Everyone’s building a ‘GPT for cells.’ Relation’s bet is manufacturing the data to train it.

The race to build an AI “foundation model of the cell” has a fuel problem. It is the same idea behind a foundation model of the chest or the AI-biology work at DeepMind’s Isomorphic. They generate “petascale” datasets of how cells respond to interventions over time. The datasets capture how cells respond to genetic and pharmacological changes, which GSK wants for finding new drug targets. Most drugs still fail in trials, and no cell foundation model has yet produced an approved medicine.