Computational design of mechanically coupled axle-rotor protein assemblies

Ion-driven rotary membrane motors: From structure to function

Ion-driven membrane motors, essential across all domains of life, convert a gradient of ions across a membrane into rotational energy, facilitating diverse biological processes including ATP synthesis, substrate transport, and bacterial locomotion. Herein, we highlight recent structural advances in the understanding of two classes of ion-driven membrane motors: rotary ATPases and 5:2 motors. The recent structure of the human F-type ATP synthase is emphasised along with the gained structural insight into clinically relevant mutations. Furthermore, we highlight the diverse roles of 5:2 motors and recent mechanistic understanding gained through the resolution of ions in the structure of a sodium-driven motor, combining insights into potential unifying mechanisms of ion selectivity and rotational torque generation in the context of their function as part of complex biological systems.

An integrative approach to protein sequence design through multiobjective optimization

With recent methodological advances in the field of computational protein design, in particular those based on deep learning, there is an increasing need for frameworks that allow for coherent, direct integration of different models and objective functions into the generative design process. Here we demonstrate how evolutionary multiobjective optimization techniques can be adapted to provide such an approach. With the established Non-dominated Sorting Genetic Algorithm II (NSGA-II) as the optimization framework, we use AlphaFold2 and ProteinMPNN confidence metrics to define the objective space, and a mutation operator composed of ESM-1v and ProteinMPNN to rank and then redesign the least favorable positions. Using the two-state design problem of the foldswitching protein RfaH as an in-depth case study, and PapD and calmodulin as examples of higher-dimensional design problems, we show that the evolutionary multiobjective optimization approach leads to significant reduction in the bias and variance in RfaH native sequence recovery, compared to a direct application of ProteinMPNN. We suggest that this improvement is due to three factors: (i) the use of an informative mutation operator that accelerates the sequence space exploration, (ii) the parallel, iterative design process inherent to the genetic algorithm that improves upon the ProteinMPNN autoregressive sequence decoding scheme, and (iii) the explicit approximation of the Pareto front that leads to optimal design candidates representing diverse tradeoff conditions. We anticipate this approach to be readily adaptable to different models and broadly relevant for protein design tasks with complex specifications.

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.

Modeling the Annexin A1-S100A11 heterotetramer: a molecular dynamics investigation of structure and correlated motion

Annexin A1 (A1) has been shown to form a tetrameric complex (A1t) with S100A11 which is implicated in calcium homeostasis and EGFR pathways. In this work, a full-length model of the A1t was generated for the first time. Multiple molecular dynamics simulations were performed on the complete A1t model for several hundred nanoseconds each to assess the structure and dynamics of A1t. These simulations yielded three structures for the A1 N-terminus (ND) which were identified via principal component analysis. The orientations and interactions of the first 11 A1-ND residues for all three structures were conserved, and their binding modes were strikingly similar to those of the Annexin A2 N-terminus in the Annexin A2-p11 tetramer. In this study, we provided detailed atomistic information for the A1t. Strong interactions were identified within the A1t between the A1-ND and both S100A11 monomers. Residues M3, V4, S5, E6, L8, K9, W12, E15, and E18 of A1 were the strongest interactions between A1 and the S100A11 dimer. The different conformations of the A1t were attributed to the interaction between W12 of the A1-ND with M63 of S100A11 which caused a kink in the A1-ND. Cross-correlation analysis revealed strong correlated motion throughout the A1t. Strong positive correlation was observed between the ND and S100A11 in all simulations regardless of conformation. This work suggests that the stable binding of the first 11 residues of A1-ND to S100A11 is potentially a theme for Annexin-S100 complexes and that the flexibility of the A1-ND allows for multiple conformations of the A1t.Communicated by Ramaswamy H. Sarma.

