Bioinformatics_Drug_Discovery_Using_Machine_Learning.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Bioinformatics - Drug Discovery Using Machine Learning.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyMEkUYj/fdur+vo25wTZq9W",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/galib96/drug-discovery-ml/blob/main/Bioinformatics_Drug_Discovery_Using_Machine_Learning.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 506
        },
        "id": "6vwW182eeMTv",
        "outputId": "f48b5c90-db04-4a32-a97b-e10f5e3d62be"
      },
      "source": [
        "!pip install chembl-webresource-client"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: chembl-webresource-client in /usr/local/lib/python3.7/dist-packages (0.10.7)\n",
            "Requirement already satisfied: urllib3 in /usr/local/lib/python3.7/dist-packages (from chembl-webresource-client) (1.24.3)\n",
            "Requirement already satisfied: easydict in /usr/local/lib/python3.7/dist-packages (from chembl-webresource-client) (1.9)\n",
            "Requirement already satisfied: requests-cache~=0.7.0 in /usr/local/lib/python3.7/dist-packages (from chembl-webresource-client) (0.7.5)\n",
            "Requirement already satisfied: requests>=2.18.4 in /usr/local/lib/python3.7/dist-packages (from chembl-webresource-client) (2.23.0)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests>=2.18.4->chembl-webresource-client) (2.10)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests>=2.18.4->chembl-webresource-client) (3.0.4)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests>=2.18.4->chembl-webresource-client) (2021.10.8)\n",
            "Requirement already satisfied: attrs<22.0,>=21.2 in /usr/local/lib/python3.7/dist-packages (from requests-cache~=0.7.0->chembl-webresource-client) (21.4.0)\n",
            "Requirement already satisfied: itsdangerous>=2.0.1 in /usr/local/lib/python3.7/dist-packages (from requests-cache~=0.7.0->chembl-webresource-client) (2.1.2)\n",
            "Collecting pyyaml>=5.4\n",
            "  Using cached PyYAML-6.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (596 kB)\n",
            "Requirement already satisfied: url-normalize<2.0,>=1.4 in /usr/local/lib/python3.7/dist-packages (from requests-cache~=0.7.0->chembl-webresource-client) (1.4.3)\n",
            "Requirement already satisfied: six in /usr/local/lib/python3.7/dist-packages (from url-normalize<2.0,>=1.4->requests-cache~=0.7.0->chembl-webresource-client) (1.15.0)\n",
            "Installing collected packages: pyyaml\n",
            "  Attempting uninstall: pyyaml\n",
            "    Found existing installation: PyYAML 5.3.1\n",
            "    Uninstalling PyYAML-5.3.1:\n",
            "      Successfully uninstalled PyYAML-5.3.1\n",
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "lazypredict 0.2.9 requires PyYAML==5.3.1, but you have pyyaml 6.0 which is incompatible.\u001b[0m\n",
            "Successfully installed pyyaml-6.0\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "yaml"
                ]
              }
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VbwJRXTkc9ip"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "\n",
        "from chembl_webresource_client.new_client import new_client"
      ],
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 641
        },
        "id": "uYm2yLTbxf5W",
        "outputId": "fe192fa1-3bbb-45c7-d2f8-7a0bd83f7ff9"
      },
      "source": [
        "# target search for Dengue virus\n",
        "\n",
        "target = new_client.target\n",
        "target_query = target.search(\"Dengue virus\")\n",
        "target_df = pd.DataFrame.from_dict(target_query)\n",
        "\n",
        "target_df"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                      cross_references  \\\n",
              "0                                                   []   \n",
              "1                                                   []   \n",
              "2                                                   []   \n",
              "3                                                   []   \n",
              "4                                                   []   \n",
              "..                                                 ...   \n",
              "165  [{'xref_id': 'P10274', 'xref_name': None, 'xre...   \n",
              "166                                                 []   \n",
              "167  [{'xref_id': 'Q69422', 'xref_name': None, 'xre...   \n",
              "168                                                 []   \n",
              "169                                                 []   \n",
              "\n",
              "                                              organism  \\\n",
              "0                                         Dengue virus   \n",
              "1                                       Dengue virus 1   \n",
              "2                                       Dengue virus 2   \n",
              "3                                       Dengue virus 3   \n",
              "4                                       Dengue virus 4   \n",
              "..                                                 ...   \n",
              "165  Human T-cell leukemia virus 1 (strain Japan AT...   \n",
              "166  Human immunodeficiency virus type 1 (RF/HAT IS...   \n",
              "167                               Hepatitis GB virus B   \n",
              "168                                       Homo sapiens   \n",
              "169                                       Homo sapiens   \n",
              "\n",
              "                                             pref_name  score  \\\n",
              "0                                         Dengue virus  24.00   \n",
              "1                                       Dengue virus 1  21.00   \n",
              "2                                       Dengue virus 2  21.00   \n",
              "3                                       Dengue virus 3  21.00   \n",
              "4                                  Dengue virus type 4  18.00   \n",
              "..                                                 ...    ...   \n",
              "165        Human T-cell leukemia virus type I protease   4.00   \n",
              "166  Human immunodeficiency virus type 1 (RF/HAT IS...   4.00   \n",
              "167  Hepatitis GB virus B NS5B RNA-dependent RNA po...   4.00   \n",
              "168                                Sharpin/RBCK1/RNF31   4.00   \n",
              "169                                       80S Ribosome   0.00   \n",
              "\n",
              "     species_group_flag target_chembl_id  \\\n",
              "0                 False     CHEMBL613757   \n",
              "1                 False     CHEMBL613360   \n",
              "2                 False     CHEMBL613966   \n",
              "3                 False     CHEMBL612717   \n",
              "4                 False     CHEMBL613728   \n",
              "..                  ...              ...   \n",
              "165               False       CHEMBL3346   \n",
              "166               False     CHEMBL613498   \n",
              "167               False       CHEMBL5981   \n",
              "168               False    CHEMBL4296109   \n",
              "169               False    CHEMBL3987582   \n",
              "\n",
              "                                     target_components  \\\n",
              "0                                                   []   \n",
              "1                                                   []   \n",
              "2                                                   []   \n",
              "3                                                   []   \n",
              "4                                                   []   \n",
              "..                                                 ...   \n",
              "165  [{'accession': 'P10274', 'component_descriptio...   \n",
              "166                                                 []   \n",
              "167  [{'accession': 'Q69422', 'component_descriptio...   \n",
              "168  [{'accession': 'Q9H0F6', 'component_descriptio...   \n",
              "169  [{'accession': 'P08865', 'component_descriptio...   \n",
              "\n",
              "                      target_type  tax_id  \n",
              "0                        ORGANISM   12637  \n",
              "1                        ORGANISM   11053  \n",
              "2                        ORGANISM   11060  \n",
              "3                        ORGANISM   11069  \n",
              "4                        ORGANISM   11070  \n",
              "..                            ...     ...  \n",
              "165                SINGLE PROTEIN   11926  \n",
              "166                      ORGANISM   11701  \n",
              "167                SINGLE PROTEIN   39113  \n",
              "168               PROTEIN COMPLEX    9606  \n",
              "169  PROTEIN NUCLEIC-ACID COMPLEX    9606  \n",
              "\n",
              "[170 rows x 9 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-8487f8d2-370f-455e-9378-5c260bf9ad0c\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>cross_references</th>\n",
              "      <th>organism</th>\n",
              "      <th>pref_name</th>\n",
              "      <th>score</th>\n",
              "      <th>species_group_flag</th>\n",
              "      <th>target_chembl_id</th>\n",
              "      <th>target_components</th>\n",
              "      <th>target_type</th>\n",
              "      <th>tax_id</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>[]</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>24.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL613757</td>\n",
              "      <td>[]</td>\n",
              "      <td>ORGANISM</td>\n",
              "      <td>12637</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>[]</td>\n",
              "      <td>Dengue virus 1</td>\n",
              "      <td>Dengue virus 1</td>\n",
              "      <td>21.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL613360</td>\n",
              "      <td>[]</td>\n",
              "      <td>ORGANISM</td>\n",
              "      <td>11053</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>[]</td>\n",
              "      <td>Dengue virus 2</td>\n",
              "      <td>Dengue virus 2</td>\n",
              "      <td>21.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL613966</td>\n",
              "      <td>[]</td>\n",
              "      <td>ORGANISM</td>\n",
              "      <td>11060</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>[]</td>\n",
              "      <td>Dengue virus 3</td>\n",
              "      <td>Dengue virus 3</td>\n",
              "      <td>21.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL612717</td>\n",
              "      <td>[]</td>\n",
              "      <td>ORGANISM</td>\n",
              "      <td>11069</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>[]</td>\n",
              "      <td>Dengue virus 4</td>\n",
              "      <td>Dengue virus type 4</td>\n",
              "      <td>18.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL613728</td>\n",
              "      <td>[]</td>\n",
              "      <td>ORGANISM</td>\n",
              "      <td>11070</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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>165</th>\n",
              "      <td>[{'xref_id': 'P10274', 'xref_name': None, 'xre...</td>\n",
              "      <td>Human T-cell leukemia virus 1 (strain Japan AT...</td>\n",
              "      <td>Human T-cell leukemia virus type I protease</td>\n",
              "      <td>4.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL3346</td>\n",
              "      <td>[{'accession': 'P10274', 'component_descriptio...</td>\n",
              "      <td>SINGLE PROTEIN</td>\n",
              "      <td>11926</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>166</th>\n",
              "      <td>[]</td>\n",
              "      <td>Human immunodeficiency virus type 1 (RF/HAT IS...</td>\n",
              "      <td>Human immunodeficiency virus type 1 (RF/HAT IS...</td>\n",
              "      <td>4.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL613498</td>\n",
              "      <td>[]</td>\n",
              "      <td>ORGANISM</td>\n",
              "      <td>11701</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>167</th>\n",
              "      <td>[{'xref_id': 'Q69422', 'xref_name': None, 'xre...</td>\n",
              "      <td>Hepatitis GB virus B</td>\n",
              "      <td>Hepatitis GB virus B NS5B RNA-dependent RNA po...</td>\n",
              "      <td>4.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL5981</td>\n",
              "      <td>[{'accession': 'Q69422', 'component_descriptio...</td>\n",
              "      <td>SINGLE PROTEIN</td>\n",
              "      <td>39113</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>168</th>\n",
              "      <td>[]</td>\n",
              "      <td>Homo sapiens</td>\n",
              "      <td>Sharpin/RBCK1/RNF31</td>\n",
              "      <td>4.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL4296109</td>\n",
              "      <td>[{'accession': 'Q9H0F6', 'component_descriptio...</td>\n",
              "      <td>PROTEIN COMPLEX</td>\n",
              "      <td>9606</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>169</th>\n",
              "      <td>[]</td>\n",
              "      <td>Homo sapiens</td>\n",
              "      <td>80S Ribosome</td>\n",
              "      <td>0.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL3987582</td>\n",
              "      <td>[{'accession': 'P08865', 'component_descriptio...</td>\n",
              "      <td>PROTEIN NUCLEIC-ACID COMPLEX</td>\n",
              "      <td>9606</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>170 rows × 9 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-8487f8d2-370f-455e-9378-5c260bf9ad0c')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-8487f8d2-370f-455e-9378-5c260bf9ad0c button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-8487f8d2-370f-455e-9378-5c260bf9ad0c');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 125
        },
        "id": "BaiQBugP0JSl",
        "outputId": "a3974cc5-5d94-4ada-d7c7-a022c746043c"
      },
      "source": [
        "target_df[(target_df['target_type']=='SINGLE PROTEIN') & (target_df['organism']=='Dengue virus')]"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  cross_references      organism                pref_name  score  \\\n",
              "6               []  Dengue virus  Nonstructural protein 5  14.00   \n",
              "\n",
              "   species_group_flag target_chembl_id  \\\n",
              "6               False    CHEMBL4295629   \n",
              "\n",
              "                                   target_components     target_type  tax_id  \n",
              "6  [{'accession': 'V5TFZ2', 'component_descriptio...  SINGLE PROTEIN   12637  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-fdb5650b-9095-452c-ae45-d2a1ac798b38\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>cross_references</th>\n",
              "      <th>organism</th>\n",
              "      <th>pref_name</th>\n",
              "      <th>score</th>\n",
              "      <th>species_group_flag</th>\n",
              "      <th>target_chembl_id</th>\n",
              "      <th>target_components</th>\n",
              "      <th>target_type</th>\n",
              "      <th>tax_id</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>[]</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>14.00</td>\n",
              "      <td>False</td>\n",
              "      <td>CHEMBL4295629</td>\n",
              "      <td>[{'accession': 'V5TFZ2', 'component_descriptio...</td>\n",
              "      <td>SINGLE PROTEIN</td>\n",
              "      <td>12637</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-fdb5650b-9095-452c-ae45-d2a1ac798b38')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-fdb5650b-9095-452c-ae45-d2a1ac798b38 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-fdb5650b-9095-452c-ae45-d2a1ac798b38');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3rx2ZcKR1aSC",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "outputId": "154a7768-cde9-4e45-b17a-ef8eabaaf767"
      },
      "source": [
        "selected_target = target_df.target_chembl_id[6]\n",
        "selected_target"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'CHEMBL4295629'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "O7Cl0qF1HUGt"
      },
      "source": [
        "activity = new_client.activity\n",
        "res = activity.filter(target_chembl_id=selected_target).filter(standard_type='IC50')"
      ],
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 473
        },
        "id": "e36gujjlH8Nn",
        "outputId": "24badc72-ef2c-45fc-af4a-f8ee448ebe1c"
      },
      "source": [
        "df = pd.DataFrame.from_dict(res)\n",
        "df.head()"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  activity_comment  activity_id activity_properties assay_chembl_id  \\\n",
              "0             None     18297472                  []   CHEMBL4123978   \n",
              "1             None     18297475                  []   CHEMBL4123975   \n",
              "2             None     18297488                  []   CHEMBL4123982   \n",
              "3             None     18297489                  []   CHEMBL4123982   \n",
              "4             None     18297490                  []   CHEMBL4123982   \n",
              "\n",
              "                                   assay_description assay_type  \\\n",
              "0  Inhibition of Dengue virus 4 NS5 full length R...          B   \n",
              "1  Inhibition of Dengue virus 2 NS5 full length R...          B   \n",
              "2  Inhibition of Dengue virus RdRp activity using...          B   \n",
              "3  Inhibition of Dengue virus RdRp activity using...          B   \n",
              "4  Inhibition of Dengue virus RdRp activity using...          B   \n",
              "\n",
              "  assay_variant_accession assay_variant_mutation bao_endpoint   bao_format  \\\n",
              "0                    None                   None  BAO_0000190  BAO_0000357   \n",
              "1                    None                   None  BAO_0000190  BAO_0000357   \n",
              "2                    None                   None  BAO_0000190  BAO_0000357   \n",
              "3                    None                   None  BAO_0000190  BAO_0000357   \n",
              "4                    None                   None  BAO_0000190  BAO_0000357   \n",
              "\n",
              "   ... target_organism         target_pref_name target_tax_id text_value  \\\n",
              "0  ...    Dengue virus  Nonstructural protein 5         12637       None   \n",
              "1  ...    Dengue virus  Nonstructural protein 5         12637       None   \n",
              "2  ...    Dengue virus  Nonstructural protein 5         12637       None   \n",
              "3  ...    Dengue virus  Nonstructural protein 5         12637       None   \n",
              "4  ...    Dengue virus  Nonstructural protein 5         12637       None   \n",
              "\n",
              "   toid  type  units    uo_units upper_value value  \n",
              "0  None  IC50     uM  UO_0000065        None  0.34  \n",
              "1  None  IC50     uM  UO_0000065        None  0.36  \n",
              "2  None  IC50     uM  UO_0000065        None   5.0  \n",
              "3  None  IC50     uM  UO_0000065        None   1.6  \n",
              "4  None  IC50     uM  UO_0000065        None   2.0  \n",
              "\n",
              "[5 rows x 45 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-f1ecb93e-08a4-4e82-af15-fd690b74b6fa\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>activity_comment</th>\n",
