While deep learning has revolutionized protein structure prediction, almost all experimentally characterized de novo protein designs have been generated using physically based approaches such as Rosetta. Here we describe a deep learning–based protein sequence design method, ProteinMPNN, with outstanding performance in both in silico and experimental tests. On native protein backbones, ProteinMPNN has a sequence recovery of 52.4%, compared to 32.9% for Rosetta. The amino acid sequence at different positions can be coupled between single or multiple chains, enabling application to a wide range of current protein design challenges. We demonstrate the broad utility and high accuracy of ProteinMPNN using X-ray crystallography, cryoEM and functional studies by rescuing previously failed designs, made using Rosetta or AlphaFold, of protein monomers, cyclic homo-oligomers, tetrahedral nanoparticles, and target binding proteins.

No abstract

SUMMARY Microbiome-encoded β-glucuronidase (GUS) enzymes play important roles in human health by metabolizing drugs in the gastrointestinal (GI) tract. The numbers, types and diversity of these proteins in the human GI microbiome, however, remain undefined. We present an atlas of GUS enzymes comprehensive for the Human Microbiome Project GI database. We identify 3,013 total and 279 unique microbiome-encoded GUS proteins clustered into six unique structural categories. We assign their taxonomy, assess cellular localization, reveal the inter-individual variability within the 139 individuals sampled, and discover 112 novel microbial GUS enzymes. A representative in vitro panel of the most common GUS proteins by read abundances highlights structural and functional variabilities within the family, including their differential processing of smaller glucuronides and larger carbohydrates. These data provide a sequencing-to-molecular roadmap for examining microbiome-encoded enzymes essential to human health.

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.