DiseaseOntology.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import csv\n",
    "import re\n",
    "\n",
    "import networkx\n",
    "import pandas\n",
    "\n",
    "#import do_tools"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Download HumanDO.obo https://disease-ontology.org/downloads/\n",
    "https://github.com/DiseaseOntology/HumanDiseaseOntology/tree/main/src/ontology/HumanDO.obo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import networkx\n",
    "\n",
    "import IGS_scripts.oboparser as oboparser \n",
    "\n",
    "def load_do(path):\n",
    "    \"\"\"path is location of obo file\"\"\"\n",
    "    return oboparser.parse(path, ['is_a'])\n",
    "\n",
    "def do_to_networkx(do):\n",
    "    \"\"\"Return a networkx representation of do\"\"\"\n",
    "    terms = do.get_terms()\n",
    "    dox = networkx.MultiDiGraph()\n",
    "    dox.add_nodes_from(term for term in terms if not term.obsolete)\n",
    "    for term in dox:\n",
    "        for typedef, id_, name in term.relationships:\n",
    "            dox.add_edge(term, do.get_term(id_), key = typedef)\n",
    "\n",
    "    assert networkx.is_directed_acyclic_graph(dox)\n",
    "    return dox"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "download_dir = '../data/DiseaseOntology'\n",
    "path = os.path.join(download_dir, 'HumanDO.obo')\n",
    "do = load_do(path)\n",
    "dox = do_to_networkx(do)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>disease_id</th>\n",
       "      <th>name</th>\n",
       "      <th>description</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DOID:0001816</td>\n",
       "      <td>angiosarcoma</td>\n",
       "      <td>A vascular cancer that derives_from the cells ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>DOID:0002116</td>\n",
       "      <td>pterygium</td>\n",
       "      <td>A corneal disease that is characterized by a t...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     disease_id          name  \\\n",
       "0  DOID:0001816  angiosarcoma   \n",
       "1  DOID:0002116     pterygium   \n",
       "\n",
       "                                         description  \n",
       "0  A vascular cancer that derives_from the cells ...  \n",
       "1  A corneal disease that is characterized by a t...  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create a table of descriptions\n",
    "pattern = re.compile(r'^\"(.*?)\"')\n",
    "rows = list()\n",
    "for term in dox:\n",
    "    match = pattern.search(term.definition)\n",
    "    description = match.group(1) if match else ''\n",
    "    rows.append((term.id, term.name, description))\n",
    "description_df = pandas.DataFrame(rows, columns = ['disease_id', 'name', 'description']).sort_values('disease_id')\n",
    "#description_df.to_csv(os.path.join(download_dir, 'description.tsv'), sep='\\t', index=False)\n",
    "description_df.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(11537, 3)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "description_df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "xref_rename = {\n",
    "    'ICD10CM': 'ICD10',\n",
    "    'ICD9CM': 'ICD9',\n",
    "    'NCI2009_04D': 'NCI',\n",
    "    'SNOMEDCT_2010_1_31': 'SNOMEDCT',\n",
    "    'SNOMEDCT_2013_01_31': 'SNOMEDCT',\n",
    "    'SNOMEDCT_US_2020_03_01': 'SNOMEDCT',\n",
    "    'SNOMEDCT_US_2021_07_31': 'SNOMEDCT',\n",
    "    'SNOMEDCT_US_2021_09_01': 'SNOMEDCT',\n",
    "    'SNOMEDCT_US_2022_07_31': 'SNOMEDCT',\n",
    "    'SNOMEDCT_US_2023_03_01': 'SNOMEDCT',\n",
    "    'SNOMEDCT_US_2023_09_01': 'SNOMEDCT',\n",
    "    'SNOMEDCT_US_2023_10_01': 'SNOMEDCT',\n",
    "    'SNOMEDCT_US_2023_11_01': 'SNOMEDCT',\n",
    "    'UMLS_CUI': 'UMLS',\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def write_xref_row(writer, doid_code, doid_name, xrefs, rename_dict):\n",
    "    rows = list()\n",
    "    for xref in xrefs:\n",
    "        resource, resource_id = xref.split(':', 1)\n",
    "        if resource in rename_dict:\n",
    "            resource = rename_dict[resource]\n",
    "        rows.append([doid_code, doid_name, resource, resource_id])\n",
    "    rows.sort()\n",
    "    writer.writerows(rows)\n",
    "\n",
    "file_unprop = open(os.path.join(download_dir, 'xrefs.tsv'), 'w')\n",
    "file_prop = open(os.path.join(download_dir, 'xrefs-prop.tsv'), 'w')\n",
    "\n",
    "writer_unprop = csv.writer(file_unprop, delimiter='\\t')\n",
    "writer_prop = csv.writer(file_prop, delimiter='\\t')\n",
    "\n",
    "for writer in writer_unprop, writer_prop:\n",
    "    writer.writerow(['doid_code', 'doid_name', 'resource', 'resource_id'])\n",
    "\n",
