sss example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "load rdk schema\n"
     ]
    }
   ],
   "source": [
    "import pickle\n",
    "from rdkit import Chem\n",
    "from rdkit.Chem import rdSubstructLibrary\n",
    "from pychembldb import *\n",
    "from rdkit.Chem import Draw\n",
    "from rdkit.Chem.Draw import IPythonConsole\n",
    "from razi.rdkit_postgresql.functions import mol_from_smarts, mol_from_smiles"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## To make ssslib please check follwoing nice post\n",
    "### https://rdkit.blogspot.com/2018/02/introducing-substructlibrary.html"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "library = pickle.load(open('chembl27_ssslib.pkl', 'rb'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# sub structure search with SMILES and rdkit-postgres cartridge."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 569 ms, sys: 16.8 ms, total: 586 ms\n",
      "Wall time: 3.39 s\n"
     ]
    }
   ],
   "source": [
    "q = chembldb.query(Mols.m)\n",
    "res = q.filter(Mols.m.hassubstruct(mol_from_smiles('c1ccccc1'))).limit(10000)\n",
    "%time a=res.all()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# subsearch molecule with SMILES and rdSubstructLibrary."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 847 ms, sys: 1.71 ms, total: 848 ms\n",
      "Wall time: 348 ms\n"
     ]
    }
   ],
   "source": [
    "%time a=library.GetMatches(Chem.MolFromSmiles('c1ccccc1'), maxResults=10000)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# substructure search with SMARTS and rdkit-postgres cartridge."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 615 ms, sys: 8.61 ms, total: 624 ms\n",
      "Wall time: 3.41 s\n"
     ]
    }
   ],
   "source": [
    "q = chembldb.query(Mols.m)\n",
    "res = q.filter(Mols.m.hassubstruct(mol_from_smarts('a1aaaaa1'))).limit(10000)\n",
    "%time a=res.all()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# subsearch molecule with SMARTS and rdSubstructLibrary."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 910 ms, sys: 0 ns, total: 910 ms\n",
      "Wall time: 342 ms\n"
     ]
    }
   ],
   "source": [
    "%time a=library.GetMatches(Chem.MolFromSmarts('a1aaaaa1'), maxResults=10000)"
   ]
  }
 ],
 "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}