Generalized biomolecular modeling and design with RoseTTAFold All-Atom.

Deep-learning methods have revolutionized protein structure prediction and design but are presently limited to protein-only systems. We describe RoseTTAFold All-Atom (RFAA), which combines a residue-based representation of amino acids and DNA bases with an atomic representation of all other groups to model assemblies that contain proteins, nucleic acids, small molecules, metals, and covalent modifications, given their sequences and chemical structures. By fine-tuning on denoising tasks, we developed RFdiffusion All-Atom (RFdiffusionAA), which builds protein structures around small molecules. Starting from random distributions of amino acid residues surrounding target small molecules, we designed and experimentally validated, through crystallography and binding measurements, proteins that bind the cardiac disease therapeutic digoxigenin, the enzymatic cofactor heme, and the light-harvesting molecule bilin.

Protein Ensemble Generation Through Variational Autoencoder Latent Space Sampling.

Mapping the ensemble of protein conformations that contribute to function and can be targeted by small molecule drugs remains an outstanding challenge. Here, we explore the use of variational autoencoders for reducing the challenge of dimensionality in the protein structure ensemble generation problem. We convert high-dimensional protein structural data into a continuous, low-dimensional representation, carry out a search in this space guided by a structure quality metric, and then use RoseTTAFold guided by the sampled structural information to generate 3D structures. We use this approach to generate ensembles for the cancer relevant protein K-Ras, train the VAE on a subset of the available K-Ras crystal structures and MD simulation snapshots, and assess the extent of sampling close to crystal structures withheld from training. We find that our latent space sampling procedure rapidly generates ensembles with high structural quality and is able to sample within 1 Å of held-out crystal structures, with a consistency higher than that of MD simulation or AlphaFold2 prediction. The sampled structures sufficiently recapitulate the cryptic pockets in the held-out K-Ras structures to allow for small molecule docking.

De novo design of high-affinity binders of bioactive helical peptides.

Many peptide hormones form an α-helix on binding their receptors1-4, and sensitive methods for their detection could contribute to better clinical management of disease5. De novo protein design can now generate binders with high affinity and specificity to structured proteins6,7. However, the design of interactions between proteins and short peptides with helical propensity is an unmet challenge. Here we describe parametric generation and deep learning-based methods for designing proteins to address this challenge. We show that by extending RFdiffusion8 to enable binder design to flexible targets, and to refining input structure models by successive noising and denoising (partial diffusion), picomolar-affinity binders can be generated to helical peptide targets by either refining designs generated with other methods, or completely de novo starting from random noise distributions without any subsequent experimental optimization. The RFdiffusion designs enable the enrichment and subsequent detection of parathyroid hormone and glucagon by mass spectrometry, and the construction of bioluminescence-based protein biosensors. The ability to design binders to conformationally variable targets, and to optimize by partial diffusion both natural and designed proteins, should be broadly useful.

Small-molecule binding and sensing with a designed protein family.

Despite transformative advances in protein design with deep learning, the design of small-molecule-binding proteins and sensors for arbitrary ligands remains a grand challenge. Here we combine deep learning and physics-based methods to generate a family of proteins with diverse and designable pocket geometries, which we employ to computationally design binders for six chemically and structurally distinct small-molecule targets. Biophysical characterization of the designed binders revealed nanomolar to low micromolar binding affinities and atomic-level design accuracy. The bound ligands are exposed at one edge of the binding pocket, enabling the de novo design of chemically induced dimerization (CID) systems; we take advantage of this to create a biosensor with nanomolar sensitivity for cortisol. Our approach provides a general method to design proteins that bind and sense small molecules for a wide range of analytical, environmental, and biomedical applications.

Computational design of sequence-specific DNA-binding proteins.

Sequence-specific DNA-binding proteins (DBPs) play critical roles in biology and biotechnology, and there has been considerable interest in the engineering of DBPs with new or altered specificities for genome editing and other applications. While there has been some success in reprogramming naturally occurring DBPs using selection methods, the computational design of new DBPs that recognize arbitrary target sites remains an outstanding challenge. We describe a computational method for the design of small DBPs that recognize specific target sequences through interactions with bases in the major groove, and employ this method in conjunction with experimental screening to generate binders for 5 distinct DNA targets. These binders exhibit specificity closely matching the computational models for the target DNA sequences at as many as 6 base positions and affinities as low as 30-100 nM. The crystal structure of a designed DBP-target site complex is in close agreement with the design model, highlighting the accuracy of the design method. The designed DBPs function in both Escherichia coli and mammalian cells to repress and activate transcription of neighboring genes. Our method is a substantial step towards a general route to small and hence readily deliverable sequence-specific DBPs for gene regulation and editing.