    "for term in list(reversed(list(networkx.topological_sort(dox)))):\n",
    "    xrefs = set(term.xrefs)\n",
    "    xrefs_prop = set(xrefs)\n",
    "    for ancestor in networkx.ancestors(dox, term):\n",
    "        xrefs_prop |= set(ancestor.xrefs)\n",
    "    \n",
    "    write_xref_row(writer_unprop, term.id, term.name, xrefs, xref_rename)\n",
    "    write_xref_row(writer_prop, term.id, term.name, xrefs_prop, xref_rename)\n",
    "\n",
    "for write_file in file_unprop, file_prop:\n",
    "    write_file.close()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'EFO',\n",
       " 'GARD',\n",
       " 'ICD10',\n",
       " 'ICD11',\n",
       " 'ICD9',\n",
       " 'ICDO',\n",
       " 'KEGG',\n",
       " 'MEDDRA',\n",
       " 'MESH',\n",
       " 'NCI',\n",
       " 'OMIM',\n",
       " 'ORDO',\n",
       " 'SNOMEDCT',\n",
       " 'UMLS'}"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# list of xrefs\n",
    "import pandas\n",
    "path = os.path.join(download_dir, 'xrefs.tsv')\n",
    "xref_df = pandas.read_table(path)\n",
    "set(xref_df.resource)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# create a name to term mapping\n",
    "rows = list()\n",
    "for term in dox:\n",
    "    rows.append({'doid': term.id, 'name': term.name, 'type': 'name'})\n",
    "    for synonym in term.synonyms:\n",
    "        rows.append({'doid': term.id, 'name': synonym[0], 'type': '{}-synonym'.format(synonym[1].lower())})\n",
    "path = os.path.join(download_dir, 'term-names.tsv')\n",
    "with open(path, 'w') as write_file:\n",
    "    writer = csv.DictWriter(write_file, delimiter='\\t', fieldnames=['doid', 'name', 'type'])\n",
    "    writer.writeheader()\n",
    "    writer.writerows(rows)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "## Create useful datasets for DO Slim -- a non-redundant set of diseases"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>doid</th>\n",
       "      <th>name</th>\n",
       "      <th>source</th>\n",
       "      <th>pathophysiology</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DOID:2531</td>\n",
       "      <td>hematologic cancer</td>\n",
       "      <td>DOcancerslim</td>\n",
       "      <td>neoplastic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>DOID:1319</td>\n",
       "      <td>brain cancer</td>\n",
       "      <td>DOcancerslim</td>\n",
       "      <td>neoplastic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>DOID:1324</td>\n",
       "      <td>lung cancer</td>\n",
       "      <td>DOcancerslim</td>\n",
       "      <td>neoplastic</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        doid                name        source pathophysiology\n",
       "0  DOID:2531  hematologic cancer  DOcancerslim      neoplastic\n",
       "1  DOID:1319        brain cancer  DOcancerslim      neoplastic\n",
       "2  DOID:1324         lung cancer  DOcancerslim      neoplastic"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# read the slim disease ontology terms\n",
    "path = os.path.join(download_dir, 'slim-terms.tsv')\n",
    "slim_df = pandas.read_table(path)\n",
    "slim_df[:3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>doid</th>\n",
       "      <th>name</th>\n",
       "      <th>source</th>\n",
       "      <th>pathophysiology</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>55</th>\n",
       "      <td>DOID:9917</td>\n",
       "      <td>pleural cancer</td>\n",
       "      <td>DOcancerslim</td>\n",
       "      <td>neoplastic</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         doid            name        source pathophysiology\n",
       "55  DOID:9917  pleural cancer  DOcancerslim      neoplastic"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check for terms that in slim but not in the DO\n",
    "all_doids = set(do.get_term_ids())\n",
    "slim_doids = set(slim_df.doid)\n",
    "unmatched = slim_doids - all_doids\n",
    "slim_doids &= all_doids\n",
    "slim_df.loc[slim_df.doid.isin(unmatched)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# check for node redundancy\n",
    "slim_terms = set(map(do.get_term, slim_doids))\n",
    "for term in slim_terms:\n",
    "    nodes_to_root = networkx.descendants(dox, term)\n",
    "    conflicts = {x.name for x in nodes_to_root & slim_terms}\n",
    "    if conflicts:\n",
    "        print(term.name, conflicts)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = os.path.join(download_dir, 'xrefs.tsv')\n",
    "map_unprop_df = pandas.read_table(path)\n",
    "\n",
    "path = os.path.join(download_dir, 'xrefs-prop.tsv')\n",
    "map_prop_df = pandas.read_table(path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>doid_code</th>\n",
