Computational Discovery and Experimental Validation of Potent Bifunctional Antimicrobial Peptides

Core Concepts

A deep learning-based framework can efficiently generate novel antimicrobial peptides with potent activities against both bacteria and viruses.

Abstract

The study presents a deep learning-based framework for the de novo design of antimicrobial peptides (AMPs) that can inhibit a broad spectrum of pathogens, including both bacteria and viruses. The framework consists of a generative adversarial network (GAN) generator and an antimicrobial activity regressor called AMPredictor. The GAN generator learns the hidden patterns of known AMPs and generates novel peptide sequences, while the AMPredictor model predicts the antimicrobial activity (minimum inhibitory concentration, MIC) of the generated peptides using a graph convolutional network. The authors discovered three bifunctional AMPs (P001, P002, and P076) that exhibited potent antimicrobial and antiviral activities. Experimental validation showed that: P076 is a highly potent bactericide with an MIC of 0.21 μM against multidrug-resistant Acinetobacter baumannii, outperforming the clinically relevant antibiotic polymyxin B in terms of safety and efficacy. P002 broadly inhibited five enveloped viruses, including CHIKV, HTNV, DENV-2, HSV-1, and SARS-CoV-2, with low cytotoxicity. The membrane-acting mechanisms of these AMPs were investigated through experimental assays and molecular dynamics simulations, revealing their abilities to bind and disrupt bacterial and viral membranes. The study demonstrates the feasibility of using deep learning to uncover novel AMPs with simultaneous antimicrobial and antiviral activities, providing a promising approach to combat a wide range of drug-resistant infections.

Stats

The minimum inhibitory concentrations (MICs) of the three peptides against various bacterial strains ranged from 0.20 to 15.18 μM. The half-maximal effective concentrations (EC50) of the three peptides against different viruses ranged from 0.37 to 2.67 μM. The 50% cytotoxic concentrations (CC50) of the three peptides on mammalian cell lines were above 30 μM. The concentration of P076 to induce 50% death in mice was 80 mg/kg, approximately 3-fold higher than that of polymyxin B (26 mg/kg).

Quotes

"P076 is a highly potent bactericide with the minimal inhibitory concentration of 0.21 μM against multidrug-resistant A. baumannii, while P002 broadly inhibits five enveloped viruses." "Our study provides feasible means to uncover sequences that simultaneously encode antimicrobial and antiviral activities, thus bolstering the function spectra of AMPs to combat a wide range of drug-resistant infections."

Key Insights Distilled From

Exploring the repository of de novo designed bifunctional antimicrobial peptides through deep learning

by Dong,R., Liu... at www.biorxiv.org 02-24-2024

https://www.biorxiv.org/content/10.1101/2024.02.23.581845v1

Deeper Inquiries

How can the computational framework be further improved to better predict the dual antimicrobial and antiviral activities of designed peptides?

To enhance the computational framework for predicting dual antimicrobial and antiviral activities of designed peptides, several improvements can be considered: Incorporating More Data: Increasing the dataset size with a wider variety of antimicrobial and antiviral peptides can improve the model's ability to learn diverse features and patterns associated with dual activities. Feature Engineering: Developing more sophisticated features that capture the unique characteristics of peptides with dual activities, such as specific physicochemical properties, structural motifs, or sequence patterns that are indicative of both antimicrobial and antiviral functions. Multi-Task Learning: Implementing a multi-task learning approach where the model is trained to predict both antimicrobial and antiviral activities simultaneously, leveraging shared information between the two tasks to improve overall performance. Fine-Tuning Hyperparameters: Optimizing hyperparameters such as learning rate, batch size, and network architecture to ensure the model is effectively capturing the complex relationships between peptide sequences and their activities. Interpretable Models: Developing models that provide insights into the underlying mechanisms driving the dual activities of peptides, allowing researchers to understand why certain sequences exhibit both antimicrobial and antiviral properties. Validation and Experimental Confirmation: Integrating experimental validation data into the model training process to continuously refine and improve the predictive capabilities of the framework based on real-world outcomes.

What are the potential limitations or drawbacks of using antimicrobial peptides as therapeutic agents compared to traditional small-molecule antibiotics?

While antimicrobial peptides (AMPs) offer several advantages as potential therapeutic agents, they also come with limitations and drawbacks compared to traditional small-molecule antibiotics: Specificity and Selectivity: AMPs may exhibit varying degrees of specificity towards different pathogens, which can limit their broad-spectrum efficacy compared to traditional antibiotics that target specific bacterial pathways. Cost of Production: The production of AMPs through chemical synthesis or recombinant methods can be more expensive than traditional antibiotics, impacting their scalability and affordability for widespread use. Stability and Shelf Life: AMPs are often susceptible to degradation by proteases and other enzymes, leading to reduced stability and shorter shelf life compared to small-molecule antibiotics. Immunogenicity: Some AMPs may trigger immune responses in the host, leading to potential allergic reactions or other adverse effects, which can limit their clinical utility. Resistance Development: While the development of resistance to AMPs is less common than with traditional antibiotics, it is still a concern, especially with prolonged use or suboptimal dosing regimens. Delivery Challenges: The effective delivery of AMPs to target sites in the body can be challenging, especially for systemic infections or conditions where precise localization is required. Regulatory Hurdles: The regulatory approval process for AMPs as therapeutic agents may be more complex and stringent compared to traditional antibiotics, delaying their clinical translation.

What other types of pathogens or infectious diseases could the discovered bifunctional antimicrobial peptides be potentially effective against, and how could this be investigated?

The discovered bifunctional antimicrobial peptides have the potential to be effective against a wide range of pathogens and infectious diseases beyond the ones tested in the study. These peptides could be investigated for their efficacy against: Fungal Infections: Testing the peptides against fungal pathogens such as Candida albicans, Aspergillus fumigatus, or Cryptococcus neoformans to assess their antifungal properties. Parasitic Infections: Evaluating the peptides against parasites like Plasmodium falciparum (malaria), Trypanosoma cruzi (Chagas disease), or Leishmania spp. (leishmaniasis) to determine their anti-parasitic activity. Emerging Viral Infections: Investigating the peptides against emerging viral pathogens like Zika virus, Ebola virus, or Nipah virus to assess their antiviral potential against new and evolving threats. Biofilm-Forming Bacteria: Studying the peptides' ability to disrupt biofilms formed by bacteria such as Pseudomonas aeruginosa or Staphylococcus aureus, which are associated with chronic infections and antibiotic resistance. Respiratory Infections: Testing the peptides against respiratory pathogens like Mycobacterium tuberculosis, Streptococcus pneumoniae, or respiratory syncytial virus (RSV) to explore their efficacy in treating respiratory infections. Investigating the efficacy of bifunctional antimicrobial peptides against these diverse pathogens can involve in vitro assays, animal models, and potentially clinical trials to assess their therapeutic potential across a broad spectrum of infectious diseases.