              "      <th>activity_id</th>\n",
              "      <th>activity_properties</th>\n",
              "      <th>assay_chembl_id</th>\n",
              "      <th>assay_description</th>\n",
              "      <th>assay_type</th>\n",
              "      <th>assay_variant_accession</th>\n",
              "      <th>assay_variant_mutation</th>\n",
              "      <th>bao_endpoint</th>\n",
              "      <th>bao_format</th>\n",
              "      <th>...</th>\n",
              "      <th>target_organism</th>\n",
              "      <th>target_pref_name</th>\n",
              "      <th>target_tax_id</th>\n",
              "      <th>text_value</th>\n",
              "      <th>toid</th>\n",
              "      <th>type</th>\n",
              "      <th>units</th>\n",
              "      <th>uo_units</th>\n",
              "      <th>upper_value</th>\n",
              "      <th>value</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>None</td>\n",
              "      <td>18297472</td>\n",
              "      <td>[]</td>\n",
              "      <td>CHEMBL4123978</td>\n",
              "      <td>Inhibition of Dengue virus 4 NS5 full length R...</td>\n",
              "      <td>B</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>BAO_0000190</td>\n",
              "      <td>BAO_0000357</td>\n",
              "      <td>...</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>12637</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>IC50</td>\n",
              "      <td>uM</td>\n",
              "      <td>UO_0000065</td>\n",
              "      <td>None</td>\n",
              "      <td>0.34</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>None</td>\n",
              "      <td>18297475</td>\n",
              "      <td>[]</td>\n",
              "      <td>CHEMBL4123975</td>\n",
              "      <td>Inhibition of Dengue virus 2 NS5 full length R...</td>\n",
              "      <td>B</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>BAO_0000190</td>\n",
              "      <td>BAO_0000357</td>\n",
              "      <td>...</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>12637</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>IC50</td>\n",
              "      <td>uM</td>\n",
              "      <td>UO_0000065</td>\n",
              "      <td>None</td>\n",
              "      <td>0.36</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>None</td>\n",
              "      <td>18297488</td>\n",
              "      <td>[]</td>\n",
              "      <td>CHEMBL4123982</td>\n",
              "      <td>Inhibition of Dengue virus RdRp activity using...</td>\n",
              "      <td>B</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>BAO_0000190</td>\n",
              "      <td>BAO_0000357</td>\n",
              "      <td>...</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>12637</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>IC50</td>\n",
              "      <td>uM</td>\n",
              "      <td>UO_0000065</td>\n",
              "      <td>None</td>\n",
              "      <td>5.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>None</td>\n",
              "      <td>18297489</td>\n",
              "      <td>[]</td>\n",
              "      <td>CHEMBL4123982</td>\n",
              "      <td>Inhibition of Dengue virus RdRp activity using...</td>\n",
              "      <td>B</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>BAO_0000190</td>\n",
              "      <td>BAO_0000357</td>\n",
              "      <td>...</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>12637</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>IC50</td>\n",
              "      <td>uM</td>\n",
              "      <td>UO_0000065</td>\n",
              "      <td>None</td>\n",
              "      <td>1.6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>None</td>\n",
              "      <td>18297490</td>\n",
              "      <td>[]</td>\n",
              "      <td>CHEMBL4123982</td>\n",
              "      <td>Inhibition of Dengue virus RdRp activity using...</td>\n",
              "      <td>B</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>BAO_0000190</td>\n",
              "      <td>BAO_0000357</td>\n",
              "      <td>...</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>12637</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>IC50</td>\n",
              "      <td>uM</td>\n",
              "      <td>UO_0000065</td>\n",
              "      <td>None</td>\n",
              "      <td>2.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 45 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f1ecb93e-08a4-4e82-af15-fd690b74b6fa')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-f1ecb93e-08a4-4e82-af15-fd690b74b6fa button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-f1ecb93e-08a4-4e82-af15-fd690b74b6fa');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KkTmXh_5IN-b",
        "outputId": "3a92c664-4423-4941-ed54-990a9e6d45b3"
      },
      "source": [
        "df.standard_type.unique()"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['IC50'], dtype=object)"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "s5nh3LTWKuvb"
      },
      "source": [
        "df.to_csv('bioactivity_data_dengue.csv', index=False)"
      ],
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NagMGji3JFZ0",
        "outputId": "b57ab676-9f0b-4bc7-af80-56f570e84fe8"
      },
      "source": [
        "from google.colab import drive\n",
        "\n",
        "drive.mount('/content/gdrive/')"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/gdrive/; to attempt to forcibly remount, call drive.mount(\"/content/gdrive/\", force_remount=True).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PF9PdeC3KNG8"
      },
      "source": [
        "#!mkdir '/content/gdrive/My Drive/Colab Notebooks/Bioinformatics Project/data'"
      ],
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "24bUWAu1KjFM"
      },
      "source": [
        "!cp bioactivity_data_dengue.csv '/content/gdrive/My Drive/Colab Notebooks/Bioinformatics Project/data'"
      ],
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 490
        },
        "id": "mEtFYruRLPiE",
        "outputId": "ac688f06-b12d-4423-fa87-f8753ea8f8e2"
      },
      "source": [
        "df_clean = df[df['standard_value'].notna()]\n",
        "df_clean = df_clean[df_clean['canonical_smiles'].notna()]\n",
        "df_clean.drop_duplicates(['canonical_smiles'], inplace = True)\n",
        "\n",
        "print(df_clean.shape)\n",
        "df_clean.head()"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(62, 45)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  activity_comment  activity_id activity_properties assay_chembl_id  \\\n",
              "0             None     18297472                  []   CHEMBL4123978   \n",
              "1             None     18297475                  []   CHEMBL4123975   \n",
              "2             None     18297488                  []   CHEMBL4123982   \n",
              "3             None     18297489                  []   CHEMBL4123982   \n",
              "4             None     18297490                  []   CHEMBL4123982   \n",
              "\n",
              "                                   assay_description assay_type  \\\n",
              "0  Inhibition of Dengue virus 4 NS5 full length R...          B   \n",
              "1  Inhibition of Dengue virus 2 NS5 full length R...          B   \n",
              "2  Inhibition of Dengue virus RdRp activity using...          B   \n",
              "3  Inhibition of Dengue virus RdRp activity using...          B   \n",
              "4  Inhibition of Dengue virus RdRp activity using...          B   \n",
              "\n",
              "  assay_variant_accession assay_variant_mutation bao_endpoint   bao_format  \\\n",
              "0                    None                   None  BAO_0000190  BAO_0000357   \n",
              "1                    None                   None  BAO_0000190  BAO_0000357   \n",
              "2                    None                   None  BAO_0000190  BAO_0000357   \n",
              "3                    None                   None  BAO_0000190  BAO_0000357   \n",
              "4                    None                   None  BAO_0000190  BAO_0000357   \n",
              "\n",
              "   ... target_organism         target_pref_name target_tax_id text_value  \\\n",
              "0  ...    Dengue virus  Nonstructural protein 5         12637       None   \n",
              "1  ...    Dengue virus  Nonstructural protein 5         12637       None   \n",
              "2  ...    Dengue virus  Nonstructural protein 5         12637       None   \n",
              "3  ...    Dengue virus  Nonstructural protein 5         12637       None   \n",
              "4  ...    Dengue virus  Nonstructural protein 5         12637       None   \n",
              "\n",
              "   toid  type  units    uo_units upper_value value  \n",
              "0  None  IC50     uM  UO_0000065        None  0.34  \n",
              "1  None  IC50     uM  UO_0000065        None  0.36  \n",
              "2  None  IC50     uM  UO_0000065        None   5.0  \n",
              "3  None  IC50     uM  UO_0000065        None   1.6  \n",
              "4  None  IC50     uM  UO_0000065        None   2.0  \n",
              "\n",
              "[5 rows x 45 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-5422e8fa-1dec-4ed8-9457-e1e721bc7eb3\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>activity_comment</th>\n",
              "      <th>activity_id</th>\n",
              "      <th>activity_properties</th>\n",
              "      <th>assay_chembl_id</th>\n",
              "      <th>assay_description</th>\n",
              "      <th>assay_type</th>\n",
              "      <th>assay_variant_accession</th>\n",
              "      <th>assay_variant_mutation</th>\n",
              "      <th>bao_endpoint</th>\n",
              "      <th>bao_format</th>\n",
              "      <th>...</th>\n",
              "      <th>target_organism</th>\n",
              "      <th>target_pref_name</th>\n",
              "      <th>target_tax_id</th>\n",
              "      <th>text_value</th>\n",
              "      <th>toid</th>\n",
              "      <th>type</th>\n",
              "      <th>units</th>\n",
              "      <th>uo_units</th>\n",
              "      <th>upper_value</th>\n",
              "      <th>value</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>None</td>\n",
              "      <td>18297472</td>\n",
              "      <td>[]</td>\n",
              "      <td>CHEMBL4123978</td>\n",
              "      <td>Inhibition of Dengue virus 4 NS5 full length R...</td>\n",
              "      <td>B</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>BAO_0000190</td>\n",
              "      <td>BAO_0000357</td>\n",
              "      <td>...</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>12637</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>IC50</td>\n",
              "      <td>uM</td>\n",
              "      <td>UO_0000065</td>\n",
              "      <td>None</td>\n",
              "      <td>0.34</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>None</td>\n",
              "      <td>18297475</td>\n",
              "      <td>[]</td>\n",
              "      <td>CHEMBL4123975</td>\n",
              "      <td>Inhibition of Dengue virus 2 NS5 full length R...</td>\n",
              "      <td>B</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>BAO_0000190</td>\n",
              "      <td>BAO_0000357</td>\n",
              "      <td>...</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>12637</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>IC50</td>\n",
              "      <td>uM</td>\n",
              "      <td>UO_0000065</td>\n",
              "      <td>None</td>\n",
              "      <td>0.36</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>None</td>\n",
              "      <td>18297488</td>\n",
              "      <td>[]</td>\n",
              "      <td>CHEMBL4123982</td>\n",
              "      <td>Inhibition of Dengue virus RdRp activity using...</td>\n",
              "      <td>B</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>BAO_0000190</td>\n",
              "      <td>BAO_0000357</td>\n",
              "      <td>...</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>12637</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>IC50</td>\n",
              "      <td>uM</td>\n",
              "      <td>UO_0000065</td>\n",
              "      <td>None</td>\n",
              "      <td>5.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>None</td>\n",
              "      <td>18297489</td>\n",
              "      <td>[]</td>\n",
              "      <td>CHEMBL4123982</td>\n",
              "      <td>Inhibition of Dengue virus RdRp activity using...</td>\n",
              "      <td>B</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>BAO_0000190</td>\n",
              "      <td>BAO_0000357</td>\n",
              "      <td>...</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>12637</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>IC50</td>\n",
              "      <td>uM</td>\n",
              "      <td>UO_0000065</td>\n",
              "      <td>None</td>\n",
              "      <td>1.6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>None</td>\n",
              "      <td>18297490</td>\n",
              "      <td>[]</td>\n",
              "      <td>CHEMBL4123982</td>\n",
              "      <td>Inhibition of Dengue virus RdRp activity using...</td>\n",
              "      <td>B</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>BAO_0000190</td>\n",
              "      <td>BAO_0000357</td>\n",
              "      <td>...</td>\n",
              "      <td>Dengue virus</td>\n",
              "      <td>Nonstructural protein 5</td>\n",
              "      <td>12637</td>\n",
              "      <td>None</td>\n",
              "      <td>None</td>\n",
              "      <td>IC50</td>\n",
              "      <td>uM</td>\n",
              "      <td>UO_0000065</td>\n",
              "      <td>None</td>\n",
              "      <td>2.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 45 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-5422e8fa-1dec-4ed8-9457-e1e721bc7eb3')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-5422e8fa-1dec-4ed8-9457-e1e721bc7eb3 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-5422e8fa-1dec-4ed8-9457-e1e721bc7eb3');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "u1X4WhO-L7Ic",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "outputId": "38845848-20b0-4489-ff52-0e5b56ae34fb"
      },
      "source": [
        "selection = ['molecule_chembl_id','canonical_smiles','standard_value']\n",
        "df_activity = df_clean[selection]\n",
        "\n",
        "df_activity.head()"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  molecule_chembl_id                                   canonical_smiles  \\\n",
              "0      CHEMBL4126343  N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...   \n",
              "1      CHEMBL3417270  [N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...   \n",
              "2       CHEMBL521487  C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...   \n",
              "3      CHEMBL4127092  C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...   \n",
              "4      CHEMBL4127819  CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...   \n",
              "\n",
              "  standard_value  \n",
              "0          340.0  \n",
              "1          360.0  \n",
              "2         5000.0  \n",
              "3         1600.0  \n",
              "4         2000.0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-7bb6984a-67c1-44b7-acae-4782314bddcd\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>molecule_chembl_id</th>\n",
              "      <th>canonical_smiles</th>\n",
              "      <th>standard_value</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>CHEMBL4126343</td>\n",
              "      <td>N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...</td>\n",
              "      <td>340.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>CHEMBL3417270</td>\n",
              "      <td>[N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...</td>\n",
              "      <td>360.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>CHEMBL521487</td>\n",
              "      <td>C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...</td>\n",
              "      <td>5000.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>CHEMBL4127092</td>\n",
              "      <td>C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...</td>\n",
              "      <td>1600.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>CHEMBL4127819</td>\n",
              "      <td>CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...</td>\n",
              "      <td>2000.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7bb6984a-67c1-44b7-acae-4782314bddcd')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-7bb6984a-67c1-44b7-acae-4782314bddcd button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-7bb6984a-67c1-44b7-acae-4782314bddcd');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PgwHAFLWlHNx"
      },
      "source": [
        "def activity_classifier(sv):\n",
        "\n",
        "    if float(sv) >= 10000:\n",
        "        return \"inactive\"\n",
        "    elif float(sv) <= 1000:\n",
        "        return \"active\"\n",
        "    else:\n",
        "        return \"intermediate\""
      ],
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "dER3eTGslqfz",
        "outputId": "718116d9-2312-4b50-bf2e-2834ad38acb7"
      },
      "source": [
        "df_activity['class'] = df_activity['standard_value'].apply(activity_classifier)\n",
        "\n",
        "df_activity.head()"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  molecule_chembl_id                                   canonical_smiles  \\\n",
              "0      CHEMBL4126343  N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...   \n",
              "1      CHEMBL3417270  [N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...   \n",
              "2       CHEMBL521487  C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...   \n",
              "3      CHEMBL4127092  C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...   \n",
              "4      CHEMBL4127819  CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...   \n",
              "\n",
              "  standard_value         class  \n",
              "0          340.0        active  \n",
              "1          360.0        active  \n",
              "2         5000.0  intermediate  \n",
              "3         1600.0  intermediate  \n",
              "4         2000.0  intermediate  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-ad9ebbbc-870b-49e1-8f54-c3b3dd6b1f9a\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>molecule_chembl_id</th>\n",
              "      <th>canonical_smiles</th>\n",
              "      <th>standard_value</th>\n",
              "      <th>class</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>CHEMBL4126343</td>\n",
              "      <td>N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...</td>\n",
              "      <td>340.0</td>\n",
              "      <td>active</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>CHEMBL3417270</td>\n",
              "      <td>[N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...</td>\n",
              "      <td>360.0</td>\n",
              "      <td>active</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>CHEMBL521487</td>\n",
