{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T23:20:05Z","timestamp":1763853605630,"version":"3.45.0"},"reference-count":47,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072210"],"award-info":[{"award-number":["62072210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Accurate prediction of RNA secondary structure remains challenging due to the presence of pseudoknots, long-range dependencies, and limited labeled data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We propose TVAE, a novel framework that integrates a Transformer encoder with a Variational Autoencoder (VAE). The Transformer captures global dependencies in the sequence, while the VAE models structural variability by learning a probabilistic latent space. Unlike deterministic models, TVAE generates diverse and biologically plausible secondary structures, enabling more comprehensive structure discovery. To obtain discrete predictions, we introduce GHA-Pairing, a fast and biologically constrained base-pairing algorithm. TVAE demonstrates strong generalization across different RNA families and achieves state-of-the-art performance on benchmark datasets, reaching an F1 score of 0.89 and 83% accuracy, surpassing existing methods by 10%. These results highlight the advantage of probabilistic modeling for RNA structure prediction and its potential to enhance biological insights.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Code and pretrained models are available at https:\/\/github.com\/mei-rna\/TVAE-RNA. The released version of the dataset and models can also be accessed via DOI: 10.5281\/zenodo.16946114.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf527","type":"journal-article","created":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T11:53:20Z","timestamp":1758369200000},"source":"Crossref","is-referenced-by-count":0,"title":["TVAE-RNA: ensemble-based RNA secondary structure prediction via transformer variational autoencoders"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9487-5630","authenticated-orcid":false,"given":"Xiyuan","family":"Mei","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , Changchun 130012,","place":["China"]}]},{"given":"Hanbo","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , Changchun 130012,","place":["China"]}]},{"given":"Yuheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , Changchun 130012,","place":["China"]}]},{"given":"Enshuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , Changchun 130012,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6572-3544","authenticated-orcid":false,"given":"Longyi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , Changchun 130012,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2058-7123","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , Changchun 130012,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"2025112218171654400_btaf527-B1","doi-asserted-by":"crossref","first-page":"1840025","DOI":"10.1142\/S0219720018400255","article-title":"A max-margin training of RNA secondary structure prediction integrated with the thermodynamic model","volume":"16","author":"Akiyama","year":"2018","journal-title":"J Bioinform Comput Biol"},{"key":"2025112218171654400_btaf527-B2","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search programs","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res"},{"key":"2025112218171654400_btaf527-B3","doi-asserted-by":"crossref","first-page":"D146","DOI":"10.1093\/nar\/gkq1138","article-title":"lncRNAdb: a reference database for long noncoding RNAs","volume":"39","author":"Amaral","year":"2011","journal-title":"Nucleic Acids Res"},{"key":"2025112218171654400_btaf527-B4","first-page":"2745","volume-title":"Proceedings of the IEEE International Conference on Computer Vision, Italy","author":"Bao","year":"2017"},{"key":"2025112218171654400_btaf527-B5","doi-asserted-by":"crossref","first-page":"a003566","DOI":"10.1101\/cshperspect.a003566","article-title":"Riboswitches and the RNA world","volume":"4","author":"Breaker","year":"2012","journal-title":"Cold Spring Harb Perspect Biol"},{"key":"2025112218171654400_btaf527-B6"},{"key":"2025112218171654400_btaf527-B7","doi-asserted-by":"crossref","first-page":"1302","DOI":"10.1021\/ar200098t","article-title":"The molecular interactions that stabilize RNA tertiary structure: RNA motifs, patterns, and networks","volume":"44","author":"Butcher","year":"2011","journal-title":"Acc Chem Res"},{"key":"2025112218171654400_btaf527-B8","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1038\/s41580-024-00748-6","article-title":"Identification of RNA structures and their roles in RNA functions","volume":"25","author":"Cao","year":"2024","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2025112218171654400_btaf527-B9"},{"key":"2025112218171654400_btaf527-B10","doi-asserted-by":"crossref","first-page":"e1004473","DOI":"10.1371\/journal.pcbi.1004473","article-title":"Rich RNA structure landscapes revealed by mutate-and-map analysis","volume":"11","author":"Cordero","year":"2015","journal-title":"PLoS Comput