example_notebook.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "G1ZRPwsBo-nL"
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "from rdkit import Chem\n",
    "\n",
    "\n",
    "import sklearn\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn import linear_model\n",
    "from sklearn.metrics import mean_squared_error, r2_score\n",
    "from sklearn import neighbors, svm\n",
    "from sklearn.model_selection import train_test_split, cross_val_score\n",
    "from sklearn.preprocessing import StandardScaler, MinMaxScaler\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import f1_score\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.svm import SVC, SVR\n",
    "from sklearn.ensemble import BaggingClassifier, RandomForestClassifier, GradientBoostingClassifier\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "\n",
    "import matplotlib\n",
    "#matplotlib.use('GTKAgg')\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib import cm\n",
    "from matplotlib.colors import ListedColormap\n",
    "%matplotlib inline\n",
    "matplotlib.rcParams.update({'font.size': 18})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "id": "XY5cMRwdo_IN"
   },
   "outputs": [],
   "source": [
    "data_AUC = pd.read_csv('adme/data/AUC_final.csv')\n",
    "data_CL_max = pd.read_csv('adme/data/CL_max_final.csv')\n",
    "data_Cmax = pd.read_csv('adme/data/Cmax_final.csv')\n",
    "data_F = pd.read_csv('adme/data/F_final.csv')\n",
    "data_IC_50 = pd.read_csv('adme/data/IC_50_final.csv')\n",
    "data_LD_50 = pd.read_csv('adme/data/LD_50_final.csv')\n",
    "data_PPB = pd.read_csv('adme/data/PPB_final.csv')\n",
    "data_T_half = pd.read_csv('adme/data/T_1_2_final.csv')\n",
    "data_Vdss = pd.read_csv('adme/data/Vdss_final.csv')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "id": "u-qPjT_Go_K6"
   },
   "outputs": [],
   "source": [
    "df = data_T_half"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 419
    },
    "id": "n0GbLLf-o_Nz",
    "outputId": "54f530e6-8b57-4b8e-be89-44a5be1d07f4"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>chembl_id</th>\n",
       "      <th>organism</th>\n",
       "      <th>canonical_smiles</th>\n",
       "      <th>T1/2 /hr</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>CHEMBL99828</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>Cc1cc(-c2ccc(S(C)(=O)=O)cc2)c(-c2ccc(F)cc2)s1</td>\n",
       "      <td>19.40000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>CHEMBL9946</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>CCCCN(CC)c1nc(C)nc2c1c(C)cn2-c1c(C)cc(C)cc1C</td>\n",
       "      <td>1.50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>CHEMBL99214</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>C[C@@H]1[C@H](OC(=O)N[C@@H](CSc2ccccc2)[C@H](O...</td>\n",
       "      <td>2.53300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>CHEMBL99066</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>CC(C)c1ccccc1Sc1ccc(/C=C/C(=O)N2CCCC(C(=O)O)C2...</td>\n",
       "      <td>0.40000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>CHEMBL98936</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>O=C(N[C@@H](Cc1ccccc1)C[C@H](O)[C@H](Cc1ccccc1...</td>\n",
       "      <td>0.69000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17232</th>\n",
       "      <td>CHEMBL101083</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>CC1(c2ccc(OCCN3CCCCC3)cc2)c2ccc(O)cc2CCN1c1ccc...</td>\n",
       "      <td>7.10000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17233</th>\n",
       "      <td>CHEMBL1007</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>CC(C)C[C@H](NC(=O)CNC(=O)[C@H](Cc1ccc(O)cc1)NC...</td>\n",
       "      <td>2.63000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17234</th>\n",
       "      <td>CHEMBL100379</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>C[C@H](NC(=O)/C=C/c1ccc(F)cc1)c1ccc(F)c(N2CCOC...</td>\n",
       "      <td>3.50000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17235</th>\n",
       "      <td>CHEMBL100367</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>O=C(O)C1CCCN(C(=O)/C=C/c2ccc(Sc3ccc4c(c3)OCCO4...</td>\n",
       "      <td>2.30000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17236</th>\n",
       "      <td>CHEMBL100259</td>\n",
       "      <td>Mus musculus</td>\n",
       "      <td>O=c1ccn([C@@H]2O[C@H](CO)[C@@H](O)[C@H]2O)c(=O...</td>\n",
       "      <td>0.03333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17237 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          chembl_id           organism  \\\n",
       "0       CHEMBL99828  Rattus norvegicus   \n",
