Count molecular fragments using RDKit in Python

count_fragments.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Count Fragments\n",
    "\n",
    "Count fragments raised in MACCS key list."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from rdkit import Chem\n",
    "from rdkit.Chem.Draw import IPythonConsole\n",
    "from rdkit.Chem import MACCSkeys\n",
    "\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "FIXME:\n",
    "This code ignore the following types of fragments in MACCS key\n",
    "\n",
    ">    1, ISOTOPE\n",
    ">\n",
    ">    125, Aromatic Ring > 1\n",
    ">\n",
    ">    166, fragments\n",
    ">\n",
    "> c.f. https://github.com/rdkit/rdkit/blob/master/rdkit/Chem/MACCSkeys.py"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,\n",
       "        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,\n",
       "        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,\n",
       "        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,\n",
       "        1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  4.,  0.,  0.,  6.,\n",
       "        0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  4.,  0.,  3.,  0.,\n",
       "        2.,  3.,  0.,  0.,  0.,  0.,  2.,  6.,  0.,  0.,  0.,  0.,  0.,\n",
       "        1.,  1.,  0.,  0.,  0.,  0.,  3.,  0.,  5.,  0.,  0.,  0.,  0.,\n",
       "        0.,  1.,  0.,  0.,  0.,  1.,  2.,  0.,  0.,  0.,  2.,  1.,  1.,\n",
       "        2.,  0.,  5.,  5.,  2.,  0.,  0.,  0.,  0.,  0.,  2.,  7.,  0.,\n",
       "        2.,  0.,  6.,  0.,  6.,  1.,  5.,  5.,  0.,  1.,  2.,  7.,  0.,\n",
       "        1.,  5.,  1.,  2.,  2.,  2.,  1.,  2.,  0.,  5.,  1.,  1.,  5.,\n",
       "        0., 10.,  1.,  2.,  7., 24.,  5.,  1., 30.,  0.])"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "smi = \"CN1CCN(CC2=CC=C(C=C2)C(=O)NC2=CC(NC3=NC=CC(=N3)C3=CN=CC=C3)=C(C)C=C2)CC1\"\n",
    "mol = Chem.MolFromSmiles(smi)\n",
    "\n",
    "\n",
    "fingerprint_maccs167 = {str(k-1):v[0] for k,v in MACCSkeys.smartsPatts.items()}\n",
    "\n",
    "list_fragment_counts = np.zeros(len(fingerprint_maccs167))\n",
    "for idx_str, smarts in fingerprint_maccs167.items():\n",
    "    if smarts is not '?':\n",
    "\n",
    "        substruct = Chem.MolFromSmarts(smarts)\n",
    "        list_fragment_counts[int(idx_str)] = len(mol.GetSubstructMatches(substruct))\n",
    "\n",
    "list_fragment_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<rdkit.Chem.rdchem.Mol at 0x2322841f530>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mol"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}