CG_DP_Global.json

{
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from numpy import zeros\n",
      "\n",
      "def exampleCost(xc, yc):\n",
      "    \"\"\" Cost function assigning 0 to match, 2 to transition, 4 to\n",
      "        transversion, and 8 to gaps \"\"\"\n",
      "    if xc == yc: return 0 # match\n",
      "    if xc == '-' or yc == '-': return 8 # gap\n",
      "    minc, maxc = min(xc, yc), max(xc, yc)\n",
      "    if minc == 'A' and maxc == 'G': return 2 # transition\n",
      "    elif minc == 'C' and maxc == 'T': return 2 # transition\n",
      "    return 4 # transversion\n",
      "\n",
      "def globalAlignment(x, y, s):\n",
      "    \"\"\" Calculate global alignment value of sequences x and y using\n",
      "        dynamic programming.  Return global alignment value. \"\"\"\n",
      "    D = zeros((len(x)+1, len(y)+1), dtype=int)\n",
      "    for j in xrange(1, len(y)+1):\n",
      "        D[0, j] = j * s('-', y[j-1])\n",
      "    for i in xrange(1, len(x)+1):\n",
      "        D[i, 0] = i * s(x[i-1], '-')\n",
      "    for i in xrange(1, len(x)+1):\n",
      "        for j in xrange(1, len(y)+1):\n",
      "            D[i, j] = min(D[i-1, j-1] + s(x[i-1], y[j-1]), # diagonal\n",
      "                          D[i-1, j  ] + s(x[i-1], '-'),    # vertical\n",
      "                          D[i  , j-1] + s('-',    y[j-1])) # horizontal\n",
      "    return D[len(x), len(y)]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "globalAlignment('TACGTCAGC', 'TATGTCATGC', exampleCost)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 2,
       "text": [
        "10"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    }
   ],
   "metadata": {}
  }
 ]
}