Recent advances in de novo protein design: Principles, methods, and applications

An in vivo target mutagenesis system for multiple hosts

In vivo target mutagenesis is a powerful approach to accelerate protein evolution. However, current approaches have been primarily developed in conventional organisms, limiting their capacity to evolve proteins with subtle variations across non-conventional host species. Here, we design an in vivo target mutagenesis system for multiple hosts (ITMU) utilizing the broad host-range plasmid RSF1010 replication element. The ITMU, which is based on a deaminase-helicase fusion and a primase error-prone DNA polymerase I fusion, induces all types of mutation in the target plasmid harboring the RSF1010 replicon, at a mutation rate 1.18 × 105-fold higher than that of the host genome. We show that ITMU-based in vivo continuous evolution is effective in Escherichia coli, Pseudomonas putida, Corynebacterium glutamicum, and Yarrowia lipolytica. This demonstrates that the ITMU is applicable to multiple microbial chassis and provides a viable alternative to in vivo continuous evolution systems.

Replicating PET Hydrolytic Activity by Positioning Active Sites with Smaller Synthetic Protein Scaffolds

Evolutionary constraints significantly limit the diversity of naturally occurring enzymes, thereby reducing the sequence repertoire available for enzyme discovery and engineering. Recent breakthroughs in protein structure prediction and de novo design, powered by artificial intelligence, now enable to create enzymes with desired functions without solely relying on traditional genome mining. Here, a computational strategy is demonstrated for creating new-to-nature polyethylene terephthalate hydrolases (PET hydrolases) by leveraging the known catalytic mechanisms and implementing multiple deep learning algorithms and molecular computations. This strategy includes the extraction of functional motifs from a template enzyme (here leaf-branch compost cutinase, LCC, is used), regeneration of new protein sequences, computational screening, experimental validation, and sequence refinement. PET hydrolytic activity is successfully replicated with designer enzymes that are at least 30% shorter in sequence length than LCC. Among them, RsPETase1 stands out due to its robust expressibility. It exhibits comparable catalytic efficiency (kcat/Km) to LCC and considerable thermostability with a melting temperature of 56 °C, despite sharing only 34% sequence similarity with LCC. This work suggests that enzyme diversity can be expanded by recapitulating functional motifs with computationally built protein scaffolds, thus generating opportunities to acquire highly active and robust enzymes that do not exist in nature.

Neural network conditioned to produce thermophilic protein sequences can increase thermal stability

This work presents Neural Optimization for Melting-temperature Enabled by Leveraging Translation (NOMELT), a novel approach for designing and ranking high-temperature stable proteins using neural machine translation. The model, trained on over 4 million protein homologous pairs from organisms adapted to different temperatures, demonstrates promising capability in targeting thermal stability. A designed variant of the Drosophila melanogaster Engrailed Homeodomain shows a melting temperature increase of 15.5 K. Furthermore, NOMELT achieves zero-shot predictive capabilities in ranking experimental melting and half-activation temperatures across a number of protein families. It achieves this without requiring extensive homology data or massive training datasets as do existing zero-shot predictors by specifically learning thermophilicity, as opposed to all natural variation. These findings underscore the potential of leveraging organismal growth temperatures in context-dependent design of proteins for enhanced thermal stability.

Methods for Theoretical Treatment of Local Fields in Proteins and Enzymes

Electric fields generated by protein scaffolds are crucial in enzymatic catalysis. This review surveys theoretical approaches for detecting, analyzing, and comparing electric fields, electrostatic potentials, and their effects on the charge density within enzyme active sites. Pioneering methods like the empirical valence bond approach rely on evaluating ionic and covalent resonance forms influenced by the field. Strategies employing polarizable force fields also facilitate field detection. The vibrational Stark effect connects computational simulations to experimental Stark spectroscopy, enabling direct comparisons. We highlight how protein dynamics induce fluctuations in local fields, influencing enzyme activity. Recent techniques assess electric fields throughout the active site volume rather than only at specific bonds, and machine learning helps relate these global fields to reactivity. Quantum theory of atoms in molecules captures the entire electron density landscape, providing a chemically intuitive perspective on field-driven catalysis. Overall, these methodologies show protein-generated fields are highly dynamic and heterogeneous, and understanding both aspects is critical for elucidating enzyme mechanisms. This holistic view empowers rational enzyme engineering by tuning electric fields, promising new avenues in drug design, biocatalysis, and industrial applications. Future directions include incorporating electric fields as explicit design targets to enhance catalytic performance and biochemical functionalities.

Advancements in protein structure prediction: A comparative overview of AlphaFold and its derivatives

This review provides a comprehensive analysis of AlphaFold (AF) and its derivatives (AF2 and AF3) in protein structure prediction. These tools have revolutionized structural biology with their highly accurate predictions, driving progress in protein modeling, drug discovery, and the study of protein dynamics. Its exceptional accuracy has redefined our understanding of protein folding, which enables groundbreaking advancements in protein design, disease research and discusses future integration with experimental techniques. In addition, their achievement features, architectures, important case studies, and noteworthy effects in the field of biology and medicine were evaluated. In consideration of the fact that AF2 is a relatively recent innovation, it has already been taken into account in many studies that highlight its applications in many ways. Moreover, the limitations of AF2 that directed to the introduction of AF3 are also reported, which is a great improvement as it provides precise predictions of the structures and interactions of proteins, DNA, RNA, and ligands, thereby aiding in the understanding of the molecular level. Addressing current challenges and forecasting future developments, this work underscores the lasting significance of AF in reshaping the scientific landscape of protein research.