De novo design of luciferases using deep learning.

De novo enzyme design has sought to introduce active sites and substrate-binding pockets that are predicted to catalyse a reaction of interest into geometrically compatible native scaffolds1,2, but has been limited by a lack of suitable protein structures and the complexity of native protein sequence-structure relationships. Here we describe a deep-learning-based 'family-wide hallucination' approach that generates large numbers of idealized protein structures containing diverse pocket shapes and designed sequences that encode them. We use these scaffolds to design artificial luciferases that selectively catalyse the oxidative chemiluminescence of the synthetic luciferin substrates diphenylterazine3 and 2-deoxycoelenterazine. The designed active sites position an arginine guanidinium group adjacent to an anion that develops during the reaction in a binding pocket with high shape complementarity. For both luciferin substrates, we obtain designed luciferases with high selectivity; the most active of these is a small (13.9 kDa) and thermostable (with a melting temperature higher than 95 °C) enzyme that has a catalytic efficiency on diphenylterazine (kcat/Km = 106 M-1 s-1) comparable to that of native luciferases, but a much higher substrate specificity. The creation of highly active and specific biocatalysts from scratch with broad applications in biomedicine is a key milestone for computational enzyme design, and our approach should enable generation of a wide range of luciferases and other enzymes.

Evaluating GPCR modeling and docking strategies in the era of deep learning-based protein structure prediction.

While deep learning (DL) has brought a revolution in the protein structure prediction field, still an important question remains how the revolution can be transferred to advances in structure-based drug discovery. Because the lessons from the recent GPCR dock challenge were inconclusive primarily due to the size of the dataset, in this work we further elaborated on 70 diverse GPCR complexes bound to either small molecules or peptides to investigate the best-practice modeling and docking strategies for GPCR drug discovery. From our quantitative analysis, it is shown that substantial improvements in docking and virtual screening have been possible by the advance in DL-based protein structure predictions with respect to the expected results from the combination of best pre-DL tools. The success rate of docking on DL-based model structures approaches that of cross-docking on experimental structures, showing over 30% improvement from the best pre-DL protocols. This amount of performance could be achieved only when two modeling points were considered properly: 1) correct functional-state modeling of receptors and 2) receptor-flexible docking. Best-practice modeling strategies and the model confidence estimation metric suggested in this work may serve as a guideline for future computer-aided GPCR drug discovery scenarios.

De novo design of diverse small molecule binders and sensors using Shape Complementary Pseudocycles.

A general method for designing proteins to bind and sense any small molecule of interest would be widely useful. Due to the small number of atoms to interact with, binding to small molecules with high affinity requires highly shape complementary pockets, and transducing binding events into signals is challenging. Here we describe an integrated deep learning and energy based approach for designing high shape complementarity binders to small molecules that are poised for downstream sensing applications. We employ deep learning generated psuedocycles with repeating structural units surrounding central pockets; depending on the geometry of the structural unit and repeat number, these pockets span wide ranges of sizes and shapes. For a small molecule target of interest, we extensively sample high shape complementarity pseudocycles to generate large numbers of customized potential binding pockets; the ligand binding poses and the interacting interfaces are then optimized for high affinity binding. We computationally design binders to four diverse molecules, including for the first time polar flexible molecules such as methotrexate and thyroxine, which are expressed at high levels and have nanomolar affinities straight out of the computer. Co-crystal structures are nearly identical to the design models. Taking advantage of the modular repeating structure of pseudocycles and central location of the binding pockets, we constructed low noise nanopore sensors and chemically induced dimerization systems by splitting the binders into domains which assemble into the original pseudocycle pocket upon target molecule addition.

Accurate prediction of protein structures and interactions using a three-track neural network.

