Bioinformatics_3.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Bioinformatics_3.ipynb",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "gpuClass": "standard"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "Lecture 3 : https://www.youtube.com/watch?v=zD2focOkQ48&list=PLtqF5YXg7GLlQJUv9XJ3RWdd5VYGwBHrP&index=3\n",
        "\n",
        "\n",
        "Data Preparation"
      ],
      "metadata": {
        "id": "9W6dsRy_N104"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Download PaDel - descriptor"
      ],
      "metadata": {
        "id": "AZQ_B7q1OOQ5"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "! wget https://github.com/dataprofessor/bioinformatics/raw/master/padel.zip\n",
        "! wget https://github.com/dataprofessor/bioinformatics/raw/master/padel.sh"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yXRQBKaHNzdz",
        "outputId": "b454ee65-8f9e-4339-ba88-18f4a52ac890"
      },
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2022-08-06 03:44:08--  https://github.com/dataprofessor/bioinformatics/raw/master/padel.zip\n",
            "Resolving github.com (github.com)... 140.82.112.3\n",
            "Connecting to github.com (github.com)|140.82.112.3|:443... connected.\n",
            "HTTP request sent, awaiting response... 302 Found\n",
            "Location: https://raw.githubusercontent.com/dataprofessor/bioinformatics/master/padel.zip [following]\n",
            "--2022-08-06 03:44:09--  https://raw.githubusercontent.com/dataprofessor/bioinformatics/master/padel.zip\n",
            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 25768637 (25M) [application/zip]\n",
            "Saving to: ‘padel.zip’\n",
            "\n",
            "padel.zip           100%[===================>]  24.57M  --.-KB/s    in 0.1s    \n",
            "\n",
            "2022-08-06 03:44:09 (167 MB/s) - ‘padel.zip’ saved [25768637/25768637]\n",
            "\n",
            "--2022-08-06 03:44:09--  https://github.com/dataprofessor/bioinformatics/raw/master/padel.sh\n",
            "Resolving github.com (github.com)... 140.82.113.3\n",
            "Connecting to github.com (github.com)|140.82.113.3|:443... connected.\n",
            "HTTP request sent, awaiting response... 302 Found\n",
            "Location: https://raw.githubusercontent.com/dataprofessor/bioinformatics/master/padel.sh [following]\n",
            "--2022-08-06 03:44:09--  https://raw.githubusercontent.com/dataprofessor/bioinformatics/master/padel.sh\n",
            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.110.133, 185.199.109.133, ...\n",
            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 231 [text/plain]\n",
            "Saving to: ‘padel.sh’\n",
            "\n",
            "padel.sh            100%[===================>]     231  --.-KB/s    in 0s      \n",
            "\n",
            "2022-08-06 03:44:09 (11.7 MB/s) - ‘padel.sh’ saved [231/231]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "! unzip padel.zip"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZvYigdrSN7He",
        "outputId": "8b05401e-c6d3-4c95-a1da-bd1a5c954a89"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Archive:  padel.zip\n",
            "   creating: PaDEL-Descriptor/\n",
            "  inflating: __MACOSX/._PaDEL-Descriptor  \n",
            "  inflating: PaDEL-Descriptor/MACCSFingerprinter.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._MACCSFingerprinter.xml  \n",
            "  inflating: PaDEL-Descriptor/AtomPairs2DFingerprinter.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._AtomPairs2DFingerprinter.xml  \n",
            "  inflating: PaDEL-Descriptor/EStateFingerprinter.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._EStateFingerprinter.xml  \n",
            "  inflating: PaDEL-Descriptor/Fingerprinter.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._Fingerprinter.xml  \n",
            "  inflating: PaDEL-Descriptor/.DS_Store  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._.DS_Store  \n",
            "   creating: PaDEL-Descriptor/license/\n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._license  \n",
            "  inflating: PaDEL-Descriptor/KlekotaRothFingerprintCount.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._KlekotaRothFingerprintCount.xml  \n",
            "  inflating: PaDEL-Descriptor/config  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._config  \n",
            "  inflating: PaDEL-Descriptor/PubchemFingerprinter.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._PubchemFingerprinter.xml  \n",
            "  inflating: PaDEL-Descriptor/ExtendedFingerprinter.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._ExtendedFingerprinter.xml  \n",
            "  inflating: PaDEL-Descriptor/KlekotaRothFingerprinter.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._KlekotaRothFingerprinter.xml  \n",
            "  inflating: PaDEL-Descriptor/GraphOnlyFingerprinter.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._GraphOnlyFingerprinter.xml  \n",
            "  inflating: PaDEL-Descriptor/SubstructureFingerprinter.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._SubstructureFingerprinter.xml  \n",
            "  inflating: PaDEL-Descriptor/Descriptors.xls  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._Descriptors.xls  \n",
            "   creating: PaDEL-Descriptor/lib/\n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._lib  \n",