              "      <td>C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...</td>\n",
              "      <td>5000.0</td>\n",
              "      <td>intermediate</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>CHEMBL4127092</td>\n",
              "      <td>C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...</td>\n",
              "      <td>1600.0</td>\n",
              "      <td>intermediate</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>CHEMBL4127819</td>\n",
              "      <td>CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...</td>\n",
              "      <td>2000.0</td>\n",
              "      <td>intermediate</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ad9ebbbc-870b-49e1-8f54-c3b3dd6b1f9a')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-ad9ebbbc-870b-49e1-8f54-c3b3dd6b1f9a button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-ad9ebbbc-870b-49e1-8f54-c3b3dd6b1f9a');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "HaM5DofHmpfG"
      },
      "source": [
        "df_activity.to_csv(\"bioactivity_dengue_preprocessed_data.csv\", index=False)\n",
        "\n",
        "!cp bioactivity_dengue_preprocessed_data.csv '/content/gdrive/My Drive/Colab Notebooks/Bioinformatics Project/data'"
      ],
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "viw7WmxgosCy",
        "outputId": "0b9c66ca-25c0-45fc-916c-bc2fa4cbd1be"
      },
      "source": [
        "!pip install rdkit-pypi"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: rdkit-pypi in /usr/local/lib/python3.7/dist-packages (2022.3.2.1)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (from rdkit-pypi) (1.19.1)\n",
            "Requirement already satisfied: Pillow in /usr/local/lib/python3.7/dist-packages (from rdkit-pypi) (7.1.2)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "m4MapgRSqHwo",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "outputId": "92108aaa-9ce1-45bb-c228-66be032f5f12"
      },
      "source": [
        "df_proc = pd.read_csv(\"/content/gdrive/My Drive/Colab Notebooks/Bioinformatics Project/data/bioactivity_dengue_preprocessed_data.csv\")\n",
        "df_proc.head()"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  molecule_chembl_id                                   canonical_smiles  \\\n",
              "0      CHEMBL4126343  N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...   \n",
              "1      CHEMBL3417270  [N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...   \n",
              "2       CHEMBL521487  C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...   \n",
              "3      CHEMBL4127092  C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...   \n",
              "4      CHEMBL4127819  CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...   \n",
              "\n",
              "   standard_value         class  \n",
              "0          340.00        active  \n",
              "1          360.00        active  \n",
              "2         5000.00  intermediate  \n",
              "3         1600.00  intermediate  \n",
              "4         2000.00  intermediate  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-04ef03e7-3c0d-4df5-a822-f874d644763b\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>molecule_chembl_id</th>\n",
              "      <th>canonical_smiles</th>\n",
              "      <th>standard_value</th>\n",
              "      <th>class</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>CHEMBL4126343</td>\n",
              "      <td>N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...</td>\n",
              "      <td>340.00</td>\n",
              "      <td>active</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>CHEMBL3417270</td>\n",
              "      <td>[N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...</td>\n",
              "      <td>360.00</td>\n",
              "      <td>active</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>CHEMBL521487</td>\n",
              "      <td>C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...</td>\n",
              "      <td>5000.00</td>\n",
              "      <td>intermediate</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>CHEMBL4127092</td>\n",
              "      <td>C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...</td>\n",
              "      <td>1600.00</td>\n",
              "      <td>intermediate</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>CHEMBL4127819</td>\n",
              "      <td>CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...</td>\n",
              "      <td>2000.00</td>\n",
              "      <td>intermediate</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-04ef03e7-3c0d-4df5-a822-f874d644763b')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-04ef03e7-3c0d-4df5-a822-f874d644763b button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-04ef03e7-3c0d-4df5-a822-f874d644763b');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "30ajf_hawdA3"
      },
      "source": [
        "##Lipinski's descriptors\n",
        "\n",
        "Christopher Lipinski, a scientist at Pfizer, came up with a set of rule-of-thumb for evaluating the druglikeness of compounds. Such druglikeness is based on the Absorption, Distribution, Metabolism and Excretion (ADME) that is also known as the pharmacokinetic profile. Lipinski analyzed all orally active FDA-approved drugs in the formulation of what is to be known as the Rule-of-Five or Lipinski's Rule.\n",
        "\n",
        "The Lipinski's Rule stated the following:\n",
        "\n",
        "* Molecular weight < 500 Dalton\n",
        "* Octanol-water partition coefficient (LogP) < 5\n",
        "* Hydrogen bond donors < 5\n",
        "* Hydrogen bond acceptors < 10"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IlmWvnf1u7b6"
      },
      "source": [
        "from rdkit import Chem\n",
        "from rdkit.Chem import Descriptors, Lipinski"
      ],
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 337
        },
        "id": "eddKhOjjx99p",
        "outputId": "62a40dce-331c-445b-957a-ffbd95dcc719"
      },
      "source": [
        "# calculate descriptors and lipinski values\n",
        "\n",
        "df_proc['canonical_smiles_mol'] = df_proc['canonical_smiles'].apply(Chem.MolFromSmiles)\n",
        "df_proc['mol_wt'] = df_proc['canonical_smiles_mol'].apply(Descriptors.MolWt)\n",
        "df_proc['mol_logp'] = df_proc['canonical_smiles_mol'].apply(Descriptors.MolLogP)\n",
        "df_proc['num_H_donors'] = df_proc['canonical_smiles_mol'].apply(Lipinski.NumHDonors)\n",
        "df_proc['num_H_acceptors'] = df_proc['canonical_smiles_mol'].apply(Lipinski.NumHAcceptors)\n",
        "\n",
        "df_proc.head()"
      ],
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  molecule_chembl_id                                   canonical_smiles  \\\n",
              "0      CHEMBL4126343  N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...   \n",
              "1      CHEMBL3417270  [N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...   \n",
              "2       CHEMBL521487  C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...   \n",
              "3      CHEMBL4127092  C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...   \n",
              "4      CHEMBL4127819  CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...   \n",
              "\n",
              "   standard_value         class  \\\n",
              "0          340.00        active   \n",
              "1          360.00        active   \n",
              "2         5000.00  intermediate   \n",
              "3         1600.00  intermediate   \n",
              "4         2000.00  intermediate   \n",
              "\n",
              "                               canonical_smiles_mol  mol_wt  mol_logp  \\\n",
              "0  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb080>  531.20     -1.13   \n",
              "1  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb030>  524.17     -1.57   \n",
              "2  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb120>  498.17     -2.11   \n",
              "3  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb170>  508.16     -2.50   \n",
              "4  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb1c0>  522.19     -2.11   \n",
              "\n",
              "   num_H_donors  num_H_acceptors  \n",
              "0             7               14  \n",
              "1             7               14  \n",
              "2             7               12  \n",
              "3             7               12  \n",
              "4             7               12  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-92a1ce2a-d332-4079-bb7b-690e3175e1b0\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>molecule_chembl_id</th>\n",
              "      <th>canonical_smiles</th>\n",
              "      <th>standard_value</th>\n",
              "      <th>class</th>\n",
              "      <th>canonical_smiles_mol</th>\n",
              "      <th>mol_wt</th>\n",
              "      <th>mol_logp</th>\n",
              "      <th>num_H_donors</th>\n",
              "      <th>num_H_acceptors</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>CHEMBL4126343</td>\n",
              "      <td>N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...</td>\n",
              "      <td>340.00</td>\n",
              "      <td>active</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb080&gt;</td>\n",
              "      <td>531.20</td>\n",
              "      <td>-1.13</td>\n",
              "      <td>7</td>\n",
              "      <td>14</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>CHEMBL3417270</td>\n",
              "      <td>[N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...</td>\n",
              "      <td>360.00</td>\n",
              "      <td>active</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb030&gt;</td>\n",
              "      <td>524.17</td>\n",
              "      <td>-1.57</td>\n",
              "      <td>7</td>\n",
              "      <td>14</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>CHEMBL521487</td>\n",
              "      <td>C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...</td>\n",
              "      <td>5000.00</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb120&gt;</td>\n",
              "      <td>498.17</td>\n",
              "      <td>-2.11</td>\n",
              "      <td>7</td>\n",
              "      <td>12</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>CHEMBL4127092</td>\n",
              "      <td>C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...</td>\n",
              "      <td>1600.00</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb170&gt;</td>\n",
              "      <td>508.16</td>\n",
              "      <td>-2.50</td>\n",
              "      <td>7</td>\n",
              "      <td>12</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>CHEMBL4127819</td>\n",
              "      <td>CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...</td>\n",
              "      <td>2000.00</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb1c0&gt;</td>\n",
              "      <td>522.19</td>\n",
              "      <td>-2.11</td>\n",
              "      <td>7</td>\n",
              "      <td>12</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-92a1ce2a-d332-4079-bb7b-690e3175e1b0')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-92a1ce2a-d332-4079-bb7b-690e3175e1b0 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-92a1ce2a-d332-4079-bb7b-690e3175e1b0');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def norm(x):\n",
        "    \"\"\"\n",
        "    to limit the standard value to 100  million\n",
        "    \"\"\"\n",
        "    if x > 100000000:\n",
        "        x = 100000000\n",
        "    return x"
      ],
      "metadata": {
        "id": "i7YrKfhxpzhM"
      },
      "execution_count": 23,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# restricting the standard value by applying the norm function and log10\n",
        "\n",
        "df_proc['pIC50'] = np.log10(df_proc['standard_value'].apply(norm))\n",
        "df_proc.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 444
        },
        "id": "ahogWwsOot0I",
        "outputId": "c024fbc4-5ada-4ec9-aafe-a03432a51f07"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  molecule_chembl_id                                   canonical_smiles  \\\n",
              "0      CHEMBL4126343  N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...   \n",
              "1      CHEMBL3417270  [N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...   \n",
              "2       CHEMBL521487  C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...   \n",
              "3      CHEMBL4127092  C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...   \n",
              "4      CHEMBL4127819  CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...   \n",
              "\n",
              "   standard_value         class  \\\n",
              "0          340.00        active   \n",
              "1          360.00        active   \n",
              "2         5000.00  intermediate   \n",
              "3         1600.00  intermediate   \n",
              "4         2000.00  intermediate   \n",
              "\n",
              "                               canonical_smiles_mol  mol_wt  mol_logp  \\\n",
              "0  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb080>  531.20     -1.13   \n",
              "1  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb030>  524.17     -1.57   \n",
              "2  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb120>  498.17     -2.11   \n",
              "3  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb170>  508.16     -2.50   \n",
              "4  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb1c0>  522.19     -2.11   \n",
              "\n",
              "   num_H_donors  num_H_acceptors  pIC50  \n",
              "0             7               14   2.53  \n",
              "1             7               14   2.56  \n",
              "2             7               12   3.70  \n",
              "3             7               12   3.20  \n",
              "4             7               12   3.30  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-135f4472-94d5-4a5f-b5cf-aa45abf53e1a\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>molecule_chembl_id</th>\n",
              "      <th>canonical_smiles</th>\n",
              "      <th>standard_value</th>\n",
              "      <th>class</th>\n",
              "      <th>canonical_smiles_mol</th>\n",
              "      <th>mol_wt</th>\n",
              "      <th>mol_logp</th>\n",
              "      <th>num_H_donors</th>\n",
              "      <th>num_H_acceptors</th>\n",
              "      <th>pIC50</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>CHEMBL4126343</td>\n",
              "      <td>N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...</td>\n",
              "      <td>340.00</td>\n",
              "      <td>active</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb080&gt;</td>\n",
              "      <td>531.20</td>\n",
              "      <td>-1.13</td>\n",
              "      <td>7</td>\n",
              "      <td>14</td>\n",
              "      <td>2.53</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>CHEMBL3417270</td>\n",
              "      <td>[N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...</td>\n",
              "      <td>360.00</td>\n",
              "      <td>active</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb030&gt;</td>\n",
              "      <td>524.17</td>\n",
              "      <td>-1.57</td>\n",
              "      <td>7</td>\n",
              "      <td>14</td>\n",
              "      <td>2.56</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>CHEMBL521487</td>\n",
              "      <td>C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...</td>\n",
              "      <td>5000.00</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb120&gt;</td>\n",
              "      <td>498.17</td>\n",
              "      <td>-2.11</td>\n",
              "      <td>7</td>\n",
              "      <td>12</td>\n",
              "      <td>3.70</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>CHEMBL4127092</td>\n",
              "      <td>C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...</td>\n",
              "      <td>1600.00</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb170&gt;</td>\n",
              "      <td>508.16</td>\n",
              "      <td>-2.50</td>\n",
              "      <td>7</td>\n",
              "      <td>12</td>\n",
              "      <td>3.20</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>CHEMBL4127819</td>\n",
              "      <td>CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...</td>\n",
              "      <td>2000.00</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb1c0&gt;</td>\n",
              "      <td>522.19</td>\n",
              "      <td>-2.11</td>\n",
              "      <td>7</td>\n",
              "      <td>12</td>\n",
              "      <td>3.30</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-135f4472-94d5-4a5f-b5cf-aa45abf53e1a')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-135f4472-94d5-4a5f-b5cf-aa45abf53e1a button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-135f4472-94d5-4a5f-b5cf-aa45abf53e1a');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# getting statistics of pIC50 values\n",
        "\n",
        "df_proc['pIC50'].describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LuWHcKzDqPwg",
        "outputId": "5abd84ee-cdb4-4e72-919b-75ae5d7a6b31"
      },
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "count   62.00\n",
              "mean     4.16\n",
              "std      1.05\n",
              "min      1.20\n",
              "25%      3.42\n",
              "50%      4.17\n",
              "75%      5.13\n",
              "max      5.66\n",
              "Name: pIC50, dtype: float64"
            ]
          },
          "metadata": {},
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# dropping the intermediate class\n",
        "\n",
        "df2 = df_proc[df_proc['class'] != 'intermediate']\n",
        "df2.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "JwgpXft4qT30",
        "outputId": "4ea038c0-735b-4a00-d68a-46dbe390736a"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  molecule_chembl_id                                   canonical_smiles  \\\n",
              "0      CHEMBL4126343  N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...   \n",
              "1      CHEMBL3417270  [N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...   \n",
              "5       CHEMBL486231  C[C@@]1(F)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...   \n",
              "6      CHEMBL4127921  C#C[C@@]1(F)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...   \n",
              "7      CHEMBL4129313  CC#C[C@@]1(F)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...   \n",
              "\n",
              "   standard_value     class                              canonical_smiles_mol  \\\n",
              "0          340.00    active  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb080>   \n",
              "1          360.00    active  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb030>   \n",
              "5        18000.00  inactive  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb210>   \n",
              "6        15900.00  inactive  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb260>   \n",
              "7        20000.00  inactive  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb2b0>   \n",
              "\n",
              "   mol_wt  mol_logp  num_H_donors  num_H_acceptors  pIC50  \n",
              "0  531.20     -1.13             7               14   2.53  \n",
