notebooks/13_full_logP_pH_dataset_analysis.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#  LogP+pH dataset normalizing. Categorial pH generating."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Summary\n",
    "### Usual pH\n",
    "- There are 2407 records\n",
    "- Only 1348 unique smiles\n",
    "- 2394 records with unique smiles+pH\n",
    "- 6 molecules with pH=7.0 had std > 1. They were dropped. The rest was avaraged.\n",
    "- All in all, 2388 records of smiles+logP+pH\n",
    "\n",
    "### Categorized pH\n",
    "- Categorazation of pH was made according to the rule: \n",
    "  - pH < 6 => acid (0)\n",
    "  - 6 <= pH < 8 => neutral (1)\n",
    "  - ph >= 8 => alkali (2)\n",
    "- After dropping duplicates there were no records with unique smiles+pH_range and variation of logP > 1\n",
    "- All the records were averaged.\n",
    "- All in all, there 1504 unique records left.\n",
    "- Environments:\n",
    "  - 0 - 594\n",
    "  - 1 - 677\n",
    "  - 2 - 233\n",
    "- LogP distribution plot in neutral environment is more \"left\", than in acidic/alcalic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import os\n",
    "import seaborn as sns\n",
    "from pathlib import Path\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "DATA_PATH = \"../data/3_final_data/\""
   ]
  },
  {
   "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>smiles</th>\n",
       "      <th>logP</th>\n",
       "      <th>pH</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>COc1ccccc1[C@@H]1CC(=O)Nc2cc(C)c(C)cc21</td>\n",
       "      <td>4.17</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>COc1ccc2c(c1)O[C@](O)(C(F)(F)F)CC2=O</td>\n",
       "      <td>2.79</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>CC(C)(C)C1(C)OC(C(N)=O)C(C(N)=O)O1</td>\n",
       "      <td>1.60</td>\n",
       "      <td>6.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>CCOc1cc(-c2nnc(-c3ccco3)o2)cc(OCC)c1OCC</td>\n",
       "      <td>3.96</td>\n",
       "      <td>10.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>C=C(c1ccc(N(C)C)cc1)c1ccc(N(C)C)cc1</td>\n",
       "      <td>5.30</td>\n",
       "      <td>7.3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                    smiles  logP    pH\n",
       "0  COc1ccccc1[C@@H]1CC(=O)Nc2cc(C)c(C)cc21  4.17   5.0\n",
       "1     COc1ccc2c(c1)O[C@](O)(C(F)(F)F)CC2=O  2.79   5.0\n",
       "2       CC(C)(C)C1(C)OC(C(N)=O)C(C(N)=O)O1  1.60   6.5\n",
       "3  CCOc1cc(-c2nnc(-c3ccco3)o2)cc(OCC)c1OCC  3.96  10.5\n",
       "4      C=C(c1ccc(N(C)C)cc1)c1ccc(N(C)C)cc1  5.30   7.3"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_ph_data = pd.read_csv(DATA_PATH + 'logP_pH.csv')\n",
    "logp_ph_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2407, 3)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_ph_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1348"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_ph_data.smiles.nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1aadc1a4ba8>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(logp_ph_data.pH)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>smiles</th>\n",
       "      <th>pH</th>\n",
       "      <th>logP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>177</th>\n",
       "      <td>CC(C)C(N)C(=O)NC(C(=O)O)C(C)C</td>\n",
       "      <td>7.0</td>\n",
       "      <td>3.12500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>454</th>\n",
       "      <td>CCC(C)C(NC(=O)C(N)CC(C)C)C(=O)O</td>\n",
       "      <td>7.0</td>\n",
       "      <td>2.69120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>203</th>\n",
       "      <td>CC(C)CC(N)C(=O)NC(C(=O)O)C(C)C</td>\n",
       "      <td>7.0</td>\n",
       "      <td>2.66805</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1393</th>\n",
       "      <td>CSCCC(N)C(=O)NC(C(=O)O)C(C)C</td>\n",
       "      <td>7.0</td>\n",
       "      <td>2.53125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>243</th>\n",
       "      <td>CC(C)CC(NC(=O)C(N)Cc1ccc(O)cc1)C(=O)O</td>\n",
       "      <td>7.0</td>\n",
       "      <td>2.14245</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1371</th>\n",
