Artificial intelligence-driven antimicrobial peptide discovery

Unlocking the power of membrane biophysics: enhancing the study of antimicrobial peptides activity and selectivity

The application of membrane-active antimicrobial peptides (AMPs) is considered to be a viable alternative to conventional antibiotics for treating infections caused by multidrug-resistant pathogenic microorganisms. In vitro and in silico biophysical approaches are indispensable for understanding the underlying molecular mechanisms of membrane-active AMPs. Lipid bilayer models are widely used to mimic and study the implication of various factors affecting these bio-active molecules, and their relationship with the physical parameters of the different membranes themselves. The quality and resemblance of these models to their target is crucial for elucidating how these AMPs work. Unfortunately, over the last few decades, no notable efforts have been made to improve or refine membrane mimetics, as it pertains to the elucidation of AMPs molecular mechanisms. In this review, we discuss the importance of improving the quality and resemblance of target membrane models, in terms of lipid composition and distribution, which ultimately directly influence physical parameters such as charge, fluidity, and thickness. In conjunction, membrane and peptide properties determine the global effect of selectivity, activity, and potency. It is therefore essential to define these interactions, and to do so, more refined lipid models are necessary. In this review, we focus on the significant advancements in promoting biomimetic membranes that closely resemble native ones, for which thorough biophysical characterization is key. This includes utilizing more complex lipid compositions that mimic various cell types. Additionally, we discuss important considerations to be taken into account when working with more complex systems.

Algae and Cyanobacteria Fatty Acids and Bioactive Metabolites: Natural Antifungal Alternative Against Fusarium sp

Fungal diseases caused by Fusarium spp. significantly threaten food security and sustainable agriculture. One of the traditional strategies for eradicating Fusarium spp. incidents is the use of chemical and synthetic fungicides. The excessive use of these products generates environmental damage and has negative effects on crop yield. It puts plants in stressful conditions, kills the natural soil microbiome, and makes phytopathogenic fungi resistant. Finally, it also causes health problems in farmers. This drives the search for and selection of natural alternatives, such as bio-fungicides. Among natural products, algae and cyanobacteria are promising sources of antifungal bio-compounds. These organisms can synthesize different bioactive molecules, such as fatty acids, phenolic acids, and some volatile organic compounds with antifungal activity, which can damage the fungal cell membrane that surrounds the hyphae and spores, either by solubilization or by making them porous and disrupted. Research in this area is still developing, but significant progress has been made in the identification of the compounds with potential for controlling this important pathogen. Therefore, this review focuses on the knowledge about the mechanisms of action of the fatty acids from macroalgae, microalgae, and cyanobacteria as principal biomolecules with antifungal activity, as well as on the benefits and challenges of applying these natural metabolites against Fusarium spp. to achieve sustainable agriculture.

StaPep: An Open-Source Toolkit for Structure Prediction, Feature Extraction, and Rational Design of Hydrocarbon-Stapled Peptides

All-hydrocarbon stapled peptides, with their covalent side-chain constraints, provide enhanced proteolytic stability and membrane permeability, making them superior to linear peptides. However, tools for extracting structural and physicochemical descriptors to predict the properties of hydrocarbon-stapled peptides are lacking. To address this, we present StaPep, a Python-based toolkit for generating 3D structures and calculating 21 features for hydrocarbon-stapled peptides. StaPep supports peptides containing two non-standard amino acids (norleucine and 2-aminoisobutyric acid) and six non-natural anchoring residues (S3, S5, S8, R3, R5, and R8), with customization options for other non-standard amino acids. We showcase StaPep's utility through three case studies. The first generates 3D structures of these peptides with a mean RMSD of 1.62 ± 0.86, offering essential structural insights for drug design and biological activity prediction. The second develops machine learning models based on calculated molecular features to differentiate between membrane-permeable and non-permeable stapled peptides, achieving an AUC of 0.93. The third constructs regression models to predict the antimicrobial activity of stapled peptides against Escherichia coli, with a Pearson correlation of 0.84. StaPep's pipeline spans data retrieval, structure generation, feature calculation, and machine learning modeling for hydrocarbon-stapled peptides. The source codes and data set are freely available on Github: https://github.com/dahuilangda/stapep_package.