       "      <th>doid_name</th>\n",
       "      <th>resource</th>\n",
       "      <th>resource_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DOID:2531</td>\n",
       "      <td>hematologic cancer</td>\n",
       "      <td>EFO</td>\n",
       "      <td>0000095</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>DOID:2531</td>\n",
       "      <td>hematologic cancer</td>\n",
       "      <td>EFO</td>\n",
       "      <td>0000096</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>DOID:2531</td>\n",
       "      <td>hematologic cancer</td>\n",
       "      <td>EFO</td>\n",
       "      <td>0000183</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   doid_code           doid_name resource resource_id\n",
       "0  DOID:2531  hematologic cancer      EFO     0000095\n",
       "1  DOID:2531  hematologic cancer      EFO     0000096\n",
       "2  DOID:2531  hematologic cancer      EFO     0000183"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "slim_df = slim_df.rename(columns={'doid': 'doid_code'})\n",
    "slim_map_unprop_df = slim_df[['doid_code']].merge(map_unprop_df)\n",
    "slim_map_prop_df = slim_df[['doid_code']].merge(map_prop_df)\n",
    "slim_map_prop_df[:3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = os.path.join(download_dir, 'xrefs-slim.tsv')\n",
    "slim_map_unprop_df.to_csv(path, sep='\\t', index=False)\n",
    "\n",
    "path = os.path.join(download_dir, 'xrefs-prop-slim.tsv')\n",
    "slim_map_prop_df.to_csv(path, sep='\\t', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "rows = list()\n",
    "for term in slim_terms:\n",
    "    subsumed = networkx.ancestors(dox, term)\n",
    "    row_part = [term.id, term.name]\n",
    "    rows.append(row_part + row_part + [0])\n",
    "    for subterm in subsumed:\n",
    "        distance = networkx.shortest_path_length(dox, subterm, term)\n",
    "        rows.append(row_part + [subterm.id, subterm.name, distance])\n",
    "rows.sort()\n",
    "\n",
    "slim_prop_df = pandas.DataFrame(rows, columns=['slim_id', 'slim_name', 'subsumed_id', 'subsumed_name', 'min_distance'])\n",
    "path = os.path.join(download_dir, 'slim-terms-prop.tsv')\n",
    "slim_prop_df.to_csv(path, sep='\\t', index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Compare with Hetionet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>doid_code</th>\n",
       "      <th>doid_name</th>\n",
       "      <th>mesh_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DOID:2531</td>\n",
       "      <td>hematologic cancer</td>\n",
       "      <td>D019337</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>DOID:1319</td>\n",
       "      <td>brain cancer</td>\n",
       "      <td>D001932</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>DOID:263</td>\n",
       "      <td>kidney cancer</td>\n",
       "      <td>D007680</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>62</th>\n",
       "      <td>DOID:1793</td>\n",
       "      <td>pancreatic cancer</td>\n",
       "      <td>D010190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>77</th>\n",
       "      <td>DOID:4159</td>\n",
       "      <td>skin cancer</td>\n",
       "      <td>D012878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1207</th>\n",
       "      <td>DOID:1312</td>\n",
       "      <td>focal segmental glomerulosclerosis</td>\n",
       "      <td>D005923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1217</th>\n",
       "      <td>DOID:216</td>\n",
       "      <td>dental caries</td>\n",
       "      <td>D003731</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1225</th>\n",
       "      <td>DOID:2355</td>\n",
       "      <td>anemia</td>\n",
       "      <td>D000740</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1231</th>\n",
       "      <td>DOID:594</td>\n",
       "      <td>panic disorder</td>\n",
       "      <td>D016584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1240</th>\n",
       "      <td>DOID:635</td>\n",
       "      <td>acquired immunodeficiency syndrome</td>\n",
       "      <td>D000163</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>127 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      doid_code                           doid_name  mesh_id\n",
       "0     DOID:2531                  hematologic cancer  D019337\n",
       "7     DOID:1319                        brain cancer  D001932\n",
       "44     DOID:263                       kidney cancer  D007680\n",
       "62    DOID:1793                   pancreatic cancer  D010190\n",
       "77    DOID:4159                         skin cancer  D012878\n",
       "...         ...                                 ...      ...\n",