       "      <td>COc1nc(=NC(=O)NS(=O)(=O)c2ccccc2OCCCl)nc(C)[nH]1</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1.42805</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2313</th>\n",
       "      <td>O=c1[nH]c2c(O)ccc(CCNCCCSCCOCCc3ccccc3)c2s1</td>\n",
       "      <td>7.4</td>\n",
       "      <td>0.74420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116</th>\n",
       "      <td>CC(C(=O)O)c1ccc(-c2ccccc2)c(F)c1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.21125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2294</th>\n",
       "      <td>O=c1[nH]c2c(O)ccc(CCNCCCS(=O)(=O)CCCOCCc3ccccc...</td>\n",
       "      <td>7.4</td>\n",
       "      <td>0.04805</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>138</th>\n",
       "      <td>CC(C(=O)O)c1cccc(C(=O)c2ccccc2)c1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.01960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>104</th>\n",
       "      <td>CC(C(=O)O)c1ccc(-c2ccccc2)c(F)c1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.01445</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>CC(C(=O)O)c1cccc(C(=O)c2ccccc2)c1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.00080</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C</td>\n",
       "      <td>7.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>C(=C/c1ccccc1)\\CN1CCN(C(c2ccccc2)c2ccccc2)CC1</td>\n",
       "      <td>4.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>C(=N/n1cnnc1)\\c1ccc(-n2nc(-c3ccccc3)cc2-c2cccc...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>C/C(=C\\c1ccco1)[C@@H]1c2c(-c3ccccc3)n[nH]c2OC(...</td>\n",
       "      <td>10.5</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 smiles    pH     logP\n",
       "177                       CC(C)C(N)C(=O)NC(C(=O)O)C(C)C   7.0  3.12500\n",
       "454                     CCC(C)C(NC(=O)C(N)CC(C)C)C(=O)O   7.0  2.69120\n",
       "203                      CC(C)CC(N)C(=O)NC(C(=O)O)C(C)C   7.0  2.66805\n",
       "1393                       CSCCC(N)C(=O)NC(C(=O)O)C(C)C   7.0  2.53125\n",
       "243               CC(C)CC(NC(=O)C(N)Cc1ccc(O)cc1)C(=O)O   7.0  2.14245\n",
       "1371   COc1nc(=NC(=O)NS(=O)(=O)c2ccccc2OCCCl)nc(C)[nH]1   7.0  1.42805\n",
       "2313        O=c1[nH]c2c(O)ccc(CCNCCCSCCOCCc3ccccc3)c2s1   7.4  0.74420\n",
       "116                    CC(C(=O)O)c1ccc(-c2ccccc2)c(F)c1   4.0  0.21125\n",
       "2294  O=c1[nH]c2c(O)ccc(CCNCCCS(=O)(=O)CCCOCCc3ccccc...   7.4  0.04805\n",
       "138                   CC(C(=O)O)c1cccc(C(=O)c2ccccc2)c1   2.0  0.01960\n",
       "104                    CC(C(=O)O)c1ccc(-c2ccccc2)c(F)c1   2.0  0.01445\n",
       "147                   CC(C(=O)O)c1cccc(C(=O)c2ccccc2)c1   5.0  0.00080\n",
       "0             C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C   7.5      NaN\n",
       "1                   C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C   5.0      NaN\n",
       "2       C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC   5.0      NaN\n",
       "3     C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...   5.0      NaN\n",
       "4     C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...   5.0      NaN\n",
       "5         C(=C/c1ccccc1)\\CN1CCN(C(c2ccccc2)c2ccccc2)CC1   4.5      NaN\n",
       "6     C(=N/n1cnnc1)\\c1ccc(-n2nc(-c3ccccc3)cc2-c2cccc...  10.0      NaN\n",
       "7     C/C(=C\\c1ccco1)[C@@H]1c2c(-c3ccccc3)n[nH]c2OC(...  10.5      NaN"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_ph_data.groupby(['smiles', 'pH'], as_index=False).agg('var').sort_values(by=['logP'], ascending=False).head(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2.1517201308778215"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_ph_data[~logp_ph_data['smiles'].duplicated(keep=False)].pH.std()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "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></th>\n",
       "      <th>logP_var</th>\n",
       "      <th>logP_count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>smiles</th>\n",
       "      <th>pH</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>CC(C)C(N)C(=O)NC(C(=O)O)C(C)C</th>\n",
       "      <th>7.0</th>\n",
       "      <td>3.12500</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CCC(C)C(NC(=O)C(N)CC(C)C)C(=O)O</th>\n",
