{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Best Fingerprint Parameters\n",
    "\n",
    "This notebook is used to identify the best parameters for encoding PROTAC SMILES as Morgan fingerprints.\n",
    "\n",
    "It uses Optuna to optimize the parameters."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import sys\n",
    "from collections import defaultdict\n",
    "import warnings\n",
    "import logging\n",
    "from typing import Literal\n",
    "\n",
    "sys.path.append('~/PROTAC-Degradation-Predictor/protac_degradation_predictor')\n",
    "import protac_degradation_predictor as pdp\n",
    "\n",
    "import pytorch_lightning as pl\n",
    "from rdkit import Chem\n",
    "from rdkit.Chem import AllChem\n",
    "from rdkit import DataStructs\n",
    "from jsonargparse import CLI\n",
    "import pandas as pd\n",
    "# Import tqdm for notebook\n",
    "from tqdm.notebook import tqdm\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import OrdinalEncoder\n",
    "from sklearn.model_selection import (\n",
    "    StratifiedKFold,\n",
    "    StratifiedGroupKFold,\n",
    ")\n",
    "\n",
    "\n",
    "active_col = 'Active (Dmax 0.6, pDC50 6.0)'\n",
    "pDC50_threshold = 6.0\n",
    "Dmax_threshold = 0.6\n",
    "\n",
    "protac_df = pd.read_csv('~/PROTAC-Degradation-Predictor/data/PROTAC-Degradation-DB.csv')\n",
    "protac_df['E3 Ligase'] = protac_df['E3 Ligase'].str.replace('Iap', 'IAP')\n",
    "protac_df[active_col] = protac_df.apply(\n",
    "    lambda x: pdp.is_active(x['DC50 (nM)'], x['Dmax (%)'], pDC50_threshold=pDC50_threshold, Dmax_threshold=Dmax_threshold), axis=1\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "771"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def get_random_split_indices(active_df: pd.DataFrame, test_split: float) -> pd.Index:\n",
    "    \"\"\" Get the indices of the test set using a random split.\n",
    "    \n",
    "    Args:\n",
    "        active_df (pd.DataFrame): The DataFrame containing the active PROTACs.\n",
    "        test_split (float): The percentage of the active PROTACs to use as the test set.\n",
    "    \n",
    "    Returns:\n",
    "        pd.Index: The indices of the test set.\n",
    "    \"\"\"\n",
    "    test_df = active_df.sample(frac=test_split, random_state=42)\n",
    "    return test_df.index\n",
    "\n",
    "protac_df['pDC50'] = -np.log10(protac_df['DC50 (nM)'] * 1e-9)\n",
    "active_df = protac_df[protac_df[active_col].notna()].copy()\n",
    "test_split = 0.1\n",
    "test_indices = get_random_split_indices(active_df, test_split)\n",
    "train_val_df = active_df[~active_df.index.isin(test_indices)].copy()\n",
    "len(train_val_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6.935675466781487"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get the mean of pDC50 for the active PROTACs\n",
    "mean_pDC50 = active_df['pDC50'].mean()\n",
    "mean_pDC50"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Compound ID', 'Uniprot', 'Smiles', 'E3 Ligase', 'InChI', 'InChI Key',\n",
       "       'Molecular Weight', 'Heavy Atom Count', 'Ring Count',\n",
       "       'Rotatable Bond Count', 'Topological Polar Surface Area',\n",
       "       'Hydrogen Bond Acceptor Count', 'Hydrogen Bond Donor Count',\n",
       "       'Cell Type', 'Treatment Time (h)', 'DC50 (nM)', 'Dmax (%)', 'Active',\n",
       "       'Article DOI', 'Comments', 'Database', 'Molecular Formula', 'cLogP',\n",
       "       'Target', 'PDB', 'Name', 'Assay (DC50/Dmax)', 'Exact Mass', 'XLogP3',\n",
       "       'Target (Parsed)', 'POI Sequence', 'E3 Ligase Uniprot',\n",
       "       'E3 Ligase Sequence', 'Cell Line Identifier', 'Active - OR',\n",
       "       'Active (Dmax 0.6, pDC50 6.0)', 'pDC50'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_val_df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>69</th>\n",
       "      <td>C=CC(=O)Nc1cccc(-n2c(=O)cc(C)c3cnc(Nc4ccc(N5CC...</td>\n",
       "      <td>H1975/WR</td>\n",
       "      <td>True</td>\n",
       "      <td>5.9</td>\n",
       "      <td>100.0</td>\n",
       "      <td>P00533</td>\n",
       "      <td>VHL</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.1016/j.ejmech.2020.112199</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1229</th>\n",
       "      <td>C=CC(=O)Nc1cccc(-n2c(=O)cc(C)c3cnc(Nc4ccc(N5CC...</td>\n",
       "      <td>A431 siYAP</td>\n",
       "      <td>False</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>P00533</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of EGFR in A431 cells after 16 h t...</td>\n",
       "      <td>10.1016/j.ejmech.2020.112199</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "69    C=CC(=O)Nc1cccc(-n2c(=O)cc(C)c3cnc(Nc4ccc(N5CC...             H1975/WR   \n",
       "1229  C=CC(=O)Nc1cccc(-n2c(=O)cc(C)c3cnc(Nc4ccc(N5CC...           A431 siYAP   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "69                           True        5.9     100.0  P00533       VHL   \n",
       "1229                        False     2000.0       NaN  P00533       VHL   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "69                                                  NaN   \n",
       "1229  Degradation of EGFR in A431 cells after 16 h t...   \n",
       "\n",
       "                       Article DOI  \n",
       "69    10.1016/j.ejmech.2020.112199  \n",
       "1229  10.1016/j.ejmech.2020.112199  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & C=CC(=O)Nc1cccc(-n2c(=O)cc(C)c3cnc(Nc4ccc(N5CCN... &             H1975/WR &                         True & 8.229148 &     100.0 &  P00533 &       VHL &                                                NaN & 10.1016/j.ejmech.2020.112199 \\\\\n",
      " NaN & C=CC(=O)Nc1cccc(-n2c(=O)cc(C)c3cnc(Nc4ccc(N5CCN... &           A431 siYAP &                        False & 5.698970 &       NaN &  P00533 &       VHL & Degradation of EGFR in A431 cells after 16 h tr... & 10.1016/j.ejmech.2020.112199 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1793</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>COLO 205</td>\n",
       "      <td>True</td>\n",
       "      <td>30.28</td>\n",
       "      <td>64.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1794</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>HCT 116</td>\n",
       "      <td>False</td>\n",
       "      <td>1000.00</td>\n",
       "      <td>28.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1793  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...             COLO 205   \n",
       "1794  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...              HCT 116   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1793                         True      30.28      64.0  P33981      CRBN   \n",
       "1794                        False    1000.00      28.0  P33981      CRBN   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1793  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "1794  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "\n",
       "                       Article DOI  \n",
       "1793  10.1021/acs.jmedchem.1c01768  \n",
       "1794  10.1021/acs.jmedchem.1c01768  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &             COLO 205 &                         True & 7.518844 &      64.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &              HCT 116 &                        False & 6.000000 &      28.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1795</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>COLO 205</td>\n",
       "      <td>True</td>\n",
       "      <td>31.35</td>\n",
       "      <td>72.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1796</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>HCT 116</td>\n",
       "      <td>False</td>\n",
       "      <td>1000.00</td>\n",
       "      <td>41.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1795  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...             COLO 205   \n",
