In silico optimization of a guava antimicrobial peptide enables combinatorial exploration for peptide design

Antibacterial and Antiviral Properties of Chenopodin-Derived Synthetic Peptides

Antimicrobial peptides have been developed based on plant-derived molecular scaffolds for the treatment of infectious diseases. Chenopodin is an abundant seed storage protein in quinoa, an Andean plant with high nutritional and therapeutic properties. Here, we used computer- and physicochemical-based strategies and designed four peptides derived from the primary structure of Chenopodin. Two peptides reproduce natural fragments of 14 amino acids from Chenopodin, named Chen1 and Chen2, and two engineered peptides of the same length were designed based on the Chen1 sequence. The two amino acids of Chen1 containing amide side chains were replaced by arginine (ChenR) or tryptophan (ChenW) to generate engineered cationic and hydrophobic peptides. The evaluation of these 14-mer peptides on Staphylococcus aureus and Escherichia coli showed that Chen1 does not have antibacterial activity up to 512 µM against these strains, while other peptides exhibited antibacterial effects at lower concentrations. The chemical substitutions of glutamine and asparagine by amino acids with cationic or aromatic side chains significantly favoured their antibacterial effects. These peptides did not show significant hemolytic activity. The fluorescence microscopy analysis highlighted the membranolytic nature of Chenopodin-derived peptides. Using molecular dynamic simulations, we found that a pore is formed when multiple peptides are assembled in the membrane. Whereas, some of them form secondary structures when interacting with the membrane, allowing water translocations during the simulations. Finally, Chen2 and ChenR significantly reduced SARS-CoV-2 infection. These findings demonstrate that Chenopodin is a highly useful template for the design, engineering, and manufacturing of non-toxic, antibacterial, and antiviral peptides.

Innovative Biomedical and Technological Strategies for the Control of Bacterial Growth and Infections

Antibiotics comprise one of the most successful groups of pharmaceutical products. Still, they have been associated with developing bacterial resistance, which has become one of the most severe problems threatening human health today. This context has prompted the development of new antibiotics or co-treatments using innovative tools to reverse the resistance context, combat infections, and offer promising antibacterial therapy. For the development of new alternatives, strategies, and/or antibiotics for controlling bacterial growth, it is necessary to know the target bacteria, their classification, morphological characteristics, the antibiotics currently used for therapies, and their respective mechanisms of action. In this regard, genomics, through the sequencing of bacterial genomes, has generated information on diverse genetic resources, aiding in the discovery of new molecules or antibiotic compounds. Nanotechnology has been applied to propose new antimicrobials, revitalize existing drug options, and use strategic encapsulating agents with their biochemical characteristics, making them more effective against various bacteria. Advanced knowledge in bacterial sequencing contributes to the construction of databases, resulting in advances in bioinformatics and the development of new antimicrobials. Moreover, it enables in silico antimicrobial susceptibility testing without the need to cultivate the pathogen, reducing costs and time. This review presents new antibiotics and biomedical and technological innovations studied in recent years to develop or improve natural or synthetic antimicrobial agents to reduce bacterial growth, promote well-being, and benefit users.

Exploring the frontiers of therapeutic breadth of antifungal peptides: A new avenue in antifungal drugs

The growing prevalence of fungal infections alongside rising resistance to antifungal drugs poses a significant challenge to public health safety. At the close of the 2000s, major pharmaceutical firms began to scale back on antimicrobial research due to repeated setbacks and diminished economic gains, leaving only smaller companies and research labs to pursue new antifungal solutions. Among various natural sources explored for novel antifungal compounds, antifungal peptides (AFPs) emerge as particularly promising. Despite their potential, AFPs receive less focus than their antibacterial counterparts. These peptides have been sourced extensively from nature, including plants, animals, insects, and especially bacteria and fungi. Furthermore, with advancements in recombinant biotechnology and computational biology, AFPs can also be synthesized in lab settings, facilitating peptide production. AFPs are noted for their wide-ranging efficacy, in vitro and in vivo safety, and ability to combat biofilms. They are distinguished by their high specificity, minimal toxicity to cells, and reduced likelihood of resistance development. This review aims to comprehensively cover AFPs, including their sources-both natural and synthetic-their antifungal and biofilm-fighting capabilities in laboratory and real-world settings, their action mechanisms, and the current status of AFP research.

ONE-SENTENCE SUMMARY

This comprehensive review of AFPs will be helpful for further research in antifungal research.

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.

Efficient Computational Framework for Target-Specific Active Peptide Discovery: A Case Study on IL-17C Targeting Cyclic Peptides

The development of potentially active peptides for specific targets is critical for the modern pharmaceutical industry's growth. In this study, we present an efficient computational framework for the discovery of active peptides targeting a specific pharmacological target, which combines a conditional variational autoencoder (CVAE) and a classifier named TCPP based on the Transformer and convolutional neural network. In our example scenario, we constructed an active cyclic peptide library targeting interleukin-17C (IL-17C) through a library-based in vitro selection strategy. The CVAE model is trained on the preprocessed peptide data sets to generate potentially active peptides and the TCPP further screens the generated peptides. Ultimately, six candidate peptides predicted by the model were synthesized and assayed for their activity, and four of them exhibited promising binding affinity to IL-17C. Our study provides a one-stop-shop for target-specific active peptide discovery, which is expected to boost up the process of peptide drug development.

Screening and investigation of a short antimicrobial peptide: AVGAV

Bacterial resistance to various drugs is a major problem concerning the field of antibacterial agents. Fortunately, peptides with antibacterial activity can alleviate this problem. In this study, a short peptide (AVGAV) with excellent antibacterial activity was successfully screened from a peptide library by a self-made membrane chromatographic packing. The AVGAV peptide exhibits good biocompatibility and is non-toxic and non-irritating, which ensures that it presents safe antibacterial effects. AVGAV promoted wound healing in a mouse wound bacterial infection model. Most importantly, as a synthetic antimicrobial peptide, AVGAV can alleviate the problem of bacterial resistance, thus improving its application potential. This study provides a solution to the existing and potential problem of bacterial resistance.

Antibiotic identified by AI

Computational approaches are emerging as powerful tools for the discovery of antibiotics. A study now uses machine learning to discover abaucin, a potent antibiotic that targets the bacterial pathogen Acinetobacter baumannii .

