{
 "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"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# MOFA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AnnData object with n_obs × n_vars = 30293 × 13\n",
       "    obs: 'batch_indices', 'n_genes', 'percent_mito', 'leiden_subclusters', 'cell_type', 'tissue', 'batch', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "latent = sc.read('../data/integrated/mofa/gayoso-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",
      "ASW label/batch...\n",
      "Graph connectivity...\n",
      "ASW label...\n",
      "NMI cluster/label...\n",
      "ARI cluster/label...\n",
      "Isolated label silhouette...\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>ASW_label/batch</th>\n",
       "      <td>0.876851</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>graph_conn</th>\n",
       "      <td>0.892205</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ASW_label</th>\n",
       "      <td>0.558320</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NMI_cluster/label</th>\n",
       "      <td>0.704188</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ARI_cluster/label</th>\n",
       "      <td>0.626555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>isolated_label_silhouette</th>\n",
       "      <td>0.632080</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                              score\n",
       "ASW_label/batch            0.876851\n",
       "graph_conn                 0.892205\n",
       "ASW_label                  0.558320\n",
       "NMI_cluster/label          0.704188\n",
       "ARI_cluster/label          0.626555\n",
       "isolated_label_silhouette  0.632080"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "metrics = mtg.metrics.metrics(None, latent,\n",
    "                      batch_key='batch_indices',\n",
    "                      label_key='cell_type',\n",
    "                      isolated_label_f1=False,\n",
    "                      pcr_batch=False,\n",
    "                      embed='latent', \n",
    "                      save='gayoso-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 = 30293 × 20\n",
       "    obs: 'cell_type', 'batch', 'nCount_RNA', 'nFeature_RNA', 'nCount_SCT', 'nFeature_SCT', 'integrated.weight'\n",
       "    obsp: 'connectivities'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "latent = sc.read('../data/integrated/seurat/gayoso-seurat.h5ad')\n",
    "latent"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "latent.obsm['latent'] = latent.X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Clustering...\n",
      "ASW label/batch...\n",
      "Graph connectivity...\n",
      "ASW label...\n",
      "NMI cluster/label...\n",
      "ARI cluster/label...\n",
      "Isolated label silhouette...\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>ASW_label/batch</th>\n",
       "      <td>0.914544</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>graph_conn</th>\n",
       "      <td>0.936758</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ASW_label</th>\n",
       "      <td>0.617050</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NMI_cluster/label</th>\n",
       "      <td>0.709452</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ARI_cluster/label</th>\n",
       "      <td>0.628502</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>isolated_label_silhouette</th>\n",
       "      <td>0.617743</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                              score\n",
       "ASW_label/batch            0.914544\n",
       "graph_conn                 0.936758\n",
       "ASW_label                  0.617050\n",
       "NMI_cluster/label          0.709452\n",
       "ARI_cluster/label          0.628502\n",
       "isolated_label_silhouette  0.617743"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "metrics = mtg.metrics.metrics(None, latent,\n",
    "                      batch_key='batch',\n",
    "                      label_key='cell_type',\n",
    "                      isolated_label_f1=False,\n",
    "                      pcr_batch=False,\n",
    "                      embed='latent', \n",
    "                      save='gayoso-seurat.csv', \n",
    "                      method='seurat')\n",
    "metrics"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# totalVI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AnnData object with n_obs × n_vars = 30293 × 20\n",
       "    obs: 'batch_indices', 'n_genes', 'percent_mito', 'leiden_subclusters', 'cell_types', 'tissue', 'batch', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts', '_scvi_batch', '_scvi_labels', '_scvi_local_l_mean', '_scvi_local_l_var'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "latent = sc.read('../data/integrated/totalvi/gayoso-totalvi.h5ad')\n",
    "latent"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "latent.obsm['latent'] = latent.X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Clustering...\n",
      "ASW label/batch...\n",
      "Graph connectivity...\n",
      "ASW label...\n",
      "NMI cluster/label...\n",
      "ARI cluster/label...\n",
      "Isolated label silhouette...\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>ASW_label/batch</th>\n",
       "      <td>0.955026</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>graph_conn</th>\n",
       "      <td>0.942385</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ASW_label</th>\n",
       "      <td>0.547595</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NMI_cluster/label</th>\n",
       "      <td>0.750054</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ARI_cluster/label</th>\n",
       "      <td>0.694281</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>isolated_label_silhouette</th>\n",
       "      <td>0.576691</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                              score\n",
       "ASW_label/batch            0.955026\n",
       "graph_conn                 0.942385\n",
       "ASW_label                  0.547595\n",
       "NMI_cluster/label          0.750054\n",
       "ARI_cluster/label          0.694281\n",
       "isolated_label_silhouette  0.576691"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "metrics = mtg.metrics.metrics(None, latent,\n",
    "                      batch_key='batch_indices',\n",
    "                      label_key='cell_types',\n",
    "                      isolated_label_f1=False,\n",
    "                      pcr_batch=False,\n",
    "                      embed='latent', \n",
    "                      save='gayoso-totalvi.csv', \n",
    "                      method='totalVI')\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
}