Assessing Cytotoxicity, Proteolytic Stability, and Selectivity of Antimicrobial Peptides: Implications for Orthopedic Applications

In orthopedics, the use of anti-infective biomaterials is considered the most promising strategy to contrast the bacterial contamination of implant surfaces and reduce the infection rate. KSL, KSL-W, and Dadapin-1 are three antimicrobial peptides (AMPs) that possess significant antibacterial properties, making them promising candidates for producing anti-infective biomaterials not based on antibiotics. To fully assess their true potential, this study explores in detail their cytocompatibility on human osteoblast-like MG63 cells, murine fibroblastoid L929 cells, and hMSCs. To this end, the cytotoxicity of the AMPs in terms of IC50 was tested over a range of concentrations of 450-0.22 µg/mL using the ATP bioluminescence assay. The tests were performed both in the presence and absence of bovine serum to assess the effects of serum components on peptide stability. IC50 values obtained under the most stringent conditions were used to extrapolate the selectivity index (S.I.) toward salient bacterial species. In medium containing serum, all AMPs exhibited minimal to no cytotoxicity, with IC50 values exceeding 100 µg/mL. Dadapin-1 was the peptide that exhibited the lowest cytotoxicity, KSL-W exhibited the highest stability, and KSL exhibited the highest selectivity. Overall, these findings highlight the potential of these AMPs for the future production of anti-infective materials.

An explainable few-shot learning model for the directed evolution of antimicrobial peptides

Due to the persistent threat of antibiotic resistance posed by Gram-negative pathogens, the discovery of new antimicrobial agents is of critical importance. In this study, we employed deep learning-guided directed evolution to explore the chemical space of antimicrobial peptides (AMPs), which present promising alternatives to traditional small-molecule antibiotics. Utilizing a fine-tuned protein language model tailored for small dataset learning, we achieved structural modifications of the lipopolysaccharide-binding domain (LBD) derived from Marsupenaeus japonicus, a prawn species of considerable value in aquaculture and commercial fisheries. The engineered LBDs demonstrated exceptional activity against a range of Gram-negative pathogens. Drawing inspiration from evolutionary principles, we elucidated the bactericidal mechanism through molecular dynamics simulations and mapped the directed evolution pathways using a ladderpath framework. This work highlights the efficacy of explainable few-shot learning in the rational design of AMPs through directed evolution.

Therapeutic peptide development revolutionized: Harnessing the power of artificial intelligence for drug discovery

Due to the spread of antibiotic resistance, global attention is focused on its inhibition and the expansion of effective medicinal compounds. The novel functional properties of peptides have opened up new horizons in personalized medicine. With artificial intelligence methods combined with therapeutic peptide products, pharmaceuticals and biotechnology advance drug development rapidly and reduce costs. Short-chain peptides inhibit a wide range of pathogens and have great potential for targeting diseases. To address the challenges of synthesis and sustainability, artificial intelligence methods, namely machine learning, must be integrated into their production. Learning methods can use complicated computations to select the active and toxic compounds of the drug and its metabolic activity. Through this comprehensive review, we investigated the artificial intelligence method as a potential tool for finding peptide-based drugs and providing a more accurate analysis of peptides through the introduction of predictable databases for effective selection and development.

