Export disease descriptions to a TSV

dhimmel · Sep 9, 2016 · 052ffcc · 052ffcc
1 parent 75050ea
commit 052ffcc
Show file tree

Hide file tree

Showing 2 changed files with 6,640 additions and 24 deletions.
diff --git a/DO-xrefs.ipynb b/DO-xrefs.ipynb
@@ -10,21 +10,14 @@
    "source": [
     "import os\n",
     "import csv\n",
+    "import re\n",
     "\n",
     "import networkx\n",
+    "import pandas\n",
     "\n",
     "import do_tools"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -47,16 +40,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {
     "collapsed": false
    },
@@ -69,12 +53,68 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\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>1509</th>\n",
+       "      <td>DOID:0001816</td>\n",
+       "      <td>angiosarcoma</td>\n",
+       "      <td>A malignant vascular tumor that results_in rap...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3043</th>\n",
+       "      <td>DOID:0002116</td>\n",
+       "      <td>pterygium</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        disease_id          name  \\\n",
+       "1509  DOID:0001816  angiosarcoma   \n",
+       "3043  DOID:0002116     pterygium   \n",
+       "\n",
+       "                                            description  \n",
+       "1509  A malignant vascular tumor that results_in rap...  \n",
+       "3043                                                     "
+      ]
+     },
+     "execution_count": 3,
+     "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('data/description.tsv', sep='\\t', index=False)\n",
+    "description_df.head(2)"
+   ]
   },
   {
    "cell_type": "code",
@@ -210,8 +250,9 @@
   }
  ],
  "metadata": {
+  "anaconda-cloud": {},
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python [default]",
    "language": "python",
    "name": "python3"
   },
@@ -225,7 +266,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.4.0"
+   "version": "3.5.2"
   }
  },
  "nbformat": 4,