       "      <th>7.0</th>\n",
       "      <td>2.69120</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC(C)CC(N)C(=O)NC(C(=O)O)C(C)C</th>\n",
       "      <th>7.0</th>\n",
       "      <td>2.66805</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CSCCC(N)C(=O)NC(C(=O)O)C(C)C</th>\n",
       "      <th>7.0</th>\n",
       "      <td>2.53125</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC(C)CC(NC(=O)C(N)Cc1ccc(O)cc1)C(=O)O</th>\n",
       "      <th>7.0</th>\n",
       "      <td>2.14245</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>COc1nc(=NC(=O)NS(=O)(=O)c2ccccc2OCCCl)nc(C)[nH]1</th>\n",
       "      <th>7.0</th>\n",
       "      <td>1.42805</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>O=c1[nH]c2c(O)ccc(CCNCCCSCCOCCc3ccccc3)c2s1</th>\n",
       "      <th>7.4</th>\n",
       "      <td>0.74420</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC(C(=O)O)c1ccc(-c2ccccc2)c(F)c1</th>\n",
       "      <th>4.0</th>\n",
       "      <td>0.21125</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>O=c1[nH]c2c(O)ccc(CCNCCCS(=O)(=O)CCCOCCc3ccccc3)c2s1</th>\n",
       "      <th>7.4</th>\n",
       "      <td>0.04805</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CC(C(=O)O)c1cccc(C(=O)c2ccccc2)c1</th>\n",
       "      <th>2.0</th>\n",
       "      <td>0.01960</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                        logP_var  logP_count\n",
       "smiles                                             pH                       \n",
       "CC(C)C(N)C(=O)NC(C(=O)O)C(C)C                      7.0   3.12500           2\n",
       "CCC(C)C(NC(=O)C(N)CC(C)C)C(=O)O                    7.0   2.69120           2\n",
       "CC(C)CC(N)C(=O)NC(C(=O)O)C(C)C                     7.0   2.66805           2\n",
       "CSCCC(N)C(=O)NC(C(=O)O)C(C)C                       7.0   2.53125           2\n",
       "CC(C)CC(NC(=O)C(N)Cc1ccc(O)cc1)C(=O)O              7.0   2.14245           2\n",
       "COc1nc(=NC(=O)NS(=O)(=O)c2ccccc2OCCCl)nc(C)[nH]1   7.0   1.42805           2\n",
       "O=c1[nH]c2c(O)ccc(CCNCCCSCCOCCc3ccccc3)c2s1        7.4   0.74420           2\n",
       "CC(C(=O)O)c1ccc(-c2ccccc2)c(F)c1                   4.0   0.21125           2\n",
       "O=c1[nH]c2c(O)ccc(CCNCCCS(=O)(=O)CCCOCCc3ccccc3... 7.4   0.04805           2\n",
       "CC(C(=O)O)c1cccc(C(=O)c2ccccc2)c1                  2.0   0.01960           3"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped_data = logp_ph_data.groupby(['smiles', 'pH']).agg(logP_var=('logP', 'var'), \n",
    "                                       logP_count=('logP', 'count')).sort_values(by=['logP_var', 'logP_count'], ascending=False)\n",
    "grouped_data.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2394, 2)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "bad_smiles = ['CC(C)C(N)C(=O)NC(C(=O)O)C(C)C',\n",
    "'CCC(C)C(NC(=O)C(N)CC(C)C)C(=O)O',\n",
    "'CC(C)CC(N)C(=O)NC(C(=O)O)C(C)C',\n",
    "'CSCCC(N)C(=O)NC(C(=O)O)C(C)C',\n",
    "'CC(C)CC(NC(=O)C(N)Cc1ccc(O)cc1)C(=O)O',\n",
    "'COc1nc(=NC(=O)NS(=O)(=O)c2ccccc2OCCCl)nc(C)[nH]1']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2395, 3)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_ph_verified_data = logp_ph_data[(~logp_ph_data.smiles.isin(bad_smiles)) | (~(logp_ph_data.pH == 7))]\n",
    "logp_ph_verified_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>smiles</th>\n",
       "      <th>pH</th>\n",
       "      <th>logP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C</td>\n",
       "      <td>7.5</td>\n",
       "      <td>4.53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6.85</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              smiles   pH  logP\n",
       "0          C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C  7.5  4.53\n",
       "1                C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C  5.0  2.28\n",
       "2    C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC  5.0  3.72\n",
       "3  C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...  5.0  4.93\n",
       "4  C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...  5.0  6.85"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_unique_dataset = logp_ph_verified_data.groupby(['smiles', 'pH']).mean().reset_index()\n",