Harnessing the power of artificial intelligence to advance cell therapy

Cell therapies are powerful technologies in which human cells are reprogrammed for therapeutic applications such as killing cancer cells or replacing defective cells. The technologies underlying cell therapies are increasing in effectiveness and complexity, making rational engineering of cell therapies more difficult. Creating the next generation of cell therapies will require improved experimental approaches and predictive models. Artificial intelligence (AI) and machine learning (ML) methods have revolutionized several fields in biology including genome annotation, protein structure prediction, and enzyme design. In this review, we discuss the potential of combining experimental library screens and AI to build predictive models for the development of modular cell therapy technologies. Advances in DNA synthesis and high-throughput screening techniques enable the construction and screening of libraries of modular cell therapy constructs. AI and ML models trained on this screening data can accelerate the development of cell therapies by generating predictive models, design rules, and improved designs.

Molecular hybridization strategy for tuning bioactive peptide function

The physicochemical and structural properties of antimicrobial peptides (AMPs) determine their mechanism of action and biological function. However, the development of AMPs as therapeutic drugs has been traditionally limited by their toxicity for human cells. Tuning the physicochemical properties of such molecules may abolish toxicity and yield synthetic molecules displaying optimal safety profiles and enhanced antimicrobial activity. Here, natural peptides were modified to improve their activity by the hybridization of sequences from two different active peptide sequences. Hybrid AMPs (hAMPs) were generated by combining the amphipathic faces of the highly toxic peptide VmCT1, derived from scorpion venom, with parts of four other naturally occurring peptides having high antimicrobial activity and low toxicity against human cells. This strategy led to the design of seven synthetic bioactive variants, all of which preserved their structure and presented increased antimicrobial activity (3.1-128 μmol L-1). Five of the peptides (three being hAMPs) presented high antiplasmodial at 0.8 μmol L-1, and virtually no undesired toxic effects against red blood cells. In sum, we demonstrate that peptide hybridization is an effective strategy for redirecting biological activity to generate novel bioactive molecules with desired properties.

Model-directed generation of CRISPR-Cas13a guide RNAs designs artificial sequences that improve nucleic acid detection

Generating maximally-fit biological sequences has the potential to transform CRISPR guide RNA design as it has other areas of biomedicine. Here, we introduce model-directed exploration algorithms (MEAs) for designing maximally-fit, artificial CRISPR-Cas13a guides-with multiple mismatches to any natural sequence-that are tailored for desired properties around nucleic acid diagnostics. We find that MEA-designed guides offer more sensitive detection of diverse pathogens and discrimination of pathogen variants compared to guides derived directly from natural sequences, and illuminate interpretable design principles that broaden Cas13a targeting.

Computational exploration of the global microbiome for antibiotic discovery

Novel antibiotics are urgently needed to combat the antibiotic-resistance crisis. We present a machine learning-based approach to predict prokaryotic antimicrobial peptides (AMPs) by leveraging a vast dataset of 63,410 metagenomes and 87,920 microbial genomes. This led to the creation of AMPSphere, a comprehensive catalog comprising 863,498 non-redundant peptides, the majority of which were previously unknown. We observed that AMP production varies by habitat, with animal-associated samples displaying the highest proportion of AMPs compared to other habitats. Furthermore, within different human-associated microbiota, strain-level differences were evident. To validate our predictions, we synthesized and experimentally tested 50 AMPs, demonstrating their efficacy against clinically relevant drug-resistant pathogens both in vitro and in vivo. These AMPs exhibited antibacterial activity by targeting the bacterial membrane. Additionally, AMPSphere provides valuable insights into the evolutionary origins of peptides. In conclusion, our approach identified AMP sequences within prokaryotic microbiomes, opening up new avenues for the discovery of antibiotics.

Human gut metagenomic mining reveals an untapped source of peptide antibiotics

Drug-resistant bacteria are outpacing traditional antibiotic discovery efforts. Here, we computationally mined 444,054 families of putative small proteins from 1,773 human gut metagenomes, identifying 323 peptide antibiotics encoded in small open reading frames (smORFs). To test our computational predictions, 78 peptides were synthesized and screened for antimicrobial activity in vitro, with 59% displaying activity against either pathogens or commensals. Since these peptides were unique compared to previously reported antimicrobial peptides, we termed them smORF-encoded peptides (SEPs). SEPs killed bacteria by targeting their membrane, synergized with each other, and modulated gut commensals, indicating that they may play a role in reconfiguring microbiome communities in addition to counteracting pathogens. The lead candidates were anti-infective in both murine skin abscess and deep thigh infection models. Notably, prevotellin-2 from Prevotella copri presented activity comparable to the commonly used antibiotic polymyxin B. We report the discovery of hundreds of peptide sequences in the human gut.

Computational Peptide Discovery with a Genetic Programming Approach

Background

The development of peptides for therapeutic targets or biomarkers for disease diagnosis is a challenging task in protein engineering. Current approaches are tedious, often time-consuming and require complex laboratory data due to the vast search space. In silico methods can accelerate research and substantially reduce costs. Evolutionary algorithms are a promising approach for exploring large search spaces and facilitating the discovery of new peptides.

Results

This study presents the development and use of a variant of the initial POET algorithm, called P O E T R e g e x , which is based on genetic programming, where individuals are represented by a list of regular expressions. The program was trained on a small curated dataset and employed to predict new peptides that can improve the problem of sensitivity in detecting peptides through magnetic resonance imaging using chemical exchange saturation transfer (CEST). The resulting model achieves a performance gain of 20% over the initial POET variant and is able to predict a candidate peptide with a 58% performance increase compared to the gold-standard peptide.

Conclusions

By combining the power of genetic programming with the flexibility of regular expressions, new potential peptide targets were identified to improve the sensitivity of detection by CEST. This approach provides a promising research direction for the efficient identification of peptides with therapeutic or diagnostic potential.

