RNA secondary structure prediction using deep learning with thermodynamic integration

Research output: Contribution to journalArticlepeer-review

68 Citations (Scopus)


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.

Original languageEnglish
Article number941
JournalNature communications
Issue number1
Publication statusPublished - 2021 Dec 1

ASJC Scopus subject areas

  • Chemistry(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • General
  • Physics and Astronomy(all)


Dive into the research topics of 'RNA secondary structure prediction using deep learning with thermodynamic integration'. Together they form a unique fingerprint.

Cite this