2025-08-15 マサチューセッツ工科大学(MIT)
With help from artificial intelligence, MIT researchers have discovered novel antibiotics that can combat two hard-to-treat infections: a drug-resistant form of gonorrhea and multi-drug-resistant Staphylococcus aureus (MRSA).
Credit: iStock, MIT News
<関連情報>
- https://news.mit.edu/2025/using-generative-ai-researchers-design-compounds-kill-drug-resistant-bacteria-0814
- https://www.cell.com/cell/abstract/S0092-8674(25)00855-4
- https://medibio.tiisys.com/111552/
- https://www.cell.com/cell/fulltext/S0092-8674(20)30102-1
新規抗生物質設計のための生成型深層学習アプローチ A generative deep learning approach to de novo antibiotic design
Aarti Krishnan ∙ Melis N. Anahtar ∙ Jacqueline A. Valer ∙ … ∙ Connor W. Coley ∙ Felix Wong ∙ James J. Collins
Cell Published:August 14, 2025
DOI:https://doi.org/10.1016/j.cell.2025.07.033
Highlights
- Genetic algorithms and variational autoencoders enable fragment-based and de novo design
- Seven of 24 custom-synthesized compounds show selective antibacterial activity
- Two lead compounds display unique modes of action against N. gonorrhoeae and S. aureus
- Two lead compounds show efficacy against multidrug-resistant strains and in mouse models
Summary
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.
抗生物質発見におけるディープラーニングアプローチ A Deep Learning Approach to Antibiotic Discovery
Jonathan M. Stokes ∙ Kevin Yang ∙ Kyle Swanson ∙ … ∙ Tommi S. Jaakkola ∙ Regina Barzilay ∙ James J. Collins
Cell Accepted: January 15, 2020
DOI:https://doi.org/10.1016/j.cell.2020.01.021
Highlights
- A deep learning model is trained to predict antibiotics based on structure
- Halicin is predicted as an antibacterial molecule from the Drug Repurposing Hub
- Halicin shows broad-spectrum antibiotic activities in mice
- More antibiotics with distinct structures are predicted from the ZINC15 database
Summary
Due to the rapid emergence of antibiotic-resistant bacteria, there is a growing need to discover new antibiotics. To address this challenge, we trained a deep neural network capable of predicting molecules with antibacterial activity. We performed predictions on multiple chemical libraries and discovered a molecule from the Drug Repurposing Hub—halicin—that is structurally divergent from conventional antibiotics and displays bactericidal activity against a wide phylogenetic spectrum of pathogens including Mycobacterium tuberculosis and carbapenem-resistant Enterobacteriaceae. Halicin also effectively treated Clostridioides difficile and pan-resistant Acinetobacter baumannii infections in murine models. Additionally, from a discrete set of 23 empirically tested predictions from >107 million molecules curated from the ZINC15 database, our model identified eight antibacterial compounds that are structurally distant from known antibiotics. This work highlights the utility of deep learning approaches to expand our antibiotic arsenal through the discovery of structurally distinct antibacterial molecules.
