Explore the vast range of titles available.

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.

The field of protein structure modeling has been revolutionized by the introduction of deep learning methods, particularly AlphaFold2, which has achieved near-experimental accuracy in predicting protein structures from amino acid sequences. This dissertation explores the application of diffusion models to create general solutions to protein design tasks. We introduce RFdiffusion, a model that generates protein structures as a series of backbone frames, which achieves state of the art performance on unconditional generation, motif scaffolding, and protein-protein binder design. We then leverage a broadened molecular vocabulary to predict general biomolecular structures including nucleic acids, small molecules, post-translational modifications, metals, and ions with RoseTTAFoldAA. Using the RoseTTAFoldAA architecture we finetune a diffusion model capable of generating proteins which bind small molecules. Finally, we present RFdiffusion2, a flow-matching model trained from random weight initializations capable of unindexed atomic motif scaffolding, enabling the design of enzymes with complex active sites. In all cases we validate the design capabilities of the models in vitro. Our work demonstrates the potential of diffusion models to advance the field of protein design and opens new avenues for enzyme engineering.

Phosphorylation on tyrosine is a key step in many signaling pathways. Despite recent progress in design of protein binders, there are no current methods for designing binders that recognize phosphorylated proteins and peptides; this is a challenging problem as phosphate groups are highly charged, and phosphorylation often occurs within unstructured regions. Here we introduce RoseTTAFold Diffusion 2 for Molecular Interfaces (RFD2-MI), a deep generative framework for the design of binders for protein, ligand, and covalently modified protein targets. We demonstrate the power and versatility of this method by designing binders for four critical phosphotyrosine sites on three clinically relevant targets: Cluster of Differentiation 3 (CD3ε), Epidermal Growth Factor Receptor (EGFR) and Insulin Receptor (INSR). Experimental characterization shows that the designs bind their phospho-tyrosine containing targets with affinities comparable to native binding sites and have negligible binding to non-phosphorylated targets or phosphopeptides with different sequences. X-ray crystal structures of generated binders to CD3ε and EGFR are very close to the design models, demonstrating the accuracy of the design approach. RFD2-MI provides a generalizable all-atom diffusion framework for probing and modulating phosphorylation-dependent signaling, and more generally, for developing research tools and targeted therapeutics against post-translationally modified proteins.

Deep learning methods trained on protein structure databases have revolutionized biomolecular structure prediction, but developing and training new models remains a considerable challenge. To facilitate the development of new models, we present AtomWorks: a broadly applicable data framework for developing state-of-the-art biomolecular foundation models spanning diverse tasks, including structure prediction, generative protein design, and fixed backbone sequence design. We use AtomWorks to train RosettaFold-3 (RF3), a structure prediction network capable of predicting arbitrary biomolecular complexes with an improved treatment of chirality that narrows the performance gap between closed-source AlphaFold3 (AF3) and existing open-source implementations. We expect that AtomWorks will accelerate the next generation of open-source biomolecular machine learning models and that RF3 will be broadly useful as a structure prediction tool. To this end, we release the AtomWorks framework (https://github.com/RosettaCommons/atomworks), together with curated training data, code and model weights for RF3 (https://github.com/RosettaCommons/modelforge) under a permissive BSD license.

Enzymes that proceed through multistep reaction mechanisms often utilize complex, polar active sites positioned with sub-angstrom precision to mediate distinct chemical steps, which makes their de novo construction extremely challenging. We sought to overcome this challenge using the classic catalytic triad and oxyanion hole of serine hydrolases as a model system. We used RFdiffusion to generate proteins housing catalytic sites of increasing complexity and varying geometry, and a newly developed ensemble generation method called ChemNet to assess active site geometry and preorganization at each step of the reaction. Experimental characterization revealed novel serine hydrolases that catalyze ester hydrolysis with catalytic efficiencies ( / ) up to 3.8 x 10 M s , closely match the design models (Cα RMSDs < 1 Å), and have folds distinct from natural serine hydrolases. In silico selection of designs based on active site preorganization across the reaction coordinate considerably increased success rates, enabling identification of new catalysts in screens of as few as 20 designs. Our de novo buildup approach provides insight into the geometric determinants of catalysis that complements what can be obtained from structural and mutational studies of native enzymes (in which catalytic group geometry and active site makeup cannot be so systematically varied), and provides a roadmap for the design of industrially relevant serine hydrolases and, more generally, for designing complex enzymes that catalyze multi-step transformations.

