De novo design of protein structure and function with RFdiffusion

By Joseph L. Watson, David Juergens, N. Bennett, Brian L. Trippe, Jason Yim, Helen E. Eisenach, Woody Ahern, A. J. Borst, R. Ragotte, L. Milles and 18 more. 2023

1,299 citations recorded by the source corpus.

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 , 11 have 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. Fine-tuning the RoseTTAFold structure prediction network on protein structure denoising tasks yields a generative model for protein design that achieves outstanding performance on a wide range of protein structure and function design challenges.

Subfields: Genetics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

1. Minkyung Baek
2. Ivan V. Anishchenko
3. Frank DiMaio
4. A. Kang
5. Jue Wang
6. Ryan McHugh
7. A. Bera
8. David Baker

Citations in the corpus

• Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom (2023, positive): “Diffusion-based methods can generate proteins in the context of a protein target that bind with considerable affinity and specificity ( 45 ) and can be trained to explicitly condition on structural features( 46 ).”
• State-specific protein–ligand complex structure prediction with a multiscale deep generative model (2022, neutral): “However, structure prediction models trained with invariant loss can cause inconsistency between integration steps when used for diffusion model sampling due to the arbitrariness of predicted global rotation, which is found to harm the generation quality in related works 30 .”
• A generative model for inorganic materials design (2025, neutral): “Given the enormous impact of generative models in domains such as image generation 47 and protein design 48 , we believe that models such as Matter Gen will equally transform materials design in the coming years.”
• Illuminating protein space with a programmable generative model (2022, neutral): “16, 24–26, Supplementary Appendices N–”