Discovery of AMPs from random peptides via deep learning-based model and biological activity validation

The ample peptide field is the best source for discovering clinically available novel antimicrobial peptides (AMPs) to address emerging drug resistance. However, discovering novel AMPs is complex and expensive, representing a major challenge. Recent advances in artificial intelligence (AI) have significantly improved the efficiency of identifying antimicrobial peptides from large libraries, whereas using random peptides as negative data increases the difficulty of discovering antimicrobial peptides from random peptides using discriminative models. In this study, we constructed three multi-discriminator models using deep learning and successfully screened twelve AMPs from a library of 30,000 random peptides. three candidate peptides (P2, P11, and P12) were screened by antimicrobial experiments, and further experiments showed that they not only possessed excellent antimicrobial activity but also had extremely low hemolytic activity. Mechanistic studies showed that these peptides exerted their bactericidal effects through membrane disruption, thus reducing the possibility of bacterial resistance. Notably, peptide 12 (P12) showed significant efficacy in a mouse model of Staphylococcus aureus wound infection with low toxicity to major organs at the highest tested dose (400 mg/kg). These results suggest deep learning-based multi-discriminator models can identify AMPs from random peptides with potential clinical applications.

Research Progress on Food-Derived Bioactive Peptides: An Overview of the 3rd International Symposium on Bioactive Peptides

Interest in food-derived bioactive peptides is on the rise. In 2023, the 3rd International Symposium on Bioactive Peptides (ISBP) was held in Niagara Falls, Canada, to provide a platform for knowledge exchange, networking, and collaboration among researchers in this field. This article aims to provide a high-level overview of the key progress and emerging trends in bioactive peptides based on the 3rd ISBP. This review highlights the production of bioactive peptides from sustainable sources through the integration of artificial intelligence and wet-lab research, the emerging roles of bioactive peptides in cognitive function, and the ability of peptides to act as taste modifiers. The emerging research trend in bioactive peptides focuses on utilizing novel processing technologies, understanding peptide-receptor interactions, applying omics in mechanistic studies, conducting clinical trials, and facilitating product development and commercialization.

Future Perspective: Harnessing the Power of Artificial Intelligence in the Generation of New Peptide Drugs

The expansive field of drug discovery is continually seeking innovative approaches to identify and develop novel peptide-based therapeutics. With the advent of artificial intelligence (AI), there has been a transformative shift in the generation of new peptide drugs. AI offers a range of computational tools and algorithms that enables researchers to accelerate the therapeutic peptide pipeline. This review explores the current landscape of AI applications in peptide drug discovery, highlighting its potential, challenges, and ethical considerations. Additionally, it presents case studies and future prospectives that demonstrate the impact of AI on the generation of new peptide drugs.

Screening and heterologous expression of an antimicrobial peptide SCAK33 with broad-spectrum antimicrobial activity resourced from sea cucumber proteome

Antimicrobial peptides (AMPs) are a family of short defense proteins that are naturally produced by all organisms and have great potential as effective substitutes for small-molecule antibiotics. The present study aims to excavate AMPs from sea cucumbers and achieve their heterologous expression in prokaryotic Escherichia coli. Using MytC as a probe, a cysteine-stabilized peptide SCAK33 with broad-spectrum antimicrobial activity was discovered from the proteome of Apostichopus japonicas. The SCAK33 showed inhibitory effects on both gram positive and gram negative bacteria with MICs of 3-28 μM, and without significant hemolysis activity in rat blood erythrocyte. Especially, it exhibited good antimicrobial activity against Bacillus megaterium, B. subtilis, and Vibrio parahaemolyticus with the MIC of 3, 7, and 7 μM, respectively. After observation by scanning electronic microscopy (SEM) and confocal laser scanning microscope (CLSM), it was found that the cell membrane of bacteria was severely damaged. Furthermore, the recombinant SCAK33 (reSCAK33) was heterologously expressed by fusion with SUMO tag in E. coli BL21(DE3), and the protein yield reached 70 mg/L. The research will supplement the existing quantity of sea cucumber AMPs and provide data support for rapid mining and biological preparation of sea cucumber AMPs.

