Researchers Discover New Antibiotic for Drug-resistant Bacteria with AI
McMaster University and the Massachusetts Institute of Technology researchers using artificial intelligence (AI) have discovered a new type of antibiotic against a drug-resistant bacteria according to a new study. The study was published in the peer-reviewed scientific journal Nature Chemical Biology.
The investigation centered on Actinetobacter baumanii, a type of bacteria commonly found in hospitals and healthcare environments, which adheres to surfaces such as doorknobs and counters. By acquiring fragments of DNA from other organisms it encounters, this bacterium assimilates advantageous genes that provide resistance against medical treatments employed by doctors. Acinetobacter baumannii has been classified as a “critical” threat among its “priority pathogens” by the World Health Organization.
This particular species is responsible for challenging skin, blood, or respiratory infections that are hard to treat. In 2019, the United States Centers for Disease Control and Prevention emphasized the urgent requirement for new forms of antibiotics to effectively address Acinetobacter baumanii infections, considering them to be the top priority in terms of medical necessity.
Leveraging the power of artificial intelligence, researchers utilized it to significantly reduce the vast pool of thousands of potential chemicals to only a few viable candidates that could undergo laboratory testing. Utilising a trained AI model, they were able to screen a selection of 6,680 molecules within a few hours.
From the initial pool of compounds, they successfully narrowed down the search to 240 chemicals, which were subjected to rigorous laboratory testing. Through this testing process, they were able to further refine the list and identify the top nine inhibitors with the highest efficacy against the bacteria. Subsequently, the researchers delved deeper into the molecular structure of each of these nine compounds.
As a result, they successfully identified a robust and experimental antibiotic named Abaucin, which exhibits significant potency. During the testing phase, researchers applied the antibiotic to the skin of mice deliberately infected with the drug-resistant superbug. The results showed that the antibiotic effectively suppressed the growth of the bacteria. This outcome indicates that the approach employed in developing the antibiotic has the potential to be applied in the creation of tailored antibiotics specifically designed to combat various drug-resistant pathogens. However, before its practical application, further extensive testing is required to ensure its effectiveness and safety.
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 says:
“This finding further supports the premise that AI can significantly accelerate and expand our search for novel antibiotics. I’m excited that this work shows that we can use AI to help combat problematic pathogens such as A. baumannii.”
The study is a great step forward for unveiling the potential of AI in drug discovery. According to the study, the discovery of abaucin, facilitated by machine learning, exemplifies the practicality of algorithmic methods in uncovering novel antibacterial molecules targeting A. baumannii. This breakthrough introduces a highly promising, narrow-spectrum molecular framework that holds significant potential in combating one of the most formidable Gram-negative pathogens worldwide. The findings contribute to advancing the field and offer a valuable addition to the arsenal of treatments for challenging bacterial infections.
Recommended Companies
More Headlines
