United States: Researchers at the Massachusetts Institute of Technology (MIT) have used artificial intelligence to design two potential antibiotics capable of killing drug-resistant gonorrhoea and MRSA.
The breakthrough, revealed in Cell, could mark the start of a ‘second golden age’ in antibiotic discovery. The AI-designed compounds, built atom-by-atom, successfully killed the superbugs in lab experiments and animal tests. However, they remain years away from clinical use, instructing further refinement and extensive human trials.
Antibiotic resistance is a growing global crisis, with over a million deaths annually linked to infections that no longer respond to treatment. Overuse of existing drugs has allowed bacteria to evolve defences, while the pipeline for new antibiotics has been drying up for decades.
Previous AI-driven research focused on screening vast chemical databases for potential antibiotics. This new MIT approach goes further, using generative AI to create entirely new drug molecules, including some for infections caused by Neisseria gonorrhoeae and methicillin-resistant Staphylococcus aureus (MRSA).
The system analysed 36 million compounds, learning how bacteria respond to different molecular structures. Two design methods were used. One built new molecules from small chemical fragments, while the other gave the AI complete creative freedom. Toxic or redundant designs were filtered out, and only the most promising candidates were synthesised.
In tests, two compounds showed strong potential, killing bacteria in mice infected with the target superbugs. Prof. James Collins of MIT stated that, “We’re excited because we show that generative AI can be used to design completely new antibiotics. This can expand our arsenal and give us a leg up in the battle against superbugs.”
Experts have hailed the work as a significant step forward. But challenges remain, from predicting real-world effectiveness to the complexity of manufacturing AI-designed drugs. Out of 80 promising gonorrhoea treatments generated by AI, only two could be practically synthesised.
Economic hurdles also loom large. New antibiotics are often used sparingly to prevent resistance, making them commercially unappealing for pharmaceutical companies.
Still, scientists say this research signals a transformative shift. If perfected, AI-driven drug design could radically speed up the fight against antibiotic-resistant infections, one of the most urgent threats in modern medicine.
MOST READ | Air Canada to halt flights as flight attendants announce strike
