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

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. 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. On native protein backbones, ProteinMPNN has a sequence recovery of 52.4%, compared to 32.9% for Rosetta. Incorporation of noise during training improves sequence recovery on protein structure models, and produces sequences which more robustly encode their structures as assessed using structure prediction algorithms. 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.

Transmembrane β-barrel proteins (TMBs) are of great interest for single-molecule analytical technologies because they can spontaneously fold and insert into membranes and form stable pores, but the range of pore properties that can be achieved by repurposing natural TMBs is limited. We leverage the power of de novo computational design coupled with a “hypothesis, design, and test” approach to determine TMB design principles, notably, the importance of negative design to slow β-sheet assembly. We design new eight-stranded TMBs, with no homology to known TMBs, that insert and fold reversibly into synthetic lipid membranes and have nuclear magnetic resonance and x-ray crystal structures very similar to the computational models. These advances should enable the custom design of pores for a wide range of applications.

Deep learning generative approaches provide an opportunity to broadly explore protein structure space beyond the sequences and structures of natural proteins. Here we use deep network hallucination to generate a wide range of symmetric protein homo-oligomers given only a specification of the number of protomers and the protomer length. Crystal structures of 7 designs are very close to the computational models (median RMSD: 0.6 Å), as are 3 cryoEM structures of giant 10 nanometer rings with up to 1550 residues and C33 symmetry; all differ considerably from previously solved structures. Our results highlight the rich diversity of new protein structures that can be generated using deep learning, and pave the way for the design of increasingly complex components for nanomachines and biomaterials.

Smart engineered and naturally derived nanovesicles, capable of targeting specific tissues and cells and delivering bioactive molecules and drugs into them, are becoming important drug delivery systems. Liposomes stand out among different types of self-assembled nanovesicles, because of their amphiphilicity and non-toxic nature. By modifying their surfaces, liposomes can become stimulus-responsive, releasing their cargo on demand. Recently, the recognized role of exosomes in cell-cell communication and their ability to diffuse through tissues to find target cells have led to an increase in their usage as smart delivery systems. Moreover, engineering “smarter” delivery systems can be done by creating hybrid exosome-liposome nanocarriers via membrane fusion. These systems can be loaded in naturally derived hydrogels to achieve sustained and controlled drug delivery. Here, the focus is on evaluating the smart behavior of liposomes and exosomes, the fabrication of hybrid exosome-liposome nanovesicles, and the controlled delivery and routes of administration of a hydrogel matrix for drug delivery systems.

Interventions that target biological mechanisms of aging have great potential to enhance quality of life by delaying morbidity and mortality. The FDA-approved drug rapamycin is a compelling candidate for such an intervention. In a previous study, it was reported that 3 months of rapamycin treatment is sufficient to increase life expectancy and remodel the gut microbiome in aged mice. Transient treatment with rapamycin or a rapamycin derivative has also been shown to delay immune stem cell senescence and rejuvenate immune function in aged mice and elderly people. Periodontal disease is an important age-related disease involving altered immune function, pathological changes to the oral microbiome, and systemic inflammation. Periodontal disease is defined clinically by loss of alveolar bone and by connective tissue degeneration. Here, we describe significant alveolar bone loss during aging in two different mouse strain backgrounds and report that rapamycin treatment is sufficient to reverse age-associated periodontal disease in mice. Partial restoration of youthful levels of alveolar bone is observed in 22-month-old rapamycin-treated mice as rapidly as 8 weeks after initiation of treatment. To the best of our knowledge, this represents the first intervention shown to substantially prevent or reverse age-associated alveolar bone loss. These findings suggest the possibility that inhibition of mTOR with rapamycin or other pharmacological agents may be useful to treat a clinically relevant condition for which there is currently no effective treatment.

A systematic and robust approach to generating complex protein nanomaterials would have broad utility. We develop a hierarchical approach to designing multi-component protein assemblies from two classes of modular building blocks: designed helical repeat proteins (DHRs) and helical bundle oligomers (HBs). We first rigidly fuse DHRs to HBs to generate a large library of oligomeric building blocks. We then generate assemblies with cyclic, dihedral, and point group symmetries from these building blocks using architecture guided rigid helical fusion with new software named WORMS. X-ray crystallography and cryo-electron microscopy characterization show that the hierarchical design approach can accurately generate a wide range of assemblies, including a 43 nm diameter icosahedral nanocage. The computational methods and building block sets described here provide a very general route to de novo designed protein nanomaterials.