A team of scientists from Canada and the United States have applied artificial intelligence to discover a new drug that has proven effective against a deadly, antibiotic-resistant superbug attacking the most vulnerable hospital patients. The discovery, carried out by the McMaster University and the Massachusetts Institute of Technology (MIT)may be key in the search for other drugs to treat these pathogens known as “superbugs,” which have developed immunity against all known treatments and could become a more common cause of death than cancer in just a few decades.
Specifically, researchers have found a new drug to treat the bacteria Acinetobacter baumannii, identified by the World Health Organization as one of the most dangerous in the world, since it is extremely difficult to eradicate. Usually contracted in the hospital setting, this pathogen can cause pneumonia, meningitis, or severely infect wounds, making it life-threatening.
The researchers have published the results of their work in the magazine Nature Chemical Biologywhere they explain that they have used an artificial intelligence algorithm to predict new antibacterial molecular structures, which has led them to identify a new compound, which they have named abaucin.
Unlike traditional methods, which are more expensive and have a very limited scope, new algorithmic approaches have access to millions of molecules with antibacterial properties and their combinations, considerably speeding up the research process.
“This work validates the benefits of machine learning in the search for new antibiotics,” he told McMaster University. Jonathan Stokeslead author of the article and professor of Biomedicine and Biochemistry at this university, who also highlighted that, thanks to artificial intelligence, “they can now quickly explore vast regions of chemical space, significantly increasing the chances of discovering new antibacterial molecules.”
Stokes has developed the study together with James J.Collinsprofessor of Medical Engineering and Science at MIT, and students Gary Liu and Denise Catacutan.
artificial intelligence training
To find the new antibiotic, the researchers first had to train artificial intelligence, providing thousands of molecules that had shown some efficacy against the bacteria Acinetobacter baumannii. Since they have a precise chemical structure, the algorithm learned the characteristics that work best against the pathogen, and provided a list of more than 6,500 hitherto unknown compounds. The scientific team tested the 240 most promising in the laboratory and found nine potential antibiotics, including abaucin.
Laboratory experiments have shown its efficacy in treating infected skin wounds in mice and killing samples of Acinetobacter baumannii belonging to human beings. The next step now will be to perfect the drug in the laboratory, before carrying out clinical trials with patients. The research team he does not believe that the first antibiotics discovered with the help of artificial intelligence can be commercialized before 2030.