AI-Guided Design of Antimicrobial Peptide Hydrogels for Precise Treatment of Drug-resistant Bacterial Infections

Traditional biomaterial development lacks systematicity and predictability, posing significant challenges in addressing the intricate engineering issues related to infections with drug-resistant bacteria. The unprecedented ability of artificial intelligence (AI) to manage complex systems offers a novel paradigm for materials development. However, no AI model currently guides the development of antibacterial biomaterials based on an in-depth understanding of the interplay between biomaterials and bacteria. In this study, an AI-guided design platform (AMP-hydrogel-Designer) is developed to generate antibacterial biomaterials. This platform utilizes generative design and multi-objective constrained optimization to generate a novel thiol-containing high-efficiency antimicrobial peptide (AMP), that is functionally coupled with hydrogel to form a complex network structure. Additionally, Cu-modified barium titanate (Cu-BTO) is incorporated to facilitate further complex cross-linking via Cu²⁺/SH coordination to produce an AI-AMP-hydrogel. In vitro, the AI-AMP-hydrogel exhibits > 99.99% bactericidal efficacy against Methicillin-resistant Staphylococcus aureus (MRSA) and Escherichia coli (E. coli). Furthermore, Cu-BTO converts mechanical stimulation into electrical signals, thereby promoting the expression of growth factors and angiogenesis. In a rat model with dynamic wounds, the AI-AMP hydrogel significantly reduces the MRSA load and markedly accelerates wound healing. Therefore, the AI-guided biomaterial development strategy offers an innovative solution to precisely treat drug-resistant bacterial infections.