Scientists at MIT and McMaster University have utilised artificial intelligence (AI) to identify a new antibiotic with the potential to combat drug-resistant infections caused by Acinetobacter baumannii, a bacterium commonly found in hospital settings.
Acinetobacter baumannii is known to cause severe infections such as pneumonia and meningitis, and it is particularly problematic due to its ability to acquire antibiotic resistance genes.
The research team trained a machine-learning algorithm to evaluate thousands of chemical compounds for their effectiveness in inhibiting the growth of A. baumannii. After analyzing a set of 6,680 compounds, the algorithm identified several potential candidates. The researchers tested 240 of these compounds in the laboratory and discovered nine antibiotics, one of which showed significant potency against A. baumannii while sparing other beneficial bacteria in the human gut.
The compound, named abaucin, was originally explored as a potential diabetes drug and demonstrated the ability to treat A. baumannii wound infections in mouse models. Further investigations revealed that abaucin disrupts lipoprotein trafficking, a process crucial for bacterial cell function.
The drug targets a protein called LolE, which is involved in this process, and its selective action against A. baumannii is thought to be due to slight differences in lipoprotein trafficking mechanisms compared to other Gram-negative bacteria.
“This finding further supports the premise that AI can significantly accelerate and expand our search for novel antibiotics,” says James Collins, the Termeer Professor of Medical Engineering and Science in MIT’s Institute for Medical Engineering and Science (IMES) and Department of Biological Engineering. “I’m excited that this work shows that we can use AI to help combat problematic pathogens such as A. baumannii.”
The team plans to optimise the compound’s medicinal properties and develop it for future use in patients. Additionally, they aim to apply their AI modeling approach to identify potential antibiotics for other drug-resistant infections caused by pathogens like Staphylococcus aureus and Pseudomonas aeruginosa. This breakthrough showcases the potential of AI in accelerating the discovery of novel antibiotics and combating multidrug-resistant bacterial infections.
