Antibiotic identified by AI

Computational approaches are emerging as powerful tools for the discovery of antibiotics. A study now uses machine learning to discover abaucin, a potent antibiotic that targets the bacterial pathogen Acinetobacter baumannii.

October 11th, 2023 Nature Chemical Biology

Diagram of AI-driven antibiotic discovery — a, Machine learning methods enable swift exploration of chemical space, enhancing the likelihood of discovering new compounds with antibacterial activity. Liu et al.11 used a message-passing neural network to predict activity against A. baumannii for compounds from the Drug Repurposing Hub. b, Abaucin was identified as an antibacterial compound with narrow-spectrum activity. This compound was shown to disrupt lipoprotein trafficking via LolE, a functionally conserved protein responsible for transferring lipoproteins from the inner to the outer membrane. Abaucin was shown to be effective at controlling an A. baumannii infection in a mouse wound model.

Read the Article

News & Events

Seminar Series: Amaka Eneanya, MD, MPH March 31,2025 Cambridge, MA

Team MATCHMAKERS makes progress at the Cancer Grand Challenges Summit

MIT faculty, alumni named 2025 Sloan Research Fellows MIT News