sourcegraph
March 28, 2024

Scientists have discovered a drug that could fight drug-resistant infections — and they’ve used artificial intelligence to do just that.

Researchers at the Massachusetts Institute of Technology (MIT) and McMaster University in Canada have used machine learning algorithms to identify a new type of antibiotic that can kill a type of bacteria that causes many drug-resistant infections.

The compound kills Acinetobacter baumannii, a bacterium commonly found in hospitals. It can cause pneumonia, meningitis, and other serious infections.

The microbe is also a leading cause of infection among wounded soldiers in Iraq and Afghanistan.

Paralyzed man regains this ‘simple joy’ thanks to AI ‘digital bridge’

Researchers at MIT and McMaster University used artificial intelligence algorithms to identify a new type of antibiotic that kills a type of bacterium (Acinetobacter baumannii, pink) that causes many drug-resistant infections. (Christine Daniloff/MIT; Acinetobacter baumannii image courtesy of CDC)

Over the past few decades, many pathogenic bacteria have become increasingly resistant to antibiotics, while few new antibiotics have been developed.

The researchers identified the drug from a catalog of nearly 7,000 potential drug compounds using a machine learning model they trained to assess whether the compound would inhibit the growth of bacteria, MIT said in a news release.

To obtain training data for the model, they first exposed bacteria growing in lab dishes to about 7,500 different compounds to see which ones inhibited the microbes’ growth. They fed the structure of each molecule into their model and told it whether each structure could inhibit bacterial growth.

MIT campus

People walk across the campus of the Massachusetts Institute of Technology in Cambridge, Mass., Wednesday, June 2, 2021. (Photographer: Adam Glanzman/Bloomberg via Getty Images)

After the model was trained to analyze a set of 6,680 never-before-seen compounds, the researchers narrowed down 240 hits for experimental testing, focusing on compounds with structures different from existing antibiotics or the training molecule data. The test resulted in nine antibiotics, including one very strong antibiotic.

AI and machines may speed up drug development and manufacturing: FDA

The compound was initially explored as a potential diabetes drug, and it turned out to be very effective at killing bacteria. However, it had no effect on other kinds of bacteria.

The university notes that a “narrow-spectrum” killing capability is desirable because it minimizes the risk of bacteria spreading resistance rapidly. In addition, the drug may preserve beneficial bacteria in the human gut and help curb opportunistic infections.

McMaster University Booth

The McMaster University booth at the Toronto Metro Convention Centre. (RJ Johnston/Toronto Star via Getty Images)

The scientists named the drug abaucin, and studies in mice have shown that it can treat wound infections caused by bacteria. In laboratory tests, it was also found to be effective against multiple drug-resistant strains of Acinetobacter baumannii isolated from human patients. In other experiments, the drug was shown to kill cells by interfering with a process called lipoprotein trafficking. Cells use it to transport proteins from the cell interior to the cell envelope.

Click here for the Fox News app

A McMaster University lab is now working with others to optimize the compound’s medicinal properties and hopes to develop it for eventual use in patients.

The study authors also plan to use their modeling approach to identify potential antibiotics for other types of drug-resistant infections.

The findings were published Thursday in the journal Nature Chemical Biology.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *