003. Pharmacological fingerprint construction using Bagging.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "56170dae",
   "metadata": {},
   "outputs": [],
   "source": [
    "from warnings import filterwarnings\n",
    "import time\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "\n",
    "import random\n",
    "import time as time\n",
    "from sklearn.ensemble import RandomForestClassifier, BaggingClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.naive_bayes import BernoulliNB\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "\n",
    "\n",
    "from rdkit import Chem\n",
    "from rdkit.Chem import MACCSkeys\n",
    "from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect\n",
    "\n",
    "# scipy hierarchy clustering\n",
    "from scipy.cluster.hierarchy import dendrogram, linkage\n",
    "from scipy.cluster.hierarchy import fcluster, cophenet\n",
    "import scipy.cluster.hierarchy as sch\n",
    "from scipy.spatial.distance import pdist\n",
    "\n",
    "# SKlearn metrics\n",
    "from sklearn.metrics import silhouette_samples, silhouette_score, adjusted_rand_score, adjusted_mutual_info_score"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "37f3d6a8",
   "metadata": {},
   "source": [
    "#### The Ph-fp of a compound is a vector containing compound's biological activities across the panel of assays predicted by corresponding ML classification models.\n",
    "The Ph-fp is composed of 8 bioactivities predicted for the set of 174 NPS compounds and 1740 decoys random sampled from DUD-E dataset. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "id": "bfaa668e",
   "metadata": {},
   "outputs": [],
   "source": [
    "def transform_fp(df):\n",
    "    fp_list = []\n",
    "    df_tmp = df.copy\n",
    "    #df = df.astype(int)\n",
    "    #df = df.astype(str)\n",
    "    \n",
    "    for x in df.columns:\n",
    "        if x == \"model1\":\n",
    "            fp_list = df[x]\n",
    "        else:\n",
    "            fp_list =  fp_list + df[x]\n",
    "    \n",
    "    return fp_list"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "12b61ad0",
   "metadata": {},
   "source": [
    "##### ML Methods:\n",
    "* SVM (SVC) \n",
    "* MLP\n",
    "* RF\n",
    "* KNN\n",
    "* Bernoulli NB\n",
    "\n",
    "##### hyperparameters\n",
    "* The  determined using 10-fold cross-validated. \n",
    "\n",
    "##### Fingerprints used\n",
    "* Morgan, or\n",
    "* MACCS"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0cd28777",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Set path\n",
    "path = '/Users/hek/Research/Cheminformatics/Project_1_NPS/Stimulant vs. Hallucinogens/Dataset/Bioassay data/ChEMBL data/'\n",
    "output_path = '/Users/hek/Research/Cheminformatics/Project_1_NPS/Stimulant vs. Hallucinogens/ChEMBL Dataset ML results/'\n",
    "df_model_list = pd.read_csv(path+\"Target - Assays - Model list and results.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "b362fa53",
   "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>Target</th>\n",
       "      <th>Receptor family</th>\n",
       "      <th>Organism</th>\n",
       "      <th>UniProtKB</th>\n",
       "      <th>ChEMBL</th>\n",
       "      <th>Target_type</th>\n",
       "      <th>Activity_type</th>\n",
       "      <th>Nunique</th>\n",
       "      <th>N_actives_p5</th>\n",
       "      <th>N_actives_p6</th>\n",
       "      <th>...</th>\n",
       "      <th>RF_p6_n_morganfp</th>\n",
       "      <th>RF_p6_MCC_morganfp</th>\n",
       "      <th>RF_p7_n_morganfp</th>\n",
       "      <th>RF_p7_MCC_morganfp</th>\n",
       "      <th>RF_p5_n_maccsfp</th>\n",
       "      <th>RF_p5_MCC_maccsfp</th>\n",
       "      <th>RF_p6_n_maccsfp</th>\n",
       "      <th>RF_p6_MCC_maccsfp</th>\n",
       "      <th>RF_p7_n_maccsfp</th>\n",
       "      <th>RF_p7_MCC_maccsfp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>CB1</td>\n",
       "      <td>cannabinoid</td>\n",
       "      <td>Homo sapiens</td>\n",
       "      <td>P21554</td>\n",
       "      <td>CHEMBL218</td>\n",
       "      <td>SINGLE PROTEIN</td>\n",
       "      <td>Ki</td>\n",
       "      <td>2710</td>\n",
       "      <td>2670</td>\n",
       "      <td>2025</td>\n",
       "      <td>...</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.935636</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.939861</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.933666</td>\n",
       "      <td>140.0</td>\n",
       "      <td>0.938051</td>\n",
       "      <td>60.0</td>\n",
       "      <td>0.929244</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Target Receptor family      Organism UniProtKB     ChEMBL     Target_type  \\\n",
       "0    CB1     cannabinoid  Homo sapiens    P21554  CHEMBL218  SINGLE PROTEIN   \n",
       "\n",
       "  Activity_type  Nunique  N_actives_p5  N_actives_p6  ...  RF_p6_n_morganfp  \\\n",
       "0            Ki     2710          2670          2025  ...             180.0   \n",
       "\n",
       "   RF_p6_MCC_morganfp  RF_p7_n_morganfp  RF_p7_MCC_morganfp  RF_p5_n_maccsfp  \\\n",
       "0            0.935636             100.0            0.939861            180.0   \n",
       "\n",
       "   RF_p5_MCC_maccsfp  RF_p6_n_maccsfp  RF_p6_MCC_maccsfp  RF_p7_n_maccsfp  \\\n",
       "0           0.933666            140.0           0.938051             60.0   \n",
       "\n",
       "   RF_p7_MCC_maccsfp  \n",
       "0           0.929244  \n",
       "\n",
       "[1 rows x 23 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_model_list.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c8d1ea8e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "70"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_model_list[\"UniProtKB\"].nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a5e5cc23",
   "metadata": {},
   "outputs": [],
   "source": [
    "target_count = 0\n",
    "for i in range(df_model_list.shape[0]):\n",
    "    if df_model_list.loc[i,'RF_p7_MCC_maccsfp'] >= 0.90:\n",
    "        target_count +=1\n",
    "print(target_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "id": "898de127",
   "metadata": {},
   "outputs": [],
   "source": [
    "def load_ChEMBL_data(filename):\n",
    "    df = pd.read_csv(path+filename,dtype=object)\n",
    "    #print(\"Shape of dataframe: \", df.shape)\n",
    "    return df\n",
    "\n",
    "def get_training_X_Y(df,method=\"maccsfp\"):\n",
    "    Y = df.active\n",
    "    total = []\n",
    "    for i in range(df.shape[0]):\n",
    "        b = [int(i) for i in list(df.loc[i,method])]\n",
    "        total.append(b)\n",
    "    X_df = pd.DataFrame(total)\n",
    "    \n",
    "    return X_df, Y\n",
    "\n",
    "def get_NPS_X(df,method=\"maccsfp\"):\n",
    "    total = []\n",
    "    for i in range(df.shape[0]):\n",
    "        b = [int(i) for i in list(df.loc[i,method])]\n",
    "        total.append(b)\n",
    "    X_df = pd.DataFrame(total)\n",
    "    \n",
    "    return X_df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f64e275d",
   "metadata": {},
   "source": [
    "##### Load NPS set and calculate fingerprint \n",
    "* MACCS: \"maccs\"\n",
    "* Morgan: \"morgan"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 174,
   "id": "2a022d13",
   "metadata": {},
   "outputs": [],
   "source": [
    "method = \"maccsfp\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "357c3e53",
   "metadata": {},
   "source": [
    "189 NPS compounds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "id": "3034eada",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(189, 166)\n"
     ]
    }
   ],
   "source": [
    "NPS = pd.read_csv(output_path+\"Drugs Raman or SERS in literature _ Paper 1.csv\", dtype=object)\n",
    "NPS_X= get_NPS_X(NPS,method=\"maccsfp\")\n",
    "print(NPS_X.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6a96402f",
   "metadata": {},
   "source": [
    "756 random sampled DUD-E decoys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "id": "81df3df9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(756, 166)\n"
     ]
    }
   ],
   "source": [
    "NPS_decoy = pd.read_csv(output_path+\"Decoys Drugs Raman or SERS in literature _ Paper 1.csv\", dtype=object)\n",
    "NPS_decoy_X = get_NPS_X(NPS_decoy,method=\"maccsfp\")\n",
    "print(NPS_decoy_X.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3f6e40c7",
   "metadata": {},
   "source": [
    "##### Check how many models are kept and confirm length of Ph-fp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 188,
   "id": "77afe0d9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "102\n"
     ]
    }
   ],
   "source": [
    "model_count = 0\n",
    "for i in range(df_model_list.shape[0]):\n",
    "    if df_model_list.loc[i,'RF_p7_MCC_maccsfp'] >= 0.90:\n",
    "        model_count +=1\n",
    "print(model_count)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9c2f6390",
   "metadata": {},
   "source": [
    "#### Load Training ChEMBL dataset\n",
    "method = fingerprint used"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "id": "26f4cc53",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'maccsfp'"
      ]
     },
     "execution_count": 178,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "method"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 189,
   "id": "0826df82",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training model 1\n",
      "Final dataset Actives >= 7.0 CB1_P21554_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 2\n",
      "Final dataset Actives >= 7.0 CB1_P21554_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 3\n",
      "Final dataset Actives >= 7.0 CB1_P21554_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 4\n",
      "Final dataset Actives >= 7.0 CB1_P20272_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 5\n",
      "Final dataset Actives >= 7.0 CB1_P20272_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 6\n",
      "Final dataset Actives >= 7.0 CB1_P47746_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 7\n",
