A new powerful antibiotic against the superbug Acinetobacter baumanniiidentified byOms as one of the most dangerous resistant bacteria in the world, was discovered thanks to theartificial intelligencethrough a process that promises to revolutionize this field: the new molecule, in fact, was found by the algorithm between almost 7 miles candidates in just 2 hours.
Revolutionary result – The result, published in the magazine
Nature Chemical Biology by a Canadian-led group
McMaster Universitypaves the way for
possibility of greatly speeding up the process of discovering new antibiotics for many other microorganisms that threaten human health and beyond. Discovering new antibiotics against the A. baumannii bacterium, which is often found in hospitals and can lead to serious infections, using traditional methods has proven to be a challenge, due to the large amount of time, high costs and poor results .
The discovery Researchers led by
Gary Liu,
Denise Catacutan e
Khushi Rathod they then turned to a
algorithm able to access hundreds of millions, perhaps billions, of molecules with antibacterial properties. To get the data to train it with, the study authors first cultured the bacterium in a lab, exposing it to about
7.500 different chemical compounds: the structure of each of these was then fed to the algorithm, together with the information associated with their effectiveness. Once ready, the AI sifted through a library of
6.680 molecules never evaluated before, providing i
240 most promising candidates in a couple of hours. At this point, the ball passed to the researchers, who by testing the compounds in the laboratory identified the new antibiotic.