{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import collections\n",
    "import requests\n",
    "import re\n",
    "import os\n",
    "import csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# url of a search through MeSH which has empty terms\n",
    "MeSH_url = 'http://www.nlm.nih.gov/cgi/mesh/2015/MB_cgi?mode=&term='"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Function (MeSH_match) to take a single disease MeSH name, search the 2014\n",
    "# MeSH database, and extract the unique MeSH ID associated with that disease.\n",
    "# Returns a two membered list including the disease name, followed by the unique MeSH ID\n",
    "def MeSH_match(disease):\n",
    "    disease_edit = disease.replace(' ', '+')\n",
    "    url = MeSH_url + disease_edit\n",
    "    returned = requests.get(url)\n",
    "    returned = returned.text\n",
    "    sub_returned = re.search('Unique ID</TH><TD colspan=1>(.+?)<', returned)\n",
    "    sub_returned = sub_returned.group(1)\n",
    "    returned_list = [disease, sub_returned]\n",
    "    return(returned_list)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/Users/leobrueggeman/GitHub/incomplete-interactome\n"
     ]
    }
   ],
   "source": [
    "# opens a file that contains a list of diseases, strips the newlines, and creates a list (your_list) \n",
    "# variable containing these diseases\n",
    "print(os.getcwd())\n",
    "f = open('disease_input.txt', 'r')\n",
    "your_list = [x.rstrip() for x in f]\n",
    "f.close()\n",
    "\n",
    "# runs the MeSH_match function on your list of diseases (your_list) and returns\n",
    "# the output to a new list (output1)\n",
    "output1 = list(map(MeSH_match, your_list))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# creates a csv file which contains MeSH disease names matched with their unique MeSH IDs\n",
    "with open('disease_output.tsv', 'w') as f:\n",
    "    writer = csv.writer(f, delimiter = '\\t')\n",
    "    writer.writerow(['name', 'mesh_id'])\n",
    "    writer.writerows(output1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.4.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}