Limits of deep-learning-based RNA prediction methods
Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML · Peer-reviewed
What this source contributed
Records in this release that cite this source. A record can cite several sources.
Results
Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.
Models, benchmarks and other records
Models (5)
Configurations (10)
- AlphaFold3 3.0.1 (Ludaic and Elofsson 2026 RNA benchmark run)
- Boltz-1 0.4.1 (Ludaic and Elofsson 2026 RNA benchmark run)
- Chai-1 0.6.1 (Ludaic and Elofsson 2026 RNA benchmark run)
- DeepFoldRNA 1.0 (Ludaic and Elofsson 2026 RNA benchmark run)
- DRfold commit pre-release-4-g9586990 (Ludaic and Elofsson 2026 RNA benchmark run)
- HelixFold3 HelixFold3/73cd80b-hpc1 (Ludaic and Elofsson 2026 RNA benchmark run)
- NuFold commit 169a618 (Ludaic and Elofsson 2026 RNA benchmark run)
- RhoFold+ 0.0.1 (Ludaic and Elofsson 2026 RNA benchmark run)
- RosettaFoldNA commit f761af2 (Ludaic and Elofsson 2026 RNA benchmark run)
- trRosettaRNA 1.0 (Ludaic and Elofsson 2026 RNA benchmark run)
Benchmarks (1)
Protocols (30)
- Ludaic and Elofsson 2026 Monomeric RNA easy set, GDT-TS success rate
- Ludaic and Elofsson 2026 Monomeric RNA easy set, INF success rate
- Ludaic and Elofsson 2026 Monomeric RNA easy set, lDDT success rate
- Ludaic and Elofsson 2026 Monomeric RNA easy set, mean GDT-TS
- Ludaic and Elofsson 2026 Monomeric RNA easy set, mean INF
- Ludaic and Elofsson 2026 Monomeric RNA easy set, mean lDDT
- Ludaic and Elofsson 2026 Monomeric RNA easy set, mean TM-score
- Ludaic and Elofsson 2026 Monomeric RNA easy set, TM-score success rate
- Ludaic and Elofsson 2026 Monomeric RNA hard set, GDT-TS success rate
- Ludaic and Elofsson 2026 Monomeric RNA hard set, INF success rate
- Ludaic and Elofsson 2026 Monomeric RNA hard set, lDDT success rate
- Ludaic and Elofsson 2026 Monomeric RNA hard set, mean GDT-TS
- Ludaic and Elofsson 2026 Monomeric RNA hard set, mean INF
- Ludaic and Elofsson 2026 Monomeric RNA hard set, mean lDDT
- Ludaic and Elofsson 2026 Monomeric RNA hard set, mean TM-score
- Ludaic and Elofsson 2026 Monomeric RNA hard set, TM-score success rate
- Ludaic and Elofsson 2026 RNA complex easy set, mean DockQ
- Ludaic and Elofsson 2026 RNA complex easy set, mean F1
- Ludaic and Elofsson 2026 RNA complex easy set, mean fnat
- Ludaic and Elofsson 2026 RNA complex easy set, mean iRMSD
- Ludaic and Elofsson 2026 RNA complex easy set, mean LRMSD
- Ludaic and Elofsson 2026 RNA complex easy set, mean TM-score
- Ludaic and Elofsson 2026 RNA complex hard set, mean DockQ
- Ludaic and Elofsson 2026 RNA complex hard set, mean F1
- Ludaic and Elofsson 2026 RNA complex hard set, mean fnat
Datasets (5)
Evaluations (216)
- AlphaFold3 on Monomeric RNA easy set (GDT-TS, success rate)
- AlphaFold3 on Monomeric RNA easy set (GDT-TS)
- AlphaFold3 on Monomeric RNA easy set (INF, success rate)
- AlphaFold3 on Monomeric RNA easy set (INF)
- AlphaFold3 on Monomeric RNA easy set (lDDT, success rate)
- AlphaFold3 on Monomeric RNA easy set (lDDT)
- AlphaFold3 on Monomeric RNA easy set (TM-score, success rate)
- AlphaFold3 on Monomeric RNA easy set (TM-score)
- AlphaFold3 on Monomeric RNA hard set (GDT-TS, success rate)
- AlphaFold3 on Monomeric RNA hard set (GDT-TS)
- AlphaFold3 on Monomeric RNA hard set (INF, success rate)
- AlphaFold3 on Monomeric RNA hard set (INF)
- AlphaFold3 on Monomeric RNA hard set (lDDT, success rate)
- AlphaFold3 on Monomeric RNA hard set (lDDT)
- AlphaFold3 on Monomeric RNA hard set (TM-score, success rate)
- AlphaFold3 on Monomeric RNA hard set (TM-score)
- AlphaFold3 on RNA complex easy set (DockQ)
- AlphaFold3 on RNA complex easy set (F1)
- AlphaFold3 on RNA complex easy set (fnat)
- AlphaFold3 on RNA complex easy set (iRMSD)
- AlphaFold3 on RNA complex easy set (LRMSD)
- AlphaFold3 on RNA complex easy set (TM-score)
- AlphaFold3 on RNA complex hard set (DockQ)
- AlphaFold3 on RNA complex hard set (F1)
- AlphaFold3 on RNA complex hard set (fnat)
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
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.