DeepMind presented notably accurate predictions at the recent 14th Critical Assessment of Structure Prediction (CASP14) conference. We explored network architectures that incorporate related ideas and obtained the best performance with a three-track network in which information at the one-dimensional (1D) sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The three-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables the rapid solution of challenging x-ray crystallography and cryo-electron microscopy structure modeling problems, and provides insights into the functions of proteins of currently unknown structure. The network also enables rapid generation of accurate protein-protein complex models from sequence information alone, short-circuiting traditional approaches that require modeling of individual subunits followed by docking. We make the method available to the scientific community to speed biological research.

De Novo Protein Design Using the Blueprint Builder in Rosetta.

While native proteins cover diverse structural spaces and achieve various biological events, not many of them can directly serve human needs. One reason is that the native proteins usually contain idiosyncrasies evolved for their native functions but disfavoring engineering requirements. To overcome this issue, one strategy is to create de novo proteins which are designed to possess improved stability, high environmental tolerance, and enhanced engineering potential. Compared to other protein engineering strategies, in silico design of de novo proteins has significantly expanded the protein structural and sequence spaces, reduced wet lab workload, and incorporated engineered features in a guided and efficient manner. In the Baker laboratory we have been applying a design pipeline that uses the blueprint builder to design different folds of de novo proteins, and have successfully obtained libraries of de novo proteins with improved stability and engineering potential. In this article, we will use the design of de novo ß-barrel proteins as an example to describe the principles and basic procedures of the blueprint builder-based design pipeline. © 2020 Wiley Periodicals LLC. Basic Protocol 1: The construction of blueprints Alternate Protocol: Build blueprints based on existing protein .pdb files Basic Protocol 2: De novo protein design pipeline using the blueprint builder.

High-accuracy refinement using Rosetta in CASP13.

Because proteins generally fold to their lowest free energy states, energy-guided refinement in principle should be able to systematically improve the quality of protein structure models generated using homologous structure or co-evolution derived information. However, because of the high dimensionality of the search space, there are far more ways to degrade the quality of a near native model than to improve it, and hence, refinement methods are very sensitive to energy function errors. In the 13th Critial Assessment of techniques for protein Structure Prediction (CASP13), we sought to carry out a thorough search for low energy states in the neighborhood of a starting model using restraints to avoid straying too far. The approach was reasonably successful in improving both regions largely incorrect in the starting models as well as core regions that started out closer to the correct structure. Models with GDT-HA over 70 were obtained for five targets and for one of those, an accuracy of 0.5 å backbone root-mean-square deviation (RMSD) was achieved. An important current challenge is to improve performance in refining oligomers and larger proteins, for which the search problem remains extremely difficult.

GalaxyRefine2: simultaneous refinement of inaccurate local regions and overall protein structure.

The 3D structure of a protein can be predicted from its amino acid sequence with high accuracy for a large fraction of cases because of the availability of large quantities of experimental data and the advance of computational algorithms. Recently, deep learning methods exploiting the coevolution information obtained by comparing related protein sequences have been successfully used to generate highly accurate model structures even in the absence of template structure information. However, structures predicted based on either template structures or related sequences require further improvement in regions for which information is missing. Refining a predicted protein structure with insufficient information on certain regions is critical because these regions may be connected to functional specificity that is not conserved among related proteins. The GalaxyRefine2 web server, freely available via http://galaxy.seoklab.org/refine2, is an upgraded version of the GalaxyRefine protein structure refinement server and reflects recent developments successfully tested through CASP blind prediction experiments. This method adopts an iterative optimization approach involving various structure move sets to refine both local and global structures. The estimation of local error and hybridization of available homolog structures are also employed for effective conformation search.

Biophysical and functional characterization of Norrin signaling through Frizzled4.

Wnt signaling is initiated by Wnt ligand binding to the extracellular ligand binding domain, called the cysteine-rich domain (CRD), of a Frizzled (Fzd) receptor. Norrin, an atypical Fzd ligand, specifically interacts with Fzd4 to activate ß-catenin-dependent canonical Wnt signaling. Much of the molecular basis that confers Norrin selectivity in binding to Fzd4 was revealed through the structural study of the Fzd4CRD-Norrin complex. However, how the ligand interaction, seemingly localized at the CRD, is transmitted across full-length Fzd4 to the cytoplasm remains largely unknown. Here, we show that a flexible linker domain, which connects the CRD to the transmembrane domain, plays an important role in Norrin signaling. The linker domain directly contributes to the high-affinity interaction between Fzd4 and Norrin as shown by ∼10-fold higher binding affinity of Fzd4CRD to Norrin in the presence of the linker. Swapping the Fzd4 linker with the Fzd5 linker resulted in the loss of Norrin signaling, suggesting the importance of the linker in ligand-specific cellular response. In addition, structural dynamics of Fzd4 associated with Norrin binding investigated by hydrogen/deuterium exchange MS revealed Norrin-induced conformational changes on the linker domain and the intracellular loop 3 (ICL3) region of Fzd4. Cell-based functional assays showed that linker deletion, L430A and L433A mutations at ICL3, and C-terminal tail truncation displayed reduced ß-catenin-dependent signaling activity, indicating the functional significance of these sites. Together, our results provide functional and biochemical dissection of Fzd4 in Norrin signaling.

