AMPlify: attentive deep learning model for discovery of novel antimicrobial peptides effective against WHO priority pathogens
Problem
Antibiotic resistance creates urgent need for new antimicrobial agents, but lab screening of candidate peptides is costly.
Why it matters
WHO priority pathogens and multidrug-resistant bacteria pose a growing global health threat.
What the AI did
AMPlify, an attentive deep learning model, prioritized candidate antimicrobial peptide sequences from the bullfrog genome for experimental testing.
Results
Four novel predicted AMPs were active against multiple bacterial species, including a multidrug-resistant carbapenemase-producing E. coli isolate.
Impact
AI-guided discovery yielded lab-validated active peptides against priority pathogens, though clinical utility is unshown.
Record
| Venue | BMC Genomics |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Chenkai Li, Darcy Sutherland, S. Austin Hammond, Chen Yang, Figali Taho, Lauren C. Bergman, Simon Houston, René L. Warren et al. |
| Citations | 221 (OpenAlex, at import time) |
| References | 55 |
| Model or method | AMPlify (attentive deep learning model) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1186/s12864-022-08310-4 |
| Open access | gold |
| Keywords | antimicrobial peptides, deep learning, antibiotic resistance, AMPlify, WHO priority pathogens |
Importance rating
significant — thousands to millions affected
Abstract frames antibiotic resistance as a growing global health concern tied to WHO priority pathogens; AI-guided discovery yielded lab-validated active peptides including against multidrug-resistant E. coli.