A general-purpose protein design framework based on mining sequence-structure relationships in known protein structures

Functionally Active Synthetic α-Helical Pores

ConspectusTransmembrane pores are currently at the forefront of nanobiotechnology, nanopore chemistry, and synthetic chemical biology research. Over the past few decades, significant studies in protein engineering have paved the way for redesigning membrane protein pores tailored for specific applications in nanobiotechnology. Most previous efforts predominantly centered on natural β-barrel pores designed with atomic precision for nucleic acid sequencing and sensing of biomacromolecules, including protein fragments. The requirement for a more efficient single-molecule detection system has driven the development of synthetic nanopores. For example, engineering channels to conduct ions and biomolecules selectively could lead to sophisticated nanopore sensors. Also, there has been an increased interest in synthetic pores, which can be fabricated to provide more control in designing architecture and diameter for single-molecule sensing of complex biomacromolecules. There have been impressive advancements in developing synthetic DNA-based pores, although their application in nanopore technology is limited. This has prompted a significant shift toward building synthetic transmembrane α-helical pores, a relatively underexplored field offering novel opportunities. Recently, computational tools have been employed to design and construct α-helical barrels of defined structure and functionality.We focus on building synthetic α-helical pores using naturally occurring transmembrane motifs of membrane protein pores. Our laboratory has developed synthetic α-helical transmembrane pores based on the natural porin PorACj (Porin A derived from Corynebacterium jeikeium) that function as nanopore sensors for single-molecule sensing of cationic cyclodextrins and polypeptides. Our breakthrough lies in being the first to create a functional and large stable synthetic transmembrane pore composed of short synthetic α-helical peptides. The key highlight of our work is that these pores can be synthesized using easy chemical synthesis, which permits its easy modification to include a variety of functional groups to build charge-selective sophisticated pores. Additionally, we have demonstrated that stable functional pores can be constructed from D-amino acid peptides. The analysis of pores composed of D- and L-amino acids in the presence of protease showed that only the D pores are highly functional and stable. The structural models of these pores revealed distinct surface charge conformation and geometry. These new classes of synthetic α-helical pores are highly original systems of general interest due to their unique architecture, functionality, and potential applications in nanopore technology and chemical biology. We emphasize that these simplified transmembrane pores have the potential to be components of functional nanodevices and therapeutic tools. We also suggest that such designed peptides might be valuable as antimicrobial agents and can be targeted to cancer cells. This article will focus on the evolutions in assembling α-helical transmembrane pores and highlight their advantages, including structural and functional versatility.

A suite of designed protein cages using machine learning and protein fragment-based protocols

Designed protein cages and related materials provide unique opportunities for applications in biotechnology and medicine, but their creation remains challenging. Here, we apply computational approaches to design a suite of tetrahedrally symmetric, self-assembling protein cages. For the generation of docked conformations, we emphasize a protein fragment-based approach, while for sequence design of the de novo interface, a comparison of knowledge-based and machine learning protocols highlights the power and increased experimental success achieved using ProteinMPNN. An analysis of design outcomes provides insights for improving interface design protocols, including prioritizing fragment-based motifs, balancing interface hydrophobicity and polarity, and identifying preferred polar contact patterns. In all, we report five structures for seven protein cages, along with two structures of intermediate assemblies, with the highest resolution reaching 2.0 Å using cryo-EM. This set of designed cages adds substantially to the body of available protein nanoparticles, and to methodologies for their creation.

Linguistics-based formalization of the antibody language as a basis for antibody language models

Apparent parallels between natural language and antibody sequences have led to a surge in deep language models applied to antibody sequences for predicting cognate antigen recognition. However, a linguistic formal definition of antibody language does not exist, and insight into how antibody language models capture antibody-specific binding features remains largely uninterpretable. Here we describe how a linguistic formalization of the antibody language, by characterizing its tokens and grammar, could address current challenges in antibody language model rule mining.

Vaccination induces broadly neutralizing antibody precursors to HIV gp41

A key barrier to the development of vaccines that induce broadly neutralizing antibodies (bnAbs) against human immunodeficiency virus (HIV) and other viruses of high antigenic diversity is the design of priming immunogens that induce rare bnAb-precursor B cells. The high neutralization breadth of the HIV bnAb 10E8 makes elicitation of 10E8-class bnAbs desirable; however, the recessed epitope within gp41 makes envelope trimers poor priming immunogens and requires that 10E8-class bnAbs possess a long heavy chain complementarity determining region 3 (HCDR3) with a specific binding motif. We developed germline-targeting epitope scaffolds with affinity for 10E8-class precursors and engineered nanoparticles for multivalent display. Scaffolds exhibited epitope structural mimicry and bound bnAb-precursor human naive B cells in ex vivo screens, protein nanoparticles induced bnAb-precursor responses in stringent mouse models and rhesus macaques, and mRNA-encoded nanoparticles triggered similar responses in mice. Thus, germline-targeting epitope scaffold nanoparticles can elicit rare bnAb-precursor B cells with predefined binding specificities and HCDR3 features.

Predicting the functional state of protein kinases using interpretable graph neural networks from sequence and structural data

Protein kinases are central to cellular activities and are actively pursued as drug targets for several conditions including cancer and autoimmune diseases. Despite the availability of a large structural database for kinases, methodologies to elucidate the structure-function relationship of these proteins (without manual intervention) are lacking. Such techniques are essential in structural biology and to accelerate drug discovery efforts. Here, we implement an interpretable graph neural network (GNN) framework for classifying the functionally active and inactive states of a large set of protein kinases by only using their tertiary structure and amino acid sequence. We show that the GNN models can classify kinase structures with high accuracy (>97%). We implement the Gradient-weighted Class Activation Mapping for graphs (Graph Grad-CAM) to automatically identify structurally important residues and residue-residue contacts of the kinases without any a priori input. We show that the motifs identified through the Graph Grad-CAM methodology are functionally critical, consistent with the existing kinase literature. Notably, the highly conserved DFG and HRD motifs of the well-known hydrophobic spine are identified by the interpretable framework in addition to some of the lesser known motifs. Further, using Grad-CAM maps as the vector embedding of the protein structures, we identify the subtle differences in the crystal structures among different sub-classes of kinases in the Protein Data Bank (PDB). Frameworks such as the one implemented here, for high-throughput identification of protein structure-function relationships are essential in designing targeted small molecules therapies as well as in engineering new proteins for novel applications.

