Only 4 percent of all cancer therapeutic drugs under development earn final approval by the U.S. Food and Drug Administration (FDA). "That's because right now we can't match the right combination of drugs to the right patients in a smart way," said Trey Ideker, Ph.D., professor at University of California San Diego School of Medicine and Moores Cancer Center. "And especially for cancer, where we can't always predict which drugs will work best given the unique, complex inner workings of a person's tumor cells." In a paper published October 20, 2020 in Cancer Cell, Ideker and Brent Kuenzi, Ph.D., and Jisoo Park, Ph.D., postdoctoral researchers in his lab, describe DrugCell, a new artificial intelligence (AI) system they created that not only matches tumors to the best drug combinations, but does so in a way that makes sense to humans. "Most AI systems are'black boxes'--they can be very predictive, but we don't actually know all that much about how they work," said Ideker, who is also co-director of the Cancer Cell Map Initiative and the National Resource for Network Biology.