            "  inflating: PaDEL-Descriptor/PaDEL-Descriptor.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._PaDEL-Descriptor.jar  \n",
            "  inflating: PaDEL-Descriptor/SubstructureFingerprintCount.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._SubstructureFingerprintCount.xml  \n",
            "  inflating: PaDEL-Descriptor/AtomPairs2DFingerprintCount.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._AtomPairs2DFingerprintCount.xml  \n",
            "  inflating: PaDEL-Descriptor/descriptors.xml  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/._descriptors.xml  \n",
            "  inflating: PaDEL-Descriptor/license/lgpl-2.1.txt  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/license/._lgpl-2.1.txt  \n",
            "  inflating: PaDEL-Descriptor/license/LICENSE.txt  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/license/._LICENSE.txt  \n",
            "  inflating: PaDEL-Descriptor/license/README - CDK  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/license/._README - CDK  \n",
            "  inflating: PaDEL-Descriptor/license/lgpl.license  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/license/._lgpl.license  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-core-2.4.7-SNAPSHOT(3).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-core-2.4.7-SNAPSHOT(3).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Jobs(6).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Jobs(6).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jgrapht-0.6.0(4).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jgrapht-0.6.0(4).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/commons-cli-1.2(2).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._commons-cli-1.2(2).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/xom-1.1(1).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._xom-1.1(1).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/swing-worker-1.1.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._swing-worker-1.1.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/commons-cli-1.2(3).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._commons-cli-1.2(3).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jgrapht-0.6.0(5).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jgrapht-0.6.0(5).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jama(1).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jama(1).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/appframework-1.0.3.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._appframework-1.0.3.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Jobs(7).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Jobs(7).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/vecmath1.2-1.14.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._vecmath1.2-1.14.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-smarts-2.4.7-SNAPSHOT(6).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-smarts-2.4.7-SNAPSHOT(6).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-core-2.4.7-SNAPSHOT(2).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-core-2.4.7-SNAPSHOT(2).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jama(6).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jama(6).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jgrapht-0.6.0(2).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jgrapht-0.6.0(2).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Descriptor(3).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Descriptor(3).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/commons-cli-1.2(4).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._commons-cli-1.2(4).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-base-2.4.7-SNAPSHOT.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-base-2.4.7-SNAPSHOT.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-smarts-2.4.7-SNAPSHOT(1).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-smarts-2.4.7-SNAPSHOT(1).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/commons-cli-1.2.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._commons-cli-1.2.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/commons-cli-1.2(8).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._commons-cli-1.2(8).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jgrapht-0.6.0.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jgrapht-0.6.0.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Jobs(1).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Jobs(1).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Jobs.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Jobs.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-core-2.4.7-SNAPSHOT(4).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-core-2.4.7-SNAPSHOT(4).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/xom-1.1.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._xom-1.1.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/commons-cli-1.2(5).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._commons-cli-1.2(5).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Descriptor(2).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Descriptor(2).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jgrapht-0.6.0(3).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jgrapht-0.6.0(3).