Biol"},{"key":"2025112218171654400_btaf527-B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1903.05789"},{"key":"2025112218171654400_btaf527-B12","doi-asserted-by":"crossref","first-page":"628137","DOI":"10.3389\/fbioe.2021.628137","article-title":"The limitless future of RNA therapeutics","volume":"9","author":"Damase","year":"2021","journal-title":"Front Bioeng Biotechnol"},{"key":"2025112218171654400_btaf527-B13","doi-asserted-by":"crossref","first-page":"5381","DOI":"10.1093\/nar\/gky285","article-title":"bpRNA: large-scale automated annotation and analysis of RNA secondary structure","volume":"46","author":"Danaee","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2025112218171654400_btaf527-B14","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1038\/nature10885","article-title":"Functional complexity and regulation through RNA dynamics","volume":"482","author":"Dethoff","year":"2012","journal-title":"Nature"},{"key":"2025112218171654400_btaf527-B15","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1038\/nature12756","article-title":"In vivo genome-wide profiling of RNA secondary structure reveals novel regulatory features","volume":"505","author":"Ding","year":"2014","journal-title":"Nature"},{"key":"2025112218171654400_btaf527-B16","doi-asserted-by":"crossref","first-page":"e90","DOI":"10.1093\/bioinformatics\/btl246","article-title":"CONTRAfold: RNA secondary structure prediction without physics-based models","volume":"22","author":"Do","year":"2006","journal-title":"Bioinformatics"},{"key":"2025112218171654400_btaf527-B17"},{"key":"2025112218171654400_btaf527-B18","doi-asserted-by":"crossref","first-page":"e14","DOI":"10.1093\/nar\/gkab1074","article-title":"UFold: fast and accurate RNA secondary structure prediction with deep learning","volume":"50","author":"Fu","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2025112218171654400_btaf527-B19","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1038\/s41576-020-00302-y","article-title":"RNA-binding proteins in human genetic disease","volume":"22","author":"Gebauer","year":"2021","journal-title":"Nat Rev Genet"},{"key":"2025112218171654400_btaf527-B20","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1038\/s42003-024-05952-w","article-title":"KnotFold for RNA secondary structure prediction with pseudoknots","volume":"7","author":"Gong","year":"2024","journal-title":"Commun Biol"},{"key":"2025112218171654400_btaf527-B21","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1093\/nar\/gkg006","article-title":"Rfam: an RNA family database","volume":"31","author":"Griffiths-Jones","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2025112218171654400_btaf527-B22","doi-asserted-by":"crossref","first-page":"5498","DOI":"10.1073\/pnas.1219988110","article-title":"Accurate SHAPE-directed RNA secondary structure modeling, including pseudoknots","volume":"110","author":"Hajdin","year":"2013","journal-title":"Proc Natl Acad Sci USA"},{"key":"2025112218171654400_btaf527-B23","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2025112218171654400_btaf527-B24","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1017\/S0033583500003620","article-title":"RNA secondary structure: physical and computational aspects","volume":"33","author":"Higgs","year":"2000","journal-title":"Q Rev Biophys"},{"key":"2025112218171654400_btaf527-B25","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1016\/j.sbi.2005.04.005","article-title":"RNA structure: the long and the short of it","volume":"15","author":"Holbrook","year":"2005","journal-title":"Curr Opin Struct Biol"},{"key":"2025112218171654400_btaf527-B26","doi-asserted-by":"crossref","first-page":"8638","DOI":"10.1093\/nar\/gkv857","article-title":"In silico and in vitro evaluation of exonic and intronic off-target effects forms a critical element of therapeutic ASO design","volume":"43","author":"Kamola","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2025112218171654400_btaf527-B27","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"Li","year":"2006","journal-title":"Bioinformatics"},{"key":"2025112218171654400_btaf527-B28","doi-asserted-by":"crossref","first-page":"1","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":"2025112218171654400_btaf527-B29","doi-asserted-by":"crossref","first-page":"btae022","DOI":"10.1093\/bioinformatics\/btae022","article-title":"Concurrent prediction of RNA secondary structures with pseudoknots and local 3D motifs in an integer programming framework","volume":"40","author":"Loyer","year":"2024","journal-title":"Bioinformatics"},{"year":"2007","author":"Mills-Tettey","key":"2025112218171654400_btaf527-B30"},{"key":"2025112218171654400_btaf527-B31","doi-asserted-by":"crossref","first-page":"6309","DOI":"10.1073\/pnas.77.11.6309","article-title":"Fast algorithm for predicting the secondary structure of single-stranded RNA","volume":"77","author":"Nussinov","year":"1980","journal-title":"Proc Natl Acad Sci USA"},{"key":"2025112218171654400_btaf527-B32","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1186\/1471-2105-11-129","article-title":"RNAstructure: software for RNA secondary structure prediction