A powerful new structurally distinct antibacterial molecule has been discovered through the use of an artificial intelligence learning algorithm, reports a new study in Cell.
Researchers trained a deep neural network to predict molecules with antibacterial activity. They performed predictions on multiple chemical libraries and discovered a molecule, halicin, from the Drug Repurposing Hub (a library of about 6000 compounds), which is structurally divergent from conventional antibiotics and displays bactericidal activity against a wide phylogenetic spectrum of pathogens including Mycobacterium tuberculosis and carbapenem-resistant Enterobacteriaceae.
Halicin effectively treated Clostridioides difficile and pan-resistant Acinetobacter baumannii infections in murine models.
E. coli did not develop any resistance to halicin during a 30-day treatment period; whereas it started to develop resistance to ciprofloxacin within 1 to 3 days.
Additionally, from a discrete set of 23 empirically tested predictions from >107 million molecules curated from the ZINC15 database, their model identified 8 antibacterial compounds structurally distant from known antibiotics.
“We wanted to develop a platform that would allow us to harness the power of artificial intelligence to usher in a new age of antibiotic drug discovery,” said study co-author Prof James Collins. “Our approach revealed this amazing molecule which is arguably one of the more powerful antibiotics that has been discovered.”