Antibiotics Found by AI Can Terminate Dangerous Hospital Bugs

This multidrug-resistant bacteria, which poses a specific danger to patients in hospitals and those whose care needs devices like ventilators and blood catheters, is described by the World Health Organisation as being particularly dangerous. 

According to the latest research that was published on Thursday in the scientific journal Nature Chemical Biology, the researchers are from the Massachusetts Institute of Technology and McMaster University, as per the Guardian.

The dangerous bug

Acinetobacter baumannii is a superbacterium. It is one of the high-priority pathogens designated for research and the creation of new antibiotics by the International Organisation for Health. According to the WHO, Acinetobacter can lead to pneumonia and bloodstream infections, both of which are serious and frequently fatal illnesses.

"These bacteria have built-in abilities to find new ways to resist treatment and can pass along genetic material that allows other bacteria to become drug-resistant as well," said the WHO.

Patients who have open surgical incisions are at high risk for infection from Acinetobacter baumannii. The Acinetobacter genus of bacteria (germs) is frequently found in the environment, such as in soil and water, according to the Centres for Disease Control and Prevention (CDC). Acinetobacter baumannii can infect wounds in various areas of the body, as well as the blood, urinary system, and lungs (pneumonia).

Gary Liu's explanation

In an effort to discover new structural classes, scientists used an AI system to analyse hundreds of antibiotic substances. The AI screening resulted in the discovery of a novel antibacterial molecule by the researchers, which they named abaucin.

A graduate student from MacMaster University, Gary Liu, said, "We had a whole bunch of data that was just telling us about which chemicals were able to kill a bunch of bacteria and which ones weren’t. My job was to train this model, and all that this model was going to be doing is telling us essentially if new molecules will have antibacterial properties or not."

"Then basically through that, we’re able to just increase the efficiency of the drug discovery pipeline and … hone in all the molecules that we really want to care about," he added.

"Using AI, we can rapidly explore vast regions of chemical space, significantly increasing the chances of discovering fundamentally new antibacterial molecules," he said adding, "We know broad-spectrum antibiotics are suboptimal and that pathogens have the ability to evolve and adjust to every trick we throw at them … AI methods afford us the opportunity to vastly increase the rate at which we discover new antibiotics, and we can do it at a reduced cost. This is an important avenue of exploration for new antibiotic drugs," said Jonathan Stokes, an assistant professor.