AI Helps Find Alternative Pharmaceutical Building Blocks for 12 Drugs under Investigation to Treat COVID-19

The U-M team of medicinal chemists was approached by chemical supplier MilliporeSigma to devise solutions to the supply issue. The team combed the federal clinical trials database for drugs currently being considered for treatment of COVID-19, and then used the AI software Synthia to determine new ways to piece the drugs together.

The medicinal chemists traced the synthetic sequences of 12 drugs currently under investigation for treating COVID-19. Those drugs include bromhexine, camostat, cobicistat, darunavir, favipiravir, galidesivir, nelfinavir, ritonavir, umifenovir, ribavirin, remdesivir and baricitinib. The U-M team used crowd-sourcing to survey the vast amount of published and patented synthetic routes to build the 12 drugs. Then, the researchers encoded these known routes into the AI software, and asked it to come up with new recipes. This approach allowed the researchers to navigate around the starting materials that are already in the supply chain of the medicinal target compounds. Each search typically returned multiple proposals, which the researchers then winnowed down according to the overall economics of the starting materials and the overall sequence.

“The route we have found for some of these potential therapeutics might be longer than what’s out there, but in most cases, such as umfenovir, we’re actually finding routes that are shorter and starting materials that are cheaper than what’s currently available,” said U-M researcher Tim Cernak, an assistant professor of medicinal chemistry and chemistry. “We found a way to make the therapeutic bromhexine in one-step, which we are pretty stoked on.”

Related Links:

University of Michigan