Protein Design Methods Research Articles

Protein A-like Peptide Design Based on Diffusion and ESM2 Models

Proteins are the foundation of life, and designing functional proteins remains a key challenge in biotechnology. Before the development of AlphaFold2, the focus of design was primarily on structure-centric approaches such as using the well-known open-source software Rosetta3. Following the development of AlphaFold2, deep-learning techniques for protein design gained prominence. This study proposes a new method to generate functional proteins using the diffusion model and ESM2 protein language model. Diffusion models, which are widely used in image and natural language generation, are used here for protein design, facilitating the controlled generation of new sequences. The ESM2 model, trained on the basis of large-scale protein sequence data, provides a deep understanding of the context of the sequence, thus improving the model’s ability to generate biologically relevant proteins. In this study, we used the Protein A-like peptide as a model study object, combined the diffusion model and the ESM2 model to generate new peptide sequences from minimal input data, and verified their biological activities through experiments such as the BLI affinity test. In conclusion, we developed a new method for protein design that provides a novel strategy to meet the challenges of generic protein generation.

Exploring the potential of structure-based deep learning approaches for T cell receptor design.

Deep learning methods, trained on the increasing set of available protein 3D structures and sequences, have substantially impacted the protein modeling and design field. These advancements have facilitated the creation of novel proteins, or the optimization of existing ones designed for specific functions, such as binding a target protein. Despite the demonstrated potential of such approaches in designing general protein binders, their application in designing immunotherapeutics remains relatively underexplored. A relevant application is the design of T cell receptors (TCRs). Given the crucial role of T cells in mediating immune responses, redirecting these cells to tumor or infected target cells through the engineering of TCRs has shown promising results in treating diseases, especially cancer. However, the computational design of TCR interactions presents challenges for current physics-based methods, particularly due to the unique natural characteristics of these interfaces, such as low affinity and cross-reactivity. For this reason, in this study, we explored the potential of two structure-based deep learning protein design methods, ProteinMPNN and ESM-IF1, in designing fixed-backbone TCRs for binding target antigenic peptides presented by the MHC through different design scenarios. To evaluate TCR designs, we employed a comprehensive set of sequence- and structure-based metrics, highlighting the benefits of these methods in comparison to classical physics-based design methods and identifying deficiencies for improvement.

Parametrically guided design of beta barrels and transmembrane nanopores using deep learning.

Francis Crick's global parameterization of coiled coil geometry has been widely useful for guiding design of new protein structures and functions. However, design guided by similar global parameterization of beta barrel structures has been less successful, likely due to the deviations required from ideal beta barrel geometry to maintain extensive inter-strand hydrogen bonding without introducing considerable backbone strain. Instead, beta barrels and other protein folds have been designed guided by 2D structural blueprints; while this approach has successfully generated new fluorescent proteins, transmembrane nanopores, and other structures, it requires considerable expert knowledge and provides only indirect control over the global barrel shape. Here we show that the simplicity and control over shape and structure provided by global parametric representations can be generalized beyond coiled coils by taking advantage of the rich sequence-structure relationships implicit in RoseTTAFold based inpainting and diffusion design methods. Starting from parametrically generated idealized barrel backbones, both RFjoint inpainting and RFdiffusion readily incorporate the backbone irregularities necessary for proper folding with minimal deviation from the idealized barrel geometries. We show that for beta barrels across a broad range of global beta sheet parameterizations, these methods achieve high in silico and experimental success rates, with atomic accuracy confirmed by an X-ray crystal structure of a novel beta barrel topology, and de novo designed 12, 14, and 16 stranded transmembrane nanopores with conductances ranging from 200 to 500 pS. By combining the simplicity and control of parametric generation with the high success rates of deep learning based protein design methods, our approach makes the design of proteins where global shape confers function, such as beta barrel nanopores, more precisely specifiable and accessible.

