Tahoe Therapeutics has secured $30 million in funding to build the largest-ever dataset for training Virtual Cell Models, aiming to map one million drug-patient interactions and generate one billion single-cell datapoints. This unprecedented scale will accelerate precision medicine development for cancer and other diseases.
The funding round, led by Amplify Partners with participation from Databricks Ventures, Wing Venture Capital, General Catalyst, Civilization Ventures, Conviction, Mubadala Capital Ventures, and AIX Ventures, follows the success of Tahoe-100M — the world’s first gigascale perturbative single-cell dataset. Released just months ago and downloaded nearly 100,000 times, Tahoe-100M has already helped identify promising therapeutic candidates for major cancer types and novel drug targets.
Tahoe’s expanded dataset will map tens of thousands of drug molecules against human biology, enabling the next generation of biological foundation models. CEO Nima Alidoust describes the vision as bringing about the “GPT moment” for AI models of human cells, with the goal of lowering clinical trial failure rates and accelerating new drug development.
In addition to advancing its own therapeutic pipeline, Tahoe will select a single strategic partner — a pharmaceutical or AI leader — to leverage the dataset in developing the first medicines powered by virtual cell models. The company’s platform, built on UCSF scientific breakthroughs, makes large-scale, disease-relevant single-cell drug screening scalable, bridging the gap between molecular design and clinical success.