An integrative approach to protein sequence design through multiobjective optimization

With recent methodological advances in the field of computational protein design, in particular those based on deep learning, there is an increasing need for frameworks that allow for coherent, direct integration of different models and objective functions into the generative design process. Here we demonstrate how evolutionary multiobjective optimization techniques can be adapted to provide such an approach. With the established Non-dominated Sorting Genetic Algorithm II (NSGA-II) as the optimization framework, we use AlphaFold2 and ProteinMPNN confidence metrics to define the objective space, and a mutation operator composed of ESM-1v and ProteinMPNN to rank and then redesign the least favorable positions. Using the multistate design problem of the foldswitching protein RfaH as an in-depth case study, we show that the evolutionary multiobjective optimization approach leads to significant reduction in the bias and variance in RfaH native sequence recovery, compared to a direct application of ProteinMPNN. We suggest that this improvement is due to three factors: (i) the use of an informative mutation operator that accelerates the sequence space exploration, (ii) the parallel, iterative design process inherent to the genetic algorithm that improves upon the ProteinMPNN autoregressive sequence decoding scheme, and (iii) the explicit approximation of the Pareto front that leads to optimal design candidates representing diverse tradeoff conditions. We anticipate this approach to be readily adaptable to different models and broadly relevant for protein design tasks with complex specifications.

A DNA turbine powered by a transmembrane potential across a nanopore

Rotary motors play key roles in energy transduction, from macroscale windmills to nanoscale turbines such as ATP synthase in cells. Despite our abilities to construct engines at many scales, developing functional synthetic turbines at the nanoscale has remained challenging. Here, we experimentally demonstrate rationally designed nanoscale DNA origami turbines with three chiral blades. These DNA nanoturbines are 24-27 nm in height and diameter and can utilize transmembrane electrochemical potentials across nanopores to drive DNA bundles into sustained unidirectional rotations of up to 10 revolutions s-1. The rotation direction is set by the designed chirality of the turbine. All-atom molecular dynamics simulations show how hydrodynamic flows drive this turbine. At high salt concentrations, the rotation direction of turbines with the same chirality is reversed, which is explained by a change in the anisotropy of the electrophoretic mobility. Our artificial turbines operate autonomously in physiological conditions, converting energy from naturally abundant electrochemical potentials into mechanical work. The results open new possibilities for engineering active robotics at the nanoscale.

CBe4H6: a molecular rotor with a built-in on-off switch

It is highly challenging to control (stop and resume as needed) molecular rotors because their intramolecular rotations are electronically enabled by delocalized σ bonding, and the desired control needs to be able to destroy and restore such σ bonding, which usually means difficult chemical manipulation (substitution or doping atom). In this work, we report CBe4H6, a molecular rotor that can be controlled independently of chemical manipulation. This molecule exhibited the uninterrupted free rotation of Be and H atoms around the central carbon in first-principles molecular dynamics simulations at high temperatures (600 and 1000 K), but the rotation cannot be witnessed in the simulation at room temperature (298 K). Specifically, when a C-H bond in the CBe4H6 molecule adopts the equatorial configuration at 298 K, it destroys the central delocalized σ bonding and blocks the intramolecular rotation (the rotor is turned "OFF"); when it can adopt the axial configuration at 600 and 1000 K, the central delocalized σ bonding can be restored and the intramolecular rotation can be resumed (the rotor is turned "ON"). Neutral CBe4H6 is thermodynamically favorable and electronically stable, as reflected by a wide HOMO-LUMO gap of 7.99 eV, a high vertical detachment energy of 9.79 eV, and a positive electron affinity of 0.24 eV, so it may be stable enough for the synthesis, not only in the gas phase, but also in the condensed phase.

Motility of an autonomous protein-based artificial motor that operates via a burnt-bridge principle

Inspired by biology, great progress has been made in creating artificial molecular motors. However, the dream of harnessing proteins - the building blocks selected by nature - to design autonomous motors has so far remained elusive. Here we report the synthesis and characterization of the Lawnmower, an autonomous, protein-based artificial molecular motor comprised of a spherical hub decorated with proteases. Its "burnt-bridge" motion is directed by cleavage of a peptide lawn, promoting motion towards unvisited substrate. We find that Lawnmowers exhibit directional motion with average speeds of up to 80 nm/s, comparable to biological motors. By selectively patterning the peptide lawn on microfabricated tracks, we furthermore show that the Lawnmower is capable of track-guided motion. Our work opens an avenue towards nanotechnology applications of artificial protein motors.

