Anndata

# Subset by metadata
filtered = adata[adata.obs['quality_score'] > 0.8]
hv_genes = adata[:, adata.var['highly_variable']]

# Transpose
adata_T = adata.T

# Copy vs view
view = adata[0:100, :]  # View (lightweight reference)
copy = adata[0:100, :].copy()  # Independent copy

# Convert strings to categoricals
adata.strings_to_categoricals()

# Use sparse matrices for sparse data
from scipy.sparse import csr_matrix
adata.X = csr_matrix(adata.X)

# Convert strings to categoricals
adata.strings_to_categoricals()

# Use backed mode for large files
adata = ad.read_h5ad('large.h5ad', backed='r')

# Store raw before filtering
adata.raw = adata.copy()
adata = adata[:, adata.var['highly_variable']]

import scanpy as sc

# Preprocessing
sc.pp.filter_cells(adata, min_genes=200)
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, n_neighbors=15)
sc.tl.umap(adata)
sc.tl.leiden(adata)

# Visualization
sc.pl.umap(adata, color=['cell_type', 'leiden'])

import muon as mu

# Combine RNA and protein data
mdata = mu.MuData({'rna': adata_rna, 'protein': adata_protein})

from anndata.experimental import AnnLoader

# Create DataLoader for deep learning
dataloader = AnnLoader(adata, batch_size=128, shuffle=True)

for batch in dataloader:
    X = batch.X
    # Train model

import anndata as ad
import scanpy as sc

# 1. Load data
adata = ad.read_10x_h5('filtered_feature_bc_matrix.h5')

# 2. Quality control
adata.obs['n_genes'] = (adata.X > 0).sum(axis=1)
adata.obs['n_counts'] = adata.X.sum(axis=1)
adata = adata[adata.obs['n_genes'] > 200]
adata = adata[adata.obs['n_counts'] < 50000]

# 3. Store raw
adata.raw = adata.copy()

# 4. Normalize and filter
sc.pp.normalize_total(adata, target_sum=1e4)
sc.pp.log1p(adata)
sc.pp.highly_variable_genes(adata, n_top_genes=2000)
adata = adata[:, adata.var['highly_variable']]

# 5. Save processed data
adata.write_h5ad('processed.h5ad')

# Load multiple batches
adata1 = ad.read_h5ad('batch1.h5ad')
adata2 = ad.read_h5ad('batch2.h5ad')
adata3 = ad.read_h5ad('batch3.h5ad')

# Concatenate with batch labels
adata = ad.concat(
    [adata1, adata2, adata3],
    label='batch',
    keys=['batch1', 'batch2', 'batch3'],
    join='inner'
)

# Apply batch correction
import scanpy as sc
sc.pp.combat(adata, key='batch')

# Continue analysis
sc.pp.pca(adata)
sc.pp.neighbors(adata)
sc.tl.umap(adata)

# Open in backed mode
adata = ad.read_h5ad('100GB_dataset.h5ad', backed='r')

# Filter based on metadata (no data loading)
high_quality = adata[adata.obs['quality_score'] > 0.8]

# Load filtered subset
adata_subset = high_quality.to_memory()

# Process subset
process(adata_subset)

# Or process in chunks
chunk_size = 1000
for i in range(0, adata.n_obs, chunk_size):
    chunk = adata[i:i+chunk_size, :].to_memory()
    process(chunk)

# Backed mode
adata = ad.read_h5ad('file.h5ad', backed='r')

# Sparse matrices
from scipy.sparse import csr_matrix
adata.X = csr_matrix(adata.X)

# Optimize for storage
adata.strings_to_categoricals()
adata.write_h5ad('file.h5ad', compression='gzip')

# Use Zarr for cloud storage
adata.write_zarr('file.zarr', chunks=(1000, 1000))

# Wrong
adata.obs['new_col'] = external_data['values']

# Correct
adata.obs['new_col'] = external_data.set_index('cell_id').loc[adata.obs_names, 'values']