Along with his team at MIT, Prof. James Collins used a machine learning model to identify a small uncovered compound from a drug used to treat diabetes. Artificial intelligence predicted that this compound could kill many bacteria with the least side effects on human cells. This AI model screened out the Halicin compound. In a laboratory test on infected mice, this drug killed many antibiotic-resistant bacteria like Clostridium difficile, Acinetobacter baumannii, and Mycobacterium tuberculosis, except Pseudomonas aeruginosa. Prof. James Collin believes that using this AI model can screen more compounds against other pathogenic diseases. The model used virtual screening of huge compounds dataset approx. 100 million compounds in few days. Read more

February, 2020