AI for Bio · Model

X-Cell

Virtual-cell model predicting expression change after genetic perturbation

Single-cell & perturbationAI-native biotechUnited StatesActiveSite entity page (Chinese site)中文

Overview

NameX-Cell · aliases: X-Cell, X-Cell-Ultra, X-Cell Mini
Full nameA product name with no expanded form
Ambiguous names (not auto-linked)None
FamilyTwo sizes from one release: the largest at about 4.9 billion parameters and a small version initialised from a public single-cell model and not yet released
  • X-Cell-Ultra · †
  • X-Cell Mini · No sourced date†
OrganizationXaira Therapeutics
Organization typeAI-native biotech
CountryUnited States
Model classSingle-cell perturbation prediction (diffusion language model)
DomainSingle-cell & perturbation
First release† partly verified · product update
Basis: Developer press release, with the repository public a day earlier
Note: Both dates rest on a company release and the repository, with no third-party corroboration source
Other milestones
  • First public evidence: † · Code repository made public (two commits only) source
  • Preprint v1: † · Preprint source
  • Code release: † · Repository made public source
  • Official announcement: † · Company press release source
Latest update† partly verified · no later event
Basis: The release event itself
No substantive event after the release was found as of 2026-11-16; the project page still lists weights and inference code as coming soon.
Note: Same-day latest update means only that no later event was found source
The most recent sourced event, not a claim that nothing changed since.
StatusActive · Released within 12 months, with no event found since
OpennessCode: Closed
Weights: Closed
Weights and inference code are marked as coming soon under a planned non-commercial share-alike licence; the test perturbation set is already public
Benchmarks reported1 counted (modified protocol 1)
Wet-lab validationNone recorded
Unverified fields† first_release, release_milestones.paper_v1, release_milestones.code_release, latest_update, training_data.a_public, training_data.c_own_wetlab_for_training, other_evaluations
As of2026-11-16

What it does

Iteratively replaces control expression values with post-perturbation values using a diffusion language model, bringing in gene and protein interaction priors through cross-attention; the preprint reports a power law in perturbation prediction with scale and zero-shot transfer to two new cell types (second-hand). It differs from State and Tahoe-x1 in architecture and in training on data the developer produced itself.

Benchmarks reported

Every row is one pairing from the survey's relation file; a score belongs to the benchmark page's ranking, where it is shown with metric, eval set, source type and date. 1 of 1 pairings are counted.

BenchmarkRelationEval set / protocolSource typeNote and evidence
24 Virtual Cell Challenge and perturbation benchmarksDeveloper report, modified protocol—Self-reportedOwn held-out iPSC set; VCC participation unconfirmed. · evidence

Other evaluations (outside the 44)

  • Held-out iPSC perturbation set (Own task set) Self-reported: A held-out perturbation set built by the developer, with training and evaluation from the same source
  • Zero-shot transfer to new cell types (Case study) Third-party: Zero-shot evaluation on two unseen cell types, per second-hand reports

Developers report: training on an in-house genome-wide perturbation dataset, a power law in perturbation prediction with model size, and a large margin over an unnamed runner-up on a held-out perturbation set.

Independent evidence: No independent evidence found. Weights are not public, no third-party evaluation was found, and it has no result on the public blind-test challenge

Training data

Group in Figure 7: Own wet-lab training data.

ClassValueDetail
a. Public databasesNot disclosedThe project page lists only the in-house perturbation set; the small version is initialised from a public single-cell model and so inherits its public data indirectly, with other public data use undisclosed source
b. Private or licensed dataNo
c. Own wet-lab data used for trainingYesAn in-house CRISPRi perturbation set of 25.6 million cells; the context count conflicts, with the project page and press release giving seven screens (9,735-18,924 perturbations each) and most reports giving 16 biological contexts source
d. Wet lab used only for validationNo

Wet-lab validation

None. The developers report no wet-lab validation.

Background

  • Organization: The developer is a US AI-first drug discovery company launched in April 2024, working on protein and antibody drugs and continuing a university lab's protein design lineage; headcount is not officially disclosed, with a third-party data provider estimating about 193 in March 2026.
  • Funding: It launched with over $1B in Series A commitments co-led by two venture firms; the valuation is undisclosed.
  • Products and partnerships: Its data products are two generations of perturbation atlas (about 8 million cells, then 25.6 million), and its models are this one at about 4.9 billion parameters plus a planned small version; it competes in perturbation prediction with State and Tahoe-x1.
  • Related models: STATE, Tahoe-x1, scGPT / Geneformer

Reading notes

  1. The held-out result is self-reported and the project page names no competitor, so it is not evidence of a lead.
  2. The in-house dataset is a moat, but training and evaluation share a source and cross-cell-type generalisation has no independent reproduction.
  3. With no public blind-test result it cannot be compared with peers under one protocol.
  4. The context count appears as both seven and 16, so any citation must state which basis it uses.

Caveats

  1. Weights and inference code are unreleased, so nothing can be rechecked.
  2. Both first release and latest update rest on a company release and the repository.
  3. Sources disagree on the number of contexts in the training set.
  4. Its only pairing here is a self-built held-out set, not a challenge result.
  5. No event found since release is not the same as the project having stalled.

Sources

  1. Project page (official site)
  2. Company press release (press)
  3. Preprint 2026 (preprint)
  4. Code repository (repository)

Corrections

None recorded.

Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.