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.

Broad-Spectrum Engineered Multivalent Nanobodies Against SARS-CoV-1/2.

SARS-CoV-2 Omicron sublineages escape most preclinical/clinical neutralizing antibodies in development, suggesting that previously employed antibody screening strategies are not well suited to counteract the rapid mutation of SARS-CoV-2. Therefore, there is an urgent need to screen better broad-spectrum neutralizing antibody. In this study, a comprehensive approach to design broad-spectrum inhibitors against both SARS-CoV-1 and SARS-CoV-2 by leveraging the structural diversity of nanobodies is proposed. This includes the de novo design of a fully human nanobody library and the camel immunization-based nanobody library, both targeting conserved epitopes, as well as the development of multivalent nanobodies that bind nonoverlapping epitopes. The results show that trivale B11-E8-F3, three nanobodies joined tandemly in trivalent form, have the broadest spectrum and efficient neutralization activity, which spans from SARS-CoV-1 to SARS-CoV-2 variants. It is also demonstrated that B11-E8-F3 has a very prominent preventive and some therapeutic effect in animal models of three authentic viruses. Therefore, B11-E8-F3 has an outstanding advantage in preventing SARS-CoV-1/SARS-CoV-2 infections, especially in immunocompromised populations or elderly people with high-risk comorbidities.

ProT-Diff: A Modularized and Efficient Strategy for De Novo Generation of Antimicrobial Peptide Sequences by Integrating Protein Language and Diffusion Models.

Antimicrobial peptides (AMPs) are a promising solution for treating antibiotic-resistant pathogens. However, efficient generation of diverse AMPs without prior knowledge of peptide structures or sequence alignments remains a challenge. Here, ProT-Diff is introduced, a modularized deep generative approach that combines a pretrained protein language model with a diffusion model for the de novo generation of AMPs sequences. ProT-Diff generates thousands of AMPs with diverse lengths and structures within a few hours. After silico physicochemical screening, 45 peptides are selected for experimental validation. Forty-four peptides showed antimicrobial activity against both gram-positive or gram-negative bacteria. Among broad-spectrum peptides, AMP_2 exhibited potent antimicrobial activity, low hemolysis, and minimal cytotoxicity. An in vivo assessment demonstrated its effectiveness against a drug-resistant E. coli strain in acute peritonitis. This study not only introduces a viable and user-friendly strategy for de novo generation of antimicrobial peptides, but also provides potential antimicrobial drug candidates with excellent activity. It is believed that this study will facilitate the development of other peptide-based drug candidates in the future, as well as proteins with tailored characteristics.

Peptide Bundlemer Networks or Lattices: Controlling Cross-Linking and Self-Assembly Using Protein-like Display of Chemistry.

Coiled-coil 'bundlemer' peptides were selectively modified with allyloxycarbonyl (alloc)-protected lysine, a non-natural amino acid containing an alkene on its side chain. The specific display of this alkene from the coiled-coil surface with protein-like specificity enabled this residue to be used as a covalent linkage for creating peptide networks with controllable properties or as a physical linkage for the self-assembly of bundlemers into unexpected, intricate lattices driven by the hydrophobic nature of the side chain. For network formation, peptides were modified with both alloc-protected lysine and cysteine amino acids for solution assembly into solvent-swollen films and subsequent covalent cross-linking via thiol-ene photo click reactions. The degree of network cross-linking, as determined by rheometry, was finely tuned by varying the specific spatial display of reactive groups on the bundlemer building block particles, transitioning between intrabundle and interbundle cross-linking. The designed display of alloc groups from the center of the bundlemer building block also prompted particle self-assembly into an unexpected intricate lattice with a porous morphology. The lattices were studied in a variety of solution conditions using transmission electron microscopy, cryotransmission electron microscopy, and small-angle X-ray scattering. The approximate particle arrangement in the lattice was determined by using coarse-grained modeling and machine learning optimization techniques along with experimental methods. The proposed truss-like face-centered cubic packing of the alloc-functionalized bundlemers agrees well with the experimental results.

Revving up a Designed Copper Nitrite Reductase Using Non-Coded Active Site Ligands.

