The Arc Institute is a well-funded nonprofit research institute building 'virtual cell' AI models and the datasets to train them.
The Arc Institute in Palo Alto is a well-funded nonprofit research institute founded in 2021 with Stanford, UCSF and Berkeley affiliations, building virtual cell AI models and the datasets needed to train them. It is home to the Evo and Evo 2 genome language models built with NVIDIA, the State perturbation-response model, the Arc Virtual Cell Atlas and the Tahoe-100M dataset, and it ran the Virtual Cell Challenge in 2025; its scale of perturbation data collection is unusual for an academic institute, and Silvana Konermann is among the people linked. OnCo connects it to the Chan Zuckerberg Biohub and to the virtual cell roadmap that runs from bulk omics to a predictive model of a cancer cell. Whether perturbation-trained models predict responses in patients, not just cell lines, is the open question. Its Evo, State and Virtual Cell Atlas programmes are listed below.
From OpenAlex, oncology works in the last five years (2022 to 2026, current year in progress); counted on 2026-09-24.
Matched to Arc Research Institute, including child institutions. 4 works · 46 citations · 100% open access · 0% clinical trials · 0% reviews.
| Work | Journal | Year | Citations |
|---|---|---|---|
| Stem-cell states converge in multistage cutaneous squamous cell carcinoma development 10.1126/science.adi7453 · open access | Science | 2024 | 27 |
| SEED-Selection enables high-efficiency enrichment of primary T cells edited at multiple loci 10.1038/s41587-024-02531-6 · open access | Nature Biotechnology | 2025 | 16 |
| Affinity-matured CD72-targeting nanobody CAR T cells enhance elimination of antigen-low B-cell malignancies 10.1136/jitc-2025-012013 · open access | Journal for ImmunoTherapy of Cancer | 2025 | 2 |
| Affinity-matured CD72-targeting Nanobody CAR T-cells Enhance Elimination of Antigen-Low B-cell Malignancies | bioRxiv (Cold Spring Harbor Laboratory) | 2025 | 1 |
Shares Tahoe-100M, Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico and the tags ai, virtual-cell.
Shares Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell and the tags ai, virtual-cell.
Shares Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell and the tags ai, virtual-cell.
Shares Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico and the tag ai.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico and the tag ai.
Shares Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico and the tag virtual-cell.
Shares Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico and the tag virtual-cell.
Shares Evo 2 (Arc Institute, NVIDIA) and the tag ai.
Open-source projects that this organisation maintains, from OnCo's own catalogue: licence and last activity as the repository reported them on the day of the fetch. Listing is not endorsement; check the licence before reuse and the validation before clinical use.
Arc Institute's genomic foundation model across all domains of life, with open weights.
Arc's virtual cell model that predicts how cells respond to perturbations, trained with the Virtual Cell Atlas.