rewire.itbenchmarks

Use caseCells and tissuesResearch only

Select perturbations for a defined cellular response

Which genetic perturbations should I test to produce a defined cellular response?

In this release 0 evaluated endpoints · 0 tested configurations · No current evaluated evidence · 3 recorded evidence gaps

Evidence collection plan

Collection planned

Evidence collection is planned for this question. The plan defines a comparison to investigate; it does not establish model performance or suitability.

Comparison question

Does a model select more perturbations producing a prespecified phenotype than simple controls at the same test budget in the intended held-out setting?

Baselines to include

  • Random candidate selection and mean-response/no-change controls
  • Linear or other simple statistical response models
  • Nearest measured perturbation

Outcomes to measure

  • Experimentally confirmed phenotype hits per test budget
  • Perturbation-specific expression signal as an intermediate endpoint
  • Coverage and uncertainty for unseen interventions or contexts

Validation requirements

  • Use the same candidate universe, phenotype definition and budget; specify how tied rankings are sampled.
  • Separate unseen genes, combinations and cell contexts, holding out biological and experimental units.
  • Audit guide efficacy, shared controls, batch effects and model training overlap.
  • Do not choose evaluation genes using held-out responses; keep information-gain design separate.

Next collection task

Inventory perturbation studies with control and split metadata, separating confirmed phenotype-selection outcomes from expression-only metrics.

Question and applicability

Allocate a fixed experimental budget to perturbations most likely to produce the prespecified phenotype.

Who this is for
  • Functional genomics screen designers
  • Cell biologists planning perturbation experiments
Research setting

Research

Research only. Predicted cellular responses do not establish patient response or treatment-selection validity.

Biological setting
Research selection for a defined genetic-perturbation screen. Chemical interventions and combinations need their own protocols. This question concerns phenotype hits rather than expression reconstruction alone.

Outside this use case

  • Transcriptome similarity alone does not establish successful experimental selection.
  • Generalisation to an unseen gene, combination and cell context must be evaluated separately.
  • Choosing experiments to maximise information gain is a separate decision.

Inputs and expected output

Inputs you need

  • A defined cell system, starting state and target phenotype
  • Candidate genetic perturbations and a fixed testing budget
  • Measured perturbations and matched controls with guide, replicate and condition metadata
  • The intended transfer setting: unseen genes, combinations or a new cellular context

Expected output

A ranked experimental shortlist with predicted phenotype effects, coverage and uncertainty about unmeasured conditions.

Evaluated evidence

Evidence is grouped by its protocol. Relevance refers to the stated endpoint and context; it is separate from clinical validation and from the review method. Limits specific to each evaluation are listed with it.

No model comparison has been collected for this question yet.

Relevant methods and studies may exist outside this collection.

View the evidence plan and next collection task

Limitations and missing evidence

These gaps apply to the question as a whole. Absence of evidence is not a zero score.

  • Fixed-budget experimental hit-selection comparisons have not yet been collected for this question.
  • Expression benchmarks may provide only intermediate evidence for the chosen phenotype.
  • Human domain review remains unassigned.

Contribute evidence or propose a correction

Sources and review

Automated source review · 2026-09-28 · Codex

Automated review of the workflow definition, cited primary-source scope and collection plan. No model evaluation or applicability mapping was added. Human domain review remains unassigned.

Release provenance and downloads

Release 2026-09-29-06401fd5b220

Use-case input digest a0dd27a5f430ec387d309fd6e8615083250873ce4cff5e882c6fb8458ef80e95

Download questions, collection plans and review metadata (JSON) · Verify release checksums

Question use-case-phenotype-perturbation-selection. Any numerical results on this page come from this release's existing evaluation records.