iPro-MP: a BERT-based model to predict multiple prokaryotic promoters · Original source · version of record
Technical metadata and extraction receipts
Stable ID: reported-task-a1151e386a3d3f
- areas
- microbes-communities
- tasks
- Multi-species prokaryotic promoter detection
- entity level
- task
- version
- Not reported
- task
- Multi-species prokaryotic promoter detection
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: primary_comparison_table_screened; primary sources: expansion-p3-ipromp-2025; inspected locators: Tables 1–3; Methods: Data collection and preprocessing; Performance evaluation; searched queries: "PMC12516880"; gaps: iPro-MP's first four scores duplicate across Tables 1–2; one result with two source occurrences.; Species-averaged accuracy/AUROC/AUPRC/MCC differ from pooled sample scores; retain source aggregation.; Runtime is seconds, lower-is-better, and hardware-dependent.; claim scope: Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
- historical missing metadata
- protocol version: not_reported_in_legacy_extract
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- benchmark
- entity classification
- review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: ipromp-2025; source locator: Methods: Data collection and preprocessing; Performance evaluation; cached text lines 54–56, 69–72; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.