anndata-data-structure

AnnData — Annotated Data Matrices for Single-Cell Genomics

Overview

AnnData provides the standard data structure for single-cell genomics in the scverse ecosystem. It stores an observations-by-variables matrix (X) alongside cell metadata (obs), gene metadata (var), layers, embeddings (obsm/varm), graphs (obsp/varp), and unstructured metadata (uns). Supports sparse matrices, H5AD/Zarr storage, backed mode for large files, and integration with Scanpy, scvi-tools, and Muon.

When to Use

• Constructing annotated matrices from raw count data with cell/gene metadata
• Reading/writing .h5ad or .zarr files for single-cell experiments
• Subsetting cells by quality metrics, gene sets, or metadata conditions
• Concatenating multiple experimental batches with consistent metadata
• Storing multiple data layers (raw counts, normalized, scaled) in one object
• Working with large datasets exceeding RAM (backed mode, lazy concatenation)
• Preparing data for Scanpy or scvi-tools pipelines
• For single-cell analysis (clustering, DE, visualization), use scanpy instead
• For probabilistic models, use scvi-tools instead

Prerequisites

• Python packages: anndata, scipy, pandas, numpy
• Optional: scanpy (analysis), zarr (cloud storage), h5py (HDF5 backend)
• Data requirements: count matrices (dense or sparse), cell/gene metadata tables

pip install "anndata>=0.10"
# Full ecosystem
pip install anndata scanpy zarr

Quick Start

import anndata as ad
import numpy as np
import pandas as pd
from scipy.sparse import csr_matrix

counts = csr_matrix(np.random.poisson(0.5, (500, 2000)).astype(np.float32))
obs = pd.DataFrame({"cell_type": np.random.choice(["T", "B", "NK"], 500)},
                    index=[f"cell_{i}" for i in range(500)])
var = pd.DataFrame(index=[f"ENSG{i:05d}" for i in range(2000)])
adata = ad.AnnData(X=counts, obs=obs, var=var)
adata.layers["raw_counts"] = counts.copy()
adata.write_h5ad("example.h5ad", compression="gzip")
print(f"Created: {adata.n_obs} cells x {adata.n_vars} genes")
# Created: 500 cells x 2000 genes

Core API

1. Object Creation

Build AnnData objects from arrays, DataFrames, and sparse matrices.

import anndata as ad
import numpy as np
import pandas as pd
from scipy.sparse import csr_matrix

# Minimal: just a matrix
adata_min = ad.AnnData(X=np.random.rand(100, 50).astype(np.float32))
print(f"Minimal: {adata_min.shape}")  # (100, 50)

# Full: sparse matrix + obs/var metadata
n_obs, n_vars = 300, 1000
X = csr_matrix(np.random.poisson(1, (n_obs, n_vars)).astype(np.float32))
obs = pd.DataFrame({"cell_type": np.random.choice(["T", "B", "Mono"], n_obs),
                     "batch": np.repeat(["ctrl", "stim"], n_obs // 2)},
                    index=[f"cell_{i}" for i in range(n_obs)])
var = pd.DataFrame({"gene_symbol": [f"Gene_{i}" for i in range(n_vars)],
                     "mt": [i < 13 for i in range(n_vars)]},
                    index=[f"ENSG{i:05d}" for i in range(n_vars)])
adata = ad.AnnData(X=X, obs=obs, var=var)
print(f"Full: {adata.shape}, obs cols: {list(adata.obs.columns)}")
# Full: (300, 1000), obs cols: ['cell_type', 'batch']

# From a pandas DataFrame (rows=obs, columns=vars)
df = pd.DataFrame(np.random.rand(50, 20),
                  index=[f"sample_{i}" for i in range(50)],
                  columns=[f"feature_{i}" for i in range(20)])
adata_df = ad.AnnData(df)
print(f"From DataFrame: {adata_df.shape}")  # (50, 20)

2. I/O Operations

Read and write in multiple formats including backed mode for large files.

import anndata as ad

# H5AD (native format, recommended for most use cases)
adata = ad.read_h5ad("data.h5ad")
adata.write_h5ad("output.h5ad", compression="gzip")  # gzip: smaller files

# 10X Genomics formats
adata_10x = ad.read_10x_h5("filtered_feature_bc_matrix.h5")
# adata_mtx = ad.read_10x_mtx("filtered_feature_bc_matrix/")