       "1        CHEMBL9946  Rattus norvegicus   \n",
       "2       CHEMBL99214  Rattus norvegicus   \n",
       "3       CHEMBL99066  Rattus norvegicus   \n",
       "4       CHEMBL98936  Rattus norvegicus   \n",
       "...             ...                ...   \n",
       "17232  CHEMBL101083  Rattus norvegicus   \n",
       "17233    CHEMBL1007  Rattus norvegicus   \n",
       "17234  CHEMBL100379  Rattus norvegicus   \n",
       "17235  CHEMBL100367  Rattus norvegicus   \n",
       "17236  CHEMBL100259       Mus musculus   \n",
       "\n",
       "                                        canonical_smiles  T1/2 /hr  \n",
       "0          Cc1cc(-c2ccc(S(C)(=O)=O)cc2)c(-c2ccc(F)cc2)s1  19.40000  \n",
       "1           CCCCN(CC)c1nc(C)nc2c1c(C)cn2-c1c(C)cc(C)cc1C   1.50000  \n",
       "2      C[C@@H]1[C@H](OC(=O)N[C@@H](CSc2ccccc2)[C@H](O...   2.53300  \n",
       "3      CC(C)c1ccccc1Sc1ccc(/C=C/C(=O)N2CCCC(C(=O)O)C2...   0.40000  \n",
       "4      O=C(N[C@@H](Cc1ccccc1)C[C@H](O)[C@H](Cc1ccccc1...   0.69000  \n",
       "...                                                  ...       ...  \n",
       "17232  CC1(c2ccc(OCCN3CCCCC3)cc2)c2ccc(O)cc2CCN1c1ccc...   7.10000  \n",
       "17233  CC(C)C[C@H](NC(=O)CNC(=O)[C@H](Cc1ccc(O)cc1)NC...   2.63000  \n",
       "17234  C[C@H](NC(=O)/C=C/c1ccc(F)cc1)c1ccc(F)c(N2CCOC...   3.50000  \n",
       "17235  O=C(O)C1CCCN(C(=O)/C=C/c2ccc(Sc3ccc4c(c3)OCCO4...   2.30000  \n",
       "17236  O=c1ccn([C@@H]2O[C@H](CO)[C@@H](O)[C@H]2O)c(=O...   0.03333  \n",
       "\n",
       "[17237 rows x 4 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "id": "1BeWBXgxo_QO"
   },
   "outputs": [],
   "source": [
    "df = df[df['T1/2 /hr'] < 1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 419
    },
    "id": "0zgiwLr1o_Tm",
    "outputId": "a82f13f4-8de3-4631-b9e2-ca63a9507544"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>chembl_id</th>\n",
       "      <th>organism</th>\n",
       "      <th>canonical_smiles</th>\n",
       "      <th>T1/2 /hr</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>CHEMBL99066</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>CC(C)c1ccccc1Sc1ccc(/C=C/C(=O)N2CCCC(C(=O)O)C2...</td>\n",
       "      <td>0.40000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>CHEMBL98936</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>O=C(N[C@@H](Cc1ccccc1)C[C@H](O)[C@H](Cc1ccccc1...</td>\n",
       "      <td>0.69000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>CHEMBL982</td>\n",
       "      <td>Mus musculus</td>\n",
       "      <td>C=C1CC[C@@]2(O)[C@H]3Cc4ccc(O)c5c4[C@@]2(CCN3C...</td>\n",
       "      <td>0.33330</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>CHEMBL9806</td>\n",
       "      <td>Mus musculus</td>\n",
       "      <td>CS(=O)(=O)Nc1ccc(Nc2c3ccccc3nc3ccccc23)cc1</td>\n",
       "      <td>0.91670</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>CHEMBL98</td>\n",
       "      <td>Mus musculus</td>\n",
       "      <td>O=C(CCCCCCC(=O)Nc1ccccc1)NO</td>\n",
       "      <td>0.38000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17219</th>\n",
       "      <td>CHEMBL10257</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>COc1ccc(C#Cc2ccc(S(=O)(=O)NC(CC#Cc3ccccc3)C(=O...</td>\n",
       "      <td>0.70000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17222</th>\n",
       "      <td>CHEMBL102299</td>\n",
       "      <td>Mus musculus</td>\n",
       "      <td>Cc1ccccc1NC(=O)Nc1ccc(CC(=O)N[C@@H](CC(C)C)C(=...</td>\n",
       "      <td>0.80000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17226</th>\n",
       "      <td>CHEMBL101874</td>\n",
       "      <td>Bos taurus</td>\n",
       "      <td>CC[C@H](C)[C@H](NC(=O)[C@@H](NC(=O)[C@H](CC(C)...</td>\n",
       "      <td>0.16670</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17230</th>\n",
       "      <td>CHEMBL1014</td>\n",
       "      <td>Rattus norvegicus</td>\n",
       "      <td>CCOc1nc2cccc(C(=O)OC(C)OC(=O)OC3CCCCC3)c2n1Cc1...</td>\n",
       "      <td>0.08200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17236</th>\n",
       "      <td>CHEMBL100259</td>\n",
       "      <td>Mus musculus</td>\n",
       "      <td>O=c1ccn([C@@H]2O[C@H](CO)[C@@H](O)[C@H]2O)c(=O...</td>\n",
       "      <td>0.03333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5796 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          chembl_id           organism  \\\n",
       "3       CHEMBL99066  Rattus norvegicus   \n",
       "4       CHEMBL98936  Rattus norvegicus   \n",
       "7         CHEMBL982       Mus musculus   \n",
       "8        CHEMBL9806       Mus musculus   \n",
       "9          CHEMBL98       Mus musculus   \n",