      "Final dataset Actives >= 7.0 CB2_P34972_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 8\n",
      "Final dataset Actives >= 7.0 CB2_P34972_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 9\n",
      "Final dataset Actives >= 7.0 CB2_Q9QZN9_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 10\n",
      "Final dataset Actives >= 7.0 CB2_P47936_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 11\n",
      "Final dataset Actives >= 7.0 5HT1A_P08908_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 12\n",
      "Final dataset Actives >= 7.0 5HT1A_P08908_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 13\n",
      "Final dataset Actives >= 7.0 5HT1A_P19327_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 14\n",
      "Final dataset Actives >= 7.0 5HT1A_P19327_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 15\n",
      "Final dataset Actives >= 7.0 5HT1B_P28222_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 16\n",
      "Final dataset Actives >= 7.0 5HT1B_P28222_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 17\n",
      "Final dataset Actives >= 7.0 5HT1D_P28221_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 18\n",
      "Final dataset Actives >= 7.0 5HT1D_P28221_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 19\n",
      "Final dataset Actives >= 7.0 5HT1F_P30939_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 20\n",
      "Final dataset Actives >= 7.0 5HT2A_P28223_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 21\n",
      "Final dataset Actives >= 7.0 5HT2A_P28223_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 22\n",
      "Final dataset Actives >= 7.0 5HT2C_P28335_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 23\n",
      "Final dataset Actives >= 7.0 5HT2C_P28335_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 24\n",
      "Final dataset Actives >= 7.0 5HT2C_P28335_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 25\n",
      "Final dataset Actives >= 7.0 5HT2C_P08909_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 26\n",
      "Final dataset Actives >= 7.0 5HT3A_P46098_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training model 27\n",
      "Final dataset Actives >= 7.0 5HT3A_P46098_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 28\n",
      "Final dataset Actives >= 7.0 5HT3A_P35563_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 29\n",
      "Final dataset Actives >= 7.0 5HT5A_P47898_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 30\n",
      "Final dataset Actives >= 7.0 5HT6_P50406_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 31\n",
      "Final dataset Actives >= 7.0 5HT6_P50406_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 32\n",
      "Final dataset Actives >= 7.0 5HT7_P34969_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 33\n",
      "Final dataset Actives >= 7.0 5HT7_P32305_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 34\n",
      "Final dataset Actives >= 7.0 SERT_P31645_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 35\n",
      "Final dataset Actives >= 7.0 SERT_P31645_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 36\n",
      "Final dataset Actives >= 7.0 SERT_P31652_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 37\n",
      "Final dataset Actives >= 7.0 SERT_P31652_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 38\n",
      "Final dataset Actives >= 7.0 D1_P21728_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 39\n",
      "Final dataset Actives >= 7.0 D1_P18901_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 40\n",
      "Final dataset Actives >= 7.0 D1_P18901_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 41\n",
      "Final dataset Actives >= 7.0 D2_P14416_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 42\n",
      "Final dataset Actives >= 7.0 D2_P14416_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 43\n",
      "Final dataset Actives >= 7.0 D2_P14416_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 44\n",
      "Final dataset Actives >= 7.0 D2_P61169_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 45\n",
      "Final dataset Actives >= 7.0 D2_P61169_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 46\n",
      "Final dataset Actives >= 7.0 D3_P35462_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 47\n",
      "Final dataset Actives >= 7.0 D3_P35462_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 48\n",
      "Final dataset Actives >= 7.0 D3_P19020_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 49\n",
      "Final dataset Actives >= 7.0 D3_P19020_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 50\n",
      "Final dataset Actives >= 7.0 D4_P21917_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 51\n",
      "Final dataset Actives >= 7.0 D4_P21917_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training model 52\n",
      "Final dataset Actives >= 7.0 D4_P30729_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 53\n",
      "Final dataset Actives >= 7.0 D5_P21918_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 54\n",
      "Final dataset Actives >= 7.0 DAT_Q01959_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 55\n",
      "Final dataset Actives >= 7.0 DAT_Q01959_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 56\n",
      "Final dataset Actives >= 7.0 DAT_P23977_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 57\n",
      "Final dataset Actives >= 7.0 DAT_P23977_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 58\n",
      "Final dataset Actives >= 7.0 alpha1A_P35348_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 59\n",
      "Final dataset Actives >= 7.0 alpha1A_P43140_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 60\n",
      "Final dataset Actives >= 7.0 alpha1B_P35368_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 61\n",
      "Final dataset Actives >= 7.0 alpha2A_P08913_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 62\n",
      "Final dataset Actives >= 7.0 beta1_P08588_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 63\n",
      "Final dataset Actives >= 7.0 beta2_P07550_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 64\n",
      "Final dataset Actives >= 7.0 beta2_P07550_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 65\n",
      "Final dataset Actives >= 7.0 beta2_P07550_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 66\n",
      "Final dataset Actives >= 7.0 beta3_P13945_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 67\n",
      "Final dataset Actives >= 7.0 beta3_P13945_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 68\n",
      "Final dataset Actives >= 7.0 NET_P23975_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 69\n",
      "Final dataset Actives >= 7.0 NET_P23975_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 70\n",
      "Final dataset Actives >= 7.0 H1_P35367_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 71\n",
      "Final dataset Actives >= 7.0 H3_Q9Y5N1_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 72\n",
      "Final dataset Actives >= 7.0 H3_Q9Y5N1_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 73\n",
      "Final dataset Actives >= 7.0 H3_Q9QYN8_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 74\n",
      "Final dataset Actives >= 7.0 H3_P58406_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 75\n",
      "Final dataset Actives >= 7.0 H4_Q9H3N8_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training model 76\n",
      "Final dataset Actives >= 7.0 kappa_P41145_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 77\n",
      "Final dataset Actives >= 7.0 kappa_P41145_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 78\n",
      "Final dataset Actives >= 7.0 kappa_P41145_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 79\n",
      "Final dataset Actives >= 7.0 kappa_P33534_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 80\n",
      "Final dataset Actives >= 7.0 mu_P35372_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "skiped this model due to MCC < 0.90\n",
      "Training model 81\n",
      "Final dataset Actives >= 7.0 mu_P35372_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=140,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 82\n",
      "Final dataset Actives >= 7.0 mu_P33535_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 83\n",
      "Final dataset Actives >= 7.0 mu_P33535_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 84\n",
      "Final dataset Actives >= 7.0 mu_P33535_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 85\n",
      "Final dataset Actives >= 7.0 mu_P42866_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 86\n",
      "Final dataset Actives >= 7.0 mu_P42866_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 87\n",
      "Final dataset Actives >= 7.0 delta_P41143_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 88\n",
      "Final dataset Actives >= 7.0 delta_P41143_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 89\n",
      "Final dataset Actives >= 7.0 delta_P41143_EC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 90\n",
      "Final dataset Actives >= 7.0 delta_P33533_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 91\n",
      "Final dataset Actives >= 7.0 delta_P33533_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 92\n",
      "Final dataset Actives >= 7.0 delta_P32300_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 93\n",
      "Final dataset Actives >= 7.0 delta_P32300_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 94\n",
      "Final dataset Actives >= 7.0 S1_Q99720_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 95\n",
      "Final dataset Actives >= 7.0 S1_Q99720_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 96\n",
      "Final dataset Actives >= 7.0 S1_Q9R0C9_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 97\n",
      "Final dataset Actives >= 7.0 S1_Q9R0C9_IC50.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 98\n",
      "Final dataset Actives >= 7.0 S1_O55242_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=20,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 99\n",
