Machine Learning Prediction of Antimicrobial Peptides

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.

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

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

Immunomodulation in Non-traditional Therapies for Methicillin-resistant Staphylococcus aureus (MRSA) Management

The rise of methicillin-resistant Staphylococcus aureus (MRSA) poses a significant challenge in clinical settings due to its ability to evade conventional antibiotic treatments. This overview explores the potential of immunomodulatory strategies as alternative therapeutic approaches to combat MRSA infections. Traditional antibiotics are becoming less effective, necessitating innovative solutions that harness the body's immune system to enhance pathogen clearance. Recent advancements in immunotherapy, including the use of antimicrobial peptides, phage therapy, and mechanisms of immune cells, demonstrate promise in enhancing the body's ability to clear MRSA infections. However, the exact interactions between these therapies and immunomodulation are not fully understood, underscoring the need for further research. Hence, this review aims to provide a broad overview of the current understanding of non-traditional therapeutics and their impact on immune responses, which could lead to more effective MRSA treatment strategies. Additionally, combining immunomodulatory agents with existing antibiotics may improve outcomes, particularly for immunocompromised patients or those with chronic infections. As the landscape of antibiotic resistance evolves, the development of effective immunotherapeutic strategies could play a vital role in managing MRSA infections and reducing reliance on traditional antibiotics. Future research must focus on optimizing these approaches and validating their efficacy in diverse clinical populations to address the urgent need for effective MRSA management strategies.

Screening antimicrobial peptides and probiotics using multiple deep learning and directed evolution strategies

Owing to their limited accuracy and narrow applicability, current antimicrobial peptide (AMP) prediction models face obstacles in industrial application. To address these limitations, we developed and improved an AMP prediction model using Comparing and Optimizing Multiple DEep Learning (COMDEL) algorithms, coupled with high-throughput AMP screening method, finally reaching an accuracy of 94.8% in test and 88% in experiment verification, surpassing other state-of-the-art models. In conjunction with COMDEL, we employed the phage-assisted evolution method to screen Sortase in vivo and developed a cell-free AMP synthesis system in vitro, ultimately increasing AMPs yields to a range of 0.5-2.1 g/L within hours. Moreover, by multi-omics analysis using COMDEL, we identified Lactobacillus plantarum as the most promising candidate for AMP generation among 35 edible probiotics. Following this, we developed a microdroplet sorting approach and successfully screened three L. plantarum mutants, each showing a twofold increase in antimicrobial ability, underscoring their substantial industrial application values.

From Data to Decisions: Leveraging Artificial Intelligence and Machine Learning in Combating Antimicrobial Resistance - a Comprehensive Review

The emergence of drug-resistant bacteria poses a significant challenge to modern medicine. In response, Artificial Intelligence (AI) and Machine Learning (ML) algorithms have emerged as powerful tools for combating antimicrobial resistance (AMR). This review aims to explore the role of AI/ML in AMR management, with a focus on identifying pathogens, understanding resistance patterns, predicting treatment outcomes, and discovering new antibiotic agents. Recent advancements in AI/ML have enabled the efficient analysis of large datasets, facilitating the reliable prediction of AMR trends and treatment responses with minimal human intervention. ML algorithms can analyze genomic data to identify genetic markers associated with antibiotic resistance, enabling the development of targeted treatment strategies. Additionally, AI/ML techniques show promise in optimizing drug administration and developing alternatives to traditional antibiotics. By analyzing patient data and clinical outcomes, these technologies can assist healthcare providers in diagnosing infections, evaluating their severity, and selecting appropriate antimicrobial therapies. While integration of AI/ML in clinical settings is still in its infancy, advancements in data quality and algorithm development suggest that widespread clinical adoption is forthcoming. In conclusion, AI/ML holds significant promise for improving AMR management and treatment outcome.