Computationally Designed AMPs with Antibacterial and Antibiofilm Activity against MDR Acinetobacter baumannii

The discovery of new antimicrobials is necessary to combat multidrug-resistant (MDR) bacteria, especially those that infect wounds and form prodigious biofilms, such as Acinetobacter baumannii. Antimicrobial peptides (AMPs) are a promising class of new therapeutics against drug-resistant bacteria, including gram-negatives. Here, we utilized a computational AMP design strategy combining database filtering technology plus positional analysis to design a series of novel peptides, named HRZN, designed to be active against A. baumannii. All of the HRZN peptides we synthesized exhibited antimicrobial activity against three MDR A. baumannii strains with HRZN-15 being the most active (MIC 4 µg/mL). This peptide also inhibited and eradicated biofilm of A. baumannii strain AB5075 at 8 and 16 µg/mL, which is highly effective. HRZN-15 permeabilized and depolarized the membrane of AB5075 rapidly, as demonstrated by the killing kinetics. HRZN 13 and 14 peptides had little to no hemolysis activity against human red blood cells, whereas HRZN-15, -16, and -17 peptides demonstrated more significant hemolytic activity. HRZN-15 also demonstrated toxicity to waxworms. Further modification of HRZN-15 could result in a new peptide with an improved toxicity profile. Overall, we successfully designed a set of new AMPs that demonstrated activity against MDR A. baumannii using a computational approach.

Activity modulation of the Escherichia coli F1FO ATP synthase by a designed antimicrobial peptide via cardiolipin sequestering

Most antimicrobial peptides (AMPs) exert their microbicidal activity through membrane permeabilization. The designed AMP EcDBS1R4 has a cryptic mechanism of action involving the membrane hyperpolarization of Escherichia coli, suggesting that EcDBS1R4 may hinder processes involved in membrane potential dissipation. We show that EcDBS1R4 can sequester cardiolipin, a phospholipid that interacts with several respiratory complexes of E. coli. Among these, F₁F_O ATP synthase uses membrane potential to fuel ATP synthesis. We found that EcDBS1R4 can modulate the activity of ATP synthase upon partition to membranes containing cardiolipin. Molecular dynamics simulations suggest that EcDBS1R4 alters the membrane environment of the transmembrane F_O motor, impairing cardiolipin interactions with the cytoplasmic face of the peripheral stalk that binds the catalytic F₁ domain to the F_O domain. The proposed mechanism of action, targeting membrane protein function through lipid reorganization may open new venues of research on the mode of action and design of other AMPs.

Structure-function-guided design of synthetic peptides with anti-infective activity derived from wasp venom

Antimicrobial peptides (AMPs) derived from natural toxins and venoms offer a promising alternative source of antibiotics. Here, through structure-function-guided design, we convert two natural AMPs derived from the venom of the solitary eumenine wasp Eumenes micado into α-helical AMPs with reduced toxicity that kill Gram-negative bacteria in vitro and in a preclinical mouse model. To identify the sequence determinants conferring antimicrobial activity, an alanine scan screen and strategic single lysine substitutions are made to the amino acid sequence of these natural peptides. These efforts yield a total of 34 synthetic derivatives, including alanine substituted and lysine-substituted sequences with stabilized α-helical structures and increased net positive charge. The resulting lead synthetic peptides kill the Gram-negative pathogens Escherichia coli and Pseudomonas aeruginosa (PAO1 and PA14) by rapidly permeabilizing both their outer and cytoplasmic membranes, exhibit anti-infective efficacy in a mouse model by reducing bacterial loads by up to three orders of magnitude, and do not readily select for bacterial resistance.

Leveraging artificial intelligence in the fight against infectious diseases

Despite advances in molecular biology, genetics, computation, and medicinal chemistry, infectious disease remains an ominous threat to public health. Addressing the challenges posed by pathogen outbreaks, pandemics, and antimicrobial resistance will require concerted interdisciplinary efforts. In conjunction with systems and synthetic biology, artificial intelligence (AI) is now leading to rapid progress, expanding anti-infective drug discovery, enhancing our understanding of infection biology, and accelerating the development of diagnostics. In this Review, we discuss approaches for detecting, treating, and understanding infectious diseases, underscoring the progress supported by AI in each case. We suggest future applications of AI and how it might be harnessed to help control infectious disease outbreaks and pandemics.

Geometric deep learning as a potential tool for antimicrobial peptide prediction

Antimicrobial peptides (AMPs) are components of natural immunity against invading pathogens. They are polymers that fold into a variety of three-dimensional structures, enabling their function, with an underlying sequence that is best represented in a non-flat space. The structural data of AMPs exhibits non-Euclidean characteristics, which means that certain properties, e.g., differential manifolds, common system of coordinates, vector space structure, or translation-equivariance, along with basic operations like convolution, in non-Euclidean space are not distinctly established. Geometric deep learning (GDL) refers to a category of machine learning methods that utilize deep neural models to process and analyze data in non-Euclidean settings, such as graphs and manifolds. This emerging field seeks to expand the use of structured models to these domains. This review provides a detailed summary of the latest developments in designing and predicting AMPs utilizing GDL techniques and also discusses both current research gaps and future directions in the field.

Deep learning tools to accelerate antibiotic discovery

INTRODUCTION

As machine learning (ML) and artificial intelligence (AI) expand to many segments of our society, they are increasingly being used for drug discovery. Recent deep learning models offer an efficient way to explore high-dimensional data and design compounds with desired properties, including those with antibacterial activity.

AREAS COVERED

This review covers key frameworks in antibiotic discovery, highlighting physicochemical features and addressing dataset limitations. The deep learning approaches here described include discriminative models such as convolutional neural networks, recurrent neural networks, graph neural networks, and generative models like neural language models, variational autoencoders, generative adversarial networks, normalizing flow, and diffusion models. As the integration of these approaches in drug discovery continues to evolve, this review aims to provide insights into promising prospects and challenges that lie ahead in harnessing such technologies for the development of antibiotics.

EXPERT OPINION

Accurate antimicrobial prediction using deep learning faces challenges such as imbalanced data, limited datasets, experimental validation, target strains, and structure. The integration of deep generative models with bioinformatics, molecular dynamics, and data augmentation holds the potential to overcome these challenges, enhance model performance, and utlimately accelerate antimicrobial discovery.

Progress towards the clinical use of antimicrobial peptides: challenges and opportunities

INTRODUCTION

To overcome the challenge of multidrug resistance, natural and synthetic peptides are candidates to become the basis of innovative therapeutics, featuring diverse mechanisms of action. Traditionally, the time elapsed from medical discoveries to their application is long. The urgency derived from the emergence of antibiotic resistance recommends an acceleration of research to put the new weapons in the hands of clinicians.

AREAS COVERED

This narrative review introduces ideas and suggestions of new strategies that may be used as a basis upon which to recommend reduced development times and to facilitate the arrival of new molecules in the fight against microbes.

