{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import warnings\n",
"warnings.simplefilter(action='ignore', category=FutureWarning)\n",
"\n",
"import multigrate as mtg\n",
"import scanpy as sc\n",
"import numpy as np"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# MOFA"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AnnData object with n_obs × n_vars = 7362 × 10\n",
" obs: 'source', 'replicate', 'experiment', 'tsne_1', 'tsne_2', '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'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"latent = sc.read('../data/integrated/mofa/cao-mofa.h5ad')\n",
"latent"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"latent.obsm['latent'] = latent.X"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Clustering...\n",
"Graph connectivity...\n",
"ASW label...\n",
"NMI cluster/label...\n",
"ARI cluster/label...\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>graph_conn</th>\n",
" <td>0.762252</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ASW_label</th>\n",
" <td>0.575249</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NMI_cluster/label</th>\n",
" <td>0.663998</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ARI_cluster/label</th>\n",
" <td>0.498524</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" score\n",
"graph_conn 0.762252\n",
"ASW_label 0.575249\n",
"NMI_cluster/label 0.663998\n",
"ARI_cluster/label 0.498524"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"metrics = mtg.metrics.metrics(None, latent,\n",
" batch_key=None,\n",
" label_key='cell_type',\n",
" isolated_label_f1=False,\n",
" isolated_label_asw=False,\n",
" pcr_batch=False,\n",
" asw_batch=False,\n",
" embed='latent', \n",
" save='cao-mofa.csv', \n",
" method='mofa')\n",
"metrics"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Seurat"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AnnData object with n_obs × n_vars = 7362 × 20\n",
" obs: 'cell_type', 'nCount_ATAC', 'nFeature_ATAC', 'nCount_SCT', 'nFeature_SCT', 'SCT.weight', 'ATAC.weight'\n",
" obsp: 'connectivities'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"latent = sc.read('../data/integrated/seurat/cao-seurat.h5ad')\n",
"latent"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AnnData object with n_obs × n_vars = 7362 × 4000\n",
" obs: 'source', 'replicate', 'experiment', 'tsne_1', 'tsne_2', '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: 'gene_type', 'gene_short_name', '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', 'highly_variable_nbatches', 'highly_variable_intersection'\n",
" uns: 'cell_type_colors', 'neighbors', 'replicate_colors', 'umap'\n",
" obsm: 'X_pca', 'X_tsne', 'X_umap'\n",
" layers: 'count'\n",
" obsp: 'connectivities', 'distances'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rna = sc.read('../data/cao-2018/expressions.h5ad')\n",
"rna"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.sum(rna.obs_names != latent.obs_names)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AnnData object with n_obs × n_vars = 7362 × 20\n",
" obs: 'cell_type', 'nCount_ATAC', 'nFeature_ATAC', 'nCount_SCT', 'nFeature_SCT', 'SCT.weight', 'ATAC.weight'\n",
" obsm: 'latent'\n",
" obsp: 'connectivities'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"latent.obsm['latent'] = latent.X\n",
"latent.obs['cell_type'] = rna.obs['cell_type'].astype('category')\n",
"latent"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Clustering...\n",
"Graph connectivity...\n",
"ASW label...\n",
"NMI cluster/label...\n",
"ARI cluster/label...\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>graph_conn</th>\n",
" <td>0.692209</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ASW_label</th>\n",
" <td>0.561667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NMI_cluster/label</th>\n",
" <td>0.623704</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ARI_cluster/label</th>\n",
" <td>0.542221</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" score\n",
"graph_conn 0.692209\n",
"ASW_label 0.561667\n",
"NMI_cluster/label 0.623704\n",
"ARI_cluster/label 0.542221"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"metrics = mtg.metrics.metrics(None, latent,\n",
" batch_key=None,\n",
" label_key='cell_type',\n",
" isolated_label_f1=False,\n",
" isolated_label_asw=False,\n",
" pcr_batch=False,\n",
" asw_batch=False,\n",
" embed='latent', \n",
" save='cao-seurat.csv', \n",
" method='seurat')\n",
"metrics"
]
},
{
"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": 4
}