{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Tutorial of pymmdb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pymmdb import MMDB"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### 1. Create a MMDB object that provides access to the datasets in scMMDB database."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MMDB(storage_path=./, server_address=https://mmdb.piaqia.com/)\n"
     ]
    }
   ],
   "source": [
    "mmdb = MMDB('./') # creates a new MMDB object with the current directory as the root\n",
    "print(mmdb) # prints the configuration of the MMDB object"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### 2. Check the scMMDB's details."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MMDB Information: \n",
      "Species:  Homo sapiens, Mus musculus, Macaca mulatta, Sus scrofa\n",
      "Tissue:  human cell line , human cell line, human blood, human bone marrow, human kidney, human primary motor cortex, human intra-abdominal lymph node tumor, human brain, human achilles tendon, mouse retina, mouse colon, mouse brain cortex, mouse cell line, mouse forebrain, mouse kidney, mouse primary motor cortex, mouse brain, human brain cortex, human jejunum, mouse thymic epithelium, human lung, bone marrow, human liver, human glioblastoma, human blood/skin, human tumor, macaca vaginal, mouse submandibular gland, mouse aorta, mouse tumor, mouse bone marrow, mouse mesenteric lymph nodes, mouse glioblastoma, mouse spleen/lymph nodes, mouse spleen, mouse epididymal adipose, mouse liver, pig liver\n",
      "Disease:  none, cancer, diffuse small lymphocytic lymphoma of the lymph node, tendinopathy, pearson syndrome, alzheimer's disease, non-small-cell lung cancer, acute myeloid leukemia, atherosclerosis, acute lymphoblastic leukemia, glioblastoma, COVID-19, B cell acute lymphoblastic leukemia, HIV, obese, epilepsy, multisystem inflammatory syndrome; COVID-19, multiple sclerosis, peruvian tuberculosis disease, cutaneous T cell lymphoma, melanoma, SHIV infection, salivary gland squamous cell carcinoma, aortic aneurysm, breast cancer, nonalcoholic fatty liver disease\n",
      "Technology:  SNARE-seq, Paired-seq, Novaseq, DOGMA-seq, SHARE-seq, NEAT-seq, sci-CAR-seq, HiSeq, ASAP-seq, CITE-seq, ECCITE-seq, Perturb-CITE-seq, REAP-seq, TEA-seq\n",
      "Technology Type:  ATAC_RNA, ATAC_PROTEIN, RNA_PROTEIN, ATAC_RNA_PROTEIN\n"
     ]
    }
   ],
   "source": [
    "mmdb.list_mmdb_info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Species:  Homo sapiens, Mus musculus, Macaca mulatta, Sus scrofa\n"
     ]
    }
   ],
   "source": [
    "mmdb.list_species() # list all species in the database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Disease:  none, cancer, diffuse small lymphocytic lymphoma of the lymph node, tendinopathy, pearson syndrome, alzheimer's disease, non-small-cell lung cancer, acute myeloid leukemia, atherosclerosis, acute lymphoblastic leukemia, glioblastoma, COVID-19, B cell acute lymphoblastic leukemia, HIV, obese, epilepsy, multisystem inflammatory syndrome; COVID-19, multiple sclerosis, peruvian tuberculosis disease, cutaneous T cell lymphoma, melanoma, SHIV infection, salivary gland squamous cell carcinoma, aortic aneurysm, breast cancer, nonalcoholic fatty liver disease\n"
     ]
    }
   ],
   "source": [
    "mmdb.list_disease() # list all diseases in the database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tissue:  human cell line , human cell line, human blood, human bone marrow, human kidney, human primary motor cortex, human intra-abdominal lymph node tumor, human brain, human achilles tendon, mouse retina, mouse colon, mouse brain cortex, mouse cell line, mouse forebrain, mouse kidney, mouse primary motor cortex, mouse brain, human brain cortex, human jejunum, mouse thymic epithelium, human lung, bone marrow, human liver, human glioblastoma, human blood/skin, human tumor, macaca vaginal, mouse submandibular gland, mouse aorta, mouse tumor, mouse bone marrow, mouse mesenteric lymph nodes, mouse glioblastoma, mouse spleen/lymph nodes, mouse spleen, mouse epididymal adipose, mouse liver, pig liver\n"