EXPERT OPINION

Although studies on new innovative antimicrobial treatments are being conducted, sooner rather than later, more clinical trials, preclinical and translational research are needed to promote the development of innovative antimicrobial treatments for multidrug resistant infections. The situation is worrying, no less than that generated by pandemics such as the ones we have just experienced and conflicts such as world wars. Although from the point of view of human perception, resistance to antibiotics may not seem as serious as these other situations, it is possibly the hidden pandemic that most jeopardizes the future of medicine.

Mining for antimicrobial peptides in sequence space

A machine-learning pipeline identifies potent antimicrobial peptides by gradually narrowing down the search space of polypeptide chain sequences.

A pilot study on ultrashort peptide with fluconazole: A promising novel anticandidal combination

Background and Aim

Human infections caused by Candida albicans are common and range in severity from relatively treatable skin and mucosal conditions to systemic, fatal invasive candidiasis. The treatment of fungal infections is challenged by major obstacles, including the scarcity of effective therapeutic options, the toxicity of available medications, and the escalating antifungal resistance. Hence, there exists an urgent need to develop new classes of antimicrobial agents. This study was conducted to investigate the effect of KW-23 peptide against standard and resistant strains of C. albicans alone and in combination with fluconazole.

Materials and Methods

A conjugated ultrashort antimicrobial peptide (KW-23) was designed and synthesized. KW-23 was challenged against standard and multidrug-resistant C. albicans alone and in combination with fluconazole using standard antimicrobial and checkerboard assays. The toxicity of the peptide was examined using hemolytic assays.

Results

KW-23 positively affected the standard and resistant Candidal strains (at 5 and 15 μg/mL respectively), exhibiting potent synergistic antimicrobial activity against the standard strain when combined with fluconazole. The effect of the combination was additive against the resistant strain (0.6 μg/mL). Furthermore, the peptide exhibited negligible toxicity on human erythrocytes.

Conclusion

KW-23 and its combination with fluconazole could be a promising candidate for developing anticandidal agents.

Role of bacterial efflux pumps in antibiotic resistance, virulence, and strategies to discover novel efflux pump inhibitors

The problem of antibiotic resistance among pathogenic bacteria has reached a crisis level. The treatment options against infections caused by multiple drug-resistant bacteria are shrinking gradually. The current pace of the discovery of new antibacterial entities is lagging behind the rate of development of new resistance. Efflux pumps play a central role in making a bacterium resistant to multiple antibiotics due to their ability to expel a wide range of structurally diverse compounds. Besides providing an escape from antibacterial compounds, efflux pumps are also involved in bacterial stress response, virulence, biofilm formation, and altering host physiology. Efflux pumps are unique yet challenging targets for the discovery of novel efflux pump inhibitors (EPIs). EPIs could help rejuvenate our currently dried pipeline of antibacterial drug discovery. The current article highlights the recent developments in the field of efflux pumps, challenges faced during the development of EPIs and potential approaches for their development. Additionally, this review highlights the utility of resources such as natural products and machine learning to expand our EPIs arsenal using these latest technologies.

Advanced delivery systems for peptide antibiotics

Antimicrobial peptides (AMPs) hold promise as alternatives to traditional antibiotics for preventing and treating multidrug-resistant infections. Although they have potent antimicrobial efficacy, AMPs are mainly limited by their susceptibility to proteases and potential off-site cytotoxicity. Designing the right delivery system for peptides can help to overcome such limitations, thus improving the pharmacokinetic and pharmacodynamic profiles of these drugs. The versatility of peptides and their genetically encodable structure make them suitable for both conventional and nucleoside-based formulations. In this review, we describe the main drug delivery procedures developed so far for peptide antibiotics: lipid nanoparticles, polymeric nanoparticles, hydrogels, functionalized surfaces, and DNA- and RNA-based delivery systems.

Intelligent De Novo Design of Novel Antimicrobial Peptides against Antibiotic-Resistant Bacteria Strains

Because of the growing number of clinical antibiotic resistance cases in recent years, novel antimicrobial peptides (AMPs) may be ideal for next-generation antibiotics. This study trained a Wasserstein generative adversarial network with gradient penalty (WGAN-GP) based on known AMPs to generate novel AMP candidates. The quality of the GAN-designed peptides was evaluated in silico, and eight of them, named GAN-pep 1–8, were selected by an AMP Artificial Intelligence (AI) classifier and synthesized for further experiments. Disc diffusion testing and minimum inhibitory concentration (MIC) determinations were used to identify the antibacterial effects of the synthesized GAN-designed peptides. Seven of the eight synthesized GAN-designed peptides displayed antibacterial activity. Additionally, GAN-pep 3 and GAN-pep 8 presented a broad spectrum of antibacterial effects and were effective against antibiotic-resistant bacteria strains, such as methicillin-resistant Staphylococcus aureus and carbapenem-resistant Pseudomonas aeruginosa. GAN-pep 3, the most promising GAN-designed peptide candidate, had low MICs against all the tested bacteria. In brief, our approach shows an efficient way to discover AMPs effective against general and antibiotic-resistant bacteria strains. In addition, such a strategy also allows other novel functional peptides to be quickly designed, identified, and synthesized for validation on the wet bench.

Bioactive Antimicrobial Peptides from Food Proteins: Perspectives and Challenges for Controlling Foodborne Pathogens

Bioactive peptides (BAPs) derived from food proteins have been extensively studied for their health benefits, majorly exploring their potential use as nutraceuticals and functional food components. These peptides possess a range of beneficial properties, including antihypertensive, antioxidant, immunomodulatory, and antibacterial activities, and are naturally present within dietary protein sequences. To release food-grade antimicrobial peptides (AMPs), enzymatic protein hydrolysis or microbial fermentation, such as with lactic acid bacteria (LAB), can be employed. The activity of AMPs is influenced by various structural characteristics, including the amino acid composition, three-dimensional conformation, liquid charge, putative domains, and resulting hydrophobicity. This review discusses the synthesis of BAPs and AMPs, their potential for controlling foodborne pathogens, their mechanisms of action, and the challenges and prospects faced by the food industry. BAPs can regulate gut microbiota by promoting the growth of beneficial bacteria or by directly inhibiting pathogenic microorganisms. LAB-promoted hydrolysis of dietary proteins occurs naturally in both the matrix and the gastrointestinal tract. However, several obstacles must be overcome before BAPs can replace antimicrobials in food production. These include the high manufacturing costs of current technologies, limited in vivo and matrix data, and the difficulties associated with standardization and commercial-scale production.