      "Final dataset Actives >= 7.0 S2_Q5BJF2_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Training model 100\n",
      "Final dataset Actives >= 7.0 S2_Q5U3Y7_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=180,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training model 101\n",
      "Final dataset Actives >= 7.0 GABAalpha2_P47869_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<ipython-input-189-aa45cfef82ec>:33: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider using pd.concat instead.  To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  NPS_pf_tmp[\"model\"+str(model_count)]=pd.to_numeric(NPS_Y_pred).astype(int).astype(str)\n",
      "<ipython-input-189-aa45cfef82ec>:36: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider using pd.concat instead.  To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  NPS_decoy_pf_tmp[\"model\"+str(model_count)]=pd.to_numeric(NPS_decoy_Y_pred).astype(int).astype(str)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training model 102\n",
      "Final dataset Actives >= 7.0 GABAalpha5_P31644_Ki.csv\n",
      "BaggingClassifier(base_estimator=RandomForestClassifier(max_features=None,\n",
      "                                                        n_estimators=60,\n",
      "                                                        random_state=13),\n",
      "                  max_samples=0.9, random_state=42)\n",
      "Total of models included in constructing the Ph-fp is  102 used 788.2086019515991 seconds\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<ipython-input-189-aa45cfef82ec>:33: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider using pd.concat instead.  To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  NPS_pf_tmp[\"model\"+str(model_count)]=pd.to_numeric(NPS_Y_pred).astype(int).astype(str)\n",
      "<ipython-input-189-aa45cfef82ec>:36: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider using pd.concat instead.  To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  NPS_decoy_pf_tmp[\"model\"+str(model_count)]=pd.to_numeric(NPS_decoy_Y_pred).astype(int).astype(str)\n"
     ]
    }
   ],
   "source": [
    "tinit = time.time()\n",
    "model_count = 0\n",
    "NPS_pf_tmp = pd.DataFrame()\n",
    "NPS_decoy_pf_tmp = pd.DataFrame()\n",
    "for i in range(df_model_list.shape[0]):\n",
    "#for i in range(0,20):\n",
    "    target = df_model_list.loc[i,\"Target\"]\n",
    "    UniProtKB = df_model_list.loc[i,'UniProtKB']\n",
    "    Act_type = df_model_list.loc[i,'Activity_type'] \n",
    "    #print(target+'_'+UniProtKB+'_'+Act_type)\n",
    "    if df_model_list.loc[i,'RF_p7_MCC_maccsfp'] >= 0.90:\n",
    "        model_count +=1\n",
    "        print(\"Training model\",model_count)\n",
    "        \n",
    "        #load training dataset\n",
    "        filename = \"Final dataset \"+\"Actives >= 7.0 \"+target+'_'+UniProtKB+'_'+Act_type+'.csv'\n",
    "        df = load_ChEMBL_data(filename)\n",
    "        print(filename)\n",
    "        #Transform dataset\n",
    "        X_df, Y = get_training_X_Y(df,method='maccsfp')\n",
    "        #print(X_df.shape[0])\n",
    "        \n",
    "        #RF as base estimator\n",
    "        RF =  RandomForestClassifier(n_estimators=int(df_model_list.loc[i,'RF_p7_n_maccsfp']),\n",
    "                                     max_features=None,\n",
    "                                     criterion = 'gini',random_state=13)\n",
    "        \n",
    "        # Bagging with RF as base estimator\n",
    "        Bagging_model = BaggingClassifier(RF, n_estimators = 10, max_samples = 0.90,random_state = 42)\n",
    "        print(Bagging_model)\n",
    "        clf = Bagging_model.fit(X_df, Y)\n",
    "        NPS_Y_pred = clf.predict(NPS_X)\n",
    "        NPS_pf_tmp[\"model\"+str(model_count)]=pd.to_numeric(NPS_Y_pred).astype(int).astype(str)\n",
    "    \n",
    "        NPS_decoy_Y_pred = clf.predict(NPS_decoy_X)\n",
    "        NPS_decoy_pf_tmp[\"model\"+str(model_count)]=pd.to_numeric(NPS_decoy_Y_pred).astype(int).astype(str)       \n",
    "        \n",
    "    else:\n",
    "        print(\"skiped this model due to MCC < 0.90\")\n",
    "        continue\n",
    "\n",
    "tfinal = time.time()\n",
    "print(\"Total of models included in constructing the Ph-fp is \",model_count, \"used\", tfinal-tinit, 'seconds')\n",
    "\n",
    "NPS_result = transform_fp(NPS_pf_tmp)\n",
    "NPS_decoy_result = transform_fp(NPS_decoy_pf_tmp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 184,
   "id": "6601579b",
   "metadata": {},
   "outputs": [],
   "source": [
    "NPS['RF_p6_maccs'] = NPS_result\n",
    "NPS_decoy['RF_p6_maccs'] = NPS_decoy_result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 185,
   "id": "94639158",
   "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>Name</th>\n",
       "      <th>Other name</th>\n",
       "      <th>Formula</th>\n",
       "      <th>MW</th>\n",
       "      <th>CAS</th>\n",
       "      <th>PubChem CID</th>\n",
       "      <th>RotBondCount</th>\n",
       "      <th>Conformers</th>\n",
       "      <th>Canonical SMILES</th>\n",
       "      <th>Pharm class</th>\n",
       "      <th>...</th>\n",
       "      <th>canonical_smiles</th>\n",
       "      <th>maccsfp</th>\n",
       "      <th>morganfp</th>\n",
       "      <th>RF_morgan</th>\n",
       "      <th>MCS_K</th>\n",
       "      <th>RF_p5_morgan</th>\n",
       "      <th>RF_p6_morgan</th>\n",
       "      <th>RF_p7_morgan</th>\n",
       "      <th>RF_p5_maccs</th>\n",
       "      <th>RF_p6_maccs</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Heroin</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C21H23NO5</td>\n",
       "      <td>369.4</td>\n",
       "      <td>561-27-3</td>\n",
       "      <td>5462328</td>\n",
       "      <td>4</td>\n",
       "      <td>9.0</td>\n",
       "      <td>CC(=O)OC1C=CC2C3CC4=C5C2(C1OC5=C(C=C4)OC(=O)C)...</td>\n",
       "      <td>Depressants_Opioids</td>\n",
       "      <td>...</td>\n",
       "      <td>CC(=O)Oc1ccc2c3c1OC1C(OC(C)=O)C=CC4C(C2)N(C)CC...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000010001000000000000000001001000000000...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>3</td>\n",
       "      <td>0000000000000000100000000000000000000001000110...</td>\n",
       "      <td>0000000000000000001000000000000000000001001110...</td>\n",
       "      <td>0000000000000100010000000000000000001000000000...</td>\n",
       "      <td>0000000000001011010101110000100010010101110111...</td>\n",
       "      <td>0000000000001010001010000000100000010001110111...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Morphine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C17H19NO3</td>\n",
       "      <td>285.34</td>\n",
       "      <td>57-27-2</td>\n",
       "      <td>5288826</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>CN1CCC23C4C1CC5=C2C(=C(C=C5)O)OC3C(C=C4)O</td>\n",
       "      <td>Depressants_Opioids</td>\n",
       "      <td>...</td>\n",
       "      <td>CN1CCC23c4c5ccc(O)c4OC2C(O)C=CC3C1C5</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000001000000000000000001001000000000...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>3</td>\n",
       "      <td>0000000000001010100001000000000000001101111111...</td>\n",
       "      <td>0000000000100100001001000010000000000001111111...</td>\n",
       "      <td>0000000000000100000000000000000000001111001110...</td>\n",
       "      <td>1100000010011111110101111110110010010111111111...</td>\n",
       "      <td>0000000000000111001110110100110010010111111111...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 25 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Name Other name    Formula      MW       CAS PubChem CID RotBondCount  \\\n",
       "0    Heroin        NaN  C21H23NO5   369.4  561-27-3     5462328            4   \n",
       "1  Morphine        NaN  C17H19NO3  285.34   57-27-2     5288826            0   \n",
       "\n",
       "  Conformers                                   Canonical SMILES  \\\n",
       "0        9.0  CC(=O)OC1C=CC2C3CC4=C5C2(C1OC5=C(C=C4)OC(=O)C)...   \n",
       "1        1.0          CN1CCC23C4C1CC5=C2C(=C(C=C5)O)OC3C(C=C4)O   \n",
       "\n",
       "           Pharm class  ...  \\\n",
       "0  Depressants_Opioids  ...   \n",
       "1  Depressants_Opioids  ...   \n",
       "\n",
       "                                    canonical_smiles  \\\n",
       "0  CC(=O)Oc1ccc2c3c1OC1C(OC(C)=O)C=CC4C(C2)N(C)CC...   \n",
       "1               CN1CCC23c4c5ccc(O)c4OC2C(O)C=CC3C1C5   \n",
       "\n",
       "                                             maccsfp  \\\n",
       "0  0000000000000000000000000000000000000000000000...   \n",
       "1  0000000000000000000000000000000000000000000000...   \n",
       "\n",
       "                                            morganfp  \\\n",
       "0  0000000000010001000000000000000001001000000000...   \n",
       "1  0000000000000001000000000000000001001000000000...   \n",
       "\n",
       "                                           RF_morgan MCS_K  \\\n",
       "0  0000000000000000000000000000000000000000000000...     3   \n",
       "1  0000000000000000000000000000000000000000000000...     3   \n",
       "\n",
       "                                        RF_p5_morgan  \\\n",
       "0  0000000000000000100000000000000000000001000110...   \n",
       "1  0000000000001010100001000000000000001101111111...   \n",
       "\n",
       "                                        RF_p6_morgan  \\\n",
       "0  0000000000000000001000000000000000000001001110...   \n",
       "1  0000000000100100001001000010000000000001111111...   \n",
       "\n",
       "                                        RF_p7_morgan  \\\n",
       "0  0000000000000100010000000000000000001000000000...   \n",
       "1  0000000000000100000000000000000000001111001110...   \n",
       "\n",
       "                                         RF_p5_maccs  \\\n",
       "0  0000000000001011010101110000100010010101110111...   \n",