Hybrid transformer-CNN model for accurate prediction of peptide hemolytic potential

Hemolysis is a crucial factor in various biomedical and pharmaceutical contexts, driving our interest in developing advanced computational techniques for precise prediction. Our proposed approach takes advantage of the unique capabilities of convolutional neural networks (CNNs) and transformers to detect complex patterns inherent in the data. The integration of CNN and transformers' attention mechanisms allows for the extraction of relevant information, leading to accurate predictions of hemolytic potential. The proposed method was trained on three distinct data sets of peptide sequences known as recurrent neural network-hemolytic (RNN-Hem), Hlppredfuse, and Combined. Our computational results demonstrated the superior efficacy of our models compared to existing methods. The proposed approach demonstrated impressive Matthews correlation coefficients of 0.5962, 0.9111, and 0.7788 respectively, indicating its effectiveness in predicting hemolytic activity. With its potential to guide experimental efforts in peptide design and drug development, this method holds great promise for practical applications. Integrating CNNs and transformers proves to be a powerful tool in the fields of bioinformatics and therapeutic research, highlighting their potential to drive advancement in this area.

Development of a defibrinated human blood hemolysis assay for rapid testing of hemolytic activity compared to computational prediction

Cytotoxicity studies determining hemolytic properties of antimicrobial peptides or other drugs are an important step in the development of novel therapeutics for clinical use. Hemolysis is an affordable, accessible, and rapid method for initial assessment of cellular toxicity for all drugs under development. However, variability in species of red blood cells and protocols used may result in significant differences in results. AMPs generally possess higher selectivity for bacterial cells but can have toxicity against host cells at high concentrations. Knowing the hemolytic activity of the peptides we are developing contributes to our understanding of their potential toxicity. Computational approaches for predicting hemolytic activity of AMPs exist and were tested head-to-head with our experimental results.

RESULTS

Starting with an observation of high hemolytic activity of LL-37 peptide against human red blood cells that were collected in EDTA, we explored alternative approaches to develop a more robust, accurate and simple hemolysis assay using defibrinated human blood. We found significant differences between the sensitivity of defibrinated red blood cells and EDTA treated red blood cells.

SIGNIFICANCE

Accurately determining the hemolytic activity using human red blood cells will allow for a more robust calculation of the therapeutic index of our potential antimicrobial compounds, a critical measure in their pre-clinical development.

CONCLUSION

We introduce a standardized, more accurate protocol for assessing hemolytic activity using defibrinated human red blood cells. This approach, facilitated by the increased commercial availability of de-identified human blood and defibrination methods, offers a robust tool for evaluating toxicity of emerging drug compounds, especially AMPs.

Structure-aware machine learning strategies for antimicrobial peptide discovery

Machine learning models are revolutionizing our approaches to discovering and designing bioactive peptides. These models often need protein structure awareness, as they heavily rely on sequential data. The models excel at identifying sequences of a particular biological nature or activity, but they frequently fail to comprehend their intricate mechanism(s) of action. To solve two problems at once, we studied the mechanisms of action and structural landscape of antimicrobial peptides as (i) membrane-disrupting peptides, (ii) membrane-penetrating peptides, and (iii) protein-binding peptides. By analyzing critical features such as dipeptides and physicochemical descriptors, we developed models with high accuracy (86-88%) in predicting these categories. However, our initial models (1.0 and 2.0) exhibited a bias towards α-helical and coiled structures, influencing predictions. To address this structural bias, we implemented subset selection and data reduction strategies. The former gave three structure-specific models for peptides likely to fold into α-helices (models 1.1 and 2.1), coils (1.3 and 2.3), or mixed structures (1.4 and 2.4). The latter depleted over-represented structures, leading to structure-agnostic predictors 1.5 and 2.5. Additionally, our research highlights the sensitivity of important features to different structure classes across models.

Arginine and tryptophan-rich dendritic antimicrobial peptides that disrupt membranes for bacterial infection in vivo

The potent antibacterial activity and low resistance of antimicrobial peptides (AMPs) render them potential candidates for treating multidrug-resistant bacterial infections. Herein, a minimalist design strategy was proposed employing the "golden partner" combination of arginine (R) and tryptophan (W), along with a dendritic structure to design AMPs. By extension, the α/ε-amino group and the carboxyl group of lysine (K) were utilized to link R and W, forming dendritic peptide templates αRn(εRn)KWm-NH2 and αWn(εWn)KRm-NH2, respectively. The corresponding linear peptide templates R2nKWm-NH2 and W2nKRm-NH2 were used as controls. Their physicochemical properties, activity, toxicity, and stability were compared. Among these new peptides, the dendritic peptide R2(R2)KW4 was screened as a prospective candidate owing to its preferable antibacterial properties, biocompatibility, and stability. Additionally, R2(R2)KW4 not only effectively restrained the progression of antibiotic resistance, but also demonstrated synergistic utility when combined with conventional antibiotics due to its unique membrane-disruptive mechanism. Furthermore, R2(R2)KW4 possessed low toxicity (LD50 = 109.31 mg/kg) in vivo, while efficiently clearing E. coli in pulmonary-infected mice. In conclusion, R2(R2)KW4 has the potential to become an antimicrobial regent or adjuvant, and the minimalist design strategy of dendritic peptides provides innovative and encouraging thoughts in designing AMPs.