Discovering highly potent antimicrobial peptides with deep generative model HydrAMP

Antimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance, prompting a need for novel computational approaches to peptide generation. Here, we propose HydrAMP, a conditional variational autoencoder that learns lower-dimensional, continuous representation of peptides and captures their antimicrobial properties. The model disentangles the learnt representation of a peptide from its antimicrobial conditions and leverages parameter-controlled creativity. HydrAMP is the first model that is directly optimized for diverse tasks, including unconstrained and analogue generation and outperforms other approaches in these tasks. An additional preselection procedure based on ranking of generated peptides and molecular dynamics simulations increases experimental validation rate. Wet-lab experiments on five bacterial strains confirm high activity of nine peptides generated as analogues of clinically relevant prototypes, as well as six analogues of an inactive peptide. HydrAMP enables generation of diverse and potent peptides, making a step towards resolving the antimicrobial resistance crisis.

Simultaneous control of infection and inflammation with keratin-derived antibacterial peptides targeting TLRs and co-receptors

Controlling infection-driven inflammation is a major clinical dilemma because of limited therapeutic options and possible adverse effects on microbial clearance. Compounding this difficulty is the continued emergence of drug-resistant bacteria, where experimental strategies aiming to augment inflammatory responses for enhanced microbial killing are not applicable treatment options for infections of vulnerable organs. As with corneal infections, severe or prolonged inflammation jeopardizes corneal transparency, leading to devastating vision loss. We hypothesized that keratin 6a-derived antimicrobial peptides (KAMPs) may be a two-pronged remedy capable of tackling bacterial infection and inflammation at once. We used murine peritoneal neutrophils and macrophages, together with an in vivo model of sterile corneal inflammation, to find that nontoxic and prohealing KAMPs with natural 10- and 18-amino acid sequences suppressed lipoteichoic acid (LTA)- and lipopolysaccharide (LPS)-induced NFκB and IRF3 activation, proinflammatory cytokine production, and phagocyte recruitment independently of their bactericidal function. Mechanistically, KAMPs not only competed with bacterial ligands for cell surface Toll-like receptor (TLR) and co-receptors (MD2, CD14, and TLR2) but also reduced cell surface availability of TLR2 and TLR4 through promotion of receptor endocytosis. Topical KAMP treatment effectively alleviated experimental bacterial keratitis, as evidenced by substantial reductions of corneal opacification, inflammatory cell infiltration, and bacterial burden. These findings reveal the TLR-targeting activities of KAMPs and demonstrate their therapeutic potential as a multifunctional drug for managing infectious inflammatory disease.

Rational Design of Stapled Antimicrobial Peptides to Enhance Stability and In Vivo Potency against Polymicrobial Sepsis

In this work, we sought to develop a TP4-based stapled peptide that can be used to counter polymicrobial sepsis. First, we segregated the TP4 sequence into hydrophobic and cationic/hydrophilic zones and substituted the preferred residue, lysine, as the sole cationic amino acid. These modifications minimized the intensity of cationic or hydrophobic characteristics within small segments. Then, we incorporated single or multiple staples into the peptide chain, bracketing the cationic/hydrophilic segments to improve pharmacological suitability. Using this approach, we were able to develop an AMP with low toxicity and notable in vivo efficacy. IMPORTANCE In our in vitro studies, one dual stapled peptide out of the series of candidates (TP4-3: FIIXKKSXGLFKKKAGAXKKKXIKK) showed significant activity, low toxicity, and high stability (in 50% human serum). When tested in cecal ligation and puncture (CLP) mouse models of polymicrobial sepsis, TP4-3 improved survival (87.5% on day 7). Furthermore, TP4-3 enhanced the activity of meropenem against polymicrobial sepsis (100% survival on day 7) compared to meropenem alone (37.5% survival on day 7). Molecules such as TP4-3 may be well suited for a wide variety of clinical applications.

Bacterial resistance to antibacterial agents: Mechanisms, control strategies, and implications for global health

The spread of bacterial drug resistance has posed a severe threat to public health globally. Here, we cover bacterial resistance to current antibacterial drugs, including traditional herbal medicines, conventional antibiotics, and antimicrobial peptides. We summarize the influence of bacterial drug resistance on global health and its economic burden while highlighting the resistance mechanisms developed by bacteria. Based on the One Health concept, we propose 4A strategies to combat bacterial resistance, including prudent Application of antibacterial agents, Administration, Assays, and Alternatives to antibiotics. Finally, we identify several opportunities and unsolved questions warranting future exploration for combating bacterial resistance, such as predicting genetic bacterial resistance through the use of more effective techniques, surveying both genetic determinants of bacterial resistance and the transmission dynamics of antibiotic resistance genes (ARGs).

Rational design of stapled antimicrobial peptides

The global increase in antimicrobial drug resistance has dramatically reduced the effectiveness of traditional antibiotics. Structurally diverse antibiotics are urgently needed to combat multiple-resistant bacterial infections. As part of innate immunity, antimicrobial peptides have been recognized as the most promising candidates because they comprise diverse sequences and mechanisms of action and have a relatively low induction rate of resistance. However, because of their low chemical stability, susceptibility to proteases, and high hemolytic effect, their usage is subject to many restrictions. Chemical modifications such as D-amino acid substitution, cyclization, and unnatural amino acid modification have been used to improve the stability of antimicrobial peptides for decades. Among them, a side-chain covalent bridge modification, the so-called stapled peptide, has attracted much attention. The stapled side-chain bridge stabilizes the secondary structure, induces protease resistance, and increases cell penetration and biological activity. Recent progress in computer-aided drug design and artificial intelligence methods has also been used in the design of stapled antimicrobial peptides and has led to the successful discovery of many prospective peptides. This article reviews the possible structure-activity relationships of stapled antimicrobial peptides, the physicochemical properties that influence their activity (such as net charge, hydrophobicity, helicity, and dipole moment), and computer-aided methods of stapled peptide design. Antimicrobial peptides under clinical trial: Pexiganan (NCT01594762, 2012-05-07). Omiganan (NCT02576847, 2015-10-13).