       "1796  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...              HCT 116   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1795                         True      31.35      72.0  P33981      CRBN   \n",
       "1796                        False    1000.00      41.0  P33981      CRBN   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1795  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "1796  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "\n",
       "                       Article DOI  \n",
       "1795  10.1021/acs.jmedchem.1c01768  \n",
       "1796  10.1021/acs.jmedchem.1c01768  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &             COLO 205 &                         True & 7.503762 &      72.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &              HCT 116 &                        False & 6.000000 &      41.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1771</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>COLO 205</td>\n",
       "      <td>True</td>\n",
       "      <td>4.97</td>\n",
       "      <td>76.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1772</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>HCT 116</td>\n",
       "      <td>False</td>\n",
       "      <td>20.30</td>\n",
       "      <td>50.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1771  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...             COLO 205   \n",
       "1772  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...              HCT 116   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1771                         True       4.97      76.0  P33981      CRBN   \n",
       "1772                        False      20.30      50.0  P33981      CRBN   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1771  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "1772  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "\n",
       "                       Article DOI  \n",
       "1771  10.1021/acs.jmedchem.1c01768  \n",
       "1772  10.1021/acs.jmedchem.1c01768  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &             COLO 205 &                         True & 8.303644 &      76.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &              HCT 116 &                        False & 7.692504 &      50.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1789</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>COLO 205</td>\n",
       "      <td>True</td>\n",
       "      <td>7.03</td>\n",
       "      <td>84.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1790</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>HCT 116</td>\n",
       "      <td>False</td>\n",
       "      <td>161.00</td>\n",
       "      <td>43.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1789  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...             COLO 205   \n",
       "1790  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...              HCT 116   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1789                         True       7.03      84.0  P33981      CRBN   \n",
       "1790                        False     161.00      43.0  P33981      CRBN   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1789  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "1790  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "\n",
       "                       Article DOI  \n",
       "1789  10.1021/acs.jmedchem.1c01768  \n",
       "1790  10.1021/acs.jmedchem.1c01768  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &             COLO 205 &                         True & 8.153045 &      84.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &              HCT 116 &                        False & 6.793174 &      43.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1781</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>COLO 205</td>\n",
       "      <td>True</td>\n",
       "      <td>3.04</td>\n",
       "      <td>85.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1782</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>HCT 116</td>\n",
       "      <td>False</td>\n",
       "      <td>663.00</td>\n",
       "      <td>50.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1781  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...             COLO 205   \n",
       "1782  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...              HCT 116   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1781                         True       3.04      85.0  P33981      CRBN   \n",
       "1782                        False     663.00      50.0  P33981      CRBN   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1781  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "1782  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "\n",
       "                       Article DOI  \n",
       "1781  10.1021/acs.jmedchem.1c01768  \n",
       "1782  10.1021/acs.jmedchem.1c01768  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &             COLO 205 &                         True & 8.517126 &      85.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &              HCT 116 &                        False & 6.178486 &      50.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1799</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>COLO 205</td>\n",
       "      <td>True</td>\n",
       "      <td>21.71</td>\n",
       "      <td>88.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1800</th>\n",
       "      <td>CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...</td>\n",
       "      <td>HCT 116</td>\n",
       "      <td>False</td>\n",
       "      <td>1000.00</td>\n",
       "      <td>13.0</td>\n",
       "      <td>P33981</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of TTK in COLO-205/HCT-116 cells a...</td>\n",
       "      <td>10.1021/acs.jmedchem.1c01768</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1799  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...             COLO 205   \n",
       "1800  CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4cc...              HCT 116   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1799                         True      21.71      88.0  P33981      CRBN   \n",
       "1800                        False    1000.00      13.0  P33981      CRBN   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1799  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "1800  Degradation of TTK in COLO-205/HCT-116 cells a...   \n",
       "\n",
       "                       Article DOI  \n",
       "1799  10.1021/acs.jmedchem.1c01768  \n",
       "1800  10.1021/acs.jmedchem.1c01768  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &   pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &             COLO 205 &                         True & 7.66334 &      88.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      " NaN & CCC(=O)N[C@H]1CC[C@@H](n2c(=O)cc(C)c3cnc(Nc4ccc... &              HCT 116 &                        False & 6.00000 &      13.0 &  P33981 &      CRBN & Degradation of TTK in COLO-205/HCT-116 cells af... & 10.1021/acs.jmedchem.1c01768 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>516</th>\n",
       "      <td>COc1cc(-c2cn(C)c(=O)c3cnccc23)cc(OC)c1CN1CCN(C...</td>\n",
       "      <td>IH-1</td>\n",
       "      <td>False</td>\n",
       "      <td>560.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>Q9H8M2</td>\n",
       "      <td>VHL</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01413</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>925</th>\n",
       "      <td>COc1cc(-c2cn(C)c(=O)c3cnccc23)cc(OC)c1CN1CCN(C...</td>\n",
       "      <td>HeLa</td>\n",
       "      <td>True</td>\n",
       "      <td>560.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>Q9H8M2</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of BRD9 in HeLa cells after 4 h tr...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01413</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                Smiles Cell Line Identifier  \\\n",