De novo design of modular protein hydrogels with programmable intra- and extracellular viscoelasticity

Relating the macroscopic properties of protein-based materials to their underlying component microstructure is an outstanding challenge. Here, we exploit computational design to specify the size, flexibility, and valency of de novo protein building blocks, as well as the interaction dynamics between them, to investigate how molecular parameters govern the macroscopic viscoelasticity of the resultant protein hydrogels. We construct gel systems from pairs of symmetric protein homo-oligomers, each comprising 2, 5, 24, or 120 individual protein components, that are crosslinked either physically or covalently into idealized step-growth biopolymer networks. Through rheological assessment, we find that the covalent linkage of multifunctional precursors yields hydrogels whose viscoelasticity depends on the crosslink length between the constituent building blocks. In contrast, reversibly crosslinking the homo-oligomeric components with a computationally designed heterodimer results in viscoelastic biomaterials exhibiting fluid-like properties under rest and low shear, but solid-like behavior at higher frequencies. Exploiting the unique genetic encodability of these materials, we demonstrate the assembly of protein networks within living mammalian cells and show via fluorescence recovery after photobleaching (FRAP) that mechanical properties can be tuned intracellularly in a manner similar to formulations formed extracellularly. We anticipate that the ability to modularly construct and systematically program the viscoelastic properties of designer protein-based materials could have broad utility in biomedicine, with applications in tissue engineering, therapeutic delivery, and synthetic biology.

Machine learning for functional protein design

Recent breakthroughs in AI coupled with the rapid accumulation of protein sequence and structure data have radically transformed computational protein design. New methods promise to escape the constraints of natural and laboratory evolution, accelerating the generation of proteins for applications in biotechnology and medicine. To make sense of the exploding diversity of machine learning approaches, we introduce a unifying framework that classifies models on the basis of their use of three core data modalities: sequences, structures and functional labels. We discuss the new capabilities and outstanding challenges for the practical design of enzymes, antibodies, vaccines, nanomachines and more. We then highlight trends shaping the future of this field, from large-scale assays to more robust benchmarks, multimodal foundation models, enhanced sampling strategies and laboratory automation.

De novo protein design-From new structures to programmable functions

Methods from artificial intelligence (AI) trained on large datasets of sequences and structures can now "write" proteins with new shapes and molecular functions de novo, without starting from proteins found in nature. In this Perspective, I will discuss the state of the field of de novo protein design at the juncture of physics-based modeling approaches and AI. New protein folds and higher-order assemblies can be designed with considerable experimental success rates, and difficult problems requiring tunable control over protein conformations and precise shape complementarity for molecular recognition are coming into reach. Emerging approaches incorporate engineering principles-tunability, controllability, and modularity-into the design process from the beginning. Exciting frontiers lie in deconstructing cellular functions with de novo proteins and, conversely, constructing synthetic cellular signaling from the ground up. As methods improve, many more challenges are unsolved.

Precisely patterned nanofibres made from extendable protein multiplexes

Molecular systems with coincident cyclic and superhelical symmetry axes have considerable advantages for materials design as they can be readily lengthened or shortened by changing the length of the constituent monomers. Among proteins, alpha-helical coiled coils have such symmetric, extendable architectures, but are limited by the relatively fixed geometry and flexibility of the helical protomers. Here we describe a systematic approach to generating modular and rigid repeat protein oligomers with coincident C2 to C8 and superhelical symmetry axes that can be readily extended by repeat propagation. From these building blocks, we demonstrate that a wide range of unbounded fibres can be systematically designed by introducing hydrophilic surface patches that force staggering of the monomers; the geometry of such fibres can be precisely tuned by varying the number of repeat units in the monomer and the placement of the hydrophilic patches.

