sdf_generation_sampl7.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "from rdkit import Chem\n",
    "from rdkit.Chem import AllChem\n",
    "import pandas as pd\n",
    "from tqdm import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "799it [00:09, 85.79it/s] \n"
     ]
    }
   ],
   "source": [
    "df = pd.read_csv(\"./SAMPL7/protein_ligand/fragments_screened.csv\", header=None)\n",
    "fragments = df[1].values\n",
    "mols = []\n",
    "for i,frag in tqdm(enumerate(fragments), total=len(fragments)):\n",
    "    m = Chem.MolFromSmiles(frag)              # Read SMILES\n",
    "    m.SetProp(\"_Name\",\"frag_{}\".format(i))    # Give the molecule a name\n",
    "    m = Chem.AddHs(m)                         # Add hydrogens\n",
    "    AllChem.EmbedMolecule(m)                  # Generate 3D coordinates\n",
    "    mols.append(m)\n",
    "w = Chem.SDWriter('fragments.sdf')\n",
    "for frag in mols: \n",
    "    w.write(frag)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}