       "516  COc1cc(-c2cn(C)c(=O)c3cnccc23)cc(OC)c1CN1CCN(C...                 IH-1   \n",
       "925  COc1cc(-c2cn(C)c(=O)c3cnccc23)cc(OC)c1CN1CCN(C...                 HeLa   \n",
       "\n",
       "    Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "516                        False      560.0      10.0  Q9H8M2       VHL   \n",
       "925                         True      560.0      80.0  Q9H8M2       VHL   \n",
       "\n",
       "                                     Assay (DC50/Dmax)  \\\n",
       "516                                                NaN   \n",
       "925  Degradation of BRD9 in HeLa cells after 4 h tr...   \n",
       "\n",
       "                      Article DOI  \n",
       "516  10.1021/acs.jmedchem.8b01413  \n",
       "925  10.1021/acs.jmedchem.8b01413  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & COc1cc(-c2cn(C)c(=O)c3cnccc23)cc(OC)c1CN1CCN(CC... &                 IH-1 &                        False & 6.251812 &      10.0 &  Q9H8M2 &       VHL &                                                NaN & 10.1021/acs.jmedchem.8b01413 \\\\\n",
      " NaN & COc1cc(-c2cn(C)c(=O)c3cnccc23)cc(OC)c1CN1CCN(CC... &                 HeLa &                         True & 6.251812 &      80.0 &  Q9H8M2 &       VHL & Degradation of BRD9 in HeLa cells after 4 h tre... & 10.1021/acs.jmedchem.8b01413 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1557</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>A549 Cas9</td>\n",
       "      <td>True</td>\n",
       "      <td>243.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1558</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "      <td>631.0</td>\n",
       "      <td>59.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1559</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>SNU-387</td>\n",
       "      <td>True</td>\n",
       "      <td>32.0</td>\n",
       "      <td>98.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1560</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>HLE</td>\n",
       "      <td>True</td>\n",
       "      <td>25.0</td>\n",
       "      <td>85.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in HLE/HuH-7/SNU-423 cells ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1561</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>Huh-7</td>\n",
       "      <td>True</td>\n",
       "      <td>100.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in HLE/HuH-7/SNU-423 cells ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1562</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>SNU-423</td>\n",
       "      <td>True</td>\n",
       "      <td>79.0</td>\n",
       "      <td>87.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in HLE/HuH-7/SNU-423 cells ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1563</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>HLF</td>\n",
       "      <td>True</td>\n",
       "      <td>40.0</td>\n",
       "      <td>66.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in HLF/SNU-398/HUCCT1 cells...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1564</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>SNU-398</td>\n",
       "      <td>True</td>\n",
       "      <td>10.0</td>\n",
       "      <td>99.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in HLF/SNU-398/HUCCT1 cells...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1565</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>HuCC-T1-G10</td>\n",
       "      <td>True</td>\n",
       "      <td>126.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in HLF/SNU-398/HUCCT1 cells...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1566</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>HuH-1</td>\n",
       "      <td>True</td>\n",
       "      <td>79.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1567</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>HepG2 hALR</td>\n",
       "      <td>True</td>\n",
       "      <td>631.0</td>\n",
       "      <td>65.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1568</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...</td>\n",
       "      <td>SK-HEP-1</td>\n",
       "      <td>True</td>\n",
       "      <td>126.0</td>\n",
       "      <td>87.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1557  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...            A549 Cas9   \n",
       "1558  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...                  NaN   \n",
       "1559  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...              SNU-387   \n",
       "1560  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...                  HLE   \n",
       "1561  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...                Huh-7   \n",
       "1562  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...              SNU-423   \n",
       "1563  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...                  HLF   \n",
       "1564  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...              SNU-398   \n",
       "1565  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...          HuCC-T1-G10   \n",
       "1566  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...                HuH-1   \n",
       "1567  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...           HepG2 hALR   \n",
       "1568  COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@...             SK-HEP-1   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1557                         True      243.0      80.0  Q05397       VHL   \n",
       "1558                        False      631.0      59.0  Q05397       VHL   \n",
       "1559                         True       32.0      98.0  Q05397       VHL   \n",
       "1560                         True       25.0      85.0  Q05397       VHL   \n",
       "1561                         True      100.0      79.0  Q05397       VHL   \n",
       "1562                         True       79.0      87.0  Q05397       VHL   \n",
       "1563                         True       40.0      66.0  Q05397       VHL   \n",
       "1564                         True       10.0      99.0  Q05397       VHL   \n",
       "1565                         True      126.0      86.0  Q05397       VHL   \n",
       "1566                         True       79.0      79.0  Q05397       VHL   \n",
       "1567                         True      631.0      65.0  Q05397       VHL   \n",
       "1568                         True      126.0      87.0  Q05397       VHL   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1557  Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...   \n",
       "1558  Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...   \n",
       "1559  Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...   \n",
       "1560  Degradation of Fak in HLE/HuH-7/SNU-423 cells ...   \n",
       "1561  Degradation of Fak in HLE/HuH-7/SNU-423 cells ...   \n",
       "1562  Degradation of Fak in HLE/HuH-7/SNU-423 cells ...   \n",
       "1563  Degradation of Fak in HLF/SNU-398/HUCCT1 cells...   \n",
       "1564  Degradation of Fak in HLF/SNU-398/HUCCT1 cells...   \n",
       "1565  Degradation of Fak in HLF/SNU-398/HUCCT1 cells...   \n",
       "1566  Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...   \n",
       "1567  Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...   \n",
       "1568  Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...   \n",
       "\n",
       "                       Article DOI  \n",
       "1557  10.1021/acs.jmedchem.8b01826  \n",
       "1558  10.1021/acs.jmedchem.8b01826  \n",
       "1559  10.1021/acs.jmedchem.8b01826  \n",
       "1560  10.1021/acs.jmedchem.8b01826  \n",
       "1561  10.1021/acs.jmedchem.8b01826  \n",
       "1562  10.1021/acs.jmedchem.8b01826  \n",
       "1563  10.1021/acs.jmedchem.8b01826  \n",
       "1564  10.1021/acs.jmedchem.8b01826  \n",
       "1565  10.1021/acs.jmedchem.8b01826  \n",
       "1566  10.1021/acs.jmedchem.8b01826  \n",
       "1567  10.1021/acs.jmedchem.8b01826  \n",