The Damietta Server: a comprehensive protein design toolkit

The growing importance of protein design to various research disciplines motivates the development of integrative computational platforms that enhance the accessibility and interoperability of different design tools. To this end, we describe a web-based toolkit that builds on the Damietta protein design engine, which deploys a tensorized energy calculation framework. The Damietta Server seamlessly integrates different design tools, in addition to other tools such as message-passing neural networks and molecular dynamics routines, allowing the user to perform multiple operations on structural models and forward them across tools. The toolkit can be used for tasks such as core or interface design, symmetric design, mutagenic scanning, or conformational sampling, through an intuitive user interface. With the envisioned integration of more tools, the Damietta Server will provide a central resource for protein design and analysis, benefiting basic and applied biomedical research communities. The toolkit is available with no login requirement through https://damietta.de/.

Biomaterials containing extracellular matrix molecules as biomimetic next-generation vascular grafts

The performance of synthetic biomaterial vascular grafts for the bypass of stenotic and dysfunctional blood vessels remains an intractable challenge in small-diameter applications. The functionalization of biomaterials with extracellular matrix (ECM) molecules is a promising approach because these molecules can regulate multiple biological processes in vascular tissues. In this review, we critically examine emerging approaches to ECM-containing vascular graft biomaterials and explore opportunities for future research and development toward clinical use.

Key interaction networks: Identifying evolutionarily conserved non-covalent interaction networks across protein families

Protein structure (and thus function) is dictated by non-covalent interaction networks. These can be highly evolutionarily conserved across protein families, the members of which can diverge in sequence and evolutionary history. Here we present KIN, a tool to identify and analyze conserved non-covalent interaction networks across evolutionarily related groups of proteins. KIN is available for download under a GNU General Public License, version 2, from https://www.github.com/kamerlinlab/KIN. KIN can operate on experimentally determined structures, predicted structures, or molecular dynamics trajectories, providing insight into both conserved and missing interactions across evolutionarily related proteins. This provides useful insight both into protein evolution, as well as a tool that can be exploited for protein engineering efforts. As a showcase system, we demonstrate applications of this tool to understanding the evolutionary-relevant conserved interaction networks across the class A β-lactamases.

DexDesign: A new OSPREY-based algorithm for designing de novo D-peptide inhibitors

With over 270 unique occurrences in the human genome, peptide-recognizing PDZ domains play a central role in modulating polarization, signaling, and trafficking pathways. Mutations in PDZ domains lead to diseases such as cancer and cystic fibrosis, making PDZ domains attractive targets for therapeutic intervention. D-peptide inhibitors offer unique advantages as therapeutics, including increased metabolic stability and low immunogenicity. Here, we introduce DexDesign, a novel OSPREY-based algorithm for computationally designing de novo D-peptide inhibitors. DexDesign leverages three novel techniques that are broadly applicable to computational protein design: the Minimum Flexible Set, K*-based Mutational Scan, and Inverse Alanine Scan, which enable exponential reductions in the size of the peptide sequence search space. We apply these techniques and DexDesign to generate novel D-peptide inhibitors of two biomedically important PDZ domain targets: CAL and MAST2. We introduce a new framework for analyzing de novo peptides-evaluation along a replication/restitution axis-and apply it to the DexDesign-generated D-peptides. Notably, the peptides we generated are predicted to bind their targets tighter than their targets' endogenous ligands, validating the peptides' potential as lead therapeutic candidates. We provide an implementation of DexDesign in the free and open source computational protein design software OSPREY.

Extracellular vesicles for developing targeted hearing loss therapy

Substantial efforts have been made for local administration of small molecules or biologics in treating hearing loss diseases caused by either trauma, genetic mutations, or drug ototoxicity. Recently, extracellular vesicles (EVs) naturally secreted from cells have drawn increasing attention on attenuating hearing impairment from both preclinical studies and clinical studies. Highly emerging field utilizing diverse bioengineering technologies for developing EVs as the bioderived therapeutic materials, along with artificial intelligence (AI)-based targeting toolkits, shed the light on the unique properties of EVs specific to inner ear delivery. This review will illuminate such exciting research field from fundamentals of hearing protective functions of EVs to biotechnology advancement and potential clinical translation of functionalized EVs. Specifically, the advancements in assessing targeting ligands using AI algorithms are systematically discussed. The overall translational potential of EVs is reviewed in the context of auditory sensing system for developing next generation gene therapy.

DexDesign: an OSPREY-based algorithm for designing de novo D-peptide inhibitors

With over 270 unique occurrences in the human genome, peptide-recognizing PDZ domains play a central role in modulating polarization, signaling, and trafficking pathways. Mutations in PDZ domains lead to diseases such as cancer and cystic fibrosis, making PDZ domains attractive targets for therapeutic intervention. D-peptide inhibitors offer unique advantages as therapeutics, including increased metabolic stability and low immunogenicity. Here, we introduce DexDesign, a novel OSPREY-based algorithm for computationally designing de novo D-peptide inhibitors. DexDesign leverages three novel techniques that are broadly applicable to computational protein design: the Minimum Flexible Set, K*-based Mutational Scan, and Inverse Alanine Scan. We apply these techniques and DexDesign to generate novel D-peptide inhibitors of two biomedically important PDZ domain targets: CAL and MAST2. We introduce a framework for analyzing de novo peptides-evaluation along a replication/restitution axis-and apply it to the DexDesign-generated D-peptides. Notably, the peptides we generated are predicted to bind their targets tighter than their targets' endogenous ligands, validating the peptides' potential as lead inhibitors. We also provide an implementation of DexDesign in the free and open source computational protein design software OSPREY.