Predicting Antimicrobial Peptides Using ESMFold-Predicted Structures and ESM-2-Based Amino Acid Features with Graph Deep Learning

Currently, antimicrobial resistance constitutes a serious threat to human health. Drugs based on antimicrobial peptides (AMPs) constitute one of the alternatives to address it. Shallow and deep learning (DL)-based models have mainly been built from amino acid sequences to predict AMPs. Recent advances in tertiary (3D) structure prediction have opened new opportunities in this field. In this sense, models based on graphs derived from predicted peptide structures have recently been proposed. However, these models are not in correspondence with state-of-the-art approaches to codify evolutionary information, and, in addition, they are memory- and time-consuming because depend on multiple sequence alignment. Herein, we presented a framework to create alignment-free models based on graph representations generated from ESMFold-predicted peptide structures, whose nodes are characterized with amino acid-level evolutionary information derived from the Evolutionary Scale Modeling (ESM-2) models. A graph attention network (GAT) was implemented to assess the usefulness of the framework in the AMP classification. To this end, a set comprised of 67,058 peptides was used. It was demonstrated that the proposed methodology allowed to build GAT models with generalization abilities consistently better than 20 state-of-the-art non-DL-based and DL-based models. The best GAT models were developed using evolutionary information derived from the 36- and 33-layer ESM-2 models. Similarity studies showed that the best-built GAT models codified different chemical spaces, and thus they were fused to significantly improve the classification. In general, the results suggest that esm-AxP-GDL is a promissory tool to develop good, structure-dependent, and alignment-free models that can be successfully applied in the screening of large data sets. This framework should not only be useful to classify AMPs but also for modeling other peptide and protein activities.

Antimicrobial Peptides towards Clinical Application-A Long History to Be Concluded

Antimicrobial peptides (AMPs) are molecules with an amphipathic structure that enables them to interact with bacterial membranes. This interaction can lead to membrane crossing and disruption with pore formation, culminating in cell death. They are produced naturally in various organisms, including humans, animals, plants and microorganisms. In higher animals, they are part of the innate immune system, where they counteract infection by bacteria, fungi, viruses and parasites. AMPs can also be designed de novo by bioinformatic approaches or selected from combinatorial libraries, and then produced by chemical or recombinant procedures. Since their discovery, AMPs have aroused interest as potential antibiotics, although few have reached the market due to stability limits or toxicity. Here, we describe the development phase and a number of clinical trials of antimicrobial peptides. We also provide an update on AMPs in the pharmaceutical industry and an overall view of their therapeutic market. Modifications to peptide structures to improve stability in vivo and bioavailability are also described.

Immunomodulatory Peptides as Vaccine Adjuvants and Antimicrobial Agents

The underdevelopment of adjuvant discovery and diversity, compared to core vaccine technology, is evident. On the other hand, antibiotic resistance is on the list of the top ten threats to global health. Immunomodulatory peptides that target a pathogen and modulate the immune system simultaneously are promising for the development of preventive and therapeutic molecules. Since investigating innate immunity in insects has led to prominent achievements in human immunology, such as toll-like receptor (TLR) discovery, we used the capacity of the immunomodulatory peptides of arthropods with concomitant antimicrobial or antitumor activity. An SVM-based machine learning classifier identified short immunomodulatory sequences encrypted in 643 antimicrobial peptides from 55 foe-to-friend arthropods. The critical features involved in efficacy and safety were calculated. Finally, 76 safe immunomodulators were identified. Then, molecular docking and simulation studies defined the target of the most optimal peptide ligands among all human cell-surface TLRs. SPalf2-453 from a crab is a cell-penetrating immunoadjuvant with antiviral properties. The peptide interacts with the TLR1/2 heterodimer. SBsib-711 from a blackfly is a TLR4/MD2 ligand used as a cancer vaccine immunoadjuvant. In addition, SBsib-711 binds CD47 and PD-L1 on tumor cells, which is applicable in cancer immunotherapy as a checkpoint inhibitor. MRh4-679 from a shrimp is a broad-spectrum or universal immunoadjuvant with a putative Th1/Th2-balanced response. We also implemented a pathway enrichment analysis to define fingerprints or immunological signatures for further in vitro and in vivo immunogenicity and reactogenicity measurements. Conclusively, combinatorial machine learning, molecular docking, and simulation studies, as well as systems biology, open a new opportunity for the discovery and development of multifunctional prophylactic and therapeutic lead peptides.