Discovery of antimicrobial peptides with notable antibacterial potency by an LLM-based foundation model

Large language models (LLMs) have revolutionized chemistry and biomedical research. AMP-Designer, an LLM-based approach, has been used to design antimicrobial peptides (AMPs) with desired properties. Within 11 days, 18 AMPs were designed with broad-spectrum activity against Gram-negative bacteria. In vitro validation showed a 94.4% success rate, with two candidates showing exceptional antibacterial efficacy and minimal hemotoxicity. The process, from design to validation, took 48 days. AMP-Designer’s efficiency and integration of advanced machine learning techniques could lead to innovative antibiotic resistance solutions.