       "...             ...                ...   \n",
       "17219   CHEMBL10257  Rattus norvegicus   \n",
       "17222  CHEMBL102299       Mus musculus   \n",
       "17226  CHEMBL101874         Bos taurus   \n",
       "17230    CHEMBL1014  Rattus norvegicus   \n",
       "17236  CHEMBL100259       Mus musculus   \n",
       "\n",
       "                                        canonical_smiles  T1/2 /hr  \n",
       "3      CC(C)c1ccccc1Sc1ccc(/C=C/C(=O)N2CCCC(C(=O)O)C2...   0.40000  \n",
       "4      O=C(N[C@@H](Cc1ccccc1)C[C@H](O)[C@H](Cc1ccccc1...   0.69000  \n",
       "7      C=C1CC[C@@]2(O)[C@H]3Cc4ccc(O)c5c4[C@@]2(CCN3C...   0.33330  \n",
       "8             CS(=O)(=O)Nc1ccc(Nc2c3ccccc3nc3ccccc23)cc1   0.91670  \n",
       "9                            O=C(CCCCCCC(=O)Nc1ccccc1)NO   0.38000  \n",
       "...                                                  ...       ...  \n",
       "17219  COc1ccc(C#Cc2ccc(S(=O)(=O)NC(CC#Cc3ccccc3)C(=O...   0.70000  \n",
       "17222  Cc1ccccc1NC(=O)Nc1ccc(CC(=O)N[C@@H](CC(C)C)C(=...   0.80000  \n",
       "17226  CC[C@H](C)[C@H](NC(=O)[C@@H](NC(=O)[C@H](CC(C)...   0.16670  \n",
       "17230  CCOc1nc2cccc(C(=O)OC(C)OC(=O)OC3CCCCC3)c2n1Cc1...   0.08200  \n",
       "17236  O=c1ccn([C@@H]2O[C@H](CO)[C@@H](O)[C@H]2O)c(=O...   0.03333  \n",
       "\n",
       "[5796 rows x 4 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "id": "RbIjsRaJuXE7"
   },
   "outputs": [],
   "source": [
    "from rdkit.Chem import Descriptors\n",
    "\n",
    "def generate(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        #desc_MolLogP = Descriptors.MolLogP(mol)\n",
    "        desc_MolWt = Descriptors.MolWt(mol)\n",
    "        desc_NumRotatableBonds = Descriptors.NumRotatableBonds(mol)\n",
    "           \n",
    "        row = np.array([#desc_MolLogP,\n",
    "                        desc_MolWt,\n",
    "                        desc_NumRotatableBonds])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"MolWt\",\"NumRotatableBonds\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_1(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_NumHAcceptors = Descriptors.NumHAcceptors(mol)\n",
    "        desc_NumHDonors = Descriptors.NumHDonors(mol)\n",
    "        desc_NumHeteroatoms = Descriptors.NumHeteroatoms(mol)\n",
    "           \n",
    "        row = np.array([desc_NumHAcceptors,\n",
    "                        desc_NumHDonors,\n",
    "                        desc_NumHeteroatoms])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"NumHAcceptors\",\"NumHDonors\",\"NumHeteroatoms\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_2(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_MolMR = Descriptors.MolMR(mol)\n",
    "        desc_HeavyAtomCount = Descriptors.HeavyAtomCount(mol)\n",
    "        desc_HeavyAtomMolwt = Descriptors.HeavyAtomMolWt(mol)\n",
    "           \n",
    "        row = np.array([desc_MolMR,\n",
    "                        desc_HeavyAtomCount,\n",
    "                        desc_HeavyAtomMolwt])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"MolMR\",\"HeavyAtomCount\",\"HeavyAtomMolwt\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_3(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_NOCount = Descriptors.NOCount(mol)\n",
    "        #desc_NHOHCount = Descriptors.NHOHCount(mol)\n",
    "        desc_NumValenceElectrons = Descriptors.NumValenceElectrons(mol)\n",
    "           \n",
    "        row = np.array([desc_NOCount,\n",
    "                        #desc_NHOHCount,\n",
    "                        desc_NumValenceElectrons])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"NOCount\",\"NumValenceElectrons\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_4(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_RingCount = Descriptors.RingCount(mol)\n",
    "        desc_qed = Descriptors.qed(mol)\n",
    "        desc_MaxAbsEStateIndex = Descriptors.MaxAbsEStateIndex(mol)\n",
    "           \n",
    "        row = np.array([desc_RingCount,\n",
    "                        desc_qed,\n",
    "                        desc_MaxAbsEStateIndex])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"RingCount\",\"qed\",\"MaxAbsEStateIndex\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_5(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_TPSA = Descriptors.TPSA(mol)\n",
    "        desc_LabuteASA = Descriptors.LabuteASA(mol)\n",
    "        desc_PEOE_VSA1 = Descriptors.PEOE_VSA1(mol)\n",
    "           \n",
    "        row = np.array([desc_TPSA,\n",
    "                        desc_LabuteASA,\n",
