cellxgene-census
Programmatically query the CZ CELLxGENE Census (61M+ cells) when you need cross-tissue, disease, or cell-type expression data for population-scale queries and reference atlas comparisons.
Best use case
cellxgene-census is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Programmatically query the CZ CELLxGENE Census (61M+ cells) when you need cross-tissue, disease, or cell-type expression data for population-scale queries and reference atlas comparisons.
Teams using cellxgene-census should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/cellxgene-census/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How cellxgene-census Compares
| Feature / Agent | cellxgene-census | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Programmatically query the CZ CELLxGENE Census (61M+ cells) when you need cross-tissue, disease, or cell-type expression data for population-scale queries and reference atlas comparisons.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
## When to Use
- **Cross-tissue or cross-disease expression comparisons** (e.g., macrophages across lung/liver/brain; COVID-19 vs control).
- **Reference atlas lookups** to contextualize findings from your own single-cell dataset (marker validation, expected expression patterns).
- **Population-scale metadata exploration** (what tissues/cell types/datasets exist; cell counts by cohort attributes).
- **Large-scale expression statistics** where results exceed RAM and require out-of-core iteration.
- **Model training on curated atlas data** (e.g., cell-type classifiers) using the experimental PyTorch integration.
## Key Features
- Programmatic access to **versioned** CZ CELLxGENE Census data (human and mouse).
- Query **cell (obs) metadata** and **gene (var) metadata** with expressive filter syntax.
- Retrieve expression as **AnnData** for small/medium queries via `get_anndata()`.
- Perform **out-of-core** expression access via SOMA `axis_query()` and chunked iteration.
- Optional **experimental ML utilities** (PyTorch dataloaders/datasets).
- Works well with **scanpy** workflows after loading AnnData.
## Dependencies
- `cellxgene-census` (latest)
- `tiledbsoma` (latest; required for `axis_query()` workflows)
- `pyarrow` (latest; used for chunked table batches)
- `anndata` (latest; for `get_anndata()` results)
- `scanpy` (latest; optional, for downstream analysis)
- `torch` (latest; optional, for experimental ML integration)
Install:
```bash
uv pip install cellxgene-census
```
Optional (experimental ML helpers):
```bash
uv pip install cellxgene-census[experimental]
```
## Example Usage
The following script is a complete, runnable example that:
1) opens a pinned Census version,
2) explores metadata,
3) loads a small AnnData slice, and
4) runs an out-of-core query to compute a simple statistic.
```python
import numpy as np
import cellxgene_census
import tiledbsoma as soma
def main():
# Pin a version for reproducibility (replace with a valid release if needed)
census_version = "2023-07-25"
with cellxgene_census.open_soma(census_version=census_version) as census:
# 1) Explore summary info
summary = census["census_info"]["summary"].read().concat().to_pandas()
total_cells = int(summary["total_cell_count"].iloc[0])
print(f"Census version: {census_version}")
print(f"Total cells: {total_cells:,}")
# 2) Explore obs metadata (always filter primary data unless you want duplicates)
obs = cellxgene_census.get_obs(
census,
"homo_sapiens",
value_filter="tissue_general == 'brain' and is_primary_data == True",
column_names=["cell_type", "tissue_general", "disease", "donor_id"],
)
print(f"Brain (primary) cells returned (metadata only): {len(obs):,}")
print("Top cell types:")
print(obs["cell_type"].value_counts().head(10))
# 3) Small/medium query -> AnnData in memory
adata = cellxgene_census.get_anndata(
census=census,
organism="Homo sapiens",
obs_value_filter=(
"cell_type == 'T cell' and disease == 'COVID-19' and is_primary_data == True"
),
var_value_filter="feature_name in ['CD4', 'CD8A', 'FOXP3']",
obs_column_names=["cell_type", "tissue_general", "disease", "donor_id", "sex"],
)
print(adata)
print("AnnData X shape:", adata.X.shape)
