{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T16:56:56Z","timestamp":1775149016214,"version":"3.50.1"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004442","name":"National Science Centre, Poland","doi-asserted-by":"publisher","award":["2020\/39\/O\/ST6\/01488"],"award-info":[{"award-number":["2020\/39\/O\/ST6\/01488"]}],"id":[{"id":"10.13039\/501100004442","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004442","name":"National Science Centre, Poland","doi-asserted-by":"publisher","award":["2024\/53\/B\/ST6\/02789"],"award-info":[{"award-number":["2024\/53\/B\/ST6\/02789"]}],"id":[{"id":"10.13039\/501100004442","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>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.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>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\u2013Crick\u2013Franklin interactions.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>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).<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf515","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T20:46:39Z","timestamp":1758314799000},"source":"Crossref","is-referenced-by-count":5,"title":["Graph neural network and diffusion model for modeling RNA interatomic interactions"],"prefix":"10.1093","volume":"41","author":[{"given":"Marek","family":"Justyna","sequence":"first","affiliation":[{"name":"Institute of Computing Science, Poznan University of Technology , Poznan 60-965,","place":["Poland"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3281-918X","authenticated-orcid":false,"given":"Craig","family":"Zirbel","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, Bowling Green State University , Bowling Green, OH 43403-0206,","place":["United States"]}]},{"given":"Maciej","family":"Antczak","sequence":"additional","affiliation":[{"name":"Institute of Computing Science, Poznan University of Technology , Poznan 60-965,","place":["Poland"]},{"name":"Department of Structural Bioinformatics, Institute of Bioorganic Chemistry PAS , Poznan 61-704,","place":["Poland"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8724-7908","authenticated-orcid":false,"given":"Marta","family":"Szachniuk","sequence":"additional","affiliation":[{"name":"Institute of Computing Science, Poznan University of Technology , Poznan 60-965,","place":["Poland"]},{"name":"Department of Structural Bioinformatics, Institute of Bioorganic Chemistry PAS , Poznan 61-704,","place":["Poland"]}]}],"member":"286","published-online":{"date-parts":[[2025,9,15]]},"reference":[{"key":"2025092619561178900_btaf515-B1","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2025092619561178900_btaf515-B2","doi-asserted-by":"crossref","first-page":"3668","DOI":"10.1093\/bioinformatics\/btac386","article-title":"RNAsolo: a repository of cleaned PDB-derived RNA 3D structures","volume":"38","author":"Adamczyk","year":"2022","journal-title":"Bioinformatics"},{"key":"2025092619561178900_btaf515-B3","author":"Agarap","year":"2019"},{"key":"2025092619561178900_btaf515-B4","doi-asserted-by":"crossref","first-page":"4862","DOI":"10.1093\/bioinformatics\/btz422","article-title":"AlphaFold at CASP13","volume":"35","author":"AlQuraishi","year":"2019","journal-title":"Bioinformatics"},{"key":"2025092619561178900_btaf515-B5","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1186\/s12859-016-1237-9","article-title":"Structural alignment of protein descriptors - a combinatorial model","volume":"17","author":"Antczak","year":"2016","journal-title":"BMC Bioinformatics"},{"key":"2025092619561178900_btaf515-B6","author":"Ba","year":"2016"},{"key":"2025092619561178900_btaf515-B7","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2025092619561178900_btaf515-B8","doi-asserted-by":"crossref","first-page":"lqae048","DOI":"10.1093\/nargab\/lqae048","article-title":"State-of-the-RNArt: benchmarking current methods for RNA 3D structure prediction","volume":"6","author":"Bernard","year":"2024","journal-title":"NAR Genom Bioinform"},{"key":"2025092619561178900_btaf515-B9","doi-asserted-by":"crossref","first-page":"e63\u2013e63","DOI":"10.1093\/nar\/gkv1479","article-title":"SimRNA: a coarse-grained method for RNA folding simulations and 3D structure prediction","volume":"44","author":"Boniecki","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2025092619561178900_btaf515-B10","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1261\/rna.067678.118","article-title":"Barnaba: software for analysis of nucleic acid structures and trajectories","volume":"25","author":"Bottaro","year":"2019","journal-title":"RNA"},{"key":"2025092619561178900_btaf515-B11","doi-asserted-by":"crossref","first-page":"13306","DOI":"10.1093\/nar\/gku972","article-title":"The role of nucleobase interactions in RNA structure and dynamics","volume":"42","author":"Bottaro","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2025092619561178900_btaf515-B12","author":"CASP16","year":"2024"},{"key":"2025092619561178900_btaf515-B13","first-page":"2204","article-title":"Interpretable