Get_Substructure_Matches.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:ba12cb34e7086f3b16d1b8b2a4f8c6767cfa0e6d322948802de4ec1f01ebe5f7"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from rdkit import rdBase\n",
      "print \"RDKit version: \", rdBase.rdkitVersion\n",
      "\n",
      "from rdkit import Chem\n",
      "from rdkit.Chem import AllChem\n",
      "from rdkit.Chem import Draw\n",
      "from rdkit.Chem.Draw import IPythonConsole"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "RDKit version:  2014.09.1\n"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "name = \"MIZOLASTINE\"\n",
      "i = 999\n",
      "mol=Chem.MolFromMol2File(\"data/%s.lig.%d.mol2\"%(name, i), sanitize = True, removeHs = False)\n",
      "Draw.MolToImage(mol)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "png": "iVBORw0KGgoAAAANSUhEUgAAASwAAAEsCAIAAAD2HxkiAAAMBElEQVR4nO3dW3ajuBqAUTirZ9Q9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\n",
       "prompt_number": 2,
       "text": [
        "<Image.Image image mode=RGB size=300x300 at 0x22CE7C8>"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "aromatic_6 = \"[c,n]1[c,n][c,n][c,n][c,n][c,n]1\"\n",
      "aromatic_5 = \"[c,n]1[c,n][c,n][c,n][c,n]1\"\n",
      "pattern6 = Chem.MolFromSmarts(aromatic_6)\n",
      "pattern5 = Chem.MolFromSmarts(aromatic_5)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print \"Pattern 6\"\n",
      "lars = mol.GetSubstructMatches(pattern6)\n",
      "print lars\n",
      "for lar in lars:\n",
      "    lar_mol = Chem.MolFragmentToSmiles(mol, \n",
      "                                       atomsToUse=lar,\n",
      "                                       isomericSmiles=True,\n",
      "                                       canonical=False)\n",
      "    print lar_mol\n",
      "#"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Pattern 6\n",
        "((0, 1, 3, 5, 7, 9), (32, 33, 35, 37, 39, 41), (46, 47, 49, 51, 53, 55))\n",
        "n1cccnc1\n",
        "c1ccccc1\n",
        "c1ccccc1\n"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print \"Pattern 5\"\n",
      "lars = mol.GetSubstructMatches(pattern5)\n",
      "print lar\n",
      "for lar in lars:\n",
      "    lar_mol = Chem.MolFragmentToSmiles(mol, \n",
      "                                       atomsToUse=lar,\n",
      "                                       isomericSmiles=True,\n",
      "                                       canonical=False)\n",
      "    print lar_mol\n",
      "#"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Pattern 5\n",
        "(46, 47, 49, 51, 53, 55)\n",
        "c1nccn1\n"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    }
   ],
   "metadata": {}
  }
 ]
}