Datasets
KEx, G4 ChIP-seq, G4-seq and G4 CUT&Tag annotation collections.
Task
G-quadruplex classification
G-quadruplex classification evaluates balanced positives and sampled genomic-background negatives from several annotation assays.
Sources
Benchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passagesOverview
Metrics
Accuracy, ROC-AUC, F1 and MCC.
Allowed inputs
DNA sequences around candidate G-quadruplex regions.
Sources
Benchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passagesEvaluation 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
Benchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passageslimited 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: DNABERT-2 | Task: G-quadruplex classification Dataset: KEx | 97 Accuracy % · unknown Uncertainty: ± 0.5 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceDNABERT-2: G-quadruplex classification Pretrained model evaluated on KEx as reported in Table 5. Aggregation: Not reported Benchmarking DNA large language models on quadruplexes · Table 5, DNABERT-2 (117 M) row, Accuracy column |
| Configuration: Caduceus | Task: G-quadruplex classification Dataset: KEx | 95 Accuracy % · unknown Uncertainty: ± 0.5 Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCaduceus: G-quadruplex classification Pretrained model evaluated on KEx as reported in Table 5. Aggregation: Not reported Benchmarking DNA large language models on quadruplexes · Table 5, Caduceus (8 M) row, Accuracy 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
KEx, G4 ChIP-seq, G4-seq and G4 CUT&Tag annotation collections. Accuracy, ROC-AUC, F1 and MCC. DNABERT, DNABERT-2, GENA-LM, HyenaDNA and Caduceus; tested context lengths differ.
Sources
Benchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages; Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages; Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passagesRecorded 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
- Balanced sampled negatives do not reproduce genome-wide prevalence. Fold variability is not the same as an independent cohort confidence interval.
Sources
Benchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages
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-c9d2a6435979e9Specifications
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 | KEx, G4 ChIP-seq, G4-seq and G4 CUT&Tag annotation collections.SourcesBenchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages |
| Splits | Five-fold cross-validation.SourcesBenchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages |
| Metrics | Accuracy, ROC-AUC, F1 and MCC.SourcesBenchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages |
| Baselines | DNABERT, DNABERT-2, GENA-LM, HyenaDNA and Caduceus; tested context lengths differ.SourcesBenchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages |
| Leakage controls | Sampled negative regions exclude annotated G-quadruplex positives. Data preparation does not specify a chromosome-disjoint or homology-disjoint partition, so non-overlapping positive/negative labels alone do not establish genomic independence.SourcesBenchmarking DNA large language models on quadruplexes · Materials and methods: Data preparation and Metrics of evaluation |
| Uncertainty | Mean and standard deviation across the five folds.SourcesBenchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages |
| Entity type | Paper-specific computational evaluation protocol.SourcesBenchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages |
| Organisms | The paper reuses KEx, G4 ChIP-seq, G4-seq and G4 CUT&Tag collections. Data preparation lists assays and sample counts without dataset-by-dataset organism/assembly identifiers. Its references include both mammalian and multispecies studies, so a single genome cannot be assigned to all four from this description. · Not reported in inspected sourcesSourcesBenchmarking DNA large language models on quadruplexes · Materials and methods: Data preparation, Table 1; primary dataset references 14–17,24 |
| Assays | G4 ChIP-seq, G4-seq, CUT&Tag and KEx annotations.SourcesBenchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages |
| Allowed inputs | DNA sequences around candidate G-quadruplex regions.SourcesBenchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages |
| Adaptation | Supervised classification with five-fold cross-validation.SourcesBenchmarking DNA large language models on quadruplexes · Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages |
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-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Benchmarking DNA large language models on quadruplexes | version of record | Read source DOI: 10.1016/j.csbj.2025.03.007 |
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.
- Complete raw tables acquired. Positive/negative construction, sequence lengths and train/test splits remain part of each G4 protocol; existing observations preserved. Structured extraction pending.
Search and extraction details
source found structured extraction pending
Searches
- Benchmarking DNA large language models on quadruplexes primary paper benchmark results
Evidence locations
- Primary results tables and G4 classification protocol
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 | Benchmarking DNA large language models on quadruplexes Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages 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
| Benchmarking DNA large language models on quadruplexes Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages 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 | Benchmarking DNA large language models on quadruplexes Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages 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 KEx, G4 ChIP-seq, G4-seq and G4 CUT&Tag annotation collections. Individual claims | Benchmarking DNA large language models on quadruplexes Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages 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. Individual claims | Benchmarking DNA large language models on quadruplexes Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages 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 classification with five-fold cross-validation. Individual claims | Benchmarking DNA large language models on quadruplexes Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages 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 Accuracy, ROC-AUC, F1 and MCC. Individual claims | Benchmarking DNA large language models on quadruplexes Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages 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 DNABERT, DNABERT-2, GENA-LM, HyenaDNA and Caduceus; tested context lengths differ. Individual claims | Benchmarking DNA large language models on quadruplexes Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages 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 Sampled negative regions exclude annotated G-quadruplex positives. Data preparation does not specify a chromosome-disjoint or homology-disjoint partition, so non-overlapping positive/negative labels alone do not establish genomic independence. Individual claims | Benchmarking DNA large language models on quadruplexes Materials and methods: Data preparation and Metrics of evaluation 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 Mean and standard deviation across the five folds. Individual claims | Benchmarking DNA large language models on quadruplexes Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages 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 |
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
- Benchmarking DNA large language models on quadruplexes · Original source · version of record
- Benchmarking DNA large language models on quadruplexes · Original source · version of record
Technical metadata and extraction receipts
Stable ID: reported-task-c9d2a6435979e9
- areas
- dna-genomes
- tasks
- G-quadruplex classification
- entity level
- task
- version
- Not reported
- task
- G-quadruplex classification
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: source_found_structured_extraction_pending; primary sources: evidence-expansion-p2-quadruplex-llm-benchmark-2025-c3d7c6d068d3; inspected locators: Primary results tables and G4 classification protocol; searched queries: Benchmarking DNA large language models on quadruplexes primary paper benchmark results; gaps: Complete raw tables acquired. Positive/negative construction, sequence lengths and train/test splits remain part of each G4 protocol; existing observations preserved. Structured extraction pending.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
- historical missing metadata
- protocol version: not_reported_in_legacy_extract; split: 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: quadruplex-llm-benchmark-2025; source locator: Methods: Data preparation; Metrics of evaluation; cached text lines 13–16, 22–23; comparative evaluation and ablation passages; 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: KEx
- benchmark: DNABERT-2: G-quadruplex classification
- benchmark: Caduceus: G-quadruplex classification