Guiding a language-model based protein design method towards MHC Class-I immune-visibility targets in vaccines and therapeutics

Proteins have an arsenal of medical applications that include disrupting protein interactions, acting as potent vaccines, and replacing genetically deficient proteins. While therapeutics must avoid triggering unwanted immune-responses, vaccines should support a robust immune-reaction targeting a broad range of pathogen variants. Therefore, computational methods modifying proteins’ immunogenicity without disrupting function are needed. While many components of the immune-system can be involved in a reaction, we focus on Cytotoxic T-lymphocytes (CTLs). These target short peptides presented via the MHC Class I (MHC-I) pathway. To explore the limits of modifying the visibility of those peptides to CTLs within the distribution of naturally occurring sequences, we developed a novel machine learning technique, CAPE-XVAE. It combines a language model with reinforcement learning to modify a protein’s immune-visibility. Our results show that CAPE-XVAE effectively modifies the visibility of the HIV Nef protein to CTLs. We contrast CAPE-XVAE to CAPE-Packer, a physics-based method we also developed. Compared to CAPE-Packer, the machine learning approach suggests sequences that draw upon local sequence similarities in the training set. This is beneficial for vaccine development, where the sequence should be representative of the real viral population. Additionally, the language model approach holds promise for preserving both known and unknown functional constraints, which is essential for the immune-modulation of therapeutic proteins. In contrast, CAPE-Packer, emphasizes preserving the protein’s overall fold and can reach greater extremes of immune-visibility, but falls short of capturing the sequence diversity of viral variants available to learn from. Source code: https://github.com/hcgasser/CAPE (Tag: v1.1)

Investigation of the MDM2-binding potential of de novo designed peptides using enhanced sampling simulations

The tumor suppressor p53 plays a crucial role in cellular responses to various stresses, regulating key processes such as apoptosis, senescence, and DNA repair. Dysfunctional p53, prevalent in approximately 50 % of human cancers, contributes to tumor development and resistance to treatment. This study employed deep learning-based protein design and structure prediction methods to identify novel high-affinity peptide binders (Pep1 and Pep2) targeting MDM2, with the aim of disrupting its interaction with p53. Extensive all-atom molecular dynamics simulations highlighted the stability of the designed peptide in complex with the target, supported by several structural analyses, including RMSD, RMSF, Rg, SASA, PCA, and free energy landscapes. Using the steered molecular dynamics and umbrella sampling simulations, we elucidate the dissociation dynamics of p53, Pep1, and Pep2 from MDM2. Notable differences in interaction profiles were observed, emphasizing the distinct dissociation patterns of each peptide. In conclusion, the results of our umbrella sampling simulations suggest Pep1 as a higher-affinity MDM2 binder compared to p53 and Pep2, positioning it as a potential inhibitor of the MDM2-p53 interaction. Using state-of-the-art protein design tools and advanced MD simulations, this study provides a comprehensive framework for rational in silico design of peptide binders with therapeutic implications in disrupting MDM2-p53 interactions for anticancer interventions.

Combining Rosetta Sequence Design with Protein Language Model Predictions Using Evolutionary Scale Modeling (ESM) as Restraint.

Computational protein sequence design has the ambitious goal of modifying existing or creating new proteins; however, designing stable and functional proteins is challenging without predictability of protein dynamics and allostery. Informing protein design methods with evolutionary information limits the mutational space to more native-like sequences and results in increased stability while maintaining functions. Recently, language models, trained on millions of protein sequences, have shown impressive performance in predicting the effects of mutations. Assessing Rosetta-designed sequences with a language model showed scores that were worse than those of their original sequence. To inform Rosetta design protocols with language model predictions, we added a new metric to restrain the energy function during design using the Evolutionary Scale Modeling (ESM) model. The resulting sequences have better language model scores and similar sequence recovery, with only a minor decrease in the fitness as assessed by Rosetta energy. In conclusion, our work combines the strength of recent machine learning approaches with the Rosetta protein design toolbox.

Graphormer supervised de novo protein design method and function validation.

Protein design is central to nearly all protein engineering problems, as it can enable the creation of proteins with new biological functions, such as improving the catalytic efficiency of enzymes. One key facet of protein design, fixed-backbone protein sequence design, seeks to design new sequences that will conform to a prescribed protein backbone structure. Nonetheless, existing sequence design methods present limitations, such as low sequence diversity and shortcomings in experimental validation of the designed functional proteins. These inadequacies obstruct the goal of functional protein design. To improve these limitations, we initially developed the Graphormer-based Protein Design (GPD) model. This model utilizes the Transformer on a graph-based representation of three-dimensional protein structures and incorporates Gaussian noise and a sequence random masks to node features, thereby enhancing sequence recovery and diversity. The performance of the GPD model was significantly better than that of the state-of-the-art ProteinMPNN model on multiple independent tests, especially for sequence diversity. We employed GPD to design CalB hydrolase and generated nine artificially designed CalB proteins. The results show a 1.7-fold increase in catalytic activity compared to that of the wild-type CalB and strong substrate selectivity on p-nitrophenyl acetate with different carbon chain lengths (C2-C16). Thus, the GPD method could be used for the de novo design of industrial enzymes and protein drugs. The code was released at https://github.com/decodermu/GPD.