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.

New Insights into the Cooperativity and Dynamics of Dimeric Enzymes

A survey of protein databases indicates that the majority of enzymes exist in oligomeric forms, with about half of those found in the UniProt database being homodimeric. Understanding why many enzymes are in their dimeric form is imperative. Recent developments in experimental and computational techniques have allowed for a deeper comprehension of the cooperative interactions between the subunits of dimeric enzymes. This review aims to succinctly summarize these recent advancements by providing an overview of experimental and theoretical methods, as well as an understanding of cooperativity in substrate binding and the molecular mechanisms of cooperative catalysis within homodimeric enzymes. Focus is set upon the beneficial effects of dimerization and cooperative catalysis. These advancements not only provide essential case studies and theoretical support for comprehending dimeric enzyme catalysis but also serve as a foundation for designing highly efficient catalysts, such as dimeric organic catalysts. Moreover, these developments have significant implications for drug design, as exemplified by Paxlovid, which was designed for the homodimeric main protease of SARS-CoV-2.

Hierarchical design of pseudosymmetric protein nanoparticles

Discrete protein assemblies ranging from hundreds of kilodaltons to hundreds of megadaltons in size are a ubiquitous feature of biological systems and perform highly specialized functions 1-3. Despite remarkable recent progress in accurately designing new self-assembling proteins, the size and complexity of these assemblies has been limited by a reliance on strict symmetry 4,5. Inspired by the pseudosymmetry observed in bacterial microcompartments and viral capsids, we developed a hierarchical computational method for designing large pseudosymmetric self-assembling protein nanomaterials. We computationally designed pseudosymmetric heterooligomeric components and used them to create discrete, cage-like protein assemblies with icosahedral symmetry containing 240, 540, and 960 subunits. At 49, 71, and 96 nm diameter, these nanoparticles are the largest bounded computationally designed protein assemblies generated to date. More broadly, by moving beyond strict symmetry, our work represents an important step towards the accurate design of arbitrary self-assembling nanoscale protein objects.

Long-Time Dynamics of Selected Molecular-Motor Components Using a Physics-Based Coarse-Grained Approach

Molecular motors are essential for the movement and transportation of macromolecules in living organisms. Among them, rotatory motors are particularly efficient. In this study, we investigated the long-term dynamics of the designed left-handed alpha/alpha toroid (PDB: 4YY2), the RBM2 flagellum protein ring from Salmonella (PDB: 6SD5), and the V-type Na+-ATPase rotor in Enterococcus hirae (PDB: 2BL2) using microcanonical and canonical molecular dynamics simulations with the coarse-grained UNRES force field, including a lipid-membrane model, on a millisecond laboratory time scale. Our results demonstrate that rotational motion can occur with zero total angular momentum in the microcanonical regime and that thermal motions can be converted into net rotation in the canonical regime, as previously observed in simulations of smaller cyclic molecules. For 6SD5 and 2BL2, net rotation (with a ratcheting pattern) occurring only about the pivot of the respective system was observed in canonical simulations. The extent and direction of the rotation depended on the initial conditions. This result suggests that rotatory molecular motors can convert thermal oscillations into net rotational motion. The energy from ATP hydrolysis is required probably to set the direction and extent of rotation. Our findings highlight the importance of molecular-motor structures in facilitating movement and transportation within living organisms.

Wetting hysteresis induces effective unidirectional water transport through a fluctuating nanochannel

We propose a water pump that actively transports water molecules through nanochannels. Spatially asymmetric noise fluctuations imposed on the channel radius cause unidirectional water flow without osmotic pressure, which can be attributed to hysteresis in the cyclic transition between the wetting/drying states. We show that the water transport depends on fluctuations, such as white, Brownian, and pink noises. Because of the high-frequency components in white noise, fast switching of open and closed states inhibits channel wetting. Conversely, pink and Brownian noises generate high-pass filtered net flow. Brownian fluctuation leads to a faster water transport rate, whereas pink noise has a higher capability to overcome pressure differences in the opposite direction. A trade-off relationship exists between the resonant frequency of the fluctuation and the flow amplification. The proposed pump can be considered as an analogy for the reversed Carnot cycle, which is the upper limit of the energy conversion efficiency.

