Scientists have harnessed artificial intelligence to discover a new antibiotic capable of killing a deadly superbug, according to a study published in Nature Chemical Biology. The research, led by teams from McMaster University and the Massachusetts Institute of Technology, identified abaucin, a compound effective against Acinetobacter baumannii, a bacterium classified by the World Health Organization as a 'critical' priority pathogen.
Acinetobacter baumannii poses a significant threat in healthcare settings, including hospitals and nursing homes, particularly for patients on ventilators, with blood catheters, or recovering from surgery. The bacterium can survive on surfaces for extended periods and spread via contaminated hands, causing infections in the blood, urinary tract, and lungs. The WHO warns that it has inherent resistance mechanisms and can transfer drug-resistant genes to other bacteria.
The research team employed an AI algorithm to screen thousands of antibacterial molecules, predicting new structural classes. Gary Liu, a graduate student at McMaster University involved in the study, explained that the AI model was trained to identify which chemicals could kill bacteria, thereby streamlining the drug discovery process. The algorithm analysed 6,680 compounds in 90 minutes, yielding several hundred candidates; subsequent laboratory tests on 240 compounds revealed nine potential antibiotics, including abaucin.
Further testing in a mouse wound infection model demonstrated that abaucin suppressed the infection. Jonathan Stokes, assistant professor at McMaster University and co-lead author, highlighted the benefits of machine learning: 'Using AI, we can rapidly explore vast regions of chemical space, significantly increasing the chances of discovering fundamentally new antibacterial molecules.' He added that AI methods offer a cost-effective way to accelerate antibiotic discovery, which is crucial as pathogens continue to evolve resistance.