SAMP: Identifying Antimicrobial Peptides by an Ensemble Learning Model Based on Proportionalized Split Amino Acid Composition

It is projected that 10 million deaths could be attributed to drug-resistant bacteria infections in 2050. To address this concern, identifying new-generation antibiotics is an effective way. Antimicrobial peptides (AMPs), a class of innate immune effectors, have received significant attention for their capacity to eliminate drug-resistant pathogens, including viruses, bacteria, and fungi. Recent years have witnessed widespread applications of computational methods especially machine learning (ML) and deep learning (DL) for discovering AMPs. However, existing methods only use features including compositional, physiochemical, and structural properties of peptides, which cannot fully capture sequence information from AMPs. Here, we present SAMP, an ensemble random projection (RP) based computational model that leverages a new type of features called Proportionalized Split Amino Acid Composition (PSAAC) in addition to conventional sequence-based features for AMP prediction. With this new feature set, SAMP captures the residue patterns like sorting signals at around both the N-terminus and the C-terminus, while also retaining the sequence order information from the middle peptide fragments. Benchmarking tests on different balanced and imbalanced datasets demonstrate that SAMP consistently outperforms existing state-of-the-art methods, such as iAMPpred and AMPScanner V2, in terms of accuracy, MCC, G-measure and F1-score. In addition, by leveraging an ensemble RP architecture, SAMP is scalable to processing large-scale AMP identification with further performance improvement, compared to those models without RP. To facilitate the use of SAMP, we have developed a Python package freely available at https://github.com/wan-mlab/SAMP .

Tackling the Antimicrobial Resistance "Pandemic" with Machine Learning Tools: A Summary of Available Evidence

Antimicrobial resistance is recognised as one of the top threats healthcare is bound to face in the future. There have been various attempts to preserve the efficacy of existing antimicrobials, develop new and efficient antimicrobials, manage infections with multi-drug resistant strains, and improve patient outcomes, resulting in a growing mass of routinely available data, including electronic health records and microbiological information that can be employed to develop individualised antimicrobial stewardship. Machine learning methods have been developed to predict antimicrobial resistance from whole-genome sequencing data, forecast medication susceptibility, recognise epidemic patterns for surveillance purposes, or propose new antibacterial treatments and accelerate scientific discovery. Unfortunately, there is an evident gap between the number of machine learning applications in science and the effective implementation of these systems. This narrative review highlights some of the outstanding opportunities that machine learning offers when applied in research related to antimicrobial resistance. In the future, machine learning tools may prove to be superbugs' kryptonite. This review aims to provide an overview of available publications to aid researchers that are looking to expand their work with new approaches and to acquaint them with the current application of machine learning techniques in this field.

AESIS-1, a Rheumatoid Arthritis Therapeutic Peptide, Accelerates Wound Healing by Promoting Fibroblast Migration in a CXCR2-Dependent Manner