Herein, we report a three stranded coiled-coil (3SCC) de novo protein containing a type II copper center (CuT2) composed of 6-membered ring N-heterocycles. This design yields the most active homogenous copper nitrite reductase (CuNiR) mimic in water. We achieved this result by controlling three factors. First, previous studies with Nδ and Nε -Methyl Histidine had indicated that a ligand providing pyridine-like electronic character to the copper site was superior to the more donating Nδ for nitrite reduction. By substitution of the parent histidine with the non-coded amino acids pyridyl alanine (3'-Pyridine [3'Py] vs 4'-Pyridine [4'Py]), an authentic pyridine donor was employed without the complications of the coupling of both electronic and tautomeric effects of histidine or methylated histidine. Second, by changing the position of the nitrogen atom within the active site (4'-Pyridine vs. 3'Pyridine) a doubling of the enzyme's catalytic efficiency resulted. This effect was driven exclusivity by substrate binding to the copper site. Third, we replaced the leucine layer adjacent to the active site with an alanine, and the disparity between the 3'Py and 4'Py became more apparent. The decreased steric bulk minimally impacted the 3'Py derivative; however, the 4'Py K m decreased by an order of magnitude (600 mM to 50 mM), resulting in a 40-fold enhancement in the k cat/K m compared to the analogues histidine site and a 1500-fold improvement compared with the initially reported CuNiR catalyst of this family, TRIW-H. When combined with XANES/EXAFS data, the relaxing of the Cu(I) site to a more 2-coordinate Cu(I) like structure in the resting state increases the overall catalytic efficiency of nitrite reduction via the lowering of K m. This study illustrates how by combining advanced spectroscopic methods, detailed kinetic analysis, and a broad toolbox of amino acid side chain functionality, one can rationally design systems that optimize biomimetic catalysis.

Chemical space exploration with Molpher: Generating and assessing a glucocorticoid receptor ligand library.

Computational exploration of chemical space is crucial in modern cheminformatics research for accelerating the discovery of new biologically active compounds. In this study, we present a detailed analysis of the chemical library of potential glucocorticoid receptor (GR) ligands generated by the molecular generator, Molpher. To generate the targeted GR library and construct the classification models, structures from the ChEMBL database as well as from the internal IMG library, which was experimentally screened for biological activity in the primary luciferase reporter cell assay, were utilized. The composition of the targeted GR ligand library was compared with a reference library that randomly samples chemical space. A random forest model was used to determine the biological activity of ligands, incorporating its applicability domain using conformal prediction. It was demonstrated that the GR library is significantly enriched with GR ligands compared to the random library. Furthermore, a prospective analysis demonstrated that Molpher successfully designed compounds, which were subsequently experimentally confirmed to be active on the GR. A collection of 34 potential new GR ligands was also identified. Moreover, an important contribution of this study is the establishment of a comprehensive workflow for evaluating computationally generated ligands, particularly those with potential activity against targets that are challenging to dock.

De novo design of mini-binder proteins against IL-2 receptor ß chain.

IL-2 regulates the immune response by interacting with different IL-2 receptor (IL-2R) subunits. High dose of IL-2 binds to IL-2Rßγc heterodimer, which induce various side effects while activating immune function. Disrupting IL-2 and IL-2R interactions can block IL-2 mediated immune response. Here, we used a computational approach to de novo design mini-binder proteins against IL-2R ß chain (IL-2Rß) to block IL-2 signaling. The hydrophobic region where IL-2 binds to IL-2Rß was selected and the promising binding mode was broadly explored. Three mini-binders with amino acid numbers ranging from 55 to 65 were obtained and binder 1 showed the best effects in inhibiting CTLL-2 cells proliferation and STAT5 phosphorylation. Molecular dynamics simulation showed that the binding of binder 1 to IL-2Rß was stable; the free energy of binder1/IL-2Rß complex was lower, indicating that the affinity of binder 1 to IL-2Rß was higher than that of IL-2. Free energy decomposition suggested that the ARG35 and ARG131 of IL-2Rß might be the key to improve the affinity of binder. Our efforts provided new insights in developing of IL-2R blocker, offering a potential strategy for ameliorating the side effects of IL-2 treatment.

Structure-based computational design of antibody mimetics: challenges and perspectives.

The design of antibody mimetics holds great promise for revolutionizing therapeutic interventions by offering alternatives to conventional antibody therapies. Structure-based computational approaches have emerged as indispensable tools in the rational design of those molecules, enabling the precise manipulation of their structural and functional properties. This review covers the main classes of designed antigen-binding motifs, as well as alternative strategies to develop tailored ones. We discuss the intricacies of different computational protein-protein interaction design strategies, showcased by selected successful cases in the literature. Subsequently, we explore the latest advancements in the computational techniques including the integration of machine and deep learning methodologies into the design framework, which has led to an augmented design pipeline. Finally, we verse onto the current challenges that stand in the way between high-throughput computer design of antibody mimetics and experimental realization, offering a forward-looking perspective into the field and the promises it holds to biotechnology.

