A powerful new antibiotic compound has been identified by researchers at MIT using a machine-learning algorithm. The drug killed many of the world's most problematic disease-causing bacteria in laboratory tests, including some strains that are resistant to all known antibiotics. It also cleared infections in two different mouse models. The computer 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. Regina Barzilay and James Collins, who are faculty co-leads for MIT's Abdul Latif Jameel Clinic for Machine Learning in Health (J-Clinic), are the senior authors of the study, which appears today in Cell. The first author of the paper is Jonathan Stokes, a post-doc at MIT and the Broad Institute of MIT and Harvard. J-Clinic is a key part of the MIT Quest for Intelligence and focuses on developing machine learning technologies to revolutionize the prevention, detection, and treatment of disease. It concentrates on creating and commercializing high-precision, affordable, and scalable machine learning technologies in areas of health care ranging from diagnostics to pharmaceuticals. In their new study, the researchers also identified several other promising antibiotic candidates, which they plan to test further. They believe the model could also be used to design new drugs, based on what it has learned about chemical structures that enable drugs to kill bacteria. "The machine learning model can explore, in silico, large chemical spaces that can be prohibitively expensive for traditional experimental approaches," says Barzilay, the Delta Electronics Professor of Electrical Engineering and Computer Science in MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL). Over the past few decades, very few new antibiotics have been developed, and most of those newly approved antibiotics are slightly different variants of existing drugs. Current methods for screening new antibiotics are often prohibitively costly, require a significant time investment, and are usually limited to a narrow spectrum of chemical diversity. "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 anaemic pipeline in the biotech and pharmaceutical industries for new antibiotics," Collins says. 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. However, the new neural networks can learn these representations automatically, mapping molecules into continuous vectors which are subsequently used to predict their properties. The molecule picked out by the model 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. "The world is in desperate need of new antibiotics to combat dangerous diseases, so it is hugely encouraging that the team at J-Clinic at MIT, have helped make a breakthrough in finding a genuinely new one using machine learning," said Fady Jameel, president, International of Community Jameel. "For decades, Community Jameel has been committed to supporting research that can help improve people's lives. Combatting the risk from antibiotic-resistant infections, like Tuberculosis, could have a profound impact on us all." The researchers plan to pursue further studies of the molecule, working with a pharmaceutical company or nonprofit organization, in hopes of developing it for use in humans. The researchers also plan to use their model to design new antibiotics and to optimize existing molecules. For example, they could train the model to add features that would make a particular antibiotic target only certain bacteria, preventing it from killing beneficial bacteria in a patient's digestive tract. The research was funded, and made possible by a number of supporters including the Abdul Latif Jameel Clinic for Machine Learning in Health. - SG
