{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import scanpy as sc"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AnnData object with n_obs × n_vars = 52117 × 3999\n",
" obs: 'batch', 'cluster_level2', 'cluster_level3', 'sample', 'cell_type', 'n_genes', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts', 'total_counts_mt', 'log1p_total_counts_mt', 'pct_counts_mt'\n",
" var: 'n_cells', 'mt', 'n_cells_by_counts', 'mean_counts', 'log1p_mean_counts', 'pct_dropout_by_counts', 'total_counts', 'log1p_total_counts', 'highly_variable', 'means', 'dispersions', 'dispersions_norm'\n",
" uns: 'batch_colors', 'cell_type_colors', 'cluster_level2_colors', 'cluster_level3_colors', 'neighbors', 'pca', 'sample_colors', 'umap'\n",
" obsm: 'X_pca', 'X_umap'\n",
" varm: 'PCs'\n",
" layers: 'count'\n",
" obsp: 'connectivities', 'distances'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"scrna = sc.read('../data/kotliarov-2020/expressions_hvg.h5ad')\n",
"scrna"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AnnData object with n_obs × n_vars = 52117 × 87\n",
" obs: 'batch', 'cluster_level2', 'cluster_level3', 'sample', 'cell_type', 'n_genes'\n",
" var: 'n_cells'\n",
" uns: 'batch_colors', 'cell_type_colors', 'cluster_level2_colors', 'cluster_level3_colors', 'neighbors', 'pca', 'sample_colors', 'umap'\n",
" obsm: 'X_pca', 'X_umap'\n",
" varm: 'PCs'\n",
" layers: 'count'\n",
" obsp: 'connectivities', 'distances'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cite = sc.read('../data/kotliarov-2020/protein.h5ad')\n",
"cite"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"scrna.obs['cluster_level1'] = scrna.obs['cell_type'].astype('category')\n",
"cite.obs['cluster_level1'] = cite.obs['cell_type'].astype('category')\n",
"\n",
"scrna.obs['cell_type'] = scrna.obs['cluster_level2'].astype('category')\n",
"cite.obs['cell_type'] = cite.obs['cluster_level2'].astype('category')"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/icb/litinetskaya/miniconda3/envs/multigrate/lib/python3.7/site-packages/anndata/_core/anndata.py:1094: FutureWarning: is_categorical is deprecated and will be removed in a future version. Use is_categorical_dtype instead\n",
" if not is_categorical(df_full[k]):\n",
"/home/icb/litinetskaya/miniconda3/envs/multigrate/lib/python3.7/site-packages/pandas/core/arrays/categorical.py:2487: FutureWarning: The `inplace` parameter in pandas.Categorical.remove_unused_categories is deprecated and will be removed in a future version.\n",
" res = method(*args, **kwargs)\n"
]
}
],
"source": [
"adata1 = scrna[scrna.obs.batch == 1]\n",
"adata2 = scrna[scrna.obs.batch == 2]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"cite1 = cite[cite.obs.batch == 1]\n",
"cite2 = cite[cite.obs.batch == 2]"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"View of AnnData object with n_obs × n_vars = 27740 × 3999\n",
" obs: 'batch', 'cluster_level2', 'cluster_level3', 'sample', 'cell_type', 'n_genes', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts', 'total_counts_mt', 'log1p_total_counts_mt', 'pct_counts_mt', 'cluster_level1'\n",
" var: 'n_cells', 'mt', 'n_cells_by_counts', 'mean_counts', 'log1p_mean_counts', 'pct_dropout_by_counts', 'total_counts', 'log1p_total_counts', 'highly_variable', 'means', 'dispersions', 'dispersions_norm'\n",
" uns: 'batch_colors', 'cluster_level2_colors', 'cluster_level3_colors', 'neighbors', 'pca', 'sample_colors', 'umap'\n",
" obsm: 'X_pca', 'X_umap'\n",
" varm: 'PCs'\n",
" layers: 'count'\n",
" obsp: 'connectivities', 'distances'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"adata1"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"View of AnnData object with n_obs × n_vars = 24377 × 3999\n",
" obs: 'batch', 'cluster_level2', 'cluster_level3', 'sample', 'cell_type', 'n_genes', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts', 'total_counts_mt', 'log1p_total_counts_mt', 'pct_counts_mt', 'cluster_level1'\n",
" var: 'n_cells', 'mt', 'n_cells_by_counts', 'mean_counts', 'log1p_mean_counts', 'pct_dropout_by_counts', 'total_counts', 'log1p_total_counts', 'highly_variable', 'means', 'dispersions', 'dispersions_norm'\n",
" uns: 'cluster_level2_colors', 'cluster_level3_colors', 'neighbors', 'pca', 'umap'\n",
" obsm: 'X_pca', 'X_umap'\n",
" varm: 'PCs'\n",
" layers: 'count'\n",
" obsp: 'connectivities', 'distances'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"adata2"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"View of AnnData object with n_obs × n_vars = 27740 × 87\n",
" obs: 'batch', 'cluster_level2', 'cluster_level3', 'sample', 'cell_type', 'n_genes', 'cluster_level1'\n",
" var: 'n_cells'\n",
" uns: 'batch_colors', 'cluster_level2_colors', 'cluster_level3_colors', 'neighbors', 'pca', 'sample_colors', 'umap'\n",
" obsm: 'X_pca', 'X_umap'\n",
" varm: 'PCs'\n",
" layers: 'count'\n",
" obsp: 'connectivities', 'distances'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cite1"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"View of AnnData object with n_obs × n_vars = 24377 × 87\n",
" obs: 'batch', 'cluster_level2', 'cluster_level3', 'sample', 'cell_type', 'n_genes', 'cluster_level1'\n",
" var: 'n_cells'\n",
" uns: 'cluster_level2_colors', 'cluster_level3_colors', 'neighbors', 'pca', 'umap'\n",
" obsm: 'X_pca', 'X_umap'\n",
" varm: 'PCs'\n",
" layers: 'count'\n",
" obsp: 'connectivities', 'distances'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cite2"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"adata1.write('../data/kotliarov-2020/adata1.h5ad')\n",
"adata2.write('../data/kotliarov-2020/adata2.h5ad')\n",
"cite1.write('../data/kotliarov-2020/cite1.h5ad')\n",
"cite2.write('../data/kotliarov-2020/cite2.h5ad')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}