Biotech startup Tahoe raises $30M for AI cancer drug discovery platform

Biotech startup Tahoe Therapeutics has raised $30 million in Series A funding led by Amplify Partners, bringing its total funding to $42 million and valuing the company at $120 million. The Palo Alto-based company has developed breakthrough technology for generating massive biological datasets needed to train AI models that can simulate living cells, positioning it to accelerate cancer drug discovery through digital cell modeling.

What you should know: Tahoe’s proprietary Mosaic platform can generate unprecedented amounts of single-cell data by testing multiple patient cell types simultaneously, rather than conventional one-patient-at-a-time approaches.

• In February 2024, the company released Tahoe-100M, a dataset containing 100 million datapoints showing how different cancer cells responded to over 1,000 molecules.
• CEO Nima Alidoust called this release “a Mars landing moment for single-cell datasets.”
• The Arc Institute, a nonprofit research organization, used Tahoe-100M to build an open-source virtual cell model called State, which achieved twice the accuracy of competing AI models.

Why this matters: Poor AI predictions have been a persistent problem in biotech, with algorithms frequently failing when tested in laboratory settings.

• “These AI algorithms keep recommending stuff, and then when you go to test it in the wet lab, it all sucks,” said Krish Ramadurai, partner at AIX Ventures and Tahoe board member.
• Virtual cell models could revolutionize drug discovery by allowing researchers to digitally simulate how new medicines would react in the body before costly animal and human testing.

The technology behind it: Tahoe’s Mosaic platform represents nearly a decade of research by cofounder Johnny Yu, developed while working at UC San Francisco.

• The platform can “take cells from many different types of patients, from all different organs and then put them together,” Yu explained.
• “Every time we run an experiment, we’re generating massive single cell atlases of which drugs affect which patients.”
• This scalable data production capability is what Alidoust calls Tahoe’s “distinguishing factor” compared to other AI drug discovery companies.

Who’s involved: The funding round included Databricks Ventures, Wing Venture Capital, General Catalyst, AIX Ventures, Mubadala Ventures, Civilization Ventures, and Conviction.

• Tahoe was founded in 2022 by Alidoust, Yu, UCSF professor Hani Goodarzi, and researcher Kevin Shokat.
• The company was originally called Vevo Therapeutics but changed its name to Tahoe in April 2024 after a legal challenge.
• It raised a $12 million seed round in December 2022.

What’s next: Tahoe is building toward a dataset with over one billion single-cell datapoints to power its own virtual cell models.

• The company currently has a drug candidate targeting “a major cancer subtype” and is conducting FDA-required studies to begin human testing.
• Tahoe plans to partner with either a major pharmaceutical company or AI company to share data and collaborate on drug development or AI model creation.
• While keeping larger datasets proprietary, the company is working with different companies on smaller collaborative projects.

What they’re saying: Alidoust emphasized the foundational nature of their work in biological AI.

• “Our core superpower is the ability to generate the massive datasets required for virtual cell models.”
• “We say in the company that this is morning in biology. We are building. And we hope others are going to build with us as well.”