TIMED-Design: flexible and accessible protein sequence design with convolutional neural networks

Sequence design is a crucial step in the process of designing or engineering proteins. Traditionally, physics-based methods have been used to solve for optimal sequences, with the main disadvantages being that they are computationally intensive for the end user. Deep learning-based methods offer an attractive alternative, outperforming physics-based methods at a significantly lower computational cost. In this paper, we explore the application of Convolutional Neural Networks (CNNs) for sequence design. We describe the development and benchmarking of a range of networks, as well as reimplementations of previously described CNNs. We demonstrate the flexibility of representing proteins in a three-dimensional voxel grid by encoding additional design constraints into the input data. Finally, we describe TIMED-Design, a web application and command line tool for exploring and applying the models described in this paper. The user interface will be available at the URL: https://pragmaticproteindesign.bio.ed.ac.uk/timed. The source code for TIMED-Design is available at https://github.com/wells-wood-research/timed-design.

Illuminating protein space with a programmable generative model

Three billion years of evolution has produced a tremendous diversity of protein molecules1, but the full potential of proteins is likely to be much greater. Accessing this potential has been challenging for both computation and experiments because the space of possible protein molecules is much larger than the space of those likely to have functions. Here we introduce Chroma, a generative model for proteins and protein complexes that can directly sample novel protein structures and sequences, and that can be conditioned to steer the generative process towards desired properties and functions. To enable this, we introduce a diffusion process that respects the conformational statistics of polymer ensembles, an efficient neural architecture for molecular systems that enables long-range reasoning with sub-quadratic scaling, layers for efficiently synthesizing three-dimensional structures of proteins from predicted inter-residue geometries and a general low-temperature sampling algorithm for diffusion models. Chroma achieves protein design as Bayesian inference under external constraints, which can involve symmetries, substructure, shape, semantics and even natural-language prompts. The experimental characterization of 310 proteins shows that sampling from Chroma results in proteins that are highly expressed, fold and have favourable biophysical properties. The crystal structures of two designed proteins exhibit atomistic agreement with Chroma samples (a backbone root-mean-square deviation of around 1.0 Å). With this unified approach to protein design, we hope to accelerate the programming of protein matter to benefit human health, materials science and synthetic biology.

Engineering and Expression Strategies for Optimization of L-Asparaginase Development and Production

Genetic engineering for heterologous expression has advanced in recent years. Model systems such as Escherichia coli, Bacillus subtilis and Pichia pastoris are often used as host microorganisms for the enzymatic production of L-asparaginase, an enzyme widely used in the clinic for the treatment of leukemia and in bakeries for the reduction of acrylamide. Newly developed recombinant L-asparaginase (L-ASNase) may have a low affinity for asparagine, reduced catalytic activity, low stability, and increased glutaminase activity or immunogenicity. Some successful commercial preparations of L-ASNase are now available. Therefore, obtaining novel L-ASNases with improved properties suitable for food or clinical applications remains a challenge. The combination of rational design and/or directed evolution and heterologous expression has been used to create enzymes with desired characteristics. Computer design, combined with other methods, could make it possible to generate mutant libraries of novel L-ASNases without costly and time-consuming efforts. In this review, we summarize the strategies and approaches for obtaining and developing L-ASNase with improved properties.

A Suite of Designed Protein Cages Using Machine Learning Algorithms and Protein Fragment-Based Protocols

Designed protein cages and related materials provide unique opportunities for applications in biotechnology and medicine, while methods for their creation remain challenging and unpredictable. In the present study, we apply new computational approaches to design a suite of new tetrahedrally symmetric, self-assembling protein cages. For the generation of docked poses, we emphasize a protein fragment-based approach, while for de novo interface design, a comparison of computational protocols highlights the power and increased experimental success achieved using the machine learning program ProteinMPNN. In relating information from docking and design, we observe that agreement between fragment-based sequence preferences and ProteinMPNN sequence inference correlates with experimental success. Additional insights for designing polar interactions are highlighted by experimentally testing larger and more polar interfaces. In all, using X-ray crystallography and cryo-EM, we report five structures for seven protein cages, with atomic resolution in the best case reaching 2.0 Å. We also report structures of two incompletely assembled protein cages, providing unique insights into one type of assembly failure. The new set of designed cages and their structures add substantially to the body of available protein nanoparticles, and to methodologies for their creation.

The design of functional proteins using tensorized energy calculations

In protein design, the energy associated with a huge number of sequence-conformer perturbations has to be routinely estimated. Hence, enhancing the throughput and accuracy of these energy calculations can profoundly improve design success rates and enable tackling more complex design problems. In this work, we explore the possibility of tensorizing the energy calculations and apply them in a protein design framework. We use this framework to design enhanced proteins with anti-cancer and radio-tracing functions. Particularly, we designed multispecific binders against ligands of the epidermal growth factor receptor (EGFR), where the tested design could inhibit EGFR activity in vitro and in vivo. We also used this method to design high-affinity Cu2+ binders that were stable in serum and could be readily loaded with copper-64 radionuclide. The resulting molecules show superior functional properties for their respective applications and demonstrate the generalizable potential of the described protein design approach.

De novo design of stable proteins that efficaciously inhibit oncogenic G proteins

Many protein therapeutics are competitive inhibitors that function by binding to endogenous proteins and preventing them from interacting with native partners. One effective strategy for engineering competitive inhibitors is to graft structural motifs from a native partner into a host protein. Here, we develop and experimentally test a computational protocol for embedding binding motifs in de novo designed proteins. The protocol uses an "inside-out" approach: Starting with a structural model of the binding motif docked against the target protein, the de novo protein is built by growing new structural elements off the termini of the binding motif. During backbone assembly, a score function favors backbones that introduce new tertiary contacts within the designed protein and do not introduce clashes with the target binding partner. Final sequences are designed and optimized using the molecular modeling program Rosetta. To test our protocol, we designed small helical proteins to inhibit the interaction between Gαq and its effector PLC-β isozymes. Several of the designed proteins remain folded above 90°C and bind to Gαq with equilibrium dissociation constants tighter than 80 nM. In cellular assays with oncogenic variants of Gαq , the designed proteins inhibit activation of PLC-β isozymes and Dbl-family RhoGEFs. Our results demonstrate that computational protein design, in combination with motif grafting, can be used to directly generate potent inhibitors without further optimization via high throughput screening or selection.

