{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "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>mol</th>\n",
       "      <th>CID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Model</th>\n",
       "      <th>pIC50</th>\n",
       "      <th>MW</th>\n",
       "      <th>AlogP</th>\n",
       "      <th>HBA</th>\n",
       "      <th>HBD</th>\n",
       "      <th>RB</th>\n",
       "      <th>...</th>\n",
       "      <th>PEOE6 (PEOE6)</th>\n",
       "      <th>PEOE7 (PEOE7)</th>\n",
       "      <th>PEOE8 (PEOE8)</th>\n",
       "      <th>PEOE9 (PEOE9)</th>\n",
       "      <th>PEOE10 (PEOE10)</th>\n",
       "      <th>PEOE11 (PEOE11)</th>\n",
       "      <th>PEOE12 (PEOE12)</th>\n",
       "      <th>PEOE13 (PEOE13)</th>\n",
       "      <th>PEOE14 (PEOE14)</th>\n",
       "      <th>canvasUID</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>O1CC[C@@H](NC(=O)[C@@H](Cc2cc3cc(ccc3nc2N)-c2c...</td>\n",
       "      <td>BACE_1</td>\n",
       "      <td>1</td>\n",
       "      <td>Train</td>\n",
       "      <td>9.154901</td>\n",
       "      <td>431.56979</td>\n",
       "      <td>4.4014</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>...</td>\n",
       "      <td>53.205711</td>\n",
       "      <td>78.640335</td>\n",
       "      <td>226.855410</td>\n",
       "      <td>107.434910</td>\n",
       "      <td>37.133846</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>7.980170</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Fc1cc(cc(F)c1)C[C@H](NC(=O)[C@@H](N1CC[C@](NC(...</td>\n",
       "      <td>BACE_2</td>\n",
       "      <td>1</td>\n",
       "      <td>Train</td>\n",
       "      <td>8.853872</td>\n",
       "      <td>657.81073</td>\n",
       "      <td>2.6412</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>16</td>\n",
       "      <td>...</td>\n",
       "      <td>73.817162</td>\n",
       "      <td>47.171600</td>\n",
       "      <td>365.676940</td>\n",
       "      <td>174.076750</td>\n",
       "      <td>34.923889</td>\n",
       "      <td>7.980170</td>\n",
       "      <td>24.148668</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24.663788</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>S1(=O)(=O)N(c2cc(cc3c2n(cc3CC)CC1)C(=O)N[C@H](...</td>\n",
       "      <td>BACE_3</td>\n",
       "      <td>1</td>\n",
       "      <td>Train</td>\n",
       "      <td>8.698970</td>\n",
       "      <td>591.74091</td>\n",
       "      <td>2.5499</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>11</td>\n",
       "      <td>...</td>\n",
       "      <td>70.365707</td>\n",
       "      <td>47.941147</td>\n",
       "      <td>192.406520</td>\n",
       "      <td>255.752550</td>\n",
       "      <td>23.654478</td>\n",
       "      <td>0.230159</td>\n",
       "      <td>15.879790</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24.663788</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>S1(=O)(=O)C[C@@H](Cc2cc(O[C@H](COCC)C(F)(F)F)c...</td>\n",
       "      <td>BACE_4</td>\n",
       "      <td>1</td>\n",
       "      <td>Train</td>\n",
       "      <td>8.698970</td>\n",
       "      <td>591.67828</td>\n",
       "      <td>3.1680</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "      <td>...</td>\n",
       "      <td>56.657166</td>\n",
       "      <td>37.954151</td>\n",
       "      <td>194.353040</td>\n",
       "      <td>202.763350</td>\n",
       "      <td>36.498634</td>\n",
       "      <td>0.980913</td>\n",
       "      <td>8.188327</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>26.385181</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>S1(=O)(=O)N(c2cc(cc3c2n(cc3CC)CC1)C(=O)N[C@H](...</td>\n",
       "      <td>BACE_5</td>\n",
       "      <td>1</td>\n",
       "      <td>Train</td>\n",
       "      <td>8.698970</td>\n",
       "      <td>629.71283</td>\n",
       "      <td>3.5086</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>11</td>\n",
       "      <td>...</td>\n",
       "      <td>78.945702</td>\n",
       "      <td>39.361153</td>\n",
       "      <td>179.712880</td>\n",
       "      <td>220.461300</td>\n",
       "      <td>23.654478</td>\n",
       "      <td>0.230159</td>\n",