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jama(7).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jama(7).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-core-2.4.7-SNAPSHOT.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-core-2.4.7-SNAPSHOT.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/commons-cli-1.2(6).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._commons-cli-1.2(6).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Descriptor(1).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Descriptor(1).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jama(4).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jama(4).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Jobs(2).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Jobs(2).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-smarts-2.4.7-SNAPSHOT(3).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-smarts-2.4.7-SNAPSHOT(3).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-smarts-2.4.7-SNAPSHOT(2).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-smarts-2.4.7-SNAPSHOT(2).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-smarts-2.4.7-SNAPSHOT.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-smarts-2.4.7-SNAPSHOT.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Jobs(3).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Jobs(3).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/l2fprod-common-all(1).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._l2fprod-common-all(1).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jama.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jama.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/l2fprod-common-all.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._l2fprod-common-all.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jama(5).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jama(5).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jgrapht-0.6.0(1).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jgrapht-0.6.0(1).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/commons-cli-1.2(7).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._commons-cli-1.2(7).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Descriptor.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Descriptor.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Jobs(4).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Jobs(4).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/cdk-1.4.15.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._cdk-1.4.15.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-smarts-2.4.7-SNAPSHOT(5).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-smarts-2.4.7-SNAPSHOT(5).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-core-2.4.7-SNAPSHOT(1).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-core-2.4.7-SNAPSHOT(1).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Jobs(8).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Jobs(8).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jgrapht-0.6.0(6).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jgrapht-0.6.0(6).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jama(2).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jama(2).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/jama(3).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._jama(3).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/commons-cli-1.2(1).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._commons-cli-1.2(1).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/guava-17.0.jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._guava-17.0.jar  \n",
            "  inflating: PaDEL-Descriptor/lib/ambit2-smarts-2.4.7-SNAPSHOT(4).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._ambit2-smarts-2.4.7-SNAPSHOT(4).jar  \n",
            "  inflating: PaDEL-Descriptor/lib/libPaDEL-Jobs(5).jar  \n",
            "  inflating: __MACOSX/PaDEL-Descriptor/lib/._libPaDEL-Jobs(5).jar  \n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Load bioactivity data"
      ],
      "metadata": {
        "id": "lEiDmEZUOkAB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "! wget https://raw.githubusercontent.com/dataprofessor/data/master/acetylcholinesterase_04_bioactivity_data_3class_pIC50.csv"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DIaCFyjcOhbp",
        "outputId": "540e851f-3bec-4e59-d83f-bbaf8670b7a6"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2022-08-06 03:44:10--  https://raw.githubusercontent.com/dataprofessor/data/master/acetylcholinesterase_04_bioactivity_data_3class_pIC50.csv\n",
            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 655414 (640K) [text/plain]\n",
            "Saving to: ‘acetylcholinesterase_04_bioactivity_data_3class_pIC50.csv’\n",
            "\n",
            "\r          acetylcho   0%[                    ]       0  --.-KB/s               \racetylcholinesteras 100%[===================>] 640.05K  --.-KB/s    in 0.004s  \n",
            "\n",
            "2022-08-06 03:44:10 (146 MB/s) - ‘acetylcholinesterase_04_bioactivity_data_3class_pIC50.csv’ saved [655414/655414]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd"
      ],
      "metadata": {
        "id": "gLJeybi2OsTO"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df3 = pd.read_csv('acetylcholinesterase_04_bioactivity_data_3class_pIC50.csv')"