Leveraging deep learning to improve vaccine design

Deep learning has led to incredible breakthroughs in areas of research, from self-driving vehicles to solutions, to formal mathematical proofs. In the biomedical sciences, however, the revolutionary results seen in other fields are only now beginning to be realized. Vaccine research and development efforts represent an application with high public health significance. Protein structure prediction, immune repertoire analysis, and phylogenetics are three principal areas in which deep learning is poised to provide key advances. Here, we opine on some of the current challenges with deep learning and how they are being addressed. Despite the nascent stage of deep learning applications in immunological studies, there is ample opportunity to utilize this new technology to address the most challenging and burdensome infectious diseases confronting global populations.

Inferring Subsystem Efficiencies in Bipartite Molecular Machines

Molecular machines composed of coupled subsystems transduce free energy between different external reservoirs, in the process internally transducing energy and information. While subsystem efficiencies of these molecular machines have been measured in isolation, less is known about how they behave in their natural setting when coupled together and acting in concert. Here, we derive upper and lower bounds on the subsystem efficiencies of a bipartite molecular machine. We demonstrate their utility by estimating the efficiencies of the F_{o} and F_{1} subunits of ATP synthase and that of kinesin pulling a diffusive cargo.

Stepwise design of pseudosymmetric protein hetero-oligomers

Pseudosymmetric hetero-oligomers with three or more unique subunits with overall structural (but not sequence) symmetry play key roles in biology, and systematic approaches for generating such proteins de novo would provide new routes to controlling cell signaling and designing complex protein materials. However, the de novo design of protein hetero-oligomers with three or more distinct chains with nearly identical structures is a challenging problem because it requires the accurate design of multiple protein-protein interfaces simultaneously. Here, we describe a divide-and-conquer approach that breaks the multiple-interface design challenge into a set of more tractable symmetric single-interface redesign problems, followed by structural recombination of the validated homo-oligomers into pseudosymmetric hetero-oligomers. Starting from de novo designed circular homo-oligomers composed of 9 or 24 tandemly repeated units, we redesigned the inter-subunit interfaces to generate 15 new homo-oligomers and recombined them to make 17 new hetero-oligomers, including ABC heterotrimers, A2B2 heterotetramers, and A3B3 and A2B2C2 heterohexamers which assemble with high structural specificity. The symmetric homo-oligomers and pseudosymmetric hetero-oligomers generated for each system share a common backbone, and hence are ideal building blocks for generating and functionalizing larger symmetric assemblies.

Kaleidoscope megamolecules synthesis and application using self-assembly technology

The megamolecules with high ordered structures play an important role in chemical biology and biomedical engineering. Self-assembly, a long-discovered but very appealing technique, could induce many reactions between biomacromolecules and organic linking molecules, such as an enzyme domain and its covalent inhibitors. Enzyme and its small-molecule inhibitors have achieved many successes in medical application, which realize the catalysis process and theranostic function. By employing the protein engineering technology, the building blocks of enzyme fusion protein and small molecule linker can be assembled into a novel architecture with the specified organization and conformation. Molecular level recognition of enzyme domain could provide both covalent reaction sites and structural skeleton for the functional fusion protein. In this review, we will discuss the range of tools available to combine functional domains by using the recombinant protein technology, which can assemble them into precisely specified architectures/valences and develop the kaleidoscope megamolecules for catalytic and medical application.

Small-angle X-ray scattering studies of enzymes

Enzyme function requires conformational changes to achieve substrate binding, domain rearrangements, and interactions with partner proteins, but these movements are difficult to observe. Small-angle X-ray scattering (SAXS) is a versatile structural technique that can probe such conformational changes under solution conditions that are physiologically relevant. Although it is generally considered a low-resolution structural technique, when used to study conformational changes as a function of time, ligand binding, or protein interactions, SAXS can provide rich insight into enzyme behavior, including subtle domain movements. In this perspective, we highlight recent uses of SAXS to probe structural enzyme changes upon ligand and partner-protein binding and discuss tools for signal deconvolution of complex protein solutions.