       "      <td>15.879790</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>26.100143</td>\n",
       "      <td>5</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>1508</th>\n",
       "      <td>Clc1cc2nc(n(c2cc1)C(CC(=O)NCC1CCOCC1)CC)N</td>\n",
       "      <td>BACE_1543</td>\n",
       "      <td>0</td>\n",
       "      <td>Test</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>364.86969</td>\n",
       "      <td>2.5942</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>37.212799</td>\n",
       "      <td>37.681076</td>\n",
       "      <td>180.226410</td>\n",
       "      <td>95.670128</td>\n",
       "      <td>30.107586</td>\n",
       "      <td>9.368159</td>\n",
       "      <td>7.980170</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1543</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1509</th>\n",
       "      <td>Clc1cc2nc(n(c2cc1)C(CC(=O)NCc1ncccc1)CC)N</td>\n",
       "      <td>BACE_1544</td>\n",
       "      <td>0</td>\n",
       "      <td>Test</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>357.83731</td>\n",
       "      <td>2.8229</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>45.792797</td>\n",
       "      <td>47.349350</td>\n",
       "      <td>122.401500</td>\n",
       "      <td>99.877144</td>\n",
       "      <td>30.107586</td>\n",
       "      <td>9.368159</td>\n",
       "      <td>7.980170</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1544</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1510</th>\n",
       "      <td>Brc1cc(ccc1)C1CC1C=1N=C(N)N(C)C(=O)C=1</td>\n",
       "      <td>BACE_1545</td>\n",
       "      <td>0</td>\n",
       "      <td>Test</td>\n",
       "      <td>2.953115</td>\n",
       "      <td>320.18451</td>\n",
       "      <td>3.0895</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>47.790600</td>\n",
       "      <td>22.563574</td>\n",
       "      <td>96.290794</td>\n",
       "      <td>58.798935</td>\n",
       "      <td>20.071724</td>\n",
       "      <td>9.368159</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>6.904104</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1545</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1511</th>\n",
       "      <td>O=C1N(C)C(=NC(=C1)C1CC1c1cc(ccc1)-c1ccccc1)N</td>\n",
       "      <td>BACE_1546</td>\n",
       "      <td>0</td>\n",
       "      <td>Test</td>\n",
       "      <td>2.733298</td>\n",
       "      <td>317.38440</td>\n",
       "      <td>3.8595</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>77.219978</td>\n",
       "      <td>9.316234</td>\n",
       "      <td>95.907784</td>\n",
       "      <td>112.609720</td>\n",
       "      <td>20.071724</td>\n",
       "      <td>9.368159</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>6.904104</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1546</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1512</th>\n",
       "      <td>Clc1cc2nc(n(c2cc1)CCCC(=O)NCC1CC1)N</td>\n",
       "      <td>BACE_1547</td>\n",
       "      <td>0</td>\n",
       "      <td>Test</td>\n",
       "      <td>2.544546</td>\n",
       "      <td>306.79059</td>\n",
       "      <td>3.4271</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>26.907076</td>\n",
       "      <td>37.681076</td>\n",
       "      <td>161.450780</td>\n",
       "      <td>40.882919</td>\n",
       "      <td>30.107586</td>\n",
       "      <td>9.368159</td>\n",
       "      <td>7.980170</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1547</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1513 rows × 595 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                    mol        CID  Class  \\\n",
       "0     O1CC[C@@H](NC(=O)[C@@H](Cc2cc3cc(ccc3nc2N)-c2c...     BACE_1      1   \n",
       "1     Fc1cc(cc(F)c1)C[C@H](NC(=O)[C@@H](N1CC[C@](NC(...     BACE_2      1   \n",
       "2     S1(=O)(=O)N(c2cc(cc3c2n(cc3CC)CC1)C(=O)N[C@H](...     BACE_3      1   \n",
       "3     S1(=O)(=O)C[C@@H](Cc2cc(O[C@H](COCC)C(F)(F)F)c...     BACE_4      1   \n",
       "4     S1(=O)(=O)N(c2cc(cc3c2n(cc3CC)CC1)C(=O)N[C@H](...     BACE_5      1   \n",
       "...                                                 ...        ...    ...   \n",
       "1508          Clc1cc2nc(n(c2cc1)C(CC(=O)NCC1CCOCC1)CC)N  BACE_1543      0   \n",