    "                        desc_PEOE_VSA1])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"TPSA\",\"LabuteASA\",\"PEOE_VSA1\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "\n",
    "\n",
    "def generate_7(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_FractionCSP3 = Descriptors.FractionCSP3(mol)\n",
    "        desc_MaxPartialCharge = Descriptors.MaxPartialCharge(mol)\n",
    "        desc_MinPartialCharge = Descriptors.MinPartialCharge(mol)\n",
    "           \n",
    "        row = np.array([desc_FractionCSP3,\n",
    "                        desc_MaxPartialCharge,\n",
    "                        desc_MinPartialCharge])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"FractionCSP3\",\"MaxPartialCharge\",\"MinPartialCharge\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_8(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_FpDensityMorgan1 = Descriptors.FpDensityMorgan1(mol)\n",
    "        desc_FpDensityMorgan2 = Descriptors.FpDensityMorgan2(mol)\n",
    "        desc_FpDensityMorgan3 = Descriptors.FpDensityMorgan3(mol)\n",
    "           \n",
    "        row = np.array([desc_FpDensityMorgan1,\n",
    "                        desc_FpDensityMorgan2,\n",
    "                        desc_FpDensityMorgan3])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"FpDensityMorgan1\",\"FpDensityMorgan2\",\"FpDensityMorgan3\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_9(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_Chi3n = Descriptors.Chi3n(mol)\n",
    "        desc_Chi3v = Descriptors.Chi3v(mol)\n",
    "        #desc_Chi4v = Descriptors.Chi4v(mol)\n",
    "           \n",
    "        row = np.array([desc_Chi3n,\n",
    "                        desc_Chi3v])\n",
    "                        #desc_Chi4v])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"Chi3n\",\"Chi3v\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_10(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_Kappa3 = Descriptors.Kappa3(mol)\n",
    "        desc_PEOE_VSA10 = Descriptors.PEOE_VSA10(mol)\n",
    "        desc_SMR_VSA4 = Descriptors.SMR_VSA4(mol)\n",
    "           \n",
    "        row = np.array([desc_Kappa3,\n",
    "                        desc_PEOE_VSA10,\n",
    "                        desc_SMR_VSA4])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"Kappa3\",\"PEOE_VSA10\",\"SMR_VSA4\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_11(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_PEOE_VSA12 = Descriptors.PEOE_VSA12(mol)\n",
    "        desc_PEOE_VSA2 = Descriptors.PEOE_VSA2(mol)\n",
    "        desc_PEOE_VSA5 = Descriptors.PEOE_VSA5(mol)\n",
    "           \n",
    "        row = np.array([desc_PEOE_VSA12,\n",
    "                        desc_PEOE_VSA2,\n",
    "                        desc_PEOE_VSA5])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"PEOE_VSA12\",\"PEOE_VSA2\",\"PEOE_VSA5\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_11(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_SMR_VSA10 = Descriptors.SMR_VSA10(mol)\n",
    "        desc_PEOE_VSA9 = Descriptors.PEOE_VSA9(mol)\n",
    "        desc_PEOE_VSA6 = Descriptors.PEOE_VSA6(mol)\n",
    "           \n",
    "        row = np.array([desc_SMR_VSA10,\n",
    "                        desc_PEOE_VSA9,\n",
    "                        desc_PEOE_VSA6])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"SMR_VSA10\",\"PEOE_VSA9\",\"PEOE_VSA6\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "def generate_14(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_SlogP_VSA4 = Descriptors.SlogP_VSA4(mol)\n",
    "        desc_SlogP_VSA5 = Descriptors.SlogP_VSA5(mol)\n",
    "        desc_SlogP_VSA2 = Descriptors.SlogP_VSA2(mol)\n",
    "           \n",
    "        row = np.array([desc_SlogP_VSA4,\n",
    "                        desc_SlogP_VSA5,\n",
    "                        desc_SlogP_VSA2])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"SlogP_VSA4\",\"SlogP_VSA5\",\"SlogP_VSA2\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_15(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_SlogP_VSA7 = Descriptors.SlogP_VSA7(mol)\n",
    "        \n",
    "        desc_Estate_VSA1 = Descriptors.EState_VSA1(mol)\n",
    "           \n",
    "        row = np.array([desc_SlogP_VSA7,\n",
    "                        \n",
    "                        desc_Estate_VSA1])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"SlogP_VSA7\",\"Estate_VSA1\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_16(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_Estate_VSA10 = Descriptors.EState_VSA10(mol)\n",
    "        desc_Estate_VSA2 = Descriptors.EState_VSA2(mol)\n",
    "        desc_Estate_VSA3 = Descriptors.EState_VSA3(mol)\n",
