diginorm_renamer.ipynb

{
 "worksheets": [
  {
   "cells": [
    {
     "metadata": {},
     "cell_type": "markdown",
     "source": "#Diginorm renamer\n##Because it expects files to have names like *1 and *2.  The input is an interleaved fastq file produced by velvet shuffle_seqs"
    },
    {
     "metadata": {},
     "input": "from IPython.parallel import Client",
     "cell_type": "code",
     "prompt_number": 1,
     "outputs": [],
     "language": "python",
     "collapsed": false
    },
    {
     "metadata": {},
     "input": "rc = Client()",
     "cell_type": "code",
     "prompt_number": 18,
     "outputs": [],
     "language": "python",
     "collapsed": false
    },
    {
     "metadata": {},
     "input": "dview = rc[:]\nlview = rc.load_balanced_view()\nprint len(dview)",
     "cell_type": "code",
     "prompt_number": 22,
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "40\n"
      }
     ],
     "language": "python",
     "collapsed": false
    },
    {
     "metadata": {},
     "input": "infile = \"/home/cfriedline/data7/assemblies/gypsy/shuffled_processed.fastq\"\noutfile = infile + \"_12.fastq\"",
     "cell_type": "code",
     "prompt_number": 2,
     "outputs": [],
     "language": "python",
     "collapsed": false
    },
    {
     "metadata": {},
     "input": "def run_diginorm_renamer(args):\n    from Bio.SeqIO.QualityIO import FastqGeneralIterator\n    infile, outfile = args\n    with open(outfile, \"w\") as o:\n        for i, (name, seq, qual) in enumerate(FastqGeneralIterator(open(infile))):\n            add = 1\n            if i % 2 != 0:\n                add = 2\n            o.write(\"@%s_%d\\n%s\\n+\\n%s\\n\" % (name.split()[0], add, seq, qual))\n            if i > 0 and i % 100000 == 0:\n                print \"at %d\" % i\ndview['run_diginorm_renamer'] = run_diginorm_renamer",
     "cell_type": "code",
     "prompt_number": 113,
     "outputs": [],
     "language": "python",
     "collapsed": false
    },
    {
     "metadata": {},
     "input": "res = lview.apply_async(run_diginorm_renamer, (infile, outfile))",
     "cell_type": "code",
     "prompt_number": 114,
     "outputs": [],
     "language": "python",
     "collapsed": false
    },
    {
     "metadata": {},
     "input": "res.r",
     "cell_type": "code",
     "prompt_number": 112,
     "outputs": [],
     "language": "python",
     "collapsed": false
    },
    {
     "metadata": {},
     "input": "",
     "cell_type": "code",
     "outputs": [],
     "language": "python",
     "collapsed": false
    }
   ],
   "metadata": {}
  }
 ],
 "metadata": {
  "name": "",
  "gist_id": "7204046"
 },
 "nbformat": 3
}