The structural landscape of the immunoglobulin fold by large-scale de novo design.

De novo designing immunoglobulin-like frameworks that allow for functional loop diversification shows great potential for crafting antibody-like scaffolds with fully customizable structures and functions. In this work, we combined de novo parametric design with deep-learning methods for protein structure prediction and design to explore the structural landscape of 7-stranded immunoglobulin domains. After screening folding of nearly 4 million designs, we have assembled a structurally diverse library of ~50,000 immunoglobulin domains with high-confidence AlphaFold2 predictions and structures diverging from naturally occurring ones. The designed dataset enabled us to identify structural requirements for the correct folding of immunoglobulin domains, shed light on β-sheet-β-sheet rotational preferences and how these are linked to functional properties. Our approach eliminates the need for preset loop conformations and opens the route to large-scale de novo design of immunoglobulin-like frameworks.

Multi-indicator comparative evaluation for deep learning-based protein sequence design methods.

Proteins found in nature represent only a fraction of the vast space of possible proteins. Protein design presents an opportunity to explore and expand this protein landscape. Within protein design, protein sequence design plays a crucial role, and numerous successful methods have been developed. Notably, deep learning-based protein sequence design methods have experienced significant advancements in recent years. However, a comprehensive and systematic comparison and evaluation of these methods have been lacking, with indicators provided by different methods often inconsistent or lacking effectiveness. To address this gap, we have designed a diverse set of indicators that cover several important aspects, including sequence recovery, diversity, root-mean-square deviation of protein structure, secondary structure, and the distribution of polar and nonpolar amino acids. In our evaluation, we have employed an improved weighted inferiority-superiority distance method to comprehensively assess the performance of eight widely used deep learning-based protein sequence design methods. Our evaluation not only provides rankings of these methods but also offers optimization suggestions by analyzing the strengths and weaknesses of each method. Furthermore, we have developed a method to select the best temperature parameter and proposed solutions for the common issue of designing sequences with consecutive repetitive amino acids, which is often encountered in protein design methods. These findings can greatly assist users in selecting suitable protein sequence design methods. Overall, our work contributes to the field of protein sequence design by providing a comprehensive evaluation system and optimization suggestions for different methods.

Outsmart™ IL-2/15, a Novel Cytokine Designed to Enhance ROR1-Specific CAR T Anti-Tumor Activity While Minimizing Treg Activation and Systemic Cytokine Exposure

