MIT AI Model Discovers Powerful Antibiotic to Fight Resistant Bacteria
MIT researchers use a deep-learning algorithm to discover a potent new antibiotic that kills drug-resistant bacteria. The computer model screens millions of compounds to find treatments that work differently than existing drugs.
MIT researchers use a deep-learning algorithm to identify a powerful new antibiotic compound that kills many of the world's most problematic disease-causing bacteria. The computer model screens over a hundred million chemical compounds in just a few days to find potential drugs with entirely new mechanisms of action.
In laboratory tests, the newly discovered drug, called halicin, successfully eliminates strains of bacteria that resist all known antibiotics. Additionally, the compound clears infections in two different mouse models and prevents the development of antibiotic resistance in E. coli.
The research team views this AI platform as a major breakthrough for ushering in a new age of antibiotic drug discovery. Along with halicin, the model identifies several other promising antibiotic candidates that the researchers plan to test further.