biostudies-literatureMei XNational Natural Science Foundation of Chinabtaf527https://www.ebi.ac.uk/biostudies/studies/S-EPMC12640237biostudies-literatureUnknown41(11)<h4>Motivation</h4>Accurate prediction of RNA secondary structure remains challenging due to the presence of pseudoknots, long-range dependencies, and limited labeled data.<h4>Results</h4>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.<h4>Availability and implementation</h4>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.Bioinformatics (Oxford, England)TVAE-RNA: ensemble-based RNA secondary structure prediction via transformer variational autoencoders.PMC1264023762072210Liu HMei XZhu YZhang HZhao ELi LfalseTVAE-RNA: ensemble-based RNA secondary structure prediction via transformer variational autoencoders.<h4>Motivation</h4>Accurate prediction of RNA secondary structure remains challenging due to the presence of pseudoknots, long-range dependencies, and limited labeled data.<h4>Results</h4>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.<h4>Availability and implementation</h4>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.16946114.2025-01-01T00:00:00Z2025 Nov2026-06-06T03:13:38.47Z2026-06-06T03:06:34.157ZS-EPMC126402374098150710.1093/bioinformatics/btaf527