Timing Global Sequence Alignment

The Limits of Global Pairwise Sequence Analysis

{
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "heading",
     "level": 3,
     "metadata": {},
     "source": [
      "The Limits of Global Pairwise Sequence Analysis"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import random\n",
      "from Bio import pairwise2\n",
      "\n",
      "#Define a few funtions to make random DNA sequences and will do pairwise global of them\n",
      "def make_sequence(size):\n",
      "    seqlist = (random.choice( ['A','C','T','G'])for i in range(size))\n",
      "    return ''.join(seqlist)\n",
      "\n",
      "def pairwise(size):\n",
      "    seq1 = make_sequence(size) \n",
      "    seq2 = make_sequence(size)\n",
      "    score = pairwise2.align.globalxx(seq1,seq2,one_alignment_only=1, score_only=1)\n",
      "    #print score"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%timeit  pairwise(10)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "10000 loops, best of 3: 125 \u00b5s per loop\n"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%timeit  pairwise(100)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "100 loops, best of 3: 3.07 ms per loop\n"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%timeit  pairwise(1000)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "1 loops, best of 3: 543 ms per loop\n"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "raw",
     "metadata": {},
     "source": [
      "This next one churns indefinitely and eats all my memory."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%timeit  pairwise(10000)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": "*"
    }
   ],
   "metadata": {}
  }
 ]
}