       "1207  DOID:1312  focal segmental glomerulosclerosis  D005923\n",
       "1217   DOID:216                       dental caries  D003731\n",
       "1225  DOID:2355                              anemia  D000740\n",
       "1231   DOID:594                      panic disorder  D016584\n",
       "1240   DOID:635  acquired immunodeficiency syndrome  D000163\n",
       "\n",
       "[127 rows x 3 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas \n",
    "import os\n",
    "\n",
    "download_dir = '../data/DiseaseOntology'\n",
    "path = os.path.join(download_dir, 'xrefs-slim.tsv')\n",
    "disease_df = pandas.read_table(path) #1244 rows\n",
    "disease_df = disease_df.query('resource == \"MESH\"').drop(columns=['resource'])\n",
    "disease_df = disease_df.rename(columns={'resource_id': 'mesh_id'})\n",
    "disease_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "121"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "disease_df['doid_code'].nunique()"
   ]
  },
  {
   "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>doid_code</th>\n",
       "      <th>doid_name</th>\n",
       "      <th>mesh_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>236</th>\n",
       "      <td>DOID:1192</td>\n",
       "      <td>peripheral nervous system neoplasm</td>\n",
       "      <td>D010524</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>237</th>\n",
       "      <td>DOID:1192</td>\n",
       "      <td>peripheral nervous system neoplasm</td>\n",
       "      <td>D018317</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>333</th>\n",
       "      <td>DOID:4045</td>\n",
       "      <td>muscle cancer</td>\n",
       "      <td>D009217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>334</th>\n",
       "      <td>DOID:4045</td>\n",
       "      <td>muscle cancer</td>\n",
       "      <td>D019042</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>509</th>\n",
       "      <td>DOID:5612</td>\n",
       "      <td>spinal cancer</td>\n",
       "      <td>D013120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>510</th>\n",
       "      <td>DOID:5612</td>\n",
       "      <td>spinal cancer</td>\n",
       "      <td>D013125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>596</th>\n",
       "      <td>DOID:3393</td>\n",
       "      <td>coronary artery disease</td>\n",
       "      <td>D003324</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>597</th>\n",
       "      <td>DOID:3393</td>\n",
       "      <td>coronary artery disease</td>\n",
       "      <td>D003327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>598</th>\n",
       "      <td>DOID:3393</td>\n",
       "      <td>coronary artery disease</td>\n",
       "      <td>D017202</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1047</th>\n",
       "      <td>DOID:13189</td>\n",
       "      <td>gout</td>\n",
       "      <td>D006073</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1048</th>\n",
       "      <td>DOID:13189</td>\n",
       "      <td>gout</td>\n",
       "      <td>D015210</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       doid_code                           doid_name  mesh_id\n",
       "236    DOID:1192  peripheral nervous system neoplasm  D010524\n",
       "237    DOID:1192  peripheral nervous system neoplasm  D018317\n",
       "333    DOID:4045                       muscle cancer  D009217\n",
       "334    DOID:4045                       muscle cancer  D019042\n",
       "509    DOID:5612                       spinal cancer  D013120\n",
       "510    DOID:5612                       spinal cancer  D013125\n",
       "596    DOID:3393             coronary artery disease  D003324\n",
       "597    DOID:3393             coronary artery disease  D003327\n",
       "598    DOID:3393             coronary artery disease  D017202\n",
       "1047  DOID:13189                                gout  D006073\n",
       "1048  DOID:13189                                gout  D015210"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "disease_df[disease_df.duplicated('doid_code', keep=False) == True]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>doid_code</th>\n",
       "      <th>doid_name</th>\n",
       "      <th>mesh_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DOID:2531</td>\n",
       "      <td>hematologic cancer</td>\n",
       "      <td>D019337</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>DOID:1319</td>\n",
       "      <td>brain cancer</td>\n",
       "      <td>D001932</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>DOID:1324</td>\n",
       "      <td>lung cancer</td>\n",
       "      <td>D008175</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>44</th>\n",