      ],
      "metadata": {
        "id": "gPigVB0-OxyD"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df3"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 626
        },
        "id": "DTyzRyZWO3EL",
        "outputId": "70ec224b-0cd1-4c2a-de9e-2baca1259c34"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      Unnamed: 0 molecule_chembl_id  \\\n",
              "0              0       CHEMBL133897   \n",
              "1              1       CHEMBL336398   \n",
              "2              2       CHEMBL131588   \n",
              "3              3       CHEMBL130628   \n",
              "4              4       CHEMBL130478   \n",
              "...          ...                ...   \n",
              "4690        4690      CHEMBL4293155   \n",
              "4691        4691      CHEMBL4282558   \n",
              "4692        4692      CHEMBL4281727   \n",
              "4693        4693      CHEMBL4292349   \n",
              "4694        4694      CHEMBL4278260   \n",
              "\n",
              "                                       canonical_smiles         class  \\\n",
              "0                 CCOc1nn(-c2cccc(OCc3ccccc3)c2)c(=O)o1        active   \n",
              "1            O=C(N1CCCCC1)n1nc(-c2ccc(Cl)cc2)nc1SCC1CC1        active   \n",
              "2     CN(C(=O)n1nc(-c2ccc(Cl)cc2)nc1SCC(F)(F)F)c1ccccc1      inactive   \n",
              "3         O=C(N1CCCCC1)n1nc(-c2ccc(Cl)cc2)nc1SCC(F)(F)F        active   \n",
              "4             CSc1nc(-c2ccc(OC(F)(F)F)cc2)nn1C(=O)N(C)C        active   \n",
              "...                                                 ...           ...   \n",
              "4690  CC(C)(C)c1cc(/C=C/C(=O)NCCC2CCN(Cc3ccccc3Cl)CC...  intermediate   \n",
              "4691  CC(C)(C)c1cc(/C=C/C(=O)NCCC2CCN(Cc3cccc(Cl)c3)...  intermediate   \n",
              "4692  CC(C)(C)c1cc(/C=C/C(=O)NCCC2CCN(Cc3ccc(Br)cc3)...  intermediate   \n",
              "4693  CC(C)(C)c1cc(/C=C/C(=O)NCCC2CCN(Cc3cccc([N+](=...  intermediate   \n",
              "4694  CC(C)(C)c1cc(/C=C/C(=O)NCCC2CCN(Cc3ccc(C#N)cc3...  intermediate   \n",
              "\n",
              "           MW     LogP  NumHDonors  NumHAcceptors     pIC50  \n",
              "0     312.325  2.80320         0.0            6.0  6.124939  \n",
              "1     376.913  4.55460         0.0            5.0  7.000000  \n",
              "2     426.851  5.35740         0.0            5.0  4.301030  \n",
              "3     404.845  4.70690         0.0            5.0  6.522879  \n",
              "4     346.334  3.09530         0.0            6.0  6.096910  \n",
              "...       ...      ...         ...            ...       ...  \n",
              "4690  511.150  7.07230         2.0            3.0  5.612610  \n",
              "4691  511.150  7.07230         2.0            3.0  5.595166  \n",
              "4692  555.601  7.18140         2.0            3.0  5.419075  \n",
              "4693  521.702  6.32710         2.0            5.0  5.460924  \n",
              "4694  501.715  6.29058         2.0            4.0  5.555955  \n",
              "\n",
              "[4695 rows x 9 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e7a25e7b-d21b-4a9c-8b4c-084a48213f70\">\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>Unnamed: 0</th>\n",
              "      <th>molecule_chembl_id</th>\n",
              "      <th>canonical_smiles</th>\n",
              "      <th>class</th>\n",
              "      <th>MW</th>\n",
              "      <th>LogP</th>\n",
              "      <th>NumHDonors</th>\n",
              "      <th>NumHAcceptors</th>\n",
              "      <th>pIC50</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>CHEMBL133897</td>\n",
              "      <td>CCOc1nn(-c2cccc(OCc3ccccc3)c2)c(=O)o1</td>\n",
              "      <td>active</td>\n",
              "      <td>312.325</td>\n",
              "      <td>2.80320</td>\n",
              "      <td>0.0</td>\n",
              "      <td>6.0</td>\n",
              "      <td>6.124939</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>CHEMBL336398</td>\n",
              "      <td>O=C(N1CCCCC1)n1nc(-c2ccc(Cl)cc2)nc1SCC1CC1</td>\n",
              "      <td>active</td>\n",
              "      <td>376.913</td>\n",
              "      <td>4.55460</td>\n",
              "      <td>0.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>7.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>CHEMBL131588</td>\n",
              "      <td>CN(C(=O)n1nc(-c2ccc(Cl)cc2)nc1SCC(F)(F)F)c1ccccc1</td>\n",
              "      <td>inactive</td>\n",
              "      <td>426.851</td>\n",
              "      <td>5.35740</td>\n",
              "      <td>0.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>4.301030</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3</td>\n",
              "      <td>CHEMBL130628</td>\n",
              "      <td>O=C(N1CCCCC1)n1nc(-c2ccc(Cl)cc2)nc1SCC(F)(F)F</td>\n",
              "      <td>active</td>\n",
              "      <td>404.845</td>\n",
              "      <td>4.70690</td>\n",
              "      <td>0.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>6.522879</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>CHEMBL130478</td>\n",
              "      <td>CSc1nc(-c2ccc(OC(F)(F)F)cc2)nn1C(=O)N(C)C</td>\n",
              "      <td>active</td>\n",
