MIT researchers used a machine-learning algorithm to identify a drug called halicin that kills many strains of bacteria. Halicin (top row) prevented the development of antibiotic resistance in E. coli, while ciprofloxacin (bottom row) did not. [Image courtesy of the Collins Lab at MIT]

Researchers at Massachusetts Institute of Technology (MIT) have harnessed a machine-learning algorithm to identify a new antibiotic compound that, in laboratory tests, killed many of the world’s most challenging disease-causing bacteria, including some strains that are resistant to all known antibiotics. The new antibiotic candidate, which has been given the name halicin—after the fictional artificial intelligence system from “2001: A Space Odyssey,”—was discovered in the Drug Repurposing Hub, and is structurally different to conventional antibiotics. Initial in vivo experiments showed that halicin was effective against Clostridium difficile and pan-resistant Acinetobacter baumannii infections in two mouse models.

“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 James Collins, PhD, the Termeer professor of medical engineering and science in MIT’s Institute for Medical Engineering and Science (IMES) and department of biological engineering. “Our approach revealed this amazing molecule which is arguably one of the more powerful antibiotics that has been discovered.” Collins and colleagues reported on their discovery in Cell, in a paper titled, “A Deep Learning Approach to Antibiotic Discovery.”

Antibiotic resistance is a major global health threat, but very few new antibiotics have been developed over recent decades, and most of those newly approved antibiotics are variants of existing drugs. Current methods for screening new antibiotics are also often prohibitively costly, require a significant time investment, and are commonly limited to a narrow spectrum of chemical diversity. And, as the authors commented, “ … the decreasing development of new antibiotics in the private sector that has resulted from a lack of economic incentives is exacerbating this already dire problem.” In fact, they noted, without immediate action to discover and develop new antibiotics, it’s estimated that drug-resistant bacterial infections could account for 10 million deaths per year by 2050.

“We’re facing a growing crisis around antibiotic resistance, and this situation is being generated by both an increasing number of pathogens becoming resistant to existing antibiotics, and an anemic pipeline in the biotech and pharmaceutical industries for new antibiotics,” commented Collins.

The idea of using predictive computer models for in silico screening is not new, but until now, these models were not sufficiently accurate to transform drug discovery. Previously, molecules were represented as vectors reflecting the presence or absence of certain chemical groups. New neural networks can learn these representations automatically, mapping molecules into continuous vectors that are subsequently used to predict their properties. “The adoption of machine learning approaches is ideally suited to address these hurdles,” the scientists stated. “Indeed, modern neural molecular representations have the potential to (1) decrease the cost of lead molecule identification because screening is limited to gathering appropriate training data, (2) increase the true positive rate of identifying structurally novel compounds with the desired bioactivity, and (3) decrease the time and labor required to find these ideal compounds from months or years to weeks.”

To try to find completely novel antibiotic compounds, Collins teamed up with Regina Barzilay, PhD, Tommi Jaakkola, PhD, 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. Barzilay is the Delta Electronics professor of electrical engineering and computer science and Jaakkola is a professor, at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL). Barzilay and Collins are faculty co-leads for MIT’s Abdul Latif Jameel Clinic for Machine Learning in Health.

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. The resulting machine learning model, which can screen more than a hundred million chemical compounds in a matter of days, is designed to pick out potential antibiotics that kill bacteria using different mechanisms than those of existing drugs. “The machine learning model can explore, in silico, large chemical spaces that can be prohibitively expensive for traditional experimental approaches,” said Barzilay.

The trained model was tested on the Broad Institute’s Drug Repurposing Hub, a library of about 6,000 compounds. The model picked out one molecule in particular that was predicted to have strong antibacterial activity and had a chemical structure that was different from any existing antibiotics. Using a separate machine-learning model, the researchers also showed that this molecule would likely have low toxicity to human cells.

