Researchers from the University of Toronto have shortened the time it takes to develop a drug from years to a month with the use of DeepMind’s AlphaFold.
Researchers from the University of Toronto have used AlphaFold, a protein structure database developed by DeepMind, to develop a potential drug to treat primary liver cancer.
The researchers, who worked in partnership with Hong Kong-based biotechnology company Insilico Medicine, have reduced the time it would normally take to design and synthesize a drug to 30 days. They published their findings in Chemical Science. Using normal methods, researchers may have taken over a year to come up with the same undiscovered treatment.
Insilico Medicine supplied the university with access to its drug discovery platform, Pharma.AI, which integrates with DeepMind’s AlphaFold database. Researchers also use the biocomputational engine PandaOmics and generative chemistry engine Chemistry42, both supplied by Insilico, to move from discovery to design and synthesize stage.
“While the world was fascinated with advances in generative AI in art and language, our generative AI algorithms managed to design potent inhibitors of a target with an AlphaFold-derived structure,” said Insilico Medicine founder and CEO Alex Zhavoronkov.
This leap in development time was one of the key benefits DeepMind said AlphaFold would bring, with its database of 200 million protein structures enabling researchers and other layers of artificial intelligence to make more precise judgements as to what pathways, molecules, and structures to use to synthesize drugs.
“This paper is further evidence of the capacity for AI to transform the drug discovery process with enhanced speed, efficiency, and accuracy,” said Michael Levitt, a Nobel Prize winner in chemistry and professor of computer science at Stanford University. “Bringing together the predictive power of AlphaFold and the target and drug-design power of the Pharma.AI platform, it’s possible to imagine that we’re on the cusp of a new era of AI-powered drug discovery.”
Insilico Medicine will not develop this drug further, stating it was more of a proof-of-concept as to the power of AlphaFold when coupled with other AI-based medical platforms. With this out of the way, Insilico will now look at further automating the drug discovery and development process, potentially enabling less technical workers to work on developing drugs with the help of AI.
The collaboration between different AI tools is really at work here, with databases of AI-generated structures, computational engines to speed up the process, and generative systems to provide thousands of suggestions as to undiscovered pathways. Speaking on the progress of AI healthcare, Levitt had this to say:
“I’m sure that AI will soon be incredibly important everywhere, from primary health care to preventative health care to pharmaceuticals. We’re going to be much smarter with AI than we were without AI. I was in the field from the very beginning and I would say that I didn’t expect to reach this level as quickly as we did. We got here in 50 years and I thought it would be 100 years.”