Datasets
Previously published enhancer/non-enhancer sequences with strong/weak labels for the enhancer subset.
Task
enhancer recognition
Enhancer recognition is evaluated separately from classification of enhancer strength.
Sources
Utilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48Overview
Metrics
Specificity, sensitivity, accuracy, balanced accuracy, MCC and AUC.
Allowed inputs
DNA sequences.
Sources
Utilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48Evaluation 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
Utilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48; Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48; Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48limited 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
1 evaluation · 1 result. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: DNABERT2-Enhancer | Task: enhancer recognition Dataset: Liu training dataset | 0.965 AUC fraction · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDNABERT2-Enhancer: enhancer recognition first-layer enhancer versus non-enhancer classifier Aggregation: Not reported Utilizing a deep learning model based on BERT for identifying enhancers and their strength · Table 4, first-layer DNABERT2-Enhancer 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
Previously published enhancer/non-enhancer sequences with strong/weak labels for the enhancer subset. Five-fold cross-validation is performed within Liu’s training data; separately listed test subsets distinguish enhancer detection from enhancer-strength classification. Specificity, sensitivity, accuracy, balanced accuracy, MCC and AUC. The source describes CD-HIT filtering of highly similar sequences. 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
Utilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48Recorded 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
- Enhancer recognition and strong-versus-weak enhancer classification use different labels and test counts. Pretraining genome coverage does not establish independence of the downstream examples.
Sources
Utilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48
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-86a628af87ff8fSpecifications
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 | Previously published enhancer/non-enhancer sequences with strong/weak labels for the enhancer subset.SourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 |
| Splits | Five-fold cross-validation is performed within Liu’s training data; separately listed test subsets distinguish enhancer detection from enhancer-strength classification.SourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 |
| Metrics | Specificity, sensitivity, accuracy, balanced accuracy, MCC and AUC.SourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 |
| Baselines | Liu cross-validation compares iEnhancer-ECNN, BERT-Enhancer and iEnhancer-BERT. Its independent test additionally includes EnhancerPred, iEnhancer-EL, iEnhancer-XG and Enhancer-MDLF; not every comparator reports both recognition and strength metrics.SourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Results: Comparison with existing methods; Tables 4–5 |
| Leakage controls | The source describes CD-HIT filtering of highly similar sequences.SourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 |
| 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 sourcesSourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 |
| Entity type | Paper-specific computational evaluation protocol.SourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 |
| Organisms | The dataset section identifies Liu’s reused enhancer collection and eight Basith cell-line collections, but does not state a species or genome assembly for the Liu collection. These identities cannot be inferred from DNABERT2’s multispecies pretraining. · Not reported in inspected sourcesSourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Materials and methods: Benchmark dataset; Tables 1–2 |
| Assays | Enhancer/non-enhancer and strong/weak enhancer annotations.SourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 |
| Allowed inputs | DNA sequences.SourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 |
| Adaptation | DNABERT-2 converts sequences to feature matrices; a convolution/pooling module and two-layer perceptron perform supervised enhancer classification. The architecture passage does not specify the encoder freezing boundary.SourcesUtilizing a deep learning model based on BERT for identifying enhancers and their strength · Methods: DNABERT-2 representation and CNN model, cached paragraphs 36–43 |
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. Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Utilizing a deep learning model based on BERT for identifying enhancers and their strength | journal full text in PMC | Read source |
Historical gaps recorded on 2026-09-17
The catalogue now holds 1 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.
- complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
- exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Search and extraction details
primary comparison tables located
Searches
- Utilizing a deep learning model based on BERT for identifying enhancers and their strength 10.1371/journal.pone.0320085
Evidence locations
- Table 4; XML table pone.0320085.t004
- Table 5; XML table pone.0320085.t005
- Table 6; XML table pone.0320085.t006
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 | Utilizing a deep learning model based on BERT for identifying enhancers and their strength Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48; Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48; Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 Version: journal full text in PMC | 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
| Utilizing a deep learning model based on BERT for identifying enhancers and their strength Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48; Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48; Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 Version: journal full text in PMC | 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 | Utilizing a deep learning model based on BERT for identifying enhancers and their strength Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48; Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48; Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 Version: journal full text in PMC | 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 Previously published enhancer/non-enhancer sequences with strong/weak labels for the enhancer subset. Individual claims | Utilizing a deep learning model based on BERT for identifying enhancers and their strength Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 Version: journal full text in PMC | 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 performed within Liu’s training data; separately listed test subsets distinguish enhancer detection from enhancer-strength classification. Individual claims | Utilizing a deep learning model based on BERT for identifying enhancers and their strength Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 Version: journal full text in PMC | 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 DNABERT-2 converts sequences to feature matrices; a convolution/pooling module and two-layer perceptron perform supervised enhancer classification. The architecture passage does not specify the encoder freezing boundary. Individual claims | Utilizing a deep learning model based on BERT for identifying enhancers and their strength Methods: DNABERT-2 representation and CNN model, cached paragraphs 36–43 Version: journal full text in PMC | 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 Specificity, sensitivity, accuracy, balanced accuracy, MCC and AUC. Individual claims | Utilizing a deep learning model based on BERT for identifying enhancers and their strength Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 Version: journal full text in PMC | 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 Liu cross-validation compares iEnhancer-ECNN, BERT-Enhancer and iEnhancer-BERT. Its independent test additionally includes EnhancerPred, iEnhancer-EL, iEnhancer-XG and Enhancer-MDLF; not every comparator reports both recognition and strength metrics. Individual claims | Utilizing a deep learning model based on BERT for identifying enhancers and their strength Results: Comparison with existing methods; Tables 4–5 Version: journal full text in PMC | 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 filtering of highly similar sequences. Individual claims | Utilizing a deep learning model based on BERT for identifying enhancers and their strength Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 Version: journal full text in PMC | 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 | Utilizing a deep learning model based on BERT for identifying enhancers and their strength Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48 Version: journal full text in PMC | 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
- Utilizing a deep learning model based on BERT for identifying enhancers and their strength · Original source · journal full text in PMC
- 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: reported-task-86a628af87ff8f
- areas
- dna-genomes
- tasks
- enhancer recognition
- entity level
- task
- version
- Not reported
- task
- enhancer recognition
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: primary_comparison_tables_located; primary sources: evidence-expansion-dnabert2-enhancer-2025-d052b80e; inspected locators: Table 4; XML table pone.0320085.t004; Table 5; XML table pone.0320085.t005; Table 6; XML table pone.0320085.t006; searched queries: Utilizing a deep learning model based on BERT for identifying enhancers and their strength 10.1371/journal.pone.0320085; gaps: complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.; exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.; claim scope: Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
- 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: dnabert2-enhancer-2025; source locator: Methods: Benchmark dataset; Performance evaluation metrics; cached text lines 12–13, 47–48; 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.
Related records
- dataset: Liu training dataset
- benchmark: DNABERT2-Enhancer: enhancer recognition