       "1509          Clc1cc2nc(n(c2cc1)C(CC(=O)NCc1ncccc1)CC)N  BACE_1544      0   \n",
       "1510             Brc1cc(ccc1)C1CC1C=1N=C(N)N(C)C(=O)C=1  BACE_1545      0   \n",
       "1511       O=C1N(C)C(=NC(=C1)C1CC1c1cc(ccc1)-c1ccccc1)N  BACE_1546      0   \n",
       "1512                Clc1cc2nc(n(c2cc1)CCCC(=O)NCC1CC1)N  BACE_1547      0   \n",
       "\n",
       "      Model     pIC50         MW   AlogP  HBA  HBD  RB  ...  PEOE6 (PEOE6)  \\\n",
       "0     Train  9.154901  431.56979  4.4014    3    2   5  ...      53.205711   \n",
       "1     Train  8.853872  657.81073  2.6412    5    4  16  ...      73.817162   \n",
       "2     Train  8.698970  591.74091  2.5499    4    3  11  ...      70.365707   \n",
       "3     Train  8.698970  591.67828  3.1680    4    3  12  ...      56.657166   \n",
       "4     Train  8.698970  629.71283  3.5086    3    3  11  ...      78.945702   \n",
       "...     ...       ...        ...     ...  ...  ...  ..  ...            ...   \n",
       "1508   Test  3.000000  364.86969  2.5942    3    2   6  ...      37.212799   \n",
       "1509   Test  3.000000  357.83731  2.8229    3    2   6  ...      45.792797   \n",
       "1510   Test  2.953115  320.18451  3.0895    2    1   2  ...      47.790600   \n",
       "1511   Test  2.733298  317.38440  3.8595    2    1   3  ...      77.219978   \n",
       "1512   Test  2.544546  306.79059  3.4271    2    2   6  ...      26.907076   \n",
       "\n",
       "      PEOE7 (PEOE7)  PEOE8 (PEOE8)  PEOE9 (PEOE9)  PEOE10 (PEOE10)  \\\n",
       "0         78.640335     226.855410     107.434910        37.133846   \n",
       "1         47.171600     365.676940     174.076750        34.923889   \n",
       "2         47.941147     192.406520     255.752550        23.654478   \n",
       "3         37.954151     194.353040     202.763350        36.498634   \n",
       "4         39.361153     179.712880     220.461300        23.654478   \n",
       "...             ...            ...            ...              ...   \n",
       "1508      37.681076     180.226410      95.670128        30.107586   \n",
       "1509      47.349350     122.401500      99.877144        30.107586   \n",
       "1510      22.563574      96.290794      58.798935        20.071724   \n",
       "1511       9.316234      95.907784     112.609720        20.071724   \n",
       "1512      37.681076     161.450780      40.882919        30.107586   \n",
       "\n",
       "      PEOE11 (PEOE11)  PEOE12 (PEOE12)  PEOE13 (PEOE13)  PEOE14 (PEOE14)  \\\n",
       "0            0.000000         7.980170         0.000000         0.000000   \n",
       "1            7.980170        24.148668         0.000000        24.663788   \n",
       "2            0.230159        15.879790         0.000000        24.663788   \n",
       "3            0.980913         8.188327         0.000000        26.385181   \n",
       "4            0.230159        15.879790         0.000000        26.100143   \n",
       "...               ...              ...              ...              ...   \n",
       "1508         9.368159         7.980170         0.000000         0.000000   \n",
       "1509         9.368159         7.980170         0.000000         0.000000   \n",
       "1510         9.368159         0.000000         6.904104         0.000000   \n",
       "1511         9.368159         0.000000         6.904104         0.000000   \n",
       "1512         9.368159         7.980170         0.000000         0.000000   \n",
       "\n",
       "      canvasUID  \n",
       "0             1  \n",
       "1             2  \n",
       "2             3  \n",
       "3             4  \n",
       "4             5  \n",
       "...         ...  \n",
       "1508       1543  \n",
       "1509       1544  \n",
       "1510       1545  \n",
       "1511       1546  \n",
       "1512       1547  \n",
       "\n",
       "[1513 rows x 595 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df= pd.read_csv('BACE.csv')\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=df[df['Class']==1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "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>mol</th>\n",
       "      <th>CID</th>\n",
