AI Can Speed Drug Discovery. But Is It Really Better Than a Human?
Machine learning and molecular image recognition are far faster than researchers at identifying potential treatments. That doesn’t mean those meds will be more effective.
In mid-January, Genentech started recruiting 200 patients to test whether one of its experimental drugs can tame ulcerative colitis, a painful, incurable type of inflammatory bowel disease. Until then, the compound had only been given during experiments to treat lung and skin disorders. Deciding whether to shift a drug for use against a different disease than originally intended often takes years of painstaking lab work, but the California biotech did it in just nine months. The difference: artificial intelligence, which the company says helped its researchers scan millions of possibilities to confirm the drug could be useful against diseases affecting the cells of the colon.
“It’s not like the human is not needed anymore,” says Aviv Regev, a Harvard University and Massachusetts Institute of Technology computational biologist who took a leave from her academic work to run Genentech’s research and development. “But the human all of a sudden gets the superpower.”