       "1  1100000010011111110101111110110010010111111111...   \n",
       "\n",
       "                                         RF_p6_maccs  \n",
       "0  0000000000001010001010000000100000010001110111...  \n",
       "1  0000000000000111001110110100110010010111111111...  \n",
       "\n",
       "[2 rows x 25 columns]"
      ]
     },
     "execution_count": 185,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "NPS.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 186,
   "id": "25cf7d3e",
   "metadata": {},
   "outputs": [],
   "source": [
    "NPS.to_csv(output_path+\"Drugs Raman or SERS in literature _ Paper 1.csv\",index = False)\n",
    "NPS_decoy.to_csv(output_path+\"Decoys Drugs Raman or SERS in literature _ Paper 1.csv\",index = False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "68d58918",
   "metadata": {},
   "source": [
    "##### BNB as baseline prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ca5093ac",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "target: CB1\n",
      "target: CB2\n",
      "target: HT2A\n",
      "target: HT2C\n",
      "target: mu\n",
      "target: NET\n",
      "target: DAT\n",
      "target: SERT\n",
      "45.052056074142456 seconds\n"
     ]
    }
   ],
   "source": [
    "BNB = BernoulliNB(alpha= 0.01, fit_prior= True)\n",
    "Bagging_model = BaggingClassifier(base_estimator = BNB, n_estimators = 50, max_samples = 0.90,random_state = 42) \n",
    "\n",
    "NPS_pf_tmp = pd.DataFrame()\n",
    "NPS_decoy_pf_tmp = pd.DataFrame()\n",
    "tinit = time.time()\n",
    "for i in range(len(targets)):\n",
    "        print(\"target:\", targets[i])\n",
    "        X = target_X[i]\n",
    "        Y = target_Y[i]\n",
    "        #print(X.shape)\n",
    "        clf = Bagging_model.fit(X, Y)\n",
    "        NPS_Y_pred = clf.predict(NPS_X)\n",
    "        NPS_pf_tmp[targets[i]] = NPS_Y_pred\n",
    "        #print(len(NPS_Y_pred))\n",
    "        NPS_decoy_Y_pred = clf.predict(NPS_decoy_X)\n",
    "        NPS_decoy_pf_tmp[targets[i]] = NPS_decoy_Y_pred\n",
    "        #print(len(NPS_decoy_Y_pred))\n",
    "        \n",
    "tfinal = time.time()\n",
    "print(tfinal-tinit, 'seconds')\n",
    "# Transform prediction for all targets as binatry vector - Phfp\n",
    "NPS['Phfp_BNB_'+method] = transform_fp(NPS_pf_tmp)\n",
    "NPS_decoy['Phfp_BNB_'+method] = transform_fp(NPS_decoy_pf_tmp)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bd5da717",
   "metadata": {},
   "source": [
    "#### Phfp prediction using other algorithms, where hyperparameters are different for each target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "db1279e8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# MACCS model hyperparameters\n",
    "SVM_MACCS = (SVC(C=16,gamma=0.0625, random_state=13),\n",
    "      SVC(C=4,gamma=0.0625, random_state=13),\n",
    "      SVC(C=4,gamma=0.125, random_state=13),\n",
    "      SVC(C=4,gamma=0.0625, random_state=13),\n",
    "      SVC(C=4,gamma=0.0625, random_state=13),\n",
    "      SVC(C=4,gamma=0.0625, random_state=13),\n",
    "      SVC(C=16,gamma=0.03125, random_state=13),\n",
    "      SVC(C=4,gamma=0.0625, random_state=13))\n",
    "RF_MACCS = (RandomForestClassifier(n_estimators=1460, criterion = 'entropy',random_state=13),\n",
    "     RandomForestClassifier(n_estimators=910, criterion = 'entropy',random_state=13),\n",
    "     RandomForestClassifier(n_estimators=960, random_state=13),\n",
    "     RandomForestClassifier(n_estimators=160, random_state=13),\n",
    "     RandomForestClassifier(n_estimators=410, random_state=13),\n",
    "     RandomForestClassifier(n_estimators=360, criterion = 'entropy',random_state=13),\n",
    "     RandomForestClassifier(n_estimators=360, criterion = 'entropy',random_state=13),\n",
    "     RandomForestClassifier(n_estimators=410, criterion = 'entropy',random_state=13))\n",
    "KNN_MACCS = (KNeighborsClassifier(n_neighbors = 1),\n",
    "       KNeighborsClassifier(n_neighbors = 5),\n",
    "       KNeighborsClassifier(n_neighbors = 5),\n",
    "       KNeighborsClassifier(n_neighbors = 7),\n",
    "       KNeighborsClassifier(n_neighbors = 5),\n",
    "       KNeighborsClassifier(n_neighbors = 5),\n",
    "       KNeighborsClassifier(n_neighbors = 5),\n",
    "       KNeighborsClassifier(n_neighbors = 5))\n",
    "MLP_MACCS = (MLPClassifier(hidden_layer_sizes = (100,),activation='tanh',alpha=0.001, max_iter = 400),\n",
    "       MLPClassifier(hidden_layer_sizes = (100,),activation='tanh',alpha=0.01, max_iter = 400),\n",
    "      MLPClassifier(hidden_layer_sizes = (50,),activation='tanh',alpha=0.001, max_iter = 400),\n",
    "      MLPClassifier(hidden_layer_sizes = (100,),activation='tanh',alpha=0.001, max_iter = 400),\n",
    "      MLPClassifier(hidden_layer_sizes = (30,),activation='tanh',alpha=0.01, max_iter = 400),\n",
    "      MLPClassifier(hidden_layer_sizes = (50,),activation='tanh',alpha=0.001, max_iter = 400),\n",
    "      MLPClassifier(hidden_layer_sizes = (50,),activation='tanh',alpha=0.001, max_iter = 400),\n",
    "      MLPClassifier(hidden_layer_sizes = (100,),activation='tanh',alpha=0.001, max_iter = 400))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "1f3c9c27",
   "metadata": {},
   "outputs": [],
   "source": [
    "def Phfp_prediction(models_target):\n",
    "    NPS_pf_tmp = pd.DataFrame()\n",
    "    NPS_decoy_pf_tmp = pd.DataFrame()\n",
    "    tinit = time.time()\n",
    "    for i in range(len(targets)):\n",
    "        print(\"target:\", targets[i])\n",
    "        X = target_X[i]\n",
    "        Y = target_Y[i]\n",
    "        #print(X.shape)\n",
    "        base_estimator = models_target[i]\n",
    "        Bagging_model = BaggingClassifier(base_estimator = base_estimator, n_estimators = 50, max_samples = 0.90,random_state = 42)\n",
    "        print(Bagging_model)\n",
    "        clf = Bagging_model.fit(X, Y)\n",
    "        \n",
    "        NPS_Y_pred = clf.predict(NPS_X)\n",
    "        NPS_pf_tmp[targets[i]] = NPS_Y_pred\n",
    "        #print(len(NPS_Y_pred))\n",
    "        NPS_decoy_Y_pred = clf.predict(NPS_decoy_X)\n",
    "        NPS_decoy_pf_tmp[targets[i]] = NPS_decoy_Y_pred\n",
    "        #print(len(NPS_decoy_Y_pred))\n",
    "    \n",
    "    tfinal = time.time()\n",
    "    print(tfinal-tinit, 'seconds')\n",
    "    # Transform prediction for all targets as binatry vector - Phfp\n",
    "    NPS_pf = transform_fp(NPS_pf_tmp)\n",
    "    NPS_decoy_pf = transform_fp(NPS_decoy_pf_tmp)\n",
    "    print(\"Done Phfp prediciton with: \"+str(models_target))\n",
    "    return NPS_pf, NPS_decoy_pf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "7b39d87f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "target: CB1\n",
      "BaggingClassifier(base_estimator=SVC(C=16, gamma=0.0625, random_state=13),\n",
      "                  max_samples=0.9, n_estimators=50, random_state=42)\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-29-b780b2e243b1>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mNPS\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Phfp_SVM_'\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNPS_decoy\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Phfp_SVM_'\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mPhfp_prediction\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mSVM_MACCS\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0mNPS\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Phfp_RF_'\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNPS_decoy\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Phfp_RF_'\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mPhfp_prediction\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mRF_MACCS\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mNPS\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Phfp_KNN_'\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNPS_decoy\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Phfp_KNN_'\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mPhfp_prediction\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mKNN_MACCS\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mNPS\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Phfp_MLP_'\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mNPS_decoy\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Phfp_MLP_'\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mPhfp_prediction\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mMLP_MACCS\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m<ipython-input-15-5475adbffc9e>\u001b[0m in \u001b[0;36mPhfp_prediction\u001b[0;34m(models_target)\u001b[0m\n\u001b[1;32m     11\u001b[0m         \u001b[0mBagging_model\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mBaggingClassifier\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbase_estimator\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbase_estimator\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mn_estimators\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m50\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_samples\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0.90\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mrandom_state\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m42\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     12\u001b[0m         \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mBagging_model\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 13\u001b[0;31m         \u001b[0mclf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mBagging_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mY\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     14\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m         \u001b[0mNPS_Y_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mclf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mNPS_X\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m    242\u001b[0m         \u001b[0mself\u001b[0m \u001b[0;34m:\u001b[0m \u001b[0mobject\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    243\u001b[0m         \"\"\"\n\u001b[0;32m--> 244\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_fit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmax_samples\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    245\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    246\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_parallel_args\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py\u001b[0m in \u001b[0;36m_fit\u001b[0;34m(self, X, y, max_samples, max_depth, sample_weight)\u001b[0m\n\u001b[1;32m    368\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_seeds\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mseeds\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    369\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 370\u001b[0;31m         all_results = Parallel(n_jobs=n_jobs, verbose=self.verbose,\n\u001b[0m\u001b[1;32m    371\u001b[0m                                \u001b[0;34m**\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_parallel_args\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    372\u001b[0m             delayed(_parallel_build_estimators)(\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/joblib/parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m   1039\u001b[0m             \u001b[0;31m# remaining jobs.