AlphaFold: Grand Challenge to Nobel Prize with John Jumper

In this episode of Google DeepMind: The Podcast, Professor Hannah Fry interviews John Jumper, a Nobel laureate, about AlphaFold, an AI system that predicts protein structures. Jumper recounts the experience of winning the Nobel Prize and reflects on his career. The conversation covers the impact and evolution of AlphaFold, from its initial breakthrough in protein structure prediction to its latest version, AlphaFold 3, which models interactions of all life's molecules. They discuss the significance of making the protein structures accessible to the public, the unexpected applications of AlphaFold, and the shift in architecture from AlphaFold 2 to AlphaFold 3, including the introduction of diffusion and the role of evolutionary data. Jumper also addresses the interpretability of AI systems and the potential for designing new proteins with applications in drug design and addressing climate change, and the integration of AI tools to build useful systems for biology.