skbio - fastq reading-with-vectorized

skbio - fastq reading-with-vectorized.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from itertools import islice\n",
    "from skbio import io, DNASequence, SequenceCollection\n",
    "\n",
    "fastq_path = './Undetermined_S0_L001_R2_001.fastq'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Pure skbio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10 loops, best of 3: 48.2 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for read in islice(io.read(fastq_path, format='fastq', verify=False, \n",
    "                   variant='illumina1.8', constructor=DNASequence), 0, 1000):\n",
    "    pass"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Simple reader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from itertools import chain, repeat\n",
    "\n",
    "def grouper(n, iterable, pad_value=None):\n",
    "    \"\"\" Group iterable into chunks of n.\n",
    "\n",
    "    grouper(3, 'abcdefg', 'x') --> ('a','b','c'), ('d','e','f'), ('g','x','x')\"\n",
    "\n",
    "    :param n:\n",
    "    :param iterable:\n",
    "    :param pad_value:\n",
    "    :return:\n",
    "    \"\"\"\n",
    "    return zip(*[chain(iterable, repeat(pad_value, n-1))]*n)\n",
    "\n",
    "def read_fastq(file_path):\n",
    "    with open(file_path, 'r') as file_:\n",
    "        for id_, seq, _, qual in grouper(4, file_):\n",
    "            yield FastqSequence(id=id_.strip(),\n",
    "                                sequence=seq.strip(),\n",
    "                                quality=qual.strip()) \n",
    "            \n",
    "class FastqSequence(object):\n",
    "    \n",
    "    def __init__(self, sequence, id, quality):\n",
    "        self.sequence = sequence\n",
    "        self.id = id\n",
    "        self.quality = quality"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100 loops, best of 3: 2.08 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for read in islice(read_fastq(fastq_path), 0, 1000):\n",
    "    pass"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "for simple, skb in zip(islice(read_fastq(fastq_path), 0, 1000), islice(io.read(fastq_path, format='fastq', verify=False, \n",
    "                   variant='illumina1.8', constructor=DNASequence), 0, 1000)):\n",
    "    print(simple.sequence == str(skb))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## With conversion"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from skbio.io._base import _decode_qual_to_phred\n",
    "\n",
    "def read_fastq_convert(file_path):\n",
    "    with open(file_path, 'r') as file_:\n",
    "        for id_, seq, _, qual in grouper(4, file_):\n",
    "            quality = _decode_qual_to_phred(qual.strip(), variant='illumina1.8')\n",
    "            yield FastqSequence(id=id_.strip(),\n",
    "                                sequence=seq.strip(),\n",
    "                                quality=quality) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "100 loops, best of 3: 15.7 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for read in islice(read_fastq_convert(fastq_path), 0, 1000):\n",
    "    pass"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## With DNASequence"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def read_fastq_convert_dna(file_path):\n",
    "    with open(file_path, 'r') as file_:\n",
    "        for id_, seq, _, qual in grouper(4, file_):\n",
    "            quality = _decode_qual_to_phred(qual.strip(), variant='illumina1.8')\n",
    "            yield DNASequence(id=id_.strip(),\n",
    "                              sequence=seq.strip(),\n",
    "                              quality=quality) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10 loops, best of 3: 26.5 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "for read in islice(read_fastq_convert_dna(fastq_path), 0, 1000):\n",
    "    pass"
   ]
  },
  {
   "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": "3.4.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}