    "           \n",
    "        row = np.array([desc_Estate_VSA10,\n",
    "                        desc_Estate_VSA2,\n",
    "                        desc_Estate_VSA3])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"Estate_VSA10\",\"Estate_VSA2\",\"Estate_VSA3\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_17(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_Estate_VSA4 = Descriptors.EState_VSA4(mol)\n",
    "        desc_Estate_VSA7 = Descriptors.EState_VSA7(mol)\n",
    "        desc_Estate_VSA8 = Descriptors.EState_VSA8(mol)\n",
    "           \n",
    "        row = np.array([desc_Estate_VSA4,\n",
    "                        desc_Estate_VSA7,\n",
    "                        desc_Estate_VSA8])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"Estate_VSA4\",\"Estate_VSA7\",\"Estate_VSA8\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "def generate_18(smiles, verbose=False):\n",
    "\n",
    "    moldata= []\n",
    "    for elem in smiles:\n",
    "        mol=Chem.MolFromSmiles(elem) \n",
    "        moldata.append(mol)\n",
    "       \n",
    "    baseData= np.arange(1,1)\n",
    "    i=0  \n",
    "    for mol in moldata:        \n",
    "       \n",
    "        desc_EState_VSA9 = Descriptors.EState_VSA9(mol)\n",
    "        desc_VSA_Estate1 = Descriptors.VSA_EState1(mol)\n",
    "        \n",
    "        row = np.array([desc_EState_VSA9,\n",
    "                        desc_VSA_Estate1\n",
    "                        ])   \n",
    "    \n",
    "        if(i==0):\n",
    "            baseData=row\n",
    "        else:\n",
    "            baseData=np.vstack([baseData, row])\n",
    "        i=i+1      \n",
    "    \n",
    "    columnNames=[\"EState_VSA9\",\"VSA_Estate1\"]   \n",
    "    descriptors = pd.DataFrame(data=baseData,columns=columnNames)\n",
    "    \n",
    "    return descriptors\n",
    "\n",
    "\n",
    "\n",
    "def AromaticAtoms(m):\n",
    "  aromatic_atoms = [m.GetAtomWithIdx(i).GetIsAromatic() for i in range(m.GetNumAtoms())]\n",
    "  aa_count = []\n",
    "  for i in aromatic_atoms:\n",
    "    if i==True:\n",
    "      aa_count.append(1)\n",
    "  sum_aa_count = sum(aa_count)\n",
    "  return sum_aa_count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "2NkXducWo_We"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "id": "3dR7b8aBpTio"
   },
   "outputs": [],
   "source": [
    "df1 = generate(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "id": "K8YUFHJBpTg1"
   },
   "outputs": [],
   "source": [
    "df2 = generate_1(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "id": "27FQN9NGpTd2"
   },
   "outputs": [],
   "source": [
    "df3 = generate_2(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "id": "jKGAzCIhpTbi"
   },
   "outputs": [],
   "source": [
    "df4 = generate_3(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "id": "Ce63h3B8pTY9"
   },
   "outputs": [],
   "source": [
    "df5 = generate_4(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "id": "fl2kkfsApTWL"
   },
   "outputs": [],
   "source": [
    "df6 = generate_5(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "id": "8gXVDfFapTTd"
   },
   "outputs": [],
   "source": [
    "df8 = generate_7(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "id": "wnor6ELtpTQv"
   },
   "outputs": [],
   "source": [
    "df9 = generate_8(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "id": "4Vlm9T0Dpi5v"
   },
   "outputs": [],
   "source": [
    "df10 = generate_9(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "id": "o3EAMv77pi3G"
   },
   "outputs": [],
   "source": [
    "df11 = generate_10(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "id": "PzNtdtcopi0v"
   },
   "outputs": [],
   "source": [
    "df12 = generate_11(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "id": "v9cjexi3piyl"
   },
   "outputs": [],
   "source": [
    "# df13 = generate_12(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "id": "_-bSC1r7pivk"
   },
   "outputs": [],
   "source": [
    "# df14 = generate_13(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "id": "pZBZbpQcpitP"
   },
   "outputs": [],
   "source": [
    "df15 = generate_14(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "id": "wJhHRWV0piqu"
   },
   "outputs": [],
   "source": [
    "df16 = generate_15(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "id": "rOhCm2_Rpin4"
   },
   "outputs": [],
   "source": [
    "df17 = generate_16(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "id": "OqDlAGcrqgm9"
   },
   "outputs": [],
   "source": [
    "df18 = generate_17(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "id": "nCtQrBVxqgj5"