Advances in designed bionanomolecular assemblies for biotechnological and biomedical applications

Recent advances in protein engineering have revolutionized the design of bionanomolecular assemblies for functional therapeutic and biotechnological applications. This review highlights the progress in creating complex protein architectures, encompassing both finite and extended assemblies. AI tools, including AlphaFold, RFDiffusion, and ProteinMPNN, have significantly enhanced the scalability and success of de novo designs. Finite assemblies, like nanocages and coiled-coil-based structures, enable precise molecular encapsulation or functional protein domain presentation. Extended assemblies, including filaments and 2D/3D lattices, offer unparalleled structural versatility for applications such as vaccine development, responsive biomaterials, and engineered cellular scaffolds. The convergence of artificial intelligence-driven design and experimental validation promises strong acceleration of the development of tailored protein assemblies, offering new opportunities in synthetic biology, materials science, biotechnology, and biomedicine.

Skin-penetrating peptides (SKPs): Enhancing skin permeation for transdermal delivery of pharmaceuticals and cosmetic compounds

Skin-penetrating peptides (SKPs) are emerging as a promising class of permeation enhancers that can facilitate macromolecule delivery across the skin. Although their pharmaceutical applications are under extensive study, SKPs are crucial for enhancing skin permeability, enabling larger molecules to penetrate the stratum corneum. This review explores the transformative role of SKPs in non-invasive transdermal drug delivery. Drawing from an extensive collection of literature, it provides insights into the current usage and application of SKPs as tools to enhance skin permeability and facilitate the delivery of larger molecules. Additionally, it highlights the opportunities, challenges, and future directions for SKP applications in transdermal drug delivery.

Enhancing Functional Protein Design Using Heuristic Optimization and Deep Learning for Anti-Inflammatory and Gene Therapy Applications

Protein sequence design is a highly challenging task, aimed at discovering new proteins that are more functional and producible under laboratory conditions than their natural counterparts. Deep learning-based approaches developed to address this problem have achieved significant success. However, these approaches often do not adequately emphasize the functional properties of proteins. In this study, we developed a heuristic optimization method to enhance key functionalities such as solubility, flexibility, and stability, while preserving the structural integrity of proteins. This method aims to reduce laboratory demands by enabling a design that is both functional and structurally sound. This approach is particularly valuable for the synthetic production of proteins with anti-inflammatory properties and those used in gene therapy. The designed proteins were initially evaluated for their ability to preserve natural structures using recovery and confidence metrics, followed by assessments with the AlphaFold tool. Additionally, natural protein sequences were mutated using a genetic algorithm and compared with those designed by our method. The results demonstrate that the protein sequences generated by our method exhibit much greater similarity to native protein sequences and structures. The code and sequences for the designed proteins are available at https://github.com/aysenursoyturk/HMHO.

De novo design protein binders for MBP and GST tags

Maltose-binding protein (MBP) and glutathione S-transferase (GST) are widely used solubility-enhancing protein tags, typically employed to address various issues related to protein expression and purification. The detection of these tags are usually achieved through binding of corresponding antibodies. Designing low-cost binders as alternatives to antibodies is of great significance. This study employed a de novo design approach, starting with a large number of protein scaffolds and screening out 6 candidate binders targeting MBP and 4 candidate binders targeting GST based on scoring functions. Flow cytometry low-affinity selection and biolayer interferometry (BLI) quantitative results showed that MBP and GST can interact strongly with one or several binders, exhibiting nanomolar binding. Among them, LZMB3 has a binding dissociation constant (KD) of 54.05 ± 1.46 nM, while LJGB3 and LJGB4 have KD values of 105.4 ± 1.812 nM and 437.9 ± 17.69 nM, respectively.

Confinement and Catalysis within De Novo Designed Peptide Barrels

De novo protein design has advanced such that many peptide assemblies and protein structures can be generated predictably and quickly. The drive now is to bring functions to these structures, for example, small-molecule binding and catalysis. The formidable challenge of binding and orienting multiple small molecules to direct chemistry is particularly important for paving the way to new functionalities. To address this, here we describe the design, characterization, and application of small-molecule:peptide ternary complexes in aqueous solution. This uses α-helical barrel (αHB) peptide assemblies, which comprise 5 or more α helices arranged around central channels. These channels are solvent accessible, and their internal dimensions and chemistries can be altered predictably. Thus, αHBs are analogous to "molecular flasks" made in supramolecular, polymer, and materials chemistry. Using Förster resonance energy transfer as a readout, we demonstrate that specific αHBs can accept two different organic dyes, 1,6-diphenyl-1,3,5-hexatriene and Nile red, in close proximity. In addition, two anthracene molecules can be accommodated within an αHB to promote anthracene photodimerization. However, not all ternary complexes are productive, either in energy transfer or photodimerization, illustrating the control that can be exerted by judicious choice and design of the αHB.

Exchange, promiscuity, and orthogonality in de novo designed coiled-coil peptide assemblies

De novo protein design is delivering new peptide and protein structures at a rapid pace. Many of these synthetic polypeptides form well-defined and hyperthermal-stable structures. Generally, however, less is known about the dynamic properties of the de novo designed structures. Here, we explore one aspect of dynamics in a series of de novo coiled-coil peptide assemblies: namely, peptide exchange within and between different oligomers from dimers through to heptamers. First, we develop a fluorescence-based reporter assay for peptide exchange that is straightforward to implement, and, thus, would be useful to others examining similar systems. We apply this assay to explore both homotypic exchange within single species, and heterotypic exchange between coiled coils of different oligomeric states. For the former, we provide a detailed study for a dimeric coiled coil, CC-Di, finding a half-life for exchange of 4.2 ± 0.3 minutes at a peptide concentration of 200 μM. Interestingly, more broadly when assessing exchange across all of the oligomeric states, we find that some of the designs are faithful and only undergo homotypic strand exchange, whereas others are promiscuous and exchange to form unexpected hetero-oligomers. Finally, we develop two design strategies to improve the orthogonality of the different oligomers: (i) using alternate positioning of salt bridge interactions; and (ii) incorporating non-canonical repeats into the designed sequences. In so doing, we reconcile the promiscuity and deliver a set of faithful homo-oligomeric de novo coiled-coil peptides. Our findings have implications for the application of these and other coiled coils as modules in chemical and synthetic biology.