# 4) Large-scale pattern -> out-of-core iteration with axis_query()
# Example: compute mean of non-zero expression values for a few genes in brain.
query = census["census_data"]["homo_sapiens"].axis_query(
measurement_name="RNA",
obs_query=soma.AxisQuery(
value_filter="tissue_general == 'brain' and is_primary_data == True"
),
var_query=soma.AxisQuery(
value_filter="feature_name in ['FOXP2', 'TBR1', 'SATB2']"
),
)
n = 0
s = 0.0
for batch in query.X("raw").tables():
# batch is a pyarrow.Table with at least: soma_data, soma_dim_0, soma_dim_1
values = batch["soma_data"].to_numpy(zero_copy_only=False)
n += values.size
s += float(values.sum())
mean_expr = s / n if n else np.nan
print(f"Out-of-core mean expression (over returned entries): {mean_expr:.6g}")
if __name__ == "__main__":
main()
```
## Implementation Details
- **Opening the Census**
- Use a context manager to ensure resources are released:
- `with cellxgene_census.open_soma(...) as census: ...`
- For reproducibility, set `census_version="YYYY-MM-DD"`; otherwise the latest stable release is used.
- **Data model (high level)**
- Census data is stored in **SOMA** collections.
- `census["census_info"]` provides summary tables (e.g., datasets, counts).
- `census["census_data"][organism]` provides the experiment for an organism (e.g., `homo_sapiens`).
- **Filtering semantics**
- `obs_value_filter` filters **cells** (obs); `var_value_filter` filters **genes** (var).
- Combine predicates with `and` / `or`; use `in [...]` for multi-value membership.
- Best practice: include `is_primary_data == True` to avoid double-counting cells that appear in multiple source datasets.
- **Choosing an access pattern**
- Use `get_anndata()` when the result is expected to fit in memory (commonly < ~100k cells, depending on gene count and sparsity).
- Use `axis_query()` + `query.X("raw").tables()` for **out-of-core** iteration and incremental statistics.
- **Expression layers / matrices**
- Examples commonly use `X("raw")` to access raw expression.
- Chunk iteration yields Arrow tables with:
- `soma_data`: expression values
- `soma_dim_0`: obs (cell) coordinates
- `soma_dim_1`: var (gene) coordinates
- **Optional ML integration**
- The `cellxgene_census.experimental.ml` utilities provide PyTorch-friendly datasets/dataloaders for training workflows, typically driven by the same obs/var filtering concepts used elsewhere.Related Skills
skill-auditor
A comprehensive auditor for any agent skill — including Manus, OpenClaw/ClawHub, Claude, LobeHub, or custom SKILL.md-based skills. Use this skill whenever a user wants to evaluate, audit, review, score, or quality-check an agent skill before publishing, updating, or deploying. Covers two hard veto gates (structural redlines + research integrity redlines), static quality scoring across 25 criteria (ISO 25010 + OpenSSF + Agent), dynamic test input generation, multi-mode execution testing, multi-layer output evaluation with five specialized category rubrics (Evidence Insight / Protocol Design / Data Analysis / Academic Writing / Other), a Research Veto that applies to all four research categories, human eval viewer generation, actionable P0/P1/P2 optimization recommendations, and automatic skill improvement that outputs a polished, production-ready SKILL.md. Also use whenever a user says "audit my skill", "evaluate my skill", "improve my skill", or wants a corrected version after evaluation.
two-sample-mr-research-planner
Generates complete two-sample Mendelian randomization (MR) research designs from a user-provided research direction. Use when users want to design, plan, or build a study using two-sample MR to test causal relationships. Triggers:"design a two-sample MR study", "build a publishable MR paper", "test whether this biomarker causally affects this disease", "generate Lite/Standard/Advanced MR plans", "screen multiple exposures with MR", "bidirectional MR design", "causal inference using GWAS summary statistics", or "I want to study X and Y using MR". Always outputs four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.
research-proposal-generator
Generates a comprehensive research proposal design based on input literature, including hypothesis, mechanism verification, and budget. Use when the user wants to design a research project from a paper.