              "      <td>346.334</td>\n",
              "      <td>3.09530</td>\n",
              "      <td>0.0</td>\n",
              "      <td>6.0</td>\n",
              "      <td>6.096910</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>4690</th>\n",
              "      <td>4690</td>\n",
              "      <td>CHEMBL4293155</td>\n",
              "      <td>CC(C)(C)c1cc(/C=C/C(=O)NCCC2CCN(Cc3ccccc3Cl)CC...</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>511.150</td>\n",
              "      <td>7.07230</td>\n",
              "      <td>2.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>5.612610</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4691</th>\n",
              "      <td>4691</td>\n",
              "      <td>CHEMBL4282558</td>\n",
              "      <td>CC(C)(C)c1cc(/C=C/C(=O)NCCC2CCN(Cc3cccc(Cl)c3)...</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>511.150</td>\n",
              "      <td>7.07230</td>\n",
              "      <td>2.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>5.595166</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4692</th>\n",
              "      <td>4692</td>\n",
              "      <td>CHEMBL4281727</td>\n",
              "      <td>CC(C)(C)c1cc(/C=C/C(=O)NCCC2CCN(Cc3ccc(Br)cc3)...</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>555.601</td>\n",
              "      <td>7.18140</td>\n",
              "      <td>2.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>5.419075</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4693</th>\n",
              "      <td>4693</td>\n",
              "      <td>CHEMBL4292349</td>\n",
              "      <td>CC(C)(C)c1cc(/C=C/C(=O)NCCC2CCN(Cc3cccc([N+](=...</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>521.702</td>\n",
              "      <td>6.32710</td>\n",
              "      <td>2.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>5.460924</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4694</th>\n",
              "      <td>4694</td>\n",
              "      <td>CHEMBL4278260</td>\n",
              "      <td>CC(C)(C)c1cc(/C=C/C(=O)NCCC2CCN(Cc3ccc(C#N)cc3...</td>\n",
              "      <td>intermediate</td>\n",
              "      <td>501.715</td>\n",
              "      <td>6.29058</td>\n",
              "      <td>2.0</td>\n",
              "      <td>4.0</td>\n",
              "      <td>5.555955</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>4695 rows × 9 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e7a25e7b-d21b-4a9c-8b4c-084a48213f70')\"\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-e7a25e7b-d21b-4a9c-8b4c-084a48213f70 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-e7a25e7b-d21b-4a9c-8b4c-084a48213f70');\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": 6
        }
      ]
    },
    {
      "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)"
      ],
      "metadata": {
        "id": "b4JAVKBmO30E"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "! cat molecule.smi | head -5"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yqQ30ZAgO9vZ",
        "outputId": "3ea6fa71-e0f5-43e5-8971-fb11fb14b6ec"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "CCOc1nn(-c2cccc(OCc3ccccc3)c2)c(=O)o1\tCHEMBL133897\n",
            "O=C(N1CCCCC1)n1nc(-c2ccc(Cl)cc2)nc1SCC1CC1\tCHEMBL336398\n",
            "CN(C(=O)n1nc(-c2ccc(Cl)cc2)nc1SCC(F)(F)F)c1ccccc1\tCHEMBL131588\n",
            "O=C(N1CCCCC1)n1nc(-c2ccc(Cl)cc2)nc1SCC(F)(F)F\tCHEMBL130628\n",
            "CSc1nc(-c2ccc(OC(F)(F)F)cc2)nn1C(=O)N(C)C\tCHEMBL130478\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "C - Carbon atom\n",
        "O - Oxygen\n",
        "N- Nytrogen\n"
      ],
      "metadata": {
        "id": "z2QAphL7PP1B"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "! cat molecule.smi | wc -l"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tAb2H0UnPB-8",
        "outputId": "a49ee657-d973-466c-827b-95c64c3c6c62"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "4695\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "line of molecules"
      ],
      "metadata": {
        "id": "CN1AT17_PgwQ"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Calculate PaDel description"
      ],
      "metadata": {
        "id": "MWtQbu3_PnEK"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "! cat padel.sh"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "k8GaDvIGPLdD",
        "outputId": "21f233ae-5a64-4494-f566-eaf0d0b1918b"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "java -Xms1G -Xmx1G -Djava.awt.headless=true -jar ./PaDEL-Descriptor/PaDEL-Descriptor.jar -removesalt -standardizenitro -fingerprints -descriptortypes ./PaDEL-Descriptor/PubchemFingerprinter.xml -dir ./ -file descriptors_output.csv\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "for below code or descriptors_output.csv"
      ],
      "metadata": {
        "id": "bGiQ1bF7QWYi"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "! bash padel.sh"
      ],
      "metadata": {
        "id": "GQ-Bgwk8PsKq"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "! ls -l"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XM0Vt7_wPumu",
        "outputId": "47df0f76-ca92-41e1-9130-28024047e991"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "total 34296\n",
            "-rw-r--r-- 1 root root   655414 Aug  6 03:44 acetylcholinesterase_04_bioactivity_data_3class_pIC50.csv\n",