       "1568  10.1021/acs.jmedchem.8b01826  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "   Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &            A549 Cas9 &                         True & 6.614394 &      80.0 &  Q05397 &       VHL & Degradation of Fak in A549/Hep3B2.1-7/SNU-387 c... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &                  NaN &                        False & 6.199971 &      59.0 &  Q05397 &       VHL & Degradation of Fak in A549/Hep3B2.1-7/SNU-387 c... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &              SNU-387 &                         True & 7.494850 &      98.0 &  Q05397 &       VHL & Degradation of Fak in A549/Hep3B2.1-7/SNU-387 c... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &                  HLE &                         True & 7.602060 &      85.0 &  Q05397 &       VHL & Degradation of Fak in HLE/HuH-7/SNU-423 cells a... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &                Huh-7 &                         True & 7.000000 &      79.0 &  Q05397 &       VHL & Degradation of Fak in HLE/HuH-7/SNU-423 cells a... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &              SNU-423 &                         True & 7.102373 &      87.0 &  Q05397 &       VHL & Degradation of Fak in HLE/HuH-7/SNU-423 cells a... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &                  HLF &                         True & 7.397940 &      66.0 &  Q05397 &       VHL & Degradation of Fak in HLF/SNU-398/HUCCT1 cells ... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &              SNU-398 &                         True & 8.000000 &      99.0 &  Q05397 &       VHL & Degradation of Fak in HLF/SNU-398/HUCCT1 cells ... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &          HuCC-T1-G10 &                         True & 6.899629 &      86.0 &  Q05397 &       VHL & Degradation of Fak in HLF/SNU-398/HUCCT1 cells ... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &                HuH-1 &                         True & 7.102373 &      79.0 &  Q05397 &       VHL & Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cell... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &           HepG2 hALR &                         True & 6.199971 &      65.0 &  Q05397 &       VHL & Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cell... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-0319 & COc1cc(C(=O)NCCOCCOCCOCC(=O)N[C@H](C(=O)N2C[C@H... &             SK-HEP-1 &                         True & 6.899629 &      87.0 &  Q05397 &       VHL & Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cell... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1545</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>HLE</td>\n",
       "      <td>True</td>\n",
       "      <td>158.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in HLE/HuH-7/SNU-423 cells ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1546</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>Huh-7</td>\n",
       "      <td>True</td>\n",
       "      <td>50.0</td>\n",
       "      <td>93.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in HLE/HuH-7/SNU-423 cells ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1547</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>SNU-423</td>\n",
       "      <td>True</td>\n",
       "      <td>13.0</td>\n",
       "      <td>93.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in HLE/HuH-7/SNU-423 cells ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1548</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>HuH-1</td>\n",
       "      <td>False</td>\n",
       "      <td>251.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1549</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>HepG2 hALR</td>\n",
       "      <td>True</td>\n",
       "      <td>32.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1550</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>SK-HEP-1</td>\n",
       "      <td>True</td>\n",
       "      <td>32.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1551</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>A549 Cas9</td>\n",
       "      <td>True</td>\n",
       "      <td>27.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1552</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "      <td>13.0</td>\n",
       "      <td>96.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1553</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>SNU-387</td>\n",
       "      <td>True</td>\n",
       "      <td>25.0</td>\n",
       "      <td>90.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1555</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>SNU-398</td>\n",
       "      <td>True</td>\n",
       "      <td>3.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in HLF/SNU-398/HUCCT1 cells...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1556</th>\n",
       "      <td>COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...</td>\n",
       "      <td>HuCC-T1-G10</td>\n",
       "      <td>True</td>\n",
       "      <td>13.0</td>\n",
       "      <td>90.0</td>\n",
       "      <td>Q05397</td>\n",
       "      <td>CRBN</td>\n",
       "      <td>Degradation of Fak in HLF/SNU-398/HUCCT1 cells...</td>\n",
       "      <td>10.1021/acs.jmedchem.8b01826</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1545  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...                  HLE   \n",
       "1546  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...                Huh-7   \n",
       "1547  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...              SNU-423   \n",
       "1548  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...                HuH-1   \n",
       "1549  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...           HepG2 hALR   \n",
       "1550  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...             SK-HEP-1   \n",
       "1551  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...            A549 Cas9   \n",
       "1552  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...                  NaN   \n",
       "1553  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...              SNU-387   \n",
       "1555  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...              SNU-398   \n",
       "1556  COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(...          HuCC-T1-G10   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1545                         True      158.0      79.0  Q05397      CRBN   \n",
       "1546                         True       50.0      93.0  Q05397      CRBN   \n",
       "1547                         True       13.0      93.0  Q05397      CRBN   \n",
       "1548                        False      251.0      50.0  Q05397      CRBN   \n",
       "1549                         True       32.0      89.0  Q05397      CRBN   \n",
       "1550                         True       32.0      89.0  Q05397      CRBN   \n",
       "1551                         True       27.0      95.0  Q05397      CRBN   \n",
       "1552                         True       13.0      96.0  Q05397      CRBN   \n",
       "1553                         True       25.0      90.0  Q05397      CRBN   \n",
       "1555                         True        3.0      95.0  Q05397      CRBN   \n",
       "1556                         True       13.0      90.0  Q05397      CRBN   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1545  Degradation of Fak in HLE/HuH-7/SNU-423 cells ...   \n",
       "1546  Degradation of Fak in HLE/HuH-7/SNU-423 cells ...   \n",
       "1547  Degradation of Fak in HLE/HuH-7/SNU-423 cells ...   \n",
       "1548  Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...   \n",
       "1549  Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...   \n",
       "1550  Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...   \n",
       "1551  Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...   \n",
       "1552  Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...   \n",