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1040\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_iterating\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1041\u001b[0;31m             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdispatch_one_batch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1042\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_iterating\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_original_iterator\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1043\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/joblib/parallel.py\u001b[0m in \u001b[0;36mdispatch_one_batch\u001b[0;34m(self, iterator)\u001b[0m\n\u001b[1;32m    857\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    858\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 859\u001b[0;31m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_dispatch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtasks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    860\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    861\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/joblib/parallel.py\u001b[0m in \u001b[0;36m_dispatch\u001b[0;34m(self, batch)\u001b[0m\n\u001b[1;32m    775\u001b[0m         \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_lock\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    776\u001b[0m             \u001b[0mjob_idx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_jobs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 777\u001b[0;31m             \u001b[0mjob\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply_async\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallback\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    778\u001b[0m             \u001b[0;31m# A job can complete so quickly than its callback is\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    779\u001b[0m             \u001b[0;31m# called before we get here, causing self._jobs to\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/joblib/_parallel_backends.py\u001b[0m in \u001b[0;36mapply_async\u001b[0;34m(self, func, callback)\u001b[0m\n\u001b[1;32m    206\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mapply_async\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallback\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    207\u001b[0m         \u001b[0;34m\"\"\"Schedule a func to be run\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 208\u001b[0;31m         \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mImmediateResult\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    209\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mcallback\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    210\u001b[0m             \u001b[0mcallback\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/joblib/_parallel_backends.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, batch)\u001b[0m\n\u001b[1;32m    570\u001b[0m         \u001b[0;31m# Don't delay the application, to avoid keeping the input\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    571\u001b[0m         \u001b[0;31m# arguments in memory\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 572\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresults\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbatch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    573\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    574\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/joblib/parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    260\u001b[0m         \u001b[0;31m# change the default number of processes to -1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    261\u001b[0m         \u001b[0;32mwith\u001b[0m \u001b[0mparallel_backend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mn_jobs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_n_jobs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 262\u001b[0;31m             return [func(*args, **kwargs)\n\u001b[0m\u001b[1;32m    263\u001b[0m                     for func, args, kwargs in self.items]\n\u001b[1;32m    264\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/joblib/parallel.py\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m    260\u001b[0m         \u001b[0;31m# change the default number of processes to -1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    261\u001b[0m         \u001b[0;32mwith\u001b[0m \u001b[0mparallel_backend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mn_jobs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_n_jobs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 262\u001b[0;31m             return [func(*args, **kwargs)\n\u001b[0m\u001b[1;32m    263\u001b[0m                     for func, args, kwargs in self.items]\n\u001b[1;32m    264\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/sklearn/utils/fixes.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    220\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__call__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    221\u001b[0m         \u001b[0;32mwith\u001b[0m \u001b[0mconfig_context\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 222\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfunction\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/sklearn/ensemble/_bagging.py\u001b[0m in \u001b[0;36m_parallel_build_estimators\u001b[0;34m(n_estimators, ensemble, X, y, sample_weight, seeds, total_n_estimators, verbose)\u001b[0m\n\u001b[1;32m    109\u001b[0m                 \u001b[0mcurr_sample_weight\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mnot_indices_mask\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    110\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 111\u001b[0;31m             \u001b[0mestimator\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfeatures\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcurr_sample_weight\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    112\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    113\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/sklearn/svm/_base.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m    224\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    225\u001b[0m         \u001b[0mseed\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrnd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0miinfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'i'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmax\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 226\u001b[0;31m         \u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msolver_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkernel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrandom_seed\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mseed\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    227\u001b[0m         \u001b[0;31m# see comment on the other call to np.iinfo in this file\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    228\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/envs/my-rdkit-env/lib/python3.9/site-packages/sklearn/svm/_base.py\u001b[0m in \u001b[0;36m_dense_fit\u001b[0;34m(self, X, y, sample_weight, solver_type, kernel, random_seed)\u001b[0m\n\u001b[1;32m    275\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msupport_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msupport_vectors_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_n_support\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    276\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdual_coef_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mintercept_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_probA\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 277\u001b[0;31m             self._probB, self.fit_status_ = libsvm.fit(\n\u001b[0m\u001b[1;32m    278\u001b[0m                 \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    279\u001b[0m                 \u001b[0msvm_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msolver_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "NPS['Phfp_SVM_'+method], NPS_decoy['Phfp_SVM_'+method] = Phfp_prediction(SVM_MACCS)\n",
    "NPS['Phfp_RF_'+method], NPS_decoy['Phfp_RF_'+method] = Phfp_prediction(RF_MACCS)\n",
    "NPS['Phfp_KNN_'+method], NPS_decoy['Phfp_KNN_'+method] = Phfp_prediction(KNN_MACCS)\n",
    "NPS['Phfp_MLP_'+method], NPS_decoy['Phfp_MLP_'+method] = Phfp_prediction(MLP_MACCS)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "8dfb49fb",
   "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>Name</th>\n",
       "      <th>Other name</th>\n",
       "      <th>Formula</th>\n",
       "      <th>MW</th>\n",
       "      <th>CAS</th>\n",
       "      <th>PubChem CID</th>\n",
       "      <th>RotBondCount</th>\n",
       "      <th>Conformers</th>\n",
