OnCo
roadmapsRoadmap

Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell

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.

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.

Steps

6top
  1. 2008-2018historic

    Atlases and bulk omics

    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.

  2. 2019-2022historic

    Pooled perturbation screens meet single cells

    Perturb-seq and genome-wide CRISPR screens (DepMap) give causal training data; GEARS shows graph models can predict some unseen knockouts.

  3. 2023-2024current

    First single-cell foundation models

    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.

  4. 2025-2026current

    Data at scale and context-aware models

    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.

  5. 2027-2029emerging

    Patient-derived contexts and spatial niches

    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.

  6. 2030+speculative

    Speculative: in silico trials and digital twins

    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.

Probability ranges are named estimates that the claim is borne out on roughly a five-year horizon. They are meant to be argued with: propose a revision with your name and reasoning via a pull request to src/data/confidence.ts.

Story

top
2008-2018historicstep 1 of 6

Atlases and bulk omics

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.

2019-2022historicstep 2 of 6

Pooled perturbation screens meet single cells

Perturb-seq and genome-wide CRISPR screens (DepMap) give causal training data; GEARS shows graph models can predict some unseen knockouts.

2023-2024currentstep 3 of 6

First single-cell foundation models

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.

2025-2026currentstep 4 of 6

Data at scale and context-aware models

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.

2027-2029emergingstep 5 of 6

Patient-derived contexts and spatial niches

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.

2030+speculativestep 6 of 6

Speculative: in silico trials and digital twins

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.

Connected

27top