In patients with autoimmune disorders such as rheumatoid arthritis (RA), delayed wound healing is often observed. Timely and effective wound healing is a crucial determinant of a patient's quality of life, and novel materials for skin wound repair, such as bioactive peptides, are continuously being studied and developed. One such bioactive peptide, AESIS-1, has been studied for its well-established anti-rheumatoid arthritis properties. In this study, we attempted to use the anti-RA material AESIS-1 as a therapeutic wound-healing agent based on disease-modifying antirheumatic drugs (DMARDs), which can help restore prompt wound healing. The efficacy of AESIS-1 in wound healing was assessed using a full-thickness excision model in diabetic mice; this is a well-established model for studying chronic wound repair. Initial observations revealed that mice treated with AESIS-1 exhibited significantly advanced wound repair compared with the control group. In vitro studies revealed that AESIS-1 increased the migration activity of human dermal fibroblasts (HDFs) without affecting proliferative activity. Moreover, increased HDF cell migration is mediated by upregulating chemokine receptor expression, such as that of CXC chemokine receptor 2 (CXCR2). The upregulation of CXCR2 through AESIS-1 treatment enhanced the chemotactic reactivity to CXCR2 ligands, including CXC motif ligand 8 (CXCL8). AESIS-1 directly activates the ERK and p38 mitogen-activated protein kinase (MAPK) signaling cascades, which regulate the migration and expression of CXCR2 in fibroblasts. Our results suggest that the AESIS-1 peptide is a strong wound-healing substance that increases the movement of fibroblasts and the expression of CXCR2 by turning on the ERK and p38 MAPK signaling cascades.

AGRAMP: machine learning models for predicting antimicrobial peptides against phytopathogenic bacteria

Introduction

Antimicrobial peptides (AMPs) are promising alternatives to traditional antibiotics for combating plant pathogenic bacteria in agriculture and the environment. However, identifying potent AMPs through laborious experimental assays is resource-intensive and time-consuming. To address these limitations, this study presents a bioinformatics approach utilizing machine learning models for predicting and selecting AMPs active against plant pathogenic bacteria.

Methods

N-gram representations of peptide sequences with 3-letter and 9-letter reduced amino acid alphabets were used to capture the sequence patterns and motifs that contribute to the antimicrobial activity of AMPs. A 5-fold cross-validation technique was used to train the machine learning models and to evaluate their predictive accuracy and robustness.

Results

The models were applied to predict putative AMPs encoded by intergenic regions and small open reading frames (ORFs) of the citrus genome. Approximately 7% of the 10,000-peptide dataset from the intergenic region and 7% of the 685,924-peptide dataset from the whole genome were predicted as probable AMPs. The prediction accuracy of the reported models range from 0.72 to 0.91. A subset of the predicted AMPs was selected for experimental test against Spiroplasma citri, the causative agent of citrus stubborn disease. The experimental results confirm the antimicrobial activity of the selected AMPs against the target bacterium, demonstrating the predictive capability of the machine learning models.

Discussion

Hydrophobic amino acid residues and positively charged amino acid residues are among the key features in predicting AMPs by the Random Forest Algorithm. Aggregation propensity appears to be correlated with the effectiveness of the AMPs. The described models would contribute to the development of effective AMP-based strategies for plant disease management in agricultural and environmental settings. To facilitate broader accessibility, our model is publicly available on the AGRAMP (Agricultural Ngrams Antimicrobial Peptides) server.

A novel bioinformatic method for the identification of antimicrobial peptides in metagenomes

AIMS

This study aimed to develop a new bioinformatic approach for the identification of novel antimicrobial peptides (AMPs), which did not depend on sequence similarity to known AMPs held within databases, but on structural mimicry of another antimicrobial compound, in this case an ultrashort, synthetic, cationic lipopeptide (C12-OOWW-NH2).

METHODS AND RESULTS

When applied to a collection of metagenomic datasets, our outlined bioinformatic method successfully identified several short (8-10aa) functional AMPs, the activity of which was verified via disk diffusion and minimum inhibitory concentration assays against a panel of 12 bacterial strains. Some peptides had activity comparable to, or in some cases, greater than, those from published studies that identified AMPs using more conventional methods. We also explored the effects of modifications, including extension of the peptides, observing an activity peak at 9-12aa. Additionally, the inclusion of a C-terminal amide enhanced activity in most cases. Our most promising candidate (named PB2-10aa-NH2) was thermally stable, lipid-soluble, and possessed synergistic activity with ethanol but not with a conventional antibiotic (streptomycin).

CONCLUSIONS

While several bioinformatic methods exist to predict AMPs, the approach outlined here is much simpler and can be used to quickly scan huge datasets. Searching for peptide sequences bearing structural similarity to other antimicrobial compounds may present a further opportunity to identify novel AMPs with clinical relevance, and provide a meaningful contribution to the pressing global issue of AMR.

