MultiPep: a hierarchical deep learning approach for multi-label classification of peptide bioactivities

Structural and functional analyses of nematode-derived antimicrobial peptides support the occurrence of direct mechanisms of worm-microbiota interactions

The complex relationships between gastrointestinal (GI) nematodes and the host gut microbiota have been implicated in key aspects of helminth disease and infection outcomes. Nevertheless, the direct and indirect mechanisms governing these interactions are, thus far, largely unknown. In this proof-of-concept study, we demonstrate that the excretory-secretory products (ESPs) and extracellular vesicles (EVs) of key GI nematodes contain peptides that, when recombinantly expressed, exert antimicrobial activity in vitro against Bacillus subtilis. In particular, using time-lapse microfluidics microscopy, we demonstrate that exposure of B. subtilis to a recombinant saposin-domain containing peptide from the 'brown stomach worm', Teladorsagia circumcincta, and a metridin-like ShK toxin from the 'barber's pole worm', Haemonchus contortus, results in cell lysis and significantly reduced growth rates. Data from this study support the hypothesis that GI nematodes may modulate the composition of the vertebrate gut microbiota directly via the secretion of antimicrobial peptides, and pave the way for future investigations aimed at deciphering the impact of such changes on the pathophysiology of GI helminth infection and disease.

Integrating a Multi-label Deep Learning Approach with Protein Information to Compare Bioactive Peptides in Brain and Plasma

Peptide therapeutics is gaining momentum. Advances in the field of peptidomics have enabled researchers to harvest vital information from various organisms and tissue types concerning peptide existence, expression and function. The development of mass spectrometry techniques for high-throughput peptide quantitation has paved the way for the identification and discovery of numerous known and novel peptides. Though much has been achieved, scientists are still facing difficulties when it comes to reducing the search space of the large mass spectrometry-generated peptidomics datasets and focusing on the subset of functionally relevant peptides. Moreover, there is currently no straightforward way to analytically compare the distributions of bioactive peptides in distinct biological samples, which may reveal much useful information when seeking to characterize tissue- or fluid-specific peptidomes. In this chapter, we demonstrate how to identify, rank, and compare predicted bioactive peptides and bioactivity distributions from extensive peptidomics datasets. To aid this task, we utilize MultiPep, a multi-label deep learning approach designed for classifying peptide bioactivities, to identify bioactive peptides. The predicted bioactivities are synergistically combined with protein information from the UniProt database, which assist in navigating through the jungle of putative therapeutic peptides and relevant peptide leads.

Multi-label classification and features investigation of antimicrobial peptides with various functional classes

The challenge of drug-resistant bacteria to global public health has led to increased attention on antimicrobial peptides (AMPs) as a targeted therapeutic alternative with a lower risk of resistance. However, high production costs and limitations in functional class prediction have hindered progress in this field. In this study, we used multi-label classifiers with binary relevance and algorithm adaptation techniques to predict different functions of AMPs across a wide range of pathogen categories, including bacteria, mammalian cells, fungi, viruses, and cancer cells. Our classifiers attained promising AUC scores varying from 0.8492 to 0.9126 on independent testing data. Forward feature selection identified sequence order and charge as critical, with specific amino acids (C and E) as discriminative. These findings provide valuable insights for the design of antimicrobial peptides (AMPs) with multiple functionalities, thus contributing to the broader effort to combat drug-resistant pathogens.

Recent Progress in the Discovery and Design of Antimicrobial Peptides Using Traditional Machine Learning and Deep Learning

Antimicrobial resistance has become a critical global health problem due to the abuse of conventional antibiotics and the rise of multi-drug-resistant microbes. Antimicrobial peptides (AMPs) are a group of natural peptides that show promise as next-generation antibiotics due to their low toxicity to the host, broad spectrum of biological activity, including antibacterial, antifungal, antiviral, and anti-parasitic activities, and great therapeutic potential, such as anticancer, anti-inflammatory, etc. Most importantly, AMPs kill bacteria by damaging cell membranes using multiple mechanisms of action rather than targeting a single molecule or pathway, making it difficult for bacterial drug resistance to develop. However, experimental approaches used to discover and design new AMPs are very expensive and time-consuming. In recent years, there has been considerable interest in using in silico methods, including traditional machine learning (ML) and deep learning (DL) approaches, to drug discovery. While there are a few papers summarizing computational AMP prediction methods, none of them focused on DL methods. In this review, we aim to survey the latest AMP prediction methods achieved by DL approaches. First, the biology background of AMP is introduced, then various feature encoding methods used to represent the features of peptide sequences are presented. We explain the most popular DL techniques and highlight the recent works based on them to classify AMPs and design novel peptide sequences. Finally, we discuss the limitations and challenges of AMP prediction.

Excretory-secretory products from the brown stomach worm, Teladorsagia circumcincta, exert antimicrobial activity in in vitro growth assays

BACKGROUND

Over the past decade, evidence has emerged of the ability of gastrointestinal (GI) helminth parasites to alter the composition of the host gut microbiome; however, the mechanism(s) underpinning such interactions remain unclear. In the current study, we (i) undertake proteomic analyses of the excretory-secretory products (ESPs), including secreted extracellular vesicles (EVs), of the 'brown stomach worm' Teladorsagia circumcincta, one of the major agents causing parasite gastroenteritis in temperate areas worldwide; (ii) conduct bioinformatic analyses to identify and characterise antimicrobial peptides (AMPs) with putative antimicrobial activity; and (iii) assess the bactericidal and/or bacteriostatic properties of T. circumcincta EVs, and whole and EV-depleted ESPs, using bacterial growth inhibition assays.

METHODS

Size-exclusion chromatography was applied to the isolation of EVs from whole T. circumcincta ESPs, followed by EV characterisation via nanoparticle tracking analysis and transmission electron microscopy. Proteomic analysis of EVs and EV-depleted ESPs was conducted using liquid chromatography-tandem mass spectrometry, and prediction of putative AMPs was performed using available online tools. The antimicrobial activities of T. circumcincta EVs and of whole and EV-depleted ESPs against Escherichia coli were evaluated using bacterial growth inhibition assays.

RESULTS

Several molecules with putative antimicrobial activity were identified in both EVs and EV-depleted ESPs from adult T. circumcincta. Whilst exposure of E. coli to whole ESPs resulted in a significant reduction of colony-forming units over 3 h, bacterial growth was not reduced following exposure to worm EVs or EV-depleted ESPs.

CONCLUSIONS

Our data points towards a bactericidal and/or bacteriostatic function of T. circumcincta ESPs, likely mediated by molecules with antimicrobial activity.