De novo design of protein structure and function with RFdiffusion

Watson, Joseph L.; Juergens, David; Bennett, Nathaniel R.; Trippe, Brian L.; Yim, Jason; Eisenach, Helen E.; Ahern, Woody; Borst, Andrew J.; Ragotte, Robert J.; Milles, Lukas F.; Wicky, Basile I.  M.; Hanikel, Nikita; Pellock, Samuel J.; Courbet, Alexis; Sheffler, William; Wang, Jue; Venkatesh, Preetham; Sappington, Isaac; Torres, Susana Vázquez; Lauko, Anna; De Bortoli, Valentin; Mathieu, Emile; Ovchinnikov, Sergey; Barzilay, Regina; Jaakkola, Tommi S.; DiMaio, Frank; Baek, Minkyung; Baker, David

doi:10.1038/s41586-023-06415-8

De novo design of protein structure and function with RFdiffusion

Journal Article · 11 July 2023 · Nature (London)

DOI:https://doi.org/10.1038/s41586-023-06415-8· OSTI ID:2420884

Watson, Joseph L. ^[1]; Juergens, David; ; Trippe, Brian L.; ; Eisenach, Helen E.; Ahern, Woody; ; Ragotte, Robert J.; ; ; ; ; ; Sheffler, William; Wang, Jue; Venkatesh, Preetham; Sappington, Isaac; Torres, Susana Vázquez; Lauko, Anna more »

OSTI

Abstract

There has been considerable recent progress in designing new proteins using deep-learning methods^1–9. Despite this progress, a general deep-learning framework for protein design that enables solution of a wide range of design challenges, including de novo binder design and design of higher-order symmetric architectures, has yet to be described. Diffusion models^10,11have had considerable success in image and language generative modelling but limited success when applied to protein modelling, probably due to the complexity of protein backbone geometry and sequence–structure relationships. Here we show that by fine-tuning the RoseTTAFold structure prediction network on protein structure denoising tasks, we obtain a generative model of protein backbones that achieves outstanding performance on unconditional and topology-constrained protein monomer design, protein binder design, symmetric oligomer design, enzyme active site scaffolding and symmetric motif scaffolding for therapeutic and metal-binding protein design. We demonstrate the power and generality of the method, called RoseTTAFold diffusion (RFdiffusion), by experimentally characterizing the structures and functions of hundreds of designed symmetric assemblies, metal-binding proteins and protein binders. The accuracy of RFdiffusion is confirmed by the cryogenic electron microscopy structure of a designed binder in complex with influenza haemagglutinin that is nearly identical to the design model. In a manner analogous to networks that produce images from user-specified inputs, RFdiffusion enables the design of diverse functional proteins from simple molecular specifications.

Research Organization:: Univ. of Washington, Seattle, WA (United States)

Sponsoring Organization:: USDOE Office of Science (SC)

DOE Contract Number:: SC0018940

OSTI ID:: 2420884

Journal Information:: Nature (London), Journal Name: Nature (London) Journal Issue: 7976 Vol. 620; ISSN 0028-0836

Publisher:: Nature Publishing Group

Country of Publication:: United States

Language:: English

References (43)

