{
 "metadata": {
  "name": "",
  "signature": "sha256:049506677190f5555e2a80ac3f0ff8517df644e573805bea4ddd6a9c0287fb22"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from Bio import SeqIO\n",
      "record = SeqIO.read(\"sequence.gb\", \"genbank\")\n",
      "info=[]\n",
      "info.append(record.features)\n",
      "f = open('ProteinTable416_166758.txt', 'r')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Guarda a posi\u00e7\u00e3o das features do tipo cds nas features (no featcds) e a localiza\u00e7\u00e3o na sequ\u00eancia do genbank (no loccds)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "featcds = [ ]\n",
      "loccds=[]\n",
      "\n",
      "for i in xrange(len(record.features)):\n",
      "    if record.features[i].type == \"CDS\":\n",
      "        featcds.append(i)\n",
      "for k in featcds:\n",
      "    loccds.append(record.features[k].location)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Guarda a posi\u00e7\u00e3o das features do tipo gene nas features (no featgene) e a localiza\u00e7\u00e3o na sequ\u00eancia do genbank (no locgene)"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "featgene = [ ]\n",
      "locgene=[]\n",
      "\n",
      "for i in xrange(len(record.features)):\n",
      "    if record.features[i].type == \"gene\":\n",
      "        featgene.append(i)\n",
      "for k in featcds:\n",
      "    locgene.append(record.features[k].location)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Ler cada linha da tabela de verifica\u00e7\u00e3o."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "cols=[]\n",
      "\n",
      "for line in f.readlines():\n",
      "    cols.append(line.split('\\t'))\n",
      "f.close()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Como as localiza\u00e7\u00f5es na tabela s\u00e3o referentes a toda a sequ\u00eancia \u00e9 necess\u00e1rio alter\u00e1-las de forma a corresponderem \u00e0 nossa parte da sequ\u00eancia, ou seja, em que o inicio da nossa sequ\u00eancia \u00e9 a posi\u00e7\u00e3o 0."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "localinicio=[]\n",
      "localfim=[]\n",
      "\n",
      "i=1\n",
      "\n",
      "\n",
      "while int(cols[i][2])<2670700:\n",
      "    if int(cols[i][2])>=2398541:\n",
      "        localinicio.append(int(cols[i][2])-2398541)\n",
      "        localfim.append(int(cols[i][3])-2398541+1)\n",
      "    i+=1"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "heading",
     "level": 5,
     "metadata": {},
     "source": [
      "Verificar se as posi\u00e7\u00f5es coincidem."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "gene=True\n",
      "cds=True\n",
      "\n",
      "while i<len(localinicio)-1:\n",
      "    for i in xrange(0,len(localinicio)):\n",
      "        if localinicio[i]!=locgene[i].nofuzzy_start or localfim[i]!=locgene[i].nofuzzy_end:\n",
      "            gene=False\n",
      "    for i in xrange(0,len(localinicio)):\n",
      "        if localinicio[i]!=locgene[i].nofuzzy_start or localfim[i]!=locgene[i].nofuzzy_end:\n",
      "            cds=False"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}