Analyze_3UTR_entries.ipynb

{
 "metadata": {
  "name": "Analyze_3UTR_entries"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": "## This is Header ##\nThis is description"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "%%bash\nls *.csv",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "hg19_3UTR_raw.csv\nhg19_3UTR_refgene.csv\nhg19_3UTR_UCSC_filtered_201307.csv\nonly_r_NM_transcripts.csv\nucsc_gene_table.csv\nucsc_names.csv\n"
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "%%bash\nhead ucsc_gene_table.csv",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "\"REFSEQ\",\"SYMBOL\",\"ENTREZID\"\n\"NM_032291\",\"SGIP1\",\"84251\"\n\"NM_032785\",\"AGBL4\",\"84871\"\n\"NM_018090\",\"NECAP2\",\"55707\"\n\"NM_052998\",\"ADC\",\"113451\"\n\"NM_001145278\",\"NECAP2\",\"55707\"\n\"NM_001080397\",\"SLC45A1\",\"50651\"\n\"NM_013943\",\"CLIC4\",\"25932\"\n\"NM_001145277\",\"NECAP2\",\"55707\"\n\"NM_001195684\",\"TGFBR3\",\"7049\"\n"
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "from collections import namedtuple\nGene = namedtuple(\"Gene\", [\"refseq\", \"symbol\", \"id\"])",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "Gene._fields",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 11,
       "text": "('refseq', 'symbol', 'id')"
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "gene_list = []",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "import csv\nwith open('ucsc_gene_table.csv') as csv_f:\n    reader = csv.reader(csv_f)\n    next(reader)  # skip the csv header\n    for record in reader:\n        gene_list.append(Gene(*record))  # unpack the readed list in order",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 20
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "len(gene_list)",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 21,
       "text": "40046"
      }
     ],
     "prompt_number": 21
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "from collections import Counter",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 22
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "symbol_counter = Counter()\nfor gene in gene_list:\n    # we put the gene symbol only in to counter\n    # put the symbol in list to keep it from upacking\n    symbol_counter.update([gene.symbol])",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 26
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "symbol_counter.most_common(10)",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 28,
       "text": "[('NA', 1302),\n ('UTY', 77),\n ('MOG', 72),\n ('AGER', 70),\n ('NRM', 56),\n ('LST1', 48),\n ('BAG6', 42),\n ('C6orf25', 42),\n ('GPANK1', 35),\n ('LOC100507547', 32)]"
      }
     ],
     "prompt_number": 28
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "tx_counter = Counter()\nfor tx in gene_list:\n    # this time count by Refseq ID\n    tx_counter.update([tx.refseq])",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 29
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "tx_counter.most_common(10)",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 30,
       "text": "[('NM_001127389', 19),\n ('NM_001127388', 19),\n ('NM_001127386', 19),\n ('NM_001164467', 19),\n ('NM_033178', 19),\n ('NM_001278056', 13),\n ('NM_001177376', 12),\n ('NM_001128590', 10),\n ('NM_032454', 10),\n ('NM_032470', 10)]"
      }
     ],
     "prompt_number": 30
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# store the top frequent transcripts\nfreq_tx_list = [tup[0] for tup in tx_counter.most_common(10)]",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 32
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "freq_tx_list",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 33,
       "text": "['NM_001127389',\n 'NM_001127388',\n 'NM_001127386',\n 'NM_001164467',\n 'NM_033178',\n 'NM_001278056',\n 'NM_001177376',\n 'NM_001128590',\n 'NM_032454',\n 'NM_032470']"
      }
     ],
     "prompt_number": 33
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# obtain back the full gene entry by creating a set,\n# which drops the duplicated entries automatically\n{gene for gene in gene_list if gene.refseq in freq_tx_list}",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "pyout",
       "prompt_number": 34,
       "text": "set([Gene(refseq='NM_001127389', symbol='DUX4L5', id='653545'),\n     Gene(refseq='NM_001164467', symbol='DUX4L3', id='653548'),\n     Gene(refseq='NM_001177376', symbol='DUX4L4', id='441056'),\n     Gene(refseq='NM_032454', symbol='STK19', id='8859'),\n     Gene(refseq='NM_001278056', symbol='NA', id='NA'),\n     Gene(refseq='NM_032470', symbol='TNXB', id='7148'),\n     Gene(refseq='NM_001128590', symbol='CYP21A2', id='1589'),\n     Gene(refseq='NM_001127386', symbol='DUX4L2', id='728410'),\n     Gene(refseq='NM_001127388', symbol='DUX4L6', id='653544'),\n     Gene(refseq='NM_033178', symbol='DUX4', id='22947')])"
      }
     ],
     "prompt_number": 34
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "",
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}