De novo design of RNA pseudoknots with deep learning
Abstract
RNA design has been hindered by the limited accuracy of 3D structure prediction. Here, 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 AI methods matched experienced human designers in solving most blind challenges, evaluated by single-nucleotide-resolution chemical mapping, compensatory mutagenesis, and cryogenic 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.
// Source
Authors: Jill Townley, Wipapat Kladwang, David Baker, Hamish M Blair, Christian Choe, Gina El Nesr, Andrew Favor, Eli Fisker, Daniel B. Haack, Shujun He, J. Hingey, R J Huang, Po‐Ssu Huang, Chaitanya K Joshi, Thomas G. Karagianes, Andrew Kubaney, Pietro Lio, Adamo Mancino, Jonathan Romano, Boris Rudolfs, Nicholas Spellmon, Navtej Toor, Jigyasa Verma, Vivian Wu, Zhiheng Yu, Eterna Participants, Rhiju Das
Institutions: University of Washington, University of California San Diego, Stanford University, University of Cambridge, Texas A&M University, Howard Hughes Medical Institute, Janelia Research Campus, Swift Engineering (United States), Eterna Massive Open Laboratory, CAE Solutions (United States)