麻省理工学院和哈佛大学的布罗德研究所James J. Collins研究组取得一项新突破。他们报道了新生抗生素设计的生成式深度学习方法。相关论文于2025年8月14日发表在《细胞》杂志上。

课题组研究人员通过两种方法开发了一个生成式人工智能框架，用于设计新抗生素：基于片段的方法，全面筛选107个针对淋病奈瑟菌或金黄色葡萄球菌的化学片段，随后扩展有希望的片段，以及不受约束的新化合物生成，每种方法都以遗传算法和变分自编码器为主题。在所合成的24个化合物中，有7个具有选择性抗菌活性。在淋病奈瑟菌阴道感染和耐甲氧西林金黄色葡萄球菌皮肤感染的motheme模型中，两种铅化合物对多重耐药分离株具有不同作用机制的抗菌效果，并减少了体内细菌负担。课题组进一步验证了这两类化合物的结构类似物的抗菌作用。他们的方法使生成式深度学习引导的新抗生素设计成为可能，为绘制化学空间的未知区域提供了一个平台。

据介绍，抗菌素耐药性危机需要结构不同的抗生素。虽然深度学习方法可以从现有的文库中识别抗菌化合物，但结构的新颖性仍然有限。

附：英文原文

Title: A generative deep learning approach to de novo antibiotic design

Author: Aarti Krishnan, Melis N. Anahtar, Jacqueline A. Valeri, Wengong Jin, Nina M. Donghia, Leif Sieben, Andreas Luttens, Yu Zhang, Seyed Majed Modaresi, Andrew Hennes, Jenna Fromer, Parijat Bandyopadhyay, Jonathan C. Chen, Danyal Rehman, Ronak Desai, Paige Edwards, Ryan S. Lach, Marie-Stéphanie Aschtgen, Margaux Gaborieau, Massimiliano Gaetani, Samantha G. Palace, Satotaka Omori, Lutete Khonde, Yurii S. Moroz, Bruce Blough, Chunyang Jin, Edmund Loh, Yonatan H. Grad, Amir Ata Saei, Connor W. Coley, Felix Wong, James J. Collins

Issue&Volume: 2025-08-14

Abstract: The antimicrobial resistance crisis necessitates structurally distinct antibiotics. While deep learning approaches can identify antibacterial compounds from existing libraries, structural novelty remains limited. Here, we developed a generative artificial intelligence framework for designing de novo antibiotics through two approaches: a fragment-based method to comprehensively screen >107 chemical fragments in silico against Neisseria gonorrhoeae or Staphylococcus aureus, subsequently expanding promising fragments, and an unconstrained de novo compound generation, each using genetic algorithms and variational autoencoders. Of 24 synthesized compounds, seven demonstrated selective antibacterial activity. Two lead compounds exhibited bactericidal efficacy against multidrug-resistant isolates with distinct mechanisms of action and reduced bacterial burden in vivo in mouse models of N. gonorrhoeae vaginal infection and methicillin-resistant S. aureus skin infection. We further validated structural analogs for both compound classes as antibacterial. Our approach enables the generative deep-learning-guided design of de novo antibiotics, providing a platform for mapping uncharted regions of chemical space.

DOI: 10.1016/j.cell.2025.07.033

Source: https://www.cell.com/cell/abstract/S0092-8674(25)00855-4