# Zarr format (cloud-friendly, parallel I/O)
adata.write_zarr("output.zarr")
adata_zarr = ad.read_zarr("output.zarr")

# Other formats
# adata = ad.read_csv("expression.csv")
# adata = ad.read_loom("data.loom")

print(f"Loaded: {adata.n_obs} obs x {adata.n_vars} vars")

import anndata as ad

# Backed mode: lazy loading for files larger than RAM
adata_backed = ad.read_h5ad("large_data.h5ad", backed="r")  # read-only
print(f"Backed: {adata_backed.n_obs} obs, isbacked={adata_backed.isbacked}")

# Filter on metadata (no data loaded), then load subset into memory
subset = adata_backed[adata_backed.obs["tissue"] == "brain"].to_memory()
print(f"Loaded subset: {subset.n_obs} cells")

# Read-write backed mode: adata_rw = ad.read_h5ad("data.h5ad", backed="r+")
# Format conversion: ad.read_loom("data.loom").write_h5ad("out.h5ad", compression="gzip")

3. Subsetting and Views

Select cells and genes by indices, names, boolean masks, or metadata conditions.

import anndata as ad

adata = ad.read_h5ad("data.h5ad")

# Boolean mask (most common)
t_cells = adata[adata.obs["cell_type"] == "T_cell"]
print(f"T cells: {t_cells.n_obs}, is_view: {t_cells.is_view}")  # is_view: True

# Integer index / name-based / combined axis
first_100 = adata[:100, :500]
selected = adata[["cell_0", "cell_1"], ["ENSG00000", "ENSG00001"]]

# Combined metadata conditions
high_quality = adata[
    (adata.obs["n_genes"] > 200) & (adata.obs["pct_mito"] < 0.2)
]
print(f"QC filter: {high_quality.n_obs} / {adata.n_obs} cells")

# Views vs copies: subsetting returns a view (lightweight, shares data)
# .copy() creates an independent object (REQUIRED before modification)
independent = adata[adata.obs["batch"] == "ctrl"].copy()
print(f"Is view: {independent.is_view}")  # False

4. Layers, Embeddings, and Graphs

Store multiple data representations, dimensionality reductions, and cell-cell graphs.

import anndata as ad
import numpy as np
from scipy.sparse import csr_matrix

adata = ad.read_h5ad("data.h5ad")

# Layers: alternative representations of X (same shape as X)
adata.layers["raw_counts"] = adata.X.copy()
adata.layers["normalized"] = adata.X.copy()
print(f"Layers: {list(adata.layers.keys())}")
# Layers: ['raw_counts', 'normalized']

# Embeddings in obsm (n_obs x n_components)
adata.obsm["X_pca"] = np.random.randn(adata.n_obs, 50).astype(np.float32)
adata.obsm["X_umap"] = np.random.randn(adata.n_obs, 2).astype(np.float32)
print(f"obsm keys: {list(adata.obsm.keys())}")

# Variable loadings in varm (n_vars x n_components)
adata.varm["PCs"] = np.random.randn(adata.n_vars, 50).astype(np.float32)

# Pairwise graphs in obsp (n_obs x n_obs, sparse)
adata.obsp["connectivities"] = csr_matrix(
    np.random.rand(adata.n_obs, adata.n_obs) > 0.99)
adata.obsp["distances"] = adata.obsp["connectivities"].copy()

# Unstructured metadata in uns (arbitrary dict)
adata.uns["experiment"] = {"date": "2024-06-01", "protocol": "10x_v3"}
adata.uns["neighbors"] = {"params": {"n_neighbors": 15, "method": "umap"}}
adata.uns["cell_type_colors"] = ["#1f77b4", "#ff7f0e", "#2ca02c"]
print(f"uns keys: {list(adata.uns.keys())}")

5. Concatenation

Merge datasets along observations or variables with flexible join and merge strategies.

import anndata as ad
import numpy as np
import pandas as pd
from scipy.sparse import csr_matrix

# Create sample datasets
def make_adata(n, genes, batch_name):
    X = csr_matrix(np.random.poisson(1, (n, len(genes))).astype(np.float32))
    obs = pd.DataFrame({"sample": batch_name}, index=[f"{batch_name}_{i}" for i in range(n)])
    return ad.AnnData(X=X, obs=obs, var=pd.DataFrame(index=genes))

shared = [f"Gene_{i}" for i in range(100)]
adata1 = make_adata(200, shared + ["GeneA"], "batch1")
adata2 = make_adata(300, shared + ["GeneB"], "batch2")

# Along observations (axis=0): stack cells
combined = ad.concat(
    [adata1, adata2], axis=0, join="inner",
    label="batch", keys=["B1", "B2"], merge="same",
)
print(f"Inner join: {combined.n_obs} cells, {combined.n_var