10ZU

MPNN-fixbb designed RNA molecule

Summary for 10ZU

• Entry DOI: 10.2210/pdb10zu/pdb
• EMDB information: 75575
• Descriptor: RNA (518-MER) (1 entity in total)
• Functional Keywords: synthetic, pseudoknot, kissing multiloops, rna
• Biological source: synthetic construct
• Total number of polymer chains: 1
• Total formula weight: 168048.89

Authors

Haack, D.B.,Spellmon, N.,Favor, A.H.,Kubaney, A.,Baker, D.,Rudolfs, B.,Hingey, J.,Mancino, A.,Yu, Z.,Toor, N.,Das, R. (deposition date: 2026-02-13, release date: 2026-05-27, Last modification date: 2026-09-09)

Primary citation

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.,Lio, P.,Mancino, A.,Romano, J.,Rudolfs, B.,Spellmon, N.,Toor, N.,Verma, J.,Wu, V.,Yu, Z.,Participants, E.,Das, R.
De novo design of RNA pseudoknots with deep learning.
Science, 393:931-937, 2026

PubMed Abstract: 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.

PubMed: 42658941
DOI: 10.1126/science.aeg6829

Experimental method

ELECTRON MICROSCOPY (4 Å)