Machine learning and genetic Algorithm-Guided directed evolution for the development of antimicrobial peptides

This study identifies the lipopolysaccharide-binding domain (LBD) of antimicrobial peptides (AMPs) from Marsupenaeus japonicus using machine learning-guided directed evolution. The LBDB exhibits a broad antimicrobial spectrum and induces a cluster of bacteria wrapped in a flexible coating. In vivo coinjection of LBDB, Vibrio alginolyticus, and Staphylococcus aureus improves M. japonicus’ survival, demonstrating its potential therapeutic role in treating infectious diseases. The findings could guide the design of activity-enhanced peptide antibiotics.