How much faster can we identify potential lifesaving medications for diseases such as COVID-19?

UBC’s Dr. Artem Cherkasov has discovered the answer to that question: “Instead of 10 years, it took us 19 days. We screened 40 billion potential drug compounds and narrowed those down to a shortlist of a handful of highly promising candidates,” he says.

Dr. Cherkasov and his team have developed Deep Docking, an AI-enabled technology that identifies previously unknown potential medications for people already infected with the virus.

“It has the potential to bring new and effective COVID-19 antivirals to patients much sooner, reducing instances of serious illness and death and improving recovery,” says Dr. Cherkasov, a professor in UBC’s department of urologic sciences and leading expert on drug design at the Vancouver Prostate Centre (VPC).

Deep Docking uses machine learning to screen hundreds of billions of molecular structures to see how they fit into a target protein — in the case of the COVID-19 virus, an enzyme that is important for its replication.

“The target enzyme can be thought of as a lock. The small molecules we screened are keys we tested in the lock to identify which ones could fit in and disable it,” says Dr. Larry Goldenberg, a professor in UBC’s department of urologic sciences and director of development and supportive care at the VPC.

Normally, computational screening is a years-long stage of the drug development process, during which scientists screen millions of chemicals for their potential efficacy. Deep Docking shows it’s possible to accelerate screening by up to 100 times.

Dr. Cherkasov’s goal is to have an anti-viral drug ready early this year.

Not only could the technology revolutionize COVID-19 treatments — it also offers a blueprint for supercharging drug development in general.

All the data collected by the Deep Docking team will also be made public through Github and the Democratizing Drug Discovery with Deep Docking (D5) platform being developed by Dr. Cherkasov — giving scientists around the world rapid access to billions of molecules they can use for their research.

“We are doing this because we want everyone to have this information, to save the world in a way,” he says.