Artificial intelligence as a smart approach to develop antimicrobial drug molecules: A paradigm to combat drug-resistant infections

Antimicrobial resistance (AMR) is a silent pandemic with the third highest global mortality. The antibiotic development pipeline is scarce even though AMR has escalated uncontrollably. Artificial intelligence (AI) is a revolutionary approach, accelerating drug discovery because of its fast pace, cost efficiency, lower labor requirements, and fewer chances of failure. AI has been used to discover several beta-lactamase inhibitors and antibiotic alternatives from antimicrobial peptides (AMPs), nonribosomal peptides, bacteriocins, and marine natural products. The significant recent increase in the use of AI platforms by pharmaceutical companies could result in the discovery of efficient antibiotic alternatives with lower chances of resistance generation.

Evaluation of the inhibitory effects of TiO2 nanoparticle and Ganoderma lucidum extract against biofilm-producing bacteria isolated from clinical samples

The emergence of multidrug-resistant pathogens leads to treatment failure. So, the need for new antibacterial drugs is urgent. We evaluated the antibacterial and antibiofilm effects of titanium dioxide (TiO₂) nanoparticles (NPs) and Ganoderma extract against biofilm-producing Pseudomonas aeruginosa and methicillin-resistant Staphylococcus aureus (MRSA) by microbroth dilution and crystal violet assays. The combined effect of these compounds was studied using the checkerboard method. The OD₂₆₀ was measured to assess the destruction of the membrane permeability. The expression of biofilm-related genes (iacA and algD) was investigated by real-time PCR. MRSA isolate was more susceptible to test compounds. The OD₂₆₀ increased and algD gene was down-regulated after treatment with TiO₂ NPs and a combination of TiO₂ NPs and Ganoderma extract. iacA gene did not affect by test compounds. Overall, these findings revealed that nanoparticles and natural substances might represent the potential candidates to develop promising antibacterial agents, especially against Gram-positive bacteria.

Inspiration from cruzioseptin-1: membranolytic analogue with improved antibacterial properties

Peptide engineering has gained attraction as a source of new cationicity-enhanced analogues with high potential for the design of next-generation antibiotics. In this context, cruzioseptin-1 (CZS-1), a peptide identified from Cruziohyla calcarifer, is recognized for its antimicrobial potency. However, this amidated-peptide is moderately hemolytic. In order to reduce toxicity and increase antimicrobial potency, 3 peptide analogues based on cruzioseptin-1 were designed and evaluated. [K4K15]CZS-1, an analogue with increased cationicity and reduced hydrophobicity, showed antibacterial, antifungal and antiproliferative properties. In addition, [K4K15]CZS-1 is less hemolytic than CZS-1. The in silico and scanning electron microscopy analysis reveal that [K4K15]CZS-1 induces a membranolytic effect on bacteria. Overall, these results confirm the potential of CZS-1 as source of inspiration for design new selective antimicrobial analogues useful for development of new therapeutic agents.

Antibiotic discovery in the artificial intelligence era

As the global burden of antibiotic resistance continues to grow, creative approaches to antibiotic discovery are needed to accelerate the development of novel medicines. A rapidly progressing computational revolution-artificial intelligence-offers an optimistic path forward due to its ability to alleviate bottlenecks in the antibiotic discovery pipeline. In this review, we discuss how advancements in artificial intelligence are reinvigorating the adoption of past antibiotic discovery models-namely natural product exploration and small molecule screening. We then explore the application of contemporary machine learning approaches to emerging areas of antibiotic discovery, including antibacterial systems biology, drug combination development, antimicrobial peptide discovery, and mechanism of action prediction. Lastly, we propose a call to action for open access of high-quality screening datasets and interdisciplinary collaboration to accelerate the rate at which machine learning models can be trained and new antibiotic drugs can be developed.

Antimicrobial Peptides with Rigid Linkers against Gram-Negative Bacteria by Targeting Lipopolysaccharide

A series of hybrid peptides were designed by connecting an antimicrobial peptide Ce(1-8) with a lipopolysaccharide (LPS)-targeting peptide Lf(28-34) via different linkers. Antimicrobial experimental results indicated that linkers play an essential role in the anti-Gram-negative bacterial activity of the hybrid peptides. Among these hybrid peptides, peptide CL5 with dipeptide rigid linker LP exhibited excellent activity and selectivity against Gram-negative bacteria. The minimum inhibitory concentrations of CL5 against the tested Gram-negative bacteria were 4-32 μM, while the toxicity toward HEK-293 cells was relatively low. It was found that the interactions of the peptides with LPS were crucial for peptide activity against Gram-negative bacteria. Antimicrobial mechanistic studies showed that peptide CL5 contributed to the death of Gram-negative bacterial cells by disrupting the integrity of the bacterial membranes. This study revealed the importance of linker selection in the design of hybrid peptides and provides the basis for the further development of antimicrobial peptides.

An optimized antimicrobial peptide analog acts as an antibiotic adjuvant to reverse methicillin-resistant Staphylococcus aureus

The misuse of antibiotics in animal protein production has driven the emergence of a range of drug-resistant pathogens, which threaten existing public health security. Consequently, there is an urgent need to develop novel antimicrobials and new infection treatment options to address the challenges posed by the dramatic spread of antibiotic resistance. Piscidins, a class of fish-specific antimicrobial peptides (AMPs), are regarded as promising therapies for biomedical applications. Progress towards potential analogs from the piscidin family has been hampered by unenforceable structural optimization strategies. Here, we leverage a strategy of bioinformatics analysis combined with molecular dynamics (MD) simulation to identify specific functional hotspots in piscidins and rationally design related analogues. As expected, this approach yields a potent and non-toxic PIS-A-1 that can be used as an antibiotic adjuvant to reverse methicillin-resistant Staphylococcus aureus (MRSA) pathogens. Remarkably, the structural optimization scheme and application strategy proposed here will contribute richer therapeutic options for the safe production of animal protein.

Biologically Active Peptides from Venoms: Applications in Antibiotic Resistance, Cancer, and Beyond

Peptides are potential therapeutic alternatives against global diseases, such as antimicrobial-resistant infections and cancer. Venoms are a rich source of bioactive peptides that have evolved over time to act on specific targets of the prey. Peptides are one of the main components responsible for the biological activity and toxicity of venoms. South American organisms such as scorpions, snakes, and spiders are important producers of a myriad of peptides with different biological activities. In this review, we report the main venom-derived peptide families produced from South American organisms and their corresponding activities and biological targets.