Seven critical challenges in synthetic one-carbon assimilation and their potential solutions

Synthetic C1 assimilation holds the promise of facilitating carbon capture while mitigating greenhouse gas emissions, yet practical implementation in microbial hosts remains relatively limited. Despite substantial progress in pathway design and prototyping, most efforts stay at the proof-of-concept stage, with frequent failures observed even under in vitro conditions. This review identifies seven major barriers constraining the deployment of synthetic C1 metabolism in microorganisms and proposes targeted strategies for overcoming these issues. A primary limitation is the low catalytic activity of carbon-fixing enzymes, particularly carboxylases, which restricts the overall pathway performance. In parallel, challenges in expressing multiple heterologous genes-especially those encoding metal-dependent or oxygen-sensitive enzymes-further hinder pathway functionality. At the systems level, synthetic C1 pathways often exhibit poor flux distribution, limited integration with the host metabolism, accumulation of toxic intermediates, and disruptions in redox and energy balance. These factors collectively reduce biomass formation and compromise product yields in biotechnological setups. Overcoming these interconnected challenges is essential for moving synthetic C1 assimilation beyond conceptual stages and enabling its application in scalable, efficient bioprocesses towards a circular bioeconomy.

Inventing Novel Protein Folds

The vastness of unexplored protein fold universe remains a significant question. Through systematic de novo design of proteins with novel αβ-folds, we demonstrated that nature has only explored a tiny portion of the possible folds. Numerous possible protein folds are still untouched by nature. This review outlines this study and discusses the prospects for design of functional proteins with novel folds.

Advancing sustainable biotechnology through protein engineering

The push for industrial sustainability benefits from the use of enzymes as a replacement for traditional chemistry. Biological catalysts, especially those that have been engineered for increased activity, stability, or novel function, and are often greener than alternative chemical approaches. This Review highlights the role of engineered enzymes (and identifies directions for further engineering efforts) in the application areas of greenhouse gas sequestration, fuel production, bioremediation, and degradation of plastic wastes.

Click, Compute, Create: A Review of Web-based Tools for Enzyme Engineering

Enzyme engineering, though pivotal across various biotechnological domains, is often plagued by its time-consuming and labor-intensive nature. This review aims to offer an overview of supportive in silico methodologies for this demanding endeavor. Starting from methods to predict protein structures, to classification of their activity and even the discovery of new enzymes we continue with describing tools used to increase thermostability and production yields of selected targets. Subsequently, we discuss computational methods to modulate both, the activity as well as selectivity of enzymes. Last, we present recent approaches based on cutting-edge machine learning methods to redesign enzymes. With exception of the last chapter, there is a strong focus on methods easily accessible via web-interfaces or simple Python-scripts, therefore readily useable for a diverse and broad community.

Exploring "dark-matter" protein folds using deep learning

De novo protein design explores uncharted sequence and structure space to generate novel proteins not sampled by evolution. A main challenge in de novo design involves crafting "designable" structural templates to guide the sequence searches toward adopting target structures. We present a convolutional variational autoencoder that learns patterns of protein structure, dubbed Genesis. We coupled Genesis with trRosetta to design sequences for a set of protein folds and found that Genesis is capable of reconstructing native-like distance and angle distributions for five native folds and three novel, the so-called "dark-matter" folds as a demonstration of generalizability. We used a high-throughput assay to characterize the stability of the designs through protease resistance, obtaining encouraging success rates for folded proteins. Genesis enables exploration of the protein fold space within minutes, unrestricted by protein topologies. Our approach addresses the backbone designability problem, showing that small neural networks can efficiently learn structural patterns in proteins. A record of this paper's transparent peer review process is included in the supplemental information.

PB-GPT: An innovative GPT-based model for protein backbone generation

With advanced computational methods, it is now feasible to modify or design proteins for specific functions, a process with significant implications for disease treatment and other medical applications. Protein structures and functions are intrinsically linked to their backbones, making the design of these backbones a pivotal aspect of protein engineering. In this study, we focus on the task of unconditionally generating protein backbones. By means of codebook quantization and compression dictionaries, we convert protein backbone structures into a distinctive coded language and propose a GPT-based protein backbone generation model, PB-GPT. To validate the generalization performance of the model, we trained and evaluated the model on both public datasets and small protein datasets. The results demonstrate that our model has the capability to unconditionally generate elaborate, highly realistic protein backbones with structural patterns resembling those of natural proteins, thus showcasing the significant potential of large language models in protein structure design.

De novo design of mini-protein binders broadly neutralizing Clostridioides difficile toxin B variants

Clostridioides difficile toxin B (TcdB) is the key virulence factor accounting for C. difficile infection-associated symptoms. Effectively neutralizing different TcdB variants with a universal solution poses a significant challenge. Here we present the de novo design and characterization of pan-specific mini-protein binders against major TcdB subtypes. Our design successfully binds to the first receptor binding interface (RBI-1) of the varied TcdB subtypes, exhibiting affinities ranging from 20 pM to 10 nM. The cryo-electron microscopy (cryo-EM) structures of the mini protein binder in complex with TcdB1 and TcdB4 are consistent with the computational design models. The engineered and evolved variants of the mini-protein binder and chondroitin sulfate proteoglycan 4 (CSPG4), another natural receptor that binds to the second RBI (RBI-2) of TcdB, better neutralize major TcdB variants both in cells and in vivo, as demonstrated by the colon-loop assay using female mice. Our findings provide valuable starting points for the development of therapeutics targeting C. difficile infections (CDI).