THEORY OF PROTEIN FOLDING: The Energy Landscape Perspective Onuchic, José Nelson; Luthey-Schulten, Zaida; Wolynes, Peter G. Annual Review of Physical Chemistry, Vol. 48, Issue 1 https://doi.org/10.1146/annurev.physchem.48.1.545	journal	October 1997
Structure of the MDM2 Oncoprotein Bound to the p53 Tumor Suppressor Transactivation Domain Kussie, Paul H.; Gorina, Svetlana; Marechal, Vincent Science, Vol. 274, Issue 5289 https://doi.org/10.1126/science.274.5289.948	journal	November 1996
Illuminating protein space with a programmable generative model Ingraham, John; Baranov, Max; Costello, Zak bioRxiv https://doi.org/10.1101/2022.12.01.518682	preprint	December 2022
The advent of de novo proteins for cancer immunotherapy Quijano-Rubio, Alfredo; Ulge, Umut Y.; Walkey, Carl D. Current Opinion in Chemical Biology, Vol. 56 https://doi.org/10.1016/j.cbpa.2020.02.002	journal	June 2020
De novo design of luciferases using deep learning Yeh, Andy Hsien-Wei; Norn, Christoffer; Kipnis, Yakov Nature, Vol. 614, Issue 7949 https://doi.org/10.1038/s41586-023-05696-3	journal	February 2023
Inhibiting the p53–MDM2 interaction: an important target for cancer therapy Chène, Patrick Nature Reviews Cancer, Vol. 3, Issue 2 https://doi.org/10.1038/nrc991	journal	February 2003
Design of a Novel Globular Protein Fold with Atomic-Level Accuracy Kuhlman, Brian; Dantas, Gautam; Ireton, Gregory C. Science, Vol. 302, Issue 5649 https://doi.org/10.1126/science.1089427	journal	November 2003
Bottom-up de novo design of functional proteins with complex structural features Yang, Che; Sesterhenn, Fabian; Bonet, Jaume Nature Chemical Biology, Vol. 17, Issue 4 https://doi.org/10.1038/s41589-020-00699-x	journal	January 2021
Control of Protein Oligomerization Symmetry by Metal Coordination: C ₂ and C ₃ Symmetrical Assemblies through Cu ^II and Ni ^II Coordination Salgado, Eric N.; Lewis, Richard A.; Mossin, Susanne Inorganic Chemistry, Vol. 48, Issue 7 https://doi.org/10.1021/ic9001237	journal	April 2009
Mechanism and Catalytic Site Atlas (M-CSA): a database of enzyme reaction mechanisms and active sites Ribeiro, António J. M.; Holliday, Gemma L.; Furnham, Nicholas Nucleic Acids Research, Vol. 46, Issue D1 https://doi.org/10.1093/nar/gkx1012	journal	November 2017
Robust deep learning–based protein sequence design using ProteinMPNN Dauparas, J.; Anishchenko, I.; Bennett, N. Science, Vol. 378, Issue 6615 https://doi.org/10.1126/science.add2187	journal	October 2022
Design of protein-binding proteins from the target structure alone Cao, Longxing; Coventry, Brian; Goreshnik, Inna Nature, Vol. 605, Issue 7910 https://doi.org/10.1038/s41586-022-04654-9	journal	March 2022
ProtGPT2 is a deep unsupervised language model for protein design Ferruz, Noelia; Schmidt, Steffen; Höcker, Birte Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-32007-7	journal	July 2022
Structural Symmetry and Protein Function Goodsell, David S.; Olson, Arthur J. Annual Review of Biophysics and Biomolecular Structure, Vol. 29, Issue 1 https://doi.org/10.1146/annurev.biophys.29.1.105	journal	June 2000
Induction of Potent Neutralizing Antibody Responses by a Designed Protein Nanoparticle Vaccine for Respiratory Syncytial Virus Marcandalli, Jessica; Fiala, Brooke; Ols, Sebastian Cell, Vol. 176, Issue 6 https://doi.org/10.1016/j.cell.2019.01.046	journal	March 2019
Accurate prediction of protein structures and interactions using a three-track neural network Baek, Minkyung; DiMaio, Frank; Anishchenko, Ivan Science, Vol. 373, Issue 6557 https://doi.org/10.1126/science.abj8754	journal	July 2021
Large-scale design and refinement of stable proteins using sequence-only models Singer, Jedediah M.; Novotney, Scott; Strickland, Devin PLOS ONE, Vol. 17, Issue 3 https://doi.org/10.1371/journal.pone.0265020	journal	March 2022
Rosetta3: An Object-Oriented Software Suite for the Simulation and Design of Macromolecules Leaver-Fay, Andrew; Tyka, Michael; Lewis, Steven M. Computer Methods, Part C https://doi.org/10.1016/B978-0-12-381270-4.00019-6	book	January 2011
Hallucinating symmetric protein assemblies Wicky, B. I. M.; Milles, L. F.; Courbet, A. Science, Vol. 378, Issue 6615 https://doi.org/10.1126/science.add1964	journal	October 2022
High-resolution de novo structure prediction from primary sequence Wu, Ruidong; Ding, Fan; Wang, Rui bioRxiv https://doi.org/10.1101/2022.07.21.500999	preprint	July 2022
The Protein Data Bank Berman, H. M. Nucleic Acids Research, Vol. 28, Issue 1 https://doi.org/10.1093/nar/28.1.235	journal	January 2000
Catalytic Versatility, Stability, and Evolution of the (βα) ₈ -Barrel Enzyme Fold Sterner, Reinhard; Höcker, Birte Chemical Reviews, Vol. 105, Issue 11 https://doi.org/10.1021/cr030191z	journal	November 2005
Evolution of a designed protein assembly encapsulating its own RNA genome Butterfield, Gabriel L.; Lajoie, Marc J.; Gustafson, Heather H. Nature, Vol. 552, Issue 7685 https://doi.org/10.1038/nature25157	journal	December 2017