       "      <th>Canonical SMILES</th>\n",
       "      <th>Pharm class</th>\n",
       "      <th>...</th>\n",
       "      <th>Canonical smiles</th>\n",
       "      <th>MCS_K</th>\n",
       "      <th>maccsfp</th>\n",
       "      <th>morganfp</th>\n",
       "      <th>fp</th>\n",
       "      <th>Phfp_BNB_maccs</th>\n",
       "      <th>Phfp_SVM_maccs</th>\n",
       "      <th>Phfp_RF_maccs</th>\n",
       "      <th>Phfp_KNN_maccs</th>\n",
       "      <th>Phfp_MLP_maccs</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>164</th>\n",
       "      <td>MiPT</td>\n",
       "      <td>N-(2-(1H-Indol-3-yl)ethyl)-N-methylpropan-2-amine</td>\n",
       "      <td>C14H20N2</td>\n",
       "      <td>216.32</td>\n",
       "      <td>96096-52-5</td>\n",
       "      <td>29935323</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>CC(C)N(C)CCC1=CNC2=CC=CC=C21</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>CC(C)N(C)CCc1c[nH]c2ccccc12</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0100000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>01111111</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>165</th>\n",
       "      <td>4-HO-DiPT</td>\n",
       "      <td>3-[2-[di(propan-2-yl)amino]ethyl]-1H-indol-4-ol</td>\n",
       "      <td>C16H24N2O</td>\n",
       "      <td>260.37</td>\n",
       "      <td>132328-45-1</td>\n",
       "      <td>21854225</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "      <td>CC(C)N(CCC1=CNC2=C1C(=CC=C2)O)C(C)C</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>CC(C)N(CCc1c[nH]c2cccc(O)c12)C(C)C</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0100000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11011111</td>\n",
       "      <td>00110010</td>\n",
       "      <td>00110000</td>\n",
       "      <td>01110001</td>\n",
       "      <td>00110000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>4-HO-MET</td>\n",
       "      <td>3-[2-[ethyl(methyl)amino]ethyl]-1H-indol-4-ol</td>\n",
       "      <td>C13H18N2O</td>\n",
       "      <td>218.29</td>\n",
       "      <td>77872-41-4</td>\n",
       "      <td>21786582</td>\n",
       "      <td>4</td>\n",
       "      <td>9</td>\n",
       "      <td>CCN(C)CCC1=CNC2=C1C(=CC=C2)O</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>CCN(C)CCc1c[nH]c2cccc(O)c12</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>00110101</td>\n",
       "      <td>01111111</td>\n",
       "      <td>01110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>167</th>\n",
       "      <td>4-HO-DET</td>\n",
       "      <td>3-(2-(Diethylamino)ethyl)-1H-indol-4-ol</td>\n",
       "      <td>C14H20N2O</td>\n",
       "      <td>232.32</td>\n",
       "      <td>22204-89-3</td>\n",
       "      <td>9991554</td>\n",
       "      <td>5</td>\n",
       "      <td>10</td>\n",
       "      <td>CCN(CC)CCC1=CNC2=C1C(=CC=C2)O</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>CCN(CC)CCc1c[nH]c2cccc(O)c12</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000010000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>00110001</td>\n",
       "      <td>01111101</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>168</th>\n",
       "      <td>4-HO-MiPT</td>\n",
       "      <td>4-Hydroxy-N-methyl-N-isopropyltryptamine</td>\n",
       "      <td>C14H20N2O</td>\n",
       "      <td>232.32</td>\n",
       "      <td>77872-43-6</td>\n",
       "      <td>10082683</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>CC(C)N(C)CCC1=CNC2=C1C(=CC=C2)O</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>CC(C)N(C)CCc1c[nH]c2cccc(O)c12</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0100000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>00110101</td>\n",
       "      <td>01111111</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>169</th>\n",
       "      <td>5-MeO-AMT</td>\n",
       "      <td>1-(5-methoxy-1H-indol-3-yl)propan-2-amine</td>\n",
       "      <td>C12H16N2O</td>\n",
       "      <td>204.27</td>\n",
       "      <td>1137-04-8</td>\n",
       "      <td>36906</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>CC(CC1=CNC2=C1C=C(C=C2)OC)N</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2[nH]cc(CC(C)N)c2c1</td>\n",
       "      <td>15</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0100000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>00010111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>00110000</td>\n",
       "      <td>00110110</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>170</th>\n",
       "      <td>5-MeO-MiPT</td>\n",
       "      <td>N-[2-(5-methoxy-1H-indol-3-yl)ethyl]-N-methylp...</td>\n",
       "      <td>C15H22N2O</td>\n",
       "      <td>246.35</td>\n",
       "      <td>96096-55-8</td>\n",
       "      <td>2763156</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>CC(C)N(C)CCC1=CNC2=C1C=C(C=C2)OC</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2[nH]cc(CCN(C)C(C)C)c2c1</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0100000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>01111111</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>171</th>\n",
       "      <td>5-MeO-DMT</td>\n",
       "      <td>5-Methoxy-N,N-dimethyltryptamine</td>\n",
       "      <td>C13H18N2O</td>\n",
       "      <td>218.29</td>\n",
       "      <td>1019-45-0</td>\n",
       "      <td>1832</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>CN(C)CCC1=CNC2=C1C=C(C=C2)OC</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2[nH]cc(CCN(C)C)c2c1</td>\n",
       "      <td>15</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>01111111</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>172</th>\n",
       "      <td>5-MeO-DiPT</td>\n",
       "      <td>5-Methoxy-N,N-diisopropyltryptamine</td>\n",
       "      <td>C17H26N2O</td>\n",
       "      <td>274.4</td>\n",
       "      <td>4021-34-5</td>\n",
       "      <td>151182</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>CC(C)N(CCC1=CNC2=C1C=C(C=C2)OC)C(C)C</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2[nH]cc(CCN(C(C)C)C(C)C)c2c1</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0100000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>00110101</td>\n",
       "      <td>01111111</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>173</th>\n",
       "      <td>5-MeO-DET</td>\n",
       "      <td>5-Methoxy-N,N-diethyltryptamine</td>\n",
       "      <td>C15H22N2O</td>\n",
       "      <td>246.35</td>\n",
       "      <td>1218-40-2</td>\n",
       "      <td>417608</td>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "      <td>CCN(CC)CCC1=CNC2=C1C=C(C=C2)OC</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>CCN(CC)CCc1c[nH]c2ccc(OC)cc12</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000010000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>01111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>11111111</td>\n",
       "      <td>01111111</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           Name                                         Other name    Formula  \\\n",
       "164        MiPT  N-(2-(1H-Indol-3-yl)ethyl)-N-methylpropan-2-amine   C14H20N2   \n",
       "165   4-HO-DiPT    3-[2-[di(propan-2-yl)amino]ethyl]-1H-indol-4-ol  C16H24N2O   \n",
       "166    4-HO-MET      3-[2-[ethyl(methyl)amino]ethyl]-1H-indol-4-ol  C13H18N2O   \n",
       "167    4-HO-DET            3-(2-(Diethylamino)ethyl)-1H-indol-4-ol  C14H20N2O   \n",
       "168   4-HO-MiPT           4-Hydroxy-N-methyl-N-isopropyltryptamine  C14H20N2O   \n",
       "169   5-MeO-AMT          1-(5-methoxy-1H-indol-3-yl)propan-2-amine  C12H16N2O   \n",
       "170  5-MeO-MiPT  N-[2-(5-methoxy-1H-indol-3-yl)ethyl]-N-methylp...  C15H22N2O   \n",
       "171   5-MeO-DMT                   5-Methoxy-N,N-dimethyltryptamine  C13H18N2O   \n",
       "172  5-MeO-DiPT                5-Methoxy-N,N-diisopropyltryptamine  C17H26N2O   \n",
       "173   5-MeO-DET                    5-Methoxy-N,N-diethyltryptamine  C15H22N2O   \n",
       "\n",
       "         MW          CAS PubChem CID RotBondCount Conformers  \\\n",
       "164  216.32   96096-52-5    29935323            4         10   \n",
       "165  260.37  132328-45-1    21854225            5          9   \n",
       "166  218.29   77872-41-4    21786582            4          9   \n",
       "167  232.32   22204-89-3     9991554            5         10   \n",
       "168  232.32   77872-43-6    10082683            4         10   \n",
       "169  204.27    1137-04-8       36906            3          7   \n",
       "170  246.35   96096-55-8     2763156            5          7   \n",
       "171  218.29    1019-45-0        1832            4         10   \n",
       "172   274.4    4021-34-5      151182            6          4   \n",
       "173  246.35    1218-40-2      417608            6         10   \n",
       "\n",
       "                         Canonical SMILES                Pharm class  ...  \\\n",
       "164          CC(C)N(C)CCC1=CNC2=CC=CC=C21  Serotonergic psychedelics  ...   \n",
       "165   CC(C)N(CCC1=CNC2=C1C(=CC=C2)O)C(C)C  Serotonergic psychedelics  ...   \n",
       "166          CCN(C)CCC1=CNC2=C1C(=CC=C2)O  Serotonergic psychedelics  ...   \n",
       "167         CCN(CC)CCC1=CNC2=C1C(=CC=C2)O  Serotonergic psychedelics  ...   \n",
       "168       CC(C)N(C)CCC1=CNC2=C1C(=CC=C2)O  Serotonergic psychedelics  ...   \n",
       "169           CC(CC1=CNC2=C1C=C(C=C2)OC)N  Serotonergic psychedelics  ...   \n",
       "170      CC(C)N(C)CCC1=CNC2=C1C=C(C=C2)OC  Serotonergic psychedelics  ...   \n",
       "171          CN(C)CCC1=CNC2=C1C=C(C=C2)OC  Serotonergic psychedelics  ...   \n",
       "172  CC(C)N(CCC1=CNC2=C1C=C(C=C2)OC)C(C)C  Serotonergic psychedelics  ...   \n",
       "173        CCN(CC)CCC1=CNC2=C1C=C(C=C2)OC  Serotonergic psychedelics  ...   \n",
       "\n",
       "                        Canonical smiles MCS_K  \\\n",
       "164          CC(C)N(C)CCc1c[nH]c2ccccc12    17   \n",
       "165   CC(C)N(CCc1c[nH]c2cccc(O)c12)C(C)C    17   \n",
       "166          CCN(C)CCc1c[nH]c2cccc(O)c12    17   \n",