Glutamine-derived peptides: Current progress and future directions.

Glutamine, the most abundant amino acid in the body, plays a critical role in preserving immune function, nitrogen balance, intestinal integrity, and resistance to infection. However, its limited solubility and instability present challenges for its use a functional nutrient. Consequently, there is a preference for utilizing glutamine-derived peptides as an alternative to achieve enhanced functionality. This article aims to review the applications of glutamine monomers in clinical, sports, and enteral nutrition. It compares the functional effectiveness of monomers and glutamine-derived peptides and provides a comprehensive assessment of glutamine-derived peptides in terms of their classification, preparation, mechanism of absorption, and biological activity. Furthermore, this study explores the potential integration of artificial intelligence (AI)-based peptidomics and synthetic biology in the de novo design and large-scale production of these peptides. The findings reveal that glutamine-derived peptides possess significant structure-related bioactivities, with the smaller molecular weight fraction serving as the primary active ingredient. These peptides possess the ability to promote intestinal homeostasis, exert hypotensive and hypoglycemic effects, and display antioxidant properties. However, our understanding of the structure-function relationships of glutamine-derived peptides remains largely exploratory at current stage. The combination of AI based peptidomics and synthetic biology presents an opportunity to explore the untapped resources of glutamine-derived peptides as functional food ingredients. Additionally, the utilization and bioavailability of these peptides can be enhanced through the use of delivery systems in vivo. This review serves as a valuable reference for future investigations of and developments in the discovery, functional validation, and biomanufacturing of glutamine-derived peptides in food science.

Validation of de novo designed water-soluble and transmembrane ß-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 ß-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.

Peptides and metal ions: A successful marriage for developing artificial metalloproteins.

The mutual relationship between peptides and metal ions enables metalloproteins to have crucial roles in biological systems, including structural, sensing, electron transport, and catalytic functions. The effort to reproduce or/and enhance these roles, or even to create unprecedented functions, is the focus of protein design, the first step toward the comprehension of the complex machinery of nature. Nowadays, protein design allows the building of sophisticated scaffolds, with novel functions and exceptional stability. Recent progress in metalloprotein design has led to the building of peptides/proteins capable of orchestrating the desired functions of different metal cofactors. The structural diversity of peptides allows proper selection of first- and second-shell ligands, as well as long-range electrostatic and hydrophobic interactions, which represent precious tools for tuning metal properties. The scope of this review is to discuss the construction of metal sites in de novo designed and miniaturized scaffolds. Selected examples of mono-, di-, and multi-nuclear binding sites, from the last 20 years will be described in an effort to highlight key artificial models of catalytic or electron-transfer metalloproteins. The authors' goal is to make readers feel like guests at the marriage between peptides and metal ions while offering sources of inspiration for future architects of innovative, artificial metalloproteins.

Structure-Based De Novo Design for the Discovery of Miniprotein Inhibitors Targeting Oncogenic Mutant BRAF.

Being a component of the Ras/Raf/MEK/ERK signaling pathway crucial for cellular responses, the VRAF murine sarcoma viral oncogene homologue B1 (BRAF) kinase has emerged as a promising target for anticancer drug discovery due to oncogenic mutations that lead to pathway hyperactivation. Despite the discovery of several small-molecule BRAF kinase inhibitors targeting oncogenic mutants, their clinical utility has been limited by challenges such as off-target effects and suboptimal pharmacological properties. This study focuses on identifying miniprotein inhibitors for the oncogenic V600E mutant BRAF, leveraging their potential as versatile drug candidates. Using a structure-based de novo design approach based on binding affinity to V600E mutant BRAF and hydration energy, 39 candidate miniprotein inhibitors comprising three helices and 69 amino acids were generated from the substructure of the endogenous ligand protein (14-3-3). Through in vitro binding and kinase inhibition assays, two miniproteins (63 and 76) were discovered as novel inhibitors of V600E mutant BRAF with low-micromolar activity, with miniprotein 76 demonstrating a specific impediment to MEK1 phosphorylation in mammalian cells. These findings highlight miniprotein 76 as a potential lead compound for developing new cancer therapeutics, and the structural features contributing to its biochemical potency against V600E mutant BRAF are discussed in detail.

Accelerated Engineering of ELP-Based Materials through Hybrid Biomimetic-De Novo Predictive Molecular Design.

