Computational Approaches in Discovery and Design of Antimicrobial Peptides

This Reprint gathers recent contributions on computational approaches for the discovery, prediction, and design of antimicrobial peptides and related bioactive peptides. The published articles cover complementary strategies ranging from alignment based and alignment free models to deep learning, geometric deep learning, structure informed prediction, and rational peptide design. Together, they illustrate how in silico methods are accelerating peptide biodiscovery, improving candidate prioritization, and supporting the interpretation of peptide structure-activity relationships. The collection is intended for researchers working in antimicrobial resistance, peptide science, bioinformatics, cheminformatics, and artificial intelligence for life sciences. By bringing these studies together, the Reprint provides an updated overview of emerging computational workflows and methodological trends that are shaping the next generation of peptide research.