Health, Longevity & Biohacking
BioHub Scientists Design Nanomolar Antibodies Using AI in Single 96-Well Plate Experiment
No Priors Podcast
Biohub: The Future of Biology is Open-Source with Co-Founders Mark Zuckerberg, Priscilla Chan, and Head of Science Alex Rives
"You can actually now use the model to design proteins and to design actually single-chain antibodies. You can do all of this digitally and then really in a small number of experimental trials, basically like a 96-well plate, select from hundreds of thousands of trajectories digitally, synthesize 96 proteins, test them in the lab in a really short, easy experimental cycle. And we found nanomolar binders there."
Alex Reeves revealed that BioHub's new ESMFold model achieved therapeutic-level antibody design in a single experimental round, demonstrating that AI can compress what traditionally required screening millions of antibodies in high-throughput lab experiments into a computational process followed by minimal wet-lab validation. This represents a dramatic acceleration in drug discovery timelines.
From this episode
No Priors Podcast