Efforts to engineer high-performance protein-based materials inspired by nature have mostly focused on altering naturally occurring sequences to confer the desired functionalities, whereas de novo design lags significantly behind and calls for unconventional innovative approaches. Here, using partially disordered elastin-like polypeptides (ELPs) as initial building blocks this work shows that de novo engineering of protein materials can be accelerated through hybrid biomimetic design, which this work achieves by integrating computational modeling, deep neural network, and recombinant DNA technology. This generalizable approach involves incorporating a series of de novo-designed sequences with α-helical conformation and genetically encoding them into biologically inspired intrinsically disordered repeating motifs. The new ELP variants maintain structural conformation and showed tunable supramolecular self-assembly out of thermal equilibrium with phase behavior in vitro. This work illustrates the effective translation of the predicted molecular designs in structural and functional materials. The proposed methodology can be applied to a broad range of partially disordered biomacromolecules and potentially pave the way toward the discovery of novel structural proteins.

Quantum-assisted fragment-based automated structure generator (QFASG) for small molecule design: an in vitro study.

Introduction: The significance of automated drug design using virtual generative models has steadily grown in recent years. While deep learning-driven solutions have received growing attention, only a few modern AI-assisted generative chemistry platforms have demonstrated the ability to produce valuable structures. At the same time, virtual fragment-based drug design, which was previously less popular due to the high computational costs, has become more attractive with the development of new chemoinformatic techniques and powerful computing technologies. Methods: We developed Quantum-assisted Fragment-based Automated Structure Generator (QFASG), a fully automated algorithm designed to construct ligands for a target protein using a library of molecular fragments. QFASG was applied to generating new structures of CAMKK2 and ATM inhibitors. Results: New low-micromolar inhibitors of CAMKK2 and ATM were designed using the algorithm. Discussion: These findings highlight the algorithm's potential in designing primary hits for further optimization and showcase the capabilities of QFASG as an effective tool in this field.

Comparison of the efficiency of the Sec and Tat secretory pathways in the secretion of recombinant neurturin protein using de novo designed signal peptides.

Since cytoplasmic expression of heterologous proteins with disulfide bonds leads to the formation of inclusion bodies in E. coli, periplasmic production is preferable. The N-terminal signal peptide attached to the secreted protein determines the type of secretory pathway through which the target protein is secreted; Sec, Tat, or SRP. The aim of this study was to design and compare two novel signal peptides for the secretion of recombinant neurturin (as a model) via the Sec and Tat pathways. For this purpose, we aligned the natural signal peptides from E. coli and Bacillus subtilis to identify the conserved amino acids and those with the highest repetition. The SignalP4.1 and TatP1.0 software were used to determine the secretion efficiency of the new signal peptides. The efficiency of new signal peptides was then evaluated and compared experimentally with two naturally used signal peptides. Quantitative analysis of Western blot bands showed that approximately 80% of the expressed neurturin was secreted into the periplasmic space by new signal peptides. Circular dichroism spectroscopy also confirmed the correct secondary structure of the secreted neurturin. In conclusion, these novel signal peptides can be used to secrete any other recombinant proteins to the periplasmic space of E. coli efficiently.

Overcoming Endosomal Escape Barriers in Gene Drug Delivery Using De Novo Designed pH-Responsive Peptides.

A major challenge in using nanocarriers for intracellular drug delivery is their restricted capacity to escape from endosomes into the cytosol. Here, we significantly enhance the drug delivery efficiency by accurately predicting and regulating the transition pH (pH0) of peptides to modulate their endosomal escape capability. Moreover, by inverting the chirality of the peptide carriers, we could further enhance their ability to deliver nucleic acid drugs as well as antitumor drugs. The resulting peptide carriers exhibit versatility in transfecting various cell types with a high efficiency of up to 90% by using siRNA, pDNA, and mRNA. In vivo antitumor experiments demonstrate a tumor growth inhibition of 83.4% using the peptide. This research offers a potent method for the rapid development of peptide vectors with exceptional transfection efficiencies for diverse pathophysiological indications.

De novo antioxidant peptide design via machine learning and DFT studies.

Antioxidant peptides (AOPs) are highly valued in food and pharmaceutical industries due to their significant role in human function. This study introduces a novel approach to identifying robust AOPs using a deep generative model based on sequence representation. Through filtration with a deep-learning classification model and subsequent clustering via the Butina cluster algorithm, twelve peptides (GP1-GP12) with potential antioxidant capacity were predicted. Density functional theory (DFT) calculations guided the selection of six peptides for synthesis and biological experiments. Molecular orbital representations revealed that the HOMO for these peptides is primarily localized on the indole segment, underscoring its pivotal role in antioxidant activity. All six synthesized peptides exhibited antioxidant activity in the DPPH assay, while the hydroxyl radical test showed suboptimal results. A hemolysis assay confirmed the non-hemolytic nature of the generated peptides. Additionally, an in silico investigation explored the potential inhibitory interaction between the peptides and the Keap1 protein. Analysis revealed that ligands GP3, GP4, and GP12 induced significant structural changes in proteins, affecting their stability and flexibility. These findings highlight the capability of machine learning approaches in generating novel antioxidant peptides.