       "      <th>Class</th>\n",
       "      <th>Model</th>\n",
       "      <th>pIC50</th>\n",
       "      <th>MW</th>\n",
       "      <th>AlogP</th>\n",
       "      <th>HBA</th>\n",
       "      <th>HBD</th>\n",
       "      <th>RB</th>\n",
       "      <th>...</th>\n",
       "      <th>PEOE6 (PEOE6)</th>\n",
       "      <th>PEOE7 (PEOE7)</th>\n",
       "      <th>PEOE8 (PEOE8)</th>\n",
       "      <th>PEOE9 (PEOE9)</th>\n",
       "      <th>PEOE10 (PEOE10)</th>\n",
       "      <th>PEOE11 (PEOE11)</th>\n",
       "      <th>PEOE12 (PEOE12)</th>\n",
       "      <th>PEOE13 (PEOE13)</th>\n",
       "      <th>PEOE14 (PEOE14)</th>\n",
       "      <th>canvasUID</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>O1CC[C@@H](NC(=O)[C@@H](Cc2cc3cc(ccc3nc2N)-c2c...</td>\n",
       "      <td>BACE_1</td>\n",
       "      <td>1</td>\n",
       "      <td>Train</td>\n",
       "      <td>9.154901</td>\n",
       "      <td>431.56979</td>\n",
       "      <td>4.4014</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>...</td>\n",
       "      <td>53.205711</td>\n",
       "      <td>78.640335</td>\n",
       "      <td>226.855410</td>\n",
       "      <td>107.43491</td>\n",
       "      <td>37.133846</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>7.980170</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Fc1cc(cc(F)c1)C[C@H](NC(=O)[C@@H](N1CC[C@](NC(...</td>\n",
       "      <td>BACE_2</td>\n",
       "      <td>1</td>\n",
       "      <td>Train</td>\n",
       "      <td>8.853872</td>\n",
       "      <td>657.81073</td>\n",
       "      <td>2.6412</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>16</td>\n",
       "      <td>...</td>\n",
       "      <td>73.817162</td>\n",
       "      <td>47.171600</td>\n",
       "      <td>365.676940</td>\n",
       "      <td>174.07675</td>\n",
       "      <td>34.923889</td>\n",
       "      <td>7.980170</td>\n",
       "      <td>24.148668</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24.663788</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>S1(=O)(=O)N(c2cc(cc3c2n(cc3CC)CC1)C(=O)N[C@H](...</td>\n",
       "      <td>BACE_3</td>\n",
       "      <td>1</td>\n",
       "      <td>Train</td>\n",
       "      <td>8.698970</td>\n",
       "      <td>591.74091</td>\n",
       "      <td>2.5499</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>11</td>\n",
       "      <td>...</td>\n",
       "      <td>70.365707</td>\n",
       "      <td>47.941147</td>\n",
       "      <td>192.406520</td>\n",
       "      <td>255.75255</td>\n",
       "      <td>23.654478</td>\n",
       "      <td>0.230159</td>\n",
       "      <td>15.879790</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24.663788</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>S1(=O)(=O)C[C@@H](Cc2cc(O[C@H](COCC)C(F)(F)F)c...</td>\n",
       "      <td>BACE_4</td>\n",
       "      <td>1</td>\n",
       "      <td>Train</td>\n",
       "      <td>8.698970</td>\n",
       "      <td>591.67828</td>\n",
       "      <td>3.1680</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "      <td>...</td>\n",
       "      <td>56.657166</td>\n",
       "      <td>37.954151</td>\n",
       "      <td>194.353040</td>\n",
       "      <td>202.76335</td>\n",
       "      <td>36.498634</td>\n",
       "      <td>0.980913</td>\n",
       "      <td>8.188327</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>26.385181</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>S1(=O)(=O)N(c2cc(cc3c2n(cc3CC)CC1)C(=O)N[C@H](...</td>\n",
       "      <td>BACE_5</td>\n",
       "      <td>1</td>\n",
       "      <td>Train</td>\n",
       "      <td>8.698970</td>\n",
       "      <td>629.71283</td>\n",
       "      <td>3.5086</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>11</td>\n",
       "      <td>...</td>\n",
       "      <td>78.945702</td>\n",
       "      <td>39.361153</td>\n",
       "      <td>179.712880</td>\n",
       "      <td>220.46130</td>\n",
       "      <td>23.654478</td>\n",
       "      <td>0.230159</td>\n",
       "      <td>15.879790</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>26.100143</td>\n",
       "      <td>5</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>789</th>\n",
