Datasets
bpRNA-1m-derived structural families and a separate bpRNA-new evaluation collection.
Task
RNA secondary structure
RNA secondary-structure assessment emphasizes held-out structural families rather than only novel sequences from familiar families.
Sources
DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37Overview
Metrics
Base-pair precision, recall and structure F1.
Allowed inputs
RNA sequences.
Sources
DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37Evaluation 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
DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37limited 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 |
|---|---|---|---|
| Pipeline: DEBFold | Task: RNA secondary structure Dataset: DEBFold TestSetβ | 55.7 Median F1 % · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDEBFold: RNA secondary structure Median F1 on the prepared TestSetβ. Aggregation: Not reported DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Table 1, DEBFold row, TestSetβ F1 (%) column |
| Configuration: RNAfold | Task: RNA secondary structure Dataset: DEBFold TestSetβ | 52.3 Median F1 % · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceRNAfold: RNA secondary structure Median F1 on the prepared TestSetβ. Aggregation: Not reported DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Table 1, RNAfold row, TestSetβ F1 (%) 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
bpRNA-1m-derived structural families and a separate bpRNA-new evaluation collection. Family-wise training/validation/test partitioning with cross-validation inside the training process. Base-pair precision, recall and structure F1. Existing RNA structure predictors, including SPOT-RNA and SPOT-RNA2, are considered in the independent-set design. A separate bpRNA-new test set is constructed because some comparators were trained on bpRNA-1m.
Sources
DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37Recorded 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
- Family-wise splitting tests transfer beyond within-family sequence similarity.
Sources
DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37
Limitations and conditions
- Family composition, sequence length and training overlap differ between the independent test sets. The paper explicitly flags potentially optimistic results for some pretrained comparators with overlapping Rfam families.
Sources
DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods and Data Sets: Family-Wise Processed RNA Structure Ground-Truth Data Set, including all three test-set construction subsections
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-016f70615f2cfcSpecifications
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 | bpRNA-1m-derived structural families and a separate bpRNA-new evaluation collection.SourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 |
| Splits | Family-wise training/validation/test partitioning with cross-validation inside the training process.SourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 |
| Metrics | Base-pair precision, recall and structure F1.SourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 |
| Baselines | Existing RNA structure predictors, including SPOT-RNA and SPOT-RNA2, are considered in the independent-set design.SourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 |
| Leakage controls | A separate bpRNA-new test set is constructed because some comparators were trained on bpRNA-1m.SourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 |
| 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 sourcesSourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 |
| Entity type | Paper-specific computational evaluation protocol.SourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 |
| Organisms | The evaluated RNA sets are selected by Rfam family, length and source rather than by organism. The dataset-construction sections identify bpRNA/Rfam and PDB origins but do not enumerate the organism composition of TestSet α, β and γ. · Not reported in inspected sourcesSourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods and Data Sets: Family-Wise Processed RNA Structure Ground-Truth Data Set, including all three test-set construction subsections |
| Assays | Reference secondary structures.SourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 |
| Allowed inputs | RNA sequences.SourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 |
| Adaptation | Supervised secondary-structure prediction with family-wise partitions and training cross-validation.SourcesDEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 |
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 |
|---|---|---|
| DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning | PMC11094721.1 | Read source DOI: 10.1021/acs.jcim.4c00458 |
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.
- Full raw tables acquired. Different family-held-out cohorts and median-over-three versus median-over-two aggregates must stay distinct. Repeated DEBFold row in Table 2 is not new independent evidence; comRNA missing predictions retained. Structured extraction pending.
Search and extraction details
source found structured extraction pending
Searches
- DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning primary paper benchmark results
Evidence locations
- Tables1–2, TestSetα/β/γ; contamination-free family-wise test procedure
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.
18 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 | DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 Version: PMC11094721.1 | 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
| DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 Version: PMC11094721.1 | 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 | DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 Version: PMC11094721.1 | 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 bpRNA-1m-derived structural families and a separate bpRNA-new evaluation collection. Individual claims | DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 Version: PMC11094721.1 | 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 Family-wise training/validation/test partitioning with cross-validation inside the training process. Individual claims | DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 Version: PMC11094721.1 | 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 Supervised secondary-structure prediction with family-wise partitions and training cross-validation. Individual claims | DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 Version: PMC11094721.1 | 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 Base-pair precision, recall and structure F1. Individual claims | DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 Version: PMC11094721.1 | 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 Existing RNA structure predictors, including SPOT-RNA and SPOT-RNA2, are considered in the independent-set design. Individual claims | DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 Version: PMC11094721.1 | 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 A separate bpRNA-new test set is constructed because some comparators were trained on bpRNA-1m. Individual claims | DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 Version: PMC11094721.1 | 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 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 | DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37 Version: PMC11094721.1 | unreported 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
- DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Original source · PMC11094721.1
- DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning · Original source · PMC11094721.1
Technical metadata and extraction receipts
Stable ID: reported-task-016f70615f2cfc
- areas
- rna-transcriptomes
- tasks
- RNA secondary structure
- entity level
- task
- version
- Not reported
- task
- RNA secondary structure
- 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-debfold-2024-e8f960eafb7f; inspected locators: Tables1–2, TestSetα/β/γ; contamination-free family-wise test procedure; searched queries: DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning primary paper benchmark results; gaps: Full raw tables acquired. Different family-held-out cohorts and median-over-three versus median-over-two aggregates must stay distinct. Repeated DEBFold row in Table 2 is not new independent evidence; comRNA missing predictions retained. 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: debfold-2024; source locator: Methods: Family-Wise Processed RNA Structure Ground-Truth Data Set; Contamination-Free Family-Wise Independent Test Set; Structure Prediction Evaluation Metrics; cached text lines 26–31, 36–37; 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: DEBFold TestSetβ
- benchmark: DEBFold: RNA secondary structure
- benchmark: RNAfold: RNA secondary structure