AI has helped scientists discover a new antibiotic that can kill a deadly species of superbug.
Researchers in Canada and the US used AI to help narrow down thousands of potential chemicals to a handful that could be tested in the laboratory to treat Acinetobacter baumannii, which can infect wounds and cause pneumonia.
They trained AI by taking thousands of drugs where the precise chemical structure was known, and tested them on Acinetobacter baumannii to see which could slow it down or kill it.
This information was fed into the AI so it could learn the chemical features of drugs that could attack it and the AI took an hour and a half to come up with 6,680 compounds that could work.
The researchers tested 240 in the laboratory, and found nine potential antibiotics.
Sign up to our free Indy100 weekly newsletter
From this they got an antibiotic called abaucin, which needs further tests before being used but looks promising. If all is well the drug could be prescribed by 2030.
More than a million people a year are estimated to die from so-called superbug infections that resist treatment with antibiotics and linger on surfaces.
Dr Jonathan Stokes, from McMaster University, describes the bug as "public enemy number one" as it's "really common" to find cases where it is "resistant to nearly every antibiotic".
"AI enhances the rate, and in a perfect world decreases the cost, with which we can discover these new classes of antibiotic that we desperately need," Dr Stokes told the BBC.
"This finding further supports the premise that AI can significantly accelerate and expand our search for novel antibiotics," said Prof James Collins, from the Massachusetts Institute of Technology.
He added: "I'm excited that this work shows that we can use AI to help combat problematic pathogens such as A. baumannii."
Have your say in our news democracy. Click the upvote icon at the top of the page to help raise this article through the indy100 rankings.