Abstract Antimicrobial resistance (AMR) is one of the most critical public health threats of the 21st century and is projected to become a leading cause of mortality by 2050. The World Health Organization (WHO) recognizes AMR as a top priority in its 2030 research agenda, emphasizing the need to find new antibiotics and innovative therapies. Research on antimicrobial peptides (AMPs) offers a promising alternative given their rapid, membrane-mediated mode of action and low probability of resistance development. Advances in artificial intelligence (AI) now enable large-scale analysis of biological data, prediction of antimicrobial activity and optimization of peptide designs. Deep-learning and machine-learning models, open-access databases and cutting-edge protein-structure prediction algorithms provide unprecedented opportunities to accelerate the discovery and development of AMPs. Beyond discovery, AI aids in predicting three-dimensional peptide structures, which is essential for understanding their mechanisms of action. Here, we highlight recent progress in integrating AI into the fight against AMR, focusing on the design and prediction of peptides as new antimicrobial agents.
Velásquez-Mejía et al. (2026) studied this question.