     ]
    }
   ],
   "source": [
    "mmdb.list_tissue() # list all tissues in the database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Technology:  SNARE-seq, Paired-seq, Novaseq, DOGMA-seq, SHARE-seq, NEAT-seq, sci-CAR-seq, HiSeq, ASAP-seq, CITE-seq, ECCITE-seq, Perturb-CITE-seq, REAP-seq, TEA-seq\n"
     ]
    }
   ],
   "source": [
    "mmdb.list_technology() # list all technologies in the database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Technology Type:  ATAC_RNA, ATAC_PROTEIN, RNA_PROTEIN, ATAC_RNA_PROTEIN\n"
     ]
    }
   ],
   "source": [
    "mmdb.list_technology_type() # list all technology types in the database"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### 3. Load the dataset in the scMMDB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "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>ID</th>\n",
       "      <th>Species</th>\n",
       "      <th>Tissue</th>\n",
       "      <th>Disease</th>\n",
       "      <th>Technology_type</th>\n",
       "      <th>Technology</th>\n",
       "      <th>Cell_num</th>\n",
       "      <th>Title</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>82</th>\n",
       "      <td>Dataset_C_004</td>\n",
       "      <td>Homo sapiens</td>\n",
       "      <td>human blood</td>\n",
       "      <td>atherosclerosis</td>\n",
       "      <td>RNA_PROTEIN</td>\n",
       "      <td>CITE-seq</td>\n",
       "      <td>5232</td>\n",
       "      <td>Single-cell immune landscape of human atherosc...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>83</th>\n",
       "      <td>Dataset_C_005</td>\n",
       "      <td>Homo sapiens</td>\n",
       "      <td>human blood</td>\n",
       "      <td>acute lymphoblastic leukemia</td>\n",
       "      <td>RNA_PROTEIN</td>\n",
       "      <td>CITE-seq</td>\n",
       "      <td>16450</td>\n",
       "      <td>Single-cell antigen-specific landscape of CAR ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84</th>\n",
       "      <td>Dataset_C_006</td>\n",
       "      <td>Homo sapiens</td>\n",
       "      <td>human blood</td>\n",
       "      <td>acute lymphoblastic leukemia</td>\n",
       "      <td>RNA_PROTEIN</td>\n",
       "      <td>CITE-seq</td>\n",
       "      <td>23287</td>\n",
       "      <td>Single-cell antigen-specific landscape of CAR ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87</th>\n",
       "      <td>Dataset_C_009</td>\n",
       "      <td>Homo sapiens</td>\n",
       "      <td>human blood</td>\n",
       "      <td>acute lymphoblastic leukemia</td>\n",
       "      <td>RNA_PROTEIN</td>\n",
       "      <td>CITE-seq</td>\n",
       "      <td>30484</td>\n",
       "      <td>Single-cell antigen-specific landscape of CAR ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>88</th>\n",
       "      <td>Dataset_C_010</td>\n",
       "      <td>Homo sapiens</td>\n",
       "      <td>human blood</td>\n",
       "      <td>acute lymphoblastic leukemia</td>\n",
       "      <td>RNA_PROTEIN</td>\n",
       "      <td>CITE-seq</td>\n",
       "      <td>31105</td>\n",
       "      <td>Single-cell antigen-specific landscape of CAR ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               ID       Species       Tissue                       Disease  \\\n",
       "82  Dataset_C_004  Homo sapiens  human blood               atherosclerosis   \n",
