Anewly designed artificial intelligence tool based on the structure of the brain has identified a molecule capable of wiping out a number of antibiotic-resistant strains of bacteria, according to a study published on February 20 in Cell. The molecule, halicin, which had previously been investigated as a potential treatment for diabetes, demonstrated activity against Mycobacterium tuberculosis, the causative agent of tuberculosis, and several other hard-to-treat microbes.
The discovery comes at a time when novel antibiotics are becoming increasingly difficult to find, reports STAT, and when drug-resistant bacteria are a growing global threat. The Interagency Coordination Group (IACG) on Antimicrobial Resistance convened by United Nations a few years ago released a report in 2019 estimating that drug-resistant diseases could result in 10 million deaths per year by 2050. Despite the urgency in the search for new antibiotics, a lack of financial incentives has caused pharmaceutical companies to scale back their research, according to STAT.
“I do think this platform will very directly reduce the cost involved in the discovery phase of antibiotic development,” coauthor James Collins of MIT tells STAT. “With these models, one can now get after novel chemistries in a shorter period of time involving less investment.”
Although earlier AI-based models required human supervision and produced inconsistent results, reports STAT, this new deep learning approach was trained on a library of more than 2,000 chemical compounds with something known about their antibacterial potency, using those data to predict function based on structure. The platform identified molecules that looked quite different from existing antibiotics, overcoming the bias that human researchers exhibit when they search for potential anti-bacterial compounds that have structures similar to existing antibiotics, according to STAT.
The team first used the deep learning model to screen a library of 6,000 molecules for those that may be effective against E. coli. The search detected halicin, which the authors tested against a number of cultured bacterial strains, finding that the molecule “displays bactericidal activity against a wide phylogenetic spectrum of pathogens including Mycobacterium tuberculosis and carbapenem-resistant Enterobacteriaceae,” the authors write in the paper. Halicin also fights C. difficile and a “pan-resistant” infection in mouse models, the team found.
In a subsequent screen of more than 107 million molecules from the ZINC15 database provided by the University of California, San Francisco, the AI tool identified eight molecules with structures distinct from known antibiotics but that might have potent anti-bacterial properties.
“The work really is remarkable,” Jacob Durrant of the University of Pittsburgh, a drug design researcher who was not part of the study, tells The Guardian. “Their approach highlights the power of computer-aided drug discovery. It would be impossible to physically test over 100m compounds for antibiotic activity.”
“Now we’re finding leads among chemical structures that in the past we wouldn’t have even hallucinated that those could be an antibiotic,” says Nigam Shah, biomedical informatics researcher at Stanford University who was not involved in the study, in remarks to STAT. Shah cautions that a long and complex process would be required before this new antibiotic could be tested in humans, but says it’s a step in the right direction. “It greatly expands the search space into dimensions we never knew existed.”
Amy Schleunes is an intern at The Scientist. Email her at firstname.lastname@example.org.