       "1553  Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...   \n",
       "1555  Degradation of Fak in HLF/SNU-398/HUCCT1 cells...   \n",
       "1556  Degradation of Fak in HLF/SNU-398/HUCCT1 cells...   \n",
       "\n",
       "                       Article DOI  \n",
       "1545  10.1021/acs.jmedchem.8b01826  \n",
       "1546  10.1021/acs.jmedchem.8b01826  \n",
       "1547  10.1021/acs.jmedchem.8b01826  \n",
       "1548  10.1021/acs.jmedchem.8b01826  \n",
       "1549  10.1021/acs.jmedchem.8b01826  \n",
       "1550  10.1021/acs.jmedchem.8b01826  \n",
       "1551  10.1021/acs.jmedchem.8b01826  \n",
       "1552  10.1021/acs.jmedchem.8b01826  \n",
       "1553  10.1021/acs.jmedchem.8b01826  \n",
       "1555  10.1021/acs.jmedchem.8b01826  \n",
       "1556  10.1021/acs.jmedchem.8b01826  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "   Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &                  HLE &                         True & 6.801343 &      79.0 &  Q05397 &      CRBN & Degradation of Fak in HLE/HuH-7/SNU-423 cells a... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &                Huh-7 &                         True & 7.301030 &      93.0 &  Q05397 &      CRBN & Degradation of Fak in HLE/HuH-7/SNU-423 cells a... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &              SNU-423 &                         True & 7.886057 &      93.0 &  Q05397 &      CRBN & Degradation of Fak in HLE/HuH-7/SNU-423 cells a... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &                HuH-1 &                        False & 6.600326 &      50.0 &  Q05397 &      CRBN & Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cell... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &           HepG2 hALR &                         True & 7.494850 &      89.0 &  Q05397 &      CRBN & Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cell... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &             SK-HEP-1 &                         True & 7.494850 &      89.0 &  Q05397 &      CRBN & Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cell... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &            A549 Cas9 &                         True & 7.568636 &      95.0 &  Q05397 &      CRBN & Degradation of Fak in A549/Hep3B2.1-7/SNU-387 c... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &                  NaN &                         True & 7.886057 &      96.0 &  Q05397 &      CRBN & Degradation of Fak in A549/Hep3B2.1-7/SNU-387 c... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &              SNU-387 &                         True & 7.602060 &      90.0 &  Q05397 &      CRBN & Degradation of Fak in A549/Hep3B2.1-7/SNU-387 c... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &              SNU-398 &                         True & 8.522879 &      95.0 &  Q05397 &      CRBN & Degradation of Fak in HLF/SNU-398/HUCCT1 cells ... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "BI-3663 & COc1cc(C(=O)NCCOCCOCCOCCC(=O)Nc2cccc3c2C(=O)N(C... &          HuCC-T1-G10 &                         True & 7.886057 &      90.0 &  Q05397 &      CRBN & Degradation of Fak in HLF/SNU-398/HUCCT1 cells ... & 10.1021/acs.jmedchem.8b01826 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1294</th>\n",
       "      <td>Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...</td>\n",
       "      <td>HeLa</td>\n",
       "      <td>True</td>\n",
       "      <td>790.0</td>\n",
       "      <td>92.0</td>\n",
       "      <td>O75530</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of EED in HeLa/DB cells after 24 h...</td>\n",
       "      <td>10.1016/j.chembiol.2019.11.006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1296</th>\n",
       "      <td>Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...</td>\n",
       "      <td>HeLa</td>\n",
       "      <td>True</td>\n",
       "      <td>300.0</td>\n",
       "      <td>75.0</td>\n",
       "      <td>Q15910</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of EZH2 in HeLa/DB cells after 24 ...</td>\n",
       "      <td>10.1016/j.chembiol.2019.11.006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1297</th>\n",
       "      <td>Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...</td>\n",
       "      <td>DB</td>\n",
       "      <td>True</td>\n",
       "      <td>670.0</td>\n",
       "      <td>96.0</td>\n",
       "      <td>Q15910</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of EZH2 in HeLa/DB cells after 24 ...</td>\n",
       "      <td>10.1016/j.chembiol.2019.11.006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1298</th>\n",
       "      <td>Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...</td>\n",
       "      <td>HeLa</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>22.0</td>\n",
       "      <td>Q15022</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of SUZ12 in HeLa/DB cells after 24...</td>\n",
       "      <td>10.1016/j.chembiol.2019.11.006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1299</th>\n",
       "      <td>Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...</td>\n",
       "      <td>DB</td>\n",
       "      <td>True</td>\n",
       "      <td>590.0</td>\n",
       "      <td>82.0</td>\n",
       "      <td>Q15022</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of SUZ12 in HeLa/DB cells after 24...</td>\n",
       "      <td>10.1016/j.chembiol.2019.11.006</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1294  Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...                 HeLa   \n",
       "1296  Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...                 HeLa   \n",
       "1297  Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...                   DB   \n",
       "1298  Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...                 HeLa   \n",
       "1299  Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...                   DB   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1294                         True      790.0      92.0  O75530       VHL   \n",
       "1296                         True      300.0      75.0  Q15910       VHL   \n",
       "1297                         True      670.0      96.0  Q15910       VHL   \n",
       "1298                        False        NaN      22.0  Q15022       VHL   \n",
       "1299                         True      590.0      82.0  Q15022       VHL   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1294  Degradation of EED in HeLa/DB cells after 24 h...   \n",
       "1296  Degradation of EZH2 in HeLa/DB cells after 24 ...   \n",
       "1297  Degradation of EZH2 in HeLa/DB cells after 24 ...   \n",
       "1298  Degradation of SUZ12 in HeLa/DB cells after 24...   \n",
       "1299  Degradation of SUZ12 in HeLa/DB cells after 24...   \n",
       "\n",
       "                         Article DOI  \n",
       "1294  10.1016/j.chembiol.2019.11.006  \n",
       "1296  10.1016/j.chembiol.2019.11.006  \n",
       "1297  10.1016/j.chembiol.2019.11.006  \n",
       "1298  10.1016/j.chembiol.2019.11.006  \n",
       "1299  10.1016/j.chembiol.2019.11.006  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "   Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                    Article DOI \\\\\n",
      "\\midrule\n",
      "UNC6852 & Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O)... &                 HeLa &                         True & 6.102373 &      92.0 &  O75530 &       VHL & Degradation of EED in HeLa/DB cells after 24 h ... & 10.1016/j.chembiol.2019.11.006 \\\\\n",
      "UNC6852 & Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O)... &                 HeLa &                         True & 6.522879 &      75.0 &  Q15910 &       VHL & Degradation of EZH2 in HeLa/DB cells after 24 h... & 10.1016/j.chembiol.2019.11.006 \\\\\n",
      "UNC6852 & Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O)... &                   DB &                         True & 6.173925 &      96.0 &  Q15910 &       VHL & Degradation of EZH2 in HeLa/DB cells after 24 h... & 10.1016/j.chembiol.2019.11.006 \\\\\n",
