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

• DOI: 10.1101/2020.06.16.155705
• Publication Date: 2020-06-17T14:36:05Z
• Authors: Chenkai Li; Darcy Sutherland; S. Austin Hammond; Chen Yang; Figali Taho; Lauren Bergman; Simon Houston; René L. Warren; Titus Wong; Linda M.N. Hoang; Caroline E. Cameron; Caren C. Helbing; Inanc Birol
• Keywords: 0301 basic medicine; 0303 health sciences; Attention mechanism; Deep learning; QH426-470; World Health Organization; Anti-Bacterial Agents; 3. Good health; 03 medical and health sciences; Deep Learning; Genetics; Attention; Antimicrobial peptide; TP248.13-248.65; Antimicrobial Peptides; Biotechnology; Research Article; Antimicrobial Cationic Peptides

AbstractAntibiotic resistance is a growing global health concern prompting researchers to seek alternatives to conventional antibiotics. Antimicrobial peptides (AMPs) are emerging therapeutic agents with promising utility in this domain and usingin silicomethods to discover novel AMPs is a strategy that is gaining interest. Such methods can filter through large volumes of candidate sequences and reduce lab screening costs. Here we introduce AMPlify, an attentive deep learning model for AMP prediction, and demonstrate its utility in prioritizing peptide sequences derived from theRana [Lithobates] catesbeiana(bullfrog) genome. We tested the bioactivity of our predicted peptides against a panel of bacterial species, including representatives from the World Health Organization’s “priority pathogens” list. Four of our novel AMPs were active against multiple species of bacteria, including a multi-drug resistant isolate of carbapenemase-producingEscherichia coli, demonstrating the utility of tools like AMPlify in our fight against antibiotic resistance.