De novo enzyme design starts from ideal active site descriptions consisting of constellations of catalytic residue functional groups around reaction transition state(s), and seeks to generate protein structures that can accurately hold the site in place. Highly active enzymes have been designed starting from such descriptions using the generative AI method RFdiffusion, but there are two current methodological limitations. First, the geometry of the active site can only be specified at the residue level, so for each catalytic residue functional group placed around the reaction transition state, the possible locations of the residue backbone must be enumerated by building side chain rotamers back from the functional group. Second, the location of the catalytic residues along the sequence must be specified in advance, which considerably limits the space of solutions which can be sampled. Here we describe a new deep generative method, RoseTTAFold diffusion 2 (RFdiffusion2), that solves both problems, enabling enzymes to be designed from sequence agnostic descriptions of functional group locations without inverse rotamer generation. We first evaluate RFdiffusion2 on an in silico enzyme design benchmark of 41 diverse active sites and find that it is able to successfully build proteins scaffolding all 41 sites, compared to 16/41 with prior state-of-the-art deep learning methods. Next, we design enzymes around three diverse catalytic sites and characterize the designs experimentally; in each case we identify active catalysts in testing less than 96 sequences. RFdiffusion2 demonstrates the potential of atomic resolution generative models for the design of de novo enzymes directly from their reaction mechanisms.

New enzymes can be designed by starting from a description of an ideal active site composed of catalytic residues surrounding the reaction transition state(s) and identifying or generating a protein scaffold that supports the site, but there are a few current limitations. First, the catalytic efficiencies achieved by such efforts have generally been quite low, and considerable optimization by directed evolution has been required to reach activities typical of native enzymes. Second, generative AI methods such as RFdiffusion now enable the direct generation of proteins around active sites, but to date, such scaffolding has required specification of both the position in the sequence and the backbone coordinates of the catalytic residue, which complicates sampling. Here we introduce a generative AI method called RFflow that overcomes these limitations and use it to design zinc metallohydrolases starting from a density functional theory description of active site geometry. Of 96 designs tested experimentally, the most active has a kcat/KM of 23,000 M-1 s-1, orders of magnitude higher than previously designed metallohydrolases. This 148 amino acid protein has a novel fold with an enclosed chamber which positions the reaction substrate nearly perfectly for attack by a catalytic water molecule activated by the bound metal and is predicted by ChemNet to have a highly preorganized active site. The ability to generate high activity catalysts starting from quantum chemistry calculated active site geometries without experimental optimization should open the door to a new generation of potent designer enzymes.Competing Interest StatementThe authors have declared no competing interest.

Phosphorylation on tyrosine is a key step in many signaling pathways. Despite recent progress in de novo design of protein binders, there are no current methods for designing binders that recognize phosphorylated proteins and peptides; this is a challenging problem as phosphate groups are highly charged, and phosphorylation often occurs within unstructured regions. Here we introduce RoseTTAFold Diffusion 2 for Molecular Interfaces (RFD2-MI), a deep generative framework for the design of binders for protein, ligand, and covalently modified protein targets. We demonstrate the power and versatility of this method by designing binders for four critical phosphotyrosine sites on three clinically relevant targets: Cluster of Differentiation 3 (CD3ε), Epidermal Growth Factor Receptor (EGFR), Insulin Receptor (INSR) and Signal Transducer and Activator of Transcription 5 (STAT5). Experimental characterization shows that the designs bind their phosphotyrosine containing targets with affinities comparable to native binding sites and have negligible binding to non-phosphorylated targets or phosphopeptides with different sequences. X-ray crystal structures of generated binders to CD3ε and EGFR are very close to the design models, demonstrating the accuracy of the design approach. A designed binder to an EGFR intracellular region phosphorylated upon EGF activation co-localizes with the receptor following EGF stimulation in single-particle tracking (SPT) experiments, demonstrating pY specific recognition in living cells. RFD2-MI provides a generalizable all-atom diffusion framework for probing and modulating phosphorylation-dependent signaling, and more generally, for developing research tools and targeted therapeutics against post-translationally modified proteins.

Although AlphaFold2 (AF2) and RoseTTAFold (RF) have transformed structural biology by enabling high-accuracy protein structure modeling, they are unable to model covalent modifications or interactions with small molecules and other non-protein molecules that can play key roles in biological function. Here, we describe RoseTTAFold All-Atom (RFAA), a deep network capable of modeling full biological assemblies containing proteins, nucleic acids, small molecules, metals, and covalent modifications given the sequences of the polymers and the atomic bonded geometry of the small molecules and covalent modifications. Following training on structures of full biological assemblies in the Protein Data Bank (PDB), RFAA has comparable protein structure prediction accuracy to AF2, excellent performance in CAMEO for flexible backbone small molecule docking, and reasonable prediction accuracy for protein covalent modifications and assemblies of proteins with multiple nucleic acid chains and small molecules which, to our knowledge, no existing method can model simultaneously. By fine-tuning on diffusive denoising tasks, we develop RFdiffusion All-Atom (RFdiffusionAA), which generates binding pockets by directly building protein structures around small molecules and other non-protein molecules. Starting from random distributions of amino acid residues surrounding target small molecules, we design and experimentally validate proteins that bind the cardiac disease therapeutic digoxigenin, the enzymatic cofactor heme, and optically active bilin molecules with potential for expanding the range of wavelengths captured by photosynthesis. We anticipate that RFAA and RFdiffusionAA will be widely useful for modeling and designing complex biomolecular systems.

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.Competing Interest StatementThe authors have declared no competing interest.