Heterogeneous Structural Disturbance of Cell Membrane by Peptides with Modulated Hydrophobic Properties

Extensive effort has been devoted to developing new clinical therapies based on membrane-active peptides (MAPs). Previous models on the membrane action mechanisms of these peptides mostly focused on the MAP−membrane interactions in a local region, while the influence of the spatial heterogeneity of the MAP distribution on the membrane was much ignored. Herein, three types of natural peptide variants, AS4-1, AS4-5, and AS4-9, with similar amphiphilic α-helical structures but distinct hydrophobic degrees (AS4-1 < AS4-5 < AS4-9) and net charges (+9 vs. +7 vs. +5), were used to interact with a mixed phosphatidylcholine (PC) and phosphatidylglycerol (PG) membrane. A combination of giant unilamellar vesicle (GUV) leakage assays, atomic force microscopy (AFM) characterizations, and molecular dynamics (MD) simulations demonstrated the coexistence of multiple action mechanisms of peptides on a membrane, probably due to the spatially heterogeneous distribution of peptides on the membrane surface. Specifically, the most hydrophobic peptide (i.e., AS4-9) had the strongest membrane binding, perturbation, and permeabilization effects, leading to the formation of large peptide−lipid aggregates (10 ± 5 nm in height and 150 ± 50 nm in size), as well as continuous fragments and ridges on the supported membrane surface. The AS4-5 peptides, with a half-hydrophilic and half-hydrophobic structure, induced membrane lysis in addition to reconstruction. The most hydrophilic peptide AS4-1 only exhibited unstable binding on the supported membrane surface. These results demonstrate the heterogeneous structural disturbance of model cell membranes by amphiphilic α-helical peptides, which could be significantly strengthened by increasing the degree of hydrophobicity and/or local number density of peptides. This work provides support for the modulation of the membrane activity of MAPs by adjusting their hydrophobicity and local concentration.

Identification of 5-(Aryl/Heteroaryl)amino-4-quinolones as Potent Membrane-Disrupting Agents to Combat Antibiotic-Resistant Gram-Positive Bacteria

Nosocomial infections caused by resistant Gram-positive organisms are on the rise, presumably due to a combination of factors including prolonged hospital exposure, increased use of invasive procedures, and pervasive antibiotic therapy. Although antibiotic stewardship and infection control measures are helpful, newer agents against multidrug-resistant (MDR) Gram-positive bacteria are urgently needed. Here, we describe our efforts that led to the identification of 5-amino-4-quinolone 111 with exceptionally potent Gram-positive activity with minimum inhibitory concentrations (MICs) ≤0.06 μg/mL against numerous clinical isolates. Preliminary mechanism of action and resistance studies demonstrate that the 5-amino-4-quinolones are bacteriostatic, do not select for resistance, and selectively disrupt bacterial membranes. While the precise molecular mechanism has not been elucidated, the lead compound is nontoxic displaying a therapeutic index greater than 500, is devoid of hemolytic activity, and has attractive physicochemical properties (clog P = 3.8, molecular weight (MW) = 441) that warrant further investigation of this promising antibacterial scaffold for the treatment of Gram-positive infections.

Improvement of the Antibacterial Activity of Phage Lysin-Derived Peptide P87 through Maximization of Physicochemical Properties and Assessment of Its Therapeutic Potential

Phage lysins are a promising alternative to common antibiotic chemotherapy. However, they have been regarded as less effective against Gram-negative pathogens unless engineered, e.g., by fusing them to antimicrobial peptides (AMPs). AMPs themselves pose an alternative to antibiotics. In this work, AMP P87, previously derived from a phage lysin (Pae87) with a presumed nonenzymatic mode-of-action, was investigated to improve its antibacterial activity. Five modifications were designed to maximize the hydrophobic moment and net charge, producing the modified peptide P88, which was evaluated in terms of bactericidal activity, cytotoxicity, MICs or synergy with antibiotics. P88 had a better bactericidal performance than P87 (an average of 6.0 vs. 1.5 log-killing activity on Pseudomonas aeruginosa strains treated with 10 µM). This did not correlate with a dramatic increase in cytotoxicity as assayed on A549 cell cultures. P88 was active against a range of P. aeruginosa isolates, with no intrinsic resistance factors identified. Synergy with some antibiotics was observed in vitro, in complex media, and in a respiratory infection mouse model. Therefore, P88 can be a new addition to the therapeutic toolbox of alternative antimicrobials against Gram-negative pathogens as a sole therapeutic, a complement to antibiotics, or a part to engineer proteinaceous antimicrobials.

Novel Insights into Fungal Infections Prophylaxis and Treatment in Pediatric Patients with Cancer

Invasive fungal diseases (IFDs) are a relevant cause of morbidity and mortality in children with cancer. Their correct prevention and management impact patients’ outcomes. The aim of this review is to highlight the rationale and novel insights into antifungal prophylaxis and treatment in pediatric patients with oncological and hematological diseases. The literature analysis showed that IFDs represent a minority of cases in comparison to bacterial and viral infections, but their impact might be far more serious, especially when prolonged antifungal therapy or invasive surgical treatments are required to eradicate colonization. A personalized approach is recommended since pediatric patients with cancer often present with different complications and require tailored therapy. Moreover, while the Aspergillus infection rate does not seem to increase, in the near future, new therapeutic recommendations should be required in light of new epidemiological data on Candidemia due to resistant species. Finally, further studies on CAR-T treatment and other immunotherapies are needed in patients with unique needs and the risk of complications. Definitive guidelines on IFD treatment considering the evolving epidemiology of antifungal resistance, new therapeutic approaches in pediatric cancer, novel antifungal drugs and the importance of an appropriate antifungal stewardship are urgently needed.

