Pharm2D2pointFingerprint.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c6b37c0d",
   "metadata": {},
   "outputs": [],
   "source": [
    "from rdkit import Chem\n",
    "from rdkit.Chem.Fingerprints import FingerprintMols\n",
    "import pandas as pd\n",
    "from molvs import standardize_smiles\n",
    "from rdkit.Chem import AllChem, ChemicalFeatures\n",
    "from rdkit.Chem.Pharm2D import Generate\n",
    "from rdkit.Chem.Pharm2D.SigFactory import SigFactory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5265ae0f",
   "metadata": {},
   "outputs": [],
   "source": [
    "fdefstr = \"\"\"\n",
    "AtomType NDonor [N&!H0&v3,N&!H0&+1&v4,n&H1&+0]\n",
    "AtomType ChalcDonor [O,S;H1;+0]\n",
    "DefineFeature SingleAtomDonor [{NDonor},{ChalcDonor},!$([D1]-[C;D3]=[O,S,N])]\n",
    "  Family Donor\n",
    "  Weights 1\n",
    "EndFeature\n",
    "\n",
    "AtomType NAcceptor [$([N&v3;H1,H2]-[!$(*=[O,N,P,S])])]\n",
    "Atomtype NAcceptor [$([N;v3;H0])]\n",
    "AtomType NAcceptor [$([n;+0])]\n",
    "AtomType ChalcAcceptor [$([O,S;H1;v2]-[!$(*=[O,N,P,S])])]\n",
    "AtomType ChalcAcceptor [O,S;H0;v2]\n",
    "Atomtype ChalcAcceptor [O,S;-]\n",
    "Atomtype ChalcAcceptor [o,s;+0]\n",
    "AtomType HalogenAcceptor [F]\n",
    "DefineFeature SingleAtomAcceptor [{NAcceptor},{ChalcAcceptor},{HalogenAcceptor}]\n",
    "  Family Acceptor\n",
    "  Weights 1\n",
    "EndFeature\n",
    "\n",
    "# this one is delightfully easy:\n",
    "DefineFeature AcidicGroup [C,S](=[O,S,P])-[O;H1,H0&-1]\n",
    "  Family NegIonizable\n",
    "  Weights 1.0,1.0,1.0\n",
    "EndFeature\n",
    "\n",
    "AtomType CarbonOrArom_NonCarbonyl [$([C,a]);!$([C,a](=O))]\n",
    "AtomType BasicNH2 [$([N;H2&+0][{CarbonOrArom_NonCarbonyl}])]\n",
    "AtomType BasicNH1 [$([N;H1&+0]([{CarbonOrArom_NonCarbonyl}])[{CarbonOrArom_NonCarbonyl}])]\n",
    "AtomType BasicNH0 [$([N;H0&+0]([{CarbonOrArom_NonCarbonyl}])([{CarbonOrArom_NonCarbonyl}])[{CarbonOrArom_NonCarbonyl}])]\n",
    "AtomType BasicNakedN [N,n;X2;+0]\n",
    "DefineFeature BasicGroup [{BasicNH2},{BasicNH1},{BasicNH0},{BasicNakedN}]\n",
    "  Family PosIonizable\n",
    "  Weights 1.0\n",
    "EndFeature\n",
    "\n",
    "# aromatic rings of various sizes:\n",
    "DefineFeature Arom5 a1aaaa1\n",
    "  Family Aromatic\n",
    "  Weights 1.0,1.0,1.0,1.0,1.0\n",
    "EndFeature\n",
    "DefineFeature Arom6 a1aaaaa1\n",
    "  Family Aromatic\n",
    "  Weights 1.0,1.0,1.0,1.0,1.0,1.0\n",
    "EndFeature\n",
    "DefineFeature Arom7 a1aaaaaa1\n",
    "  Family Aromatic\n",
    "  Weights 1.0,1.0,1.0,1.0,1.0,1.0,1.0\n",
    "EndFeature\n",
    "DefineFeature Arom8 a1aaaaaaa1\n",
    "  Family Aromatic\n",
    "  Weights 1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0\n",
    "EndFeature\n",
    "\"\"\"\n",
    "featFactory = ChemicalFeatures.BuildFeatureFactoryFromString(fdefstr)\n",
    "\n",
    "\n",
    "def CalculatePharm2D2pointFingerprint(mol, featFactory=featFactory):\n",
    "    sigFactory_2point = SigFactory(featFactory, minPointCount=2, maxPointCount=2)\n",
    "    sigFactory_2point.SetBins(\n",
    "        [(0, 1), (1, 2), (2, 3), (3, 4), (4, 5), (5, 6), (6, 7), (7, 8), (8, 9)]\n",
    "    )\n",
    "    sigFactory_2point.Init()\n",
    "    res = Generate.Gen2DFingerprint(mol, sigFactory_2point)\n",
    "\n",
    "    res_keys = tuple(res.GetOnBits())\n",
    "    init_list = [0] * 135\n",
    "    for res_key in res_keys:\n",
    "        init_list[res_key] = 1\n",
    "\n",
    "    BitVect = tuple(init_list)\n",
    "\n",
    "    return BitVect, res_keys, res\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b7933c49",
   "metadata": {},
   "outputs": [],
   "source": [
    "filename = './data/temp.csv'\n",
    "df = pd.read_csv(filename)               \n",
    "smiles = [standardize_smiles(i) for i in df['smiles'].values] \n",
    "all_ecfp2_data = []\n",
    "df = pd.DataFrame()\n",
    "for smile in smiles:\n",
    "    mol = Chem.MolFromSmiles(smile)\n",
    "    result=CalculatePharm2D2pointFingerprint(mol)\n",
    "    df = pd.concat([df, pd.DataFrame([result])], ignore_index=True)\n",
    "\n",
    "df.insert(loc = 0,\n",
    "          column = \"smiles\",\n",
    "          value = smiles)\n",
    "   \n",
    "df.to_csv('./output/output_Pharm2D2pointFingerprint.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f8ad128d",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}