- By James Gallagher
- Health and Science Correspondent
Scientists have used artificial intelligence (AI) to discover a new antibiotic that can kill a deadly species of superbug.
The AI helped narrow down thousands of potential chemicals to a handful that could be tested in the lab.
The result was a powerful, experimental antibiotic called abaucin, which needs further testing before being used.
The researchers in Canada and the US say AI has the power to vastly accelerate the discovery of new drugs.
It is the latest example of how the tools of artificial intelligence can be a revolutionary force in science and medicine.
Stopping the superbugs
Antibiotics kill bacteria. However, there has been a lack of new drugs for decades, and bacteria are becoming increasingly difficult to treat as they develop resistance to the ones we have.
The researchers focused on one of the most problematic bacterial species: Acinetobacter baumanniiwhich can infect wounds and cause pneumonia.
You may not have heard of it, but it’s one of three superbugs that the World Health Organization has identified as a “critical” threat.
It is often able to shake off multiple antibiotics and is a problem in hospitals and care homes, where it can survive on surfaces and medical equipment.
Dr. Jonathan Stokes, of McMaster University, describes the bug as “public enemy number one” as it is “very common” to find cases where it is “resistant to almost every antibiotic”.
To find a new antibiotic, the researchers first had to train the AI. They took thousands of drugs whose precise chemical structure was known and tested them by hand Acinetobacter baumannii to see which one could slow it down or kill it.
This information was fed into the AI so it could learn the chemical characteristics of drugs that could attack the problematic bacteria.
The AI was then unleashed on a list of 6,680 compounds whose effectiveness was unknown. The results – published in Nature Chemical Biology – showed that it took the AI an hour and a half to make a shortlist.
The researchers tested 240 of them in the lab and found nine potential antibiotics. One was the incredibly powerful antibiotic abaucin.
Laboratory experiments showed that it could treat and even kill infected wounds in mice A. baumannii patient samples.
Dr. However, Stokes told me, “This is when the work begins.”
The next step is to perfect the drug in the lab and then conduct clinical trials. He expects it could be as late as 2030 before the first AI antibiotics are available for prescription.
Oddly enough, this experimental antibiotic had no effect on other types of bacteria and only acts on them A. baumannii.
Many antibiotics kill bacteria indiscriminately. The researchers believe that abaucin’s precision will make it more difficult for drug resistance to occur, and could lead to fewer side effects.
In principle, the AI could screen tens of millions of potential connections – something that would be impractical to do manually.
“AI increases the speed, and in a perfect world reduces the cost, that will allow us to discover these new classes of antibiotics that we desperately need,” said Dr. Stokes me.
The researchers tested the principles of AI-assisted antibiotic discovery in E. coli in 2020, but have now used that knowledge to focus on the big bad stuff. They plan to watch Staphylococcus aureus And Pseudomonas aeruginosa next one.
“This finding further supports the premise that AI can significantly accelerate and expand our search for new antibiotics,” said Massachusetts Institute of Technology Professor James Collins.
He added: “I am delighted that this work shows that we can use AI to help combat problematic pathogens such as A. baumannii.”