Canadian and US researchers have - with the help of artificial intelligence - discovered a new antibiotic that kills a deadly species of "superbug" which can infect wounds and cause pneumonia, media reports said.

'Acinetobacter baumannii' is one of the three superbugs the World Health Organisation has identified as a "critical" threat, as the bacteria can withstand multiple antibiotics and survives on surfaces and medical equipment.

Infections caused by superbugs or antibiotic resistant infections kill more than a million people a year.

Dr Jonathan Stokes, from Canada's McMaster University, described this bug as "public enemy number one" as it's "really common" to find cases where it is "resistant to nearly every antibiotic", the BBC reported.

Scientists used AI to narrow down thousands of potential chemicals to a handful that could be tested in the laboratory and zeroed in on a potent, experimental antibiotic called abaucin. However, it will need further tests before being used, with the researchers saying that the process could take up to 2030.

Researchers first had to "train" the AI, taking thousands of drugs where the precise chemical structure was known, and manually tested them on Acinetobacter baumannii to see which could slow it down or kill it.

This information was fed into the AI so it could learn the chemical features of drugs that could attack the problematic bacterium, the BBC reported.

The AI was then unleashed on a list of 6,680 compounds whose effectiveness was unknown. The results - published in Nature Chemical Biology - showed it took the AI an hour and a half to produce a shortlist.

The researchers tested 240 in the laboratory, and found nine potential antibiotics. One of them was the incredibly potent abaucin, with laboratory experiments showed it could treat infected wounds in mice and was able to kill the bacteria samples from patients.

More significantly, abaucin only killed A. baumannii and had no effect on other species of bacteria, unlike many antibiotics that kill bacteria indiscriminately. Researchers believe the precision of abaucin will make it harder for drug-resistance to emerge, and could lead to fewer side-effects.

However, the drug has to be further tested in the laboratory and then in clinical trials. Researchers expects the first AI antibiotics could take until 2030 until they are available to be prescribed.

In principle, AI could screen tens of millions of potential compounds - something that would be impractical to do manually, the BBC reported,

The researchers tested the principles of AI-aided antibiotic discovery in E. coli in 2020, but have now used that knowledge to focus on the big superbugs. They plan to look at Staphylococcus aureus and Pseudomonas aeruginosa next.

"This finding further supports the premise that AI can significantly accelerate and expand our search for novel antibiotics," said Prof James Collins, from the Massachusetts Institute of Technology. (IANS/NS)