Improving de novo protein binder design with deep learning Bennett, Nathaniel R.; Coventry, Brian; Goreshnik, Inna Nature Communications, Vol. 14, Issue 1 https://doi.org/10.1038/s41467-023-38328-5	journal	May 2023
De novo protein design by deep network hallucination Anishchenko, Ivan; Pellock, Samuel J.; Chidyausiku, Tamuka M. Nature, Vol. 600, Issue 7889 https://doi.org/10.1038/s41586-021-04184-w	journal	December 2021
An enumerative algorithm for de novo design of proteins with diverse pocket structures Basanta, Benjamin; Bick, Matthew J.; Bera, Asim K. Proceedings of the National Academy of Sciences, Vol. 117, Issue 36 https://doi.org/10.1073/pnas.2005412117	journal	August 2020
Multivalent designed proteins neutralize SARS-CoV-2 variants of concern and confer protection against infection in mice Hunt, Andrew C.; Case, James Brett; Park, Young-Jun Science Translational Medicine, Vol. 14, Issue 646 https://doi.org/10.1126/scitranslmed.abn1252	journal	May 2022
Scaffolding protein functional sites using deep learning Wang, Jue; Lisanza, Sidney; Juergens, David Science, Vol. 377, Issue 6604 https://doi.org/10.1126/science.abn2100	journal	July 2022
Quadrivalent influenza nanoparticle vaccines induce broad protection Boyoglu-Barnum, Seyhan; Ellis, Daniel; Gillespie, Rebecca A. Nature, Vol. 592, Issue 7855 https://doi.org/10.1038/s41586-021-03365-x	journal	March 2021
De novo protein design enables the precise induction of RSV-neutralizing antibodies Sesterhenn, Fabian; Yang, Che; Bonet, Jaume Science, Vol. 368, Issue 6492 https://doi.org/10.1126/science.aay5051	journal	May 2020
Multivalent avimer proteins evolved by exon shuffling of a family of human receptor domains Silverman, Joshua; Lu, Qiang; Bakker, Alice Nature Biotechnology, Vol. 23, Issue 12 https://doi.org/10.1038/nbt1166	journal	November 2005
Computational design of trimeric influenza-neutralizing proteins targeting the hemagglutinin receptor binding site Strauch, Eva-Maria; Bernard, Steffen M.; La, David Nature Biotechnology, Vol. 35, Issue 7 https://doi.org/10.1038/nbt.3907	journal	June 2017
Highly accurate protein structure prediction with AlphaFold Jumper, John; Evans, Richard; Pritzel, Alexander Nature https://doi.org/10.1038/s41586-021-03819-2	journal	July 2021
Massively parallel de novo protein design for targeted therapeutics Chevalier, Aaron; Silva, Daniel-Adriano; Rocklin, Gabriel J. Nature, Vol. 550, Issue 7674 https://doi.org/10.1038/nature23912	journal	September 2017
Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models Anand, Namrata; Achim, Tudor arXiv https://doi.org/10.48550/arXiv.2205.15019	preprint	January 2022
Engineered ACE2 receptor traps potently neutralize SARS-CoV-2 Glasgow, Anum; Glasgow, Jeff; Limonta, Daniel Proceedings of the National Academy of Sciences, Vol. 117, Issue 45 https://doi.org/10.1073/pnas.2016093117	journal	October 2020
Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures Luo, Shitong; Su, Yufeng; Peng, Xingang bioRxiv https://doi.org/10.1101/2022.07.10.499510	preprint	October 2022
Metal templated design of protein interfaces Salgado, Eric N.; Ambroggio, Xavier I.; Brodin, Jeffrey D. Proceedings of the National Academy of Sciences, Vol. 107, Issue 5 https://doi.org/10.1073/pnas.0906852107	journal	December 2009
Generation and Characterization of ALX-0171, a Potent Novel Therapeutic Nanobody for the Treatment of Respiratory Syncytial Virus Infection Detalle, Laurent; Stohr, Thomas; Palomo, Concepción Antimicrobial Agents and Chemotherapy, Vol. 60, Issue 1 https://doi.org/10.1128/AAC.01802-15	journal	October 2015
Evolutionary-scale prediction of atomic-level protein structure with a language model Lin, Zeming; Akin, Halil; Rao, Roshan Science, Vol. 379, Issue 6637 https://doi.org/10.1126/science.ade2574	journal	March 2023
Elicitation of Potent Neutralizing Antibody Responses by Designed Protein Nanoparticle Vaccines for SARS-CoV-2 Walls, Alexandra C.; Fiala, Brooke; Schäfer, Alexandra Cell, Vol. 183, Issue 5 https://doi.org/10.1016/j.cell.2020.10.043	journal	November 2020
Expanding the space of protein geometries by computational design of de novo fold families Pan, Xingjie; Thompson, Michael C.; Zhang, Yang Science, Vol. 369, Issue 6507 https://doi.org/10.1126/science.abc0881	journal	August 2020
Protein structure generation via folding diffusion Wu, Kevin E.; Yang, Kevin K.; Berg, Rianne van den arXiv https://doi.org/10.48550/arXiv.2209.15611	preprint	January 2022

Similar Records

De novo design of high-affinity binders of bioactive helical peptides

Journal Article · 2023 · Nature (London) · OSTI ID:2470002

De novo design of small beta barrel proteins

Journal Article · 2023 · Proceedings of the National Academy of Sciences of the United States of America · OSTI ID:2472357

Computational design of mixed chirality peptide macrocycles with internal symmetry

Journal Article · 2020 · Protein Science · OSTI ID:1786512

Related Subjects

Science & Technology - Other Topics

De novo design of protein structure and function with RFdiffusion

Citation Formats

References (43)

Similar Records

Related Subjects