      "UNC6852 & Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O)... &                 HeLa &                        False &      NaN &      22.0 &  Q15022 &       VHL & Degradation of SUZ12 in HeLa/DB cells after 24 ... & 10.1016/j.chembiol.2019.11.006 \\\\\n",
      "UNC6852 & Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O)... &                   DB &                         True & 6.229148 &      82.0 &  Q15022 &       VHL & Degradation of SUZ12 in HeLa/DB cells after 24 ... & 10.1016/j.chembiol.2019.11.006 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1435</th>\n",
       "      <td>Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...</td>\n",
       "      <td>LNCaP</td>\n",
       "      <td>True</td>\n",
       "      <td>50.0</td>\n",
       "      <td>71.0</td>\n",
       "      <td>P10275</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of AR in LNCaP/VCaP cells after 2-...</td>\n",
       "      <td>10.1021/acsmedchemlett.9b00115</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1436</th>\n",
       "      <td>Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...</td>\n",
       "      <td>VCaP</td>\n",
       "      <td>False</td>\n",
       "      <td>50.0</td>\n",
       "      <td>51.0</td>\n",
       "      <td>P10275</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of AR in LNCaP/VCaP cells after 2-...</td>\n",
       "      <td>10.1021/acsmedchemlett.9b00115</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1435  Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...                LNCaP   \n",
       "1436  Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O...                 VCaP   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1435                         True       50.0      71.0  P10275       VHL   \n",
       "1436                        False       50.0      51.0  P10275       VHL   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1435  Degradation of AR in LNCaP/VCaP cells after 2-...   \n",
       "1436  Degradation of AR in LNCaP/VCaP cells after 2-...   \n",
       "\n",
       "                         Article DOI  \n",
       "1435  10.1021/acsmedchemlett.9b00115  \n",
       "1436  10.1021/acsmedchemlett.9b00115  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &   pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                    Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O)... &                LNCaP &                         True & 7.30103 &      71.0 &  P10275 &       VHL & Degradation of AR in LNCaP/VCaP cells after 2-4... & 10.1021/acsmedchemlett.9b00115 \\\\\n",
      " NaN & Cc1ncsc1-c1ccc(CNC(=O)[C@@H]2C[C@@H](O)CN2C(=O)... &                 VCaP &                        False & 7.30103 &      51.0 &  P10275 &       VHL & Degradation of AR in LNCaP/VCaP cells after 2-4... & 10.1021/acsmedchemlett.9b00115 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...</td>\n",
       "      <td>MOLT-4</td>\n",
       "      <td>True</td>\n",
       "      <td>53.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Q07817</td>\n",
       "      <td>VHL</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.1016/j.ejmech.2020.112186</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1245</th>\n",
       "      <td>Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...</td>\n",
       "      <td>MOLT-4</td>\n",
       "      <td>True</td>\n",
       "      <td>63.0</td>\n",
       "      <td>90.8</td>\n",
       "      <td>Q07817</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of BCL-xL in MOLT-4/platelets cell...</td>\n",
       "      <td>10.1038/s41591-019-0668-z</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1246</th>\n",
       "      <td>Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...</td>\n",
       "      <td>2T60</td>\n",
       "      <td>False</td>\n",
       "      <td>3000.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>Q07817</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of BCL-xL in MOLT-4/platelets cell...</td>\n",
       "      <td>10.1038/s41591-019-0668-z</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "4     Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...               MOLT-4   \n",
       "1245  Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...               MOLT-4   \n",
       "1246  Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...                 2T60   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "4                            True       53.0     100.0  Q07817       VHL   \n",
       "1245                         True       63.0      90.8  Q07817       VHL   \n",
       "1246                        False     3000.0      26.0  Q07817       VHL   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "4                                                   NaN   \n",
       "1245  Degradation of BCL-xL in MOLT-4/platelets cell...   \n",
       "1246  Degradation of BCL-xL in MOLT-4/platelets cell...   \n",
       "\n",
       "                       Article DOI  \n",
       "4     10.1016/j.ejmech.2020.112186  \n",
       "1245     10.1038/s41591-019-0668-z  \n",
       "1246     10.1038/s41591-019-0668-z  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "  Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &    pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                  Article DOI \\\\\n",
      "\\midrule\n",
      "   NaN & Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)C... &               MOLT-4 &                         True & 7.275724 &     100.0 &  Q07817 &       VHL &                                                NaN & 10.1016/j.ejmech.2020.112186 \\\\\n",
      "DT2216 & Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)C... &               MOLT-4 &                         True & 7.200659 &      90.8 &  Q07817 &       VHL & Degradation of BCL-xL in MOLT-4/platelets cells... &    10.1038/s41591-019-0668-z \\\\\n",
      "DT2216 & Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)C... &                 2T60 &                        False & 5.522879 &      26.0 &  Q07817 &       VHL & Degradation of BCL-xL in MOLT-4/platelets cells... &    10.1038/s41591-019-0668-z \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1479</th>\n",
       "      <td>Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...</td>\n",
       "      <td>LNCaP</td>\n",
       "      <td>True</td>\n",
       "      <td>50.0</td>\n",
       "      <td>71.0</td>\n",
       "      <td>P10275</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of AR in LNCaP/VCaP cells using EL...</td>\n",
       "      <td>10.1021/acsmedchemlett.0c00236</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1480</th>\n",
       "      <td>Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...</td>\n",
       "      <td>VCaP</td>\n",
       "      <td>False</td>\n",
       "      <td>50.0</td>\n",
       "      <td>51.0</td>\n",
       "      <td>P10275</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of AR in LNCaP/VCaP cells using EL...</td>\n",
       "      <td>10.1021/acsmedchemlett.0c00236</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1479  Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...                LNCaP   \n",
       "1480  Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...                 VCaP   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1479                         True       50.0      71.0  P10275       VHL   \n",
       "1480                        False       50.0      51.0  P10275       VHL   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1479  Degradation of AR in LNCaP/VCaP cells using EL...   \n",
       "1480  Degradation of AR in LNCaP/VCaP cells using EL...   \n",
       "\n",
       "                         Article DOI  \n",
       "1479  10.1021/acsmedchemlett.0c00236  \n",