            "-rw-r--r-- 1 root root  8356701 Aug  6 03:49 descriptors_output.csv\n",
            "drwxr-xr-x 3 root root     4096 Aug  6 03:44 __MACOSX\n",
            "-rw-r--r-- 1 root root   310658 Aug  6 03:44 molecule.smi\n",
            "drwxrwxr-x 4 root root     4096 May 30  2020 PaDEL-Descriptor\n",
            "-rw-r--r-- 1 root root      231 Aug  6 03:44 padel.sh\n",
            "-rw-r--r-- 1 root root 25768637 Aug  6 03:44 padel.zip\n",
            "drwxr-xr-x 1 root root     4096 Aug  3 20:21 sample_data\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Preparing the X and Y Matrices"
      ],
      "metadata": {
        "id": "lTTnJP1aSwGt"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df3_X = pd.read_csv('descriptors_output.csv')"
      ],
      "metadata": {
        "id": "TY_O1xDQSt5W"
      },
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df3_X"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 488
        },
        "id": "iOq_Xz4NS0w1",
        "outputId": "e07ddea5-4b73-4c94-b6c8-4b50f2302bd0"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "               Name  PubchemFP0  PubchemFP1  PubchemFP2  PubchemFP3  \\\n",
              "0      CHEMBL336398           1           1           1           0   \n",
              "1      CHEMBL133897           1           1           1           0   \n",
              "2      CHEMBL130628           1           1           1           0   \n",
              "3      CHEMBL131588           1           1           0           0   \n",
              "4      CHEMBL130478           1           1           0           0   \n",
              "...             ...         ...         ...         ...         ...   \n",
              "4690  CHEMBL4293155           1           1           1           1   \n",
              "4691  CHEMBL4282558           1           1           1           1   \n",
              "4692  CHEMBL4281727           1           1           1           1   \n",
              "4693  CHEMBL4292349           1           1           1           1   \n",
              "4694  CHEMBL4278260           1           1           1           1   \n",
              "\n",
              "      PubchemFP4  PubchemFP5  PubchemFP6  PubchemFP7  PubchemFP8  ...  \\\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",
              "4690           0           0           0           0           0  ...   \n",
              "4691           0           0           0           0           0  ...   \n",
              "4692           0           0           0           0           0  ...   \n",
              "4693           0           0           0           0           0  ...   \n",
              "4694           0           0           0           0           0  ...   \n",
              "\n",
              "      PubchemFP871  PubchemFP872  PubchemFP873  PubchemFP874  PubchemFP875  \\\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",
              "4690             0             0             0             0             0   \n",
              "4691             0             0             0             0             0   \n",
              "4692             0             0             0             0             0   \n",
              "4693             0             0             0             0             0   \n",
              "4694             0             0             0             0             0   \n",
              "\n",
              "      PubchemFP876  PubchemFP877  PubchemFP878  PubchemFP879  PubchemFP880  \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",
              "4690             0             0             0             0             0  \n",
              "4691             0             0             0             0             0  \n",
              "4692             0             0             0             0             0  \n",
              "4693             0             0             0             0             0  \n",
              "4694             0             0             0             0             0  \n",
              "\n",
              "[4695 rows x 882 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-c4e1820d-149f-44ce-8c43-cfca21333aad\">\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>CHEMBL336398</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>CHEMBL133897</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>2</th>\n",
              "      <td>CHEMBL130628</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>CHEMBL131588</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>CHEMBL130478</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>...</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>4690</th>\n",
              "      <td>CHEMBL4293155</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>4691</th>\n",
              "      <td>CHEMBL4282558</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>4692</th>\n",
              "      <td>CHEMBL4281727</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>4693</th>\n",
              "      <td>CHEMBL4292349</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>4694</th>\n",
              "      <td>CHEMBL4278260</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",
              "  </tbody>\n",
              "</table>\n",
