AI helps find new antibiotic for hard-to-treat bacteria

Using artificial intelligence, scientists from Canada and the United States have discovered an antibiotic that could be used to fight a deadly, drug-resistant pathogen – and they hope to use a similar process to discover treatments for other difficult bacteria.

In a study published Thursday in the journal Nature Chemical Biology, researchers from McMaster University and the Massachusetts Institute of Technology shared their promising findings about the new antibacterial treatment, which they named abaucin.

Jon Stokes, one of the lead authors of the research paper, said the antibiotic could be used to fight Acinetobacter baumannii, which the World Health Organization has identified as one of the most antibiotic-resistant bacteria. dangerous in the world.

“In my opinion, this is public enemy No. 1 of antibiotic resistance – it’s very difficult to treat,” said Stokes, who is an assistant professor in the department of biochemistry and biomedical sciences at McMaster.

“It tends to live in hospitals, so you find it on doorknobs and hospital equipment and everything. And it’s really hard to sterilize, so it can survive on those hospital surfaces for long periods of time.

The bacterial pathogen, also known as A. baumannii, can cause pneumonia, meningitis and infect wounds, all of which can lead to death. It is also able to pick up DNA from other species of bacteria in its environment, which may encode antibiotic resistance genes, Stokes noted.

In order to discover an antibiotic to fight the highly drug-resistant pathogen, Stokes said researchers tested around 7,500 molecules with different structures in a lab to see which of them were able to inhibit the growth of bacteria. ‘AT. baumannii and which of them were not. .

Next, he said they trained an AI model to understand what chemical characteristics result in molecules with A. baumannii activity.

“Once we trained our model, we were able to start showing the model a bunch of images of new molecules it had never seen, like a flashcard,” Stokes explained.

“And then, based on what the model learned during training, it would predict which chemicals it thought were antibacterial and which it thought weren’t.”

After that, the researchers acquired the molecules that the AI ​​model predicted to be antibacterial and tested them to see how well they could fight A. baumannii.

“And that was easy, because instead of having to test thousands of molecules, we were testing a few hundred,” Stokes said.

“We ended up finding this molecule that was potent in inhibiting the growth of Acinetobacter in the lab – and it was structurally unique from all the other known antibiotics we have. So this AI model helped us extract quite effectively an interesting molecule with antibacterial properties against the bug we were trying to kill.

Stokes conducted the research with James J. Collins, professor of medical engineering and science at MIT, McMaster graduate students Gary Liu and Denise Catacutan, and Khushi Rathod, a recent McMaster graduate.

Stokes said their research offers evidence that the application of AI methods can “significantly influence” the discovery of new antibiotics across a whole host of different challenging pathogens. And he hopes to use similar methods to discover other antibacterial treatments.

“I’m not saying AI is a panacea – it won’t solve all of our problems for us – but it is a very powerful tool in our toolbox that we use to find new medicines for people.”