Cellxgene Census

uv pip install cellxgene-census

uv pip install cellxgene-census[experimental]

import cellxgene_census

# Open latest stable version
with cellxgene_census.open_soma() as census:
    # Work with census data

# Open specific version for reproducibility
with cellxgene_census.open_soma(census_version="2023-07-25") as census:
    # Work with census data

# Get summary statistics
summary = census["census_info"]["summary"].read().concat().to_pandas()
print(f"Total cells: {summary['total_cell_count'][0]}")

# Get all datasets
datasets = census["census_info"]["datasets"].read().concat().to_pandas()

# Filter datasets by criteria
covid_datasets = datasets[datasets["disease"].str.contains("COVID", na=False)]

# Get unique cell types in a tissue
cell_metadata = cellxgene_census.get_obs(
    census,
    "homo_sapiens",
    value_filter="tissue_general == 'brain' and is_primary_data == True",
    column_names=["cell_type"]
)
unique_cell_types = cell_metadata["cell_type"].unique()
print(f"Found {len(unique_cell_types)} cell types in brain")

# Count cells by tissue
tissue_counts = cell_metadata.groupby("tissue_general").size()

# Basic query with cell type and tissue filters
adata = cellxgene_census.get_anndata(
    census=census,
    organism="Homo sapiens",  # or "Mus musculus"
    obs_value_filter="cell_type == 'B cell' and tissue_general == 'lung' and is_primary_data == True",
    obs_column_names=["assay", "disease", "sex", "donor_id"],
)

# Query specific genes with multiple filters
adata = cellxgene_census.get_anndata(
    census=census,
    organism="Homo sapiens",
    var_value_filter="feature_name in ['CD4', 'CD8A', 'CD19', 'FOXP3']",
    obs_value_filter="cell_type == 'T cell' and disease == 'COVID-19' and is_primary_data == True",
    obs_column_names=["cell_type", "tissue_general", "donor_id"],
)

# Query cell metadata
cell_metadata = cellxgene_census.get_obs(
    census, "homo_sapiens",
    value_filter="disease == 'COVID-19' and is_primary_data == True",
    column_names=["cell_type", "tissue_general", "donor_id"]
)

# Query gene metadata
gene_metadata = cellxgene_census.get_var(
    census, "homo_sapiens",
    value_filter="feature_name in ['CD4', 'CD8A']",
    column_names=["feature_id", "feature_name", "feature_length"]
)

import tiledbsoma as soma

# Create axis query
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']"
    )
)

# Iterate through expression matrix in chunks
iterator = query.X("raw").tables()
for batch in iterator:
    # batch is a pyarrow.Table with columns:
    # - soma_data: expression value
    # - soma_dim_0: cell (obs) coordinate
    # - soma_dim_1: gene (var) coordinate
    process_batch(batch)

# Example: Calculate mean expression
n_observations = 0
sum_values = 0.0

iterator = query.X("raw").tables()
for batch in iterator:
    values = batch["soma_data"].to_numpy()
    n_observations += len(values)
    sum_values += values.sum()

mean_expression = sum_values / n_observations

from cellxgene_census.experimental.ml import experiment_dataloader

with cellxgene_census.open_soma() as census:
    # Create dataloader
    dataloader = experiment_dataloader(
        census["census_data"]["homo_sapiens"],
        measurement_name="RNA",
        X_name="raw",
        obs_value_filter="tissue_general == 'liver' and is_primary_data == True",
        obs_column_names=["cell_type"],
        batch_size=128,
        shuffle=True,
    )

    # Training loop
    for epoch in range(num_epochs):
        for batch in dataloader:
            X = batch["X"]  # Gene expression tensor
            labels = batch["obs"]["cell_type"]  # Cell type labels

            # Forward pass
            outputs = model(X)
            loss = criterion(outputs, labels)

            # Backward pass
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

from cellxgene_census.experimental.ml import ExperimentDataset

# Create dataset from experiment
dataset = ExperimentDataset(
    experiment_axis_query,
    layer_name="raw",
    obs_column_names=["cell_type"],
    batch_size=128,
)

# Split into train and test
train_dataset, test_dataset = dataset.random_split(
    split=[0.8, 0.2],
    seed=42
)

import scanpy as sc

# Load data from Census
adata = cellxgene_census.get_anndata(
    census=census,
    organism="Homo sapiens",
    obs_value_filter="cell_type == 'neuron' and tissue_general == 'cortex' and is_primary_data == True",
)

# Standard scanpy workflow
sc.pp.normalize_total(adata, target_sum=1e4)
sc.pp.log1p(adata)
sc.pp.highly_variable_genes(adata, n_top_genes=2000)

# Dimensionality reduction
sc.pp.pca(adata, n_comps=50)
sc.pp.neighbors(adata)
sc.tl.umap(adata)

# Visualization
sc.pl.umap(adata, color=["cell_type", "tissue", "disease"])

# Strategy 1: Query multiple tissues separately
tissues = ["lung", "liver", "kidney"]
adatas = []

for tissue in tissues:
    adata = cellxgene_census.get_anndata(
        census=census,
        organism="Homo sapiens",
        obs_value_filter=f"tissue_general == '{tissue}' and is_primary_data == True",
    )
    adata.obs["tissue"] = tissue
    adatas.append(adata)

# Concatenate
combined = adatas[0].concatenate(adatas[1:])

# Strategy 2: Query multiple datasets directly
adata = cellxgene_census.get_anndata(
    census=census,
    organism="Homo sapiens",
    obs_value_filter="tissue_general in ['lung', 'liver', 'kidney'] and is_primary_data == True",
)

obs_value_filter="cell_type == 'B cell' and is_primary_data == True"

census = cellxgene_census.open_soma(census_version="2023-07-25")

# Get cell count
metadata = cellxgene_census.get_obs(
    census, "homo_sapiens",
    value_filter="tissue_general == 'brain' and is_primary_data == True",
    column_names=["soma_joinid"]
)
n_cells = len(metadata)
print(f"Query will return {n_cells:,} cells")

# If too large (>100k), use out-of-core processing

# Broader grouping
obs_value_filter="tissue_general == 'immune system'"

# Specific tissue
obs_value_filter="tissue == 'peripheral blood mononuclear cell'"

obs_column_names=["cell_type", "tissue_general", "disease"]  # Not all columns

presence = cellxgene_census.get_presence_matrix(
    census,
    "homo_sapiens",
    var_value_filter="feature_name in ['CD4', 'CD8A']"
)

# Step 1: Explore what's available
metadata = cellxgene_census.get_obs(
    census, "homo_sapiens",
    value_filter="disease == 'COVID-19' and is_primary_data == True",
    column_names=["cell_type", "tissue_general"]
)
print(metadata.value_counts())

# Step 2: Query based on findings
adata = cellxgene_census.get_anndata(
    census=census,
    organism="Homo sapiens",
    obs_value_filter="disease == 'COVID-19' and cell_type == 'T cell' and is_primary_data == True",
)