Revolutionizing Molecular Design for Innovative Therapeutic Applications through Artificial Intelligence

The field of computational protein engineering has been transformed by recent advancements in machine learning, artificial intelligence, and molecular modeling, enabling the design of proteins with unprecedented precision and functionality. Computational methods now play a crucial role in enhancing the stability, activity, and specificity of proteins for diverse applications in biotechnology and medicine. Techniques such as deep learning, reinforcement learning, and transfer learning have dramatically improved protein structure prediction, optimization of binding affinities, and enzyme design. These innovations have streamlined the process of protein engineering by allowing the rapid generation of targeted libraries, reducing experimental sampling, and enabling the rational design of proteins with tailored properties. Furthermore, the integration of computational approaches with high-throughput experimental techniques has facilitated the development of multifunctional proteins and novel therapeutics. However, challenges remain in bridging the gap between computational predictions and experimental validation and in addressing ethical concerns related to AI-driven protein design. This review provides a comprehensive overview of the current state and future directions of computational methods in protein engineering, emphasizing their transformative potential in creating next-generation biologics and advancing synthetic biology.

On synergy between ultrahigh throughput screening and machine learning in biocatalyst engineering

Protein design and directed evolution have separately contributed enormously to protein engineering. Without being mutually exclusive, the former relies on computation from first principles, while the latter is a combinatorial approach based on chance. Advances in ultrahigh throughput (uHT) screening, next generation sequencing and machine learning may create alternative routes to engineered proteins, where functional information linked to specific sequences is interpreted and extrapolated in silico. In particular, the miniaturisation of functional tests in water-in-oil emulsion droplets with picoliter volumes and their rapid generation and analysis (>1 kHz) allows screening of >107-membered libraries in a day. Subsequently, decoding the selected clones by short or long-read sequencing methods leads to large sequence-function datasets that may allow extrapolation from experimental directed evolution to further improved mutants beyond the observed hits. In this work, we explore experimental strategies for how to draw up 'fitness landscapes' in sequence space with uHT droplet microfluidics, review the current state of AI/ML in enzyme engineering and discuss how uHT datasets may be combined with AI/ML to make meaningful predictions and accelerate biocatalyst engineering.

Generative β-hairpin design using a residue-based physicochemical property landscape

De novo peptide design is a new frontier that has broad application potential in the biological and biomedical fields. Most existing models for de novo peptide design are largely based on sequence homology that can be restricted based on evolutionarily derived protein sequences and lack the physicochemical context essential in protein folding. Generative machine learning for de novo peptide design is a promising way to synthesize theoretical data that are based on, but unique from, the observable universe. In this study, we created and tested a custom peptide generative adversarial network intended to design peptide sequences that can fold into the β-hairpin secondary structure. This deep neural network model is designed to establish a preliminary foundation of the generative approach based on physicochemical and conformational properties of 20 canonical amino acids, for example, hydrophobicity and residue volume, using extant structure-specific sequence data from the PDB. The beta generative adversarial network model robustly distinguishes secondary structures of β hairpin from α helix and intrinsically disordered peptides with an accuracy of up to 96% and generates artificial β-hairpin peptide sequences with minimum sequence identities around 31% and 50% when compared against the current NCBI PDB and nonredundant databases, respectively. These results highlight the potential of generative models specifically anchored by physicochemical and conformational property features of amino acids to expand the sequence-to-structure landscape of proteins beyond evolutionary limits.

Design of intrinsically disordered protein variants with diverse structural properties

Intrinsically disordered proteins (IDPs) perform a broad range of functions in biology, suggesting that the ability to design IDPs could help expand the repertoire of proteins with novel functions. Computational design of IDPs with specific conformational properties has, however, been difficult because of their substantial dynamics and structural complexity. We describe a general algorithm for designing IDPs with specific structural properties. We demonstrate the power of the algorithm by generating variants of naturally occurring IDPs that differ in compaction, long-range contacts, and propensity to phase separate. We experimentally tested and validated our designs and analyzed the sequence features that determine conformations. We show how our results are captured by a machine learning model, enabling us to speed up the algorithm. Our work expands the toolbox for computational protein design and will facilitate the design of proteins whose functions exploit the many properties afforded by protein disorder.

From De Novo to Xeno: Advancing Macromolecule Design beyond Proteins

Protein synthesis methods have been adapted to incorporate an ever-growing level of non-natural components. Meanwhile, design of de novo protein structure and function has rapidly emerged as a viable capability. Yet, these two exciting trends have yet to intersect in a meaningful way. The ability to perform de novo design with non-proteinogenic components requires that synthesis and computation align on common targets and applications. This perspective examines the state of the art in these areas and identifies specific, consequential applications to advance the field toward generalized macromolecule design.

The art of designed coiled-coils for the regulation of mammalian cells

Synthetic biology aims to engineer complex biological systems using modular elements, with coiled-coil (CC) dimer-forming modules are emerging as highly useful building blocks in the regulation of protein assemblies and biological processes. Those small modules facilitate highly specific and orthogonal protein-protein interactions, offering versatility for the regulation of diverse biological functions. Additionally, their design rules enable precise control and tunability over these interactions, which are crucial for specific applications. Recent advancements showcase their potential for use in innovative therapeutic interventions and biomedical applications. In this review, we discuss the potential of CCs, exploring their diverse applications in mammalian cells, such as synthetic biological circuit design, transcriptional and allosteric regulation, cellular assemblies, chimeric antigen receptor (CAR) T cell regulation, and genome editing and their role in advancing the understanding and regulation of cellular processes.