RNA foundation model from unannotated data for highly accurate RNA structure and function predictions","author":"Chen","year":"2022","journal-title":"arXiv"},{"key":"2025092619561178900_btaf515-B14","author":"Corso"},{"key":"2025092619561178900_btaf515-B15","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1186\/1471-2105-12-344","article-title":"A novel method to compare protein structures using local descriptors","volume":"12","author":"Daniluk","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2025092619561178900_btaf515-B16","author":"Dao","year":"2022"},{"key":"2025092619561178900_btaf515-B17","doi-asserted-by":"crossref","first-page":"1747","DOI":"10.1002\/prot.26602","article-title":"Assessment of three-dimensional RNA structure prediction in CASP15","volume":"91","author":"Das","year":"2023","journal-title":"Proteins"},{"key":"2025092619561178900_btaf515-B18","author":"Gasteiger","year":"2020"},{"key":"2025092619561178900_btaf515-B19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025092619561178900_btaf515-B20","author":"Huguet","year":"2024"},{"key":"2025092619561178900_btaf515-B21","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1002\/prot.22296","article-title":"Local descriptors of protein structure: a systematic analysis of the sequence-structure relationship in proteins using short- and long-range interactions","volume":"75","author":"Hvidsten","year":"2009","journal-title":"Proteins"},{"key":"2025092619561178900_btaf515-B22","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1038\/s42256-024-00815-9","article-title":"Equivariant 3d-conditional diffusion model for molecular linker design","volume":"6","author":"Igashov","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2025092619561178900_btaf515-B23","author":"Joshi","year":"2024"},{"key":"2025092619561178900_btaf515-B24","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1002\/prot.26257","article-title":"Applying and improving AlphaFold at CASP14","volume":"89","author":"Jumper","year":"2021","journal-title":"Proteins"},{"key":"2025092619561178900_btaf515-B25","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2025092619561178900_btaf515-B26","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbad153","article-title":"Machine learning for RNA 2D structure prediction benchmarked on experimental data","volume":"24","author":"Justyna","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025092619561178900_btaf515-B27","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1107\/S0567739476001873","article-title":"A solution for the best rotation to relate two sets of vectors","volume":"32","author":"Kabsch","year":"1976","journal-title":"Acta Cryst A"},{"key":"2025092619561178900_btaf515-B28","doi-asserted-by":"crossref","first-page":"D192","DOI":"10.1093\/nar\/gkaa1047","article-title":"Rfam 14: expanded coverage of metagenomic, viral and microRNA families","volume":"49","author":"Kalvari","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2025092619561178900_btaf515-B29","article-title":"Functional relevance of casp16 nucleic acid predictions as evaluated by structure providers","author":"Kretsch","year":"2025","journal-title":"bioRxiv"},{"key":"2025092619561178900_btaf515-B30","doi-asserted-by":"crossref","first-page":"5745","DOI":"10.1038\/s41467-023-41303-9","article-title":"Integrating end-to-end learning with deep geometrical potentials for ab initio RNA structure prediction","volume":"14","author":"Li","year":"2023","journal-title":"Nat Commun"},{"key":"2025092619561178900_btaf515-B31","author":"Lin","year":"2022"},{"key":"2025092619561178900_btaf515-B32","author":"Lipman","year":"2023"},{"key":"2025092619561178900_btaf515-B33","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/1748-7188-6-26","article-title":"ViennaRNA package 2.0","volume":"6","author":"Lorenz","year":"2011","journal-title":"Algorithms Mol Biol"},{"key":"2025092619561178900_btaf515-B35","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1038\/s41392-022-00916-0","article-title":"Cryo-EM advances in RNA structure determination","volume":"7","author":"Ma","year":"2022","journal-title":"Signal Transduct Target Ther"},{"key":"2025092619561178900_btaf515-B36","doi-asserted-by":"crossref","first-page":"2722","DOI":"10.1093\/bioinformatics\/btt473","article-title":"lDDT: a local superposition-free score for comparing protein structures and models using distance difference tests","volume":"29","author":"Mariani","year":"2013","journal-title":"Bioinformatics"},{"key":"2025092619561178900_btaf515-B37","doi-asserted-by":"crossref","first-page":"1875","DOI":"10.1261\/rna.1700409","article-title":"New metrics for comparing and assessing discrepancies between RNA 3D structures and models","volume":"15","author":"Parisien","year":"2009","journal-title":"RNA"},{"key":"2025092619561178900_btaf515-B38","doi-asserted-by":"crossref","first-page":"5671","DOI":"10.1038\/s41467-025-60872-5","article-title":"RiNALMo: general-purpose RNA language models can generalize well on structure prediction