MIT researchers have designed novel antibiotics using artificial intelligence that can combat hard-to-treat infections, including drug-resistant Neisseria gonorrhoeae and multi-drug-resistant Staphylococcus aureus (MRSA). The team used generative AI algorithms to generate over 36 million possible compounds and computationally screened them for antimicrobial properties.
The top candidates discovered by the researchers appear to work by novel mechanisms that disrupt bacterial cell membranes. One of these molecules, named NG1, was found to be highly effective in killing N. gonorrhoeae in a lab dish and in a mouse model of drug-resistant gonorrhea infection.
The researchers also explored the potential of using AI to freely design molecules without constraints, which yielded over 29 million compounds. Six of these molecules showed strong antibacterial activity against multi-drug-resistant S. aureus grown in a lab dish.
The development of new antibiotics is crucial due to the growing problem of antibiotic resistance. Globally, it is estimated that drug-resistant bacterial infections cause nearly 5 million deaths per year. The researchers hope that their work will enable them to identify and design compounds with activity against other species of bacteria.
Collins and his team are now exploring further modifications of NG1 and DN1 to make them suitable for additional testing. They also plan to apply the platforms developed by the team toward other bacterial pathogens, including Mycobacterium tuberculosis and Pseudomonas aeruginosa.
Source: https://news.mit.edu/2025/using-generative-ai-researchers-design-compounds-kill-drug-resistant-bacteria-0814