MLL Status.ipynb

MLL Status.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "import requests\nimport bs4\nimport csv",
      "execution_count": 2,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "url = 'http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE11877'\nres = requests.get(url)\nres.raise_for_status()",
      "execution_count": 3,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "soup = bs4.BeautifulSoup(res.text, \"html.parser\")\nelement = soup.find(text='Samples (207)')",
      "execution_count": 6,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "rows = element.parent.findNextSibling().findAll('td')",
      "execution_count": 7,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "with open('mll_status.tsv', 'w') as f:\n    csv_writer = csv.writer(f, delimiter='\\t')\n    i = 0\n    for row in rows:\n        try:\n            url = 'http://www.ncbi.nlm.nih.gov' + row.find('a').attrs['href']\n        except AttributeError:\n            continue\n        i += 1\n        res = requests.get(url)\n        res.raise_for_status()\n        rowSoup = bs4.BeautifulSoup(res.text, \"html.parser\")\n        characteristics = [x.next for x in rowSoup.find(text='Characteristics').parent.findNextSibling().findAll('br')]\n        patient_id = rowSoup.find(text='Title').parent.findNextSibling().text\n        mll_status = None\n        for characteristic in characteristics:\n            trait, status = characteristic.split(' : ', 1)\n            if trait == 'MLL':\n                mll_status = status\n                break\n        if mll_status is None:\n            raise ValueError('MLL status not found in  {0}!'.format(row.text))\n        else:\n            csv_writer.writerow((patient_id, mll_status))\n    print('{0} samples processed'.format(i))",
      "execution_count": 15,
      "outputs": [
        {
          "text": "207 samples processed\n",
          "output_type": "stream",
          "name": "stdout"
        }
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "mimetype": "text/x-python",
      "nbconvert_exporter": "python",
      "codemirror_mode": {
        "version": 3,
        "name": "ipython"
      },
      "file_extension": ".py",
      "name": "python",
      "pygments_lexer": "ipython3",
      "version": "3.5.1"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "MLL Status.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}