What Can De Novo Protein Design Bring to the Treatment of Hematological Disorders?

Protein therapeutics have been widely used to treat hematological disorders. With the advent of de novo protein design, protein therapeutics are not limited to ameliorating natural proteins but also produce novel protein sequences, folds, and functions with shapes and functions customized to bind to the therapeutic targets. De novo protein techniques have been widely used biomedically to design novel diagnostic and therapeutic drugs, novel vaccines, and novel biological materials. In addition, de novo protein design has provided new options for treating hematological disorders. Scientists have designed protein switches called Colocalization-dependent Latching Orthogonal Cage-Key pRoteins (Co-LOCKR) that perform computations on the surface of cells. De novo designed molecules exhibit a better capacity than the currently available tyrosine kinase inhibitors in chronic myeloid leukemia therapy. De novo designed protein neoleukin-2/15 enhances chimeric antigen receptor T-cell activity. This new technique has great biomedical potential, especially in exploring new treatment methods for hematological disorders. This review discusses the development of de novo protein design and its biological applications, with emphasis on the treatment of hematological disorders.

Design of Diverse Asymmetric Pockets in De Novo Homo-oligomeric Proteins

A challenge for design of protein-small-molecule recognition is that incorporation of cavities with size, shape, and composition suitable for specific recognition can considerably destabilize protein monomers. This challenge can be overcome through binding pockets formed at homo-oligomeric interfaces between folded monomers. Interfaces surrounding the central homo-oligomer symmetry axes necessarily have the same symmetry and so may not be well suited to binding asymmetric molecules. To enable general recognition of arbitrary asymmetric substrates and small molecules, we developed an approach to designing asymmetric interfaces at off-axis sites on homo-oligomers, analogous to those found in native homo-oligomeric proteins such as glutamine synthetase. We symmetrically dock curved helical repeat proteins such that they form pockets at the asymmetric interface of the oligomer with sizes ranging from several angstroms, appropriate for binding a single ion, to up to more than 20 Å across. Of the 133 proteins tested, 84 had soluble expression in E. coli, 47 had correct oligomeric states in solution, 35 had small-angle X-ray scattering (SAXS) data largely consistent with design models, and 8 had negative-stain electron microscopy (nsEM) 2D class averages showing the structures coming together as designed. Both an X-ray crystal structure and a cryogenic electron microscopy (cryoEM) structure are close to the computational design models. The nature of these proteins as homo-oligomers allows them to be readily built into higher-order structures such as nanocages, and the asymmetric pockets of these structures open rich possibilities for small-molecule binder design free from the constraints associated with monomer destabilization.

From sequence to function through structure: Deep learning for protein design

The process of designing biomolecules, in particular proteins, is witnessing a rapid change in available tooling and approaches, moving from design through physicochemical force fields, to producing plausible, complex sequences fast via end-to-end differentiable statistical models. To achieve conditional and controllable protein design, researchers at the interface of artificial intelligence and biology leverage advances in natural language processing (NLP) and computer vision techniques, coupled with advances in computing hardware to learn patterns from growing biological databases, curated annotations thereof, or both. Once learned, these patterns can be used to provide novel insights into mechanistic biology and the design of biomolecules. However, navigating and understanding the practical applications for the many recent protein design tools is complex. To facilitate this, we 1) document recent advances in deep learning (DL) assisted protein design from the last three years, 2) present a practical pipeline that allows to go from de novo-generated sequences to their predicted properties and web-powered visualization within minutes, and 3) leverage it to suggest a generated protein sequence which might be used to engineer a biosynthetic gene cluster to produce a molecular glue-like compound. Lastly, we discuss challenges and highlight opportunities for the protein design field.