Atomwise has launched a drug discovery initiative that aims to screen up to 10 billion virtual compounds for potential therapies against childhood cancer in collaboration with global chemical supplier Enamine.
Dubbed the 10-to-the-10 program, the artificial intelligence-driven project will simulate the binding of billions of small molecules to target cancer proteins to find the ones that may offer safer pediatric treatments.
“Many of our partners have successfully identified early drug candidates, including submicromolar hits, by screening only 10 million compounds with our AI virtual screening platform,” Atomwise co-founder and CEO Abraham Heifets said in a statement. “We’ve barely scratched the surface of what is possible—imagine what will be found when we screen a chemical library that is a thousand times larger.”
RELATED: Eli Lilly to pay Atomwise $1M for each AI-discovered drug
The research will be directed by academic cancer researchers including those at the University of North Carolina, according to the companies, with many compounds being examined for druglike properties for the first time. The targets themselves range from applications in slowing cancer growth to halting metastasis.
RELATED: Charles River and AI specialist Atomwise team on drug discovery
Using scalable cloud computing and Enamine’s enormous virtual library of easily synthesized compounds, Atomwise hopes to deliver drugs that could take years to find using traditional discovery methods. The companies said they plan to publish the results of the initiative in peer-reviewed journals.
Earlier, Atomwise signed on to a multiyear collaboration with Eli Lilly, setting a price of $1 million a pop for each AI-sifted molecule. The San Francisco-based company could reap up to $550 million if as many as 10 of its discoveries pay off in the Big Pharma’s clinical testing and gain FDA approval, and Atomwise also gets to retain the compounds Lilly decides not to pursue.