       "167         CCN(CC)CCc1c[nH]c2cccc(O)c12    17   \n",
       "168       CC(C)N(C)CCc1c[nH]c2cccc(O)c12    17   \n",
       "169           COc1ccc2[nH]cc(CC(C)N)c2c1    15   \n",
       "170      COc1ccc2[nH]cc(CCN(C)C(C)C)c2c1    17   \n",
       "171          COc1ccc2[nH]cc(CCN(C)C)c2c1    15   \n",
       "172  COc1ccc2[nH]cc(CCN(C(C)C)C(C)C)c2c1    17   \n",
       "173        CCN(CC)CCc1c[nH]c2ccc(OC)cc12    17   \n",
       "\n",
       "                                               maccsfp  \\\n",
       "164  0000000000000000000000000000000000000000000000...   \n",
       "165  0000000000000000000000000000000000000000000000...   \n",
       "166  0000000000000000000000000000000000000000000000...   \n",
       "167  0000000000000000000000000000000000000000000000...   \n",
       "168  0000000000000000000000000000000000000000000000...   \n",
       "169  0000000000000000000000000000000000000000000000...   \n",
       "170  0000000000000000000000000000000000000000000000...   \n",
       "171  0000000000000000000000000000000000000000000000...   \n",
       "172  0000000000000000000000000000000000000000000000...   \n",
       "173  0000000000000000000000000000000000000000000000...   \n",
       "\n",
       "                                              morganfp  \\\n",
       "164  0100000000000000000000000000000000000000000000...   \n",
       "165  0100000000000000000000000000000000000000000000...   \n",
       "166  0000000000000000000000000000000000000000000000...   \n",
       "167  0000000000000000000000000010000000000000000000...   \n",
       "168  0100000000000000000000000000000000000000000000...   \n",
       "169  0100000000000000000000000000000000000000000000...   \n",
       "170  0100000000000000000000000000000000000000000000...   \n",
       "171  0000000000000000000000000000000000000000000000...   \n",
       "172  0100000000000000000000000000000000000000000000...   \n",
       "173  0000000000000000000000000010000000000000000000...   \n",
       "\n",
       "                                                    fp Phfp_BNB_maccs  \\\n",
       "164  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "165  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11011111   \n",
       "166  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "167  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "168  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "169  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       00010111   \n",
       "170  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "171  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "172  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "173  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "\n",
       "    Phfp_SVM_maccs Phfp_RF_maccs Phfp_KNN_maccs Phfp_MLP_maccs  \n",
       "164       00110111      00110111       01111111       00110111  \n",
       "165       00110010      00110000       01110001       00110000  \n",
       "166       00110111      00110101       01111111       01110111  \n",
       "167       00110111      00110001       01111101       00110111  \n",
       "168       00110111      00110101       01111111       00110111  \n",
       "169       00110111      00110000       00110110       00110111  \n",
       "170       00111111      00110111       01111111       00110111  \n",
       "171       00110111      00110111       01111111       00110111  \n",
       "172       00110111      00110101       01111111       00110111  \n",
       "173       01111111      00110111       11111111       01111111  \n",
       "\n",
       "[10 rows x 33 columns]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "NPS.tail(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9203d190",
   "metadata": {},
   "source": [
    "Drop RDKit mol and save results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "6c7614b7",
   "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>Name</th>\n",
       "      <th>Other name</th>\n",
       "      <th>Formula</th>\n",
       "      <th>MW</th>\n",
       "      <th>CAS</th>\n",
       "      <th>PubChem CID</th>\n",
       "      <th>RotBondCount</th>\n",
       "      <th>Conformers</th>\n",
       "      <th>Canonical SMILES</th>\n",
       "      <th>Pharm class</th>\n",
       "      <th>...</th>\n",
       "      <th>Canonical smiles</th>\n",
       "      <th>MCS_K</th>\n",
       "      <th>maccsfp</th>\n",
       "      <th>morganfp</th>\n",
       "      <th>fp</th>\n",
       "      <th>Phfp_BNB_maccs</th>\n",
       "      <th>Phfp_SVM_maccs</th>\n",
       "      <th>Phfp_RF_maccs</th>\n",
       "      <th>Phfp_KNN_maccs</th>\n",
       "      <th>Phfp_MLP_maccs</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Heroin</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C21H23NO5</td>\n",
       "      <td>369.4</td>\n",
       "      <td>561-27-3</td>\n",
       "      <td>5462328</td>\n",
       "      <td>4</td>\n",
       "      <td>9</td>\n",
       "      <td>CC(=O)OC1C=CC2C3CC4=C5C2(C1OC5=C(C=C4)OC(=O)C)...</td>\n",
       "      <td>Sedatives</td>\n",
       "      <td>...</td>\n",
       "      <td>CC(=O)Oc1ccc2c3c1OC1C(OC(C)=O)C=CC4C(C2)N(C)CC...</td>\n",
       "      <td>3</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11101111</td>\n",
       "      <td>00001000</td>\n",
       "      <td>00001000</td>\n",
       "      <td>01111001</td>\n",
       "      <td>00001000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Morphine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C17H19NO3</td>\n",
       "      <td>285.34</td>\n",
       "      <td>57-27-2</td>\n",
       "      <td>5288826</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>CN1CCC23C4C1CC5=C2C(=C(C=C5)O)OC3C(C=C4)O</td>\n",
       "      <td>Sedatives</td>\n",
       "      <td>...</td>\n",
       "      <td>CN1CCC23c4c5ccc(O)c4OC2C(O)C=CC3C1C5</td>\n",
       "      <td>3</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00111000</td>\n",
       "      <td>00101000</td>\n",
       "      <td>01101000</td>\n",
       "      <td>00111100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Acetylcodeine</td>\n",
       "      <td>6-Acetylcodiene</td>\n",
       "      <td>C20H23NO4</td>\n",
       "      <td>341.4</td>\n",
       "      <td>6703-27-1</td>\n",
       "      <td>5486550</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>CC(=O)OC1C=CC2C3CC4=C5C2(C1OC5=C(C=C4)OC)CCN3C</td>\n",
       "      <td>Sedatives</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2c3c1OC1C(OC(C)=O)C=CC4C(C2)N(C)CCC341</td>\n",
       "      <td>3</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00011000</td>\n",
       "      <td>00101000</td>\n",
       "      <td>01111011</td>\n",
       "      <td>11111000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Codeine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C18H21NO3</td>\n",
       "      <td>299.4</td>\n",
       "      <td>76-57-3</td>\n",
       "      <td>5284371</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>CN1CCC23C4C1CC5=C2C(=C(C=C5)OC)OC3C(C=C4)O</td>\n",
       "      <td>Sedatives</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2c3c1OC1C(O)C=CC4C(C2)N(C)CCC341</td>\n",
       "      <td>3</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00111000</td>\n",
       "      <td>00101001</td>\n",
       "      <td>00111001</td>\n",
       "      <td>00101000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Hydrocodone</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C18H21NO3</td>\n",
       "      <td>299.4</td>\n",
       "      <td>125-29-1</td>\n",
       "      <td>5284569</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>CN1CCC23C4C1CC5=C2C(=C(C=C5)OC)OC3C(=O)CC4</td>\n",
       "      <td>Sedatives</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2c3c1OC1C(=O)CCC4C(C2)N(C)CCC314</td>\n",
       "      <td>3</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>01111001</td>\n",
       "      <td>00101001</td>\n",
       "      <td>11111011</td>\n",
       "      <td>01111111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>169</th>\n",
       "      <td>5-MeO-AMT</td>\n",
       "      <td>1-(5-methoxy-1H-indol-3-yl)propan-2-amine</td>\n",
       "      <td>C12H16N2O</td>\n",
       "      <td>204.27</td>\n",
       "      <td>1137-04-8</td>\n",
       "      <td>36906</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>CC(CC1=CNC2=C1C=C(C=C2)OC)N</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2[nH]cc(CC(C)N)c2c1</td>\n",
       "      <td>15</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0100000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>00010111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>00110000</td>\n",
       "      <td>00110110</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>170</th>\n",
       "      <td>5-MeO-MiPT</td>\n",
       "      <td>N-[2-(5-methoxy-1H-indol-3-yl)ethyl]-N-methylp...</td>\n",
       "      <td>C15H22N2O</td>\n",
       "      <td>246.35</td>\n",
       "      <td>96096-55-8</td>\n",
       "      <td>2763156</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>CC(C)N(C)CCC1=CNC2=C1C=C(C=C2)OC</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2[nH]cc(CCN(C)C(C)C)c2c1</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0100000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>01111111</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>171</th>\n",
       "      <td>5-MeO-DMT</td>\n",
       "      <td>5-Methoxy-N,N-dimethyltryptamine</td>\n",
       "      <td>C13H18N2O</td>\n",
       "      <td>218.29</td>\n",
       "      <td>1019-45-0</td>\n",
       "      <td>1832</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>CN(C)CCC1=CNC2=C1C=C(C=C2)OC</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2[nH]cc(CCN(C)C)c2c1</td>\n",
       "      <td>15</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>01111111</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>172</th>\n",
       "      <td>5-MeO-DiPT</td>\n",
       "      <td>5-Methoxy-N,N-diisopropyltryptamine</td>\n",
