Machine Learning Designs Non-Hemolytic Antimicrobial Peptides

Abstract

<p>Machine learning (ML) consists in the recognition of patterns from training data and offers the opportunity to exploit large structure-activity database sets for drug design. In the area of peptide drugs, ML is mostly being tested to design antimicrobial peptides (AMPs), a class of biomolecules potentially useful to fight multidrug resistant bacteria. ML models have successfully identified membrane disruptive amphiphilic AMPs, however without addressing the associated toxicity to human red blood cells. Here we trained recurrent neural networks (RNN) with data from DBAASP (Database of Antimicrobial Activity and Structure of Peptides) to design short non-hemolytic AMPs. Synthesis and testing of 28 generated peptides, each at least 5 mutations away from training data, allowed us to identify eight new non-hemolytic AMPs against <i>Pseudomonas aeruginosa</i>, <i>Acinetobacter baumannii</i>, and methicillin resistant<i> Staphylococcus aureus</i> (MRSA). These results show that machine learning (ML) can be used to design new non-hemolytic AMPs.</p>

Peptide Dendrimers: From Enzyme Models to Antimicrobials and Transfection Reagents

“…The definitive version of this article is the electronic one that can be found at https://doi.org/10.2533/chimia.2021.535 and machine learning methods tested for proteins, [45] macromolecules, [46,47] linear [48] and bicyclic peptides. [49,50] In terms of activity types, our current focus is on antimicrobials and immunomodulatory dendrimers.…”