open_reading_frame.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# Open reading frames"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from Bio.Seq import Seq\n",
    "from Bio import SeqIO\n",
    "from Bio.Alphabet import generic_rna\n",
    "import re\n",
    "\n",
    "def get_seq(path):\n",
    "    'get single sequence from fasta file'\n",
    "    fasta = SeqIO.parse(open(path), \"fasta\")\n",
    "    for i in fasta: s = str(i.seq)\n",
    "    return s\n",
    "\n",
    "def get_orf(s):\n",
    "    \"\"\"\n",
    "    Given a DNA sequence, return\n",
    "    6 possible ORFS as a list\n",
    "    \"\"\"\n",
    "    revc = lambda s: str(Seq(s).reverse_complement())\n",
    "    out = []\n",
    "    out.extend((s, s[1:], s[2:]))\n",
    "    revc_s = revc(s)\n",
    "    out.extend((revc_s, revc_s[1:], revc_s[2:])) \n",
    "    assert len(out) == 6\n",
    "    return out\n",
    "                                        \n",
    "def translate(seq):\n",
    "    'nucleotides -> aa'\n",
    "    out = Seq(str(seq), generic_rna).translate(to_stop=True)\n",
    "    return str(out)\n",
    "\n",
    "def trim_m(s):\n",
    "    \"\"\"\n",
    "    trim aa sequence before start aa,\n",
    "    if no M is present, return None\n",
    "    \"\"\"\n",
    "    start_aa = 'M'\n",
    "    if start_aa not in s:\n",
    "        return None\n",
    "    else:\n",
    "        return s[s.index(s):]\n",
    "\n",
    "def split_short(s):\n",
    "    \"\"\" e.g:\n",
    "    in : 'MAAMBBMCC'\n",
    "    out: ['MAAMBBMCC, MBBMCC, MCC]\n",
    "    \"\"\"\n",
    "    o = ['M' + i for i in s.split('M')[1:]]\n",
    "    new = []\n",
    "    new.append(''.join(o))\n",
    "    for i in range(1, len(o)):\n",
    "        new.append(''.join(o[i:len(o)]))\n",
    "    return new"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['MGMTPRLGLESLLE', 'MTPRLGLESLLE', 'M', 'MLLGSFRLIPKETLIQVAGSSPCNLS']\n"
     ]
    }
   ],
   "source": [
    "path_test = 'rosalind_orf_test.txt'\n",
    "\n",
    "def open_reading_frame(path):\n",
    "    seq = get_seq(path)\n",
    "    orfs = get_orf(seq)\n",
    "    trans = [translate(i) for i in orfs]\n",
    "    trimd = [trim_m(j) for j in trans]\n",
    "    no_none = [x for x in trimd if x is not None]\n",
    "    out = [split_short(k) for k in no_none]\n",
    "    flatten_out = [v for s in out for v in s] #WTF python\n",
    "    return flatten_out\n",
    "\n",
    "\n",
    "print open_reading_frame(path_test)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

protein_mass.ipynb