Datasets
Human 5mC annotation windows from previously published benchmark datasets; positives and negatives derive from experimental profiling.
Task
Human 5mC detection
Human DNA methylation-site classification compares frozen foundation-model embeddings with supervised classifiers and a compact CNN baseline.
Sources
Benchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114Overview
Metrics
AUC for binary tasks; pairwise DeLong tests assess AUC differences.
Allowed inputs
DNA windows represented by foundation-model embeddings.
Sources
Benchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114Evaluation 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 foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114limited 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: Caduceus-Ph | Task: Human 5mC detection Dataset: Human 5mC | 0.783 AUC unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCaduceus-Ph: Human 5mC detection Binary epigenetic-modification classification as reported in the paper. Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, Human 5mC row, Caduceus-Ph column |
| Configuration: NT-v2 | Task: Human 5mC detection Dataset: Human 5mC | 0.738 AUC unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceBinary epigenetic-modification classification as reported in the paper. Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 3, Human 5mC row, NT-v2 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
Human 5mC annotation windows from previously published benchmark datasets; positives and negatives derive from experimental profiling. The classification framework retains clearly specified source splits or applies randomized partitions; exact 5mC membership remains unextracted. AUC for binary tasks; pairwise DeLong tests assess AUC differences. Random forest, Naive Bayes and elastic-net classifiers over embeddings; a sequence CNN baseline. Similar sequences are filtered in the source dataset; complete pretraining exclusion is not established by this review. The paper uses significance testing for AUC differences; test-set uncertainty is distinct from variation across retraining.
Sources
Benchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114Recorded 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
- The chromosome-held-out nested protocol elsewhere in the paper concerns variant-effect quantification and is not asserted for this methylation classification task.
Sources
Benchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114
Profile review details
Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.
Stable record: reported-task-988ff78f86471eSpecifications
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 | Human 5mC annotation windows from previously published benchmark datasets; positives and negatives derive from experimental profiling.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
| Splits | The classification framework retains clearly specified source splits or applies randomized partitions; exact 5mC membership remains unextracted.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
| Metrics | AUC for binary tasks; pairwise DeLong tests assess AUC differences.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
| Baselines | Random forest, Naive Bayes and elastic-net classifiers over embeddings; a sequence CNN baseline.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
| Leakage controls | Similar sequences are filtered in the source dataset; complete pretraining exclusion is not established by this review.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
| Uncertainty | The paper uses significance testing for AUC differences; test-set uncertainty is distinct from variation across retraining.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
| Entity type | Paper-specific computational evaluation protocol.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
| Organisms | Human.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
| Assays | Experimental 5mC site annotations.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
| Allowed inputs | DNA windows represented by foundation-model embeddings.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
| Adaptation | Supervised conventional classifiers over embeddings; the sequence CNN is a separate baseline.SourcesBenchmarking DNA foundation models for genomic and genetic tasks · Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 |
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 |
|---|---|---|
| Benchmarking DNA foundation models for genomic and genetic tasks | PMC12663285.1 | Read source |
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 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
- Benchmarking DNA foundation models for genomic and genetic tasks 10.1038/s41467-025-65823-8
Evidence locations
- Table 3; XML table Tab3
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 foundation models for genomic and genetic tasks Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 Version: PMC12663285.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Diagram steps
| Benchmarking DNA foundation models for genomic and genetic tasks Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 Version: PMC12663285.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | Benchmarking DNA foundation models for genomic and genetic tasks Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 Version: PMC12663285.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets Human 5mC annotation windows from previously published benchmark datasets; positives and negatives derive from experimental profiling. Individual claims | Benchmarking DNA foundation models for genomic and genetic tasks Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 Version: PMC12663285.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits The classification framework retains clearly specified source splits or applies randomized partitions; exact 5mC membership remains unextracted. Individual claims | Benchmarking DNA foundation models for genomic and genetic tasks Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 Version: PMC12663285.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Supervised conventional classifiers over embeddings; the sequence CNN is a separate baseline. Individual claims | Benchmarking DNA foundation models for genomic and genetic tasks Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 Version: PMC12663285.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics AUC for binary tasks; pairwise DeLong tests assess AUC differences. Individual claims | Benchmarking DNA foundation models for genomic and genetic tasks Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 Version: PMC12663285.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines Random forest, Naive Bayes and elastic-net classifiers over embeddings; a sequence CNN baseline. Individual claims | Benchmarking DNA foundation models for genomic and genetic tasks Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 Version: PMC12663285.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls Similar sequences are filtered in the source dataset; complete pretraining exclusion is not established by this review. Individual claims | Benchmarking DNA foundation models for genomic and genetic tasks Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 Version: PMC12663285.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty The paper uses significance testing for AUC differences; test-set uncertainty is distinct from variation across retraining. Individual claims | Benchmarking DNA foundation models for genomic and genetic tasks Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114 Version: PMC12663285.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. 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 foundation models for genomic and genetic tasks · Original source · PMC12663285.1
- Benchmarking DNA foundation models for genomic and genetic tasks · Original source · PMC12663285.1
Technical metadata and extraction receipts
Stable ID: reported-task-988ff78f86471e
- areas
- dna-genomes
- tasks
- Human 5mC detection
- entity level
- task
- version
- Not reported
- task
- Human 5mC detection
- 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-dna-foundation-models-2025-5d8ca9bc; inspected locators: Table 3; XML table Tab3; searched queries: Benchmarking DNA foundation models for genomic and genetic tasks 10.1038/s41467-025-65823-8; 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; 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: dna-foundation-models-2025; source locator: Methods: 5mC and 6mA modifications detection; Sequence classification benchmark; cached text lines 86, 110–114; 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: Human 5mC
- benchmark: Caduceus-Ph: Human 5mC detection
- benchmark: NT-v2: Human 5mC detection