- Monday, October 02, 2023
Using machine learning, the scientists examined a vast catalog of 7,000 potential drug compounds to identify one that could inhibit the growth of Acinetobacter baumannii
By: Kimberly Rodrigues
Researchers from Massachusetts Institute of Technology (MIT) and McMaster University have utilised machine learning, a branch of Artificial Intelligence (AI), to discover a new antibiotic that shows promise in fighting drug-resistant infections caused by a bacteria called Acinetobacter baumannii.
This bacterium is commonly found in hospitals and can lead to severe infections like pneumonia and meningitis, making it a significant concern for healthcare settings and wounded soldiers.
Using AI, the scientists examined a vast catalog of 7,000 potential drug compounds to identify one that could inhibit the growth of A. baumannii.
“Acinetobacter can survive on hospital doorknobs and equipment for long periods of time, and it can take up antibiotic resistance genes from its environment. It’s really common now to find A. baumannii isolates that are resistant to nearly every antibiotic,” Jonathan Stokes, a former MIT postdoc, said in a statement.
This discovery holds importance because Acinetobacter has developed resistance to numerous antibiotics, making it challenging to treat.
The study, published in the journal Nature Chemical Biology, highlights how machine learning techniques allow for rapid exploration of chemical space, increasing the chances of finding new molecules with antibacterial properties.
This finding further supports the valuable role of AI in expediting the identification of novel antibiotics.
The AI system was initially trained to identify chemical structures capable of inhibiting the growth of E. coli.
After screening over 100 million compounds, the researchers discovered a molecule named halicin, which demonstrated effectiveness against E. coli and various other bacterial species.
Focusing on Acinetobacter as a priority, the team conducted experiments where they exposed A. baumannii to around 7,500 different chemical compounds in a lab setting. They fed the structural information of each molecule to the AI system to assess their potential.
Eventually, they identified a drug called abaucin, which effectively treated wound infections caused by A. baumannii and exhibited activity against several drug-resistant infections.
Further investigation revealed that the drug kills cells by disrupting a process called lipoprotein trafficking, which is responsible for protein transportation within cells.
The researchers believe that the unique lipoprotein trafficking mechanism of A. baumannii makes abaucin specifically effective against this bacterium, giving it a narrow spectrum of activity.
While the experimental data acquisition is ongoing, the findings so far offer promising prospects for addressing multidrug-resistant bacterial infections, especially those caused by Acinetobacter.
