A team of scientists at the Massachusetts Institute of Technology (MIT) has used artificial intelligence to create two new antibiotics capable of killing dangerous drug-resistant bacteria, including MRSA, in laboratory and animal tests — a breakthrough researchers say could mark the start of a “second golden age” in antibiotic discovery.
The study, published in the journal Cell, describes how researchers used AI to generate more than 36 potential drug compounds. These were then screened by the system for antimicrobial properties, with the most promising turned into chemical compounds for testing. In trials on bacteria in the lab and mice infected with methicillin-resistant Staphylococcus aureus (MRSA) or antibiotic-resistant gonorrhoea, the drugs demonstrated strong antibacterial activity. In one experiment, they successfully cleared an MRSA skin infection in mice.
While the findings are encouraging, the antibiotics must undergo further refinement and extensive clinical trials before they can be prescribed to humans — a process that could take several years.
Professor James Collins, the study’s senior author, said the results highlight the transformative potential of AI in drug discovery. “Our work shows the power of AI from a drug design standpoint, and enables us to exploit much larger chemical spaces that were previously inaccessible,” he said. The team now plans to apply the same approach to other dangerous pathogens, including the bacteria that cause tuberculosis.
Antibiotic resistance is a growing global health crisis. More than a million people die each year from antimicrobial-resistant infections, and in 2023 the UK recorded 66,730 serious cases — including those caused by MRSA, sometimes referred to as a “superbug” because of its resistance to multiple drugs.
Unlike many previous efforts, MIT’s research deliberately avoided chemical structures similar to existing antibiotics, in an effort to make it harder for bacteria to develop resistance. “We wanted to get rid of anything that would look like an existing antibiotic, to help address the antimicrobial resistance crisis in a fundamentally different way,” said co-author Dr Aarti Krishnan.
If successful in human trials, the AI-designed drugs could herald a long-awaited revival in antibiotic development — and offer a powerful new weapon against some of the world’s most dangerous infections.