Rationally seeded computational protein design of ɑ-helical barrels

Computational protein design is advancing rapidly. Here we describe efficient routes starting from validated parallel and antiparallel peptide assemblies to design two families of α-helical barrel proteins with central channels that bind small molecules. Computational designs are seeded by the sequences and structures of defined de novo oligomeric barrel-forming peptides, and adjacent helices are connected by loop building. For targets with antiparallel helices, short loops are sufficient. However, targets with parallel helices require longer connectors; namely, an outer layer of helix-turn-helix-turn-helix motifs that are packed onto the barrels. Throughout these computational pipelines, residues that define open states of the barrels are maintained. This minimizes sequence sampling, accelerating the design process. For each of six targets, just two to six synthetic genes are made for expression in Escherichia coli. On average, 70% of these genes express to give soluble monomeric proteins that are fully characterized, including high-resolution structures for most targets that match the design models with high accuracy.

Opportunities and challenges in design and optimization of protein function

The field of protein design has made remarkable progress over the past decade. Historically, the low reliability of purely structure-based design methods limited their application, but recent strategies that combine structure-based and sequence-based calculations, as well as machine learning tools, have dramatically improved protein engineering and design. In this Review, we discuss how these methods have enabled the design of increasingly complex structures and therapeutically relevant activities. Additionally, protein optimization methods have improved the stability and activity of complex eukaryotic proteins. Thanks to their increased reliability, computational design methods have been applied to improve therapeutics and enzymes for green chemistry and have generated vaccine antigens, antivirals and drug-delivery nano-vehicles. Moreover, the high success of design methods reflects an increased understanding of basic rules that govern the relationships among protein sequence, structure and function. However, de novo design is still limited mostly to α-helix bundles, restricting its potential to generate sophisticated enzymes and diverse protein and small-molecule binders. Designing complex protein structures is a challenging but necessary next step if we are to realize our objective of generating new-to-nature activities.

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/.

The State-of-the-Art Overview to Application of Deep Learning in Accurate Protein Design and Structure Prediction

In recent years, there has been a notable increase in the scientific community's interest in rational protein design. The prospect of designing an amino acid sequence that can reliably fold into a desired three-dimensional structure and exhibit the intended function is captivating. However, a major challenge in this endeavor lies in accurately predicting the resulting protein structure. The exponential growth of protein databases has fueled the advancement of the field, while newly developed algorithms have pushed the boundaries of what was previously achievable in structure prediction. In particular, using deep learning methods instead of brute force approaches has emerged as a faster and more accurate strategy. These deep-learning techniques leverage the vast amount of data available in protein databases to extract meaningful patterns and predict protein structures with improved precision. In this article, we explore the recent developments in the field of protein structure prediction. We delve into the newly developed methods that leverage deep learning approaches, highlighting their significance and potential for advancing our understanding of protein design.

A de novo designed coiled coil-based switch regulates the microtubule motor kinesin-1

Many enzymes are allosterically regulated via conformational change; however, our ability to manipulate these structural changes and control function is limited. Here we install a conformational switch for allosteric activation into the kinesin-1 microtubule motor in vitro and in cells. Kinesin-1 is a heterotetramer that accesses open active and closed autoinhibited states. The equilibrium between these states centers on a flexible elbow within a complex coiled-coil architecture. We target the elbow to engineer a closed state that can be opened with a de novo designed peptide. The alternative states are modeled computationally and confirmed by biophysical measurements and electron microscopy. In cells, peptide-driven activation increases kinesin transport, demonstrating a primary role for conformational switching in regulating motor activity. The designs are enabled by our understanding of ubiquitous coiled-coil structures, opening possibilities for controlling other protein activities.

Validation of de novo designed water-soluble and transmembrane β-barrels by in silico folding and melting

In silico validation of de novo designed proteins with deep learning (DL)-based structure prediction algorithms has become mainstream. However, formal evidence of the relationship between a high-quality predicted model and the chance of experimental success is lacking. We used experimentally characterized de novo water-soluble and transmembrane β-barrel designs to show that AlphaFold2 and ESMFold excel at different tasks. ESMFold can efficiently identify designs generated based on high-quality (designable) backbones. However, only AlphaFold2 can predict which sequences have the best chance of experimentally folding among similar designs. We show that ESMFold can generate high-quality structures from just a few predicted contacts and introduce a new approach based on incremental perturbation of the prediction ("in silico melting"), which can reveal differences in the presence of favorable contacts between designs. This study provides a new insight on DL-based structure prediction models explainability and on how they could be leveraged for the design of increasingly complex proteins; in particular membrane proteins which have historically lacked basic in silico validation tools.

Diversifying de novo TIM barrels by hallucination

De novo protein design expands the protein universe by creating new sequences to accomplish tailor-made enzymes in the future. A promising topology to implement diverse enzyme functions is the ubiquitous TIM-barrel fold. Since the initial de novo design of an idealized four-fold symmetric TIM barrel, the family of de novo TIM barrels is expanding rapidly. Despite this and in contrast to natural TIM barrels, these novel proteins lack cavities and structural elements essential for the incorporation of binding sites or enzymatic functions. In this work, we diversified a de novo TIM barrel by extending multiple βα-loops using constrained hallucination. Experimentally tested designs were found to be soluble upon expression in Escherichia coli and well-behaved. Biochemical characterization and crystal structures revealed successful extensions with defined α-helical structures. These diversified de novo TIM barrels provide a framework to explore a broad spectrum of functions based on the potential of natural TIM barrels.

