Antimicrobial Peptides and Activities

AMP-Diffusion: Integrating Latent Diffusion with Protein Language Models for Antimicrobial Peptide Generation

AMP-Diffusion generates functional antimicrobial peptides using a latent diffusion model integrated with the ESM-2 protein language model, showing alignment with experimentally validated AMPs in pseudo-perplexity and physicochemical properties.

AntiBP3: A hybrid method for predicting antibacterial peptides against gram-positive/negative/variable bacteria

This paper introduces AntiBP3, a hybrid method for predicting antibacterial peptides effective against gram-positive, gram-negative, and gram-variable bacteria, achieving high AUC scores on independent datasets.

Sequence-function mapping of proline-rich antimicrobial peptides

The paper maps sequence-function relationships in proline-rich antimicrobial peptides using SAMP-Dep, identifying mutational patterns and epistasis that influence activity and specificity.

Bibacillin 1: A two-component lantibiotic from Bacillus thuringiensis

This paper identifies bibacillin 1, a two-component lantibiotic from Bacillus thuringiensis, showing cooperative bactericidal activity and distinct mechanism of action compared to other lantibiotics.

Unsupervised learning elucidates the interplay between conformational flexibility and aggregation in synergistic antimicrobial peptides

This study uses unsupervised learning and molecular dynamics to show that mixing two AMPs reduces their conformational diversity and alters aggregation behavior, revealing how synergy influences their structural dynamics.

Cell-free biosynthesis combined with deep learning accelerates de novo-development of antimicrobial peptides

Autoencoder design plus a roughly 24-hour cell-free screen tested 500 candidates over five rounds, finding 30 functional AMPs; six were broad-spectrum with no resistance emerging in E. coli.

Bioinformatics analysis of Uncyclotides: a potential antimicrobial peptide to protect against heart failure diseases

This study uses bioinformatics analysis to identify Uncyclotides as a potential antimicrobial peptide for heart failure treatment.

Mining the heparinome for cryptic antimicrobial peptides that selectively kill gram-negative bacteria

The paper identifies antimicrobial peptides from heparin-binding proteins that selectively kill gram-negative bacteria by binding to LPS.

An antimicrobial peptide expression platform for targeting pathogenic bacterial species

The paper develops a modular platform for expressing and secreting bacteriocins from non-pathogenic E. coli to target pathogenic bacteria, demonstrating antimicrobial activity and modeling strain interactions.

PandoraGAN: Generating antiviral peptides using Generative Adversarial Network

PandoraGAN generates novel antiviral peptides using a GAN model trained on curated data, producing sequences with properties similar to known active peptides.

Novel integrated computational AMP discovery approaches highlight diversity in the helminth AMP repertoire

This study introduces a novel computational pipeline to discover antimicrobial peptides (AMPs) in helminths, revealing unique AMP-like peptides and highlighting their potential as novel antimicrobials.

Discovering highly potent antimicrobial peptides with deep generative model HydrAMP

This paper introduces HydrAMP, a deep generative model for creating potent antimicrobial peptides, which outperforms existing methods and validates nine new peptides in lab tests.

Cyclic lipopeptides as membrane fusion inhibitors against SARS-CoV-2: new tricks for old dogs

The paper investigates the antiviral effects of cyclic lipopeptides against SARS-CoV-2 by assessing their ability to inhibit membrane fusion in vitro.

Inhibition of translation termination by Drosocin, an antimicrobial peptide from fruit flies

This study identifies Drosocin as a type II PrAMP that inhibits protein synthesis termination by stalling ribosomes at stop codons, distinct from apidaecin.

Machine learning-guided directed evolution for the development of small-molecule antibiotics originating from antimicrobial peptides

This study uses machine learning-guided directed evolution to develop a peptide antibiotic from antimicrobial peptides, showing improved antimicrobial activity and therapeutic potential.

In silico assessment of missense point mutations on human cathelicidin LL-37

The paper assesses the impact of missense mutations on human LL-37 structure and antimicrobial activity using computational methods, finding some mutations may reduce activity and contribute to inflammatory diseases.

Targeting the Search: An Upgraded Structural and Functional Repository of Antimicrobial Peptides for Biofilm Studies (B-AMP v2.0) with a Focus on Biofilm Protein Targets

The paper introduces B-AMP v2.0, an upgraded repository of antimicrobial peptides and biofilm targets, with tools for in silico evaluation of AMPs against specific bacterial biofilm proteins.

The Nematode Antimicrobial Peptidome: a novel opportunity for parasite control?

This study identifies 5887 AMP-encoding genes across 134 nematode genomes, revealing diverse AMP profiles influenced by lifestyle and clade, with implications for drug discovery.

Benchmarks in antimicrobial peptide prediction are biased due to the selection of negative data

This study shows that AMP prediction benchmarks are biased due to negative data selection and introduces a web server for fair benchmarking.

The Cryo-EM Structures of two Amphibian Antimicrobial Cross-β Amyloid Fibrils

The paper determines the cryo-EM structures of two amphibian antimicrobial peptides, revealing cross-β amyloid fibrils and their structural polymorphism.

Deep attention based variational autoencoder for antimicrobial peptide discovery

This study uses a variational autoencoder with attention mechanisms to generate novel antimicrobial peptides with physicochemical properties similar to real ones.

Comparative analysis of machine learning algorithms on the microbial strain-specific AMP prediction

The paper compares machine learning algorithms for predicting antimicrobial peptides (AMPs) specific to microbial strains, finding Random Forest and AdaBoost perform best with improved accuracy using genome characteristics.

HybAVPnet: a novel hybrid network architecture for antiviral peptides identification

This paper introduces HybAVPnet, a hybrid network architecture for antiviral peptide identification, showing improved performance over existing methods on independent datasets.

The antibiotic phazolicin displays a dual mode of uptake in Gram-negative bacteria

The paper identifies two distinct transporters, BacA and YejABEF, that mediate the uptake of the peptide antibiotic phazolicin in Sinorhizobium meliloti, reducing resistance acquisition.

Unsupervised encoding selection through ensemble pruning for biomedical classification

The paper presents a workflow for unsupervised encoding selection and ensemble creation for peptide classification, demonstrating that Pareto frontier pruning and Decision Tree base models perform well across datasets.

AMPlify: attentive deep learning model for discovery of novel antimicrobial peptides effective against WHO priority pathogens

AMPlify is a deep learning model that predicts antimicrobial peptides from bullfrog genomes, identifying novel peptides effective against WHO priority pathogens including drug-resistant bacteria.

LMPred: Predicting Antimicrobial Peptides Using Pre-Trained Language Models and Deep Learning

This paper introduces LMPred, a model using pre-trained language models and convolutional neural networks to predict antimicrobial peptides with high accuracy.

Small molecules enhance the potency of natural antimicrobial peptides

The paper shows that certain small molecules, like niacinamide, enhance the activity of antimicrobial peptides against Staphylococcus aureus by altering bacterial membrane properties.

Sense the Moment: a highly sensitive antimicrobial activity predictor based on hydrophobic moment

This paper introduces a new antimicrobial activity predictor called 'Sense the Moment' that outperforms deep-learning methods in distinguishing antimicrobial peptides from shuffled versions.

HMD-AMP: Protein Language-Powered Hierarchical Multi-label Deep Forest for Annotating Antimicrobial Peptides

This study introduces HMD-AMP, a deep learning framework for multi-label classification of antimicrobial peptides, improving performance on minor classes and handling multiple targets.