Tahoe Therapeutics announced $30 million in Series A funding to construct what the company describes as the definitive foundational dataset for training Virtual Cell Models, representing a 10-fold expansion from their current capabilities. The San Francisco-based company plans to generate one billion single-cell datapoints mapping one million drug-patient interactions, a scale the company states was previously impossible to achieve.
The funding round was led by Amplify Partners, with participation from Databricks Ventures, Wing Venture Capital, General Catalyst, Civilization Ventures, Conviction, Mubadala Capital Ventures, and AIX Ventures.
Building on Proven Foundation
The investment follows the success of Tahoe-100M, which the company released as the world's first gigascale perturbative single-cell dataset. Since being open-sourced several months ago, Tahoe-100M has been downloaded nearly 100,000 times and has become foundational for teams building virtual cell models across major AI laboratories and research institutions.
The existing dataset and models trained on it have already demonstrated clinical potential, leading to the discovery of promising new therapeutic candidates for major cancer subtypes as well as novel targets across multiple therapeutic modalities.
"Building Tahoe-100M required us to invent new ways to generate single-cell data," said Nima Alidoust, co-founder and CEO of Tahoe Therapeutics. "Now, we're applying that superpower to go 10x further. This next phase is about using these massive datasets to bring about the GPT moment for AI models of human cells, translating insights to clinical readouts, and developing new medicines with much lower clinical failure rates."
Unprecedented Scale for Drug Discovery
The new billion-cell dataset will map interactions between tens of thousands of drug molecules and human biology, expanding the boundaries of biological foundation models. Tahoe aims to use this comprehensive mapping to reduce clinical trial failure rates and accelerate the development of precision medicines for cancer and other therapeutic areas.
The company's approach involves generating single-cell datapoints that capture how different drug compounds affect cellular behavior, creating a comprehensive reference for understanding drug-patient interactions at an unprecedented scale.
Strategic Partnership Model
With the new capital, Tahoe is advancing its internal therapeutic programs toward clinical development while launching a novel collaboration framework. The company plans to select a single strategic partner—either a pharmaceutical company or AI company with complementary capabilities—to access the forthcoming dataset.
This partnership model aims to combine Tahoe's extensive biological data with a partner's clinical development expertise or advanced modeling capabilities to develop what would be the first medicines powered by virtual cell models. The collaboration is designed to accelerate the translation of AI-driven insights into clinical outcomes and therapeutic applications.
