EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Graph neural network and diffusion model for modeling RNA interatomic interactions

Marek Justyna, Craig Zirbel iD, Maciej Antczak, Marta Szachniuk iD

Bioinformatics · 01.09.2025 · 41 (9)

DOI: 10.1093/bioinformatics/btaf515 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 15.09.2025. Verfasst von Marek Justyna und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Computing Science, Poznan University of Technology, Poznan 60-965, Poland. Hauptthemen laut MEDLINE: Neural Networks, Computer, RNA, Computational Biology. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Centre, Poland.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Ribonucleic acid (RNA) function is inherently linked to its 3D structure, traditionally determined by X-ray crystallography, Nuclear Magnetic Resonance, and Cryo-EM. However, these techniques often lack atomic-level resolution, highlighting the need for accurate in silico RNA structure prediction tools. Current state-of-the-art methods, such as AlphaFold3, Boltz1, RhoFold, or trRosettaRNA, rely on deep learning models that represent residues as frames and use transformers to learn relative positions. While effective for known RNA families, their performance drops for synthetic or novel families. Results In this work, we explore the potential of graph neural networks and denoising diffusion probabilistic models for learning interatomic interactions. We model RNA as a graph in a coarse-grained, five-atom representation and evaluate our approach on a dataset of small RNA substructures, known as local RNA descriptors, which recur even in non-homologous structures. Generalization is assessed using a dataset partitioned by RNA family: the training set consists of rRNA and tRNA structures, while the test set includes descriptors from all other families. Our results demonstrate that the proposed method reliably predicts the structures of unseen descriptors and effectively adheres to user-defined constraints, such as Watson–Crick–Franklin interactions. Availability and implementation The GraphaRNA source code is available on GitHub (github.com/mjustynaPhD/GraphaRNA); training/test datasets and pre-trained model weights are provided on Zenodo (zenodo.org/records/13750967).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerRNAComputational BiologyNucleic Acid ConformationModels, MolecularRNA, TransferGraph Neural Networks

Substanzen

RNARNA, Transfer

Autor:innen und Institutionen

  • Institute of Computing Science, Poznan University of Technology, Poznan 60-965, Poland.
  • Department of Mathematics and Statistics, Bowling Green State University, Bowling Green, OH 43403-0206, United States.
  • Department of Structural Bioinformatics, Institute of Bioorganic Chemistry PAS, Poznan 61-704, Poland.

ORCID-Profile: Craig Zirbel, Marta Szachniuk

Förderung

  • National Science Centre, Poland

Zitieren

APA

Justyna, M., Zirbel, C., Antczak, M., & Szachniuk, M. (2025). Graph neural network and diffusion model for modeling RNA interatomic interactions. Bioinformatics, 41(9). https://doi.org/10.1093/bioinformatics/btaf515

Vancouver

Justyna M, Zirbel C, Antczak M, Szachniuk M. Graph neural network and diffusion model for modeling RNA interatomic interactions. Bioinformatics. 2025;41(9). doi:10.1093/bioinformatics/btaf515

BibTeX
@article{Justyna2025,
  author = {Justyna, Marek and Zirbel, Craig and Antczak, Maciej and Szachniuk, Marta},
  title = {Graph neural network and diffusion model for modeling RNA interatomic interactions},
  journal = {Bioinformatics},
  year = {2025},
  volume = {41},
  number = {9},
  doi = {10.1093/bioinformatics/btaf515}
}
Kostenlos starten →