The newly identified molecule, a c-Jun N-terminal kinase inhibitor, SU3327—which the team renamed halicin—had previously been investigated as a possible diabetes drug. Tests showed that halicin effectively killed many of the dozens of lab-grown, patient-derived bacterial strains against which it was tested, including drug-resistant Clostridium difficile, Acinetobacter baumannii, and Mycobacterium tuberculosis. The drug worked against every species tested, with the exception of Pseudomonas aeruginosa, a difficult-to-treat lung pathogen.

Experiments also showed that E. coli did not develop any resistance to halicin during a 30-day treatment period. In contrast, the bacteria started to develop resistance to the antibiotic ciprofloxacin within one to three days, and after 30 days, the bacteria were about 200 times more resistant to ciprofloxacin than they were at the beginning of the experiment.

The team carried out a series of experiments to test halicin’s effectiveness in live mice. They showed that a halicin-containing ointment completely cleared infection with A. baumannii—a bacterium that has infected many U.S. soldiers stationed in Iraq and Afghanistan—within 24 hours. “Of note, the World Health Organization has designated A. baumannii as one of the highest priority pathogens against which new antibiotics are urgently required,” the authors wrote.

Preliminary analyses suggested that halicin kills bacteria by disrupting their ability to maintain an electrochemical gradient across their cell membranes. This gradient is necessary, among other functions, to produce ATP, so if the gradient is disrupted, the cells die. The researchers suggested that it could be difficult for bacteria to develop resistance to drugs that target this mechanism. “When you’re dealing with a molecule that likely associates with membrane components, a cell can’t necessarily acquire a single mutation or a couple of mutations to change the chemistry of the outer membrane. Mutations like that tend to be far more complex to acquire evolutionarily,” Stokes commented. The researchers will continue their research with halicin, and aim to work with a pharmaceutical company or nonprofit organization, with a view to its development for use in humans.

The team also used their computational model to screen more than 100 million molecules selected from the ZINC15 database, an online collection of about 1.5 billion chemical compounds. The screen, which took three days, identified 23 candidates that were structurally dissimilar to existing antibiotics and were also predicted to be nontoxic to human cells. The researchers found that eight of these molecules showed antibacterial activity in tests against five species, with two demonstrating particular efficacy. “Additionally, from a discrete set of 23 empirically tested predictions from >107 million molecules curated from the ZINC15 database, our model identified eight antibacterial compounds that are structurally distant from known antibiotics,” the investigators noted. They also plan to test these molecules further, and to screen more of the ZINC15 database.

As well as identifying antibiotic activity in existing compounds, the team aims to use the model to help design new antibiotics and to optimize existing molecules, based on what it has learned about chemical structures that enable drugs to kill bacteria. The potential exists to train the model to add features that would make a particular antibiotic target only certain pathogenic bacteria, and so prevent it from killing beneficial bacteria in a patient’s digestive tract. “ … with repeated training cycles across phylogenetically diverse species, it may be possible to predict molecules with antibacterial activity against a specified spectrum of pathogens,” the authors stated. “This has the promise to result in narrow-spectrum agents that can be administered systemically without damaging the host microbiota. Moreover, by training on multidrug-resistant pathogens, it may be possible to identify scaffolds that overcome pre-existing resistance determinants.”

The investigators say their results indicate that “the time is ripe” for the application of machine learning approaches to antibiotic discovery, and potentially help to outpace the spread of antibiotic resistance. “ … such efforts could increase the rate at which new molecular entities are discovered, decrease the resources required to identify these molecules, and decrease associated costs.”

 

Previous articleCRISPR Base Editor Repairs Faulty Genes in Cystic Fibrosis Organoids
Next articleOptogenetic Modulation for the Treatment of Traumatic Brain Injury
Previous articleCRISPR Base Editor Repairs Faulty Genes in Cystic Fibrosis Organoids
Next articleOptogenetic Modulation for the Treatment of Traumatic Brain Injury