Reshaping Phosphatase Substrate Preference for Controlled Biosynthesis Using a "Design-Build-Test-Learn" Framework

Biosynthesis is the application of enzymes in microbial cell factories and has emerged as a promising alternative to chemical synthesis. However, natural enzymes with limited catalytic performance often need to be engineered to meet specific needs through a time-consuming trial-and-error process. This study presents a quantum mechanics (QM)-incorporated design-build-test-learn (DBTL) framework to rationally design phosphatase BT4131, an enzyme with an ambiguous substrate spectrum involved in N-acetylglucosamine (GlcNAc) biosynthesis. First, mutant M1 (L129Q) is designed using force field-based methods, resulting in a 1.4-fold increase in substrate preference (kcat/Km) toward GlcNAc-6-phosphate (GlcNAc6P). QM calculations indicate that the shift in substrate preference is caused by a 13.59 kcal mol-1 reduction in activation energy. Furthermore, an iterative computer-aided design is conducted to stabilize the transition state. As a result, mutant M4 (I49Q/L129Q/G172L) with a 9.5-fold increase in kcat-GlcNAc6P/Km-GlcNAc6P and a 59% decrease in kcat-Glc6P/Km-Glc6P is highly desirable compared to the wild type in the GlcNAc-producing chassis. The GlcNAc titer increases to 217.3 g L-1 with a yield of 0.597 g (g glucose)-1 in a 50-L bioreactor, representing the highest reported level. Collectively, this DBTL framework provides an easy yet fascinating approach to the rational design of enzymes for industrially viable biocatalysts.

Autonomous assembly and disassembly of gliding molecular robots regulated by a DNA-based molecular controller

In recent years, there has been a growing interest in engineering dynamic and autonomous systems with robotic functionalities using biomolecules. Specifically, the ability of molecular motors to convert chemical energy to mechanical forces and the programmability of DNA are regarded as promising components for these systems. However, current systems rely on the manual addition of external stimuli, limiting the potential for autonomous molecular systems. Here, we show that DNA-based cascade reactions can act as a molecular controller that drives the autonomous assembly and disassembly of DNA-functionalized microtubules propelled by kinesins. The DNA controller is designed to produce two different DNA strands that program the interaction between the microtubules. The gliding microtubules integrated with the controller autonomously assemble to bundle-like structures and disassemble into discrete filaments without external stimuli, which is observable by fluorescence microscopy. We believe this approach to be a starting point toward more autonomous behavior of motor protein-based multicomponent systems with robotic functionalities.

Co(II) Substitution Enhances the Esterase Activity of a de Novo Designed Zn(II) Carbonic Anhydrase

Carbonic Anhydrases (CAs) have been a target for de novo protein designers due to the simplicity of the active site and rapid rate of the reaction. The first reported mimic contained a Zn(II) bound to three histidine imidazole nitrogens and an exogenous water molecule, hence closely mimicking the native enzymes' first coordination sphere. Co(II) has served as an alternative metal to interrogate CAs due to its d7 electronic configuration for more detailed solution characterization. We present here the Co(II) substituted [Co(II)(H2O/OH-)]N(TRIL2WL23H)3 n+ that behaves similarly to native Co(II) substituted human-CAs. Like the Zn(II) analogue, the cobalt-derivative at slightly basic pH is incapable of hydrolyzing p-nitrophenylacetate (pNPA); however, as the pH is increased a significant activity develops, which at pH values above 10 eventually yields a catalytic efficiency that exceeds that of the [Zn(II)(OH-)]N(TRIL2WL23H)3 + peptide complex. X-ray absorption analysis is consistent with an octahedral species at pH 7.5 that converts to a 5-coordinate species by pH 11. UV-vis spectroscopy can monitor this transition, giving a pKa for the conversion of 10.3. We assign this conversion to the formation of a 5-coordinate Co(II)(Nimid)3(OH)(H2O) species. The pH dependent kinetic analysis indicates the maximal rate (kcat), and thus the catalytic efficiency (kcat/Km), follow the same pH profile as the spectroscopic conversion to the pentacoordinate species. This correlation suggests that the chemically irreversible ester hydrolysis corresponds to the rate determining process.

Integrated Computational Pipeline for the High-Throughput Discovery of Cell Adhesion Peptides

Cell adhesion peptides (CAPs) often play a critical role in tissue engineering research. However, the discovery of novel CAPs for diverse applications remains a challenging and time-intensive process. This study presents an efficient computational pipeline integrating sequence embeddings, binding predictors, and molecular dynamics simulations to expedite the discovery of new CAPs. A Pro2vec model, trained on vast CAP data sets, was built to identify RGD-similar tripeptide candidates. These candidates were further evaluated for their binding affinity with integrin receptors using the Mutabind2 machine learning model. Additionally, molecular dynamics simulations were applied to model receptor-peptide interactions and calculate their binding free energies, providing a quantitative assessment of the binding strength for further screening. The resulting peptide demonstrated performance comparable to that of RGD in endothelial cell adhesion and spreading experimental assays, validating the efficacy of the integrated computational pipeline.