       "      <td>DOID:263</td>\n",
       "      <td>kidney cancer</td>\n",
       "      <td>D007680</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>57</th>\n",
       "      <td>DOID:1793</td>\n",
       "      <td>pancreatic cancer</td>\n",
       "      <td>D010190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1761</th>\n",
       "      <td>DOID:1312</td>\n",
       "      <td>focal segmental glomerulosclerosis</td>\n",
       "      <td>D005923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1776</th>\n",
       "      <td>DOID:216</td>\n",
       "      <td>dental caries</td>\n",
       "      <td>D003731</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1787</th>\n",
       "      <td>DOID:2355</td>\n",
       "      <td>anemia</td>\n",
       "      <td>D000740</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1797</th>\n",
       "      <td>DOID:594</td>\n",
       "      <td>panic disorder</td>\n",
       "      <td>D016584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1808</th>\n",
       "      <td>DOID:635</td>\n",
       "      <td>acquired immunodeficiency syndrome</td>\n",
       "      <td>D000163</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>143 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      doid_code                           doid_name  mesh_id\n",
       "0     DOID:2531                  hematologic cancer  D019337\n",
       "7     DOID:1319                        brain cancer  D001932\n",
       "27    DOID:1324                         lung cancer  D008175\n",
       "44     DOID:263                       kidney cancer  D007680\n",
       "57    DOID:1793                   pancreatic cancer  D010190\n",
       "...         ...                                 ...      ...\n",
       "1761  DOID:1312  focal segmental glomerulosclerosis  D005923\n",
       "1776   DOID:216                       dental caries  D003731\n",
       "1787  DOID:2355                              anemia  D000740\n",
       "1797   DOID:594                      panic disorder  D016584\n",
       "1808   DOID:635  acquired immunodeficiency syndrome  D000163\n",
       "\n",
       "[143 rows x 3 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas\n",
    "url = 'https://raw.githubusercontent.com/dhimmel/disease-ontology/72614ade9f1cc5a5317b8f6836e1e464b31d5587/data/xrefs-slim.tsv'\n",
    "disease_df_hetionet = pandas.read_table(url)\n",
    "disease_df_hetionet = disease_df_hetionet.query('resource == \"MSH\"').drop(columns=['resource'])\n",
    "disease_df_hetionet = disease_df_hetionet.rename(columns={'resource_id': 'mesh_id'})\n",
    "disease_df_hetionet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "133"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "disease_df_hetionet['doid_code'].nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>doid_code</th>\n",
       "      <th>doid_name</th>\n",
       "      <th>mesh_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>198</th>\n",
       "      <td>DOID:10283</td>\n",
       "      <td>prostate cancer</td>\n",
       "      <td>C537243</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>199</th>\n",
       "      <td>DOID:10283</td>\n",
       "      <td>prostate cancer</td>\n",
       "      <td>D011471</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>607</th>\n",
       "      <td>DOID:8778</td>\n",
       "      <td>Crohn's disease</td>\n",
       "      <td>C536215</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>608</th>\n",
       "      <td>DOID:8778</td>\n",
       "      <td>Crohn's disease</td>\n",
       "      <td>D003424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>705</th>\n",
       "      <td>DOID:3393</td>\n",
       "      <td>coronary artery disease</td>\n",
       "      <td>D003324</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>706</th>\n",
       "      <td>DOID:3393</td>\n",
       "      <td>coronary artery disease</td>\n",
       "      <td>D003327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>707</th>\n",
       "      <td>DOID:3393</td>\n",
       "      <td>coronary artery disease</td>\n",
       "      <td>D017202</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>966</th>\n",
       "      <td>DOID:10652</td>\n",
       "      <td>Alzheimer's disease</td>\n",
       "      <td>C536597</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>967</th>\n",
       "      <td>DOID:10652</td>\n",
       "      <td>Alzheimer's disease</td>\n",
       "      <td>D000544</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1152</th>\n",
       "      <td>DOID:5408</td>\n",
       "      <td>Paget's disease of bone</td>\n",
