There has been considerable recent progress in designing new proteins using deep-learning methods1–9. 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 models10,11 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.

Heavy alcohol consumption appears to be the primary driver of changes in the circulating microbiome associated with a shift in its inferred metabolic functions. (Hepatology 2018;67:1284-1302).

There has been considerable recent progress in designing new proteins using deep learning methods. 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 have had considerable success in image and language generative modeling but limited success when applied to protein modeling, likely 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 new designs. In a manner analogous to networks which produce images from user-specified inputs, RFdiffusion enables the design of diverse, complex, functional proteins from simple molecular specifications.

SUMMARY Broadly HIV-1 neutralizing VRC01 class antibodies target the CD4-binding site of Env. They are derived from VH1–2*02 antibody heavy chains paired with rare light chains expressing 5-amino acid-long CDRL3s. They have been isolated from infected subjects but have not yet been elicited by immunization. Env-derived immunogens capable of binding the germline forms of VRC01 B cell receptors on naive B cells have been designed and evaluated in knockin mice. However, the elicited antibodies cannot bypass glycans present on the conserved position N276 of Env, which restricts access to the CD4-binding site. Efforts to guide the appropriate maturation of these antibodies by sequential immunization have not yet been successful. Here, we report on a two-step immunization scheme that leads to the maturation of VRC01-like antibodies capable of accommodating the N276 glycan and displaying autologous tier 2 neutralizing activities. Our results are relevant to clinical trials aiming to elicit VRC01 antibodies.