Approximately three years ago, using a deep learning algorithm, MIT researchers identified a powerful new antibiotic compound—potentially the first novel broad-based antibiotic in more than four decades.
Quoting from the February 20, 2020, edition of MIT News author Anne Trafton, “The drug killed many of the world’s most problematic disease-causing bacteria, including some strains that are resistant to all known antibiotics. It also cleared infections in two different mouse models.”
The MIT team decided to name the new molecule after the fictional artificial intelligence (AI) system in the movie “2001: A Space Odyssey”—halicin.
A team from Indiana University decided to test halicin against the bacteria in biofilms. Their study, “Halicin Is Effective Against Staphylococcus aureus Biofilms In Vitro,” appears in the August 2022 edition of Clinical Orthopaedics and Related Research.
“Biofilm-based infections are among the worst complications in orthopaedics,” said Edward Greenfield, Ph.D., co-author and professor of orthopaedic surgery at the Indiana University, to OTW. “Halicin was recently shown to kill many species of planktonic bacteria, including drug-resistant strains, but was not tested against biofilms. Importantly, it was effective against both proliferating and quiescent bacteria. Since quiescence is a major cause of antibiotic resistance by bacteria in biofilms, we hypothesized that halicin might also kill bacteria in biofilms.”
The researchers used 96-well peg plates to measure minimal biofilm eradication. “The peg plates are commercially available culture devices designed for biofilm studies,” explained Dr. Greenfield. “
Each peg sticks down into a bacterial suspension contained in a well of a standard 96-well plate. After a suitable culture period, highly reproducible biofilms form on the tip of each peg and the biofilms can then be exposed to antibiotics or other anti-bacterial agents. We used the peg plates to study effects of halicin and conventional antibiotics on S. aureus in both less-mature and more-mature biofilms.”
After S. aureus-Xen36 biofilm formation, the scientists removed the planktonic bacteria from the cultures, and the biofilms were exposed to halicin, tobramycin, cefazolin, vancomycin, or rifampicin for 20 hours.
According to the study authors, there were “no differences between halicin’s effectiveness against planktonic S. aureus and 3-day biofilms (minimum inhibitory concentrations) and minimal biofilm eradication concentrations75 for 3-day biofilms was 25 μM. Halicin was eightfold less effective against more mature 7-day biofilms (minimal biofilm eradication concentrations75 = 200 μM).”
“Similarly, tobramycin was equally effective against planktonic culture and 3-day biofilms (minimum inhibitory concentrations and minimal biofilm eradication concentrations75 for 3-day biofilms was 20 μM). Tobramycin’s minimal biofilm eradication concentrations75 against more mature 7-day biofilms was 320 μM, which is 16-fold greater than its planktonic minimum inhibitory concentrations.”
“In contrast, the minimal biofilm eradication concentrations75 for cefazolin, vancomycin, and rifampicin against more mature 7-day biofilms were more than 1000-fold, 500-fold, and 3125-fold greater than their planktonic minimum inhibitory concentrations, respectively, consistent with those antibiotics’ relative inactivity against biofilms.
“Encouragingly,” Dr. Greenfield told OTW, “both my lab and an independent group of investigators (van Gent et al. 2022, Antibiotics 1(5):673) showed that halicin is effective against bacteria in biofilms. Remarkably, the two papers were published online on the exact same day (May 17, 2022).”
“If we find that halicin is also effective against biofilm-based infections in animal models, it should then be tested in patients with orthopaedic infections. If those studies show positive results, halicin could be an extremely useful new drug for orthopaedic infections.”
Halicin’s AI Roots
Halicin may not be the first, but it is certainly the poster child of an AI discovered pharmaceutical product and may well represent the future of drug discovery.
Halicin was created by an MIT research team that employed artificial intelligence, specifically a neural networking type algorithm to screen more than a hundred million chemical compounds in a matter of days and provide a predictive value as to the bacteria killing capacity to various theoretical antibiotic molecules.
Again, from the MIT News article by Anne Trafton, the lead researcher, James Collins, the Termeer Professor of Medical Engineering Science in MIT’s Institute for Medical Engineering and Science (IMES) and Department of Biological Engineering, said, “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. Our approach revealed this amazing molecule which is arguably one of the more powerful antibiotics that has been discovered.”
“To try to find completely novel compounds, Dr. Collins teamed up with Barzilay, Professor Tommi Jaakkola, and their students Kevin Yang, Kyle Swanson, and Wengong Jin, who have previously developed machine-learning computer models that can be trained to analyze the molecular structures of compounds and correlate them with particular traits, such as the ability to kill bacteria.”
“The idea of using predictive computer models for “in silico” screening is not new…but, the new neural networks can learn these representations automatically, mapping molecules into continuous vectors which are subsequently used to predict their properties.”
“In this case, the researchers designed their model to look for chemical features that make molecules effective at killing E. coli. To do so, they trained the model on about 2,500 molecules, including about 1,700 FDA-approved drugs and a set of 800 natural products with diverse structures and a wide range of bioactivities.”
“Once the model was trained, the researchers tested it on the Broad Institute’s Drug Repurposing Hub, a library of about 6,000 compounds. The model picked out one molecule that was predicted to have strong antibacterial activity and had a chemical structure different from any existing antibiotics. Using a different machine-learning model, the researchers also showed that this molecule would likely have low toxicity to human cells.”
Named halicin, the MIT team then tested this AI discovered molecule “against dozens of bacterial strains isolated from patients and grown in lab dishes and found that it was able to kill many that are resistant to treatment, including Clostridium difficile, Acinetobacter baumannii, and Mycobacterium tuberculosis. The drug worked against every species that they tested, with the exception of Pseudomonas aeruginosa, a difficult-to-treat lung pathogen.”