Introduction: Effective treatment with chimeric antigen receptor T (CAR-T) cells against solid and some liquid tumors will require the safe production of immune-modulating cytokines to promote CAR-T cell expansion and to stimulate endogenous anti-tumor immune responses within the tumor microenvironment. OutSmart™ IL-2/15 is a computationally designed, CD8α-targeted, IL-2-based cytokine produced by engineered T cells via a T cell activation-dependent promoter. Here, we demonstrate that inducible production of CD8-targeted IL-2/15 drives proliferation and anti-tumor efficacy of ROR1-specific CAR-T cells, stimulates bystander CD8 + T and NK cells, and minimizes activation of immune suppressive T regulatory cells (Tregs). Methods and Results: Wild-type (wt) IL-2 was modified using Rosetta protein design software package to eliminate IL-2Rα binding while retaining native IL-2Rβγ binding interfaces. Out of 10,355 designs, 38 were prioritized based on in silico analysis and ML-guided structure prediction, and evaluated for IL-2R binding as recombinant proteins. Consistent with the design criteria, none of the designs bound IL-2Rα, and 33 (87%) retained IL-2Rβγ binding and signaling activity. pSTAT5 analysis showed wt IL-2 highly activated CD4 +CD25 +FoxP3 + Treg cells, whereas the novel IL-2 designs showed a >3-log reduction Treg stimulation. These designs were iteratively optimized to generate a version exhibiting improved thermostability and IL-2Rβγ binding affinity equivalent to wt IL-2. To increase the potency against immune effector cells, but not Tregs, an anti-CD8α VHH was tethered to the modified IL-2 molecules (CD8-IL-2/15) to mimic high-affinity IL-2Rα binding and selectively activate CD8 + T and NK cells. This prosthetic binding interaction dramatically increased CD8 + T cell stimulation and CD8α + NK cell activation (>2-logs and 1-log by pSTAT5, respectively), while retaining its reduced capacity to stimulate Tregs. CD8-IL-2/15 gene expression was subsequently placed under the control of a T cell activation-dependent promoter and integrated into a lentiviral construct with a constitutively expressed ROR1-specific CAR. T cells transduced with a lentivirus expressing CD8-IL-2/15 and a ROR1-targeting CAR showed inducible cytokine production following exposure to ROR1 + tumor cells (H1975) leading to enhanced CAR-T cell proliferation and anti-tumor killing during repeat tumor challenge assays in vitro. Using immune-deficient mice (NSG) engrafted with H1975 tumors, inducible CD8-IL-2/15 enhanced ROR1-specific CAR-T cells showed durable tumor control at low doses (1e6 - 4e6 CAR T cells/animal), which was comparable to wt IL-2, whereas mock T cells and ROR1 CAR only T cells failed to control tumor growth ( Figure 1). In addition, CAR-T expansion with CD8-IL-2/15 increased >4-fold over wt IL-2 (p<0.0001), measured by cell counts in peripheral blood. Conclusions: In summary, OutSmart™ IL-2/15 is a genetic module that produces CD8-IL-2/15 in response to T cell activation, promoting robust CAR-T expansion and enhanced anti-tumor efficacy. Furthermore, local production of a CD8-IL-2/15 enhances the effector function of bystander CD8 + T cells and NK cells, but only minimally activates Treg cells due to removing the IL-2Rα binding interface. Inducible production of CD8-IL-2/15 dramatically improves the potency of a ROR1 CAR for treating ROR1 + solid and liquid cancers. More generally, OutSmart™ protein design methods and control technologies can be applied to create other designed cytokines for oncology and beyond.

Peptide binder design with inverse folding and protein structure prediction

The computational design of peptide binders towards a specific protein interface can aid diagnostic and therapeutic efforts. Here, we design peptide binders by combining the known structural space searched with Foldseek, the protein design method ESM-IF1, and AlphaFold2 (AF) in a joint framework. Foldseek generates backbone seeds for a modified version of ESM-IF1 adapted to protein complexes. The resulting sequences are evaluated with AF using an MSA representation for the receptor structure and a single sequence for the binder. We show that AF can accurately evaluate protein binders and that our bind score can select these (ROC AUC = 0.96 for the heterodimeric case). We find that designs created from seeds with more contacts per residue are more successful and tend to be short. There is a relationship between the sequence recovery in interface positions and the plDDT of the designs, where designs with ≥80% recovery have an average plDDT of 84 compared to 55 at 0%. Designed sequences have 60% higher median plDDT values towards intended receptors than non-intended ones. Successful binders (predicted interface RMSD ≤ 2 Å) are designed towards 185 (6.5%) heteromeric and 42 (3.6%) homomeric protein interfaces with ESM-IF1 compared with 18 (1.5%) using ProteinMPNN from 100 samples.

De novo design of knotted tandem repeat proteins

De novo protein design methods can create proteins with folds not yet seen in nature. These methods largely focus on optimizing the compatibility between the designed sequence and the intended conformation, without explicit consideration of protein folding pathways. Deeply knotted proteins, whose topologies may introduce substantial barriers to folding, thus represent an interesting test case for protein design. Here we report our attempts to design proteins with trefoil (31) and pentafoil (51) knotted topologies. We extended previously described algorithms for tandem repeat protein design in order to construct deeply knotted backbones and matching designed repeat sequences (N = 3 repeats for the trefoil and N = 5 for the pentafoil). We confirmed the intended conformation for the trefoil design by X ray crystallography, and we report here on this protein’s structure, stability, and folding behaviour. The pentafoil design misfolded into an asymmetric structure (despite a 5-fold symmetric sequence); two of the four repeat-repeat units matched the designed backbone while the other two diverged to form local contacts, leading to a trefoil rather than pentafoil knotted topology. Our results also provide insights into the folding of knotted proteins.