and analysis","volume":"11","author":"Reuter","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2025112218171654400_btaf527-B33","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1038\/nature12894","article-title":"Genome-wide probing of RNA structure reveals active unfolding of mRNA structures in vivo","volume":"505","author":"Rouskin","year":"2014","journal-title":"Nature"},{"key":"2025112218171654400_btaf527-B34","doi-asserted-by":"crossref","first-page":"bbad186","DOI":"10.1093\/bib\/bbad186","article-title":"RNA information science trends: a review of machine learning and deep learning in RNA secondary structure prediction and RNA drug discovery","volume":"24","author":"Sato","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025112218171654400_btaf527-B35","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1038\/s41467-021-21194-4","article-title":"RNA secondary structure prediction using deep learning with thermodynamic integration","volume":"12","author":"Sato","year":"2021","journal-title":"Nat Commun"},{"key":"2025112218171654400_btaf527-B36","first-page":"1","article-title":"E2Efold-3D: end-to-end deep learning method for accurate de novo RNA 3D structure prediction","volume":"13","author":"Shen","year":"2022","journal-title":"Nat Commun"},{"key":"2025112218171654400_btaf527-B37","doi-asserted-by":"crossref","first-page":"5407","DOI":"10.1038\/s41467-019-13395-9","article-title":"RNA secondary structure prediction using an ensemble of two-dimensional deep neural networks and transfer learning","volume":"10","author":"Singh","year":"2019","journal-title":"Nat Commun"},{"key":"2025112218171654400_btaf527-B38","doi-asserted-by":"crossref","first-page":"2589","DOI":"10.1093\/bioinformatics\/btab165","article-title":"Improved RNA secondary structure and tertiary base-pairing prediction using evolutionary profile, mutational coupling and two-dimensional transfer learning","volume":"37","author":"Singh","year":"2021","journal-title":"Bioinformatics"},{"key":"2025112218171654400_btaf527-B39","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1007\/s00018-005-5558-5","article-title":"Hairpin RNA: a secondary structure of primary importance","volume":"63","author":"Svoboda","year":"2006","journal-title":"Cell Mol Life Sci"},{"key":"2025112218171654400_btaf527-B40","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1007\/s00362-012-0443-4","article-title":"A generalization of the Wilcoxon signed-rank test and its applications","volume":"54","author":"Taheri","year":"2013","journal-title":"Stat Papers"},{"key":"2025112218171654400_btaf527-B41","doi-asserted-by":"crossref","first-page":"e7","DOI":"10.1017\/S0033583516000020","article-title":"RNA structure through multidimensional chemical mapping","volume":"49","author":"Tian","year":"2016","journal-title":"Q Rev Biophys"},{"key":"2025112218171654400_btaf527-B42","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1038\/nrg3049","article-title":"Understanding the transcriptome through RNA structure","volume":"12","author":"Wan","year":"2011","journal-title":"Nat Rev Genet"},{"key":"2025112218171654400_btaf527-B43","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1038\/nature08237","article-title":"Architecture and secondary structure of an entire HIV-1 RNA genome","volume":"460","author":"Watts","year":"2009","journal-title":"Nature"},{"key":"2025112218171654400_btaf527-B44","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.sbi.2010.04.001","article-title":"Advances in RNA structure analysis by chemical probing","volume":"20","author":"Weeks","year":"2010","journal-title":"Curr Opin Struct Biol"},{"key":"2025112218171654400_btaf527-B45","doi-asserted-by":"crossref","first-page":"e7","DOI":"10.1093\/nar\/gkac1029","article-title":"LazySampling and LinearSampling: fast stochastic sampling of RNA secondary structure with applications to SARS-CoV-2","volume":"51","author":"Zhang","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2025112218171654400_btaf527-B46","doi-asserted-by":"crossref","first-page":"2647","DOI":"10.1016\/j.bpj.2024.01.026","article-title":"Machine learning in RNA structure prediction: advances and challenges","volume":"123","author":"Zhang","year":"2024","journal-title":"Biophys J"},{"first-page":"16259","year":"2021","author":"Zhao","key":"2025112218171654400_btaf527-B47"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf527\/64344537\/btaf527.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/11\/btaf527\/64344537\/btaf527.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/11\/btaf527\/64344537\/btaf527.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T23:17:53Z","timestamp":1763853473000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf527\/8261371"}},"subtitle":[],"editor":[{"given":"Jianlin","family":"Cheng","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":47,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf527","relation":{},"ISSN":["1367-4811"],"issn-type":[{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2025,11]]},"published":{"date-parts":[[2025,9,22]]},"article-number":"btaf527"}}