       "      <td>C538098</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1153</th>\n",
       "      <td>DOID:5408</td>\n",
       "      <td>Paget's disease of bone</td>\n",
       "      <td>D010001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1254</th>\n",
       "      <td>DOID:986</td>\n",
       "      <td>alopecia areata</td>\n",
       "      <td>C531609</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1255</th>\n",
       "      <td>DOID:986</td>\n",
       "      <td>alopecia areata</td>\n",
       "      <td>D000506</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1288</th>\n",
       "      <td>DOID:2986</td>\n",
       "      <td>IgA glomerulonephritis</td>\n",
       "      <td>C538412</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1289</th>\n",
       "      <td>DOID:2986</td>\n",
       "      <td>IgA glomerulonephritis</td>\n",
       "      <td>D005922</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1489</th>\n",
       "      <td>DOID:12930</td>\n",
       "      <td>dilated cardiomyopathy</td>\n",
       "      <td>C536231</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1490</th>\n",
       "      <td>DOID:12930</td>\n",
       "      <td>dilated cardiomyopathy</td>\n",
       "      <td>C536277</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1491</th>\n",
       "      <td>DOID:12930</td>\n",
       "      <td>dilated cardiomyopathy</td>\n",
       "      <td>D002311</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       doid_code                doid_name  mesh_id\n",
       "198   DOID:10283          prostate cancer  C537243\n",
       "199   DOID:10283          prostate cancer  D011471\n",
       "607    DOID:8778          Crohn's disease  C536215\n",
       "608    DOID:8778          Crohn's disease  D003424\n",
       "705    DOID:3393  coronary artery disease  D003324\n",
       "706    DOID:3393  coronary artery disease  D003327\n",
       "707    DOID:3393  coronary artery disease  D017202\n",
       "966   DOID:10652      Alzheimer's disease  C536597\n",
       "967   DOID:10652      Alzheimer's disease  D000544\n",
       "1152   DOID:5408  Paget's disease of bone  C538098\n",
       "1153   DOID:5408  Paget's disease of bone  D010001\n",
       "1254    DOID:986          alopecia areata  C531609\n",
       "1255    DOID:986          alopecia areata  D000506\n",
       "1288   DOID:2986   IgA glomerulonephritis  C538412\n",
       "1289   DOID:2986   IgA glomerulonephritis  D005922\n",
       "1489  DOID:12930   dilated cardiomyopathy  C536231\n",
       "1490  DOID:12930   dilated cardiomyopathy  C536277\n",
       "1491  DOID:12930   dilated cardiomyopathy  D002311"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "disease_df_hetionet[disease_df_hetionet.duplicated('doid_code', keep=False) == True]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['both', 'left_only']\n",
       "Categories (3, object): ['left_only', 'right_only', 'both']"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "check = disease_df_hetionet.merge(disease_df, on='doid_code', how='outer', indicator=True)\n",
    "check['_merge'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "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>doid_code</th>\n",
       "      <th>doid_name_x</th>\n",
       "      <th>mesh_id_x</th>\n",
       "      <th>doid_name_y</th>\n",
       "      <th>mesh_id_y</th>\n",
       "      <th>_merge</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>DOID:1324</td>\n",
       "      <td>lung cancer</td>\n",
       "      <td>D008175</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>DOID:8850</td>\n",
       "      <td>salivary gland cancer</td>\n",
       "      <td>D012468</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>DOID:10153</td>\n",
       "      <td>ileum cancer</td>\n",
       "      <td>D007078</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>DOID:1115</td>\n",
       "      <td>sarcoma</td>\n",
       "      <td>D012509</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>DOID:11920</td>\n",
       "      <td>tracheal cancer</td>\n",
       "      <td>D014134</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43</th>\n",
       "      <td>DOID:1725</td>\n",
       "      <td>peritoneum cancer</td>\n",
       "      <td>D010534</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>110</th>\n",
       "      <td>DOID:0050741</td>\n",
       "      <td>alcohol dependence</td>\n",
       "      <td>D000437</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>118</th>\n",
       "      <td>DOID:8398</td>\n",
       "      <td>osteoarthritis</td>\n",