AntiBP3: A Method for Predicting Antibacterial Peptides against Gram-Positive/Negative/Variable Bacteria

Most of the existing methods developed for predicting antibacterial peptides (ABPs) are mostly designed to target either gram-positive or gram-negative bacteria. In this study, we describe a method that allows us to predict ABPs against gram-positive, gram-negative, and gram-variable bacteria. Firstly, we developed an alignment-based approach using BLAST to identify ABPs and achieved poor sensitivity. Secondly, we employed a motif-based approach to predict ABPs and obtained high precision with low sensitivity. To address the issue of poor sensitivity, we developed alignment-free methods for predicting ABPs using machine/deep learning techniques. In the case of alignment-free methods, we utilized a wide range of peptide features that include different types of composition, binary profiles of terminal residues, and fastText word embedding. In this study, a five-fold cross-validation technique has been used to build machine/deep learning models on training datasets. These models were evaluated on an independent dataset with no common peptide between training and independent datasets. Our machine learning-based model developed using the amino acid binary profile of terminal residues achieved maximum AUC 0.93, 0.98, and 0.94 for gram-positive, gram-negative, and gram-variable bacteria, respectively, on an independent dataset. Our method performs better than existing methods when compared with existing approaches on an independent dataset. A user-friendly web server, standalone package and pip package have been developed to facilitate peptide-based therapeutics.

Artificial intelligence and machine learning in clinical pharmacological research

BACKGROUND

Clinical pharmacology research has always involved computational analysis. With the abundance of drug-related data available, the integration of artificial intelligence (AI) and machine learning (ML) methods has emerged as a promising way to enhance clinical pharmacology research.

METHODS

Based on an accepted definition of clinical pharmacology as a field of research dealing with all aspects of drug-human interactions, the analysis included publications from institutes specializing in clinical pharmacology. Research topics and the most used machine learning methods in clinical pharmacology were retrieved from the PubMed database and summarized.

RESULTS

ML was identified in 674 publications attributed to clinical pharmacology research, with a significant increase in publication activity over the last decade. Notable research topics addressed by ML/AI included Covid-19-related clinical pharmacology research, clinical neuropharmacology, drug safety and risk assessment, clinical pharmacology related to cancer research, and antimicrobial and antiviral research unrelated to Covid-19. In terms of ML methods, neural networks, random forests, and support vector machines were frequently mentioned in the abstracts of the retrieved papers.

CONCLUSIONS

ML, and AI in general, is increasingly being used in various research areas within clinical pharmacology. This report presents specific examples of applications and highlights the most used ML methods.

A systematical review on antimicrobial peptides and their food applications

Food safety issues are a major concern in food processing and packaging industries. Food spoilage is caused by microbial contamination, where antimicrobial peptides (APs) provide solutions by eliminating microorganisms. APs such as nisin have been successfully and commonly used in food processing and preservation. Here, we discuss all aspects of the functionalization of APs in food applications. We briefly review the natural sources of APs and their native functions. Recombinant expression of APs in microorganisms and their yields are described. The molecular mechanisms of AP antibacterial action are explained, and this knowledge can further benefit the design of functional APs. We highlight current utilities and challenges for the application of APs in the food industry, and address rational methods for AP design that may overcome current limitations.

ACP-BC: A Model for Accurate Identification of Anticancer Peptides Based on Fusion Features of Bidirectional Long Short-Term Memory and Chemically Derived Information

Anticancer peptides (ACPs) have been proven to possess potent anticancer activities. Although computational methods have emerged for rapid ACPs identification, their accuracy still needs improvement. In this study, we propose a model called ACP-BC, a three-channel end-to-end model that utilizes various combinations of data augmentation techniques. In the first channel, features are extracted from the raw sequence using a bidirectional long short-term memory network. In the second channel, the entire sequence is converted into a chemical molecular formula, which is further simplified using Simplified Molecular Input Line Entry System notation to obtain deep abstract features through a bidirectional encoder representation transformer (BERT). In the third channel, we manually selected four effective features according to dipeptide composition, binary profile feature, k-mer sparse matrix, and pseudo amino acid composition. Notably, the application of chemical BERT in predicting ACPs is novel and successfully integrated into our model. To validate the performance of our model, we selected two benchmark datasets, ACPs740 and ACPs240. ACP-BC achieved prediction accuracy with 87% and 90% on these two datasets, respectively, representing improvements of 1.3% and 7% compared to existing state-of-the-art methods on these datasets. Therefore, systematic comparative experiments have shown that the ACP-BC can effectively identify anticancer peptides.

