Join the club for FREE to access the whole archive and other member benefits.

Artificial Intelligence assists in discovery of potent antibiotic to combat superbugs

AI scrutinized a list of 6,680 compounds, ultimately shortlisting potential antibiotics in under two hours

25-May-2023

Key points from article :

Scientists have utilized artificial intelligence (AI) to discover a new antibiotic, named 'abaucin,' capable of killing a deadly superbug species.

AI was instrumental in sifting through thousands of potential chemicals, resulting in a select few that were lab-tested.

The researchers from Canada and the U.S. emphasize that AI can expedite the discovery of novel drugs significantly.

The new antibiotic could be a breakthrough in the fight against drug-resistant bacteria, a growing problem as bacteria evolve resistance to current antibiotics.

The research targeted Acinetobacter baumannii, a superbug recognized by the World Health Organization as a critical threat, often resistant to multiple antibiotics.

The AI was trained using data from thousands of drugs whose chemical structures were known and manually tested against Acinetobacter baumannii.

Preliminary experiments showed that abaucin effectively treated infected wounds in mice and killed A. baumannii samples from patients.

However, the researchers stress that this discovery is just the beginning, with more laboratory refinement and clinical trials necessary before prescription use, possibly by 2030.

Research led by McMaster University published in Nature Chemical Biology.

Mentioned in this article:

Click on resource name for more details.

McMaster University

One of four Canadian universities listed among the Top 100 universities in the world

Nature Chemical Biology

Scientific journal that publishes the most compelling research, opinion and analysis at the intersection of chemistry and biology

Topics mentioned on this page:
Antibiotic Resistance, AI in Healthcare
Artificial Intelligence assists in discovery of potent antibiotic to combat superbugs