       "      <td>C17H26N2O</td>\n",
       "      <td>274.4</td>\n",
       "      <td>4021-34-5</td>\n",
       "      <td>151182</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>CC(C)N(CCC1=CNC2=C1C=C(C=C2)OC)C(C)C</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>COc1ccc2[nH]cc(CCN(C(C)C)C(C)C)c2c1</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0100000000000000000000000000000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>00110101</td>\n",
       "      <td>01111111</td>\n",
       "      <td>00110111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>173</th>\n",
       "      <td>5-MeO-DET</td>\n",
       "      <td>5-Methoxy-N,N-diethyltryptamine</td>\n",
       "      <td>C15H22N2O</td>\n",
       "      <td>246.35</td>\n",
       "      <td>1218-40-2</td>\n",
       "      <td>417608</td>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "      <td>CCN(CC)CCC1=CNC2=C1C=C(C=C2)OC</td>\n",
       "      <td>Serotonergic psychedelics</td>\n",
       "      <td>...</td>\n",
       "      <td>CCN(CC)CCc1c[nH]c2ccc(OC)cc12</td>\n",
       "      <td>17</td>\n",
       "      <td>0000000000000000000000000000000000000000000000...</td>\n",
       "      <td>0000000000000000000000000010000000000000000000...</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "      <td>11111111</td>\n",
       "      <td>01111111</td>\n",
       "      <td>00110111</td>\n",
       "      <td>11111111</td>\n",
       "      <td>01111111</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>174 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "              Name                                         Other name  \\\n",
       "0           Heroin                                                NaN   \n",
       "1         Morphine                                                NaN   \n",
       "2    Acetylcodeine                                    6-Acetylcodiene   \n",
       "3          Codeine                                                NaN   \n",
       "4      Hydrocodone                                                NaN   \n",
       "..             ...                                                ...   \n",
       "169      5-MeO-AMT          1-(5-methoxy-1H-indol-3-yl)propan-2-amine   \n",
       "170     5-MeO-MiPT  N-[2-(5-methoxy-1H-indol-3-yl)ethyl]-N-methylp...   \n",
       "171      5-MeO-DMT                   5-Methoxy-N,N-dimethyltryptamine   \n",
       "172     5-MeO-DiPT                5-Methoxy-N,N-diisopropyltryptamine   \n",
       "173      5-MeO-DET                    5-Methoxy-N,N-diethyltryptamine   \n",
       "\n",
       "       Formula      MW         CAS PubChem CID RotBondCount Conformers  \\\n",
       "0    C21H23NO5   369.4    561-27-3     5462328            4          9   \n",
       "1    C17H19NO3  285.34     57-27-2     5288826            0          1   \n",
       "2    C20H23NO4   341.4   6703-27-1     5486550            3          3   \n",
       "3    C18H21NO3   299.4     76-57-3     5284371            1          1   \n",
       "4    C18H21NO3   299.4    125-29-1     5284569            1          1   \n",
       "..         ...     ...         ...         ...          ...        ...   \n",
       "169  C12H16N2O  204.27   1137-04-8       36906            3          7   \n",
       "170  C15H22N2O  246.35  96096-55-8     2763156            5          7   \n",
       "171  C13H18N2O  218.29   1019-45-0        1832            4         10   \n",
       "172  C17H26N2O   274.4   4021-34-5      151182            6          4   \n",
       "173  C15H22N2O  246.35   1218-40-2      417608            6         10   \n",
       "\n",
       "                                      Canonical SMILES  \\\n",
       "0    CC(=O)OC1C=CC2C3CC4=C5C2(C1OC5=C(C=C4)OC(=O)C)...   \n",
       "1            CN1CCC23C4C1CC5=C2C(=C(C=C5)O)OC3C(C=C4)O   \n",
       "2       CC(=O)OC1C=CC2C3CC4=C5C2(C1OC5=C(C=C4)OC)CCN3C   \n",
       "3           CN1CCC23C4C1CC5=C2C(=C(C=C5)OC)OC3C(C=C4)O   \n",
       "4           CN1CCC23C4C1CC5=C2C(=C(C=C5)OC)OC3C(=O)CC4   \n",
       "..                                                 ...   \n",
       "169                        CC(CC1=CNC2=C1C=C(C=C2)OC)N   \n",
       "170                   CC(C)N(C)CCC1=CNC2=C1C=C(C=C2)OC   \n",
       "171                       CN(C)CCC1=CNC2=C1C=C(C=C2)OC   \n",
       "172               CC(C)N(CCC1=CNC2=C1C=C(C=C2)OC)C(C)C   \n",
       "173                     CCN(CC)CCC1=CNC2=C1C=C(C=C2)OC   \n",
       "\n",
       "                   Pharm class  ...  \\\n",
       "0                    Sedatives  ...   \n",
       "1                    Sedatives  ...   \n",
       "2                    Sedatives  ...   \n",
       "3                    Sedatives  ...   \n",
       "4                    Sedatives  ...   \n",
       "..                         ...  ...   \n",
       "169  Serotonergic psychedelics  ...   \n",
       "170  Serotonergic psychedelics  ...   \n",
       "171  Serotonergic psychedelics  ...   \n",
       "172  Serotonergic psychedelics  ...   \n",
       "173  Serotonergic psychedelics  ...   \n",
       "\n",
       "                                      Canonical smiles MCS_K  \\\n",
       "0    CC(=O)Oc1ccc2c3c1OC1C(OC(C)=O)C=CC4C(C2)N(C)CC...     3   \n",
       "1                 CN1CCC23c4c5ccc(O)c4OC2C(O)C=CC3C1C5     3   \n",
       "2        COc1ccc2c3c1OC1C(OC(C)=O)C=CC4C(C2)N(C)CCC341     3   \n",
       "3              COc1ccc2c3c1OC1C(O)C=CC4C(C2)N(C)CCC341     3   \n",
       "4              COc1ccc2c3c1OC1C(=O)CCC4C(C2)N(C)CCC314     3   \n",
       "..                                                 ...   ...   \n",
       "169                         COc1ccc2[nH]cc(CC(C)N)c2c1    15   \n",
       "170                    COc1ccc2[nH]cc(CCN(C)C(C)C)c2c1    17   \n",
       "171                        COc1ccc2[nH]cc(CCN(C)C)c2c1    15   \n",
       "172                COc1ccc2[nH]cc(CCN(C(C)C)C(C)C)c2c1    17   \n",
       "173                      CCN(CC)CCc1c[nH]c2ccc(OC)cc12    17   \n",
       "\n",
       "                                               maccsfp  \\\n",
       "0    0000000000000000000000000000000000000000000000...   \n",
       "1    0000000000000000000000000000000000000000000000...   \n",
       "2    0000000000000000000000000000000000000000000000...   \n",
       "3    0000000000000000000000000000000000000000000000...   \n",
       "4    0000000000000000000000000000000000000000000000...   \n",
       "..                                                 ...   \n",
       "169  0000000000000000000000000000000000000000000000...   \n",
       "170  0000000000000000000000000000000000000000000000...   \n",
       "171  0000000000000000000000000000000000000000000000...   \n",
       "172  0000000000000000000000000000000000000000000000...   \n",
       "173  0000000000000000000000000000000000000000000000...   \n",
       "\n",
       "                                              morganfp  \\\n",
       "0    0000000000000000000000000000000000000000000000...   \n",
       "1    0000000000000000000000000000000000000000000000...   \n",
       "2    0000000000000000000000000000000000000000000000...   \n",
       "3    0000000000000000000000000000000000000000000000...   \n",
       "4    0000000000000000000000000000000000000000000000...   \n",
       "..                                                 ...   \n",
       "169  0100000000000000000000000000000000000000000000...   \n",
       "170  0100000000000000000000000000000000000000000000...   \n",
       "171  0000000000000000000000000000000000000000000000...   \n",
       "172  0100000000000000000000000000000000000000000000...   \n",
       "173  0000000000000000000000000010000000000000000000...   \n",
       "\n",
       "                                                    fp Phfp_BNB_maccs  \\\n",
       "0    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11101111   \n",
       "1    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "2    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "3    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "4    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "..                                                 ...            ...   \n",
       "169  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       00010111   \n",
       "170  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "171  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "172  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "173  [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...       11111111   \n",
       "\n",
       "    Phfp_SVM_maccs Phfp_RF_maccs Phfp_KNN_maccs Phfp_MLP_maccs  \n",
       "0         00001000      00001000       01111001       00001000  \n",
       "1         00111000      00101000       01101000       00111100  \n",
       "2         00011000      00101000       01111011       11111000  \n",
       "3         00111000      00101001       00111001       00101000  \n",
       "4         01111001      00101001       11111011       01111111  \n",
       "..             ...           ...            ...            ...  \n",
       "169       00110111      00110000       00110110       00110111  \n",
       "170       00111111      00110111       01111111       00110111  \n",
       "171       00110111      00110111       01111111       00110111  \n",
       "172       00110111      00110101       01111111       00110111  \n",
       "173       01111111      00110111       11111111       01111111  \n",
       "\n",
       "[174 rows x 33 columns]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "NPS"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "dc288ca0",
   "metadata": {},
   "outputs": [],
   "source": [
    "NPS.drop([\"fp\"],axis=1).to_csv(output_path+\"Drugs Raman or SERS in literature _ Paper 1.csv\",index=False)\n",
    "NPS_decoy.drop([\"fp\"],axis=1).to_csv(output_path+\"Inactives Drugs Raman or SERS in literature _ Paper 1.csv\",index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bfcd091c",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}