Temporal Resolution of Activity-Related Solvation Dynamics in the TIM Barrel Enzyme Murine Adenosine Deaminase

Murine adenosine deaminase (mADA) is a prototypic system for studying the thermal activation of active site chemistry within the TIM barrel family of enzyme reactions. Previous temperature-dependent hydrogen deuterium exchange studies under various conditions have identified interconnected thermal networks for heat transfer from opposing protein-solvent interfaces to active site residues in mADA. One of these interfaces contains a solvent exposed helix-loop-helix moiety that presents the hydrophobic face of its long α-helix to the backside of bound substrate. Herein we pursue the time and temperature dependence of solvation dynamics at the surface of mADA, for comparison to established kinetic parameters that represent active site chemistry. We first created a modified protein devoid of native tryptophans with close to native kinetic behavior. Single site-specific tryptophan mutants were back inserted into each of the four positions where native tryptophans reside. Measurements of nanosecond fluorescence relaxation lifetimes and Stokes shift decays, that reflect time dependent environmental reoroganization around the photo-excited state of Trp*, display minimal temperature dependences. These regions serve as controls for the behavior of a new single tryptophan inserted into a solvent exposed region near the helix-loop-helix moiety located behind the bound substrate, Lys54Trp. This installed Trp displays a significantly elevated value for Ea ( k Stokes shift ) ; further, when Phe61 within the long helix positioned behind bound substrate is replaced by a series of aliphatic hydrophobic side chains, the trends in Ea ( k Stokes shift ) mirror the earlier reported impact of the same series of function-altering hydrophobic side chains on the activation energy of catalysis, Ea ( k cat ) .The reported experimental findings implicate a solvent initiated and rapid (>ns) protein restructuring that contributes to the enthalpic activation barrier to catalysis in mADA.

Directing RNA-modifying machineries towards endogenous RNAs: opportunities and challenges

Over 170 chemical modifications can be naturally installed on RNA, all of which are catalyzed by dedicated machineries. These modifications can alter RNA sequence structure, stability, and translation as well as serving as quality control marks that record aspects of RNA processing. The diverse roles played by RNAs within cells has motivated endeavors to exogenously introduce RNA modifications at target sites for diverse purposes ranging from recording RNA:protein interactions to therapeutic applications. Here, we discuss these applications and the approaches that have been employed to engineer RNA-modifying machineries, and highlight persisting challenges and perspectives.

Rational evolution for altering the ligand preference of estrogen receptor alpha

Estrogen receptor α is commonly used in synthetic biology to control the activity of genome editing tools. The activating ligands, estrogens, however, interfere with various cellular processes, thereby limiting the applicability of this receptor. Altering its ligand preference to chemicals of choice solves this hurdle but requires adaptation of unspecified ligand-interacting residues. Here, we provide a solution by combining rational protein design with multi-site-directed mutagenesis and directed evolution of stably integrated variants in Saccharomyces cerevisiae. This method yielded an estrogen receptor variant, named TERRA, that lost its estrogen responsiveness and became activated by tamoxifen, an anti-estrogenic drug used for breast cancer treatment. This tamoxifen preference of TERRA was maintained in mammalian cells and mice, even when fused to Cre recombinase, expanding the mammalian synthetic biology toolbox. Not only is our platform transferable to engineer ligand preference of any steroid receptor, it can also profile drug-resistance landscapes for steroid receptor-targeted therapies.

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.

CRD: A de novo design algorithm for the prediction of cognate protein receptors for small molecule ligands

While predicting a ligand that binds to a protein is feasible with current methods, the opposite, i.e., the prediction of a receptor for a ligand remains challenging. We present an approach for predicting receptors of a given ligand that uses de novo design and structural bioinformatics. We have developed the algorithm CRD, comprising multiple modules combining fragment-based sub-site finding, a machine learning function to estimate the size of the site, a genetic algorithm that encodes knowledge on protein structures and a physics-based fitness scoring scheme. CRD includes a pseudo-receptor design component followed by a mapping component to identify proteins that might contain these sites. CRD recovers the sites and receptors of several natural ligands. It designs similar sites for similar ligands, yet to some extent can distinguish between closely related ligands. CRD correctly predicts receptor classes for several drugs and might become a valuable tool for drug discovery.

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.

Is Novelty Predictable?

Machine learning-based design has gained traction in the sciences, most notably in the design of small molecules, materials, and proteins, with societal applications ranging from drug development and plastic degradation to carbon sequestration. When designing objects to achieve novel property values with machine learning, one faces a fundamental challenge: how to push past the frontier of current knowledge, distilled from the training data into the model, in a manner that rationally controls the risk of failure. If one trusts learned models too much in extrapolation, one is likely to design rubbish. In contrast, if one does not extrapolate, one cannot find novelty. Herein, we ponder how one might strike a useful balance between these two extremes. We focus in particular on designing proteins with novel property values, although much of our discussion is relevant to machine learning-based design more broadly.

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.

DNA-Mediated Peptide Assembly into Protein Mimics

The design of new protein structures is challenging due to their vast sequence space and the complexity of protein folding. Here, we report a new modular DNA-templated strategy to construct protein mimics. We achieve the spatial control of multiple peptide units by conjugation with DNA and hybridization to a branched DNA trimer template followed by covalent stapling of the preorganized peptides into a single unit. A library of protein mimics with different lengths, sequences, and heptad registers has been efficiently constructed. DNA-templated protein mimics show an α-helix or coiled-coil motif formation even when they are constructed from weakly interacting peptide units. Their attached DNA handles can be used to exert dynamic control over the protein mimics' secondary and tertiary structures. This modular strategy will facilitate the development of DNA-encoded protein libraries for the rapid discovery of new therapeutics, enzymes, and antibody mimics.

Engineering Anticytokine Antibodies for Immune Modulation

The delicate balance of immune homeostasis is regulated by the interactions between cytokines and their cognate cell surface signaling receptors. There is intensive interest in harnessing cytokines as drugs for diseases such as cancer and autoimmune disorders. However, the multifarious and often contradictory activities of cytokines, coupled with their short serum half-lives, limit clinical performance and result in dangerous toxicities. There is thus growing emphasis on manipulating natural cytokines to enhance their selectivity, safety, and durability through various strategies. One strategy that has gained traction in recent years is the development of anticytokine Abs that not only extend the circulation half-life of cytokines but also specifically bias their immune activities through multilayered molecular mechanisms. Although Abs are notorious for their antagonistic activities, this review focuses on anticytokine Abs that selectively agonize the activity of the target protein. This approach has potential to help realize the clinical promise of cytokine-based therapies.

