Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
Task
RNA secondary structure
RNA secondary-structure evaluation includes an explicit held-out-family generalization setting.
Sources
RNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77At a glance
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 | RNA8F combines RNAStrAlign, ArchiveII, bpRNA and CRW2, retaining sequences no longer than 500 nucleotides from eight RNA families. Table 1 gives family-by-length counts for training, validation and test subsets.SourcesRNA secondary structure prediction by conducting multi-class classifications · Materials and methods: Experimental settings; Table 1 |
| Splits | Cross-family experiments train on the other families and test the held-out family.SourcesRNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 |
| Metrics | F1 and interaction network fidelity, with overall averages across family evaluations.SourcesRNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 |
| Baselines | CONTRAfold, RNAstructure, LinearFold and MXfold2; TU-Fold is also compared with its knowledge-merge variant.SourcesRNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 |
| Leakage controls | Family holdout is separated from ordinary sequence-level evaluation.SourcesRNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 |
| Uncertainty | The sequence-length-stratified tables report means and standard deviations over three folds. This does not establish a separate interval for every cross-family experiment.SourcesRNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 |
| Entity type | Paper-specific computational evaluation protocol.SourcesRNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 |
| Organisms | RNA8F combines RNAStrAlign, ArchiveII, bpRNA and CRW2 into eight RNA families. Table 1 stratifies by family and sequence length; the paper does not provide the organism distribution of the processed train/validation/test subsets. Family names are not organism labels. · Not reported in inspected sourcesSourcesRNA secondary structure prediction by conducting multi-class classifications · Materials and methods: Experimental settings; Table 1 |
| Assays | RNA secondary-structure annotations.SourcesRNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 |
| Allowed inputs | RNA sequence.SourcesRNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 |
| Adaptation | Supervised structure learning; cross-family runs train on other families and hold one family out.SourcesRNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 |
How it works
How it worksComputational evaluation flow
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Sources
RNA secondary structure prediction by conducting multi-class classifications · Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77Evaluation methodology
RNA8F combines RNAStrAlign, ArchiveII, bpRNA and CRW2, retaining sequences no longer than 500 nucleotides from eight RNA families. Table 1 gives family-by-length counts for training, validation and test subsets. Cross-family experiments train on the other families and test the held-out family. F1 and interaction network fidelity, with overall averages across family evaluations. CONTRAfold, RNAstructure, LinearFold and MXfold2; TU-Fold is also compared with its knowledge-merge variant. Family holdout is separated from ordinary sequence-level evaluation.
Sources
RNA secondary structure prediction by conducting multi-class classifications · Materials and methods: Experimental settings; Table 1; Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77Recorded evaluations
Each evaluation records what was tested and under which conditions.
Tested entities and results
Release 2026-09-17-d277315f7d76 · 2 evaluations · 2 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| TU-Fold (aug): RNA secondary structure Three-fold training and evaluation; source reports mean and standard deviation. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.947 F1 Unit: unitless · Direction: unknown | Uncertainty: ± 0.002 standard deviation Scored: Not reported · Eligible: Not reported | source checkedRNA secondary structure prediction by conducting multi-class classifications · Table 2, TU-Fold (aug) row, Overall F1 column Source checking is not independent reproduction. |
| UFold: RNA secondary structure Three-fold training and evaluation; source reports mean and standard deviation. Independent external evaluation · Evaluation metadata: needs review | ||
| 0.938 F1 Unit: unitless · Direction: unknown | Uncertainty: ± 0.004 standard deviation Scored: Not reported · Eligible: Not reported | source checkedRNA secondary structure prediction by conducting multi-class classifications · Table 2, UFold row, Overall F1 column Source checking is not 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 |
|---|---|---|
| RNA secondary structure prediction by conducting multi-class classifications | version of record | Read source DOI: 10.1016/j.csbj.2025.04.001 |
What is still missing
- Complete raw comparison acquired,11 methods across overall and two length bands; means/SD preserved. F1/INF and precision/recall separate columns; no aggregate across different length cohorts. Structured extraction pending.
Search and extraction details
source found structured extraction pending
Searches
- RNA secondary structure prediction by conducting multi-class classifications primary paper benchmark results
Evidence locations
- Tables2–3; three-fold dataset evaluation and length strata
Strengths and limitations
Limitations and conditions
- RNA family and sequence-length imbalance affect pooled performance. Within-family and held-out-family tests are separate regimes; output constraints are part of the prediction procedure.
Sources
RNA secondary structure prediction by conducting multi-class classifications · Materials and methods: Experimental settings; Table 1
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-5ec7581b246ea6Evidence 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 | RNA secondary structure prediction by conducting multi-class classifications Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 Version: version of record | 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 ["Input: RNA sequence.","Evaluation: Cross-family experiments train on the other families and test the held-out family.","Readout: F1 and interaction network fidelity, with overall averages across family evaluations."] Individual claims | RNA secondary structure prediction by conducting multi-class classifications Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 Version: version of record | 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 | RNA secondary structure prediction by conducting multi-class classifications Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 Version: version of record | 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 RNA8F combines RNAStrAlign, ArchiveII, bpRNA and CRW2, retaining sequences no longer than 500 nucleotides from eight RNA families. Table 1 gives family-by-length counts for training, validation and test subsets. Individual claims | RNA secondary structure prediction by conducting multi-class classifications Materials and methods: Experimental settings; Table 1 Version: version of record | 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 Cross-family experiments train on the other families and test the held-out family. Individual claims | RNA secondary structure prediction by conducting multi-class classifications Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 Version: version of record | 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 structure learning; cross-family runs train on other families and hold one family out. Individual claims | RNA secondary structure prediction by conducting multi-class classifications Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 Version: version of record | 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 F1 and interaction network fidelity, with overall averages across family evaluations. Individual claims | RNA secondary structure prediction by conducting multi-class classifications Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 Version: version of record | 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 CONTRAfold, RNAstructure, LinearFold and MXfold2; TU-Fold is also compared with its knowledge-merge variant. Individual claims | RNA secondary structure prediction by conducting multi-class classifications Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 Version: version of record | 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 Family holdout is separated from ordinary sequence-level evaluation. Individual claims | RNA secondary structure prediction by conducting multi-class classifications Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 Version: version of record | 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 sequence-length-stratified tables report means and standard deviations over three folds. This does not establish a separate interval for every cross-family experiment. Individual claims | RNA secondary structure prediction by conducting multi-class classifications Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77 Version: version of record | 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
Release 2026-09-17-d277315f7d76 · Record review: needs review
2 source records and release history
- RNA secondary structure prediction by conducting multi-class classifications · Original source · version of record
- RNA secondary structure prediction by conducting multi-class classifications · Original source · version of record
Technical metadata and extraction receipts
Stable ID: reported-task-5ec7581b246ea6
- 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-tu-fold-2025-5aa376d6466d; inspected locators: Tables2–3; three-fold dataset evaluation and length strata; searched queries: RNA secondary structure prediction by conducting multi-class classifications primary paper benchmark results; gaps: Complete raw comparison acquired,11 methods across overall and two length bands; means/SD preserved. F1/INF and precision/recall separate columns; no aggregate across different length cohorts. 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: tu-fold-2025; source locator: Methods: Evaluation method; Results: cross-RNA-family evaluation; cached text lines 23–25, 75–77; 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: RNA8F
- benchmark: TU-Fold (aug): RNA secondary structure
- benchmark: UFold: RNA secondary structure