SeqPredNN: a neural network that generates protein sequences that fold into specified tertiary structures

BackgroundThe relationship between the sequence of a protein, its structure, and the resulting connection between its structure and function, is a foundational principle in biological science. Only recently has the computational prediction of protein structure based only on protein sequence been addressed effectively by AlphaFold, a neural network approach that can predict the majority of protein structures with X-ray crystallographic accuracy.A question that is now of acute relevance is the “inverse protein folding problem”: predicting the sequence of a protein that folds into a specified structure. This will be of immense value in protein engineering and biotechnology, and will allow the design and expression of recombinant proteins that can, for instance, fold into specified structures as a scaffold for the attachment of recombinant antigens, or enzymes with modified or novel catalytic activities.Here we describe the development of SeqPredNN, a feed-forward neural network trained with X-ray crystallographic structures from the RCSB Protein Data Bank to predict the identity of amino acids in a protein structure using only the relative positions, orientations, and backbone dihedral angles of nearby residues.ResultsWe predict the sequence of a protein expected to fold into a specified structure and assess the accuracy of the prediction using both AlphaFold and RoseTTAFold to computationally generate the fold of the derived sequence. We show that the sequences predicted by SeqPredNN fold into a structure with a median TM-score of 0.638 when compared to the crystal structure according to AlphaFold predictions, yet these sequences are unique and only 28.4% identical to the sequence of the crystallized protein.ConclusionsWe propose that SeqPredNN will be a valuable tool to generate proteins of defined structure for the design of novel biomaterials, pharmaceuticals, catalysts, and reporter systems. The low sequence identity of its predictions compared to the native sequence could prove useful for developing proteins with modified physical properties, such as water solubility and thermal stability. The speed and ease of use of SeqPredNN offers a significant advantage over physics-based protein design methods.

Design of Cyclic Peptides Targeting Protein-Protein Interactions Using AlphaFold.

More than 930,000 protein-protein interactions (PPIs) have been identified in recent years, but their physicochemical properties differ from conventional drug targets, complicating the use of conventional small molecules as modalities. Cyclic peptides are a promising modality for targeting PPIs, but it is difficult to predict the structure of a target protein-cyclic peptide complex or to design a cyclic peptide sequence that binds to the target protein using computational methods. Recently, AlphaFold with a cyclic offset has enabled predicting the structure of cyclic peptides, thereby enabling de novo cyclic peptide designs. We developed a cyclic peptide complex offset to enable the structural prediction of target proteins and cyclic peptide complexes and found AlphaFold2 with a cyclic peptide complex offset can predict structures with high accuracy. We also applied the cyclic peptide complex offset to the binder hallucination protocol of AfDesign, a de novo protein design method using AlphaFold, and we could design a high predicted local-distance difference test and lower separated binding energy per unit interface area than the native MDM2/p53 structure. Furthermore, the method was applied to 12 other protein-peptide complexes and one protein-protein complex. Our approach shows that it is possible to design putative cyclic peptide sequences targeting PPI.

Atomically Accurate Design of Metalloproteins with Predefined Coordination Geometries.

We report a new computational protein design method for the construction of oligomeric protein assemblies around metal centers with predefined coordination geometries. We apply this method to design two homotrimeric assemblies, Tet4 and TP1, with tetrahedral and trigonal-pyramidal tris(histidine) metal coordination geometries, respectively, and demonstrate that both assemblies form the targeted metal centers with ≤0.2 Å accuracy. Although Tet4 and TP1 are constructed from the same parent protein building block, they are distinct in terms of their overall architectures, the environment surrounding the metal centers, and their metal-based reactivities, illustrating the versatility of our approach.

AlphaFold2 and Deep Learning for Elucidating Enzyme Conformational Flexibility and Its Application for Design.

The recent success of AlphaFold2 (AF2) and other deep learning (DL) tools in accurately predicting the folded three-dimensional (3D) structure of proteins and enzymes has revolutionized the structural biology and protein design fields. The 3D structure indeed reveals key information on the arrangement of the catalytic machinery of enzymes and which structural elements gate the active site pocket. However, comprehending enzymatic activity requires a detailed knowledge of the chemical steps involved along the catalytic cycle and the exploration of the multiple thermally accessible conformations that enzymes adopt when in solution. In this Perspective, some of the recent studies showing the potential of AF2 in elucidating the conformational landscape of enzymes are provided. Selected examples of the key developments of AF2-based and DL methods for protein design are discussed, as well as a few enzyme design cases. These studies show the potential of AF2 and DL for allowing the routine computational design of efficient enzymes.