   },
   "outputs": [],
   "source": [
    "df19 = generate_18(df.canonical_smiles)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "id": "B_WG3CTLqghO"
   },
   "outputs": [],
   "source": [
    "mol_list= []\n",
    "for element in df.canonical_smiles:\n",
    "  mol = Chem.MolFromSmiles(element)\n",
    "  mol_list.append(mol)\n",
    "\n",
    "desc_AromaticProportion = [AromaticAtoms(element)/Descriptors.HeavyAtomCount(element) for element in mol_list]\n",
    "df_desc_AromaticProportion = pd.DataFrame(desc_AromaticProportion, columns=['AromaticProportion'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 439
    },
    "id": "J6kqOHo2qgen",
    "outputId": "4d321096-84f2-43e1-bc9d-e76809998127"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>MolWt</th>\n",
       "      <th>NumRotatableBonds</th>\n",
       "      <th>NumHAcceptors</th>\n",
       "      <th>NumHDonors</th>\n",
       "      <th>NumHeteroatoms</th>\n",
       "      <th>MolMR</th>\n",
       "      <th>HeavyAtomCount</th>\n",
       "      <th>HeavyAtomMolwt</th>\n",
       "      <th>NOCount</th>\n",
       "      <th>NumValenceElectrons</th>\n",
       "      <th>...</th>\n",
       "      <th>SlogP_VSA7</th>\n",
       "      <th>Estate_VSA1</th>\n",
       "      <th>Estate_VSA10</th>\n",
       "      <th>Estate_VSA2</th>\n",
       "      <th>Estate_VSA3</th>\n",
       "      <th>Estate_VSA4</th>\n",
       "      <th>Estate_VSA7</th>\n",
       "      <th>Estate_VSA8</th>\n",
       "      <th>EState_VSA9</th>\n",
       "      <th>VSA_Estate1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>454.548</td>\n",
       "      <td>7.0</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>123.7242</td>\n",
       "      <td>32.0</td>\n",
       "      <td>428.340</td>\n",
       "      <td>7</td>\n",
       "      <td>168</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>16.810522</td>\n",
       "      <td>24.809920</td>\n",
       "      <td>18.139322</td>\n",
       "      <td>35.763241</td>\n",
       "      <td>10.458935</td>\n",
       "      <td>24.265468</td>\n",
       "      <td>13.847474</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>567.664</td>\n",
       "      <td>11.0</td>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>11</td>\n",
       "      <td>146.9692</td>\n",
       "      <td>40.0</td>\n",
       "      <td>534.400</td>\n",
       "      <td>10</td>\n",
       "      <td>212</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>36.478095</td>\n",
       "      <td>14.695602</td>\n",
       "      <td>25.235636</td>\n",
       "      <td>24.511733</td>\n",
       "      <td>17.547725</td>\n",
       "      <td>60.663671</td>\n",
       "      <td>15.617556</td>\n",
       "      <td>18.947452</td>\n",
       "      <td>22.165829</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>339.435</td>\n",
       "      <td>2.0</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>93.9306</td>\n",
       "      <td>25.0</td>\n",
       "      <td>314.235</td>\n",
       "      <td>4</td>\n",
       "      <td>132</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>11.016041</td>\n",
       "      <td>10.213055</td>\n",
       "      <td>17.895319</td>\n",
       "      <td>5.749512</td>\n",
       "      <td>55.827261</td>\n",
       "      <td>6.066367</td>\n",
       "      <td>11.478845</td>\n",
       "      <td>4.736863</td>\n",
       "      <td>6.287456</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>363.442</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>107.4402</td>\n",
       "      <td>26.0</td>\n",
       "      <td>346.306</td>\n",
       "      <td>5</td>\n",
       "      <td>130</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10.023291</td>\n",
       "      <td>8.417797</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>5.687386</td>\n",
       "      <td>39.436392</td>\n",
       "      <td>60.663671</td>\n",
       "      <td>10.038883</td>\n",
       "      <td>4.983979</td>\n",
       "      <td>25.137508</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>264.325</td>\n",
       "      <td>8.0</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>72.7029</td>\n",
       "      <td>19.0</td>\n",
       "      <td>244.165</td>\n",
       "      <td>5</td>\n",
       "      <td>104</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>9.589074</td>\n",
       "      <td>11.814359</td>\n",
       "      <td>12.841643</td>\n",
       "      <td>31.370673</td>\n",
       "      <td>30.331835</td>\n",
       "      <td>5.316789</td>\n",
       "      <td>5.207253</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5791</th>\n",
