Merging_htseq_counts.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import subprocess, os, sys, signal, pip, collections, optparse, sys, tempfile, re, optparse\n",
    "import rpy2\n",
    "from joblib import Parallel, delayed\n",
    "import multiprocessing\n",
    "import threading\n",
    "import time\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# inputFolder : Folder name with all the fastq files\n",
    "intputFolder = '/mnt/fls01-bcf01/ngsdata/Analysis/2016/nextseq/161025_NB500968_0056_AHGCMVAFXX_analysis/Raphael_Thuret/fastqs'\n",
    "\n",
    "# Setting the output folder where all the results would be stored\n",
    "outputFolder = '/mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def expanderuser(path):\n",
    "    \"\"\"Replaces the ~ with the users home directory\"\"\"\n",
    "    if path.startswith(\"~\"):\n",
    "        return os.path.expanduser(\"~\") + path[1: ]\n",
    "    return path\n",
    "\n",
    "def multiple_match(regex, old_name, name):\n",
    "    report_error(regex+\" matched both \" + old_name + \" and \" + name + \"strickter regex required\")\n",
    "\n",
    "def do_walk(source, regex, target_path, onerror=None, followlinks=False, verbose=True, divider=None, sort=None):\n",
    "    \"\"\"\n",
    "    Walker method\n",
    "    Inputs are:\n",
    "    source Parent directory to be walked through\n",
    "    onerror is a function on underlying os.listdir fails\n",
    "    followlinks would allow following symbolic links\n",
    "        WARNING Be aware that setting followlinks to True can lead to infinite\n",
    "           recursion if a link points to a parent directory of itself.\n",
    "           walk() does not keep track of the directories it visited already.\n",
    "    verbose: Flag passed to action methods to provide more output\n",
    "    \"\"\"\n",
    "    source = expanderuser(source)\n",
    "    (names_number, names_path) = tempfile.mkstemp()\n",
    "    re_object = re.compile(regex)\n",
    "    file_paths = []\n",
    "    with open(names_path, 'w') as f:\n",
    "        # Must be topdown=True otherwise walk will process subdirectories before checking them\n",
    "        for root, dirs, files in os.walk(source, topdown=True, onerror=onerror, followlinks=followlinks):\n",
    "            for name in files:\n",
    "                if re_object.search(name):\n",
    "                    file_path = os.path.join(root, name)\n",
    "                    f.write(file_path)\n",
    "                    f.write(\"\\n\")\n",
    "                    file_paths.append(file_path)\n",
    "                    if verbose:\n",
    "                        print(\"Merging\",file_path)\n",
    "                #else:\n",
    "                #    print \"NO\",name, root\n",
    "    if len(file_paths) == 0:\n",
    "        report_error(\"NO files found to match \"+ regex)\n",
    "    if divider:\n",
    "        if sort:\n",
    "            merge_files(file_paths, names_path, target_path, verbose=verbose, divider = divider, sort = sort)\n",
    "        else:\n",
    "            merge_files(file_paths, names_path, target_path, verbose=verbose, divider = divider)\n",
    "    else:\n",
    "        if sort:\n",
    "            merge_files(file_paths, names_path, target_path, verbose, sort=sort)\n",
    "        else:\n",
    "            merge_files(file_paths, names_path, target_path, verbose)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "\n",
    "def report_error(error):\n",
    "    \"\"\"Prints the error, and exits -1\"\"\"\n",
    "    print(error) \n",
    "    sys.stderr.write(error)\n",
    "    sys.stderr.write(\"\\n\")\n",
    "    sys.stderr.flush()\n",
    "    sys.exit(1)\n",
    "\n",
    "\n",
    "def remove_common(names):\n",
    "    start = names[0]\n",
    "    end = names[0]\n",
    "    for name in names:\n",
    "        while len(start) > 0 and not(name.startswith(start)):\n",
    "            start = start[: -1]\n",
    "        while len(end) > 0 and not(name.endswith(end)):\n",
    "            end = end[1:]\n",
    "    new_names = []\n",
    "    for name in names:\n",
    "        new_name = name[len(start): -len(end)]\n",
    "        new_names.append(\"C\"+new_name)\n",
    "    return new_names\n",
    "\n",
    "\n",
    "def remove_symbols(s):\n",
    "    if s.find(\"__\") == -1:\n",
    "        return s\n",
    "    # Patterns used by Galaxy\n",
    "    s = s.replace(\"__cb__\", ']')\n",
    "    s = s.replace(\"__cc__\", '}')\n",
    "    s = s.replace(\"__dq__\", '\"')\n",
    "    s = s.replace(\"__lt__\", '<')\n",
    "    s = s.replace(\"__gt__\", '>')\n",
    "    s = s.replace(\"__ob__\", '[')\n",
    "    s = s.replace(\"__oc__\", '{')\n",
    "    s = s.replace(\"__sq__\", \"'\")\n",
    "    # Patterns added by Christian\n",
    "    s = s.replace(\"__in__\", '%in%')\n",
    "    s = s.replace(\"__not__\", '!')\n",
    "    end = -2\n",
    "    # tab = 9\n",
    "    # | = 124\n",
    "    while True:\n",
    "        start = s.find(\"__\", end + 2) + 2\n",
    "        if start == 1:\n",
    "            return s\n",
    "        end = s.find(\"__\", start)\n",
    "        if end == -1:\n",
    "            return s\n",
    "        part = s[start: end]\n",
    "        try:\n",
    "            ascii = int(part)\n",
    "            s = s.replace(\"__\" + part + \"__\", chr(ascii))\n",
    "            end = -2\n",
    "        except ValueError:\n",
    "            pass\n",
    "    return s\n",
    "\n",
    "\n",
    "def clean_part(part):\n",
    "    part = part.strip()\n",
    "    part = part.replace(\"\\t\", \"__9__\")\n",
    "    return part\n",
    "\n",
    "\n",
    "def return_blank():\n",
    "    return \"0\"\n",
    "\n",
    "\n",
    "def black_dict():\n",
    "    return collections.defaultdict(return_blank)\n",
    "\n",
    "\n",
    "def merge_files(file_paths, names_path, target_path, verbose=False, divider=\"\\t\", sort = None):\n",
    "    if sort:\n",
    "        if sort == \"column_names\":\n",
    "            column_sort = True\n",
    "            row_sort = False\n",
    "        elif sort == \"row_names\":\n",
    "            column_sort = False\n",
    "            row_sort = true\n",
    "        elif sort == \"both\":\n",
    "            column_sort = True\n",
    "            row_sort = True\n",
    "        elif sort == \"none\":\n",
    "            column_sort = False\n",
    "            row_sort = False\n",
    "        else:\n",
    "            report_error(\"Unexpected value: \" + sort + \" for sort parameter. Legeal values are: column_names, row_names, both or none\")\n",
    "    else:\n",
    "        column_sort = False\n",
    "        row_sort = False\n",
    "\n",
    "    names = []\n",
    "    with open(names_path, 'r') as f:\n",
    "        for line in f:\n",
    "            line = line.strip()\n",
    "            if len(line) > 0:\n",
    "                names.append(line)\n",
    "    if len(names) != len(file_paths):\n",
    "        report_error(\"Found \" + str(len(file_paths)) + \" file_paths but \" + names_path + \" contains \" + str(len(names)) + \" lines.\")\n",
    "    new_names = remove_common(names)\n",
    "    clean_divider = remove_symbols(divider)\n",
    "    all_values = collections.defaultdict(black_dict)\n",
    "    for count, file_path in enumerate(file_paths):\n",
    "        mis_match = 0\n",
    "        with open(file_path, 'r') as f:\n",
    "            for line in f:\n",
    "                parts = line.strip().split(clean_divider)\n",