       "      <td>Fc1cc(cc(F)c1)CC(NC(=O)C)C(O)C[NH2+]C1(CCCCC1)...</td>\n",
       "      <td>BACE_821</td>\n",
       "      <td>1</td>\n",
       "      <td>Test</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>457.57581</td>\n",
       "      <td>3.8757</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>32.844196</td>\n",
       "      <td>68.638565</td>\n",
       "      <td>260.466370</td>\n",
       "      <td>108.20742</td>\n",
       "      <td>23.302103</td>\n",
       "      <td>7.980170</td>\n",
       "      <td>8.188327</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24.663788</td>\n",
       "      <td>821</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>790</th>\n",
       "      <td>Fc1ccc(cc1OCCCCF)[C@]1(N=C(N)N(C)C1=O)c1ccc(OC...</td>\n",
       "      <td>BACE_822</td>\n",
       "      <td>1</td>\n",
       "      <td>Test</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>439.40341</td>\n",
       "      <td>4.4032</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>25.739992</td>\n",
       "      <td>48.511223</td>\n",
       "      <td>89.019829</td>\n",
       "      <td>138.51161</td>\n",
       "      <td>36.094353</td>\n",
       "      <td>8.951914</td>\n",
       "      <td>7.980170</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>6.970751</td>\n",
       "      <td>822</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>791</th>\n",
       "      <td>O=C1N(C)C(=NC1(c1cc(ccc1)-c1cncnc1)c1cn(nc1)C)N</td>\n",
       "      <td>BACE_823</td>\n",
       "      <td>1</td>\n",
       "      <td>Test</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>347.37390</td>\n",
       "      <td>0.2846</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>25.739992</td>\n",
       "      <td>13.182580</td>\n",
       "      <td>127.748380</td>\n",
       "      <td>97.01915</td>\n",
       "      <td>44.097675</td>\n",
       "      <td>3.271739</td>\n",
       "      <td>7.980170</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>823</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>792</th>\n",
       "      <td>FC1(F)CN2C(=NC1)C(N=C2N)(c1cc(ccc1)-c1cncnc1)c...</td>\n",
       "      <td>BACE_824</td>\n",
       "      <td>1</td>\n",
       "      <td>Test</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>434.44131</td>\n",
       "      <td>2.6596</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>42.899986</td>\n",
       "      <td>32.988831</td>\n",
       "      <td>58.408638</td>\n",
       "      <td>173.93533</td>\n",
       "      <td>57.899143</td>\n",
       "      <td>3.271739</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-1.273524</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>824</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>793</th>\n",
       "      <td>S1(=O)(=O)CC(Cc2cc(OCCOC)c(N)c(F)c2)C(O)C([NH2...</td>\n",
       "      <td>BACE_825</td>\n",
       "      <td>1</td>\n",
       "      <td>Test</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>509.65369</td>\n",
       "      <td>1.7831</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>10</td>\n",
       "      <td>...</td>\n",
       "      <td>56.657166</td>\n",
       "      <td>27.648426</td>\n",
       "      <td>167.337080</td>\n",
       "      <td>231.51552</td>\n",
       "      <td>36.498634</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>8.188327</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24.663788</td>\n",
       "      <td>825</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>691 rows × 595 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                   mol       CID  Class  \\\n",
       "0    O1CC[C@@H](NC(=O)[C@@H](Cc2cc3cc(ccc3nc2N)-c2c...    BACE_1      1   \n",
       "1    Fc1cc(cc(F)c1)C[C@H](NC(=O)[C@@H](N1CC[C@](NC(...    BACE_2      1   \n",
       "2    S1(=O)(=O)N(c2cc(cc3c2n(cc3CC)CC1)C(=O)N[C@H](...    BACE_3      1   \n",
       "3    S1(=O)(=O)C[C@@H](Cc2cc(O[C@H](COCC)C(F)(F)F)c...    BACE_4      1   \n",
       "4    S1(=O)(=O)N(c2cc(cc3c2n(cc3CC)CC1)C(=O)N[C@H](...    BACE_5      1   \n",
       "..                                                 ...       ...    ...   \n",
       "789  Fc1cc(cc(F)c1)CC(NC(=O)C)C(O)C[NH2+]C1(CCCCC1)...  BACE_821      1   \n",
