Datasets
GENCODE v38 human annotations with balanced Gene-Gene and Gene-Intergene datasets; a separate mouse transfer evaluation.
Task
polyadenylation site detection
Polyadenylation-site classification compares two background definitions and two adaptation regimes.
Sources
PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51Overview
Metrics
Accuracy, precision, recall, F1 and AUC, averaged across folds.
Allowed inputs
DNA/RNA sequence context for candidate polyadenylation sites.
Sources
PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51Evaluation 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
PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51Source reviewed · 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: HyenaDNA | Task: polyadenylation site detection Dataset: poly(A) Gene-Gene | 0.751 AUC fraction · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceHyenaDNA: polyadenylation site detection few-shot Gene-Gene negative-set comparison Aggregation: Not reported PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Table 1, Few-shot HyenaDNA row, G-G 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
GENCODE v38 human annotations with balanced Gene-Gene and Gene-Intergene datasets; a separate mouse transfer evaluation. Five-fold evaluation with 60:20:20 training/validation/test proportions per fold. Accuracy, precision, recall, F1 and AUC, averaged across folds. DNABERT-2, Nucleotide Transformer and HyenaDNA under few-shot and fine-tuned conditions. Negative examples exclude genic regions overlapping GENCODE v38 polyadenylation annotations. This is a label-construction control; the evaluation description does not establish chromosome or homologous-sequence separation between the five-fold training and test partitions.
Sources
PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51; Methods: dataset construction and evaluation frameworkRecorded 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 supported by sources
No source-reviewed explanatory claims are recorded here yet.
Limitations and conditions
- Changing the negative-region definition changes the classification problem. Negative-label overlap exclusion alone does not establish chromosome- or homology-disjoint evaluation.
Sources
PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation framework; Methods: few-shot evaluation; Table 1 caption
Profile review details
Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.
Stable record: reported-task-13dfe6b33e71edSpecifications
Inputs, training, access and other details
Explanatory profile: source reviewed · 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 | GENCODE v38 human annotations with balanced Gene-Gene and Gene-Intergene datasets; a separate mouse transfer evaluation.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 |
| Splits | Five-fold evaluation with 60:20:20 training/validation/test proportions per fold.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 |
| Metrics | Accuracy, precision, recall, F1 and AUC, averaged across folds.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 |
| Baselines | DNABERT-2, Nucleotide Transformer and HyenaDNA under few-shot and fine-tuned conditions.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 |
| Leakage controls | Negative examples exclude genic regions overlapping GENCODE v38 polyadenylation annotations. This is a label-construction control; the evaluation description does not establish chromosome or homologous-sequence separation between the five-fold training and test partitions.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation framework |
| Uncertainty | Table 1 reports averages over five folds. For few-shot predictions, ten random prototype pairs per fold are averaged. No confidence interval or standard-error estimator for the table’s aggregate metrics is specified there.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: few-shot evaluation; Table 1 caption |
| Entity type | Paper-specific computational evaluation protocol.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 |
| Organisms | Human; separate transfer evaluation in mouse.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 |
| Assays | GENCODE polyadenylation annotations.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 |
| Allowed inputs | DNA/RNA sequence context for candidate polyadenylation sites.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 |
| Adaptation | Few-shot and task fine-tuning settings are compared separately.SourcesPolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 |
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 |
|---|---|---|
| PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models | journal full text in PMC | Read source DOI: 10.1016/j.csbj.2025.12.011 |
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.
- Raw complete comparison acquired. Few-shot versus fine-tuning and Gene-Gene versus Intergenic-Gene conditions cannot share a chart group; NT100M and 500M are different configurations. Structured extraction pending.
Search and extraction details
source found structured extraction pending
Searches
- PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models primary paper benchmark results
Evidence locations
- Table1 two negative-set conditions and few-shot/fine-tuning row groups
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 | PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Diagram steps
| PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets GENCODE v38 human annotations with balanced Gene-Gene and Gene-Intergene datasets; a separate mouse transfer evaluation. Individual claims | PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits Five-fold evaluation with 60:20:20 training/validation/test proportions per fold. Individual claims | PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Few-shot and task fine-tuning settings are compared separately. Individual claims | PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics Accuracy, precision, recall, F1 and AUC, averaged across folds. Individual claims | PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines DNABERT-2, Nucleotide Transformer and HyenaDNA under few-shot and fine-tuned conditions. Individual claims | PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls Negative examples exclude genic regions overlapping GENCODE v38 polyadenylation annotations. This is a label-construction control; the evaluation description does not establish chromosome or homologous-sequence separation between the five-fold training and test partitions. Individual claims | PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models Methods: dataset construction and evaluation framework Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty Table 1 reports averages over five folds. For few-shot predictions, ten random prototype pairs per fold are averaged. No confidence interval or standard-error estimator for the table’s aggregate metrics is specified there. Individual claims | PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models Methods: few-shot evaluation; Table 1 caption Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. 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
- PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Original source · journal full text in PMC
- PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models · Original source · journal full text in PMC
Technical metadata and extraction receipts
Stable ID: reported-task-13dfe6b33e71ed
- areas
- dna-genomes
- tasks
- polyadenylation site detection
- entity level
- task
- version
- Not reported
- task
- polyadenylation site detection
- 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-polya-glm-2025-e9ebd53d8883; inspected locators: Table1 two negative-set conditions and few-shot/fine-tuning row groups; searched queries: PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models primary paper benchmark results; gaps: Raw complete comparison acquired. Few-shot versus fine-tuning and Gene-Gene versus Intergenic-Gene conditions cannot share a chart group; NT100M and 500M are different configurations. 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
- 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: polya-glm-2025; source locator: Methods: dataset construction and evaluation; Results Table 1; cached text lines 12–15, 37, 49–51; 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: poly(A) Gene-Gene
- benchmark: HyenaDNA: polyadenylation site detection