    "logp_pH_unique_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2388, 3)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_unique_dataset.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1aadbeb11d0>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(logp_ph_data.pH)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>smiles</th>\n",
       "      <th>pH</th>\n",
       "      <th>logP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C</td>\n",
       "      <td>7.5</td>\n",
       "      <td>4.53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6.85</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              smiles   pH  logP\n",
       "0          C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C  7.5  4.53\n",
       "1                C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C  5.0  2.28\n",
       "2    C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC  5.0  3.72\n",
       "3  C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...  5.0  4.93\n",
       "4  C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...  5.0  6.85"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_unique_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pH\n",
       "(1, 6]     1033\n",
       "(6, 8]     1009\n",
       "(8, 14]     330\n",
       "Name: pH, dtype: int64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ranges = [1, 6, 8, 14]\n",
    "logp_pH_unique_dataset['pH'].groupby(pd.cut(logp_pH_unique_dataset['pH'], ranges)).count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "f = lambda x: 2 if x >= 8 else (1 if x >= 6 else 0)  \n",
    "logp_pH_range_dataset = logp_pH_unique_dataset.copy()\n",
    "pH_series = logp_pH_unique_dataset.pH\n",
    "logp_pH_range_dataset['pH_range'] = pH_series.map(f) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>smiles</th>\n",
       "      <th>pH</th>\n",
       "      <th>logP</th>\n",
       "      <th>pH_range</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C</td>\n",
       "      <td>7.5</td>\n",
       "      <td>4.53</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.28</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.72</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.93</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6.85</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>C(=C/c1ccccc1)\\CN1CCN(C(c2ccccc2)c2ccccc2)CC1</td>\n",
       "      <td>4.5</td>\n",
       "      <td>5.77</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>C(=N/n1cnnc1)\\c1ccc(-n2nc(-c3ccccc3)cc2-c2cccc...</td>\n",
       "      <td>10.0</td>\n",
       "      <td>5.58</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>C/C(=C\\c1ccco1)[C@@H]1c2c(-c3ccccc3)n[nH]c2OC(...</td>\n",
       "      <td>10.5</td>\n",
       "      <td>4.82</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>C/C=C/CC(C)C(O)C1C(=O)NC(CC)C(=O)N(C)CC(=O)N(C...</td>\n",
       "      <td>5.5</td>\n",
       "      <td>2.92</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>C=C(C)CSc1nnc(-c2cccc(S(=O)(=O)N3CCOCC3)c2)n1C...</td>\n",
       "      <td>10.5</td>\n",
       "      <td>4.73</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              smiles    pH  logP  pH_range\n",
       "0          C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C   7.5  4.53         1\n",
       "1                C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C   5.0  2.28         0\n",
       "2    C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC   5.0  3.72         0\n",
       "3  C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...   5.0  4.93         0\n",
       "4  C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...   5.0  6.85         0\n",
       "5      C(=C/c1ccccc1)\\CN1CCN(C(c2ccccc2)c2ccccc2)CC1   4.5  5.77         0\n",
       "6  C(=N/n1cnnc1)\\c1ccc(-n2nc(-c3ccccc3)cc2-c2cccc...  10.0  5.58         2\n",
       "7  C/C(=C\\c1ccco1)[C@@H]1c2c(-c3ccccc3)n[nH]c2OC(...  10.5  4.82         2\n",
       "8  C/C=C/CC(C)C(O)C1C(=O)NC(CC)C(=O)N(C)CC(=O)N(C...   5.5  2.92         0\n",