Atligator Web: A Graphical User Interface for Analysis and Design of Protein-Peptide Interactions

A key functionality of proteins is based on their ability to form interactions with other proteins or peptides. These interactions are neither easily described nor fully understood, which is why the design of specific protein-protein interaction interfaces remains a challenge for protein engineering. We recently developed the software ATLIGATOR to extract common interaction patterns between different types of amino acids and store them in a database. The tool enables the user to better understand frequent interaction patterns and find groups of interactions. Furthermore, frequent motifs can be directly transferred from the database to a user-defined scaffold as a starting point for the engineering of new binding capabilities. Since three-dimensional visualization is a crucial part of ATLIGATOR, we created ATLIGATOR web-a web server offering an intuitive graphical user interface (GUI) available at https://atligator.uni-bayreuth.de. This new interface empowers users to apply ATLIGATOR by providing easy access with having all parts directly connected. Moreover, we extended the web by a design functionality so that, overall, ATLIGATOR web facilitates the use of ATLIGATOR with a more intuitive UI and advanced design options.

Designed Rubredoxin miniature in a fully artificial electron chain triggered by visible light

Designing metal sites into de novo proteins has significantly improved, recently. However, identifying the minimal coordination spheres, able to encompass the necessary information for metal binding and activity, still represents a great challenge, today. Here, we test our understanding with a benchmark, nevertheless difficult, case. We assemble into a miniature 28-residue protein, the quintessential elements required to fold properly around a FeCys₄ redox center, and to function efficiently in electron-transfer. This study addresses a challenge in de novo protein design, as it reports the crystal structure of a designed tetra-thiolate metal-binding protein in sub-Å agreement with the intended design. This allows us to well correlate structure to spectroscopic and electrochemical properties. Given its high reduction potential compared to natural and designed FeCys₄-containing proteins, we exploit it as terminal electron acceptor of a fully artificial chain triggered by visible light.

De novo design of stable proteins that efficaciously inhibit oncogenic G proteins

Many protein therapeutics are competitive inhibitors that function by binding to endogenous proteins and preventing them from interacting with native partners. One effective strategy for engineering competitive inhibitors is to graft structural motifs from a native partner into a host protein. Here, we develop and experimentally test a computational protocol for embedding binding motifs in de novo designed proteins. The protocol uses an "inside-out" approach: Starting with a structural model of the binding motif docked against the target protein, the de novo protein is built by growing new structural elements off the termini of the binding motif. During backbone assembly, a score function favors backbones that introduce new tertiary contacts within the designed protein and do not introduce clashes with the target binding partner. Final sequences are designed and optimized using the molecular modeling program Rosetta. To test our protocol, we designed small helical proteins to inhibit the interaction between Gα q and its effector PLC-β isozymes. Several of the designed proteins remain folded above 90°C and bind to Gα q with equilibrium dissociation constants tighter than 80 nM. In cellular assays with oncogenic variants of Gα q , the designed proteins inhibit activation of PLC-β isozymes and Dbl-family RhoGEFs. Our results demonstrate that computational protein design, in combination with motif grafting, can be used to directly generate potent inhibitors without further optimization via high throughput screening or selection.

statement for broader audience

Engineered proteins that bind to specific target proteins are useful as research reagents, diagnostics, and therapeutics. We used computational protein design to engineer de novo proteins that bind and competitively inhibit the G protein, Gα q , which is an oncogene for uveal melanomas. This computational method is a general approach that should be useful for designing competitive inhibitors against other proteins of interest.

Peptides from human BNIP5 and PXT1 and non-native binders of pro-apoptotic BAK can directly activate or inhibit BAK-mediated membrane permeabilization

Apoptosis is important for development and tissue homeostasis, and its dysregulation can lead to diseases, including cancer. As an apoptotic effector, BAK undergoes conformational changes that promote mitochondrial outer membrane disruption, leading to cell death. This is termed "activation" and can be induced by peptides from the human proteins BID, BIM, and PUMA. To identify additional peptides that can regulate BAK, we used computational protein design, yeast surface display screening, and structure-based energy scoring to identify 10 diverse new binders. We discovered peptides from the human proteins BNIP5 and PXT1 and three non-native peptides that activate BAK in liposome assays and induce cytochrome c release from mitochondria. Crystal structures and binding studies reveal a high degree of similarity among peptide activators and inhibitors, ruling out a simple function-determining property. Our results shed light on the vast peptide sequence space that can regulate BAK function and will guide the design of BAK-modulating tools and therapeutics.

Towards de novo design of transmembrane α-helical assemblies using structural modelling and molecular dynamics simulation

Computational de novo protein design involves iterative processes consisting of amino acid sequence design, structural modelling and scoring, and design validation by synthesis and experimental characterisation. Recent advances in protein structure prediction and modelling methods have enabled the highly efficient and accurate design of water-soluble proteins. However, the design of membrane proteins remains a major challenge. To advance membrane protein design, considering the higher complexity of membrane protein folding, stability, and dynamic interactions between water, ions, lipids, and proteins is an important task. For introducing explicit solvents and membranes to these design methods, all-atom molecular dynamics (MD) simulations of designed proteins provide useful information that cannot be obtained experimentally. In this review, we first describe two major approaches to designing transmembrane α-helical assemblies, consensus and de novo design. We further illustrate recent MD studies of membrane protein folding related to protein design, as well as advanced treatments in molecular models and conformational sampling techniques in the simulations. Finally, we discuss the possibility to introduce MD simulations after the existing static modelling and screening of design decoys as an additional step for refinement of the design, which considers membrane protein folding dynamics and interactions with explicit membranes.

