Isomorphic Labs Discusses AI-Driven Drug Discovery and the Future of Medicine - Ep. 252

What It Covers

Isomorphic Labs' Chief AI Officer Max Jaderberg and CTO Sergei Yakhnin explain how their company uses general AI models like AlphaFold 3 to design drugs computationally, eliminating traditional design-make-test cycles and targeting previously intractable proteins.

Key Questions Answered

• •General vs Local Models: Isomorphic builds AI models that work across the entire proteome and chemical space, allowing the same technology to design drugs for multiple diseases simultaneously, unlike traditional approaches where each target requires starting from scratch with no knowledge transfer.
• •In Silico Design Cycles: The company aims to complete entire drug design programs through computational modeling alone, validating only once at the end with physical experiments. This contrasts with conventional methods requiring continuous wet lab testing, enabling bolder molecular changes and faster iteration.
• •Chemical Space Exploration: Even with perfect predictive models, the drug design space contains 10 to the 60 possible molecules. Isomorphic uses generative AI and search agents to navigate this space, vastly exceeding traditional screening libraries of one million to one billion compounds.
• •AlphaFold 3 Capabilities: Released in 2024, AlphaFold 3 predicts structures of proteins interacting with DNA, RNA, and small molecules at experimental accuracy. Chemists can now see structural changes from molecular modifications in seconds rather than months, fundamentally changing the design workflow.