              "1  524.17     -1.57             7               14   2.56  \n",
              "5  500.16     -1.13             6               11   4.26  \n",
              "6  510.15     -1.52             6               11   4.20  \n",
              "7  524.18     -1.13             6               11   4.30  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-cf0dd8d1-5425-4393-8a14-c025f8640772\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>molecule_chembl_id</th>\n",
              "      <th>canonical_smiles</th>\n",
              "      <th>standard_value</th>\n",
              "      <th>class</th>\n",
              "      <th>canonical_smiles_mol</th>\n",
              "      <th>mol_wt</th>\n",
              "      <th>mol_logp</th>\n",
              "      <th>num_H_donors</th>\n",
              "      <th>num_H_acceptors</th>\n",
              "      <th>pIC50</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>CHEMBL4126343</td>\n",
              "      <td>N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...</td>\n",
              "      <td>340.00</td>\n",
              "      <td>active</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb080&gt;</td>\n",
              "      <td>531.20</td>\n",
              "      <td>-1.13</td>\n",
              "      <td>7</td>\n",
              "      <td>14</td>\n",
              "      <td>2.53</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>CHEMBL3417270</td>\n",
              "      <td>[N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...</td>\n",
              "      <td>360.00</td>\n",
              "      <td>active</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb030&gt;</td>\n",
              "      <td>524.17</td>\n",
              "      <td>-1.57</td>\n",
              "      <td>7</td>\n",
              "      <td>14</td>\n",
              "      <td>2.56</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>CHEMBL486231</td>\n",
              "      <td>C[C@@]1(F)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...</td>\n",
              "      <td>18000.00</td>\n",
              "      <td>inactive</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb210&gt;</td>\n",
              "      <td>500.16</td>\n",
              "      <td>-1.13</td>\n",
              "      <td>6</td>\n",
              "      <td>11</td>\n",
              "      <td>4.26</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>CHEMBL4127921</td>\n",
              "      <td>C#C[C@@]1(F)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...</td>\n",
              "      <td>15900.00</td>\n",
              "      <td>inactive</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb260&gt;</td>\n",
              "      <td>510.15</td>\n",
              "      <td>-1.52</td>\n",
              "      <td>6</td>\n",
              "      <td>11</td>\n",
              "      <td>4.20</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>CHEMBL4129313</td>\n",
              "      <td>CC#C[C@@]1(F)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...</td>\n",
              "      <td>20000.00</td>\n",
              "      <td>inactive</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb2b0&gt;</td>\n",
              "      <td>524.18</td>\n",
              "      <td>-1.13</td>\n",
              "      <td>6</td>\n",
              "      <td>11</td>\n",
              "      <td>4.30</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-cf0dd8d1-5425-4393-8a14-c025f8640772')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-cf0dd8d1-5425-4393-8a14-c025f8640772 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-cf0dd8d1-5425-4393-8a14-c025f8640772');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import seaborn as sns\n",
        "sns.set(style= 'ticks')\n",
        "import matplotlib.pyplot as plt\n",
        "%matplotlib inline"
      ],
      "metadata": {
        "id": "amHQGgpvrYMB"
      },
      "execution_count": 27,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# frequency of Bioactivity class\n",
        "\n",
        "sns.countplot(x='class', data=df2)\n",
        "\n",
        "plt.xlabel('Bioactivity class')\n",
        "plt.ylabel('Frequency')\n",
        "\n",
        "plt.savefig('plot_bioactivity_class.pdf')\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 285
        },
        "id": "fOlDAI5Jr0aZ",
        "outputId": "14b80fd3-a0e3-411c-b6bf-f6b862ed3d40"
      },
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# molecular weight and log of standard P value\n",
        "\n",
        "sns.scatterplot(x='mol_wt', y='mol_logp', data=df2, hue='class', size='pIC50', alpha = 0.7)\n",
        "\n",
        "plt.xlabel('Molecular Weght')\n",
        "plt.ylabel('LogP')\n",
        "plt.legend(bbox_to_anchor=(1.05,1), loc=2, borderaxespad=0)\n",
        "plt.savefig('plot_mw_vs_logp.pdf')\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 287
        },
        "id": "cC8gfykPsgR7",
        "outputId": "90f00aec-a4d0-4a16-e006-f28b59196a6c"
      },
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Mann-Whitney U significance test"
      ],
      "metadata": {
        "id": "9NMRXl6CAwmJ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Running Mann-Whitney U test for statstically significant difference between classes\n",
        "\n",
        "from numpy.random import seed, randn\n",
        "from scipy.stats import mannwhitneyu\n",
        "\n",
        "seed (1)\n",
        "\n",
        "def whhitney_test(descriptor, verbose=False):\n",
        "\n",
        "    \"\"\"\n",
        "    function to run mann-whitney U test\n",
        "    \"\"\"\n",
        "\n",
        "    selection = [descriptor, 'class']\n",
        "    df = df2[selection]\n",
        "    active = df[df['class'] == 'active']\n",
        "    active = active[descriptor]\n",
        "\n",
        "    selection = [descriptor, 'class']\n",
        "    df = df2[selection]\n",
        "    inactive = df[df['class'] == 'inactive']\n",
        "    inactive = inactive[descriptor]\n",
        "\n",
        "    # compare samples\n",
        "    stat, p = mannwhitneyu(active, inactive)\n",
        "\n",
        "    # interpretattion\n",
        "    alpha = 0.05\n",
        "    if p > alpha:\n",
        "        inter = \"No significant difference\"\n",
        "    else:\n",
        "        inter = \"Distribution significantly different\"\n",
        "\n",
        "    results = pd.DataFrame({'Descriptor':descriptor,\n",
        "                          'Statistics':stat,\n",
        "                          'p':p,\n",
        "                          'alpha':alpha,\n",
        "                          'Interpretation':inter}, index=[0])\n",
        "    filename = 'mannwhitneyu_' + descriptor + '.csv'\n",
        "    results.to_csv(filename)\n",
        "\n",
        "    return results"
      ],
      "metadata": {
        "id": "aY6PEyOGwkhA"
      },
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# bioactivity class and pIC50 value\n",
        "\n",
        "sns.boxplot(x='class', y='pIC50', data=df2)\n",
        "plt.xlabel('Bioactivity class')\n",
        "plt.ylabel('pIC50 Value')\n",
        "\n",
        "plt.savefig('plot_bioactivity_class.pdf')\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 285
        },
        "id": "YsDfqufRuDIr",
        "outputId": "e79e49f9-a501-4a82-c1b6-e225e76fb5b4"
      },
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# whitney test for pIC50\n",
        "whhitney_test('pIC50')"
      ],
      "metadata": {
        "id": "15NpukAMEegA",
        "outputId": "d4ebcd04-e0db-47c9-df32-8d0af91ca857",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        }
      },
      "execution_count": 32,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  Descriptor  Statistics    p  alpha                        Interpretation\n",
              "0      pIC50        0.00 0.00   0.05  Distribution significantly different"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-fd6eb1fe-a31e-4926-952c-5639f8837658\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Descriptor</th>\n",
              "      <th>Statistics</th>\n",
              "      <th>p</th>\n",
              "      <th>alpha</th>\n",
              "      <th>Interpretation</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>pIC50</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.05</td>\n",
              "      <td>Distribution significantly different</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-fd6eb1fe-a31e-4926-952c-5639f8837658')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-fd6eb1fe-a31e-4926-952c-5639f8837658 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-fd6eb1fe-a31e-4926-952c-5639f8837658');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 32
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# bioactivity class and molecular weight value\n",
        "\n",
        "sns.boxplot(x='class', y='mol_wt', data=df2)\n",
        "plt.xlabel('Bioactivity class')\n",
        "plt.ylabel('Molecular Weight')\n",
        "\n",
        "plt.savefig('plot_bioactivity_class.pdf')\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 285
        },
        "id": "HHOxK68Ryky9",
        "outputId": "115f423a-b939-4fd8-b502-4101d324e5c1"
      },
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# whitney test for pIC50\n",
        "whhitney_test('mol_wt')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        },
        "id": "w9iGIFQJxUCQ",
        "outputId": "ebe80509-6011-40a9-c689-86809a56826e"
      },
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  Descriptor  Statistics    p  alpha             Interpretation\n",
              "0     mol_wt      130.00 0.43   0.05  No significant difference"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-41dc9fe5-978b-4dba-9d6d-836bea34f5d4\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Descriptor</th>\n",
              "      <th>Statistics</th>\n",
              "      <th>p</th>\n",
              "      <th>alpha</th>\n",
              "      <th>Interpretation</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>mol_wt</td>\n",
              "      <td>130.00</td>\n",
              "      <td>0.43</td>\n",
              "      <td>0.05</td>\n",
              "      <td>No significant difference</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-41dc9fe5-978b-4dba-9d6d-836bea34f5d4')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-41dc9fe5-978b-4dba-9d6d-836bea34f5d4 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-41dc9fe5-978b-4dba-9d6d-836bea34f5d4');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 34
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# bioactivity class and log of P value\n",
        "\n",
        "sns.boxplot(x='class', y='mol_logp', data=df2)\n",
        "plt.xlabel('Bioactivity class')\n",
        "plt.ylabel('logP')\n",
        "\n",
        "plt.savefig('plot_bioactivity_class.pdf')\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 287
        },
        "id": "owTtbNrFyScB",
        "outputId": "1ce77b5e-9b48-41d4-d68e-4f58a78e2d75"
      },
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# whitney test for mol_logP\n",
        "whhitney_test('mol_logp')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        },
        "id": "D6l-FrkiyyAF",
        "outputId": "57044650-cbfa-48b6-931d-9d5fa7860160"
      },
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  Descriptor  Statistics    p  alpha                        Interpretation\n",
              "0   mol_logp       74.00 0.02   0.05  Distribution significantly different"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-59875b3b-3974-45ab-bf06-0fb3434936fa\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Descriptor</th>\n",
              "      <th>Statistics</th>\n",
              "      <th>p</th>\n",
              "      <th>alpha</th>\n",
              "      <th>Interpretation</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>mol_logp</td>\n",
              "      <td>74.00</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.05</td>\n",
              "      <td>Distribution significantly different</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-59875b3b-3974-45ab-bf06-0fb3434936fa')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-59875b3b-3974-45ab-bf06-0fb3434936fa button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-59875b3b-3974-45ab-bf06-0fb3434936fa');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 36
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# bioactivity class and num_H_donors\n",
        "\n",
        "sns.boxplot(x='class', y='num_H_donors', data=df2)\n",
        "plt.xlabel('Bioactivity class')\n",
        "plt.ylabel('Number of H donors')\n",
        "\n",
        "plt.savefig('plot_bioactivity_class.pdf')\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 285
        },
        "id": "xwC795UdzOXW",
        "outputId": "dc2d12ec-2f7a-467b-ed44-32e7f6d2364c"
      },
      "execution_count": 37,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# whitney test for num_H_donors\n",
        "whhitney_test('num_H_donors')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        },
        "id": "Ln-D1ElNzKez",
        "outputId": "b03cb83c-a8e8-4d4c-f122-680c5be93886"
      },
      "execution_count": 38,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     Descriptor  Statistics    p  alpha             Interpretation\n",
              "0  num_H_donors       90.50 0.07   0.05  No significant difference"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-977f5a1a-c2e6-4a01-b449-a4ec494aaa3f\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Descriptor</th>\n",
              "      <th>Statistics</th>\n",
              "      <th>p</th>\n",
              "      <th>alpha</th>\n",
              "      <th>Interpretation</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>num_H_donors</td>\n",
              "      <td>90.50</td>\n",
              "      <td>0.07</td>\n",
              "      <td>0.05</td>\n",
              "      <td>No significant difference</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-977f5a1a-c2e6-4a01-b449-a4ec494aaa3f')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-977f5a1a-c2e6-4a01-b449-a4ec494aaa3f button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-977f5a1a-c2e6-4a01-b449-a4ec494aaa3f');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 38
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# bioactivity class and num_H_acceptors\n",
        "\n",
        "sns.boxplot(x='class', y='num_H_acceptors', data=df2)\n",
        "plt.xlabel('Bioactivity class')\n",
        "plt.ylabel('Number of H acceptors')\n",
        "\n",
        "plt.savefig('plot_bioactivity_class.pdf')\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 285
        },
        "id": "vTEM2WpJznpE",
        "outputId": "7d25b8c7-2314-4792-a3f9-8a6e272b1921"
      },
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# whitney test for number of H acceptors\n",
        "whhitney_test('num_H_acceptors')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        },
        "id": "UKRSbmPnzs_2",
        "outputId": "b4461747-646e-4053-9c75-07fede634f6c"
      },
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "        Descriptor  Statistics    p  alpha  \\\n",
              "0  num_H_acceptors       57.50 0.00   0.05   \n",
              "\n",
              "                         Interpretation  \n",
              "0  Distribution significantly different  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-d46318e1-0ad6-4ea3-ad92-bcad6577a66f\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Descriptor</th>\n",
              "      <th>Statistics</th>\n",
              "      <th>p</th>\n",
              "      <th>alpha</th>\n",
              "      <th>Interpretation</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>num_H_acceptors</td>\n",
              "      <td>57.50</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.05</td>\n",
              "      <td>Distribution significantly different</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d46318e1-0ad6-4ea3-ad92-bcad6577a66f')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-d46318e1-0ad6-4ea3-ad92-bcad6577a66f button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-d46318e1-0ad6-4ea3-ad92-bcad6577a66f');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 40
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Descriptor Claculations"
      ],
      "metadata": {
        "id": "DnE6ztnz1gn3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Package for Descriptor Calculation\n",
        "\n",
        "! pip install padelpy"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VCRIlFDF0Bn5",
        "outputId": "a03b84ce-5e00-495c-b195-feb217c50586"
      },
      "execution_count": 41,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: padelpy in /usr/local/lib/python3.7/dist-packages (0.1.11)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df3 = df_proc.copy()\n",
        "\n",
        "df3.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 444
        },
        "id": "QXivqucA1ohB",
        "outputId": "292704f2-7501-4d2e-b42b-00415c209b76"
      },
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  molecule_chembl_id                                   canonical_smiles  \\\n",
              "0      CHEMBL4126343  N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...   \n",
              "1      CHEMBL3417270  [N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...   \n",
              "2       CHEMBL521487  C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...   \n",
              "3      CHEMBL4127092  C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...   \n",
              "4      CHEMBL4127819  CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...   \n",
              "\n",
              "   standard_value         class  \\\n",
              "0          340.00        active   \n",
              "1          360.00        active   \n",
              "2         5000.00  intermediate   \n",
              "3         1600.00  intermediate   \n",
              "4         2000.00  intermediate   \n",
              "\n",
              "                               canonical_smiles_mol  mol_wt  mol_logp  \\\n",
              "0  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb080>  531.20     -1.13   \n",
              "1  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb030>  524.17     -1.57   \n",
              "2  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb120>  498.17     -2.11   \n",
              "3  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb170>  508.16     -2.50   \n",
              "4  <rdkit.Chem.rdchem.Mol object at 0x7f6242eeb1c0>  522.19     -2.11   \n",
              "\n",
              "   num_H_donors  num_H_acceptors  pIC50  \n",
              "0             7               14   2.53  \n",
              "1             7               14   2.56  \n",
              "2             7               12   3.70  \n",
              "3             7               12   3.20  \n",
              "4             7               12   3.30  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-96896aea-4a03-47ab-9492-ec6cbbf6aae6\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>molecule_chembl_id</th>\n",
              "      <th>canonical_smiles</th>\n",
              "      <th>standard_value</th>\n",
              "      <th>class</th>\n",
              "      <th>canonical_smiles_mol</th>\n",
              "      <th>mol_wt</th>\n",
              "      <th>mol_logp</th>\n",
              "      <th>num_H_donors</th>\n",
              "      <th>num_H_acceptors</th>\n",
              "      <th>pIC50</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>CHEMBL4126343</td>\n",
              "      <td>N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...</td>\n",
              "      <td>340.00</td>\n",
