Helical structure motifs made searchable for functional peptide design

AlphaMut: A Deep Reinforcement Learning Model to Suggest Helix-Disrupting Mutations

Helices are important secondary structural motifs within proteins and are pivotal in numerous physiological processes. While amino acids (AA) such as alanine and leucine are known to promote helix formation, proline and glycine disfavor it. Helical structure formation, however, also depends on its environment, and hence, prior prediction of a mutational effect on a helical structure is difficult. Here, we employ a reinforcement learning algorithm to develop a predictive model for helix-disrupting mutations. We start with a model to disrupt helices independent of their protein environment. Our results show that only a few mutations lead to a drastic disruption of the target helix. We further extend our approach to helices in proteins and validate the results using rigorous free energy calculations. Our strategy identifies amino acids crucial for maintaining structural integrity and predicts key mutations that could alter protein structure. Through our work, we present a new use case for reinforcement learning in protein structure disruption.

Accelerating Antimicrobial Peptide Discovery for WHO Priority Pathogens through Predictive and Interpretable Machine Learning Models

The escalating menace of multidrug-resistant (MDR) pathogens necessitates a paradigm shift from conventional antibiotics to innovative alternatives. Antimicrobial peptides (AMPs) emerge as a compelling contender in this arena. Employing in silico methodologies, we can usher in a new era of AMP discovery, streamlining the identification process from vast candidate sequences, thereby optimizing laboratory screening expenditures. Here, we unveil cutting-edge machine learning (ML) models that are both predictive and interpretable, tailored for the identification of potent AMPs targeting World Health Organization's (WHO) high-priority pathogens. Furthermore, we have developed ML models that consider the hemolysis of human erythrocytes, emphasizing their therapeutic potential. Anchored in the nuanced physical-chemical attributes gleaned from the three-dimensional (3D) helical conformations of AMPs, our optimized models have demonstrated commendable performance-boasting an accuracy exceeding 75% when evaluated against both low-sequence-identified peptides and recently unveiled AMPs. As a testament to their efficacy, we deployed these models to prioritize peptide sequences stemming from PEM-2 and subsequently probed the bioactivity of our algorithm-predicted peptides vis-à-vis WHO's priority pathogens. Intriguingly, several of these new AMPs outperformed the native PEM-2 in their antimicrobial prowess, thereby underscoring the robustness of our modeling approach. To elucidate ML model outcomes, we probe via Shapley Additive exPlanations (SHAP) values, uncovering intricate mechanisms guiding diverse actions against bacteria. Our state-of-the-art predictive models expedite the design of new AMPs, offering a robust countermeasure to antibiotic resistance. Our prediction tool is available to the public at https://ai-meta.chem.ncu.edu.tw/amp-meta.

Uncovering the anti-biofilm activity of Ilicicolin B against Staphylococcus aureus

The formation of bacterial biofilms reduces the entry of antibiotics into bacteria and helps bacteria tolerate otherwise lethal concentrations of antimicrobials, leading to antibiotic resistance. Therefore, clearing bacterial biofilm is an effective strategy to tackle drug resistance. Currently, there are no approved antibiotics for inhibiting bacterial biofilm formation. We found that Ilicicolin B had excellent antibacterial activity against MRSA without obvious hemolytic activity. More importantly, Ilicicolin B effectively inhibited the biofilm formation in a concentration-dependent manner by crystal violet colorimetric assay and fluorescence microscopy analysis. Exposure of Staphylococcus aureus to Ilicicolin B for 24 h reduced the protein and polysaccharide components in EPS, suggesting that Ilicicolin B disintegrated the biofilms by dissociating the EPS in a matrix. In addition, Ilicicolin B demonstrated strong antibacterial effects in a murine abscess model of S. aureus. Our findings suggest that Ilicicolin B has the potential to treat S. aureus infection by inhibiting biofilm formation.

Design and evaluation of tadpole-like conformational antimicrobial peptides

Antimicrobial peptides are promising alternatives to conventional antibiotics. Herein, we report a class of "tadpole-like" peptides consisting of an amphipathic α-helical head and an aromatic tail. A structure-activity relationship (SAR) study of "tadpole-like" temporin-SHf and its analogs revealed that increasing the number of aromatic residues in the tail, introducing Arg to the α-helical head and rearranging the peptide topology dramatically increased antimicrobial activity. Through progressive structural optimization, we obtained two peptides, HT2 and RI-HT2, which exhibited potent antimicrobial activity, no hemolytic activity and cytotoxicity, and no propensity to induce resistance. NMR and molecular dynamics simulations revealed that both peptides indeed adopted "tadpole-like" conformations. Fluorescence experiments and electron microscopy confirmed the membrane targeting mechanisms of the peptides. Our studies not only lead to the discovery of a series of ultrashort peptides with potent broad-spectrum antimicrobial activities, but also provide a new strategy for rational design of novel "tadpole-like" antimicrobial peptides.