An analysis and evaluation of the WeFold collaborative for protein structure prediction and its pipelines in CASP11 and CASP12.

Every two years groups worldwide participate in the Critical Assessment of Protein Structure Prediction (CASP) experiment to blindly test the strengths and weaknesses of their computational methods. CASP has significantly advanced the field but many hurdles still remain, which may require new ideas and collaborations. In 2012 a web-based effort called WeFold, was initiated to promote collaboration within the CASP community and attract researchers from other fields to contribute new ideas to CASP. Members of the WeFold coopetition (cooperation and competition) participated in CASP as individual teams, but also shared components of their methods to create hybrid pipelines and actively contributed to this effort. We assert that the scale and diversity of integrative prediction pipelines could not have been achieved by any individual lab or even by any collaboration among a few partners. The models contributed by the participating groups and generated by the pipelines are publicly available at the WeFold website providing a wealth of data that remains to be tapped. Here, we analyze the results of the 2014 and 2016 pipelines showing improvements according to the CASP assessment as well as areas that require further adjustments and research.

GalaxyGPCRloop: Template-Based and Ab Initio Structure Sampling of the Extracellular Loops of G-Protein-Coupled Receptors.

The second extracellular loops (ECL2s) of G-protein-coupled receptors (GPCRs) are often involved in GPCR functions, and their structures have important implications in drug discovery. However, structure prediction of ECL2 is difficult because of its long length and the structural diversity among different GPCRs. In this study, a new ECL2 conformational sampling method involving both template-based and ab initio sampling was developed. Inspired by the observation of similar ECL2 structures of closely related GPCRs, a template-based sampling method employing loop structure templates selected from the structure database was developed. A new metric for evaluating similarity of the target loop to templates was introduced for template selection. An ab initio loop sampling method was also developed to treat cases without highly similar templates. The ab initio method is based on the previously developed fragment assembly and loop closure method. A new sampling component that takes advantage of secondary structure prediction was added. In addition, a conserved disulfide bridge restraining ECL2 conformation was predicted and analytically incorporated into sampling, reducing the effective dimension of the conformational search space. The sampling method was combined with an existing energy function for comparison with previously reported loop structure prediction methods, and the benchmark test demonstrated outstanding performance.

Simultaneous refinement of inaccurate local regions and overall structure in the CASP12 protein model refinement experiment.

Advances in protein model refinement techniques are required as diverse sources of protein structure information are available from low-resolution experiments or informatics-based computations such as cryo-EM, NMR, homology models, or predicted residue contacts. Given semi-reliable or incomplete structural information, structure quality of a protein model has to be improved by ab initio methods such as energy-based simulation. In this study, we describe a new automatic refinement server method designed to improve locally inaccurate regions and overall structure simultaneously. Locally inaccurate regions may occur in protein structures due to non-convergent or missing information in template structures used in homology modeling or due to intrinsic structural flexibilities not resolved by experimental techniques. However, such variable or dynamic regions often play important functional roles by participating in interactions with other biomolecules or in transitions between different functional states. The new refinement method introduced here utilizes diverse types of geometric operators which drive both local and global changes, and the effect of structure changes and relaxations are accumulated. This resulted in consistent refinement of both local and global structural features. Performance of this method in CASP12 is discussed.

Cell-cell adhesion in metazoans relies on evolutionarily conserved features of the α-catenin·ß-catenin-binding interface.

