Researchers at MIT have discovered a new class of compounds that can kill a drug-resistant bacterium called methicillin-resistant Staphylococcus aureus (MRSA) using deep learning artificial intelligence. These compounds can kill MRSA grown in a lab dish and in two mouse models of MRSA infection. They also have very low toxicity against human cells, making them great drug candidates.
The researchers were able to use this deep-learning model to figure out what types of information the model was using to make its antibiotic potency predictions. This knowledge could help researchers to design additional drugs that might work even better than the ones identified by the model.
In a study, the researchers trained a deep learning model using approximately 39,000 compounds for antibiotic activity against MRSA and fed this information into the model. A search algorithm allowed the model to generate estimates of each molecule’s antimicrobial activity with a prediction for which substructures of the molecule likely account for that activity.
In their search, the researchers screened about 12 million compounds and discovered compounds with minimal adverse effects on the human body. From this, they identified two promising antibiotic candidates that reduced the MRSA population by a factor of 10 in tests in two mouse models.
The researchers have shared their findings with Phare Bio, a nonprofit by MIT. This nonprofit plans to do more detailed analysis of the chemical properties and potential clinical use of these compounds. Meanwhile, researchers are working on designing additional drug candidates based on their findings and using the models to seek compounds that can kill other types of bacteria. The study was funded by several organizations including the James S. McDonnell Foundation, the U.S. National Institute of Allergy and Infectious Diseases, and the Defense Threat Reduction Agency, among others.
This research shows the potential of deep learning to find effective new antibiotics and the power of artificial intelligence in drug discovery.