On May 8, Google DeepMind announced its third iteration of AlphaFold, an artificial intelligence (A.I.) model designed to help researchers design drugs and target diseases more effectively.
Findings from researchers with DeepMind and Isomorphic Labs were published in Nature on May 8. AlphaFold 3 is “giving scientists the ability to predict the structures of proteins during interactions with other molecules,” wrote Nature’s Ewen Callaway.
The new iteration builds upon AlphaFold 2, released in 2021, a model predicting the structure of proteins. “This model is a powerful unified framework for structure prediction, encompassing unprecedented breadth and accuracy,” wrote Max Jaderberg, Adria Stecula, and Pascal Savy in a blog post for Isomorphic Labs.
“This breakthrough,” the authors with Isomorphic Labs added, “opens up exciting possibilities for drug discovery, allowing us to rationally develop therapeutics against targets that were previously difficult or deemed intractable to modulate.”
Isomorphic Labs' authors reported that with the latest release, it’s hoped that drug developers can accurately predict the structure of complexes that have not been characterized before, allowing for new approaches to drug development.
“With these new capabilities, we can design a molecule that will bind to a specific place on a protein, and we can predict how strongly it will bind,” Hassabis Demis Hassabis, CEO of Google DeepMind, said in a statement on May 7. “It's a critical step if you want to design drugs and compounds that will help with disease.”
AlphaFold 3 is limited to non-commercial use, whereas the previous version is freely available to researchers.
