Generalized biomolecular modeling and design with RoseTTAFold All-Atom

Abstract

Deep learning methods have revolutionized protein structure prediction and design but are currently limited to protein-only systems. We describe RoseTTAFold All-Atom (RFAA) which combines a residue-based representation of amino acids and DNA bases with an atomic representation of all other groups to model assemblies containing proteins, nucleic acids, small molecules, metals, and covalent modifications given their sequences and chemical structures. By fine tuning on denoising tasks we obtain RFdiffusionAA, which builds protein structures around small molecules. Starting from random distributions of amino acid residues surrounding target small molecules, we design and experimentally validate, through crystallography and binding measurements, proteins that bind the cardiac disease therapeutic digoxigenin, the enzymatic cofactor heme, and the light harvesting molecule bilin.

Metadata

Item Type:	Article
Authors/Creators:	Krishna, R. https://orcid.org/0009-0003-6387-9622 Wang, J. https://orcid.org/0000-0002-1139-6640 Ahern, W. https://orcid.org/0009-0006-1247-8847 Sturmfels, P. Venkatesh, P. https://orcid.org/0000-0002-0089-9365 Kalvet, I. https://orcid.org/0000-0002-6610-2857 Lee, G.R. https://orcid.org/0000-0002-9119-5303 Morey-Burrows, F.S. https://orcid.org/0009-0005-2309-6062 Anishchenko, I. Humphreys, I.R. https://orcid.org/0000-0002-3058-6714 McHugh, R. Vafeados, D. https://orcid.org/0000-0002-2560-8907 Li, X. https://orcid.org/0000-0001-5559-7578 Sutherland, G.A. https://orcid.org/0000-0002-6319-4637 Hitchcock, A. https://orcid.org/0000-0001-6572-434X Hunter, C.N. https://orcid.org/0000-0003-2533-9783 Kang, A. https://orcid.org/0000-0001-5487-0499 Brackenbrough, E. https://orcid.org/0009-0004-1476-0219 Bera, A.K. https://orcid.org/0000-0001-9473-2912 Baek, M. https://orcid.org/0000-0003-3414-9404 DiMaio, F. https://orcid.org/0000-0002-7524-8938 Baker, D. https://orcid.org/0000-0001-7896-6217
Copyright, Publisher and Additional Information:	© 2024 The Authors. Except as otherwise noted, this author-accepted version of a journal article published in Science is made available via the University of Sheffield Research Publications and Copyright Policy under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/
Keywords:	Biochemistry and Cell Biology; Bioinformatics and Computational Biology; Chemical Sciences; Biological Sciences; Bioengineering
Dates:	Published: 19 April 2024 Published (online): 7 March 2024 Accepted: 27 February 2024 Submitted: 9 October 2023
Institution:	The University of Sheffield
Academic Units:	The University of Sheffield > Faculty of Science (Sheffield) > School of Biosciences (Sheffield)
Funding Information:	Funder Grant number EUROPEAN COMMISSION - HORIZON 2020 854126
Depositing User:	Symplectic Sheffield
Date Deposited:	04 Apr 2024 14:44
Last Modified:	08 Nov 2024 16:52
Status:	Published
Publisher:	American Association for the Advancement of Science (AAAS)
Refereed:	Yes
Identification Number:	10.1126/science.adl2528
Related URLs:	PubMed URL
Open Archives Initiative ID (OAI ID):	oai:eprints.whiterose.ac.uk:211216

CORE (COnnecting REpositories)

Generalized biomolecular modeling and design with RoseTTAFold All-Atom

Abstract

Metadata

Download

Accepted Version

Export

Statistics