The antimicrobial peptide database is 20 years old: Recent developments and future directions

In 2023, the Antimicrobial Peptide Database (currently available at https://aps.unmc.edu) is 20-years-old. The timeline for the APD expansion in peptide entries, classification methods, search functions, post-translational modifications, binding targets, and mechanisms of action of antimicrobial peptides (AMPs) has been summarized in our previous Protein Science paper. This article highlights new database additions and findings. To facilitate antimicrobial development to combat drug-resistant pathogens, the APD has been re-annotating the data for antibacterial activity (active, inactive, and uncertain), toxicity (hemolytic and nonhemolytic AMPs), and salt tolerance (salt sensitive and insensitive). Comparison of the respective desired and undesired AMP groups produces new knowledge for peptide design. Our unification of AMPs from the six life kingdoms into "natural AMPs" enabled the first comparison with globular or transmembrane proteins. Due to the dominance of amphipathic helical and disulfide-linked peptides, cysteine, glycine, and lysine in natural AMPs are much more abundant than those in globular proteins. To include peptides predicted by machine learning, a new "predicted" group has been created. Remarkably, the averaged amino acid composition of predicted peptides is located between the lower bound of natural AMPs and the upper bound of synthetic peptides. Synthetic peptides in the current APD, with the highest cationic and hydrophobic amino acid percentages, are mostly designed with varying degrees of optimization. Hence, natural AMPs accumulated in the APD over 20 years have laid the foundation for machine learning prediction. We discuss future directions for peptide discovery. It is anticipated that the APD will continue to play a role in research and education.

Drug discovery efforts at George Mason University

With over 39,000 students, and research expenditures in excess of $200 million, George Mason University (GMU) is the largest R1 (Carnegie Classification of very high research activity) university in Virginia. Mason scientists have been involved in the discovery and development of novel diagnostics and therapeutics in areas as diverse as infectious diseases and cancer. Below are highlights of the efforts being led by Mason researchers in the drug discovery arena. To enable targeted cellular delivery, and non-biomedical applications, Veneziano and colleagues have developed a synthesis strategy that enables the design of self-assembling DNA nanoparticles (DNA origami) with prescribed shape and size in the 10 to 100 nm range. The nanoparticles can be loaded with molecules of interest such as drugs, proteins and peptides, and are a promising new addition to the drug delivery platforms currently in use. The investigators also recently used the DNA origami nanoparticles to fine tune the spatial presentation of immunogens to study the impact on B cell activation. These studies are an important step towards the rational design of vaccines for a variety of infectious agents. To elucidate the parameters for optimizing the delivery efficiency of lipid nanoparticles (LNPs), Buschmann, Paige and colleagues have devised methods for predicting and experimentally validating the pKa of LNPs based on the structure of the ionizable lipids used to formulate the LNPs. These studies may pave the way for the development of new LNP delivery vehicles that have reduced systemic distribution and improved endosomal release of their cargo post administration. To better understand protein-protein interactions and identify potential drug targets that disrupt such interactions, Luchini and colleagues have developed a methodology that identifies contact points between proteins using small molecule dyes. The dye molecules noncovalently bind to the accessible surfaces of a protein complex with very high affinity, but are excluded from contact regions. When the complex is denatured and digested with trypsin, the exposed regions covered by the dye do not get cleaved by the enzyme, whereas the contact points are digested. The resulting fragments can then be identified using mass spectrometry. The data generated can serve as the basis for designing small molecules and peptides that can disrupt the formation of protein complexes involved in disease processes. For example, using peptides based on the interleukin 1 receptor accessory protein (IL-1RAcP), Luchini, Liotta, Paige and colleagues disrupted the formation of IL-1/IL-R/IL-1RAcP complex and demonstrated that the inhibition of complex formation reduced the inflammatory response to IL-1B. Working on the discovery of novel antimicrobial agents, Bishop, van Hoek and colleagues have discovered a number of antimicrobial peptides from reptiles and other species. DRGN-1, is a synthetic peptide based on a histone H1-derived peptide that they had identified from Komodo Dragon plasma. DRGN-1 was shown to disrupt bacterial biofilms and promote wound healing in an animal model. The peptide, along with others, is being developed and tested in preclinical studies. Other research by van Hoek and colleagues focuses on in silico antimicrobial peptide discovery, screening of small molecules for antibacterial properties, as well as assessment of diffusible signal factors (DFS) as future therapeutics. The above examples provide insight into the cutting-edge studies undertaken by GMU scientists to develop novel methodologies and platform technologies important to drug discovery.