tasks","volume":"16","author":"Peni\u0107","year":"2025","journal-title":"Nat Commun"},{"key":"2025092619561178900_btaf515-B39","doi-asserted-by":"crossref","first-page":"168210","DOI":"10.1016\/j.jmb.2023.168210","article-title":"Arena: rapid and accurate reconstruction of full atomic rna structures from coarse-grained models","volume":"435","author":"Perry","year":"2023","journal-title":"J Mol Biol"},{"key":"2025092619561178900_btaf515-B46","doi-asserted-by":"crossref","first-page":"D128","DOI":"10.1093\/nar\/gkw1008","article-title":"RNAcentral: a comprehensive database of non-coding RNA sequences","volume":"45","author":"Petrov","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2025092619561178900_btaf515-B40","author":"Rombach","year":"2022"},{"key":"2025092619561178900_btaf515-B41","doi-asserted-by":"crossref","first-page":"9522","DOI":"10.1093\/nar\/gkad726","article-title":"When will RNA get its AlphaFold moment?","volume":"51","author":"Schneider","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2025092619561178900_btaf515-B42","doi-asserted-by":"crossref","first-page":"6355","DOI":"10.1093\/nar\/gkn544","article-title":"Unifying evolutionary and thermodynamic information for RNA folding of multiple alignments","volume":"36","author":"Seemann","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2025092619561178900_btaf515-B43","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1038\/s41586-019-1923-7","article-title":"Improved protein structure prediction using potentials from deep learning","volume":"577","author":"Senior","year":"2020","journal-title":"Nature"},{"key":"2025092619561178900_btaf515-B44","author":"Shen","year":"2022"},{"key":"2025092619561178900_btaf515-B45","doi-asserted-by":"crossref","first-page":"2287","DOI":"10.1038\/s41592-024-02487-0","article-title":"Accurate RNA 3D structure prediction using a language model-based deep learning approach","volume":"21","author":"Shen","year":"2024","journal-title":"Nat Methods"},{"key":"2025092619561178900_btaf515-B34","doi-asserted-by":"crossref","first-page":"241","DOI":"10.2478\/fcds-2019-0012","article-title":"RNApolis: computational platform for RNA structure analysis","volume":"44","author":"Szachniuk","year":"2019","journal-title":"Found Comput Decis Sci"},{"key":"2025092619561178900_btaf515-B47","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.1126\/science.abe5650","article-title":"Geometric deep learning of RNA structure","volume":"373","author":"Townshend","year":"2021","journal-title":"Science"},{"key":"2025092619561178900_btaf515-B48","author":"Vaswani","year":"2023"},{"key":"2025092619561178900_btaf515-B49","doi-asserted-by":"crossref","first-page":"7266","DOI":"10.1038\/s41467-023-42528-4","article-title":"trRosettaRNA: automated prediction of RNA 3D structure with transformer network","volume":"14","author":"Wang","year":"2023","journal-title":"Nat Commun"},{"key":"2025092619561178900_btaf515-B50","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1016\/j.str.2020.05.011","article-title":"FARFAR2: improved DE novo rosetta prediction of complex global RNA folds","volume":"28","author":"Watkins","year":"2020","journal-title":"Structure"},{"key":"2025092619561178900_btaf515-B51","article-title":"Boltz-1: democratizing biomolecular interaction modeling","author":"Wohlwend","year":"2024","journal-title":"bioRxiv"},{"key":"2025092619561178900_btaf515-B52","first-page":"9","article-title":"RNA biomarkers: frontier of precision medicine for cancer","volume":"3","author":"Xi","year":"2017","journal-title":"Noncoding RNA"},{"key":"2025092619561178900_btaf515-B53","author":"Xu","year":"2022"},{"key":"2025092619561178900_btaf515-B54","article-title":"Physics-aware graph neural network for accurate RNA 3D structure prediction","author":"Zhang","year":"2022","journal-title":"arXiv Preprint"},{"key":"2025092619561178900_btaf515-B55","doi-asserted-by":"crossref","first-page":"19171","DOI":"10.1038\/s41598-023-46382-8","article-title":"A universal framework for accurate and efficient geometric deep learning of molecular systems","volume":"13","author":"Zhang","year":"2023","journal-title":"Sci Rep"},{"key":"2025092619561178900_btaf515-B56","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1038\/s41419-022-05075-2","article-title":"RNA-based therapeutics: an overview and prospectus","volume":"13","author":"Zhu","year":"2022","journal-title":"Cell Death Dis"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf515\/64274808\/btaf515.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/9\/btaf515\/64274808\/btaf515.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/9\/btaf515\/64274808\/btaf515.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T23:56:22Z","timestamp":1758930982000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf515\/8254448"}},"subtitle":[],"editor":[{"given":"Yann","family":"Ponty","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"references-count":56,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf515","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,9,1]]},"article-number":"btaf515"}}