cellxgene-census

Query CELLxGENE Census single-cell data via Python APIs for scalable analytics.

48|6|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/qinyan-ai/qinyan-academic-skills --skill cellxgene-census-qinyan-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cellxgene-census
Source: https://github.com/qinyan-ai/qinyan-academic-skills/tree/main/skills/05-%E7%94%9F%E7%89%A9%E4%BF%A1%E6%81%AF%E4%B8%8E%E5%9F%BA%E5%9B%A0%E7%BB%84%E5%AD%A6/cellxgene-census
Command: npx skills add https://github.com/qinyan-ai/qinyan-academic-skills --skill cellxgene-census-qinyan-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The CZ CELLxGENE Census is a versioned collection of single-cell data that researchers can query programmatically to perform scalable, reproducible analyses across millions of cells and datasets. This skill enables machine-driven discovery by exposing observations, gene expression matrices, and metadata through Python APIs, so users can build reproducible pipelines without manual data wrangling.

Core Features & Use Cases

  • Programmatic access to census observations and gene expression across Homo sapiens and Mus musculus.
  • Query metadata and expression using Python APIs (get_obs, get_anndata, get_var, axis_query) to retrieve metadata, expression matrices, and embeddings.
  • Seamless integration with analysis tools like Scanpy and PyTorch; supports out-of-core processing and dataset versioning for reproducible analyses.

Quick Start

Query the CELLxGENE Census programmatically and return a concise dataset summary of available datasets and sample metadata.

Frequently Asked Questions about cellxgene-census

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query single-cell gene expression data programmatically?

Access single-cell metadata and gene expression using Python APIs like get_obs, get_var, and get_anndata to retrieve specific slices from the CELLxGENE Census data.

Can I use Scanpy to analyze CELLxGENE Census data?

Yes, the CELLxGENE Census supports seamless integration with analysis tools like Scanpy and PyTorch, allowing you to pass queried data directly into your existing single-cell analysis pipelines.

What is the best way to access millions of single-cell observations without manual data wrangling?

Accessing millions of single-cell observations without manual wrangling is achieved by using the TileDB-SOMA based census_data objects, which expose observations and matrices directly via Python APIs.

Does the CELLxGENE Census support reproducible single-cell analytics?

The CELLxGENE Census supports reproducible single-cell analytics through dataset versioning using census_version and primary data filtering, ensuring consistent results across analyses.

How do I retrieve cell metadata for Homo sapiens and Mus musculus datasets?

Retrieve cell metadata for Homo sapiens and Mus musculus datasets by utilizing the get_obs API to programmatically query and extract observation-level metadata from the census.

Can I perform out-of-core processing on large-scale single-cell datasets using this API?

Yes, the API supports out-of-core processing for scalable single-cell analytics, enabling you to process large-scale gene expression datasets that exceed memory limits.