Nature Reviews Microbiology Microbiology
Artificial intelligence for antibiotic discovery and design
Abstract
Antibiotic-resistant bacterial infections cause more than 1 million deaths worldwide each year. To effectively address this escalating global health crisis, there is a critical need for new classes of antibiotics, particularly those with novel mechanisms of action. In this Review, we focus on recent advances in small-molecule antibiotic discovery enabled by artificial intelligence. We present a range of innovative approaches that are substantially increasing the size and diversity of the explored chemical space. We highlight recent artificial intelligence-driven advancements in phenotypic antibiotic discovery, mechanism of action elucidation, target-based discovery, de novo molecular design and lead optimization, which promise to expand the repertoire of antibacterial agents and uncover bacterial pathways and vulnerabilities amenable to therapeutic intervention. In this Review, Collins and colleagues explore recent advances in small-molecule antibiotic discovery enabled by artificial intelligence, highlighting recent artificial intelligence-driven advancements in phenotypic antibiotic discovery, mechanism of action elucidation, target-based discovery, de novo molecular design and lead optimization.