De novo design of RNA pseudoknots with deep learning
Science · 27.08.2026 · 393 (6814) · 931-937
DOI: 10.1126/science.aeg6829 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science, erschienen am 27.08.2026. Verfasst von Jill Townley und 26 weiteren Autor:innen. Beteiligte Einrichtung: Eterna Massive Open Laboratory, USA. Hauptthemen laut MEDLINE: Deep Learning, RNA, Nucleic Acid Conformation. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: National Science Foundation, National Institutes of Health, Howard Hughes Medical Institute.
Abstract (Originalsprache)
RNA design has been hindered by the limited accuracy of three-dimensional (3D) structure prediction. In this study, we show that intricate RNA structures can be generated with current deep learning tools through accurate de novo design of pseudoknot secondary structures. In an Eterna competition involving 57 pseudoknots, generative artificial intelligence (AI) methods matched experienced human designers in solving most blind challenges, evaluated by single nucleotide–resolution chemical mapping, compensatory mutagenesis, and cryo–electron microscopy. AI-generated molecules with accurate secondary structures formed well-ordered 3D folds stabilized by noncanonical tertiary interactions not modeled during design. Success was guided by an RNet foundation model trained on prior chemical mapping data, suggesting that some difficult RNA design tasks may be tractable without first solving RNA 3D structure prediction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Eterna Massive Open Laboratory, USA.
- Frameshifter, San Francisco, CA, USA.
- Department of Biochemistry, Stanford University School of Medicine, Stanford, CA, USA.
- Howard Hughes Medical Institute, Stanford, CA, USA.
- Department of Biochemistry, University of Washington, Seattle, WA, USA.
- Howard Hughes Medical Institute, Seattle, WA, USA.
ORCID-Profile: Wipapat Kladwang, David Baker, Hamish M Blair, Christian A Choe, Gina El Nesr, Andrew Favor, Eli Fisker, Daniel B Haack, Shujun He, Jason Hingey, Po-Ssu Huang, Rui Huang, Chaitanya K Joshi, Thomas Karagianes, Andrew Kubaney, Pietro Liò, Adamo Mancino, Jonathan Romano, Boris Rudolfs, Nicholas Spellmon, Navtej Toor, Jigyasa Verma, Vivian Wu, Zhiheng Yu, Rhiju Das
Förderung
- National Science Foundation
- National Institutes of Health
- Howard Hughes Medical Institute
- Qualcomm Innovation Fellowship
- A*STAR Singapore National Science Scholarship
Zitieren
APA
Townley, J., Kladwang, W., Baker, D., Blair, H. M., Choe, C. A., El Nesr, G., Favor, A., Fisker, E., Haack, D. B., He, S., Hingey, J., Huang, P. S., Huang, R., Joshi, C. K., Karagianes, T., Kubaney, A., Liò, P., Mancino, A., Romano, J., …, & Das, R. (2026). De novo design of RNA pseudoknots with deep learning. Science, 393(6814), 931-937. https://doi.org/10.1126/science.aeg6829
Vancouver
Townley J, Kladwang W, Baker D, Blair HM, Choe CA, El Nesr G, et al. De novo design of RNA pseudoknots with deep learning. Science. 2026;393(6814):931-937. doi:10.1126/science.aeg6829
BibTeX
@article{Townley2026,
author = {Townley, Jill and Kladwang, Wipapat and Baker, David and Blair, Hamish M and Choe, Christian A and El Nesr, Gina and Favor, Andrew and Fisker, Eli and Haack, Daniel B and He, Shujun and Hingey, Jason and Huang, Po-Ssu and Huang, Rui and Joshi, Chaitanya K and Karagianes, Thomas and Kubaney, Andrew and Liò, Pietro and Mancino, Adamo and Romano, Jonathan and Rudolfs, Boris and Spellmon, Nicholas and Toor, Navtej and Verma, Jigyasa and Wu, Vivian and Yu, Zhiheng and Participants, Eterna and Das, Rhiju},
title = {De novo design of RNA pseudoknots with deep learning},
journal = {Science},
year = {2026},
volume = {393},
number = {6814},
pages = {931--937},
doi = {10.1126/science.aeg6829}
}
EUVIMED