       "      <td>459.523</td>\n",
       "      <td>6.0</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>7</td>\n",
       "      <td>125.0983</td>\n",
       "      <td>33.0</td>\n",
       "      <td>438.355</td>\n",
       "      <td>6</td>\n",
       "      <td>166</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>22.034437</td>\n",
       "      <td>18.318862</td>\n",
       "      <td>11.316305</td>\n",
       "      <td>5.563451</td>\n",
       "      <td>16.876415</td>\n",
       "      <td>30.331835</td>\n",
       "      <td>28.403832</td>\n",
       "      <td>4.736863</td>\n",
       "      <td>32.633011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5792</th>\n",
       "      <td>522.646</td>\n",
       "      <td>10.0</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>9</td>\n",
       "      <td>146.9569</td>\n",
       "      <td>38.0</td>\n",
       "      <td>484.342</td>\n",
       "      <td>9</td>\n",
       "      <td>204</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>12.011146</td>\n",
       "      <td>24.284676</td>\n",
       "      <td>42.646864</td>\n",
       "      <td>25.073786</td>\n",
       "      <td>29.655933</td>\n",
       "      <td>45.036680</td>\n",
       "      <td>15.950366</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5793</th>\n",
       "      <td>813.010</td>\n",
       "      <td>21.0</td>\n",
       "      <td>10</td>\n",
       "      <td>7</td>\n",
       "      <td>17</td>\n",
       "      <td>216.6869</td>\n",
       "      <td>58.0</td>\n",
       "      <td>748.498</td>\n",
       "      <td>17</td>\n",
       "      <td>322</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>89.368446</td>\n",
       "      <td>33.561760</td>\n",
       "      <td>31.098277</td>\n",
       "      <td>12.114750</td>\n",
       "      <td>5.563451</td>\n",
       "      <td>26.837579</td>\n",
       "      <td>41.868689</td>\n",
       "      <td>9.473726</td>\n",
       "      <td>10.260239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5794</th>\n",
       "      <td>610.671</td>\n",
       "      <td>10.0</td>\n",
       "      <td>11</td>\n",
       "      <td>1</td>\n",
       "      <td>12</td>\n",
       "      <td>164.3702</td>\n",
       "      <td>45.0</td>\n",
       "      <td>576.399</td>\n",
       "      <td>12</td>\n",
       "      <td>232</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>18.414698</td>\n",
       "      <td>9.589074</td>\n",
       "      <td>11.667418</td>\n",
       "      <td>36.019909</td>\n",
       "      <td>54.357914</td>\n",
       "      <td>66.088140</td>\n",
       "      <td>25.608112</td>\n",
       "      <td>18.947452</td>\n",
       "      <td>23.894188</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5795</th>\n",
       "      <td>244.203</td>\n",
       "      <td>2.0</td>\n",
       "      <td>7</td>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "      <td>54.3321</td>\n",
       "      <td>17.0</td>\n",
       "      <td>232.107</td>\n",
       "      <td>8</td>\n",
       "      <td>94</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>42.395693</td>\n",
       "      <td>19.802129</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>16.830310</td>\n",
       "      <td>4.983979</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>9.843390</td>\n",
       "      <td>6.082136</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5796 rows × 43 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        MolWt  NumRotatableBonds  NumHAcceptors  NumHDonors  NumHeteroatoms  \\\n",
       "0     454.548                7.0              5           1               8   \n",
       "1     567.664               11.0              9           3              11   \n",
       "2     339.435                2.0              4           2               4   \n",
       "3     363.442                4.0              4           2               6   \n",
       "4     264.325                8.0              3           3               5   \n",
       "...       ...                ...            ...         ...             ...   \n",
       "5791  459.523                6.0              4           2               7   \n",
       "5792  522.646               10.0              4           4               9   \n",
       "5793  813.010               21.0             10           7              17   \n",
       "5794  610.671               10.0             11           1              12   \n",
       "5795  244.203                2.0              7           4               8   \n",
       "\n",
