Skip to main content
AI drug discovery models/Virtual Cells & Single-Cell/CZI Virtual Cells (rBio, TranscriptFormer)
platform passport · Review date not recorded

CZI Virtual Cells (rBio, TranscriptFormer)

A moonshot to build AI models of every human cell.

1/7Evidence fields documented
60-SECOND EVALUATION VIEW

What should a scientist know before using CZI Virtual Cells (rBio, TranscriptFormer)?

UnresolvedEvidence direction is incomplete or not yet resolved
Best suited forPlatform · Training
Evidence supportsPrimary links may be present, but BioAtlas does not claim a review date without a record-level timestamp.
Evidence does not establishUniversal superiority, therapeutic success, clinical utility or regulatory acceptance.
Major limitationPerformance depends on the evaluation dataset and operating conditions.
Current registry recordVersion history not yet curated1 recorded release · Review date not recorded. A newer version is not assumed to be universally better.

What it is

CZI is investing heavily toward an AI 'virtual cell', releasing models like TranscriptFormer (a generative cross-species single-cell atlas model) and rBio (which learns biological reasoning from simulations). Its CELLxGENE platform and the newly-acquired EvolutionaryScale team anchor an open ecosystem for cell modeling.

Evidence trail

BioAtlas keeps the path from source to decision visible. A connection records provenance; it does not imply that evidence is sufficient for every context.

Sources1 connectedPrimary resources and normalized claims
Claims0 normalizedNo normalized claim yet
EntityCZI Virtual Cells (rBio, TranscriptFormer)platform · Version history not yet curated
ReviewReview date not recordedReview date not claimed
ConclusionContext requiredAdd to an evaluation before operational use

Model passport

Entity typeplatform
OrganizationChan Zuckerberg Initiative
Platform introduced / founded2024
AccessOpen source
Commercial useAllowed / verify checkpoint terms
DeploymentSelf-hosted
ComputePlatform dependent
Domainscells · protein
Biology → representation → computation → evidence

How CZI Virtual Cells (rBio, TranscriptFormer) represents biology

platformcellsprotein

Category is navigation. These fields describe the model-specific computational transformation and deliberately override broad category defaults.

1 · Biological inputs
Single-cell datasetsSimulation and biological data
2 · Input representation
Platform-dependent
3 · Internal representation
Multiple model families
4 · Architecture
Model ecosystem / data platform
5 · Learning objective
Virtual-cell and biological foundation-model research
6 · Output representation
Platform-dependent

Biological scale

cellprotein

Modalities & tasks

TranscriptomicsProteinMultimodalPlatformTrainingModel ecosystem

Registry, claims and frontier intelligence

Versioned registry

Version history not yet curated

1 version record · release year not yet normalized. Model-family identity remains separate from capability and access changes.

Explore version lineage →
Benchmark claim ledger

0 normalized claims

No task, dataset, split and metric claim has been normalized for this record yet.

Open claim intelligence →

Connected research frontiers

These records describe active research directions, not guaranteed capabilities of this model. Evidence stages and unresolved questions are preserved separately.

Virtual cells

Virtual cells that predict perturbation response

Arc Institute · Virtual Cell research community · 2026-04-30
Recent preprint

Can models forecast how cell populations respond to unseen drugs, gene edits, cytokines and environmental changes across biological contexts?

Evidence boundary and unresolved questions

Recent strict evaluations show marked performance drops under unseen contexts and metric-dependent rankings; simple baselines remain competitive on some global trends.

  • Can models recover perturbation-specific mechanisms rather than average expression shifts?
  • How should cell distributions, dose and time be represented?
  • Which metrics predict prospective experimental usefulness?
virtual cells · perturbation · single cell · OOD generalization · world modelsOpen frontier record →

Inputs and outputs

Inputs

Single-cell datasetsSimulation and biological data

Outputs

ModelsDatasetsVirtual-cell research tools

Scientific and technical profile

Scientific principles

Virtual-cell modelingCross-species transferReasoning from simulation

Technology

Generative single-cell transformersCELLxGENE dataFoundation-model training
Ideas before algorithms

Scientific lineage

Explore all foundations

These are transparent concept matches—not claims that one scientist alone caused this model. Each connection is based on the model’s recorded domain, scientific principles, technical terms or an explicit lineage link.

Genomics & cell systems

The epigenetic landscape and cell-fate trajectories

Conrad H. Waddington

Single-cell embeddings, trajectory inference, reprogramming and virtual-cell models often represent cell identity as movement through a learned state landscape.

Matched concepts: single-cell
Genomics & cell systems

Gene regulation and the operon model

François Jacob & Jacques Monod

Target biology, perturbation models, transcriptomic response prediction and virtual cells all require an explicit model of regulated gene programs.

Matched concepts: transcript
Computational intelligence

Transformer self-attention

Ashish Vaswani and colleagues

Protein, genome, molecule and single-cell foundation models use attention to learn dependencies across biological sequences and multimodal inputs.

Matched concepts: transformer

Evaluation evidence

Dataset or evaluationNot yet curated
Task or metricNot yet extracted
Evidence statusNo task-specific benchmark record curated
Open source ↗

BioAtlas has not yet extracted a structured benchmark claim for this record.

Known limitations

  • Performance depends on the evaluation dataset and operating conditions.
  • A structured benchmark claim has not yet been extracted for this record.
  • Outputs require task-specific scientific and experimental validation.

Milestones

2024

Acquired the EvolutionaryScale (ESM3) team in 2025.

Evidence

CELLxGENE hosts tens of millions of open cells.