A divide-and-conquer approach based on deep learning for long RNA secondary structure prediction: Focus on pseudoknots identification.

The accurate prediction of RNA secondary structure, and pseudoknots in particular, is of great importance in understanding the functions of RNAs since they give insights into their folding in three-dimensional space. However, existing approaches often face computational challenges or lack precision...

Full description

Saved in:
Bibliographic Details
Main Authors: Loïc Omnes, Eric Angel, Pierre Bartet, François Radvanyi, Fariza Tahi
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0314837
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850172043475025920
author Loïc Omnes
Eric Angel
Pierre Bartet
François Radvanyi
Fariza Tahi
author_facet Loïc Omnes
Eric Angel
Pierre Bartet
François Radvanyi
Fariza Tahi
author_sort Loïc Omnes
collection DOAJ
description The accurate prediction of RNA secondary structure, and pseudoknots in particular, is of great importance in understanding the functions of RNAs since they give insights into their folding in three-dimensional space. However, existing approaches often face computational challenges or lack precision when dealing with long RNA sequences and/or pseudoknots. To address this, we propose a divide-and-conquer method based on deep learning, called DivideFold, for predicting the secondary structures including pseudoknots of long RNAs. Our approach is able to scale to long RNAs by recursively partitioning sequences into smaller fragments until they can be managed by an existing model able to predict RNA secondary structure including pseudoknots. We show that our approach exhibits superior performance compared to state-of-the-art methods for pseudoknot prediction and secondary structure prediction including pseudoknots for long RNAs. The source code of DivideFold, along with all the datasets used in this study, is accessible at https://evryrna.ibisc.univ-evry.fr/evryrna/dividefold/home.
format Article
id doaj-art-a82d378a02c24065835c3232f71fd5a4
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-a82d378a02c24065835c3232f71fd5a42025-08-20T02:20:09ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01204e031483710.1371/journal.pone.0314837A divide-and-conquer approach based on deep learning for long RNA secondary structure prediction: Focus on pseudoknots identification.Loïc OmnesEric AngelPierre BartetFrançois RadvanyiFariza TahiThe accurate prediction of RNA secondary structure, and pseudoknots in particular, is of great importance in understanding the functions of RNAs since they give insights into their folding in three-dimensional space. However, existing approaches often face computational challenges or lack precision when dealing with long RNA sequences and/or pseudoknots. To address this, we propose a divide-and-conquer method based on deep learning, called DivideFold, for predicting the secondary structures including pseudoknots of long RNAs. Our approach is able to scale to long RNAs by recursively partitioning sequences into smaller fragments until they can be managed by an existing model able to predict RNA secondary structure including pseudoknots. We show that our approach exhibits superior performance compared to state-of-the-art methods for pseudoknot prediction and secondary structure prediction including pseudoknots for long RNAs. The source code of DivideFold, along with all the datasets used in this study, is accessible at https://evryrna.ibisc.univ-evry.fr/evryrna/dividefold/home.https://doi.org/10.1371/journal.pone.0314837
spellingShingle Loïc Omnes
Eric Angel
Pierre Bartet
François Radvanyi
Fariza Tahi
A divide-and-conquer approach based on deep learning for long RNA secondary structure prediction: Focus on pseudoknots identification.
PLoS ONE
title A divide-and-conquer approach based on deep learning for long RNA secondary structure prediction: Focus on pseudoknots identification.
title_full A divide-and-conquer approach based on deep learning for long RNA secondary structure prediction: Focus on pseudoknots identification.
title_fullStr A divide-and-conquer approach based on deep learning for long RNA secondary structure prediction: Focus on pseudoknots identification.
title_full_unstemmed A divide-and-conquer approach based on deep learning for long RNA secondary structure prediction: Focus on pseudoknots identification.
title_short A divide-and-conquer approach based on deep learning for long RNA secondary structure prediction: Focus on pseudoknots identification.
title_sort divide and conquer approach based on deep learning for long rna secondary structure prediction focus on pseudoknots identification
url https://doi.org/10.1371/journal.pone.0314837
work_keys_str_mv AT loicomnes adivideandconquerapproachbasedondeeplearningforlongrnasecondarystructurepredictionfocusonpseudoknotsidentification
AT ericangel adivideandconquerapproachbasedondeeplearningforlongrnasecondarystructurepredictionfocusonpseudoknotsidentification
AT pierrebartet adivideandconquerapproachbasedondeeplearningforlongrnasecondarystructurepredictionfocusonpseudoknotsidentification
AT francoisradvanyi adivideandconquerapproachbasedondeeplearningforlongrnasecondarystructurepredictionfocusonpseudoknotsidentification
AT farizatahi adivideandconquerapproachbasedondeeplearningforlongrnasecondarystructurepredictionfocusonpseudoknotsidentification
AT loicomnes divideandconquerapproachbasedondeeplearningforlongrnasecondarystructurepredictionfocusonpseudoknotsidentification
AT ericangel divideandconquerapproachbasedondeeplearningforlongrnasecondarystructurepredictionfocusonpseudoknotsidentification
AT pierrebartet divideandconquerapproachbasedondeeplearningforlongrnasecondarystructurepredictionfocusonpseudoknotsidentification
AT francoisradvanyi divideandconquerapproachbasedondeeplearningforlongrnasecondarystructurepredictionfocusonpseudoknotsidentification
AT farizatahi divideandconquerapproachbasedondeeplearningforlongrnasecondarystructurepredictionfocusonpseudoknotsidentification