Nanoparticles in association with antimicrobial peptides (NanoAMPs) as a promising combination for agriculture development

Antimicrobial peptides are small molecules, up to 10 kDa, present in all kingdoms of life, including in plants. Several studies report that these molecules have a broad spectrum of activity, including antibacterial, antifungal, antiviral, and insecticidal activity. Thus, they can be employed in agriculture as alternative tools for phytopathogen and pest control. However, the application of peptides in agriculture can present challenges, such as loss of activity due to degradation of these molecules, off-target effects, and others. In this context, nanotechnology can offer versatile structures, including metallic nanoparticles, liposomes, polymeric nanoparticles, nanofibers, and others, which might act both in protection and in release of AMPs. Several polymers and biomaterials can be employed for the development of nanostructures, such as inorganic metals, natural or synthetic lipids, synthetic and hybrid polymers, and others. This review addresses the versatility of NanoAMPs (Nanoparticles in association with antimicrobial peptides), and their potential applications in agribusiness, as an alternative for the control of phytopathogens in crops.

In silico identification of two peptides with antibacterial activity against multidrug-resistant Staphylococcus aureus

Here we report two antimicrobial peptides (AMPs), HG2 and HG4 identified from a rumen microbiome metagenomic dataset, with activity against multidrug-resistant (MDR) bacteria, especially methicillin-resistant Staphylococcus aureus (MRSA) strains, a major hospital and community-acquired pathogen. We employed the classifier model design to analyse, visualise, and interpret AMP activities. This approach allowed in silico discrimination of promising lead AMP candidates for experimental evaluation. The lead AMPs, HG2 and HG4, are fast-acting and show anti-biofilm and anti-inflammatory activities in vitro and demonstrated little toxicity to human primary cell lines. The peptides were effective in vivo within a Galleria mellonella model of MRSA USA300 infection. In terms of mechanism of action, HG2 and HG4 appear to interact with the cytoplasmic membrane of target cells and may inhibit other cellular processes, whilst preferentially binding to bacterial lipids over human cell lipids. Therefore, these AMPs may offer additional therapeutic templates for MDR bacterial infections.

Antimicrobial bioactive peptides from goat Milk proteins: In silico prediction and analysis

The main goal of this study was to assess the potential proteins of goat milk (i.e. α-s1-casein, α-s2-casein, β-casein, κ-casein, α-lactoglobulin and β-lactalbumin) as precursors of antimicrobial peptides (AMPs). Bioinformatics tools such as BIOPEP-UWM (enzyme action) were used for the in silico gastrointestinal digestion via a cocktail of pepsin, trypsin, and chymotrypsin A. The antimicrobial activity of peptides was predicted by using four algorithms, including Random Forest, Support Vector Machines, Artificial Neural Network and Discriminant Analysis on CAMPR3 online server, which works on Hidden Markov Models. Different online tools predicted the physiochemical properties, allergenicity, and toxicity of peptides as well. In silico gastrointestinal digestion simulation of proteins by enzymes cocktail yielded a total of 83 potential AMPs, with thirteen peptides being confident by all four algorithms. More AMPs were released from β-casein (21) than from β-lactoglobulin (16), α-s1-casein (15), α-s2-casein (12), κ-casein (11) and α-lactalbumin (9). A total of 17 peptides were cationic, and the majority of the peptides were extended AMPs. These peptides were released from α-s1-casein (SGK, IQK), α-s2-casein (SIR, AIH, TQPK), β-casein (GPVR, AVPQR, AIAR, GVPK, SQPK, PVPQK, IH, VPK), k-casein (AIPPK, QQR, IAK, TVPAK). All of the AMPs were anticipated to be non-toxic, and 54 of the 83 peptides were confirmed to be non-allergic, with the remaining 29 suspected of being allergenic and 31 to be predicted to have good water solubility. Further the molecular docking was used to evaluate the potent dihydropteroate synthase (DHPS) inhibitors. On the basis of ligand binding energy, 17 predicted AMPs were selected and then analyzed by AutoDock tools. Among the 17 AMPs, 3 AMPs were predicted as high-potent antimicrobial. Based on these findings, in silico investigations reveal that proteins of goat milk are a potential source of AMPs. These peptides can be synthesized and improved for use in the food sector. PRACTICAL APPLICATIONS: Goat milk is regarded as a high-quality milk protein source. According to this study, goat milk protein is a possible source of AMPs, and therefore, most important AMPs can be synthesized and developed for use in the food sector.

Sequential Properties Representation Scheme for Recurrent Neural Network-Based Prediction of Therapeutic Peptides

The discovery of therapeutic peptides is often accelerated by means of virtual screening supported by machine learning-based predictive models. The predictive performance of such models is sensitive to the choice of data and its representation scheme. While the peptide physicochemical and compositional representations fail to distinguish sequence permutations, the amino acid arrangement within the sequence lacks the important information contained in physicochemical, conformational, topological, and geometrical properties. In this paper, we propose a solution to the identified information gap by implementing a hybrid scheme that complements the best traits from both approaches with the aim of predicting antimicrobial and antiviral activities based on experimental data from DRAMP 2.0, AVPdb, and Uniprot data repositories. Using the Friedman test of statistical significance, we compared our hybrid, sequential properties approach to peptide properties, one-hot vector encoding, and word embedding schemes in the 10-fold cross-validation setting, with respect to the F1 score, Matthews correlation coefficient, geometric mean, recall, and precision evaluation metrics. Moreover, the sequence modeling neural network was employed to gain insight into the synergic effect of both properties- and amino acid order-based predictions. The results suggest that sequential properties significantly (P < 0.01) surpasses the aforementioned state-of-the-art representation schemes. This makes it a strong candidate for increasing the predictive power of screening methods based on machine learning, applicable to any category of peptides.

Deep generative models for peptide design

Computers can already be programmed for superhuman pattern recognition of images and text. For machines to discover novel molecules, they must first be trained to sort through the many characteristics of molecules and determine which properties should be retained, suppressed, or enhanced to optimize functions of interest. Machines need to be able to understand, read, write, and eventually create new molecules. Today, this creative process relies on deep generative models, which have gained popularity since powerful deep neural networks were introduced to generative model frameworks. In recent years, they have demonstrated excellent ability to model complex distribution of real-word data (e.g., images, audio, text, molecules, and biological sequences). Deep generative models can generate data beyond those provided in training samples, thus yielding an efficient and rapid tool for exploring the massive search space of high-dimensional data such as DNA/protein sequences and facilitating the design of biomolecules with desired functions. Here, we review the emerging field of deep generative models applied to peptide science. In particular, we discuss several popular deep generative model frameworks as well as their applications to generate peptides with various kinds of properties (e.g., antimicrobial, anticancer, cell penetration, etc). We conclude our review with a discussion of current limitations and future perspectives in this emerging field.