    "                if len(parts) == 2:\n",
    "                    key = clean_part(parts[0])\n",
    "                    value = clean_part(parts[1])\n",
    "                    all_values[key][new_names[count]] = value\n",
    "                else:\n",
    "                    mis_match+= 1\n",
    "                    if verbose:\n",
    "                        if mis_match < 5:\n",
    "                            print(\"ignoring following line from\", file_path)\n",
    "                            print(line)\n",
    "        if mis_match > 0:\n",
    "            print(\"In file \" + file_path + \" \" + str(mis_match) + \" lines did not have 1 divider (\" + clean_divider + \") \" + divider)\n",
    "\n",
    "    if column_sort:\n",
    "        new_names = sorted(new_names)\n",
    "    if row_sort:\n",
    "        row_names = sorted(all_values.keys())\n",
    "    else:\n",
    "        row_names = all_values.keys()\n",
    "\n",
    "    with open(target_path, 'w') as f:\n",
    "        for name in new_names:\n",
    "            f.write(\"\\t\")\n",
    "            f.write(name)\n",
    "        f.write(\"\\n\")\n",
    "        for key in row_names:\n",
    "            f.write(key)\n",
    "            for name in new_names:\n",
    "                f.write(\"\\t\")\n",
    "                f.write(all_values[key][name])\n",
    "            f.write(\"\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C12_S50_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C05_S57_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C18_S51_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C84_S78_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C31_S6_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C77_S85_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C68_S36_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C22_S68_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C15_S3_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C13_S19_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C25_S5_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C09_S2_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C61_S27_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C36_S70_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C83_S86_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C71_S84_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C49_S25_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C48_S72_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C60_S90_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C10_S66_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C37_S7_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C28_S53_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C11_S58_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C39_S23_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C95_S88_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C32_S14_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C04_S65_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C30_S69_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C34_S54_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C76_S93_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C23_S60_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C73_S45_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C67_S28_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C96_S80_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C43_S8_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C81_S30_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C03_S1_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C33_S22_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C20_S12_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C19_S20_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C14_S11_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C21_S4_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C82_S94_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C42_S71_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C90_S79_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C35_S62_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C51_S41_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C72_S92_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C40_S55_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C93_S32_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C75_S29_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C45_S24_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C58_S74_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C70_S76_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C27_S21_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C47_S64_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C65_S83_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C41_S63_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C26_S13_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C50_S33_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C08_S10_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C57_S42_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C56_S34_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C16_S67_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C07_S18_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C85_S47_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C87_S31_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C79_S46_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C01_S17_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C91_S48_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C53_S81_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C78_S77_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C63_S43_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C24_S52_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C94_S96_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C55_S26_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C29_S61_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C80_S38_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C59_S82_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C92_S40_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C44_S16_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C74_S37_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C02_S9_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C54_S89_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C38_S15_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C46_S56_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C89_S87_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C17_S59_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C52_S73_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C62_S35_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C88_S95_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C66_S91_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C69_S44_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C64_S75_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C06_S49_R1_001.txt\n",
      "Merging /mnt/mr01-home01/mqbsxsm2/scratch/Shane_Herbert/output/htseq_output/C86_S39_R1_001.txt\n"
     ]
    }
   ],
   "source": [
    "HTSEQFolder = outputFolder + 'htseq_output/'\n",
    "HTSEqFile = outputFolder + 'AllHtseqCounts_Shane_Herbert.tsv'\n",
    "do_walk(HTSEQFolder, '_R1_001.txt', HTSEqFile, onerror=None, followlinks=False, verbose=True, divider=None, sort=\"both\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}