Neural network-derived Potts models for structure-based protein design using backbone atomic coordinates and tertiary motifs

Designing novel proteins to perform desired functions, such as binding or catalysis, is a major goal in synthetic biology. A variety of computational approaches can aid in this task. An energy-based framework rooted in the sequence-structure statistics of tertiary motifs (TERMs) can be used for sequence design on predefined backbones. Neural network models that use backbone coordinate-derived features provide another way to design new proteins. In this work, we combine the two methods to make neural structure-based models more suitable for protein design. Specifically, we supplement backbone-coordinate features with TERM-derived data, as inputs, and we generate energy functions as outputs. We present two architectures that generate Potts models over the sequence space: TERMinator, which uses both TERM-based and coordinate-based information, and COORDinator, which uses only coordinate-based information. Using these two models, we demonstrate that TERMs can be utilized to improve native sequence recovery performance of neural models. Furthermore, we demonstrate that sequences designed by TERMinator are predicted to fold to their target structures by AlphaFold. Finally, we show that both TERMinator and COORDinator learn notions of energetics, and these methods can be fine-tuned on experimental data to improve predictions. Our results suggest that using TERM-based and coordinate-based features together may be beneficial for protein design and that structure-based neural models that produce Potts energy tables have utility for flexible applications in protein science.

Masked inverse folding with sequence transfer for protein representation learning

Self-supervised pretraining on protein sequences has led to state-of-the art performance on protein function and fitness prediction. However, sequence-only methods ignore the rich information contained in experimental and predicted protein structures. Meanwhile, inverse folding methods reconstruct a protein's amino-acid sequence given its structure, but do not take advantage of sequences that do not have known structures. In this study, we train a masked inverse folding protein masked language model parameterized as a structured graph neural network. During pretraining, this model learns to reconstruct corrupted sequences conditioned on the backbone structure. We then show that using the outputs from a pretrained sequence-only protein masked language model as input to the inverse folding model further improves pretraining perplexity. We evaluate both of these models on downstream protein engineering tasks and analyze the effect of using information from experimental or predicted structures on performance.

Deep learning of protein sequence design of protein-protein interactions

MOTIVATION

As more data of experimentally determined protein structures are becoming available, data-driven models to describe protein sequence-structure relationships become more feasible. Within this space, the amino acid sequence design of protein-protein interactions is still a rather challenging subproblem with very low success rates-yet, it is central to most biological processes.

RESULTS

We developed an attention-based deep learning model inspired by algorithms used for image-caption assignments to design peptides or protein fragment sequences. Our trained model can be applied for the redesign of natural protein interfaces or the designed protein interaction fragments. Here, we validate the potential by recapitulating naturally occurring protein-protein interactions including antibody-antigen complexes. The designed interfaces accurately capture essential native interactions and have comparable native-like binding affinities in silico. Furthermore, our model does not need a precise backbone location, making it an attractive tool for working with de novo design of protein-protein interactions.

AVAILABILITY AND IMPLEMENTATION

The source code of the method is available at https://github.com/strauchlab/iNNterfaceDesign.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

PPI-Miner: A Structure and Sequence Motif Co-Driven Protein-Protein Interaction Mining and Modeling Computational Method

Protein-protein interactions (PPIs) play important roles in biological processes of life, and predicting PPIs becomes a critical scientific issue of concern. Most PPIs occur through small domains or motifs (fragments), which are challenging and laborious to map by standard biochemical approaches because they generally require the cloning of several truncation mutants. Here, we present a computational method, named as PPI-Miner, to fish potential protein interacting partners utilizing protein motifs as queries. In brief, this work first developed a motif-matching algorithm designed to identify the proteins that contain sequential or structural similar motifs with the given query motif. Being aligned to the query motif, the binding mode of the discovered motif and its receptor protein will be initially determined to be used to build PPI complexes accordingly. Eventually, a PPI complex structure could be built and optimized with a designed automatic protocol. Besides discovering PPIs, PPI-Miner can also be applied to other areas, i.e., the rational design of molecular glues and protein vaccines. In this work, PPI-Miner was employed to mine the potential cereblon (CRBN) substrates from human proteome. As a result, 1,739 candidates were predicted, and 16 of them have been experimentally validated in previous studies. The source code of PPI-Miner can be obtained from the GitHub repository (https://github.com/Wang-Lin-boop/PPI-Miner), the webserver is freely available for users (https://bailab.siais.shanghaitech.edu.cn/services/ppi-miner), and the database of predicted CRBN substrates is accessible at https://bailab.siais.shanghaitech.edu.cn/services/crbn-subslib.

Protein re-surfacing of E. coli L-Asparaginase to evade pre-existing anti-drug antibodies and hypersensitivity responses

The optimal use of many biotherapeutics is restricted by Anti-drug antibodies (ADAs) and hypersensitivity responses which can affect potency and ability to administer a treatment. Here we demonstrate that Re-surfacing can be utilized as a generalizable approach to engineer proteins with extensive surface residue modifications in order to avoid binding by pre-existing ADAs. This technique was applied to E. coli Asparaginase (ASN) to produce functional mutants with up to 58 substitutions resulting in direct modification of 35% of surface residues. Re-surfaced ASNs exhibited significantly reduced binding to murine, rabbit and human polyclonal ADAs, with a negative correlation observed between binding and mutational distance from the native protein. Reductions in ADA binding correlated with diminished hypersensitivity responses in an in vivo mouse model. By using computational design approaches to traverse extended distances in mutational space while maintaining function, protein Re-surfacing may provide a means to generate novel or second line therapies for life-saving drugs with limited therapeutic alternatives.