       "9  C=C(C)CSc1nnc(-c2cccc(S(=O)(=O)N3CCOCC3)c2)n1C...  10.5  4.73         2"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_range_dataset.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    1014\n",
       "1    1011\n",
       "2     363\n",
       "Name: pH_range, dtype: int64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_range_dataset.pH_range.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>smiles</th>\n",
       "      <th>logP</th>\n",
       "      <th>pH_range</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C</td>\n",
       "      <td>4.53</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C</td>\n",
       "      <td>2.28</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC</td>\n",
       "      <td>3.72</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...</td>\n",
       "      <td>4.93</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...</td>\n",
       "      <td>6.85</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              smiles  logP  pH_range\n",
       "0          C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C  4.53         1\n",
       "1                C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C  2.28         0\n",
       "2    C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC  3.72         0\n",
       "3  C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...  4.93         0\n",
       "4  C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...  6.85         0"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_range_dataset = logp_pH_range_dataset.drop(columns=['pH'])\n",
    "logp_pH_range_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "logp_pH_range_dataset = logp_pH_range_dataset.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "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>smiles</th>\n",
       "      <th>pH_range</th>\n",
       "      <th>logP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1271</th>\n",
       "      <td>O=C(CCCN1CCC(O)(c2ccc(Cl)cc2)CC1)c1ccc(F)cc1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.441800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78</th>\n",
       "      <td>CC(C(=O)O)c1ccc(-c2ccccc2)c(F)c1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.211250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>77</th>\n",
       "      <td>CC(C(=O)O)c1ccc(-c2ccccc2)c(F)c1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.112442</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>370</th>\n",
       "      <td>CCCCCCCCCCCC(=O)O</td>\n",
       "      <td>0</td>\n",
       "      <td>0.080000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1397</th>\n",
       "      <td>O=C1NC(=O)C(c2ccccc2)(c2ccccc2)N1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.033800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1398</th>\n",
       "      <td>O=C1NC(=O)C(c2ccccc2)(c2ccccc2)N1</td>\n",
       "      <td>2</td>\n",
       "      <td>0.033800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>490</th>\n",
       "      <td>CCN1CC(C(O)C(CC2CCCCC2)NC(=O)C(Cc2c[nH]cn2)NC(...</td>\n",
       "      <td>1</td>\n",
       "      <td>0.020000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>82</th>\n",
       "      <td>CC(C(=O)O)c1cccc(C(=O)c2ccccc2)c1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.019600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>489</th>\n",
       "      <td>CCN1CC(C(O)C(CC2CCCCC2)NC(=O)C(Cc2c[nH]cn2)NC(...</td>\n",
       "      <td>1</td>\n",
       "      <td>0.016200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81</th>\n",
       "      <td>CC(C(=O)O)c1cccc(C(=O)c2ccccc2)c1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.013967</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 smiles  pH_range      logP\n",
       "1271       O=C(CCCN1CCC(O)(c2ccc(Cl)cc2)CC1)c1ccc(F)cc1         1  0.441800\n",
       "78                     CC(C(=O)O)c1ccc(-c2ccccc2)c(F)c1         1  0.211250\n",
       "77                     CC(C(=O)O)c1ccc(-c2ccccc2)c(F)c1         0  0.112442\n",
       "370                                   CCCCCCCCCCCC(=O)O         0  0.080000\n",
       "1397                  O=C1NC(=O)C(c2ccccc2)(c2ccccc2)N1         1  0.033800\n",
