Science bets on artificial intelligence to stop a deadly superbug

A group of scientists has discovered, using AI (artificial intelligence), a new antibiotic capable of killing a deadly hospital superbug. The new study on it came out in the scientific journal Nature Chemical Biology on Thursday (25).

What you need to know:

The team that discovered the new antibiotic has researchers from McMaster University and MIT (Massachusetts Institute of Technology).

the superbug

The superbug in question is Acinetobacter baumanniiwhich the WHO (World Health Organization) has classified as a “critical” threat among its “priority pathogens” – a group of bacterial families that pose the “greatest threat” to human health.

According to the WHO, bacteria have the inherent ability to find new ways to resist treatment and can pass on genetic material that also allows other bacteria to become resistant to drugs.

A baumannii poses a threat to hospitals, nursing homes, and patients who need ventilators and blood catheters, as well as those with open wounds from surgery.

Bacteria can live for long periods on shared surfaces and equipment. And it can often be spread by contaminated hands. In addition to bloodstream infections, A. baumannii can cause urinary tract and lung infections.

According to the Centers for Disease Control and Prevention, the bacteria can also “colonize” or live in a patient without causing infection or symptoms.

Research

The researchers used an AI algorithm to screen thousands of antibacterial molecules in an attempt to predict new structural classes. As a result of the AI ​​screening, the scientists were able to identify a new antibacterial compound, which they named abaucin.

We had a set of data telling us which chemicals were capable of killing a bunch of bacteria and which weren’t. My job was to train this model, and all this model would essentially do is tell us whether or not the new molecules would have antibacterial properties.

Gary Liu, a MacMaster University graduate student who worked on the research

After the scientists trained the AI ​​model, they used it to analyze 6,680 compounds that hadn’t been found previously. The analysis took an hour and a half and ended up yielding several hundred compounds, 240 of which were then tested in the laboratory. Lab tests have finally revealed nine potential antibiotics, including abaucin.

The tests

The scientists then tested the new molecule against the superbug in a mouse model of wound infection and found that the molecule suppressed the infection.

This work validates the benefits of machine learning in the search for new antibiotics. Using artificial intelligence, we can rapidly explore vast regions of chemical space, significantly increasing the chances of discovering fundamentally new antibacterial molecules.

Jonathan Stokes, assistant professor in McMaster University’s department of biomedicine and biochemistry, who helped lead the study.

With information from The Guardian

The post Science bets on artificial intelligence to stop a deadly superbug that appeared for the first time on Olhar Digital.

Source: Olhar Digital