Tahoe provides a gigascale perturbative single‑cell platform that generates hundreds of millions of data points linking drug molecules to patient biology. The dataset fuels foundation AI models of virtual human cells, enabling target deconvolution and precision drug discovery, initially focused on oncology. Revenue is derived from licensing its proprietary datasets and AI models to pharmaceutical partners and from co‑development of therapeutics through joint ventures and collaborations.
Funding
$30M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Current drug discovery pipelines rely on low‑resolution in vitro assays and small‑scale in vivo studies, which fail to capture how chemical compounds perturb patient biology across diverse genetic backgrounds. This limits the ability to predict efficacy, deconvolute mechanisms of action, and design precision therapeutics, especially in oncology.
Solution
Tahoe’s platform generates perturbational single‑cell atlases at gigascale by applying its Mosaic in vivo workflow to hundreds of millions of patient‑derived cells exposed to thousands of drug candidates. The resulting datasets—currently exceeding 100 million cells and tens of thousands of drug‑patient interactions—are used to train foundation‑level AI models that predict cellular responses, identify novel targets, and guide rational drug design. Researchers can access the data and models through a cloud‑native analytics stack and a natural‑language interface (TahoeDive), enabling rapid hypothesis testing without building bespoke bioinformatics pipelines.
Features
- High‑throughput Mosaic platform that profiles single‑cell transcriptomes from in vivo drug perturbations across hundreds of patient samples.
- Gigascale perturbational atlas (Tahoe‑100M) comprising >100 M cells and >60 k drug‑patient interaction measurements, openly released for community use.
- Foundation AI models pre‑trained on the atlas to predict gene‑expression changes, deconvolute drug mechanisms, and prioritize therapeutic candidates.
- TahoeDive query engine that leverages large‑language models to translate natural‑language questions into reproducible analyses and visualizations.
- Scalable data storage and retrieval via TileDB integration, supporting fast sub‑setting and downstream pipeline integration.
- Secure, HIPAA‑compliant data handling with role‑based access controls and end‑to‑end encryption.
- API and SDKs for programmatic access, enabling seamless incorporation into existing drug‑discovery workflows and computational biology toolchains.