19 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.artifact_sha256 02043b4a3edbb62101f6abbca56c896a63fa5c7dc0c3956c58164daff015ad1f Source metadata | Limits of deep-learning-based RNA prediction methods No field-specific location recorded Version: Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Artifact url https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13501138/fullTextXML Source metadata | Limits of deep-learning-based RNA prediction methods No field-specific location recorded Version: Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Code url https://github.com/iammarcol/RNA-Benchmark Source metadata | Limits of deep-learning-based RNA prediction methods No field-specific location recorded Version: Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Doi 10.1093/nar/gkag813 Source metadata | Limits of deep-learning-based RNA prediction methods No field-specific location recorded Version: Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Licence CC-BY-4.0 Source metadata | Limits of deep-learning-based RNA prediction methods No field-specific location recorded Version: Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Limitations3 values
| Limits of deep-learning-based RNA prediction methods No field-specific location recorded Version: Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Media type application/xml Source metadata | Limits of deep-learning-based RNA prediction methods No field-specific location recorded Version: Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Publication status peer_reviewed Source metadata | Limits of deep-learning-based RNA prediction methods No field-specific location recorded Version: Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Retrieved at 2026-10-11T21:27:03Z Source metadata | Limits of deep-learning-based RNA prediction methods No field-specific location recorded Version: Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Url https://doi.org/10.1093/nar/gkag813 Source metadata | Limits of deep-learning-based RNA prediction methods No field-specific location recorded Version: Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
Primary source retrieved and hashed for the 2026-10-11 RNA and other-omics literature pass.
Technical metadata and extraction receipts
Stable ID: lit-rna-20261011-rna3d-source-ludaic2026
- areas
- rna-transcriptomes; protein-structure
- contexts
- research
- url
- https://doi.org/10.1093/nar/gkag813
- artifact url
- https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13501138/fullTextXML
- version
- Nucleic Acids Research 2026, gkag813 (issue date 2026-08-01); PMC13501138 full-text XML
- retrieved at
- 2026-10-11T21:27:03Z
- artifact sha256
- 02043b4a3edbb62101f6abbca56c896a63fa5c7dc0c3956c58164daff015ad1f
- doi
- 10.1093/nar/gkag813
- publication status
- peer_reviewed
- licence
- CC-BY-4.0
- media type
- application/xml
- code url
- https://github.com/iammarcol/RNA-Benchmark
- limitations
- Tables 2 and 3 print identical GDT-TS, INF and lDDT means for DRfold and DeepFoldRNA (0.559, 0.736, 0.481 easy; 0.436, 0.617, 0.361 hard) while their TM-scores differ. The per-target columns for the two methods in Supplementary Tables S3-S5 are also identical, so the duplication is upstream of the means. Not resolved from the source.; Table 3 prints INF 0.668 for RF2NA on the hard set; the mean of the RF2NA column of Supplementary Table S3 (hard rows) is 0.608 by the extractor's own check. Not resolved from the source.; The tables print bold, underline and italic marks for statistical ties (Wilcoxon signed-rank test); the XML carries no formatting, so those marks are not recorded.