Fragment-based computational design of antibodies targeting structured epitopes

De novo design methods hold the promise of reducing the time and cost of antibody discovery while enabling the facile and precise targeting of predetermined epitopes. Here, we describe a fragment-based method for the combinatorial design of antibody binding loops and their grafting onto antibody scaffolds. We designed and tested six single-domain antibodies targeting different epitopes on three antigens, including the receptor-binding domain of the SARS-CoV-2 spike protein. Biophysical characterization showed that all designs are stable and bind their intended targets with affinities in the nanomolar range without in vitro affinity maturation. We further discuss how a high-resolution input antigen structure is not required, as similar predictions are obtained when the input is a crystal structure or a computer-generated model. This computational procedure, which readily runs on a laptop, provides a starting point for the rapid generation of lead antibodies binding to preselected epitopes.

ATLIGATOR: editing protein interactions with an atlas-based approach

MOTIVATION

Recognition of specific molecules by proteins is a fundamental cellular mechanism and relevant for many applications. Being able to modify binding is a key interest and can be achieved by repurposing established interaction motifs. We were specifically interested in a methodology for the design of peptide binding modules. By leveraging interaction data from known protein structures, we plan to accelerate the design of novel protein or peptide binders.

RESULTS

We developed ATLIGATOR-a computational method to support the analysis and design of a protein's interaction with a single side chain. Our program enables the building of interaction atlases based on structures from the PDB. From these atlases pocket definitions are extracted that can be searched for frequent interactions. These searches can reveal similarities in unrelated proteins as we show here for one example. Such frequent interactions can then be grafted onto a new protein scaffold as a starting point of the design process. The ATLIGATOR tool is made accessible through a python API as well as a CLI with python scripts.

AVAILABILITY AND IMPLEMENTATION

Source code can be downloaded at github (https://www.github.com/Hoecker-Lab/atligator), installed from PyPI ('atligator') and is implemented in Python 3.

Protein Design: From the Aspect of Water Solubility and Stability

Water solubility and structural stability are key merits for proteins defined by the primary sequence and 3D-conformation. Their manipulation represents important aspects of the protein design field that relies on the accurate placement of amino acids and molecular interactions, guided by underlying physiochemical principles. Emulated designer proteins with well-defined properties both fuel the knowledge-base for more precise computational design models and are used in various biomedical and nanotechnological applications. The continuous developments in protein science, increasing computing power, new algorithms, and characterization techniques provide sophisticated toolkits for solubility design beyond guess work. In this review, we summarize recent advances in the protein design field with respect to water solubility and structural stability. After introducing fundamental design rules, we discuss the transmembrane protein solubilization and de novo transmembrane protein design. Traditional strategies to enhance protein solubility and structural stability are introduced. The designs of stable protein complexes and high-order assemblies are covered. Computational methodologies behind these endeavors, including structure prediction programs, machine learning algorithms, and specialty software dedicated to the evaluation of protein solubility and aggregation, are discussed. The findings and opportunities for Cryo-EM are presented. This review provides an overview of significant progress and prospects in accurate protein design for solubility and stability.

Rotamer-free protein sequence design based on deep learning and self-consistency

Several previously proposed deep learning methods to design amino acid sequences that autonomously fold into a given protein backbone yielded promising results in computational tests but did not outperform conventional energy function-based methods in wet experiments. Here we present the ABACUS-R method, which uses an encoder-decoder network trained using a multitask learning strategy to predict the sidechain type of a central residue from its three-dimensional local environment, which includes, besides other features, the types but not the conformations of the surrounding sidechains. This eliminates the need to reconstruct and optimize sidechain structures, and drastically simplifies the sequence design process. Thus iteratively applying the encoder-decoder to different central residues is able to produce self-consistent overall sequences for a target backbone. Results of wet experiments, including five structures solved by X-ray crystallography, show that ABACUS-R outperforms state-of-the-art energy function-based methods in success rate and design precision.

Large-scale design and refinement of stable proteins using sequence-only models

Engineered proteins generally must possess a stable structure in order to achieve their designed function. Stable designs, however, are astronomically rare within the space of all possible amino acid sequences. As a consequence, many designs must be tested computationally and experimentally in order to find stable ones, which is expensive in terms of time and resources. Here we use a high-throughput, low-fidelity assay to experimentally evaluate the stability of approximately 200,000 novel proteins. These include a wide range of sequence perturbations, providing a baseline for future work in the field. We build a neural network model that predicts protein stability given only sequences of amino acids, and compare its performance to the assayed values. We also report another network model that is able to generate the amino acid sequences of novel stable proteins given requested secondary sequences. Finally, we show that the predictive model—despite weaknesses including a noisy data set—can be used to substantially increase the stability of both expert-designed and model-generated proteins.

Propagation of seminal toxins through binary expression gene drives could suppress populations

Gene drives can be highly effective in controlling a target population by disrupting a female fertility gene. To spread across a population, these drives require that disrupted alleles be largely recessive so as not to impose too high of a fitness penalty. We argue that this restriction may be relaxed by using a double gene drive design to spread a split binary expression system. One drive carries a dominant lethal/toxic effector alone and the other a transactivator factor, without which the effector will not act. Only after the drives reach sufficiently high frequencies would individuals have the chance to inherit both system components and the effector be expressed. We explore through mathematical modeling the potential of this design to spread dominant lethal/toxic alleles and suppress populations. We show that this system could be implemented to spread engineered seminal proteins designed to kill females, making it highly effective against polyandrous populations.

Making Enzymes Suitable for Organic Chemistry by Rational Protein Design

This review outlines recent developments in protein engineering of stereo‐ and regioselective enzymes, which are of prime interest in organic and pharmaceutical chemistry as well as biotechnology. The widespread application of enzymes was hampered for decades due to limited enantio‐, diastereo‐ and regioselectivity, which was the reason why most organic chemists were not interested in biocatalysis. This attitude began to change with the advent of semi‐rational directed evolution methods based on focused saturation mutagenesis at sites lining the binding pocket. Screening constitutes the labor‐intensive step (bottleneck), which is the reason why various research groups are continuing to develop techniques for the generation of small and smart mutant libraries. Rational enzyme design, traditionally an alternative to directed evolution, provides small collections of mutants which require minimal screening. This approach first focused on thermostabilization, and did not enter the field of stereoselectivity until later. Computational guides such as the Rosetta algorithms, HotSpot Wizard metric, and machine learning (ML) contribute significantly to decision making. The newest advancements show that semi‐rational directed evolution such as CAST/ISM and rational enzyme design no longer develop on separate tracks, instead, they have started to merge. Indeed, researchers utilizing the two approaches have learned from each other. Today, the toolbox of organic chemists includes enzymes, primarily because the possibility of controlling stereoselectivity by protein engineering has ensured reliability when facing synthetic challenges. This review was also written with the hope that undergraduate and graduate education will include enzymes more so than in the past.