       "1398                  O=C1NC(=O)C(c2ccccc2)(c2ccccc2)N1         2  0.033800\n",
       "490   CCN1CC(C(O)C(CC2CCCCC2)NC(=O)C(Cc2c[nH]cn2)NC(...         1  0.020000\n",
       "82                    CC(C(=O)O)c1cccc(C(=O)c2ccccc2)c1         1  0.019600\n",
       "489   CCN1CC(C(O)C(CC2CCCCC2)NC(=O)C(Cc2c[nH]cn2)NC(...         1  0.016200\n",
       "81                    CC(C(=O)O)c1cccc(C(=O)c2ccccc2)c1         0  0.013967"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped_data = logp_pH_range_dataset.groupby(['smiles', 'pH_range'], as_index=False).agg('var').sort_values(by=['logP'], ascending=False)\n",
    "grouped_data.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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>smiles</th>\n",
       "      <th>pH_range</th>\n",
       "      <th>logP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C</td>\n",
       "      <td>1</td>\n",
       "      <td>4.53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C</td>\n",
       "      <td>0</td>\n",
       "      <td>2.28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC</td>\n",
       "      <td>0</td>\n",
       "      <td>3.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...</td>\n",
       "      <td>0</td>\n",
       "      <td>4.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...</td>\n",
       "      <td>0</td>\n",
       "      <td>6.85</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              smiles  pH_range  logP\n",
       "0          C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C         1  4.53\n",
       "1                C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C         0  2.28\n",
       "2    C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC         0  3.72\n",
       "3  C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...         0  4.93\n",
       "4  C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...         0  6.85"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_range_unique_dataset = logp_pH_range_dataset.groupby(['smiles', 'pH_range']).mean().reset_index()\n",
    "logp_pH_range_unique_dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1504, 3)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_range_unique_dataset.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    677\n",
       "0    594\n",
       "2    233\n",
       "Name: pH_range, dtype: int64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_range_unique_dataset.pH_range.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1aadbfd39e8>"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(logp_pH_range_unique_dataset[logp_pH_range_unique_dataset.pH_range == 0].logP, color='g')\n",
    "sns.distplot(logp_pH_range_unique_dataset[logp_pH_range_unique_dataset.pH_range == 1].logP, color='b')\n",
    "sns.distplot(logp_pH_range_unique_dataset[logp_pH_range_unique_dataset.pH_range == 2].logP, color='r')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>smiles</th>\n",
       "      <th>pH</th>\n",
       "      <th>logP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C</td>\n",
       "      <td>7.5</td>\n",
       "      <td>4.53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6.85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2383</th>\n",
       "      <td>c1ccc2c(c1)OCCOCCOCCO2</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2384</th>\n",
       "      <td>c1ccc2c(c1)[nH]c(=NCCCN1CCN(CCCN=c3[nH]c4ccccc...</td>\n",
       "      <td>7.4</td>\n",
       "      <td>2.52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2385</th>\n",
       "      <td>c1cnc2c(c1)[nH]c(=NCCCN1CCN(CCCN=c3[nH]c4cccnc...</td>\n",
       "      <td>7.4</td>\n",
       "      <td>5.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2386</th>\n",
       "      <td>c1nc(=NC2CCCC2)c2c3c(sc2[nH]1)CCCC3</td>\n",
       "      <td>10.0</td>\n",
       "      <td>4.17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2387</th>\n",
       "      <td>n1onc2c1NC1Nc3nonc3NC1N2</td>\n",
       "      <td>7.3</td>\n",
       "      <td>0.30</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2388 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 smiles    pH  logP\n",
       "0             C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C   7.5  4.53\n",
