Systematic benchmarking of deep-learning methods for tertiary RNA structure prediction
PLOS Computational Biology · 30.12.2024 · 20 (12) · e1012715
DOI: 10.1371/journal.pcbi.1012715 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 30.12.2024. Verfasst von Akash Bahai und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Biological Sciences (SBS), Nanyang Technological University, Singapore, Singapore. Hauptthemen laut MEDLINE: Deep Learning, RNA, Benchmarking, Nucleic Acid Conformation. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 97 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCIPC CDC HHS, Nanyang Technological University, Ministry of Education Singapore.
Abstract (Originalsprache)
The 3D structure of RNA critically influences its functionality, and understanding this structure is vital for deciphering RNA biology. Experimental methods for determining RNA structures are labour-intensive, expensive, and time-consuming. Computational approaches have emerged as valuable tools, leveraging physics-based-principles and machine learning to predict RNA structures rapidly. Despite advancements, the accuracy of computational methods remains modest, especially when compared to protein structure prediction. Deep learning methods, while successful in protein structure prediction, have shown some promise for RNA structure prediction as well, but face unique challenges. This study systematically benchmarks state-of-the-art deep learning methods for RNA structure prediction across diverse datasets. Our aim is to identify factors influencing performance variation, such as RNA family diversity, sequence length, RNA type, multiple sequence alignment (MSA) quality, and deep learning model architecture. We show that generally ML-based methods perform much better than non-ML methods on most RNA targets, although the performance difference isn’t substantial when working with unseen novel or synthetic RNAs. The quality of the MSA and secondary structure prediction both play an important role and most methods aren’t able to predict non-Watson-Crick pairs in the RNAs. Overall among the automated 3D RNA structure prediction methods, DeepFoldRNA has the best prediction results followed by DRFold as the second best method. Finally, we also suggest possible mitigations to improve the quality of the prediction for future method development.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Biological Sciences (SBS), Nanyang Technological University, Singapore, Singapore.
- School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore.
ORCID-Profile: Yinghui Li
Förderung
- NCIPC CDC HHS
- Nanyang Technological University
- Ministry of Education Singapore
Zitieren
APA
Bahai, A., Kwoh, C. K., Mu, Y., & Li, Y. (2024). Systematic benchmarking of deep-learning methods for tertiary RNA structure prediction. PLOS Computational Biology, 20(12), e1012715. https://doi.org/10.1371/journal.pcbi.1012715
Vancouver
Bahai A, Kwoh CK, Mu Y, Li Y. Systematic benchmarking of deep-learning methods for tertiary RNA structure prediction. PLOS Computational Biology. 2024;20(12):e1012715. doi:10.1371/journal.pcbi.1012715
BibTeX
@article{Bahai2024,
author = {Bahai, Akash and Kwoh, Chee Keong and Mu, Yuguang and Li, Yinghui},
title = {Systematic benchmarking of deep-learning methods for tertiary RNA structure prediction},
journal = {PLOS Computational Biology},
year = {2024},
volume = {20},
number = {12},
pages = {e1012715},
doi = {10.1371/journal.pcbi.1012715}
}
EUVIMED