Tuna trimmings (Thunnas albacares) hydrolysate alleviates immune stress and intestinal mucosal injury during chemotherapy on mice and identification of potentially active peptides

In this study, Tuna trimmings (Thunnas albacares) protein hydrolysate (TPA) was produced by alcalase. The anti-tumor synergistic effect and intestinal mucosa protective effect of TPA on S180 tumor-bearing mice treated with 5-fluorouracil (5-FU) chemotherapy were investigated. The results showed that TPA can enhance the anti-tumor effect of 5-FU chemotherapy, as evident by a significant reduction in tumor volume observed in the medium and high dose TPA+5-FU groups compared to the 5-FU group (p < 0.001). Moreover, TPA significantly elevated the content of total protein and albumin in all TPA dose groups (p < 0.01, p < 0.001), indicating its ability to regulate the nutritional status of the mice. Furthermore, histopathological studies revealed a significant increase in the height of small intestinal villi, crypt depth, mucosal thickness, and villi area in the TPA+5-FU groups compared to the 5-FU group (p < 0.05), suggesting that TPA has a protective effect on the intestinal mucosa. Amino acid analysis revealed that TPA had a total amino acid content of 66.30 g/100 g, with essential amino acids accounting for 30.36 g/100 g. Peptide molecular weight distribution analysis of TPA indicated that peptides ranging from 0.25 to 1 kDa constituted 64.54%. LC-MS/MS analysis identified 109 peptide sequences, which were predicted to possess anti-cancer and anti-inflammatory activities through database prediction. Therefore, TPA has the potential to enhance the antitumor effects of 5-FU, mitigate immune depression and intestinal mucosal damage induced by 5-FU. Thus, TPA could be serve as an adjuvant nutritional support for malnourished patients undergoing chemotherapy.

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.

Thinking on the Construction of Antimicrobial Peptide Databases: Powerful Tools for the Molecular Design and Screening

With the accelerating growth of antimicrobial resistance (AMR), there is an urgent need for new antimicrobial agents with low or no AMR. Antimicrobial peptides (AMPs) have been extensively studied as alternatives to antibiotics (ATAs). Coupled with the new generation of high-throughput technology for AMP mining, the number of derivatives has increased dramatically, but manual running is time-consuming and laborious. Therefore, it is necessary to establish databases that combine computer algorithms to summarize, analyze, and design new AMPs. A number of AMP databases have already been established, such as the Antimicrobial Peptides Database (APD), the Collection of Antimicrobial Peptides (CAMP), the Database of Antimicrobial Activity and Structure of Peptides (DBAASP), and the Database of Antimicrobial Peptides (dbAMPs). These four AMP databases are comprehensive and are widely used. This review aims to cover the construction, evolution, characteristic function, prediction, and design of these four AMP databases. It also offers ideas for the improvement and application of these databases based on merging the various advantages of these four peptide libraries. This review promotes research and development into new AMPs and lays their foundation in the fields of druggability and clinical precision treatment.

PTPAMP: prediction tool for plant-derived antimicrobial peptides

The emergence of antimicrobial peptides (AMPs) as a potential alternative to conventional antibiotics has led to the development of efficient computational methods for predicting AMPs. Among all organisms, the presence of multiple genes encoding AMPs in plants demands the development of a plant-based prediction tool. To this end, we developed models based on multiple peptide features like amino acid composition, dipeptide composition, and physicochemical attributes for predicting plant-derived AMPs. The selected compositional models are integrated into a web server termed PTPAMP. The designed web server is capable of classifying a query peptide sequence into four functional activities, i.e., antimicrobial (AMP), antibacterial (ABP), antifungal (AFP), and antiviral (AVP). Our models achieved an average area under the curve of 0.95, 0.91, 0.85, and 0.88 for AMP, ABP, AFP, and AVP, respectively, on benchmark datasets, which were ~ 6.75% higher than the state-of-the-art methods. Moreover, our analysis indicates the abundance of cysteine residues in plant-derived AMPs and the distribution of other residues like G, S, K, and R, which differ as per the peptide structural family. Finally, we have developed a user-friendly web server, available at the URL: http://www.nipgr.ac.in/PTPAMP/ . We expect the substantial input of this predictor for high-throughput identification of plant-derived AMPs followed by additional insights into their functions.