       "83  Dataset_C_005  Homo sapiens  human blood  acute lymphoblastic leukemia   \n",
       "84  Dataset_C_006  Homo sapiens  human blood  acute lymphoblastic leukemia   \n",
       "87  Dataset_C_009  Homo sapiens  human blood  acute lymphoblastic leukemia   \n",
       "88  Dataset_C_010  Homo sapiens  human blood  acute lymphoblastic leukemia   \n",
       "\n",
       "   Technology_type Technology  Cell_num  \\\n",
       "82     RNA_PROTEIN   CITE-seq      5232   \n",
       "83     RNA_PROTEIN   CITE-seq     16450   \n",
       "84     RNA_PROTEIN   CITE-seq     23287   \n",
       "87     RNA_PROTEIN   CITE-seq     30484   \n",
       "88     RNA_PROTEIN   CITE-seq     31105   \n",
       "\n",
       "                                                Title  \n",
       "82  Single-cell immune landscape of human atherosc...  \n",
       "83  Single-cell antigen-specific landscape of CAR ...  \n",
       "84  Single-cell antigen-specific landscape of CAR ...  \n",
       "87  Single-cell antigen-specific landscape of CAR ...  \n",
       "88  Single-cell antigen-specific landscape of CAR ...  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mmdb.list_dataset(species='Homo sapiens', tissue='human blood', disease=None, technology_type='RNA_PROTEIN').head(5) # list datasets information under the corresponding conditions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Load dataset: [Dataset_C_004]\n"
     ]
    }
   ],
   "source": [
    "Dataset_A_000 = mmdb.load_dataset('Dataset_C_004') # load the dataset based on the Dataset ID."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'RNA': AnnData object with n_obs × n_vars = 5232 × 100\n",
       "     obs: 'orig.ident', 'nCount_RNA', 'nFeature_RNA', 'nCount_ADT', 'nFeature_ADT', 'sample', 'tissue', 'celltype', 'ident', 'RNA.weight', 'ADT.weight', 'wsnn_res.1', 'seurat_clusters'\n",
       "     var: 'features'\n",
       "     uns: 'neighbors'\n",
       "     obsm: 'X_pca_rna', 'X_umap_adt', 'X_umap_rna', 'X_wnnUMAP'\n",
       "     varm: 'PCA_RNA'\n",
       "     obsp: 'distances',\n",
       " 'PROTEIN': AnnData object with n_obs × n_vars = 5232 × 21\n",
       "     obs: 'orig.ident', 'nCount_RNA', 'nFeature_RNA', 'nCount_ADT', 'nFeature_ADT', 'sample', 'tissue', 'celltype', 'ident', 'RNA.weight', 'ADT.weight', 'wsnn_res.1', 'seurat_clusters'\n",
       "     var: 'features'\n",
       "     obsm: 'X_pca_adt', 'X_umap_adt', 'X_umap_rna', 'X_wnnUMAP'\n",
       "     varm: 'PCA_ADT'}"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Dataset_A_000 # check the dataset information"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AnnData object with n_obs × n_vars = 5232 × 100\n",
       "    obs: 'orig.ident', 'nCount_RNA', 'nFeature_RNA', 'nCount_ADT', 'nFeature_ADT', 'sample', 'tissue', 'celltype', 'ident', 'RNA.weight', 'ADT.weight', 'wsnn_res.1', 'seurat_clusters'\n",
       "    var: 'features'\n",
       "    uns: 'neighbors'\n",
       "    obsm: 'X_pca_rna', 'X_umap_adt', 'X_umap_rna', 'X_wnnUMAP'\n",
       "    varm: 'PCA_RNA'\n",
       "    obsp: 'distances'"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Dataset_A_000['RNA']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AnnData object with n_obs × n_vars = 5232 × 21\n",
       "    obs: 'orig.ident', 'nCount_RNA', 'nFeature_RNA', 'nCount_ADT', 'nFeature_ADT', 'sample', 'tissue', 'celltype', 'ident', 'RNA.weight', 'ADT.weight', 'wsnn_res.1', 'seurat_clusters'\n",
       "    var: 'features'\n",
       "    obsm: 'X_pca_adt', 'X_umap_adt', 'X_umap_rna', 'X_wnnUMAP'\n",
       "    varm: 'PCA_ADT'"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Dataset_A_000['PROTEIN']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.9.19"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}