              "      <td>active</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb080&gt;</td>\n",
              "      <td>531.20</td>\n",
              "      <td>-1.13</td>\n",
              "      <td>7</td>\n",
              "      <td>14</td>\n",
              "      <td>2.53</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>CHEMBL3417270</td>\n",
              "      <td>[N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...</td>\n",
              "      <td>360.00</td>\n",
              "      <td>active</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb030&gt;</td>\n",
              "      <td>524.17</td>\n",
              "      <td>-1.57</td>\n",
              "      <td>7</td>\n",
              "      <td>14</td>\n",
              "      <td>2.56</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>CHEMBL521487</td>\n",
              "      <td>C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...</td>\n",
              "      <td>5000.00</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb120&gt;</td>\n",
              "      <td>498.17</td>\n",
              "      <td>-2.11</td>\n",
              "      <td>7</td>\n",
              "      <td>12</td>\n",
              "      <td>3.70</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>CHEMBL4127092</td>\n",
              "      <td>C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...</td>\n",
              "      <td>1600.00</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb170&gt;</td>\n",
              "      <td>508.16</td>\n",
              "      <td>-2.50</td>\n",
              "      <td>7</td>\n",
              "      <td>12</td>\n",
              "      <td>3.20</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>CHEMBL4127819</td>\n",
              "      <td>CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...</td>\n",
              "      <td>2000.00</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7f6242eeb1c0&gt;</td>\n",
              "      <td>522.19</td>\n",
              "      <td>-2.11</td>\n",
              "      <td>7</td>\n",
              "      <td>12</td>\n",
              "      <td>3.30</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-96896aea-4a03-47ab-9492-ec6cbbf6aae6')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-96896aea-4a03-47ab-9492-ec6cbbf6aae6 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-96896aea-4a03-47ab-9492-ec6cbbf6aae6');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 42
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "selection = ['canonical_smiles', 'molecule_chembl_id']\n",
        "df3_selection = df3[selection]\n",
        "df3_selection.to_csv('molecule.smi', sep='\\t', index = False, header = False)\n",
        "\n",
        "df3_selection.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "EkwLFD2P1_Tn",
        "outputId": "38ba96fc-1d92-477e-e090-85e4f1a6624a"
      },
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                    canonical_smiles molecule_chembl_id\n",
              "0  N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...      CHEMBL4126343\n",
              "1  [N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...      CHEMBL3417270\n",
              "2  C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...       CHEMBL521487\n",
              "3  C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...      CHEMBL4127092\n",
              "4  CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...      CHEMBL4127819"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-7f010c39-f9f4-4cae-a7f9-1f513c50da8f\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>canonical_smiles</th>\n",
              "      <th>molecule_chembl_id</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O...</td>\n",
              "      <td>CHEMBL4126343</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>[N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O...</td>\n",
              "      <td>CHEMBL3417270</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP...</td>\n",
              "      <td>CHEMBL521487</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)...</td>\n",
              "      <td>CHEMBL4127092</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O...</td>\n",
              "      <td>CHEMBL4127819</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7f010c39-f9f4-4cae-a7f9-1f513c50da8f')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-7f010c39-f9f4-4cae-a7f9-1f513c50da8f button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-7f010c39-f9f4-4cae-a7f9-1f513c50da8f');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 43
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "! cat molecule.smi | head -5"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ekuaqs7G9GeC",
        "outputId": "d0d1c77f-d7e8-4855-8fbe-6f131cb98d57"
      },
      "execution_count": 44,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "N#C[C@]1(O)C(n2ccc3c(N)ncnc32)O[C@H](COP(=O)(O)OP(=O)(O)OP(=O)(O)O)[C@H]1O\tCHEMBL4126343\n",
            "[N-]=[N+]=N[C@]1(COP(=O)(O)OP(=O)(O)OP(=O)(O)O)O[C@@H](n2ccc(N)nc2=O)[C@H](O)[C@@H]1O\tCHEMBL3417270\n",
            "C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP(=O)(O)O)O[C@H]1n1ccc(=O)[nH]c1=O\tCHEMBL521487\n",
            "C#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP(=O)(O)O)O[C@H]1n1ccc(=O)[nH]c1=O\tCHEMBL4127092\n",
            "CC#C[C@@]1(O)[C@H](O)[C@@H](COP(=O)(O)OP(=O)(O)OP(=O)(O)O)O[C@H]1n1ccc(=O)[nH]c1=O\tCHEMBL4127819\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "! cat molecule.smi | wc -l"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MmSZkfKc9URQ",
        "outputId": "2a9464d9-0fa8-4a87-913d-e9418ab82062"
      },
      "execution_count": 45,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "62\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from padelpy import padeldescriptor\n",
        "\n",
        "padeldescriptor(mol_dir='/content/molecule.smi', d_file='descriptors.csv', \n",
        "                fingerprints=True, removesalt=True, detectaromaticity=True, \n",
        "                log=True, retainorder=True)"
      ],
      "metadata": {
        "id": "c76mPIJ47nnP"
      },
      "execution_count": 46,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df3_padel = pd.read_csv('descriptors.csv')\n",
        "df3_padel"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 488
        },
        "id": "s66QgPKh8dWn",
        "outputId": "58648299-4333-4dca-d3b5-e8dee4fa52eb"
      },
      "execution_count": 47,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "             Name  PubchemFP0  PubchemFP1  PubchemFP2  PubchemFP3  PubchemFP4  \\\n",
              "0   CHEMBL4126343           1           1           1           0           0   \n",
              "1   CHEMBL3417270           1           1           0           0           0   \n",
              "2    CHEMBL521487           1           1           1           0           0   \n",
              "3   CHEMBL4127092           1           1           0           0           0   \n",
              "4   CHEMBL4127819           1           1           1           0           0   \n",
              "..            ...         ...         ...         ...         ...         ...   \n",
              "57   CHEMBL269277           1           1           1           1           0   \n",
              "58  CHEMBL4526128           1           1           1           0           0   \n",
              "59  CHEMBL1418094           1           1           1           0           0   \n",
              "60  CHEMBL1214186           1           1           1           0           0   \n",
              "61   CHEMBL418052           1           1           1           0           0   \n",
              "\n",
              "    PubchemFP5  PubchemFP6  PubchemFP7  PubchemFP8  ...  PubchemFP871  \\\n",
              "0            0           0           0           0  ...             0   \n",
              "1            0           0           0           0  ...             0   \n",
              "2            0           0           0           0  ...             0   \n",
              "3            0           0           0           0  ...             0   \n",
              "4            0           0           0           0  ...             0   \n",
              "..         ...         ...         ...         ...  ...           ...   \n",
              "57           0           0           0           0  ...             0   \n",
              "58           0           0           0           0  ...             0   \n",
              "59           0           0           0           0  ...             0   \n",
              "60           0           0           0           0  ...             0   \n",
              "61           0           0           0           0  ...             0   \n",
              "\n",
              "    PubchemFP872  PubchemFP873  PubchemFP874  PubchemFP875  PubchemFP876  \\\n",
              "0              0             0             0             0             0   \n",
              "1              0             0             0             0             0   \n",
              "2              0             0             0             0             0   \n",
              "3              0             0             0             0             0   \n",
              "4              0             0             0             0             0   \n",
              "..           ...           ...           ...           ...           ...   \n",
              "57             0             0             0             0             0   \n",
              "58             0             0             0             0             0   \n",
              "59             0             0             0             0             0   \n",
              "60             0             0             0             0             0   \n",
              "61             0             0             0             0             0   \n",
              "\n",
              "    PubchemFP877  PubchemFP878  PubchemFP879  PubchemFP880  \n",
              "0              0             0             0             0  \n",
              "1              0             0             0             0  \n",
              "2              0             0             0             0  \n",
              "3              0             0             0             0  \n",
              "4              0             0             0             0  \n",
              "..           ...           ...           ...           ...  \n",
              "57             0             0             0             0  \n",
              "58             0             0             0             0  \n",
              "59             0             0             0             0  \n",
              "60             0             0             0             0  \n",
              "61             0             0             0             0  \n",
              "\n",
              "[62 rows x 882 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-b67e8337-69bb-49b3-a36a-13d7ff26b9c3\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>PubchemFP0</th>\n",
              "      <th>PubchemFP1</th>\n",
              "      <th>PubchemFP2</th>\n",
              "      <th>PubchemFP3</th>\n",
              "      <th>PubchemFP4</th>\n",
              "      <th>PubchemFP5</th>\n",
              "      <th>PubchemFP6</th>\n",
              "      <th>PubchemFP7</th>\n",
              "      <th>PubchemFP8</th>\n",
              "      <th>...</th>\n",
              "      <th>PubchemFP871</th>\n",
              "      <th>PubchemFP872</th>\n",
              "      <th>PubchemFP873</th>\n",
              "      <th>PubchemFP874</th>\n",
              "      <th>PubchemFP875</th>\n",
              "      <th>PubchemFP876</th>\n",
              "      <th>PubchemFP877</th>\n",
              "      <th>PubchemFP878</th>\n",
              "      <th>PubchemFP879</th>\n",
              "      <th>PubchemFP880</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>CHEMBL4126343</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>CHEMBL3417270</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>CHEMBL521487</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>CHEMBL4127092</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>CHEMBL4127819</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</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>57</th>\n",
              "      <td>CHEMBL269277</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>58</th>\n",
              "      <td>CHEMBL4526128</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>59</th>\n",
              "      <td>CHEMBL1418094</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>60</th>\n",
              "      <td>CHEMBL1214186</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>61</th>\n",
              "      <td>CHEMBL418052</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>62 rows × 882 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b67e8337-69bb-49b3-a36a-13d7ff26b9c3')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-b67e8337-69bb-49b3-a36a-13d7ff26b9c3 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-b67e8337-69bb-49b3-a36a-13d7ff26b9c3');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 47
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df3_padel = df3_padel.drop(columns='Name')\n",
        "df3_padel.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 300
        },
        "id": "LMGA7yZV80T2",
        "outputId": "402df000-009c-49ea-b390-6f78d6827ea4"
      },
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   PubchemFP0  PubchemFP1  PubchemFP2  PubchemFP3  PubchemFP4  PubchemFP5  \\\n",
              "0           1           1           1           0           0           0   \n",
              "1           1           1           0           0           0           0   \n",
              "2           1           1           1           0           0           0   \n",
              "3           1           1           0           0           0           0   \n",
              "4           1           1           1           0           0           0   \n",
              "\n",
              "   PubchemFP6  PubchemFP7  PubchemFP8  PubchemFP9  ...  PubchemFP871  \\\n",
              "0           0           0           0           1  ...             0   \n",
              "1           0           0           0           1  ...             0   \n",
              "2           0           0           0           1  ...             0   \n",
              "3           0           0           0           1  ...             0   \n",
              "4           0           0           0           1  ...             0   \n",
              "\n",
              "   PubchemFP872  PubchemFP873  PubchemFP874  PubchemFP875  PubchemFP876  \\\n",
              "0             0             0             0             0             0   \n",
              "1             0             0             0             0             0   \n",
              "2             0             0             0             0             0   \n",
              "3             0             0             0             0             0   \n",
              "4             0             0             0             0             0   \n",
              "\n",
              "   PubchemFP877  PubchemFP878  PubchemFP879  PubchemFP880  \n",
              "0             0             0             0             0  \n",
              "1             0             0             0             0  \n",
              "2             0             0             0             0  \n",
              "3             0             0             0             0  \n",
              "4             0             0             0             0  \n",
              "\n",
              "[5 rows x 881 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-34b59e53-5af9-409d-9529-c5fb646b4fbc\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>PubchemFP0</th>\n",
              "      <th>PubchemFP1</th>\n",
              "      <th>PubchemFP2</th>\n",
              "      <th>PubchemFP3</th>\n",
              "      <th>PubchemFP4</th>\n",
              "      <th>PubchemFP5</th>\n",
              "      <th>PubchemFP6</th>\n",
              "      <th>PubchemFP7</th>\n",
              "      <th>PubchemFP8</th>\n",
              "      <th>PubchemFP9</th>\n",
              "      <th>...</th>\n",
              "      <th>PubchemFP871</th>\n",
              "      <th>PubchemFP872</th>\n",
              "      <th>PubchemFP873</th>\n",
              "      <th>PubchemFP874</th>\n",
              "      <th>PubchemFP875</th>\n",
              "      <th>PubchemFP876</th>\n",
              "      <th>PubchemFP877</th>\n",
              "      <th>PubchemFP878</th>\n",
              "      <th>PubchemFP879</th>\n",
              "      <th>PubchemFP880</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 881 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-34b59e53-5af9-409d-9529-c5fb646b4fbc')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-34b59e53-5af9-409d-9529-c5fb646b4fbc button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-34b59e53-5af9-409d-9529-c5fb646b4fbc');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 48
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_1 = df3_padel.copy()\n",
        "Y_1 = df3['pIC50']\n",
        "data_xy = pd.concat([X_1, Y_1], axis=1)\n",
        "data_xy.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 300
        },
        "id": "77G00Een_g9l",
        "outputId": "265d7082-eb5a-40e8-e974-26a46a730d00"
      },
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   PubchemFP0  PubchemFP1  PubchemFP2  PubchemFP3  PubchemFP4  PubchemFP5  \\\n",
              "0           1           1           1           0           0           0   \n",
              "1           1           1           0           0           0           0   \n",
              "2           1           1           1           0           0           0   \n",
              "3           1           1           0           0           0           0   \n",
              "4           1           1           1           0           0           0   \n",
              "\n",
              "   PubchemFP6  PubchemFP7  PubchemFP8  PubchemFP9  ...  PubchemFP872  \\\n",
              "0           0           0           0           1  ...             0   \n",
              "1           0           0           0           1  ...             0   \n",
              "2           0           0           0           1  ...             0   \n",
              "3           0           0           0           1  ...             0   \n",
              "4           0           0           0           1  ...             0   \n",
              "\n",
              "   PubchemFP873  PubchemFP874  PubchemFP875  PubchemFP876  PubchemFP877  \\\n",
              "0             0             0             0             0             0   \n",
              "1             0             0             0             0             0   \n",
              "2             0             0             0             0             0   \n",
              "3             0             0             0             0             0   \n",
              "4             0             0             0             0             0   \n",
              "\n",
              "   PubchemFP878  PubchemFP879  PubchemFP880  pIC50  \n",
              "0             0             0             0   2.53  \n",
              "1             0             0             0   2.56  \n",
              "2             0             0             0   3.70  \n",
              "3             0             0             0   3.20  \n",
              "4             0             0             0   3.30  \n",
              "\n",
              "[5 rows x 882 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-7ac24e88-34fc-4ba6-8fa1-aabc40cd07e9\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>PubchemFP0</th>\n",