              "<p>4695 rows × 882 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c4e1820d-149f-44ce-8c43-cfca21333aad')\"\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-c4e1820d-149f-44ce-8c43-cfca21333aad 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-c4e1820d-149f-44ce-8c43-cfca21333aad');\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": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df3_X = df3_X.drop(columns=['Name'])\n",
        "df3_X"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 488
        },
        "id": "Abo3W71LS4uS",
        "outputId": "05bc6b04-c1c9-44aa-9f94-77fcba72c396"
      },
      "execution_count": 17,
      "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           1           0           0           0   \n",
              "2              1           1           1           0           0           0   \n",
              "3              1           1           0           0           0           0   \n",
              "4              1           1           0           0           0           0   \n",
              "...          ...         ...         ...         ...         ...         ...   \n",
              "4690           1           1           1           1           0           0   \n",
              "4691           1           1           1           1           0           0   \n",
              "4692           1           1           1           1           0           0   \n",
              "4693           1           1           1           1           0           0   \n",
              "4694           1           1           1           1           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",
              "4690           0           0           0           1  ...             0   \n",
              "4691           0           0           0           1  ...             0   \n",
              "4692           0           0           0           1  ...             0   \n",
              "4693           0           0           0           1  ...             0   \n",
              "4694           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",
              "4690             0             0             0             0             0   \n",
              "4691             0             0             0             0             0   \n",
              "4692             0             0             0             0             0   \n",
              "4693             0             0             0             0             0   \n",
              "4694             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",
              "4690             0             0             0             0  \n",
              "4691             0             0             0             0  \n",
              "4692             0             0             0             0  \n",
              "4693             0             0             0             0  \n",
              "4694             0             0             0             0  \n",
              "\n",
              "[4695 rows x 881 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-b432b109-36e8-42a4-a550-4442cc819b70\">\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>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>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>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>...</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>4690</th>\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>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>4691</th>\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>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>4692</th>\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>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>4693</th>\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>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>4694</th>\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>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>4695 rows × 881 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b432b109-36e8-42a4-a550-4442cc819b70')\"\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-b432b109-36e8-42a4-a550-4442cc819b70 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-b432b109-36e8-42a4-a550-4442cc819b70');\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": "markdown",
      "source": [
        "Y variable\n",
        "\n",
        "Note : Convert IC50 to pIC50"
      ],
      "metadata": {
        "id": "IwkQjX-lS7AR"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df3_Y = df3['pIC50']\n",
        "df3_Y"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "o4c27qVDS1vc",
        "outputId": "2b2a5345-9bc5-46cb-809d-daf91a4617f0"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0       6.124939\n",
              "1       7.000000\n",
              "2       4.301030\n",
              "3       6.522879\n",
              "4       6.096910\n",
              "          ...   \n",
              "4690    5.612610\n",
              "4691    5.595166\n",
              "4692    5.419075\n",
              "4693    5.460924\n",
              "4694    5.555955\n",
              "Name: pIC50, Length: 4695, dtype: float64"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Combining X and Y variable"
      ],
      "metadata": {
