Ortiz-Gómez Valerie, Maldonado-Hernández Rafael
Department of Natural Sciences and Technology, Ana G. Méndez University, Gurabo Campus, Gurabo, Puerto Rico 00777, United States.
Molecular Sciences Research Center, University of Puerto Rico, San Juan, Puerto Rico 00926, United States.
ACS Omega. 2025 May 20;10(21):20968-20983. doi: 10.1021/acsomega.5c01011. eCollection 2025 Jun 3.
Antimicrobial resistance (AMR) is a growing silent pandemic driven by multidrug-resistant infections, particularly those associated with medical devices such as dental implants, heart valves, and urinary catheters. This review addresses the urgent need for alternative antimicrobial strategies by exploring the integration of artificial intelligence (AI) in the discovery of antimicrobial peptides (AMPs) and the rational design of bioactive surfaces. We describe how AI-based models accelerate the identification and optimization of peptide candidates with potent antibiofilm activity. Moreover, we examine recent advancements in surface engineering, such as biomimetic coatings, quorum sensing inhibitors, and enzyme-based strategies, that disrupt bacterial colonization and biofilm formation. The novelty of this work lies in its unified perspective that bridges computational prediction, materials science, and microbial pathogenesis to inform the next generation of antimicrobial surfaces. By highlighting innovative AI-assisted approaches and emerging hybrid strategies, this review underscores their potential to mitigate device-associated infections and address the broader challenge of AMR in healthcare settings.
抗菌耐药性（AMR）是一场由多重耐药感染驱动的日益严重的无声大流行，尤其是那些与牙科植入物、心脏瓣膜和导尿管等医疗设备相关的感染。本综述通过探索人工智能（AI）在抗菌肽（AMPs）发现中的整合以及生物活性表面的合理设计，探讨了对抗菌替代策略的迫切需求。我们描述了基于AI的模型如何加速具有强大抗生物膜活性的肽候选物的鉴定和优化。此外，我们研究了表面工程的最新进展，如仿生涂层、群体感应抑制剂和基于酶的策略，这些策略可破坏细菌定植和生物膜形成。这项工作的新颖之处在于其统一的视角，将计算预测、材料科学和微生物发病机制联系起来，为下一代抗菌表面提供信息。通过强调创新的AI辅助方法和新兴的混合策略，本综述强调了它们在减轻与设备相关的感染以及应对医疗环境中AMR这一更广泛挑战方面的潜力。
