Advancing discovery of better drugs and medicine

This July 2022 DeepMind blog post features Karen Akinsanya, President of R&D at Schrödinger, explaining how drug developers must design molecules that hit a target protein while avoiding similar "family member" proteins that cause side effects. Schrödinger combines AlphaFold's protein-structure predictions with its own physics-based simulation software to model how related protein families behave, and is applying this to design molecules targeting neurotransmitter receptors for conditions including schizophrenia and bipolar disorder, which Akinsanya says can be targeted "with exquisite accuracy." The post frames AlphaFold as "an additional piece of the puzzle" in understanding biology; it does not report specific numerical outcomes or name other partners.

Google supplies AI to pharma through several distinct lines — Gemini/Vertex AI as an enterprise platform, and AlphaFold-based drug design licensed commercially through Isomorphic Labs.

This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.