STAT+: Prominent AI startup rolls out virtual cell model in race to speed up science

Aug. 18, 2026 Keshavan, a biotech correspondent, is the co-author of The Readout, a newsletter about the business, science, and politics of biotech. Imagine Google Earth, but for a human cell. Zoom in closely enough, and instead of streets and buildings, there are proteins and strands of RNA and DNA. Then knock out a gene, or drop in a drug, and you’d see the system predict how the cellular landscape changes. That’s the idea behind AIDO Cell, a new virtual cell system unveiled Tuesday by Palo Alto, Calif., startup GenBio AI. If Google DeepMind’s AlphaFold sought to predict the structure of individual proteins, AIDO Cell is taking much broader aim: predicting how the molecular machinery of an entire cell behaves. “With AlphaFold, you’re predicting the structure of one house or learning about one person in that city, whereas in AIDO Cell, you’re sort of predicting how that whole city works,” said David Baker, a University of Washington scientist who co-founded GenBio AI and shared the 2024 Nobel Prize in chemistry with the makers of AlphaFold for his work in computational protein design. STAT+ Exclusive Story Already have an account? Log in This article is exclusive to STAT+ subscribers Unlock this article — plus in-depth analysis, newsletters, premium events, and news alerts. Already have an account? Log in View All Plans To read the rest of this story subscribe to STAT+. Subscribe