Abstract
Antimicrobial resistance (AMR) poses a critical global health threat, demanding innovative strategies for drug discovery. Antimicrobial peptides (AMPs) represent promising alternatives, yet traditional experimental identification is limited by cost and scalability. Advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have transformed AMP discovery by enabling the accurate prediction, design, and optimization of novel candidates. This perspective highlights recent progress in AI-driven approaches, including predictive models and generative models, which accelerate large-scale peptide screening and functional annotation. We further emphasize the integration of multiomics data and the potential role of emerging technologies, such as quantum computing (QC), in overcoming computational bottlenecks for peptide design. Together, these approaches promise to expand the therapeutic landscape, paving the way toward next-generation peptide-based antimicrobials capable of circumventing resistance mechanisms and addressing urgent clinical needs.