RNA secondary structure prediction using deep learning with thermodynamic integration

By Kengo Sato, Manato Akiyama, Yasubumi Sakakibara. Nature Communications, 2020

362 citations recorded by the source corpus.

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. Accurately predicting the secondary structure of non-coding RNAs can help unravel their function. Here the authors propose a method integrating thermodynamic information and deep learning to improve the robustness of RNA secondary structure prediction compared to several existing algorithms.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/5d6cff0177271273a166b3c675a972d044c568cd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Accurate prediction of nucleic acid and protein-nucleic acid complexes using RoseTTAFoldNA (2022, methodology): “More recently, deep learning methods have been used for contact prediction to aid in RNA structure determination [8], and to select models from ensembles generated using other structure sampling approaches [9].”
Integrating end-to-end learning with deep geometrical potentials for ab initio RNA structure prediction (2022, positive): “For example, SPOT-RNA 11 , MXfold2 12 and Ufold 13 utilize convolutional neural networks (CNNs) or recurrent neural networks (RNNs) to improve the accuracy of secondary structure (SS) prediction for RNAs.”
Recent advances in RNA structurome (2022, background): “, 2020), MXfold (Sato et al., 2021), SPOT-RNA2 (Singh et al.”
Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions (2022, background): “For example, SPOT-RNA [28], E2Efold [30], MXfold2 [31], and UFold [32] are shown to be able to improve the prediction accuracy significantly on different datasets.”
UFold: fast and accurate RNA secondary structure prediction with deep learning (2020, neutral): “…together with the results of a collection of traditional energy-based, including Con-textfold (52), Contrafold (21), Linearfold (25), Eternafold (53), RNAfold (18), RNAStructure (Fold) (54), RNAsoft (55) and Mfold (19), and recent learning-based methods MXfold2 (41), SPOT-RNA (37) and e2efold (36).”
Accurate prediction of protein–nucleic acid complexes using RoseTTAFoldNA (2023, methodology): “For predicting protein components, machine learning-guided approaches like RoseTTAFold 4 and Alpha-Fold 5 are highly accurate, while RNA structure prediction has used a combination of Monte Carlo sampling approaches 6–9 as well as deep learning methods 10,11 .”