              "      <th>PubchemFP1</th>\n",
              "      <th>PubchemFP2</th>\n",
              "      <th>PubchemFP3</th>\n",
              "      <th>PubchemFP4</th>\n",
              "      <th>PubchemFP5</th>\n",
              "      <th>PubchemFP6</th>\n",
              "      <th>PubchemFP7</th>\n",
              "      <th>PubchemFP8</th>\n",
              "      <th>PubchemFP9</th>\n",
              "      <th>...</th>\n",
              "      <th>PubchemFP872</th>\n",
              "      <th>PubchemFP873</th>\n",
              "      <th>PubchemFP874</th>\n",
              "      <th>PubchemFP875</th>\n",
              "      <th>PubchemFP876</th>\n",
              "      <th>PubchemFP877</th>\n",
              "      <th>PubchemFP878</th>\n",
              "      <th>PubchemFP879</th>\n",
              "      <th>PubchemFP880</th>\n",
              "      <th>pIC50</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>2.53</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>2.56</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>3.70</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>3.20</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>3.30</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 882 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7ac24e88-34fc-4ba6-8fa1-aabc40cd07e9')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-7ac24e88-34fc-4ba6-8fa1-aabc40cd07e9 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-7ac24e88-34fc-4ba6-8fa1-aabc40cd07e9');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 49
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data_xy.to_csv('data with descriptors padel.csv', index=False)"
      ],
      "metadata": {
        "id": "0ZVRNeczACqG"
      },
      "execution_count": 50,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X = data_xy.drop('pIC50', axis = 1)\n",
        "Y = data_xy['pIC50']"
      ],
      "metadata": {
        "id": "ejWtkQiQAfcw"
      },
      "execution_count": 51,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NEvnaDUGKxSO",
        "outputId": "0ad14c73-5d25-48b7-bd84-3cc0ad404baf"
      },
      "execution_count": 52,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(62, 881)"
            ]
          },
          "metadata": {},
          "execution_count": 52
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "Y.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ghm3KcX4Ky-h",
        "outputId": "ae60701a-26f6-4498-aa7d-873808079b82"
      },
      "execution_count": 53,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(62,)"
            ]
          },
          "metadata": {},
          "execution_count": 53
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Model Building"
      ],
      "metadata": {
        "id": "vbWs7MUeS0XD"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# remove low variance features\n",
        "\n",
        "from sklearn.feature_selection import VarianceThreshold\n",
        "selection = VarianceThreshold(threshold=(0.8*(1-0.8)))\n",
        "X = selection.fit_transform(X)\n",
        "X.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PBeq5EyYK0ly",
        "outputId": "fdd5d19b-201b-4199-e579-42419f7a6aef"
      },
      "execution_count": 54,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(62, 186)"
            ]
          },
          "metadata": {},
          "execution_count": 54
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# data split into train and test set\n",
        "\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size = 0.2)"
      ],
      "metadata": {
        "id": "5d1S66RVLeIj"
      },
      "execution_count": 55,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "x_train.shape, y_train.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Oe6DyBRQMBDr",
        "outputId": "e28b9592-4dd2-43ae-9b58-a4d23a48a39b"
      },
      "execution_count": 56,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "((49, 186), (49,))"
            ]
          },
          "metadata": {},
          "execution_count": 56
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x_test.shape, y_test.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "A4k7i7NsMD4y",
        "outputId": "32f53d96-6b6a-42f0-efa7-efc34f91066f"
      },
      "execution_count": 57,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "((13, 186), (13,))"
            ]
          },
          "metadata": {},
          "execution_count": 57
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install lazypredict"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 732
        },
        "id": "D6QgIF12dzyH",
        "outputId": "62cb776d-5da7-440c-8a97-8870aa20697d"
      },
      "execution_count": 61,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: lazypredict in /usr/local/lib/python3.7/dist-packages (0.2.9)\n",
            "Requirement already satisfied: six==1.15.0 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (1.15.0)\n",
            "Collecting PyYAML==5.3.1\n",
            "  Using cached PyYAML-5.3.1-cp37-cp37m-linux_x86_64.whl\n",
            "Requirement already satisfied: scikit-learn==0.23.1 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (0.23.1)\n",
            "Requirement already satisfied: tqdm==4.56.0 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (4.56.0)\n",
            "Requirement already satisfied: joblib==1.0.0 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (1.0.0)\n",
            "Requirement already satisfied: click==7.1.2 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (7.1.2)\n",
            "Requirement already satisfied: lightgbm==2.3.1 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (2.3.1)\n",
            "Requirement already satisfied: pandas==1.0.5 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (1.0.5)\n",
            "Requirement already satisfied: xgboost==1.1.1 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (1.1.1)\n",
            "Requirement already satisfied: pytest==5.4.3 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (5.4.3)\n",
            "Requirement already satisfied: scipy==1.5.4 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (1.5.4)\n",
            "Requirement already satisfied: numpy==1.19.1 in /usr/local/lib/python3.7/dist-packages (from lazypredict) (1.19.1)\n",
            "Requirement already satisfied: python-dateutil>=2.6.1 in /usr/local/lib/python3.7/dist-packages (from pandas==1.0.5->lazypredict) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.7/dist-packages (from pandas==1.0.5->lazypredict) (2022.1)\n",
            "Requirement already satisfied: importlib-metadata>=0.12 in /usr/local/lib/python3.7/dist-packages (from pytest==5.4.3->lazypredict) (4.11.3)\n",
            "Requirement already satisfied: wcwidth in /usr/local/lib/python3.7/dist-packages (from pytest==5.4.3->lazypredict) (0.2.5)\n",
            "Requirement already satisfied: pluggy<1.0,>=0.12 in /usr/local/lib/python3.7/dist-packages (from pytest==5.4.3->lazypredict) (0.13.1)\n",
            "Requirement already satisfied: more-itertools>=4.0.0 in /usr/local/lib/python3.7/dist-packages (from pytest==5.4.3->lazypredict) (8.12.0)\n",
            "Requirement already satisfied: attrs>=17.4.0 in /usr/local/lib/python3.7/dist-packages (from pytest==5.4.3->lazypredict) (21.4.0)\n",
            "Requirement already satisfied: py>=1.5.0 in /usr/local/lib/python3.7/dist-packages (from pytest==5.4.3->lazypredict) (1.11.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.7/dist-packages (from pytest==5.4.3->lazypredict) (21.3)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn==0.23.1->lazypredict) (3.1.0)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata>=0.12->pytest==5.4.3->lazypredict) (3.8.0)\n",
            "Requirement already satisfied: typing-extensions>=3.6.4 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata>=0.12->pytest==5.4.3->lazypredict) (4.2.0)\n",
            "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from packaging->pytest==5.4.3->lazypredict) (3.0.8)\n",
            "Installing collected packages: PyYAML\n",
            "  Attempting uninstall: PyYAML\n",
            "    Found existing installation: PyYAML 6.0\n",
            "    Uninstalling PyYAML-6.0:\n",
            "      Successfully uninstalled PyYAML-6.0\n",
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "requests-cache 0.7.5 requires pyyaml>=5.4, but you have pyyaml 5.3.1 which is incompatible.\u001b[0m\n",
            "Successfully installed PyYAML-5.3.1\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "yaml"
                ]
              }
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from lazypredict.Supervised import LazyRegressor\n",
        "\n",
        "clf = LazyRegressor(verbose=0, ignore_warnings=True, custom_metric=None)\n",
        "train, test = clf.fit(x_train, x_test, y_train, y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lCf-Q18kq-fa",
        "outputId": "557838a6-d65f-4f86-9fcc-628a66304a66"
      },
      "execution_count": 62,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 42/42 [00:05<00:00,  7.54it/s]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "12DFOkpBsxeW",
        "outputId": "473db23f-c4f2-41f3-8e39-4d3ccb1db809"
      },
      "execution_count": 63,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                                              Adjusted R-Squared  \\\n",
              "Model                                                                              \n",
              "Lars                          24504444672710904257829102848509112108058660956...   \n",
              "KernelRidge                                                                 1.78   \n",
              "GaussianProcessRegressor                                                    1.69   \n",
              "DummyRegressor                                                              1.09   \n",
              "LassoLars                                                                   1.09   \n",
              "Lasso                                                                       1.09   \n",
              "ElasticNet                                                                  1.06   \n",
              "LassoLarsIC                                                                 1.05   \n",
              "OrthogonalMatchingPursuit                                                   1.03   \n",
              "LGBMRegressor                                                               1.03   \n",
              "HistGradientBoostingRegressor                                               1.03   \n",
              "LassoLarsCV                                                                 1.02   \n",
              "OrthogonalMatchingPursuitCV                                                 1.02   \n",
              "LassoCV                                                                     1.02   \n",
              "LarsCV                                                                      1.02   \n",
              "ElasticNetCV                                                                1.02   \n",
              "NuSVR                                                                       1.01   \n",
              "KNeighborsRegressor                                                         1.01   \n",
              "SVR                                                                         1.01   \n",
              "GammaRegressor                                                              1.01   \n",
              "AdaBoostRegressor                                                           1.01   \n",
              "TweedieRegressor                                                            1.01   \n",
              "GeneralizedLinearRegressor                                                  1.01   \n",
              "RandomForestRegressor                                                       1.01   \n",
              "DecisionTreeRegressor                                                       1.01   \n",
              "ExtraTreeRegressor                                                          1.01   \n",
              "ExtraTreesRegressor                                                         1.01   \n",
              "BaggingRegressor                                                            1.01   \n",
              "XGBRegressor                                                                1.01   \n",
              "LinearRegression                                                            1.01   \n",
              "TransformedTargetRegressor                                                  1.01   \n",
              "GradientBoostingRegressor                                                   1.01   \n",
              "HuberRegressor                                                              1.01   \n",
              "PoissonRegressor                                                            1.01   \n",
              "Ridge                                                                       1.00   \n",
              "LinearSVR                                                                   1.00   \n",
              "BayesianRidge                                                               1.00   \n",
              "PassiveAggressiveRegressor                                                  1.00   \n",
              "MLPRegressor                                                                1.00   \n",
              "RidgeCV                                                                     1.00   \n",
              "SGDRegressor                                                                1.00   \n",
              "\n",
              "                                                                       R-Squared  \\\n",
              "Model                                                                              \n",
              "Lars                          -3553144477543081245821142408477825905874475975...   \n",
              "KernelRidge                                                               -10.27   \n",
              "GaussianProcessRegressor                                                   -9.06   \n",
              "DummyRegressor                                                             -0.27   \n",
              "LassoLars                                                                  -0.27   \n",
              "Lasso                                                                      -0.27   \n",
              "ElasticNet                                                                  0.08   \n",
              "LassoLarsIC                                                                 0.33   \n",
              "OrthogonalMatchingPursuit                                                   0.58   \n",
              "LGBMRegressor                                                               0.64   \n",
              "HistGradientBoostingRegressor                                               0.64   \n",
              "LassoLarsCV                                                                 0.70   \n",
              "OrthogonalMatchingPursuitCV                                                 0.71   \n",
              "LassoCV                                                                     0.71   \n",
              "LarsCV                                                                      0.76   \n",
              "ElasticNetCV                                                                0.78   \n",
              "NuSVR                                                                       0.81   \n",
              "KNeighborsRegressor                                                         0.82   \n",
              "SVR                                                                         0.84   \n",
              "GammaRegressor                                                              0.86   \n",
              "AdaBoostRegressor                                                           0.86   \n",
              "TweedieRegressor                                                            0.86   \n",
              "GeneralizedLinearRegressor                                                  0.86   \n",
              "RandomForestRegressor                                                       0.88   \n",
              "DecisionTreeRegressor                                                       0.89   \n",
              "ExtraTreeRegressor                                                          0.89   \n",
              "ExtraTreesRegressor                                                         0.90   \n",
              "BaggingRegressor                                                            0.90   \n",
              "XGBRegressor                                                                0.91   \n",
              "LinearRegression                                                            0.91   \n",
              "TransformedTargetRegressor                                                  0.91   \n",
              "GradientBoostingRegressor                                                   0.91   \n",
              "HuberRegressor                                                              0.92   \n",
              "PoissonRegressor                                                            0.92   \n",
              "Ridge                                                                       0.93   \n",
              "LinearSVR                                                                   0.93   \n",
              "BayesianRidge                                                               0.93   \n",
              "PassiveAggressiveRegressor                                                  0.93   \n",
              "MLPRegressor                                                                0.93   \n",
              "RidgeCV                                                                     0.93   \n",
              "SGDRegressor                                                                0.94   \n",
              "\n",
              "                                                                            RMSE  \\\n",
              "Model                                                                              \n",
              "Lars                          71007751113557157421113940864538607263614444206...   \n",
              "KernelRidge                                                                 4.00   \n",
              "GaussianProcessRegressor                                                    3.78   \n",
              "DummyRegressor                                                              1.34   \n",
              "LassoLars                                                                   1.34   \n",
              "Lasso                                                                       1.34   \n",
              "ElasticNet                                                                  1.14   \n",
              "LassoLarsIC                                                                 0.98   \n",
              "OrthogonalMatchingPursuit                                                   0.77   \n",
              "LGBMRegressor                                                               0.72   \n",
              "HistGradientBoostingRegressor                                               0.72   \n",
              "LassoLarsCV                                                                 0.65   \n",
              "OrthogonalMatchingPursuitCV                                                 0.64   \n",
              "LassoCV                                                                     0.64   \n",
              "LarsCV                                                                      0.59   \n",
              "ElasticNetCV                                                                0.56   \n",