research-grants
Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan's NSTC when you need agency-compliant narratives, budgets, and review-criteria alignment for a specific solicitation/FOA/BAA.
protocol-standardization
Standardize fragmented experimental steps into reproducible protocol documents when you need method organization, lab SOP drafting, or cross-operator reproducibility; missing parameters must be explicitly marked as "To be supplemented/Not provided".
prospero-registration-helper
Assists researchers in generating PROSPERO registration content for meta-analyses from a title and optional protocol. Use when the user wants to draft a PROSPERO registration form.
non-tumor-ml-research-planner
Generates complete non-tumor biomedical machine learning research designs from a user-provided research direction. Always use this skill when users want to plan bioinformatics + ML papers for non-cancer diseases (metabolic, cardiovascular, kidney, inflammatory, autoimmune, infectious, neurological, endocrine, wound healing, chronic multifactor), design diagnostic biomarker studies, combine GEO datasets with feature selection and ML modeling, or generate Lite/Standard/Advanced/Publication+ workload plans. Trigger for:"non-tumor ML study", "bioinformatics paper outside oncology", "key genes and diagnostic model for a disease", "pyroptosis/ferroptosis/senescence/autophagy + disease", "GEO datasets + machine learning", "RF + LASSO diagnostic model", "DEG + feature selection + validation", "immune infiltration + biomarker", "non-cancer biomarker paper". Trigger even for casual phrasings like "I want to study X using machine learning", "help me design a non-tumor bioinformatics paper", or "how do I build a diagnostic model for disease Y".
network-tox-docking-research-planner
Generates complete network toxicology + molecular docking research designs from a user-provided toxicant and disease/phenotype. Always use this skill when users want to investigate how an environmental toxicant, endocrine disruptor, heavy metal, food contaminant, pharmaceutical residue, or consumer product chemical may contribute to a disease through shared molecular targets, hub genes, pathways, and docking evidence. Trigger for:"network toxicology study", "toxicology mechanism paper", "target prediction + PPI + docking", "environmental pollutant and disease mechanism", "hub genes and docking for toxicant", "Lite/Standard/Advanced toxicology plan", "CTD + SwissTargetPrediction + GeneCards + STRING", "CB-Dock2 docking study", "triclosan/BPA/cadmium/PFAS + disease". Also triggers for Chinese phrasings:"网络毒理学研究设计"、"毒物机制论文"、"靶点预测+PPI+对接"、"环境污染物与疾病机制". Trigger even for casual phrasings like "I want to study how chemical X affects disease Y" or "help me design a toxicology paper". Always output four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.
meta-protocol-writer
Generates a PROSPERO-compliant Meta-analysis protocol based on Title and PICOS. Use when the user wants to write a protocol for a systematic review or meta-analysis.
hypothesis-generation
Structured scientific hypothesis formulation from observations; use when you have experimental observations or preliminary data and need testable hypotheses with predictions, mechanisms, and validation experiments.
hypogenic
Automated LLM-driven hypothesis generation and testing for tabular datasets; use when you need systematic exploration of empirical patterns (e.g., fraud detection, content analysis) and want to combine literature insights with data-driven hypothesis evaluation.
faers-multi-drug-soc-planner
Generates complete FAERS-based multi-drug single-SOC safety comparison research designs from a user-provided drug set, comparator, and adverse event domain. Always use this skill when users want to compare safety signals across multiple drugs using FAERS or OpenFDA data within one System Organ Class (SOC) or bounded AE domain. Trigger for:"FAERS study comparing drugs within one SOC", "publishable FAERS safety comparison paper", "compare neuropsychiatric adverse events across beta-blockers", "Lite/Standard/Advanced FAERS safety plans", "active-comparator restricted disproportionality", "adjusted ROR logistic regression FAERS", "within-class head-to-head drug comparison", "pharmacovigilance signal comparison", "single-SOC PT-level FAERS design", or any phrasing like "I want to compare drug X and drug Y for adverse events in FAERS" or "build a comparative pharmacovigilance paper". Always output four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.