LargestNumberOfContiguousRotatableBonds

LargestNumberOfContiguousRotatableBonds.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from rdkit import Chem\n",
    "from rdkit.Chem.Lipinski import RotatableBondSmarts\n",
    "from rdkit.Chem.Draw import IPythonConsole"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "mol = Chem.MolFromSmiles('NCC1CCC1C(=O)O')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<rdkit.Chem.rdchem.Mol at 0x1f165012a80>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mol"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def find_bond_groups(mol):\n",
    "    \"\"\"Find groups of contiguous rotatable bonds and return them sorted by decreasing size\"\"\"\n",
    "    rot_atom_pairs = mol.GetSubstructMatches(RotatableBondSmarts)\n",
    "    rot_bond_set = set([mol.GetBondBetweenAtoms(*ap).GetIdx() for ap in rot_atom_pairs])\n",
    "    rot_bond_groups = []\n",
    "    while (rot_bond_set):\n",
    "        i = rot_bond_set.pop()\n",
    "        connected_bond_set = set([i])\n",
    "        stack = [i]\n",
    "        while (stack):\n",
    "            i = stack.pop()\n",
    "            b = mol.GetBondWithIdx(i)\n",
    "            bonds = []\n",
    "            for a in (b.GetBeginAtom(), b.GetEndAtom()):\n",
    "                bonds.extend([b.GetIdx() for b in a.GetBonds() if (\n",
    "                    (b.GetIdx() in rot_bond_set) and (not (b.GetIdx() in connected_bond_set)))])\n",
    "            connected_bond_set.update(bonds)\n",
    "            stack.extend(bonds)\n",
    "        rot_bond_set.difference_update(connected_bond_set)\n",
    "        rot_bond_groups.append(tuple(connected_bond_set))\n",
    "    return tuple(sorted(rot_bond_groups, reverse = True, key = lambda x: len(x)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Find groups of contiguous rotatable bonds in mol"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "bond_groups = find_bond_groups(mol)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As bond groups are sorted by decreasing size, the size of the first group (if any) is the largest number of contiguous rotatable bonds in mol"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "largest_n_cont_rot_bonds = len(bond_groups[0]) if bond_groups else 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "largest_n_cont_rot_bonds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((1,), (5,))"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bond_groups"
   ]
  }
 ],
 "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

This is a great idea - probably will use this or a similar concept in Open Babel for a project. 👍