Hydrophobic diversification is the key to simultaneously increased antifungal activity and decreased cytotoxicity of two ab initio designed peptides

The fact that some antimicrobial peptides have been utilized clinically and as food preservatives stimulated the efforts in search of new candidates. In our previous studies, we succeeded in designing potent peptides against methicillin-resistant Staphylococcus aureus (MRSA), severe acute respiratory syndrome coronavirus 2 (SARS-Cov-2), and Ebola viruses based on the database filtering technology. The designed peptides were proved highly potent. However, this ab initio method has not been utilized to design antifungal peptides. This study report two novel antifungal peptides with 21 and 15 amino acids designed by more effectively extracting the most probable parameters from ∼1200 antifungal peptides in the antimicrobial peptide database (APD). Subsequent hydrophobic diversification led to two peptide variants with enhanced activity against four fungal strains but reduced cytotoxicity to four mammalian cell lines. DFTAFP-1A (KWSGAAAKKLKSLLSGLGKLL) and DFTAFP-2A (KWSGLLLKLGAASKL) retained activity against Zygosaccharomyces bailii at pH 5.6 and 6.3 or after autoclave. The peptides could permeabilize fungal membranes and adopted helical conformations in membrane mimetic micelles. Collectively, this study demonstrated not only the successful design of two novel antifungal peptides based on the APD database but also optimization of desired peptide properties. This improved database approach may be utilized to design useful peptides to combat other drug-resistant pathogens as well.

Linearized teixobactin is inactive and after sequence enhancement, kills methicillin-resistant Staphylococcus aureus via a different mechanism

Staphylococcus aureus is a highly adaptable pathogen that can rapidly develop resistance to conventional antibiotics such as penicillin. Recently, teixobactin was discovered from uncultivated soil bacteria by using the i-chip technology. This depsipeptide forms an ester bond between the backbone C-terminal isoleucine carboxylic acid and the hydroxyl group of threonine at position 8. Also, it contains multiple nonstandard amino acids, making it costly to synthesize. This study reports new peptides designed by linearizing teixobactin. After linearization and conversion to normal amino acids, teixobactin lost its antibacterial activity. Using this inactive template, a series of peptides were designed via hydrophobic patching and residue replacements. Three out of the five peptides were active. YZ105, only active against Gram-positive bacteria, however, showed the highest cell selectivity index. Different from teixobactin, which inhibits cell wall synthesis, YZ105 targeted the membranes of methicillin-resistant S. aureus (MRSA) based on kinetic killing, membrane permeation, depolarization, and scanning electron microscopy studies. Moreover, YZ105 could kill nafcillin-resistant MRSA, Staphylococcal clinical strains, and disrupted preformed biofilms. Taken together, YZ105, with a simpler sequence, is a promising lead for developing novel anti-MRSA agents.

Improved Database Filtering Technology Enables More Efficient Ab Initio Design of Potent Peptides against Ebola Viruses

The rapid mutations of viruses such as SARS-CoV-2 require vaccine updates and the development of novel antiviral drugs. This article presents an improved database filtering technology for a more effective design of novel antiviral agents. Different from the previous approach, where the most probable parameters were obtained stepwise from the antimicrobial peptide database, we found it possible to accelerate the design process by deriving multiple parameters in a single step during the peptide amino acid analysis. The resulting peptide DFTavP1 displays the ability to inhibit Ebola virus. A deviation from the most probable peptide parameters reduces antiviral activity. The designed peptides appear to block viral entry. In addition, the amino acid signature provides a clue to peptide engineering to gain cell selectivity. Like human cathelicidin LL-37, our engineered peptide DDIP1 inhibits both Ebola and SARS-CoV-2 viruses. These peptides, with broad antiviral activity, may selectively disrupt viral envelopes and offer the lasting efficacy required to treat various RNA viruses, including their emerging mutants.