Current progress, challenges, and future perspectives of language models for protein representation and protein design

The sequence-structure-function paradigm of protein is the basis of molecular biology. What is the underlying mechanism of such sequence and structure/function corresponding relationship? We reviewed the methods for protein representation and protein design. With these protein representation models, we can accurately predict many properties of proteins, such as stability and binding affinity. Progen, Chroma, RF Diffusion, SCUBA, and other protein design models have demonstrated how human-designed artificial proteins can have desired biological functions. The protein design will revolutionize drug development. And more efficient artificial enzymes that break down industrial waste or plastics will contribute to carbon neutrality. We also discussed the three greatest challenges of protein design in future and possible solutions.

Hallucinating structure-conditioned antibody libraries for target-specific binders.

Antibodies are widely developed and used as therapeutics to treat cancer, infectious disease, and inflammation. During development, initial leads routinely undergo additional engineering to increase their target affinity. Experimental methods for affinity maturation are expensive, laborious, and time-consuming and rarely allow the efficient exploration of the relevant design space. Deep learning (DL) models are transforming the field of protein engineering and design. While several DL-based protein design methods have shown promise, the antibody design problem is distinct, and specialized models for antibody design are desirable. Inspired by hallucination frameworks that leverage accurate structure prediction DL models, we propose the FvHallucinator for designing antibody sequences, especially the CDR loops, conditioned on an antibody structure. Such a strategy generates targeted CDR libraries that retain the conformation of the binder and thereby the mode of binding to the epitope on the antigen. On a benchmark set of 60 antibodies, FvHallucinator generates sequences resembling natural CDRs and recapitulates perplexity of canonical CDR clusters. Furthermore, the FvHallucinator designs amino acid substitutions at the VH-VL interface that are enriched in human antibody repertoires and therapeutic antibodies. We propose a pipeline that screens FvHallucinator designs to obtain a library enriched in binders for an antigen of interest. We apply this pipeline to the CDR H3 of the Trastuzumab-HER2 complex to generate in silico designs predicted to improve upon the binding affinity and interfacial properties of the original antibody. Thus, the FvHallucinator pipeline enables generation of inexpensive, diverse, and targeted antibody libraries enriched in binders for antibody affinity maturation.

Dissecting the stability determinants of a challenging de novo protein fold using massively parallel design and experimentation

Designing entirely new protein structures remains challenging because we do not fully understand the biophysical determinants of folding stability. Yet, some protein folds are easier to design than others. Previous work identified the 43-residue ɑββɑ fold as especially challenging: The best designs had only a 2% success rate, compared to 39 to 87% success for other simple folds [G. J. Rocklin etal., Science 357, 168-175 (2017)]. This suggested the ɑββɑ fold would be a useful model system for gaining a deeper understanding of folding stability determinants and for testing new protein design methods. Here, we designed over 10,000 new ɑββɑ proteins and found over 3,000 of them to fold into stable structures using a high-throughput protease-based assay. NMR, hydrogen-deuterium exchange, circular dichroism, deep mutational scanning, and scrambled sequence control experiments indicated that our stable designs fold into their designed ɑββɑ structures with exceptional stability for their small size. Our large dataset enabled us to quantify the influence of universal stability determinants including nonpolar burial, helix capping, and buried unsatisfied polar atoms, as well as stability determinants unique to the ɑββɑ topology. Our work demonstrates how large-scale design and test cycles can solve challenging design problems while illuminating the biophysical determinants of folding.

Deep learning approaches for conformational flexibility and switching properties in protein design.

Following the hugely successful application of deep learning methods to protein structure prediction, an increasing number of design methods seek to leverage generative models to design proteins with improved functionality over native proteins or novel structure and function. The inherent flexibility of proteins, from side-chain motion to larger conformational reshuffling, poses a challenge to design methods, where the ideal approach must consider both the spatial and temporal evolution of proteins in the context of their functional capacity. In this review, we highlight existing methods for protein design before discussing how methods at the forefront of deep learning-based design accommodate flexibility and where the field could evolve in the future.