Predicting RNA Structure Utilizing Attention from Pretrained Language Models
Journal of Chemical Information and Modeling · 14.07.2025 · 65 (13) · 6483-6498
DOI: 10.1021/acs.jcim.4c02094 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 02.07.2025. Verfasst von Ioannis Papazoglou und 3 weiteren Autor:innen. Beteiligte Einrichtung: Biomedical Research Foundation, Academy of Athens, Athens 11527, Greece. Hauptthemen laut MEDLINE: Nucleic Acid Conformation, RNA, Natural Language Processing, Models, Molecular. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Amazon Web Services.
Abstract (Originalsprache)
RNA possesses functional significance that extends beyond the transport of genetic information. The functional roles of noncoding RNA can be mediated through their tertiary and secondary structure, and thus, predicting RNA structure holds great promise for unleashing their applications in diagnostics and therapeutics. However, predicting the three-dimensional (3D) structure of RNA remains challenging. Applying artificial intelligence techniques in the context of natural language processing and large language models (LLMs) could incorporate evolutionary information to RNA 3D structure predictions and address both resource and data scarcity limitations. This approach could achieve faster inference times, while keeping similar accuracy outcomes compared to employing time-consuming multiple sequence alignment schemes, akin to its successful application in protein structure prediction. Herein, we evaluate the suitability of currently available pretrained nucleic acid language models (RNABERT, ERNIE-RNA, RNA Foundational Model (RNA-FM), RiboNucleic Acid Language Model (RiNALMo), and DNABERT) to predict secondary and tertiary RNA structures. We demonstrate that current nucleic acid language models do not effectively capture structural information, mainly due to architectural constraints.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Biomedical Research Foundation, Academy of Athens, Athens 11527, Greece.
- Department of Biology, National and Kapodistrian University of Athens, Athens 15784, Greece.
ORCID-Profile: Zoe Cournia
Förderung
- Amazon Web Services
Zitieren
APA
Papazoglou, I., Chatzigoulas, A., Tsekenis, G., & Cournia, Z. (2025). Predicting RNA Structure Utilizing Attention from Pretrained Language Models. Journal of Chemical Information and Modeling, 65(13), 6483-6498. https://doi.org/10.1021/acs.jcim.4c02094
Vancouver
Papazoglou I, Chatzigoulas A, Tsekenis G, Cournia Z. Predicting RNA Structure Utilizing Attention from Pretrained Language Models. Journal of Chemical Information and Modeling. 2025;65(13):6483-6498. doi:10.1021/acs.jcim.4c02094
BibTeX
@article{Papazoglou2025,
author = {Papazoglou, Ioannis and Chatzigoulas, Alexios and Tsekenis, George and Cournia, Zoe},
title = {Predicting RNA Structure Utilizing Attention from Pretrained Language Models},
journal = {Journal of Chemical Information and Modeling},
year = {2025},
volume = {65},
number = {13},
pages = {6483--6498},
doi = {10.1021/acs.jcim.4c02094}
}
EUVIMED