              "NuSVR                                                                       0.51   \n",
              "KNeighborsRegressor                                                         0.50   \n",
              "SVR                                                                         0.48   \n",
              "GammaRegressor                                                              0.45   \n",
              "AdaBoostRegressor                                                           0.44   \n",
              "TweedieRegressor                                                            0.44   \n",
              "GeneralizedLinearRegressor                                                  0.44   \n",
              "RandomForestRegressor                                                       0.42   \n",
              "DecisionTreeRegressor                                                       0.40   \n",
              "ExtraTreeRegressor                                                          0.39   \n",
              "ExtraTreesRegressor                                                         0.38   \n",
              "BaggingRegressor                                                            0.38   \n",
              "XGBRegressor                                                                0.36   \n",
              "LinearRegression                                                            0.35   \n",
              "TransformedTargetRegressor                                                  0.35   \n",
              "GradientBoostingRegressor                                                   0.35   \n",
              "HuberRegressor                                                              0.35   \n",
              "PoissonRegressor                                                            0.34   \n",
              "Ridge                                                                       0.32   \n",
              "LinearSVR                                                                   0.31   \n",
              "BayesianRidge                                                               0.30   \n",
              "PassiveAggressiveRegressor                                                  0.30   \n",
              "MLPRegressor                                                                0.30   \n",
              "RidgeCV                                                                     0.30   \n",
              "SGDRegressor                                                                0.30   \n",
              "\n",
              "                               Time Taken  \n",
              "Model                                      \n",
              "Lars                                 0.11  \n",
              "KernelRidge                          0.02  \n",
              "GaussianProcessRegressor             0.02  \n",
              "DummyRegressor                       0.05  \n",
              "LassoLars                            0.01  \n",
              "Lasso                                0.05  \n",
              "ElasticNet                           0.04  \n",
              "LassoLarsIC                          0.03  \n",
              "OrthogonalMatchingPursuit            0.03  \n",
              "LGBMRegressor                        0.04  \n",
              "HistGradientBoostingRegressor        0.17  \n",
              "LassoLarsCV                          0.07  \n",
              "OrthogonalMatchingPursuitCV          0.04  \n",
              "LassoCV                              1.36  \n",
              "LarsCV                               0.61  \n",
              "ElasticNetCV                         1.13  \n",
              "NuSVR                                0.03  \n",
              "KNeighborsRegressor                  0.03  \n",
              "SVR                                  0.03  \n",
              "GammaRegressor                       0.03  \n",
              "AdaBoostRegressor                    0.25  \n",
              "TweedieRegressor                     0.03  \n",
              "GeneralizedLinearRegressor           0.03  \n",
              "RandomForestRegressor                0.24  \n",
              "DecisionTreeRegressor                0.03  \n",
              "ExtraTreeRegressor                   0.02  \n",
              "ExtraTreesRegressor                  0.17  \n",
              "BaggingRegressor                     0.05  \n",
              "XGBRegressor                         0.18  \n",
              "LinearRegression                     0.03  \n",
              "TransformedTargetRegressor           0.03  \n",
              "GradientBoostingRegressor            0.11  \n",
              "HuberRegressor                       0.06  \n",
              "PoissonRegressor                     0.03  \n",
              "Ridge                                0.03  \n",
              "LinearSVR                            0.06  \n",
              "BayesianRidge                        0.03  \n",
              "PassiveAggressiveRegressor           0.02  \n",
              "MLPRegressor                         0.16  \n",
              "RidgeCV                              0.03  \n",
              "SGDRegressor                         0.03  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-c20a3984-5817-4b8e-b879-648803b94edc\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Adjusted R-Squared</th>\n",
              "      <th>R-Squared</th>\n",
              "      <th>RMSE</th>\n",
              "      <th>Time Taken</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Model</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>Lars</th>\n",
              "      <td>24504444672710904257829102848509112108058660956...</td>\n",
              "      <td>-3553144477543081245821142408477825905874475975...</td>\n",
              "      <td>71007751113557157421113940864538607263614444206...</td>\n",
              "      <td>0.11</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>KernelRidge</th>\n",
              "      <td>1.78</td>\n",
              "      <td>-10.27</td>\n",
              "      <td>4.00</td>\n",
              "      <td>0.02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>GaussianProcessRegressor</th>\n",
              "      <td>1.69</td>\n",
              "      <td>-9.06</td>\n",
              "      <td>3.78</td>\n",
              "      <td>0.02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>DummyRegressor</th>\n",
              "      <td>1.09</td>\n",
              "      <td>-0.27</td>\n",
              "      <td>1.34</td>\n",
              "      <td>0.05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LassoLars</th>\n",
              "      <td>1.09</td>\n",
              "      <td>-0.27</td>\n",
              "      <td>1.34</td>\n",
              "      <td>0.01</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Lasso</th>\n",
              "      <td>1.09</td>\n",
              "      <td>-0.27</td>\n",
              "      <td>1.34</td>\n",
              "      <td>0.05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ElasticNet</th>\n",
              "      <td>1.06</td>\n",
              "      <td>0.08</td>\n",
              "      <td>1.14</td>\n",
              "      <td>0.04</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LassoLarsIC</th>\n",
              "      <td>1.05</td>\n",
              "      <td>0.33</td>\n",
              "      <td>0.98</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>OrthogonalMatchingPursuit</th>\n",
              "      <td>1.03</td>\n",
              "      <td>0.58</td>\n",
              "      <td>0.77</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LGBMRegressor</th>\n",
              "      <td>1.03</td>\n",
              "      <td>0.64</td>\n",
              "      <td>0.72</td>\n",
              "      <td>0.04</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>HistGradientBoostingRegressor</th>\n",
              "      <td>1.03</td>\n",
              "      <td>0.64</td>\n",
              "      <td>0.72</td>\n",
              "      <td>0.17</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LassoLarsCV</th>\n",
              "      <td>1.02</td>\n",
              "      <td>0.70</td>\n",
              "      <td>0.65</td>\n",
              "      <td>0.07</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>OrthogonalMatchingPursuitCV</th>\n",
              "      <td>1.02</td>\n",
              "      <td>0.71</td>\n",
              "      <td>0.64</td>\n",
              "      <td>0.04</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LassoCV</th>\n",
              "      <td>1.02</td>\n",
              "      <td>0.71</td>\n",
              "      <td>0.64</td>\n",
              "      <td>1.36</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LarsCV</th>\n",
              "      <td>1.02</td>\n",
              "      <td>0.76</td>\n",
              "      <td>0.59</td>\n",
              "      <td>0.61</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ElasticNetCV</th>\n",
              "      <td>1.02</td>\n",
              "      <td>0.78</td>\n",
              "      <td>0.56</td>\n",
              "      <td>1.13</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>NuSVR</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.81</td>\n",
              "      <td>0.51</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>KNeighborsRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.82</td>\n",
              "      <td>0.50</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>SVR</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.84</td>\n",
              "      <td>0.48</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>GammaRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.86</td>\n",
              "      <td>0.45</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>AdaBoostRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.86</td>\n",
              "      <td>0.44</td>\n",
              "      <td>0.25</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>TweedieRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.86</td>\n",
              "      <td>0.44</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>GeneralizedLinearRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.86</td>\n",
              "      <td>0.44</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>RandomForestRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.88</td>\n",
              "      <td>0.42</td>\n",
              "      <td>0.24</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>DecisionTreeRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.89</td>\n",
              "      <td>0.40</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ExtraTreeRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.89</td>\n",
              "      <td>0.39</td>\n",
              "      <td>0.02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ExtraTreesRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.90</td>\n",
              "      <td>0.38</td>\n",
              "      <td>0.17</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>BaggingRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.90</td>\n",
              "      <td>0.38</td>\n",
              "      <td>0.05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>XGBRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.91</td>\n",
              "      <td>0.36</td>\n",
              "      <td>0.18</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LinearRegression</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.91</td>\n",
              "      <td>0.35</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>TransformedTargetRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.91</td>\n",
              "      <td>0.35</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>GradientBoostingRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.91</td>\n",
              "      <td>0.35</td>\n",
              "      <td>0.11</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>HuberRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.92</td>\n",
              "      <td>0.35</td>\n",
              "      <td>0.06</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>PoissonRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.92</td>\n",
              "      <td>0.34</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Ridge</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.32</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LinearSVR</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.31</td>\n",
              "      <td>0.06</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>BayesianRidge</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.30</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>PassiveAggressiveRegressor</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.30</td>\n",
              "      <td>0.02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>MLPRegressor</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.30</td>\n",
              "      <td>0.16</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>RidgeCV</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.30</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>SGDRegressor</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.94</td>\n",
              "      <td>0.30</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c20a3984-5817-4b8e-b879-648803b94edc')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-c20a3984-5817-4b8e-b879-648803b94edc button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-c20a3984-5817-4b8e-b879-648803b94edc');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 63
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "test"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "P7q6Gz37vwf7",
        "outputId": "383fdcbc-d8d6-4804-d78b-9f562b889550"
      },
      "execution_count": 65,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                                              Adjusted R-Squared  \\\n",
              "Model                                                                              \n",
              "Lars                          24504444672710904257829102848509112108058660956...   \n",
              "KernelRidge                                                                 1.78   \n",
              "GaussianProcessRegressor                                                    1.69   \n",
              "DummyRegressor                                                              1.09   \n",
              "LassoLars                                                                   1.09   \n",
              "Lasso                                                                       1.09   \n",
              "ElasticNet                                                                  1.06   \n",
              "LassoLarsIC                                                                 1.05   \n",
              "OrthogonalMatchingPursuit                                                   1.03   \n",
              "LGBMRegressor                                                               1.03   \n",
              "HistGradientBoostingRegressor                                               1.03   \n",
              "LassoLarsCV                                                                 1.02   \n",
              "OrthogonalMatchingPursuitCV                                                 1.02   \n",
              "LassoCV                                                                     1.02   \n",
              "LarsCV                                                                      1.02   \n",
              "ElasticNetCV                                                                1.02   \n",
              "NuSVR                                                                       1.01   \n",
              "KNeighborsRegressor                                                         1.01   \n",
              "SVR                                                                         1.01   \n",
              "GammaRegressor                                                              1.01   \n",
              "AdaBoostRegressor                                                           1.01   \n",
              "TweedieRegressor                                                            1.01   \n",
              "GeneralizedLinearRegressor                                                  1.01   \n",
              "RandomForestRegressor                                                       1.01   \n",
              "DecisionTreeRegressor                                                       1.01   \n",
              "ExtraTreeRegressor                                                          1.01   \n",
              "ExtraTreesRegressor                                                         1.01   \n",
              "BaggingRegressor                                                            1.01   \n",
              "XGBRegressor                                                                1.01   \n",
              "LinearRegression                                                            1.01   \n",
              "TransformedTargetRegressor                                                  1.01   \n",
              "GradientBoostingRegressor                                                   1.01   \n",
              "HuberRegressor                                                              1.01   \n",
              "PoissonRegressor                                                            1.01   \n",
              "Ridge                                                                       1.00   \n",
              "LinearSVR                                                                   1.00   \n",
              "BayesianRidge                                                               1.00   \n",
              "PassiveAggressiveRegressor                                                  1.00   \n",
              "MLPRegressor                                                                1.00   \n",
              "RidgeCV                                                                     1.00   \n",
              "SGDRegressor                                                                1.00   \n",
              "\n",
              "                                                                       R-Squared  \\\n",
              "Model                                                                              \n",
              "Lars                          -3553144477543081245821142408477825905874475975...   \n",
              "KernelRidge                                                               -10.27   \n",
              "GaussianProcessRegressor                                                   -9.06   \n",
              "DummyRegressor                                                             -0.27   \n",
              "LassoLars                                                                  -0.27   \n",
              "Lasso                                                                      -0.27   \n",
              "ElasticNet                                                                  0.08   \n",
              "LassoLarsIC                                                                 0.33   \n",
              "OrthogonalMatchingPursuit                                                   0.58   \n",
              "LGBMRegressor                                                               0.64   \n",
              "HistGradientBoostingRegressor                                               0.64   \n",
              "LassoLarsCV                                                                 0.70   \n",
              "OrthogonalMatchingPursuitCV                                                 0.71   \n",
              "LassoCV                                                                     0.71   \n",
