Atomwise Inc. and the University of Toronto announced today an initiative to search for new treatments for the Ebola virus using artificial intelligence. Deploying a groundbreaking research technology that learns and thinks like a human chemist, the team will use Canada’s most powerful supercomputer to simulate and analyze millions of potential medicines in a matter of weeks. Like software used to design airplanes and computer chips in simulation, this new system can predict the possible effectiveness of new medicines, without the need for costly and time-consuming physical synthesis and testing.
The World Health Organization has projected that new cases of Ebola could reach 10,000 each week by December, underscoring the urgent need for research to address the crisis. The unprecedented speed and scale of this investigation is enabled by the unique strengths of three partners: Atomwise Inc. is offering the core artificial intelligence technology that performs the drug research. The University of Toronto is contributing biological insights about Ebola that the system will exploit to search for new treatments. IBM Inc. is supplying the supercomputer, a 64,000-CPU Blue Gene/Q.
“If we can find promising drug candidates for Ebola using computers alone, it will be a milestone for we develop cures.”
“What we are attempting would have been considered science fiction, until now,” said Atomwise CEO, Dr. Abraham Heifets. “We are going to explore the possible effectiveness of millions of drugs, something that used to take decades of physical research and tens of millions of dollars, in mere days with our technology.”
Atomwise’s technology is a virtual drug discovery platform based on the science of Deep Learning Neural Networks, and has previously been used for research on Malaria, Multiple Sclerosis, C. Difficile, and Leukemia. The system is driven by a virtual brain, modeled on the human visual cortex, that teaches itself by “studying” millions of datapoints about how drugs have worked in the past. With this vast knowledge, Atomwise’s brain can apply the patterns it perceives to predict the effectiveness of hypothetical drugs, and suggest surprising uses for existing drugs, transforming the way medicines are discovered.
“Our team is focusing on the mechanism Ebola uses to latch on to the cells it infects. Interrupting that process with a new drug could prevent the virus from replicating.”
The Ebola initiative will exploit critical biological insights about how the virus replicates. “Our team is focusing on the mechanism Ebola uses to latch on to the cells it infects,” said Dr. Jeffrey Lee of the University of Toronto. “Interrupting that process with a new drug could prevent the virus from replicating, and potentially work against other viruses like Marburg and HIV that use the same mechanism.” While there are “broad spectrum” antibiotics that can treat multiple kinds of bacterial infections, most antiviral medications are only effective against a single kind of virus.
The initiative may also demonstrate an alternative approach to high-speed medical research. While giving drugs to patients will always require thorough clinical testing, zeroing in on the best drug candidates can take years using today’s most common methods. This slow and prohibitively expensive process is one of the key reasons that finding treatments for rare and emerging diseases is difficult.
“If we can find promising drug candidates for Ebola using computers alone,” said Abraham Heifets, “It will be a milestone for how we develop cures.”