Accelerated NLRP3 inflammasome-inhibitory peptide design using a recurrent neural network model and molecular dynamics simulations

Anomalous NLRP3 inflammasome responses have been linked to multiple health issues, including but not limited to atherosclerosis, diabetes, metabolic syndrome, cardiovascular disease, and neurodegenerative disease. Thus, targeting NLRP3 and modulating its associated immune response might be a promising strategy for developing new anti-inflammatory drugs. Herein, we report a computational method for de novo peptide design for targeting NLRP3 inflammasomes. The described method leverages a long-short-term memory (LSTM) network based on a recurrent neural network (RNN) to model a valuable latent space of molecules. The resulting classifiers are utilized to guide the selection of molecules generated by the model based on circular dichroism spectra and physicochemical features derived from high-throughput molecular dynamics simulations. Of the experimentally tested sequences, 60% of the peptides showed NLRP3-mediated inhibition of IL-1β and IL-18. One peptide displayed high potency against NLRP3-mediated IL-1β inhibition. However, NLRC4 and AIM2 inflammasome-mediated IL-1β secretion was uninterrupted by this peptide, demonstrating its selectivity toward the NLRP3 inflammasome. Overall, these results indicate that deep learning and molecular dynamics can accelerate the discovery of NLRP3 inhibitors with potent and selective activity.

Synthetic extracellular matrices with function-encoding peptides

The communication of cells with their surroundings is mostly encoded in the epitopes of structural and signalling proteins present in the extracellular matrix (ECM). These peptide epitopes can be incorporated in biomaterials to serve as function-encoding molecules to modulate cell-cell and cell-ECM interactions. In this Review, we discuss natural and synthetic peptide epitopes as molecular tools to bioengineer bioactive hydrogel materials. We present a library of functional peptide sequences that selectively communicate with cells and the ECM to coordinate biological processes, including epitopes that directly signal to cells, that bind ECM components that subsequently signal to cells, and that regulate ECM turnover. We highlight how these epitopes can be incorporated in different biomaterials as individual or multiple signals, working synergistically or additively. This molecular toolbox can be applied in the design of biomaterials aimed at regulating or controlling cellular and tissue function, repair and regeneration.

Probing local changes to α-helical structures with 2D IR spectroscopy and isotope labeling

α-Helical secondary structures impart specific mechanical and physiochemical properties to peptides and proteins, enabling them to perform a vast array of molecular tasks ranging from membrane insertion to molecular allostery. Loss of α-helical content in specific regions can inhibit native protein function or induce new, potentially toxic, biological activities. Thus, identifying specific residues that exhibit loss or gain of helicity is critical for understanding the molecular basis of function. Two-dimensional infrared (2D IR) spectroscopy coupled with isotope labeling is capable of capturing detailed structural changes in polypeptides. Yet, questions remain regarding the inherent sensitivity of isotope-labeled modes to local changes in α-helicity, such as terminal fraying; the origin of spectral shifts (hydrogen-bonding versus vibrational coupling); and the ability to definitively detect coupled isotopic signals in the presence of overlapping side chains. Here, we address each of these points individually by characterizing a short, model α-helix (DPAEAAKAAAGR-NH2) with 2D IR and isotope labeling. These results demonstrate that pairs of 13C18O probes placed three residues apart can detect subtle structural changes and variations along the length of the model peptide as the α-helicity is systematically tuned. Comparison of singly and doubly labeled peptides affirm that frequency shifts arise primarily from hydrogen-bonding, while vibrational coupling between paired isotopes leads to increased peak areas that can be clearly differentiated from underlying side-chain modes or uncoupled isotope labels not participating in helical structures. These results demonstrate that 2D IR in tandem with i,i+3 isotope-labeling schemes can capture residue-specific molecular interactions within a single turn of an α-helix.

The Role of Helicobacter pylori Neutrophil-Activating Protein in the Pathogenesis of H. pylori and Beyond: From a Virulence Factor to Therapeutic Targets and Therapeutic Agents

Helicobacter pylori neutrophil-activating protein (HP-NAP), a major virulence factor of H. pylori, plays a role in bacterial protection and host inflammation. HP-NAP activates a variety of innate immune cells, including neutrophils, monocytes, and mast cells, to induce their pro-oxidant and pro-inflammatory activities. This protein also induces T-helper type 1 (Th1) immune response and cytotoxic T lymphocyte (CTL) activity, supporting that HP-NAP is able to promote gastric inflammation by activation of adaptive immune responses. Thus, HP-NAP is a potential therapeutic target for the treatment of H. pylori-induced gastric inflammation. The inflammatory responses triggered by HP-NAP are mediated by a PTX-sensitive G protein-coupled receptor and Toll-like receptor 2. Drugs designed to block the interactions between HP-NAP and its receptors could alleviate the inflammation in gastric mucosa caused by H. pylori infection. In addition, HP-NAP acts as a promising therapeutic agent for vaccine development, allergy treatment, and cancer immunotherapy. The high antigenicity of HP-NAP makes this protein a component of vaccines against H. pylori infection. Due to its immunomodulatory activity to stimulate the Th1-inducing ability of dendritic cells, enhance Th1 immune response and CTL activity, and suppress Th2-mediated allergic responses, HP-NAP could also act as an adjuvant in vaccines, a drug candidate against allergic diseases, and an immunotherapeutic agent for cancer. This review highlights the role of HP-NAP in the pathogenesis of H. pylori and the potential for this protein to be a therapeutic target in the treatment of H. pylori infection and therapeutic agents against H. pylori-associated diseases, allergies, and cancer.

Design of Protein Segments and Peptides for Binding to Protein Targets

Recent years have witnessed a rise in methods for accurate prediction of structure and design of novel functional proteins. Design of functional protein fragments and peptides occupy a small, albeit unique, space within the general field of protein design. While the smaller size of these peptides allows for more exhaustive computational methods, flexibility in their structure and sparsity of data compared to proteins, as well as presence of noncanonical building blocks, add additional challenges to their design. This review summarizes the current advances in the design of protein fragments and peptides for binding to targets and discusses the challenges in the field, with an eye toward future directions.