{"entity":{"id":"virtual-cell","kind":"roadmap","name":"Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell","aka":[],"tldr":"The attempt to build a computer model of a cell good enough to predict what a drug or mutation will do before anyone runs the experiment.","summary":"A virtual cell would let researchers test thousands of drug ideas in silico and personalise treatment from a patient's own tumour profile. The field moved from static atlases to perturbation-trained models in five years; the honest status is that current models generalise poorly to unseen contexts and barely beat simple baselines on rigorous benchmarks, while data generation has begun to scale to the size the problem needs.","asOf":"2026-09-08","links":[{"label":"Defining a Cancer Dependency Map: which genes each cancer cell line cannot live without (Cell 2017)","url":"https://doi.org/10.1016/j.cell.2017.06.010"}],"tags":[],"related":[],"cancers":[],"sections":["ai-computation","drug-discovery"],"technologies":["geneformer","scgpt","state-arc","c2s-scale","universal-cell-embedding","gears","transcriptformer","single-cell-spatial","crispr-screens"],"targets":[],"drugs":[],"companies":["vevo-therapeutics","chan-zuckerberg-initiative","google-deepmind"],"institutions":["arc-institute","stanford","yale-school-of-medicine"],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"dependsOn":[],"notes":[],"steps":[{"era":"2008-2018","title":"Atlases and bulk omics","description":"TCGA catalogues the genomes of 11,000 tumours; single-cell RNA-seq matures; the Human Cell Atlas begins. Models are statistical, per-dataset, and descriptive.","refs":["tcga-gdc","cellxgene-hca","single-cell-spatial"],"status":"historic"},{"era":"2019-2022","title":"Pooled perturbation screens meet single cells","description":"Perturb-seq and genome-wide CRISPR screens (DepMap) give causal training data; GEARS shows graph models can predict some unseen knockouts.","refs":["crispr-screens","depmap","gears"],"status":"historic"},{"era":"2023-2024","title":"First single-cell foundation models","description":"Geneformer, scGPT, UCE, scFoundation and others pretrain on tens of millions of cells. Benchmarks reveal that perturbation prediction often does not beat linear or mean baselines, forcing better evaluation.","refs":["geneformer","scgpt","universal-cell-embedding","scfoundation","gears"],"status":"current"},{"era":"2025-2026","title":"Data at scale and context-aware models","description":"Tahoe-100M (100M cells, 1,100 drugs, 50 cancer lines), Arc's Virtual Cell Atlas and Challenge, State trained on 100M+ perturbed cells, C2S-Scale's lab-validated hypothesis, CZI's cross-species models. The problem becomes one of held-out generalisation across cell contexts.","refs":["tahoe-100m","arc-virtual-cell-atlas","state-arc","c2s-scale","transcriptformer","nicheformer"],"status":"current"},{"era":"2027-2029","title":"Patient-derived contexts and spatial niches","description":"Models trained on perturbations in patient-derived organoids and spatial data (tumour niches, immune contexts) rather than cell lines alone; coupling with structure models for mechanism; prospective use to rank drug combinations for organoid confirmation.","refs":["organoids","functional-drug-testing","nicheformer","boltz"],"status":"emerging"},{"era":"2030+","title":"Speculative: in silico trials and digital twins","description":"A tumour's multi-omic profile seeds a patient-specific virtual cell population; treatment sequences are simulated before the first cycle; models are updated from ctDNA and imaging during care. Requires validation standards that do not yet exist.","refs":["idea-multimodal-foundation-model","mrd-testing"],"status":"speculative"}],"watch":[]},"route":"/roadmaps/virtual-cell/","neighbours":{"section":[{"id":"ai-computation","kind":"section","name":"AI & Computation","route":"/fronts/ai-computation/"},{"id":"drug-discovery","kind":"section","name":"Drug Discovery Platforms","route":"/fronts/drug-discovery/"}],"technology":[{"id":"boltz","kind":"technology","name":"Boltz-1 / Boltz-2 (MIT, open)","route":"/technologies/boltz/"},{"id":"c2s-scale","kind":"technology","name":"Cell2Sentence / C2S-Scale (Yale, Google)","route":"/technologies/c2s-scale/"},{"id":"crispr-screens","kind":"technology","name":"CRISPR functional genomics","route":"/technologies/crispr-screens/"},{"id":"functional-drug-testing","kind":"technology","name":"Functional (ex vivo) drug testing","route":"/technologies/functional-drug-testing/"},{"id":"gears","kind":"technology","name":"GEARS and perturbation prediction benchmarks","route":"/technologies/gears/"},{"id":"geneformer","kind":"technology","name":"Geneformer","route":"/technologies/geneformer/"},{"id":"mrd-testing","kind":"technology","name":"MRD / molecular residual disease testing","route":"/technologies/mrd-testing/"},{"id":"nicheformer","kind":"technology","name":"Nicheformer (spatial single-cell)","route":"/technologies/nicheformer/"},{"id":"organoids","kind":"technology","name":"Patient-derived organoids","route":"/technologies/organoids/"},{"id":"scfoundation","kind":"technology","name":"scFoundation (BioMap)","route":"/technologies/scfoundation/"},{"id":"scgpt","kind":"technology","name":"scGPT","route":"/technologies/scgpt/"},{"id":"single-cell-spatial","kind":"technology","name":"Single-cell & spatial profiling","route":"/technologies/single-cell-spatial/"},{"id":"state-arc","kind":"technology","name":"State (Arc Institute perturbation model)","route":"/technologies/state-arc/"},{"id":"transcriptformer","kind":"technology","name":"TranscriptFormer and rBio (CZI virtual cell models)","route":"/technologies/transcriptformer/"},{"id":"universal-cell-embedding","kind":"technology","name":"Universal Cell Embedding (UCE)","route":"/technologies/universal-cell-embedding/"}],"company":[{"id":"chan-zuckerberg-initiative","kind":"company","name":"Chan Zuckerberg Initiative (Biohub)","route":"/companies/chan-zuckerberg-initiative/"},{"id":"google-deepmind","kind":"company","name":"Google DeepMind (and Google Research)","route":"/companies/google-deepmind/"},{"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/"},{"id":"stanford","kind":"institution","name":"Stanford Health Care / Stanford Cancer Institute","route":"/institutions/stanford/"},{"id":"yale-school-of-medicine","kind":"institution","name":"Yale School of Medicine / Yale Cancer Center","route":"/institutions/yale-school-of-medicine/"}],"collection":[{"id":"arc-virtual-cell-atlas","kind":"collection","name":"Arc Virtual Cell Atlas","route":"/collections/arc-virtual-cell-atlas/"},{"id":"cellxgene-hca","kind":"collection","name":"CZ CELLxGENE / Human Cell Atlas","route":"/collections/cellxgene-hca/"},{"id":"depmap","kind":"collection","name":"DepMap (Cancer Dependency Map)","route":"/collections/depmap/"},{"id":"tahoe-100m","kind":"collection","name":"Tahoe-100M","route":"/collections/tahoe-100m/"},{"id":"tcga-gdc","kind":"collection","name":"TCGA / NCI Genomic Data Commons","route":"/collections/tcga-gdc/"}],"idea":[{"id":"idea-multimodal-foundation-model","kind":"idea","name":"Patient-level multimodal foundation models for treatment selection","route":"/ideas/idea-multimodal-foundation-model/"}],"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/"}]}}