        "id": "PqNHPbV1TFUI"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "dataset3 = pd.concat([df3_X,df3_Y], axis=1)\n",
        "dataset3"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 488
        },
        "id": "uG4km-LxTB6V",
        "outputId": "8ffec09a-8bd4-4983-93d9-09db1c21f8c8"
      },
      "execution_count": 19,
      "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           1           0           0           0   \n",
              "2              1           1           1           0           0           0   \n",
              "3              1           1           0           0           0           0   \n",
              "4              1           1           0           0           0           0   \n",
              "...          ...         ...         ...         ...         ...         ...   \n",
              "4690           1           1           1           1           0           0   \n",
              "4691           1           1           1           1           0           0   \n",
              "4692           1           1           1           1           0           0   \n",
              "4693           1           1           1           1           0           0   \n",
              "4694           1           1           1           1           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",
              "4690           0           0           0           1  ...             0   \n",
              "4691           0           0           0           1  ...             0   \n",
              "4692           0           0           0           1  ...             0   \n",
              "4693           0           0           0           1  ...             0   \n",
              "4694           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",
              "4690             0             0             0             0             0   \n",
              "4691             0             0             0             0             0   \n",
              "4692             0             0             0             0             0   \n",
              "4693             0             0             0             0             0   \n",
              "4694             0             0             0             0             0   \n",
              "\n",
              "      PubchemFP878  PubchemFP879  PubchemFP880     pIC50  \n",
              "0                0             0             0  6.124939  \n",
              "1                0             0             0  7.000000  \n",
              "2                0             0             0  4.301030  \n",
              "3                0             0             0  6.522879  \n",
              "4                0             0             0  6.096910  \n",
              "...            ...           ...           ...       ...  \n",
              "4690             0             0             0  5.612610  \n",
              "4691             0             0             0  5.595166  \n",
              "4692             0             0             0  5.419075  \n",
              "4693             0             0             0  5.460924  \n",
              "4694             0             0             0  5.555955  \n",
              "\n",
              "[4695 rows x 882 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-fab9f451-c182-4ae9-a8b9-6e120fa27a1c\">\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>6.124939</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</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>7.000000</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>4.301030</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>6.522879</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</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>6.096910</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>4690</th>\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>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>5.612610</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4691</th>\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>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>5.595166</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4692</th>\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>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>5.419075</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4693</th>\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>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>5.460924</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4694</th>\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>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>5.555955</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>4695 rows × 882 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-fab9f451-c182-4ae9-a8b9-6e120fa27a1c')\"\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-fab9f451-c182-4ae9-a8b9-6e120fa27a1c 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-fab9f451-c182-4ae9-a8b9-6e120fa27a1c');\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": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset3.to_csv('acetylcholinesterase_06_bioactivity_data_3class_pIC50_pubchem_fp.csv', index=False)\n"
      ],
      "metadata": {
        "id": "D_nyagSNTHo8"
      },
      "execution_count": 20,
      "outputs": []
    }
  ]
}