Scientists are using AI to find drugs that kill bacteria responsible for many drug-resistant infections

Scientists have found a drug that can fight resistant infections – and they did it with the help of artificial intelligence.

Using a machine-learning algorithm, researchers at the Massachusetts Institute of Technology (MIT) and McMaster University in Canada have identified a new antibiotic that can kill a type of bacteria responsible for many drug-resistant infections.

The compound kills Acinetobacter baumannii, a species of bacteria commonly found in hospitals. It can lead to pneumonia, meningitis and other serious infections.

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


Using an artificial intelligence algorithm, researchers at MIT and McMaster University have identified a new antibiotic that can kill a type of bacteria (Acinetobacter baumannii, pink) responsible for many drug-resistant infections. (Christine Daniloff/MIT; Acinetobacter baumannii image courtesy of CDC)

In recent decades, many pathogenic bacteria have become increasingly resistant to antibiotics, while few new antibiotics have been developed.

MIT said in a release that researchers identified the drug from a catalog of nearly 7,000 potential drug compounds using a machine learning model they trained to evaluate whether a chemical compound will inhibit the growth of the bacteria.

To get training data for the model, they first exposed the bacteria grown in a lab dish to about 7,500 different chemical compounds to see which could inhibit the growth of the microbe. They fed the structure of each molecule into their model and told whether each structure could inhibit bacterial growth.

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

Once the model was trained, it was used to analyze a set of 6,680 compounds it hadn’t seen before, and researchers narrowed down to 240 hits to test experimentally, focusing on compounds with structures that were different than that of existing antibiotics or molecules from training. facts. Those tests led to nine antibiotics, including one that was very strong.


The compound, which was originally researched as a potential drug for diabetes, proved to be extremely effective at killing the bacteria. However, it had no effect on other bacterial species.

The university noted that a “narrow spectrum” kill capability is desirable because it minimizes the risk of bacteria quickly spreading resistance to the drug. Furthermore, the drug would likely spare the beneficial bacteria that live in the human gut and help suppress opportunistic infections.

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

The scientists named the drug abaucin and in studies in mice they showed that it could treat wound infections caused by the bacteria. In lab tests, it was also found to be effective against a variety of drug-resistant strains of Acinetobacter baumannii isolated from human patients. In additional experiments, the drug was shown to kill cells by disrupting a process known as lipoprotein trafficking. Cells use that to transport proteins from the cell interior to the cell envelope.


A lab at McMaster University is now working for others to optimize and hopefully develop the compound’s medicinal properties 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.”

Leave a comment