       "         MolMR  HeavyAtomCount  HeavyAtomMolwt  NOCount  NumValenceElectrons  \\\n",
       "0     123.7242            32.0         428.340        7                  168   \n",
       "1     146.9692            40.0         534.400       10                  212   \n",
       "2      93.9306            25.0         314.235        4                  132   \n",
       "3     107.4402            26.0         346.306        5                  130   \n",
       "4      72.7029            19.0         244.165        5                  104   \n",
       "...        ...             ...             ...      ...                  ...   \n",
       "5791  125.0983            33.0         438.355        6                  166   \n",
       "5792  146.9569            38.0         484.342        9                  204   \n",
       "5793  216.6869            58.0         748.498       17                  322   \n",
       "5794  164.3702            45.0         576.399       12                  232   \n",
       "5795   54.3321            17.0         232.107        8                   94   \n",
       "\n",
       "      ...  SlogP_VSA7  Estate_VSA1  Estate_VSA10  Estate_VSA2  Estate_VSA3  \\\n",
       "0     ...         0.0    16.810522     24.809920    18.139322    35.763241   \n",
       "1     ...         0.0    36.478095     14.695602    25.235636    24.511733   \n",
       "2     ...         0.0    11.016041     10.213055    17.895319     5.749512   \n",
       "3     ...         0.0    10.023291      8.417797     0.000000     5.687386   \n",
       "4     ...         0.0     0.000000      9.589074    11.814359    12.841643   \n",
       "...   ...         ...          ...           ...          ...          ...   \n",
       "5791  ...         0.0    22.034437     18.318862    11.316305     5.563451   \n",
       "5792  ...         0.0    12.011146     24.284676    42.646864    25.073786   \n",
       "5793  ...         0.0    89.368446     33.561760    31.098277    12.114750   \n",
       "5794  ...         0.0    18.414698      9.589074    11.667418    36.019909   \n",
       "5795  ...         0.0    42.395693     19.802129     0.000000     0.000000   \n",
       "\n",
       "      Estate_VSA4  Estate_VSA7  Estate_VSA8  EState_VSA9  VSA_Estate1  \n",
       "0       10.458935    24.265468    13.847474     0.000000     0.000000  \n",
       "1       17.547725    60.663671    15.617556    18.947452    22.165829  \n",
       "2       55.827261     6.066367    11.478845     4.736863     6.287456  \n",
       "3       39.436392    60.663671    10.038883     4.983979    25.137508  \n",
       "4       31.370673    30.331835     5.316789     5.207253     0.000000  \n",
       "...           ...          ...          ...          ...          ...  \n",
       "5791    16.876415    30.331835    28.403832     4.736863    32.633011  \n",
       "5792    29.655933    45.036680    15.950366     0.000000     0.000000  \n",
       "5793     5.563451    26.837579    41.868689     9.473726    10.260239  \n",
       "5794    54.357914    66.088140    25.608112    18.947452    23.894188  \n",
       "5795    16.830310     4.983979     0.000000     9.843390     6.082136  \n",
       "\n",
       "[5796 rows x 43 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = pd.concat([df1,df2,df3,df4,df5,df6,df8,df9,df10,df11,df12,df15,df16,df17,df18,df19], axis=1)\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "id": "4xFwVQILqgcA"
   },
   "outputs": [],
   "source": [
    "y = df.iloc[:,3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "id": "CvLESg9YVxbj"
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "AcXz3r8uqgUS",
    "outputId": "9b81d584-98b5-4c7c-abb5-99bf419a7278"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean squared error (MSE): 0.06\n",
      "Coefficient of determination (R^2): 0.19\n"
     ]
    }
   ],
   "source": [
    "X_train_SS = StandardScaler().fit(X_train)\n",
    "X_train = X_train_SS.transform(X_train)\n",
    "X_test = X_train_SS.transform(X_test)\n",
    "\n",
    "regressor=SVR(kernel='rbf',verbose=False, C = 1, gamma = 0.2)\n",
    "regressor.fit(X_train, y_train)\n",
    "\n",
    "y_pred_test = regressor.predict(X_test)\n",
    "\n",
    "print('Mean squared error (MSE): %.2f'\n",
    "      % mean_squared_error(y_test, y_pred_test))\n",
    "print('Coefficient of determination (R^2): %.2f'\n",
    "      % r2_score(y_test, y_pred_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "TnNdF0g_qgRs"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Cmax.ipynb",
   "provenance": []
  },
  "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": "3.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}