Cargando…

RNA secondary structure prediction using deep learning with thermodynamic integration

Accurate predictions of RNA secondary structures can help uncover the roles of functional non-coding RNAs. Although machine learning-based models have achieved high performance in terms of prediction accuracy, overfitting is a common risk for such highly parameterized models. Here we show that overf...

Descripción completa

Detalles Bibliográficos
Autores principales: Sato, Kengo, Akiyama, Manato, Sakakibara, Yasubumi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7878809/
https://www.ncbi.nlm.nih.gov/pubmed/33574226
http://dx.doi.org/10.1038/s41467-021-21194-4
_version_ 1783650398361354240
author Sato, Kengo
Akiyama, Manato
Sakakibara, Yasubumi
author_facet Sato, Kengo
Akiyama, Manato
Sakakibara, Yasubumi
author_sort Sato, Kengo
collection PubMed
description Accurate predictions of RNA secondary structures can help uncover the roles of functional non-coding RNAs. Although machine learning-based models have achieved high performance in terms of prediction accuracy, overfitting is a common risk for such highly parameterized models. Here we show that overfitting can be minimized when RNA folding scores learnt using a deep neural network are integrated together with Turner’s nearest-neighbor free energy parameters. Training the model with thermodynamic regularization ensures that folding scores and the calculated free energy are as close as possible. In computational experiments designed for newly discovered non-coding RNAs, our algorithm (MXfold2) achieves the most robust and accurate predictions of RNA secondary structures without sacrificing computational efficiency compared to several other algorithms. The results suggest that integrating thermodynamic information could help improve the robustness of deep learning-based predictions of RNA secondary structure.
format Online
Article
Text
id pubmed-7878809
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-78788092021-02-24 RNA secondary structure prediction using deep learning with thermodynamic integration Sato, Kengo Akiyama, Manato Sakakibara, Yasubumi Nat Commun Article Accurate predictions of RNA secondary structures can help uncover the roles of functional non-coding RNAs. Although machine learning-based models have achieved high performance in terms of prediction accuracy, overfitting is a common risk for such highly parameterized models. Here we show that overfitting can be minimized when RNA folding scores learnt using a deep neural network are integrated together with Turner’s nearest-neighbor free energy parameters. Training the model with thermodynamic regularization ensures that folding scores and the calculated free energy are as close as possible. In computational experiments designed for newly discovered non-coding RNAs, our algorithm (MXfold2) achieves the most robust and accurate predictions of RNA secondary structures without sacrificing computational efficiency compared to several other algorithms. The results suggest that integrating thermodynamic information could help improve the robustness of deep learning-based predictions of RNA secondary structure. Nature Publishing Group UK 2021-02-11 /pmc/articles/PMC7878809/ /pubmed/33574226 http://dx.doi.org/10.1038/s41467-021-21194-4 Text en © The Author(s) 2021 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.
spellingShingle Article
Sato, Kengo
Akiyama, Manato
Sakakibara, Yasubumi
RNA secondary structure prediction using deep learning with thermodynamic integration
title RNA secondary structure prediction using deep learning with thermodynamic integration
title_full RNA secondary structure prediction using deep learning with thermodynamic integration
title_fullStr RNA secondary structure prediction using deep learning with thermodynamic integration
title_full_unstemmed RNA secondary structure prediction using deep learning with thermodynamic integration
title_short RNA secondary structure prediction using deep learning with thermodynamic integration
title_sort rna secondary structure prediction using deep learning with thermodynamic integration
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7878809/
https://www.ncbi.nlm.nih.gov/pubmed/33574226
http://dx.doi.org/10.1038/s41467-021-21194-4
work_keys_str_mv AT satokengo rnasecondarystructurepredictionusingdeeplearningwiththermodynamicintegration
AT akiyamamanato rnasecondarystructurepredictionusingdeeplearningwiththermodynamicintegration
AT sakakibarayasubumi rnasecondarystructurepredictionusingdeeplearningwiththermodynamicintegration