PLM-GAN: A Large-Scale Protein Loop Modeling Using pix2pix GAN

Revealing the tertiary structure of proteins holds huge significance as it unveils their vital properties and functions. These intricate three-dimensional configurations comprise diverse interactions including ionic, hydrophobic, and disulfide forces. In certain instances, these structures exhibit missing regions, necessitating the reconstruction of specific segments, thereby resulting in challenges in protein design, which encompasses loop modeling, circular permutation, and interface prediction. To address this problem, we present two pioneering models: pix2pix generative adversarial network (GAN) and PLM-GAN. The pix2pix GAN model is adept at generating and inpainting distance matrices of protein structures, whereas the PLM-GAN model incorporates residual blocks into the U-Net network of the GAN, building upon the foundation of the pix2pix GAN model. To bolster the models' performance, we introduce a novel loss function named the "missing to real regions loss" (LMTR) within the GAN framework. Additionally, we introduce a distinctive approach of pairing two different distance matrices: one representing the native protein structure and the other representing the same structure with a missing region that undergoes changes in each successive epoch. Moreover, we extend the reconstruction of missing regions, encompassing up to 30 amino acids and increase the protein length by 128 amino acids. The evaluation of our pix2pix GAN and PLM-GAN models on a random selection of natural proteins (4ZCB, 3FJB, and 2REZ) demonstrated promising experimental results. Our models constitute significant contributions to addressing intricate challenges in protein structure design. These contributions hold immense potential to propel advancements in protein-protein interactions, drug design, and further innovations in protein engineering. Data, code, trained models, examples, and measurements are available on https://github.com/mena01/PLM-GAN-A-Large-Scale-Protein-Loop-Modeling-Using-pix2pix-GAN_.

Accelerating the Discovery and Design of Antimicrobial Peptides with Artificial Intelligence

Peptides modulate many processes of human physiology targeting ion channels, protein receptors, or enzymes. They represent valuable starting points for the development of new biologics against communicable and non-communicable disorders. However, turning native peptide ligands into druggable materials requires high selectivity and efficacy, predictable metabolism, and good safety profiles. Machine learning models have gradually emerged as cost-effective and time-saving solutions to predict and generate new proteins with optimal properties. In this chapter, we will discuss the evolution and applications of predictive modeling and generative modeling to discover and design safe and effective antimicrobial peptides. We will also present their current limitations and suggest future research directions, applicable to peptide drug design campaigns.

Next generation of multispecific antibody engineering

Multispecific antibodies recognize two or more epitopes located on the same or distinct targets. This added capability through protein design allows these man-made molecules to address unmet medical needs that are no longer possible with single targeting such as with monoclonal antibodies or cytokines alone. However, the approach to the development of these multispecific molecules has been met with numerous road bumps, which suggests that a new workflow for multispecific molecules is required. The investigation of the molecular basis that mediates the successful assembly of the building blocks into non-native quaternary structures will lead to the writing of a playbook for multispecifics. This is a must do if we are to design workflows that we can control and in turn predict success. Here, we reflect on the current state-of-the-art of therapeutic biologics and look at the building blocks, in terms of proteins, and tools that can be used to build the foundations of such a next-generation workflow.

A supramolecular system mimicking the infection process of an enveloped virus through membrane fusion

Membrane fusion is an essential step for the entry of enveloped viruses, such as human immunodeficiency virus and influenza virus, into the host cell, often triggered by the binding of membrane proteins on the viral envelope to host cell membrane. Recently, external stimuli was shown to trigger membrane fusion in an artificial system. Direct observation of artificial membrane fusion using a giant unilamellar vesicle (GUV), which is similar in size to a cell, is useful as a biological model system. However, there are no model systems for studying membrane fusion of enveloped viruses with host cells. Here, we report a supramolecular model system for viral entry into a GUV or cell through membrane fusion. The system was constructed by complexing a cationic lipid bilayer on an anionic artificial viral capsid, self-assembled from viral β-annulus peptides. We demonstrate that the cationic enveloped artificial viral capsid electrostatically interacts with the anionic GUV or cell, and the capsid enters the GUV or cell through membrane fusion. The model system established in this study will be important for analyzing membrane fusion during infection of a natural virus.

Mutexa: A Computational Ecosystem for Intelligent Protein Engineering

Protein engineering holds immense promise in shaping the future of biomedicine and biotechnology. This Review focuses on our ongoing development of Mutexa, a computational ecosystem designed to enable "intelligent protein engineering". In this vision, researchers will seamlessly acquire sequences of protein variants with desired functions as biocatalysts, therapeutic peptides, and diagnostic proteins through a finely-tuned computational machine, akin to Amazon Alexa's role as a versatile virtual assistant. The technical foundation of Mutexa has been established through the development of a database that combines and relates enzyme structures and their respective functions (e.g., IntEnzyDB), workflow software packages that enable high-throughput protein modeling (e.g., EnzyHTP and LassoHTP), and scoring functions that map the sequence-structure-function relationship of proteins (e.g., EnzyKR and DeepLasso). We will showcase the applications of these tools in benchmarking the convergence conditions of enzyme functional descriptors across mutants, investigating protein electrostatics and cavity distributions in SAM-dependent methyltransferases, and understanding the role of nonelectrostatic dynamic effects in enzyme catalysis. Finally, we will conclude by addressing the future steps and fundamental challenges in our endeavor to develop new Mutexa applications that assist the identification of beneficial mutants in protein engineering.