Accelerating therapeutic protein design

Protein structures provide for defined microenvironments that can support complex pharmacological functions, otherwise unachievable by small molecules. The advent of therapeutic proteins has thus greatly broadened the range of manageable disorders. Leveraging the knowledge and recent advances in de novo protein design methods has the prospect of revolutionizing how protein drugs are discovered and developed. This review lays out the main challenges facing therapeutic proteins discovery and development, and how present and future advancements of protein design can accelerate the protein drug pipelines.

Structure‐conditioned amino‐acid couplings: how contact geometry affects pairwise sequence preferences

Relating a protein's sequence to its conformation is a central challenge for both structure prediction and sequence design. Statistical contact potentials, as well as their more descriptive versions that account for side‐chain orientation and other geometric descriptors, have served as simplistic but useful means of representing second‐order contributions in sequence–structure relationships. Here we ask what happens when a pairwise potential is conditioned on the fully defined geometry of interacting backbones fragments. We show that the resulting structure‐conditioned coupling energies more accurately reflect pair preferences as a function of structural contexts. These structure‐conditioned energies more reliably encode native sequence information and more highly correlate with experimentally determined coupling energies. Clustering a database of interaction motifs by structure results in ensembles of similar energies and clustering them by energy results in ensembles of similar structures. By comparing many pairs of interaction motifs and showing that structural similarity and energetic similarity go hand‐in‐hand, we provide a tangible link between modular sequence and structure elements. This link is applicable to structural modeling, and we show that scoring CASP models with structured‐conditioned energies results in substantially higher correlation with structural quality than scoring the same models with a contact potential. We conclude that structure‐conditioned coupling energies are a good way to model the impact of interaction geometry on second‐order sequence preferences.

Graph representation learning for structural proteomics

The field of structural proteomics, which is focused on studying the structure-function relationship of proteins and protein complexes, is experiencing rapid growth. Since the early 2000s, structural databases such as the Protein Data Bank are storing increasing amounts of protein structural data, in addition to modeled structures becoming increasingly available. This, combined with the recent advances in graph-based machine-learning models, enables the use of protein structural data in predictive models, with the goal of creating tools that will advance our understanding of protein function. Similar to using graph learning tools to molecular graphs, which currently undergo rapid development, there is also an increasing trend in using graph learning approaches on protein structures. In this short review paper, we survey studies that use graph learning techniques on proteins, and examine their successes and shortcomings, while also discussing future directions.

Facilitating Machine Learning-Guided Protein Engineering with Smart Library Design and Massively Parallel Assays

Protein design plays an important role in recent medical advances from antibody therapy to vaccine design. Typically, exhaustive mutational screens or directed evolution experiments are used for the identification of the best design or for improvements to the wild-type variant. Even with a high-throughput screening on pooled libraries and Next-Generation Sequencing to boost the scale of read-outs, surveying all the variants with combinatorial mutations for their empirical fitness scores is still of magnitudes beyond the capacity of existing experimental settings. To tackle this challenge, in-silico approaches using machine learning to predict the fitness of novel variants based on a subset of empirical measurements are now employed. These machine learning models turn out to be useful in many cases, with the premise that the experimentally determined fitness scores and the amino-acid descriptors of the models are informative. The machine learning models can guide the search for the highest fitness variants, resolve complex epistatic relationships, and highlight bio-physical rules for protein folding. Using machine learning-guided approaches, researchers can build more focused libraries, thus relieving themselves from labor-intensive screens and fast-tracking the optimization process. Here, we describe the current advances in massive-scale variant screens, and how machine learning and mutagenesis strategies can be integrated to accelerate protein engineering. More specifically, we examine strategies to make screens more economical, informative, and effective in discovery of useful variants.

A distributed residue network permits conformational binding specificity in a conserved family of actin remodelers

Metazoan proteomes contain many paralogous proteins that have evolved distinct functions. The Ena/VASP family of actin regulators consists of three members that share an EVH1 interaction domain with a 100 % conserved binding site. A proteome-wide screen revealed photoreceptor cilium actin regulator (PCARE) as a high-affinity ligand for ENAH EVH1. Here, we report the surprising observation that PCARE is ~100-fold specific for ENAH over paralogs VASP and EVL and can selectively bind ENAH and inhibit ENAH-dependent adhesion in cells. Specificity arises from a mechanism whereby PCARE stabilizes a conformation of the ENAH EVH1 domain that is inaccessible to family members VASP and EVL. Structure-based modeling rapidly identified seven residues distributed throughout EVL that are sufficient to differentiate binding by ENAH vs. EVL. By exploiting the ENAH-specific conformation, we rationally designed the tightest and most selective ENAH binder to date. Our work uncovers a conformational mechanism of interaction specificity that distinguishes highly similar paralogs and establishes tools for dissecting specific Ena/VASP functions in processes including cancer cell invasion.

Structure-based protein design with deep learning

Since the first revelation of proteins functioning as macromolecular machines through their three dimensional structures, researchers have been intrigued by the marvelous ways the biochemical processes are carried out by proteins. The aspiration to understand protein structures has fueled extensive efforts across different scientific disciplines. In recent years, it has been demonstrated that proteins with new functionality or shapes can be designed via structure-based modeling methods, and the design strategies have combined all available information - but largely piece-by-piece - from sequence derived statistics to the detailed atomic-level modeling of chemical interactions. Despite the significant progress, incorporating data-derived approaches through the use of deep learning methods can be a game changer. In this review, we summarize current progress, compare the arc of developing the deep learning approaches with the conventional methods, and describe the motivation and concepts behind current strategies that may lead to potential future opportunities.