       "      <td>D010003</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133</th>\n",
       "      <td>DOID:90</td>\n",
       "      <td>degenerative disc disease</td>\n",
       "      <td>D055959</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>140</th>\n",
       "      <td>DOID:4481</td>\n",
       "      <td>allergic rhinitis</td>\n",
       "      <td>D065631</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>142</th>\n",
       "      <td>DOID:585</td>\n",
       "      <td>nephrolithiasis</td>\n",
       "      <td>D053040</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>DOID:12185</td>\n",
       "      <td>otosclerosis</td>\n",
       "      <td>D010040</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        doid_code                doid_name_x mesh_id_x doid_name_y mesh_id_y  \\\n",
       "2       DOID:1324                lung cancer   D008175         NaN       NaN   \n",
       "14      DOID:8850      salivary gland cancer   D012468         NaN       NaN   \n",
       "35     DOID:10153               ileum cancer   D007078         NaN       NaN   \n",
       "36      DOID:1115                    sarcoma   D012509         NaN       NaN   \n",
       "40     DOID:11920            tracheal cancer   D014134         NaN       NaN   \n",
       "43      DOID:1725          peritoneum cancer   D010534         NaN       NaN   \n",
       "110  DOID:0050741         alcohol dependence   D000437         NaN       NaN   \n",
       "118     DOID:8398             osteoarthritis   D010003         NaN       NaN   \n",
       "133       DOID:90  degenerative disc disease   D055959         NaN       NaN   \n",
       "140     DOID:4481          allergic rhinitis   D065631         NaN       NaN   \n",
       "142      DOID:585            nephrolithiasis   D053040         NaN       NaN   \n",
       "146    DOID:12185               otosclerosis   D010040         NaN       NaN   \n",
       "\n",
       "        _merge  \n",
       "2    left_only  \n",
       "14   left_only  \n",
       "35   left_only  \n",
       "36   left_only  \n",
       "40   left_only  \n",
       "43   left_only  \n",
       "110  left_only  \n",
       "118  left_only  \n",
       "133  left_only  \n",
       "140  left_only  \n",
       "142  left_only  \n",
       "146  left_only  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "check[(check['_merge']=='left_only')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'DOID:1324'}"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "slim_doids&{'DOID:1324'}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "https://disease-ontology.org/do"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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>doid_code</th>\n",
       "      <th>doid_name</th>\n",
       "      <th>resource</th>\n",
       "      <th>resource_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [doid_code, doid_name, resource, resource_id]\n",
       "Index: []"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "slim_map_unprop_df[(slim_map_unprop_df['doid_code']=='DOID:1324')&(slim_map_unprop_df['resource']=='MESH')]#['resource'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "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>doid_code</th>\n",
       "      <th>doid_name</th>\n",
       "      <th>resource</th>\n",
       "      <th>resource_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [doid_code, doid_name, resource, resource_id]\n",
       "Index: []"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "map_unprop_df[(map_unprop_df['doid_code']=='DOID:1324')&(map_unprop_df['resource']=='MESH')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "rows = list()\n",
    "for term in list(reversed(list(networkx.topological_sort(dox)))):\n",
    "    xrefs = set(term.xrefs)\n",
    "    for xref in xrefs:\n",
    "        resource, resource_id = xref.split(':', 1)\n",
    "        if resource in xref_rename:\n",
    "            resource = xref_rename[resource]\n",
    "        rows.append([term.id, term.name, resource, resource_id])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "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>doid_code</th>\n",
       "      <th>doid_name</th>\n",
       "      <th>mesh_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>DOID:1324</td>\n",
       "      <td>lung cancer</td>\n",
       "      <td>D008175</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    doid_code    doid_name  mesh_id\n",
       "27  DOID:1324  lung cancer  D008175"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "disease_df_hetionet[disease_df_hetionet['doid_code']=='DOID:1324']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}