{"entity":{"id":"tahoe-100m","kind":"collection","name":"Tahoe-100M","aka":[],"tldr":"Tahoe-100M is the biggest single-cell dataset ever released, built to teach AI how cancer cells respond to drugs.","summary":"Tahoe-100M is the largest single-cell dataset ever released, built to teach AI models how cancer cells respond to drugs. It comprises 100 million single-cell transcriptomes across 1,100 drugs and 50 cancer cell lines, making it the biggest perturbation atlas for training virtual cell models, and it was generated with the Mosaic platform to limit batch effects. It is used to train and benchmark State (Arc Institute perturbation model) and other perturbation models. The dataset was produced by Vevo Therapeutics with Parse Biosciences and the Arc Institute and is released openly under CC BY. It is referenced by the virtual cell roadmap, the AI in oncology roadmap and the drug discovery roadmap.","asOf":"2026-09-08","links":[{"label":"Tahoe-100M","url":"https://www.biorxiv.org/content/10.1101/2025.02.20.639398v1"}],"tags":["data","virtual-cell"],"related":[],"cancers":[],"sections":[],"technologies":["state-arc"],"targets":[],"drugs":[],"companies":["vevo-therapeutics"],"institutions":["arc-institute"],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"dependsOn":[],"notes":[],"url":"https://www.biorxiv.org/content/10.1101/2025.02.20.639398v1","holds":"100 million single-cell transcriptomes across 1,100 drugs and 50 cancer cell lines: the largest perturbation atlas for training virtual cell models.","license":"Open (CC BY)","maintainer":"Vevo Therapeutics with Parse Biosciences and Arc Institute"},"route":"/collections/tahoe-100m/","neighbours":{"technology":[{"id":"state-arc","kind":"technology","name":"State (Arc Institute perturbation model)","route":"/technologies/state-arc/"}],"company":[{"id":"vevo-therapeutics","kind":"company","name":"Vevo Therapeutics","route":"/companies/vevo-therapeutics/"}],"institution":[{"id":"arc-institute","kind":"institution","name":"Arc Institute","route":"/institutions/arc-institute/"}],"roadmap":[{"id":"ai-oncology-roadmap","kind":"roadmap","name":"AI in oncology roadmap: pattern readers → foundation models → agents in the workflow","route":"/roadmaps/ai-oncology-roadmap/"},{"id":"drug-discovery-roadmap","kind":"roadmap","name":"Drug discovery roadmap: screening in mice → maps of dependency → designing in silico","route":"/roadmaps/drug-discovery-roadmap/"},{"id":"virtual-cell","kind":"roadmap","name":"Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell","route":"/roadmaps/virtual-cell/"}]}}