Dynamics-Evolution Correspondence in Protein Structures

The genotype-phenotype mapping of proteins is a fundamental question in structural biology. In this Letter, with the analysis of a large dataset of proteins from hundreds of protein families, we quantitatively demonstrate the correlations between the noise-induced protein dynamics and mutation-induced variations of native structures, indicating the dynamics-evolution correspondence of proteins. Based on the investigations of the linear responses of native proteins, the origin of such a correspondence is elucidated. It is essential that the noise- and mutation-induced deformations of the proteins are restricted on a common low-dimensional subspace, as confirmed from the data. These results suggest an evolutionary mechanism of the proteins gaining both dynamical flexibility and evolutionary structural variability.

Decorated networks of native proteins: nanomaterials with tunable mesoscopic domain size

Natural and artificial proteins with designer properties and functionalities offer unparalleled opportunity for functional nanoarchitectures formed through self-assembly. However, to exploit this potential we need to design the system such that assembly results in desired architecture forms while avoiding denaturation and therefore retaining protein functionality. Here we address this challenge with a model system of fluorescent proteins. By manipulating self-assembly using techniques inspired by soft matter where interactions between the components are controlled to yield the desired structure, we have developed a methodology to assemble networks of proteins of one species which we can decorate with another, whose coverage we can tune. Consequently, the interfaces between domains of each component can also be tuned, with potential applications for example in energy - or electron - transfer. Our model system of eGFP and mCherry with tuneable interactions reveals control over domain sizes in the resulting networks.

Evolution, folding, and design of TIM barrels and related proteins

Proteins are chief actors in life that perform a myriad of exquisite functions. This diversity has been enabled through the evolution and diversification of protein folds. Analysis of sequences and structures strongly suggest that numerous protein pieces have been reused as building blocks and propagated to many modern folds. This information can be traced to understand how the protein world has diversified. In this review, we discuss the latest advances in the analysis of protein evolutionary units, and we use as a model system one of the most abundant and versatile topologies, the TIM-barrel fold, to highlight the existing common principles that interconnect protein evolution, structure, folding, function, and design.

A fragment-based protein interface design algorithm for symmetric assemblies

Theoretical and experimental advances in protein engineering have led to the creation of precisely defined, novel protein assemblies of great size and complexity, with diverse applications. One powerful approach involves designing a new attachment or binding interface between two simpler symmetric oligomeric protein components. The required methods of design, which present both similarities and key differences compared to problems in protein docking, remain challenging and are not yet routine. With the aim of more fully enabling this emerging area of protein material engineering, we developed a computer program, nanohedra, to introduce two key advances. First, we encoded in the program the construction rules (i.e. the search space parameters) that underlie all possible symmetric material constructions. Second, we developed algorithms for rapidly identifying favorable docking/interface arrangements based on tabulations of empirical patterns of known protein fragment-pair associations. As a result, the candidate poses that nanohedra generates for subsequent amino acid interface design appear highly native-like (at the protein backbone level), while simultaneously conforming to the exacting requirements for symmetry-based assembly. A retrospective computational analysis of successful vs failed experimental studies supports the expectation that this should improve the success rate for this challenging area of protein engineering.

Data-driven computational protein design

Computational protein design can generate proteins not found in nature that adopt desired structures and perform novel functions. Although proteins could, in theory, be designed with ab initio methods, practical success has come from using large amounts of data that describe the sequences, structures, and functions of existing proteins and their variants. We present recent creative uses of multiple-sequence alignments, protein structures, and high-throughput functional assays in computational protein design. Approaches range from enhancing structure-based design with experimental data to building regression models to training deep neural nets that generate novel sequences. Looking ahead, deep learning will be increasingly important for maximizing the value of data for protein design.

Breakthroughs in computational design methods open up new frontiers for de novo protein engineering

Proteins catalyze the majority of chemical reactions in organisms, and harnessing this power has long been the focus of the protein engineering field. Computational protein design aims to create new proteins and functions in silico, and in doing so, accelerate the process, reduce costs and enable more sophisticated engineering goals to be accomplished. Challenges that very recently seemed impossible are now within reach thanks to several landmark advances in computational protein design methods. Here, we summarize these new methods, with a particular emphasis on de novo protein design advancements occurring within the past 5 years.

Repeat proteins: designing new shapes and functions for solenoid folds

The modular nature of repeat proteins has inspired the design of regular and completely novel sequences and structures. Research in the past years has provided a broad set of design approaches and new repeat proteins that have found applications in molecular recognition, taking advantage of the natural ability of some of these families to bind proteins, peptides and nucleic acids. Here, we provide an overview on the recent trends in design of repeat proteins, particularly solenoid folds, and their applications. By exploiting the intrinsic modularity of repeats, new architectures have been designed that combine different types of repeat, are easily scalable by changing the number of repeats and can be quickly generated by using existing modular building blocks.

Structural analysis of cross α-helical nanotubes provides insight into the designability of filamentous peptide nanomaterials

The exquisite structure-function correlations observed in filamentous protein assemblies provide a paradigm for the design of synthetic peptide-based nanomaterials. However, the plasticity of quaternary structure in sequence-space and the lability of helical symmetry present significant challenges to the de novo design and structural analysis of such filaments. Here, we describe a rational approach to design self-assembling peptide nanotubes based on controlling lateral interactions between protofilaments having an unusual cross-α supramolecular architecture. Near-atomic resolution cryo-EM structural analysis of seven designed nanotubes provides insight into the designability of interfaces within these synthetic peptide assemblies and identifies a non-native structural interaction based on a pair of arginine residues. This arginine clasp motif can robustly mediate cohesive interactions between protofilaments within the cross-α nanotubes. The structure of the resultant assemblies can be controlled through the sequence and length of the peptide subunits, which generates synthetic peptide filaments of similar dimensions to flagella and pili.