MIT Scientists Develop Superbug-Killing Antibiotics Using Generative AI

Scientists have developed two potential antibiotics using artificial intelligence (AI) that could kill drug-resistant gonorrhoea and MRSA. Researchers at the Massachusetts Institute of Technology (MIT) used generative AI algorithms to scan through a list of potential molecules to predict which one could work as an antibiotic for the superbugs.

AI also helped scientists avoid structures that could be harmful to humans or too similar to existing drugs, according to the study published in the journal Cell. After identifying the molecules, both new antibiotics were able to kill strains of bacteria that are becoming increasingly difficult to treat with existing antibiotics.

"We're excited because we show that generative AI can be used to design completely new antibiotics," Professor James Collins, MIT, was quoted as saying by the BBC.

"AI can enable us to come up with molecules, cheaply and quickly and in this way, expand our arsenal, and really give us a leg up in the battle of our wits against the genes of superbugs."

Overusing antibiotics has helped bacteria evolve to develop mechanisms to dodge the drugs' effects. Subsequently, there has been a shortage of new antibiotics for decades. However, the latest development has given scientists a ray of hope. The researchers behind the discovery stated that AI could start a "second golden age" in antibiotic discovery.

The breakthrough addresses the growing global public health crisis of antimicrobial resistance, which is responsible for over one million deaths annually.

Also Read | Brazilian Woman Married To Indian Man Shares Her Love Story: 'When You Know'

Previous instance

In May, a team from the US, UK and Switzerland announced they had developed an AI test that can predict which men with prostate cancer will benefit most from a drug that reduces the risk of dying.

The test uses AI to study images of tumours and examine features invisible to the human eye. The team trialled the test on biopsy images from more than 1,000 men with high-risk prostate cancer that had not spread.

"The natural history of advanced and aggressive prostate cancer is highly variable and now with better treatments, the risk of cancer relapse can be significantly reduced," said Professor Gert Attard, co-lead of the study.

"This study shows, in a very large cohort of patients, that novel AI algorithms can be used to extract information from routinely available pathology slides to tailor these treatments to specific patients and minimise overtreatment whilst maximising the chance of cure."