Skip to Content

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.
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

AI & Health Summer High School Bootcamp
APPLY NOW
When an antibiotic fails: MIT scientists are using AI to target “sleeper” bacteria MIT News
READ MORE
A new computational technique could make it easier to engineer useful proteins MIT News
READ MORE
image description