Researchers at MIT have developed novel antibiotics using generative AI to combat drug-resistant infections. The AI algorithms designed and screened over 36 million compounds, identifying candidates structurally distinct from existing antibiotics. These compounds disrupt bacterial cell membranes, offering a new approach to fighting infections.
The AI used two approaches: designing molecules based on a specific chemical fragment with antimicrobial activity and freely generating molecules without a specific fragment. This led to the discovery of potential drugs effective against Neisseria gonorrhoeae and multi-drug-resistant Staphylococcus aureus (MRSA). The AI's ability to explore vast chemical spaces has opened new possibilities for antibiotic development.
With drug-resistant bacterial infections causing nearly 5 million deaths annually, this AI-driven approach offers a promising solution. The researchers hope to apply this strategy to identify compounds effective against other bacterial species, potentially revitalising the antibiotic pipeline.