Stable tissue integrity during embryonic development relies on the function of the cadherin·catenin complex (CCC). The Caenorhabditis elegans CCC is a useful paradigm for analyzing in vivo requirements for specific interactions among the core components of the CCC, and it provides a unique opportunity to examine evolutionarily conserved mechanisms that govern the interaction between α- and ß-catenin. HMP-1, unlike its mammalian homolog α-catenin, is constitutively monomeric, and its binding affinity for HMP-2/ß-catenin is higher than that of α-catenin for ß-catenin. A crystal structure shows that the HMP-1·HMP-2 complex forms a five-helical bundle structure distinct from the structure of the mammalian α-catenin·ß-catenin complex. Deletion analysis based on the crystal structure shows that the first helix of HMP-1 is necessary for binding HMP-2 avidly in vitro and for efficient recruitment of HMP-1 to adherens junctions in embryos. HMP-2 Ser-47 and Tyr-69 flank its binding interface with HMP-1, and we show that phosphomimetic mutations at these two sites decrease binding affinity of HMP-1 to HMP-2 by 40-100-fold in vitro. In vivo experiments using HMP-2 S47E and Y69E mutants showed that they are unable to rescue hmp-2(zu364) mutants, suggesting that phosphorylation of HMP-2 on Ser-47 and Tyr-69 could be important for regulating CCC formation in C. elegans Our data provide novel insights into how cadherin-dependent cell-cell adhesion is modulated in metazoans by conserved elements as well as features unique to specific organisms.

Benchmarking predictions of allostery in liver pyruvate kinase in CAGI4.

The Critical Assessment of Genome Interpretation (CAGI) is a global community experiment to objectively assess computational methods for predicting phenotypic impacts of genomic variation. One of the 2015-2016 competitions focused on predicting the influence of mutations on the allosteric regulation of human liver pyruvate kinase. More than 30 different researchers accessed the challenge data. However, only four groups accepted the challenge. Features used for predictions ranged from evolutionary constraints, mutant site locations relative to active and effector binding sites, and computational docking outputs. Despite the range of expertise and strategies used by predictors, the best predictions were marginally greater than random for modified allostery resulting from mutations. In contrast, several groups successfully predicted which mutations severely reduced enzymatic activity. Nonetheless, poor predictions of allostery stands in stark contrast to the impression left by more than 700 PubMed entries identified using the identifiers "computational + allosteric." This contrast highlights a specialized need for new computational tools and utilization of benchmarks that focus on allosteric regulation.

Template-based modeling and ab initio refinement of protein oligomer structures using GALAXY in CAPRI round 30.

Many proteins function as homo- or hetero-oligomers; therefore, attempts to understand and regulate protein functions require knowledge of protein oligomer structures. The number of available experimental protein structures is increasing, and oligomer structures can be predicted using the experimental structures of related proteins as templates. However, template-based models may have errors due to sequence differences between the target and template proteins, which can lead to functional differences. Such structural differences may be predicted by loop modeling of local regions or refinement of the overall structure. In CAPRI (Critical Assessment of PRotein Interactions) round 30, we used recently developed features of the GALAXY protein modeling package, including template-based structure prediction, loop modeling, model refinement, and protein-protein docking to predict protein complex structures from amino acid sequences. Out of the 25 CAPRI targets, medium and acceptable quality models were obtained for 14 and 1 target(s), respectively, for which proper oligomer or monomer templates could be detected. Symmetric interface loop modeling on oligomer model structures successfully improved model quality, while loop modeling on monomer model structures failed. Overall refinement of the predicted oligomer structures consistently improved the model quality, in particular in interface contacts. Proteins 2017; 85:399-407. © 2016 Wiley Periodicals, Inc.

Galaxy7TM: flexible GPCR-ligand docking by structure refinement.

G-protein-coupled receptors (GPCRs) play important physiological roles related to signal transduction and form a major group of drug targets. Prediction of GPCR-ligand complex structures has therefore important implications to drug discovery. With previously available servers, it was only possible to first predict GPCR structures by homology modeling and then perform ligand docking on the model structures. However, model structures generated without explicit consideration of specific ligands of interest can be inaccurate because GPCR structures can be affected by ligand binding. The Galaxy7TM server, freely accessible at http://galaxy.seoklab.org/7TM, improves an input GPCR structure by simultaneous ligand docking and flexible structure refinement using GALAXY methods. The server shows better performance in both ligand docking and GPCR structure refinement than commonly used programs AutoDock Vina and Rosetta MPrelax, respectively.