       "1                   C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C   5.0  2.28\n",
       "2       C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC   5.0  3.72\n",
       "3     C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...   5.0  4.93\n",
       "4     C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...   5.0  6.85\n",
       "...                                                 ...   ...   ...\n",
       "2383                             c1ccc2c(c1)OCCOCCOCCO2   5.0  1.81\n",
       "2384  c1ccc2c(c1)[nH]c(=NCCCN1CCN(CCCN=c3[nH]c4ccccc...   7.4  2.52\n",
       "2385  c1cnc2c(c1)[nH]c(=NCCCN1CCN(CCCN=c3[nH]c4cccnc...   7.4  5.05\n",
       "2386                c1nc(=NC2CCCC2)c2c3c(sc2[nH]1)CCCC3  10.0  4.17\n",
       "2387                           n1onc2c1NC1Nc3nonc3NC1N2   7.3  0.30\n",
       "\n",
       "[2388 rows x 3 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_unique_dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "logp_pH_unique_dataset.to_csv(\"../data/3_final_data/logp_pH_mean.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "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>smiles</th>\n",
       "      <th>pH_range</th>\n",
       "      <th>logP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C</td>\n",
       "      <td>1</td>\n",
       "      <td>4.53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C</td>\n",
       "      <td>0</td>\n",
       "      <td>2.28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC</td>\n",
       "      <td>0</td>\n",
       "      <td>3.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...</td>\n",
       "      <td>0</td>\n",
       "      <td>4.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...</td>\n",
       "      <td>0</td>\n",
       "      <td>6.85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1499</th>\n",
       "      <td>c1ccc2c(c1)OCCOCCOCCO2</td>\n",
       "      <td>0</td>\n",
       "      <td>1.81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1500</th>\n",
       "      <td>c1ccc2c(c1)[nH]c(=NCCCN1CCN(CCCN=c3[nH]c4ccccc...</td>\n",
       "      <td>1</td>\n",
       "      <td>2.52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1501</th>\n",
       "      <td>c1cnc2c(c1)[nH]c(=NCCCN1CCN(CCCN=c3[nH]c4cccnc...</td>\n",
       "      <td>1</td>\n",
       "      <td>5.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1502</th>\n",
       "      <td>c1nc(=NC2CCCC2)c2c3c(sc2[nH]1)CCCC3</td>\n",
       "      <td>2</td>\n",
       "      <td>4.17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1503</th>\n",
       "      <td>n1onc2c1NC1Nc3nonc3NC1N2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.30</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1504 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 smiles  pH_range  logP\n",
       "0             C#CC1(O)CCC2C3CCC4=Cc5oncc5CC4(C)C3CCC21C         1  4.53\n",
       "1                   C#CCN1C(=O)C2CC[C@@](C)(C1=O)C2(C)C         0  2.28\n",
       "2       C#CCOc1c(I)cc(C=C2C(=O)N(C)C(=S)N(C)C2=O)cc1OCC         0  3.72\n",
       "3     C#CCOc1ccc(C2C3=C(CC(C)(C)CC3=O)OC3=C2C(=O)CC(...         0  4.93\n",
       "4     C#Cc1cccc(NC(=O)c2cc(C(=O)Nc3cccc(C#C)c3)cc(N3...         0  6.85\n",
       "...                                                 ...       ...   ...\n",
       "1499                             c1ccc2c(c1)OCCOCCOCCO2         0  1.81\n",
       "1500  c1ccc2c(c1)[nH]c(=NCCCN1CCN(CCCN=c3[nH]c4ccccc...         1  2.52\n",
       "1501  c1cnc2c(c1)[nH]c(=NCCCN1CCN(CCCN=c3[nH]c4cccnc...         1  5.05\n",
       "1502                c1nc(=NC2CCCC2)c2c3c(sc2[nH]1)CCCC3         2  4.17\n",
       "1503                           n1onc2c1NC1Nc3nonc3NC1N2         1  0.30\n",
       "\n",
       "[1504 rows x 3 columns]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logp_pH_range_unique_dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "logp_pH_range_unique_dataset.to_csv(\"../data/3_final_data/logp_pH_range_mean.csv\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "chemvae",
   "language": "python",
   "name": "chemvae"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}