In this episode, Mark Zuckerberg, Priscilla Chan, and Alex Rives discuss the Chan Zuckerberg Biohub's ambitious mission to accelerate biomedical research through open-source AI tools and frontier biology. They emphasize building world models of biology—from proteins to cells—to enable personalized medicine and democratize scientific discovery.
Summarized by Podsumo
The Biohub aims to cure, prevent, or manage all diseases by the century's end, with AI accelerating this timeline—potentially less than 100 years.
Their open-source approach includes ESM Fold, a protein language model that predicts structures and designs novel proteins, achieving nanomolar binders in just 96 experimental trials.
They are building hierarchical world models (proteins → cells → systems) to understand biology, integrating frontier AI with novel wet-lab data generation.
The initiative is a non-profit to maximize impact, enabling long-tail diseases to be tackled by empowering the entire scientific community.
Alex Rives leads the AI team, shifting from biology-focused leadership to an AI-first approach, with a stable, world-class team.
"We just want to give tools to the whole scientific community."
"We want to understand the genetics of this person. I want to understand the risks they have to different illnesses. My goal is to be able to treat the individual as an individual, understand the mechanisms and be able to intervene."
"We'll have a bigger impact by getting this in more scientists and quicker by doing it as open source projects instead."