       "1480  10.1021/acsmedchemlett.0c00236  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &   pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                    Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)C... &                LNCaP &                         True & 7.30103 &      71.0 &  P10275 &       VHL & Degradation of AR in LNCaP/VCaP cells using ELI... & 10.1021/acsmedchemlett.0c00236 \\\\\n",
      " NaN & Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)C... &                 VCaP &                        False & 7.30103 &      51.0 &  P10275 &       VHL & Degradation of AR in LNCaP/VCaP cells using ELI... & 10.1021/acsmedchemlett.0c00236 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    },
    {
     "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>Cell Line Identifier</th>\n",
       "      <th>Active (Dmax 0.6, pDC50 6.0)</th>\n",
       "      <th>DC50 (nM)</th>\n",
       "      <th>Dmax (%)</th>\n",
       "      <th>Uniprot</th>\n",
       "      <th>E3 Ligase</th>\n",
       "      <th>Assay (DC50/Dmax)</th>\n",
       "      <th>Article DOI</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1477</th>\n",
       "      <td>Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...</td>\n",
       "      <td>LNCaP</td>\n",
       "      <td>True</td>\n",
       "      <td>50.0</td>\n",
       "      <td>71.0</td>\n",
       "      <td>P10275</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of AR in LNCaP/VCaP cells using EL...</td>\n",
       "      <td>10.1021/acsmedchemlett.0c00236</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1478</th>\n",
       "      <td>Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...</td>\n",
       "      <td>VCaP</td>\n",
       "      <td>False</td>\n",
       "      <td>50.0</td>\n",
       "      <td>51.0</td>\n",
       "      <td>P10275</td>\n",
       "      <td>VHL</td>\n",
       "      <td>Degradation of AR in LNCaP/VCaP cells using EL...</td>\n",
       "      <td>10.1021/acsmedchemlett.0c00236</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 Smiles Cell Line Identifier  \\\n",
       "1477  Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...                LNCaP   \n",
       "1478  Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)...                 VCaP   \n",
       "\n",
       "     Active (Dmax 0.6, pDC50 6.0)  DC50 (nM)  Dmax (%) Uniprot E3 Ligase  \\\n",
       "1477                         True       50.0      71.0  P10275       VHL   \n",
       "1478                        False       50.0      51.0  P10275       VHL   \n",
       "\n",
       "                                      Assay (DC50/Dmax)  \\\n",
       "1477  Degradation of AR in LNCaP/VCaP cells using EL...   \n",
       "1478  Degradation of AR in LNCaP/VCaP cells using EL...   \n",
       "\n",
       "                         Article DOI  \n",
       "1477  10.1021/acsmedchemlett.0c00236  \n",
       "1478  10.1021/acsmedchemlett.0c00236  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\begin{tabular}{llllrrllll}\n",
      "\\toprule\n",
      "Name &                                             Smiles & Cell Line Identifier & Active (Dmax 0.6, pDC50 6.0) &   pDC50 &  Dmax (\\%) & Uniprot & E3 Ligase &                                  Assay (DC50/Dmax) &                    Article DOI \\\\\n",
      "\\midrule\n",
      " NaN & Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)C... &                LNCaP &                         True & 7.30103 &      71.0 &  P10275 &       VHL & Degradation of AR in LNCaP/VCaP cells using ELI... & 10.1021/acsmedchemlett.0c00236 \\\\\n",
      " NaN & Cc1ncsc1-c1ccc([C@H](C)NC(=O)[C@@H]2C[C@@H](O)C... &                 VCaP &                        False & 7.30103 &      51.0 &  P10275 &       VHL & Degradation of AR in LNCaP/VCaP cells using ELI... & 10.1021/acsmedchemlett.0c00236 \\\\\n",
      "\\bottomrule\n",
      "\\end{tabular}\n",
      "\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3711258/332080580.py:17: FutureWarning: In future versions `DataFrame.to_latex` is expected to utilise the base implementation of `Styler.to_latex` for formatting and rendering. The arguments signature may therefore change. It is recommended instead to use `DataFrame.style.to_latex` which also contains additional functionality.\n",
      "  print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n"
     ]
    }
   ],
   "source": [
    "# Get the entries for which the same SMILES is active for one cell and inactive for another\n",
    "# This is a sign of a potential error in the data\n",
    "# This is a sign of a potential error in the data\n",
    "active_smiles = train_val_df[train_val_df[active_col] == 1]['Smiles']\n",
    "inactive_smiles = train_val_df[train_val_df[active_col] == 0]['Smiles']\n",
    "active_smiles = active_smiles.drop_duplicates()\n",
    "inactive_smiles = inactive_smiles.drop_duplicates()\n",
    "\n",
    "common_smiles = active_smiles[active_smiles.isin(inactive_smiles)]\n",
    "common_df = train_val_df[train_val_df['Smiles'].isin(common_smiles)]\n",
    "\n",
    "# # Group by Smiles and check if the same SMILES is active for one cell and inactive for another\n",
    "# grouped = common_df.groupby('Smiles')\n",
    "# for name, group in grouped:\n",
    "#     if group[active_col].nunique() > 1 and group['Cell Line Identifier'].nunique() > 1:\n",
    "#         display(group[['Smiles', 'Cell Line Identifier', active_col, 'DC50 (nM)', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']])\n",
    "#         print(group[['Name', 'Smiles', 'Cell Line Identifier', active_col, 'pDC50', 'Dmax (%)', 'Uniprot', 'E3 Ligase', 'Assay (DC50/Dmax)', 'Article DOI']].to_latex(index=False))\n",
    "#         print()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "import optuna\n",
    "\n",
    "def objective(trial: optuna.Trial, verbose: int = 0) -> float:\n",
    "    \n",
    "    radius = trial.suggest_int('radius', 1, 15)\n",
    "    fpsize = trial.suggest_int('fpsize', 128, 2048, step=128)\n",
    "\n",
    "    morgan_fpgen = AllChem.GetMorganGenerator(\n",
    "        radius=radius,\n",
    "        fpSize=fpsize,\n",
    "        includeChirality=True,\n",
    "    )\n",
    "\n",
    "    smiles2fp = {}\n",
    "    for smiles in train_val_df['Smiles'].unique().tolist():\n",
    "        smiles2fp[smiles] = pdp.get_fingerprint(smiles, morgan_fpgen)\n",
    "\n",
    "    # Count the number of unique SMILES and the number of unique Morgan fingerprints\n",
    "    unique_fps = set([tuple(fp) for fp in smiles2fp.values()])\n",
    "    # Get the list of SMILES with overlapping fingerprints\n",
    "    overlapping_smiles = []\n",
    "    unique_fps = set()\n",
    "    for smiles, fp in smiles2fp.items():\n",
    "        if tuple(fp) in unique_fps:\n",
    "            overlapping_smiles.append(smiles)\n",
    "        else:\n",
    "            unique_fps.add(tuple(fp))\n",
    "    num_overlaps = len(train_val_df[train_val_df[\"Smiles\"].isin(overlapping_smiles)])\n",
    "    num_overlaps_tot = len(protac_df[protac_df[\"Smiles\"].isin(overlapping_smiles)])\n",
    "\n",
    "    if verbose:\n",
    "        print(f'Radius: {radius}')\n",
    "        print(f'FP length: {fpsize}')\n",
    "        print(f'Number of unique SMILES: {len(smiles2fp)}')\n",
    "        print(f'Number of unique fingerprints: {len(unique_fps)}')\n",
    "        print(f'Number of SMILES with overlapping fingerprints: {len(overlapping_smiles)}')\n",
    "        print(f'Number of overlapping SMILES in train_val_df: {num_overlaps}')\n",
    "        print(f'Number of overlapping SMILES in protac_df: {num_overlaps_tot}')\n",
    "    return num_overlaps + radius + fpsize / 100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[I 2024-04-29 11:28:05,626] A new study created in memory with name: no-name-4db5d822-6220-4ab8-bc3a-c776b0e5cac2\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "678150f59ec548bb89562e2230993989",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/50 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[I 2024-04-29 11:28:07,705] Trial 0 finished with value: 39.480000000000004 and parameters: {'radius': 6, 'fpsize': 2048}. Best is trial 0 with value: 39.480000000000004.\n",