              "LarsCV                                                                      0.76   \n",
              "ElasticNetCV                                                                0.78   \n",
              "NuSVR                                                                       0.81   \n",
              "KNeighborsRegressor                                                         0.82   \n",
              "SVR                                                                         0.84   \n",
              "GammaRegressor                                                              0.86   \n",
              "AdaBoostRegressor                                                           0.86   \n",
              "TweedieRegressor                                                            0.86   \n",
              "GeneralizedLinearRegressor                                                  0.86   \n",
              "RandomForestRegressor                                                       0.88   \n",
              "DecisionTreeRegressor                                                       0.89   \n",
              "ExtraTreeRegressor                                                          0.89   \n",
              "ExtraTreesRegressor                                                         0.90   \n",
              "BaggingRegressor                                                            0.90   \n",
              "XGBRegressor                                                                0.91   \n",
              "LinearRegression                                                            0.91   \n",
              "TransformedTargetRegressor                                                  0.91   \n",
              "GradientBoostingRegressor                                                   0.91   \n",
              "HuberRegressor                                                              0.92   \n",
              "PoissonRegressor                                                            0.92   \n",
              "Ridge                                                                       0.93   \n",
              "LinearSVR                                                                   0.93   \n",
              "BayesianRidge                                                               0.93   \n",
              "PassiveAggressiveRegressor                                                  0.93   \n",
              "MLPRegressor                                                                0.93   \n",
              "RidgeCV                                                                     0.93   \n",
              "SGDRegressor                                                                0.94   \n",
              "\n",
              "                                                                            RMSE  \\\n",
              "Model                                                                              \n",
              "Lars                          71007751113557157421113940864538607263614444206...   \n",
              "KernelRidge                                                                 4.00   \n",
              "GaussianProcessRegressor                                                    3.78   \n",
              "DummyRegressor                                                              1.34   \n",
              "LassoLars                                                                   1.34   \n",
              "Lasso                                                                       1.34   \n",
              "ElasticNet                                                                  1.14   \n",
              "LassoLarsIC                                                                 0.98   \n",
              "OrthogonalMatchingPursuit                                                   0.77   \n",
              "LGBMRegressor                                                               0.72   \n",
              "HistGradientBoostingRegressor                                               0.72   \n",
              "LassoLarsCV                                                                 0.65   \n",
              "OrthogonalMatchingPursuitCV                                                 0.64   \n",
              "LassoCV                                                                     0.64   \n",
              "LarsCV                                                                      0.59   \n",
              "ElasticNetCV                                                                0.56   \n",
              "NuSVR                                                                       0.51   \n",
              "KNeighborsRegressor                                                         0.50   \n",
              "SVR                                                                         0.48   \n",
              "GammaRegressor                                                              0.45   \n",
              "AdaBoostRegressor                                                           0.44   \n",
              "TweedieRegressor                                                            0.44   \n",
              "GeneralizedLinearRegressor                                                  0.44   \n",
              "RandomForestRegressor                                                       0.42   \n",
              "DecisionTreeRegressor                                                       0.40   \n",
              "ExtraTreeRegressor                                                          0.39   \n",
              "ExtraTreesRegressor                                                         0.38   \n",
              "BaggingRegressor                                                            0.38   \n",
              "XGBRegressor                                                                0.36   \n",
              "LinearRegression                                                            0.35   \n",
              "TransformedTargetRegressor                                                  0.35   \n",
              "GradientBoostingRegressor                                                   0.35   \n",
              "HuberRegressor                                                              0.35   \n",
              "PoissonRegressor                                                            0.34   \n",
              "Ridge                                                                       0.32   \n",
              "LinearSVR                                                                   0.31   \n",
              "BayesianRidge                                                               0.30   \n",
              "PassiveAggressiveRegressor                                                  0.30   \n",
              "MLPRegressor                                                                0.30   \n",
              "RidgeCV                                                                     0.30   \n",
              "SGDRegressor                                                                0.30   \n",
              "\n",
              "                               Time Taken  \n",
              "Model                                      \n",
              "Lars                                 0.11  \n",
              "KernelRidge                          0.02  \n",
              "GaussianProcessRegressor             0.02  \n",
              "DummyRegressor                       0.05  \n",
              "LassoLars                            0.01  \n",
              "Lasso                                0.05  \n",
              "ElasticNet                           0.04  \n",
              "LassoLarsIC                          0.03  \n",
              "OrthogonalMatchingPursuit            0.03  \n",
              "LGBMRegressor                        0.04  \n",
              "HistGradientBoostingRegressor        0.17  \n",
              "LassoLarsCV                          0.07  \n",
              "OrthogonalMatchingPursuitCV          0.04  \n",
              "LassoCV                              1.36  \n",
              "LarsCV                               0.61  \n",
              "ElasticNetCV                         1.13  \n",
              "NuSVR                                0.03  \n",
              "KNeighborsRegressor                  0.03  \n",
              "SVR                                  0.03  \n",
              "GammaRegressor                       0.03  \n",
              "AdaBoostRegressor                    0.25  \n",
              "TweedieRegressor                     0.03  \n",
              "GeneralizedLinearRegressor           0.03  \n",
              "RandomForestRegressor                0.24  \n",
              "DecisionTreeRegressor                0.03  \n",
              "ExtraTreeRegressor                   0.02  \n",
              "ExtraTreesRegressor                  0.17  \n",
              "BaggingRegressor                     0.05  \n",
              "XGBRegressor                         0.18  \n",
              "LinearRegression                     0.03  \n",
              "TransformedTargetRegressor           0.03  \n",
              "GradientBoostingRegressor            0.11  \n",
              "HuberRegressor                       0.06  \n",
              "PoissonRegressor                     0.03  \n",
              "Ridge                                0.03  \n",
              "LinearSVR                            0.06  \n",
              "BayesianRidge                        0.03  \n",
              "PassiveAggressiveRegressor           0.02  \n",
              "MLPRegressor                         0.16  \n",
              "RidgeCV                              0.03  \n",
              "SGDRegressor                         0.03  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-02c734e2-04e8-4538-889d-f8d30465b4aa\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>Adjusted R-Squared</th>\n",
              "      <th>R-Squared</th>\n",
              "      <th>RMSE</th>\n",
              "      <th>Time Taken</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Model</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>Lars</th>\n",
              "      <td>24504444672710904257829102848509112108058660956...</td>\n",
              "      <td>-3553144477543081245821142408477825905874475975...</td>\n",
              "      <td>71007751113557157421113940864538607263614444206...</td>\n",
              "      <td>0.11</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>KernelRidge</th>\n",
              "      <td>1.78</td>\n",
              "      <td>-10.27</td>\n",
              "      <td>4.00</td>\n",
              "      <td>0.02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>GaussianProcessRegressor</th>\n",
              "      <td>1.69</td>\n",
              "      <td>-9.06</td>\n",
              "      <td>3.78</td>\n",
              "      <td>0.02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>DummyRegressor</th>\n",
              "      <td>1.09</td>\n",
              "      <td>-0.27</td>\n",
              "      <td>1.34</td>\n",
              "      <td>0.05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LassoLars</th>\n",
              "      <td>1.09</td>\n",
              "      <td>-0.27</td>\n",
              "      <td>1.34</td>\n",
              "      <td>0.01</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Lasso</th>\n",
              "      <td>1.09</td>\n",
              "      <td>-0.27</td>\n",
              "      <td>1.34</td>\n",
              "      <td>0.05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ElasticNet</th>\n",
              "      <td>1.06</td>\n",
              "      <td>0.08</td>\n",
              "      <td>1.14</td>\n",
              "      <td>0.04</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LassoLarsIC</th>\n",
              "      <td>1.05</td>\n",
              "      <td>0.33</td>\n",
              "      <td>0.98</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>OrthogonalMatchingPursuit</th>\n",
              "      <td>1.03</td>\n",
              "      <td>0.58</td>\n",
              "      <td>0.77</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LGBMRegressor</th>\n",
              "      <td>1.03</td>\n",
              "      <td>0.64</td>\n",
              "      <td>0.72</td>\n",
              "      <td>0.04</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>HistGradientBoostingRegressor</th>\n",
              "      <td>1.03</td>\n",
              "      <td>0.64</td>\n",
              "      <td>0.72</td>\n",
              "      <td>0.17</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LassoLarsCV</th>\n",
              "      <td>1.02</td>\n",
              "      <td>0.70</td>\n",
              "      <td>0.65</td>\n",
              "      <td>0.07</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>OrthogonalMatchingPursuitCV</th>\n",
              "      <td>1.02</td>\n",
              "      <td>0.71</td>\n",
              "      <td>0.64</td>\n",
              "      <td>0.04</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LassoCV</th>\n",
              "      <td>1.02</td>\n",
              "      <td>0.71</td>\n",
              "      <td>0.64</td>\n",
              "      <td>1.36</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LarsCV</th>\n",
              "      <td>1.02</td>\n",
              "      <td>0.76</td>\n",
              "      <td>0.59</td>\n",
              "      <td>0.61</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ElasticNetCV</th>\n",
              "      <td>1.02</td>\n",
              "      <td>0.78</td>\n",
              "      <td>0.56</td>\n",
              "      <td>1.13</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>NuSVR</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.81</td>\n",
              "      <td>0.51</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>KNeighborsRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.82</td>\n",
              "      <td>0.50</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>SVR</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.84</td>\n",
              "      <td>0.48</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>GammaRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.86</td>\n",
              "      <td>0.45</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>AdaBoostRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.86</td>\n",
              "      <td>0.44</td>\n",
              "      <td>0.25</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>TweedieRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.86</td>\n",
              "      <td>0.44</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>GeneralizedLinearRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.86</td>\n",
              "      <td>0.44</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>RandomForestRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.88</td>\n",
              "      <td>0.42</td>\n",
              "      <td>0.24</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>DecisionTreeRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.89</td>\n",
              "      <td>0.40</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ExtraTreeRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.89</td>\n",
              "      <td>0.39</td>\n",
              "      <td>0.02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ExtraTreesRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.90</td>\n",
              "      <td>0.38</td>\n",
              "      <td>0.17</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>BaggingRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.90</td>\n",
              "      <td>0.38</td>\n",
              "      <td>0.05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>XGBRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.91</td>\n",
              "      <td>0.36</td>\n",
              "      <td>0.18</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LinearRegression</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.91</td>\n",
              "      <td>0.35</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>TransformedTargetRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.91</td>\n",
              "      <td>0.35</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>GradientBoostingRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.91</td>\n",
              "      <td>0.35</td>\n",
              "      <td>0.11</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>HuberRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.92</td>\n",
              "      <td>0.35</td>\n",
              "      <td>0.06</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>PoissonRegressor</th>\n",
              "      <td>1.01</td>\n",
              "      <td>0.92</td>\n",
              "      <td>0.34</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Ridge</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.32</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>LinearSVR</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.31</td>\n",
              "      <td>0.06</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>BayesianRidge</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.30</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>PassiveAggressiveRegressor</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.30</td>\n",
              "      <td>0.02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>MLPRegressor</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.30</td>\n",
              "      <td>0.16</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>RidgeCV</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.93</td>\n",
              "      <td>0.30</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>SGDRegressor</th>\n",
              "      <td>1.00</td>\n",
              "      <td>0.94</td>\n",
              "      <td>0.30</td>\n",
              "      <td>0.03</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-02c734e2-04e8-4538-889d-f8d30465b4aa')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-02c734e2-04e8-4538-889d-f8d30465b4aa button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-02c734e2-04e8-4538-889d-f8d30465b4aa');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 65
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.linear_model import SGDRegressor\n",
        "\n",
        "np.random.seed(42)\n",
        "\n",
        "sgd_model = SGDRegressor(max_iter=1000, tol=1e-3)\n",
        "sgd_model.fit(x_train, y_train)\n",
        "\n",
        "s1 = sgd_model.score(x_test, y_test)\n",
        "s1"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "x9N5DlHQMOmd",
        "outputId": "9d3a62f2-aece-4823-aa54-6b91999ef3d9"
      },
      "execution_count": 64,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.8364099858768093"
            ]
          },
          "metadata": {},
          "execution_count": 64
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred = sgd_model.predict(x_test)"
      ],
      "metadata": {
        "id": "iiTdZQ7FScq8"
      },
      "execution_count": 67,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# plotting predicted vs actual data\n",
        "\n",
        "ax = sns.regplot(y_test, y_pred, scatter_kws={'alpha':0.4})\n",
        "ax.set_xlabel('Experimental pIC50')\n",
        "ax.set_ylabel('Predicted pIC50')\n",
        "ax.set_xlim(0, 6)\n",
        "ax.set_ylim(0, 6)\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 289
        },
        "id": "vnEpBp4pSmZK",
        "outputId": "516bcc7f-9553-4141-82d1-d22a612dc6a9"
      },
      "execution_count": 68,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        ""
      ],
      "metadata": {
        "id": "yY885DAPs11B"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}