Researchers at the University of Pennsylvania introduced ApexGO, an AI-powered method for peptide antibiotic optimization that starts with imperfect candidate peptides and iteratively improves them. In lab testing, the approach reported high success rates—molecules designed by the system often halted bacterial growth and outperformed parent peptides. The work also extended into in vivo mouse experiments, where optimized antimicrobial peptides reduced bacterial counts comparably to polymyxin B. ApexGO’s design is intended to be faster than broad-library screening workflows by focusing search on targeted chemical modifications. For biotech R&D teams dealing with antibiotic resistance, the results suggest a practical path for accelerating lead optimization cycles while preserving experimental validation guardrails.