Artificial intelligence yields powerful new antibiotic

  • Stokes JM, et al.
  • Cell
  • 20 Feb 2020

  • curated by Priscilla Lynch
  • Medical News
Access to the full content of this site is available only to registered healthcare professionals. Access to the full content of this site is available only to registered healthcare professionals.

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.”