      "[I 2024-04-29 11:28:09,590] Trial 1 finished with value: 23.8 and parameters: {'radius': 11, 'fpsize': 1280}. Best is trial 1 with value: 23.8.\n",
      "[I 2024-04-29 11:28:10,474] Trial 2 finished with value: 131.84 and parameters: {'radius': 3, 'fpsize': 384}. Best is trial 1 with value: 23.8.\n",
      "[I 2024-04-29 11:28:11,978] Trial 3 finished with value: 281.92 and parameters: {'radius': 1, 'fpsize': 1792}. Best is trial 1 with value: 23.8.\n",
      "[I 2024-04-29 11:28:13,994] Trial 4 finished with value: 25.36 and parameters: {'radius': 10, 'fpsize': 1536}. Best is trial 1 with value: 23.8.\n",
      "[I 2024-04-29 11:28:15,642] Trial 5 finished with value: 284.48 and parameters: {'radius': 1, 'fpsize': 2048}. Best is trial 1 with value: 23.8.\n",
      "[I 2024-04-29 11:28:17,154] Trial 6 finished with value: 18.12 and parameters: {'radius': 13, 'fpsize': 512}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:18,057] Trial 7 finished with value: 131.84 and parameters: {'radius': 3, 'fpsize': 384}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:19,570] Trial 8 finished with value: 41.519999999999996 and parameters: {'radius': 5, 'fpsize': 1152}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:20,860] Trial 9 finished with value: 23.4 and parameters: {'radius': 7, 'fpsize': 640}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:22,631] Trial 10 finished with value: 22.68 and parameters: {'radius': 15, 'fpsize': 768}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:24,427] Trial 11 finished with value: 22.68 and parameters: {'radius': 15, 'fpsize': 768}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:25,756] Trial 12 finished with value: 92.28 and parameters: {'radius': 15, 'fpsize': 128}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:27,466] Trial 13 finished with value: 20.96 and parameters: {'radius': 12, 'fpsize': 896}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:29,156] Trial 14 finished with value: 20.96 and parameters: {'radius': 12, 'fpsize': 896}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:30,727] Trial 15 finished with value: 18.12 and parameters: {'radius': 13, 'fpsize': 512}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:31,842] Trial 16 finished with value: 22.28 and parameters: {'radius': 9, 'fpsize': 128}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:33,365] Trial 17 finished with value: 18.12 and parameters: {'radius': 13, 'fpsize': 512}. Best is trial 6 with value: 18.12.\n",
      "[I 2024-04-29 11:28:34,801] Trial 18 finished with value: 16.84 and parameters: {'radius': 13, 'fpsize': 384}. Best is trial 18 with value: 16.84.\n",
      "[I 2024-04-29 11:28:35,986] Trial 19 finished with value: 13.56 and parameters: {'radius': 9, 'fpsize': 256}. Best is trial 19 with value: 13.56.\n",
      "[I 2024-04-29 11:28:37,122] Trial 20 finished with value: 14.56 and parameters: {'radius': 8, 'fpsize': 256}. Best is trial 19 with value: 13.56.\n",
      "[I 2024-04-29 11:28:38,175] Trial 21 finished with value: 30.28 and parameters: {'radius': 8, 'fpsize': 128}. Best is trial 19 with value: 13.56.\n",
      "[I 2024-04-29 11:28:39,406] Trial 22 finished with value: 13.56 and parameters: {'radius': 9, 'fpsize': 256}. Best is trial 19 with value: 13.56.\n",
      "[I 2024-04-29 11:28:40,649] Trial 23 finished with value: 13.56 and parameters: {'radius': 9, 'fpsize': 256}. Best is trial 19 with value: 13.56.\n",
      "[I 2024-04-29 11:28:41,868] Trial 24 finished with value: 12.56 and parameters: {'radius': 10, 'fpsize': 256}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:43,109] Trial 25 finished with value: 12.56 and parameters: {'radius': 10, 'fpsize': 256}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:44,587] Trial 26 finished with value: 16.4 and parameters: {'radius': 10, 'fpsize': 640}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:46,599] Trial 27 finished with value: 25.08 and parameters: {'radius': 11, 'fpsize': 1408}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:48,015] Trial 28 finished with value: 31.96 and parameters: {'radius': 6, 'fpsize': 896}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:49,347] Trial 29 finished with value: 23.4 and parameters: {'radius': 7, 'fpsize': 640}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:51,503] Trial 30 finished with value: 27.64 and parameters: {'radius': 11, 'fpsize': 1664}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:52,657] Trial 31 finished with value: 13.56 and parameters: {'radius': 9, 'fpsize': 256}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:53,840] Trial 32 finished with value: 12.56 and parameters: {'radius': 10, 'fpsize': 256}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:55,159] Trial 33 finished with value: 13.84 and parameters: {'radius': 10, 'fpsize': 384}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:56,140] Trial 34 finished with value: 39.28 and parameters: {'radius': 7, 'fpsize': 128}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:57,508] Trial 35 finished with value: 14.84 and parameters: {'radius': 11, 'fpsize': 384}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:28:58,900] Trial 36 finished with value: 15.120000000000001 and parameters: {'radius': 10, 'fpsize': 512}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:00,203] Trial 37 finished with value: 14.56 and parameters: {'radius': 12, 'fpsize': 256}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:02,225] Trial 38 finished with value: 49.2 and parameters: {'radius': 5, 'fpsize': 1920}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:03,942] Trial 39 finished with value: 22.52 and parameters: {'radius': 8, 'fpsize': 1152}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:05,240] Trial 40 finished with value: 13.84 and parameters: {'radius': 10, 'fpsize': 384}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:06,396] Trial 41 finished with value: 13.56 and parameters: {'radius': 9, 'fpsize': 256}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:07,422] Trial 42 finished with value: 30.28 and parameters: {'radius': 8, 'fpsize': 128}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:08,590] Trial 43 finished with value: 13.56 and parameters: {'radius': 9, 'fpsize': 256}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:09,949] Trial 44 finished with value: 14.84 and parameters: {'radius': 11, 'fpsize': 384}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:11,378] Trial 45 finished with value: 15.120000000000001 and parameters: {'radius': 10, 'fpsize': 512}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:12,637] Trial 46 finished with value: 26.4 and parameters: {'radius': 6, 'fpsize': 640}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:14,232] Trial 47 finished with value: 18.68 and parameters: {'radius': 11, 'fpsize': 768}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:14,904] Trial 48 finished with value: 214.28 and parameters: {'radius': 2, 'fpsize': 128}. Best is trial 24 with value: 12.56.\n",
      "[I 2024-04-29 11:29:16,323] Trial 49 finished with value: 16.56 and parameters: {'radius': 14, 'fpsize': 256}. Best is trial 24 with value: 12.56.\n"
     ]
    }
   ],
   "source": [
    "sampler = optuna.samplers.TPESampler(seed=42)\n",
    "study = optuna.create_study(sampler=sampler, direction='minimize')\n",
    "study.optimize(objective, n_trials=50, show_progress_bar=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Radius: 10\n",
      "FP length: 256\n",
      "Number of unique SMILES: 532\n",
      "Number of unique fingerprints: 532\n",
      "Number of SMILES with overlapping fingerprints: 0\n",
      "Number of overlapping SMILES in train_val_df: 0\n",
      "Number of overlapping SMILES in protac_df: 0\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "12.56"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Run objective with best params and verbose\n",
    "objective(study.best_trial, verbose=1)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}