       "790  Fc1ccc(cc1OCCCCF)[C@]1(N=C(N)N(C)C1=O)c1ccc(OC...  BACE_822      1   \n",
       "791    O=C1N(C)C(=NC1(c1cc(ccc1)-c1cncnc1)c1cn(nc1)C)N  BACE_823      1   \n",
       "792  FC1(F)CN2C(=NC1)C(N=C2N)(c1cc(ccc1)-c1cncnc1)c...  BACE_824      1   \n",
       "793  S1(=O)(=O)CC(Cc2cc(OCCOC)c(N)c(F)c2)C(O)C([NH2...  BACE_825      1   \n",
       "\n",
       "     Model     pIC50         MW   AlogP  HBA  HBD  RB  ...  PEOE6 (PEOE6)  \\\n",
       "0    Train  9.154901  431.56979  4.4014    3    2   5  ...      53.205711   \n",
       "1    Train  8.853872  657.81073  2.6412    5    4  16  ...      73.817162   \n",
       "2    Train  8.698970  591.74091  2.5499    4    3  11  ...      70.365707   \n",
       "3    Train  8.698970  591.67828  3.1680    4    3  12  ...      56.657166   \n",
       "4    Train  8.698970  629.71283  3.5086    3    3  11  ...      78.945702   \n",
       "..     ...       ...        ...     ...  ...  ...  ..  ...            ...   \n",
       "789   Test  7.000000  457.57581  3.8757    2    3   9  ...      32.844196   \n",
       "790   Test  7.000000  439.40341  4.4032    4    0   9  ...      25.739992   \n",
       "791   Test  7.000000  347.37390  0.2846    5    0   3  ...      25.739992   \n",
       "792   Test  7.000000  434.44131  2.6596    5    0   4  ...      42.899986   \n",
       "793   Test  7.000000  509.65369  1.7831    4    3  10  ...      56.657166   \n",
       "\n",
       "     PEOE7 (PEOE7)  PEOE8 (PEOE8)  PEOE9 (PEOE9)  PEOE10 (PEOE10)  \\\n",
       "0        78.640335     226.855410      107.43491        37.133846   \n",
       "1        47.171600     365.676940      174.07675        34.923889   \n",
       "2        47.941147     192.406520      255.75255        23.654478   \n",
       "3        37.954151     194.353040      202.76335        36.498634   \n",
       "4        39.361153     179.712880      220.46130        23.654478   \n",
       "..             ...            ...            ...              ...   \n",
       "789      68.638565     260.466370      108.20742        23.302103   \n",
       "790      48.511223      89.019829      138.51161        36.094353   \n",
       "791      13.182580     127.748380       97.01915        44.097675   \n",
       "792      32.988831      58.408638      173.93533        57.899143   \n",
       "793      27.648426     167.337080      231.51552        36.498634   \n",
       "\n",
       "     PEOE11 (PEOE11)  PEOE12 (PEOE12)  PEOE13 (PEOE13)  PEOE14 (PEOE14)  \\\n",
       "0           0.000000         7.980170         0.000000         0.000000   \n",
       "1           7.980170        24.148668         0.000000        24.663788   \n",
       "2           0.230159        15.879790         0.000000        24.663788   \n",
       "3           0.980913         8.188327         0.000000        26.385181   \n",
       "4           0.230159        15.879790         0.000000        26.100143   \n",
       "..               ...              ...              ...              ...   \n",
       "789         7.980170         8.188327         0.000000        24.663788   \n",
       "790         8.951914         7.980170         0.000000         6.970751   \n",
       "791         3.271739         7.980170         0.000000         0.000000   \n",
       "792         3.271739         0.000000        -1.273524         0.000000   \n",
       "793         0.000000         8.188327         0.000000        24.663788   \n",
       "\n",
       "     canvasUID  \n",
       "0            1  \n",
       "1            2  \n",
       "2            3  \n",
       "3            4  \n",
       "4            5  \n",
       "..         ...  \n",
       "789        821  \n",
       "790        822  \n",
       "791        823  \n",
       "792        824  \n",
       "793        825  \n",
       "\n",
       "[691 rows x 595 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "np.savetxt(r'bace.txt', df.mol.values, fmt='%s')"
   ]
  },
  {
   "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": "3.9.5"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "a4329ea539b1232b51730207fd9c93849c82cf9ff2a2d6356a1e6b85d15167f8"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}