EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Limits of deep-learning-based RNA prediction methods

Marko Ludaic, Arne Elofsson iD

Nucleic Acids Research · 24.08.2026 · 54 (16)

DOI: 10.1093/nar/gkag813 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nucleic Acids Research, online erschienen am 24.08.2026. Verfasst von Marko Ludaic und 1 weiteren Autor:innen. Beteiligte Einrichtung: Science for Life Laboratory and Department of Biochemistry and Biophysics, Stockholm University, Solna 171 21, Sweden. Hauptthemen laut MEDLINE: RNA, Deep Learning, Computational Biology. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vetenskapsrådet, Knut and Alice Wallenberg Foundation, National Supercomputer Centre at Linköping University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, tremendous advances have been made in predicting protein structures and protein–protein interactions, but progress on RNA structure, alone or in complex with other macromolecules, has lagged behind despite recent methodological developments. It remains unclear whether reported gains in accuracy generalize to novel RNA structures. Here, we benchmark 10 deep learning methods on an independent, non-redundant dataset of monomeric RNAs and RNA complexes. For monomeric RNA, AlphaFold3 and Boltz-1 achieve the best overall performance, but accuracy depends greatly on similarity to the training set: predictions are reliable mainly for RNAs with well-defined or recurring folds, such as L-shaped and simple loop structures, while structurally divergent RNAs remain poorly modelled. Extending the evaluation to RNA complexes, AlphaFold3 and Boltz-1 substantially outperform HelixFold3 and RosettaFoldNA, with no statistically significant difference between the two leading methods on most measures. Together, these results show that current methods are constrained by limited, structurally biased training data and recognize recurring motifs rather than generalize to novel RNA folds.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RNADeep LearningComputational BiologyNucleic Acid ConformationPrediction AlgorithmsRNA FoldingModels, MolecularSoftwareAlgorithms

Substanzen

RNA

Autor:innen und Institutionen

  • Science for Life Laboratory and Department of Biochemistry and Biophysics, Stockholm University, Solna 171 21, Sweden.

ORCID-Profile: Arne Elofsson

Förderung

  • Vetenskapsrådet
  • Knut and Alice Wallenberg Foundation
  • National Supercomputer Centre at Linköping University
  • SNIC

Zitieren

APA

Ludaic, M., & Elofsson, A. (2026). Limits of deep-learning-based RNA prediction methods. Nucleic Acids Research, 54(16). https://doi.org/10.1093/nar/gkag813

Vancouver

Ludaic M, Elofsson A. Limits of deep-learning-based RNA prediction methods. Nucleic Acids Research. 2026;54(16). doi:10.1093/nar/gkag813

BibTeX
@article{Ludaic2026,
  author = {Ludaic, Marko and Elofsson, Arne},
  title = {Limits of deep-learning-based RNA prediction methods},
  journal = {Nucleic Acids Research},
  year = {2026},
  volume = {54},
  number = {16},
  doi = {10.1093/nar/gkag813}
}
Kostenlos starten →