news✓ VerifiedVC0143

Generating high-quality Perturb-seq data for the 2026 Virtual Cell Challenge

Arc's description of how the 2026 Challenge dataset was generated (organisation statement, not independent evaluation): CRISPRi Perturb-seq in six human cell lines, 10x Flex profiling, >10,000 perturbations and 100 non-targeting guides per line, curated to perturbations with >=80% median on-target knockdown and subsampled to 400 cells per perturbation; zero-shot task (only unperturbed cells are given); no model results reported.

Authors / organisation: Arc Institute
Venue: Arc news
Date: 2026-10-01
Type: news
Year: 2026
Source: https://arcinstitute.org/news/behind-the-data-virtual-cell-challenge-2026
Verification: Arc Institute news page (publisher; fetched 2026-10-16: title, date 2026-10-01, six cell lines, CRISPRi, 10x Flex, 400 cells/perturbation, >=80% median knockdown, NTC and cell counts)

Challenge Arc Institute Benchmark & validation Zero-shot Perturb-seq DatasetCRISPRi10x-Genomics

Cited by GlioState topics

Virtual Cell Challenge metrics and baselines: what the scores reward, and where the evidence conflicts (Validation)

Entities mentioned

Open in the searchable library → · JSON

Generating high-quality Perturb-seq data for the 2026 Virtual Cell Challenge

Cited by GlioState topics

Entities mentioned

Related papers (shared tags)

Virtual Cell Challenge 2026: Benchmarking zero-shot generalization across cellular contexts.

Virtual Cell Challenge 2026 (zero-shot, 6 unseen cell lines)

Virtual Cell Challenge: Toward a Turing test for the virtual cell.

X-Atlas/Orion: Genome-wide Perturb-seq Datasets via a Scalable Fix-Cryopreserve Platform for Training Dose-Dependent Biological Foundation Models

Mapping information-rich genotype-phenotype landscapes with genome-scale Perturb-seq.

Zero-shot evaluation reveals limitations of single-cell foundation models.