Machine Learning Accelerates De Novo Design of Antimicrobial Peptides.

Efficient and precise design of antimicrobial peptides (AMPs) is of great importance in the field of AMP development. Computing provides opportunities for peptide de novo design. In the present investigation, a new machine learning-based AMP prediction model, AP_Sin, was trained using 1160 AMP sequences and 1160 non-AMP sequences. The results showed that AP_Sin correctly classified 94.61% of AMPs on a comprehensive dataset, outperforming the mainstream and open-source models (Antimicrobial Peptide Scanner vr.2, iAMPpred and AMPlify) and being effective in identifying AMPs. In addition, a peptide sequence generator, AP_Gen, was devised based on the concept of recombining dominant amino acids and dipeptide compositions. After inputting the parameters of the 71 tridecapeptides from antimicrobial peptides database (APD3) into AP_Gen, a tridecapeptide bank consisting of de novo designed 17,496 tridecapeptide sequences were randomly generated, from which 2675 candidate AMP sequences were identified by AP_Sin. Chemical synthesis was performed on 180 randomly selected candidate AMP sequences, of which 18 showed high antimicrobial activities against a wide range of the tested pathogenic microorganisms, and 16 of which had a minimal inhibitory concentration of less than 10 µg/mL against at least one of the tested pathogenic microorganisms. The method established in this research accelerates the discovery of valuable candidate AMPs and provides a novel approach for de novo design of antimicrobial peptides.

Carving out a Glycoside Hydrolase Active Site for Incorporation into a New Protein Scaffold Using Deep Network Hallucination.

Enzymes are indispensable biocatalysts for numerous industrial applications, yet stability, selectivity, and restricted substrate recognition present limitations for their use. Despite the importance of enzyme engineering in overcoming these limitations, success is often challenged by the intricate architecture of enzymes derived from natural sources. Recent advances in computational methods have enabled the de novo design of simplified scaffolds with specific functional sites. Such scaffolds may be advantageous as platforms for enzyme engineering. Here, we present a strategy for the de novo design of a simplified scaffold of an endo-α-N-acetylgalactosaminidase active site, a glycoside hydrolase from the GH101 enzyme family. Using a combination of trRosetta hallucination, iterative cycles of deep-learning-based structure prediction, and ProteinMPNN sequence design, we designed proteins with 290 amino acids incorporating the active site while reducing the molecular weight by over 100 kDa compared to the initial endo-α-N-acetylgalactosaminidase. Of 11 tested designs, six were expressed as soluble monomers, displaying similar or increased thermostabilities compared to the natural enzyme. Despite lacking detectable enzymatic activity, the experimentally determined crystal structures of a representative design closely matched the design with a root-mean-square deviation of 1.0 Å, with most catalytically important side chains within 2.0 Å. The results highlight the potential of scaffold hallucination in designing proteins that may serve as a foundation for subsequent enzyme engineering.

De Novo Generation and Identification of Novel Compounds with Drug Efficacy Based on Machine Learning.

One of the main challenges in small molecule drug discovery is finding novel chemical compounds with desirable activity. Traditional drug development typically begins with target selection, but the correlation between targets and disease remains to be further investigated, and drugs designed based on targets may not always have the desired drug efficacy. The emergence of machine learning provides a powerful tool to overcome the challenge. Herein, a machine learning-based strategy is developed for de novo generation of novel compounds with drug efficacy termed DTLS (Deep Transfer Learning-based Strategy) by using dataset of disease-direct-related activity as input. DTLS is applied in two kinds of disease: colorectal cancer (CRC) and Alzheimer's disease (AD). In each case, novel compound is discovered and identified in in vitro and in vivo disease models. Their mechanism of actionis further explored. The experimental results reveal that DTLS can not only realize the generation and identification of novel compounds with drug efficacy but also has the advantage of identifying compounds by focusing on protein targets to facilitate the mechanism study. This work highlights the significant impact of machine learning on the design of novel compounds with drug efficacy, which provides a powerful new approach to drug discovery.