4_Acetylcholinesterase_Regression_Random_Forest.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "7AAfh_j7hSwQ"
   },
   "source": [
    "# **Bioinformatics Project - Computational Drug Discovery [Part 4] Regression Models with Random Forest**\n",
    "\n",
    "Chanin Nantasenamat\n",
    "\n",
    "[*'Data Professor' YouTube channel*](http://youtube.com/dataprofessor)\n",
    "\n",
    "In this Jupyter notebook, we will be building a real-life **data science project** that you can include in your **data science portfolio**. Particularly, we will be building a machine learning model using the ChEMBL bioactivity data.\n",
    "\n",
    "In **Part 4**, we will be building a regression model of acetylcholinesterase inhibitors using the random forest algorithm.\n",
    "\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "jw7MqTMphSwR"
   },
   "source": [
    "## **1. Import libraries**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "D3rFTNAIhSwS"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.ensemble import RandomForestRegressor"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "0GvT3PArhSwX"
   },
   "source": [
    "## **2. Load the data set**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 289
    },
    "colab_type": "code",
    "id": "043mRJZIhSwY",
    "outputId": "96bc783e-89f4-4013-dc58-376965a73425"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "--2020-07-01 12:24:14--  https://github.com/dataprofessor/data/raw/master/acetylcholinesterase_06_bioactivity_data_3class_pIC50_pubchem_fp.csv\n",
      "Resolving github.com (github.com)... 140.82.112.4\n",
      "Connecting to github.com (github.com)|140.82.112.4|:443... connected.\n",
      "HTTP request sent, awaiting response... 302 Found\n",
      "Location: https://raw.githubusercontent.com/dataprofessor/data/master/acetylcholinesterase_06_bioactivity_data_3class_pIC50_pubchem_fp.csv [following]\n",
      "--2020-07-01 12:24:15--  https://raw.githubusercontent.com/dataprofessor/data/master/acetylcholinesterase_06_bioactivity_data_3class_pIC50_pubchem_fp.csv\n",
      "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.0.133, 151.101.64.133, 151.101.128.133, ...\n",
      "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.0.133|:443... connected.\n",
      "HTTP request sent, awaiting response... 200 OK\n",
      "Length: 8363909 (8.0M) [text/plain]\n",
      "Saving to: ‘acetylcholinesterase_06_bioactivity_data_3class_pIC50_pubchem_fp.csv’\n",
      "\n",
      "acetylcholinesteras 100%[===================>]   7.98M  18.2MB/s    in 0.4s    \n",
      "\n",
      "2020-07-01 12:24:15 (18.2 MB/s) - ‘acetylcholinesterase_06_bioactivity_data_3class_pIC50_pubchem_fp.csv’ saved [8363909/8363909]\n",
      "\n"
     ]
    }
   ],
   "source": [
    "! wget https://github.com/dataprofessor/data/raw/master/acetylcholinesterase_06_bioactivity_data_3class_pIC50_pubchem_fp.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "cSgppzqPiR0G"
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('pubchem_fp_acetylcholinesterase_bioactivity_data_3class_pIC50.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "kuiiC0xthSwb"
   },
   "source": [
    "## **3. Input features**\n",
    "The ***Acetylcholinesterase*** data set contains 881 input features and 1 output variable (pIC50 values)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "iCeQQn0uhSwb"
   },
   "source": [
    "### **3.1. Input features**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 439
    },
    "colab_type": "code",
    "id": "li32nAPohSwc",
    "outputId": "e3cbf177-e82b-4e57-c32a-af9ab924dda8"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>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>6363</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>6364</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>6365</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>6366</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>6367</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>6368 rows × 881 columns</p>\n",
       "</div>"
      ],
      "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",
       "6363           1           1           1           0           0           0   \n",
       "6364           1           1           1           0           0           0   \n",
       "6365           1           1           1           0           0           0   \n",
       "6366           1           1           1           0           0           0   \n",
       "6367           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",
       "6363           0           0           0           1  ...             0   \n",
       "6364           0           0           0           1  ...             0   \n",
       "6365           0           0           0           1  ...             0   \n",
       "6366           0           0           0           1  ...             0   \n",
       "6367           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",
       "6363             0             0             0             0             0   \n",
       "6364             0             0             0             0             0   \n",
       "6365             0             0             0             0             0   \n",
       "6366             0             0             0             0             0   \n",
       "6367             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",
       "6363             0             0             0             0  \n",
       "6364             0             0             0             0  \n",
       "6365             0             0             0             0  \n",
       "6366             0             0             0             0  \n",
       "6367             0             0             0             0  \n",
       "\n",
       "[6368 rows x 881 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = df.drop('pIC50', axis=1)\n",
    "X"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "sGQjCQtfhSwg"
   },
   "source": [
    "### **3.2. Output features**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 221
    },
    "colab_type": "code",
    "id": "OWylAtAVhSwh",
    "outputId": "5747e12a-3abb-4e43-fc1c-c8dbe42f3992"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       6.124939\n",
       "1       7.000000\n",
       "2       4.301030\n",
       "3       6.522879\n",
       "4       6.096910\n",
       "          ...   \n",
       "6363    6.795880\n",
       "6364    5.100000\n",
       "6365    4.000000\n",
       "6366    4.200000\n",
       "6367    5.000000\n",
       "Name: pIC50, Length: 6368, dtype: float64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y = df.pIC50\n",
    "Y"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "E-zGSqXohSwx"
   },
   "source": [
    "### **3.3. Let's examine the data dimension**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "nhT04XtLhSwx",
    "outputId": "0e36315c-a8c1-4d11-8e99-8a92038ff80d"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(6368, 881)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "uzQlK8gNhSw0",
    "outputId": "6526f2b6-8875-49f4-bd38-dc2db7225e52"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(6368,)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "0qQCpX097qf_"
   },
   "source": [
    "### **3.4. Remove low variance features**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "rjHK2SoI7tXI"
   },
   "outputs": [],
   "source": [
    "from sklearn.feature_selection import VarianceThreshold\n",
    "selection = VarianceThreshold(threshold=(.8 * (1 - .8)))    \n",
    "X = selection.fit_transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "nXcpQh_s8nx7",
    "outputId": "cb3a135a-9b96-4f69-bb28-538ae4be7d5d"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(6368, 145)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "AjhOlkOVhSxR"
   },
   "source": [
    "## **4. Data split (80/20 ratio)**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "M1Bmg1HWhSxR"
   },
   "outputs": [],
   "source": [
    "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "uz1o3c1LhSxU",
    "outputId": "dc0b23f3-eebc-4159-ae71-6d9e27ce9e26"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((5094, 145), (5094,))"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape, Y_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "4tnwDASChSxW",
    "outputId": "15c12f57-053b-4e28-afe1-b403510fd6ea"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((1274, 145), (1274,))"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.shape, Y_test.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "PYsE-tIAhSw3"
   },
   "source": [
    "## **5. Building a Regression Model using Random Forest**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "YHM3DCD5wuNe",
    "outputId": "42a4752a-c4ea-414d-ac19-dff9c64cfbcb"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5642628835930328"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = RandomForestRegressor(n_estimators=100)\n",
    "model.fit(X_train, Y_train)\n",
    "r2 = model.score(X_test, Y_test)\n",
    "r2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "A4Rv5wdQ1M6H"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Y_pred</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6.338287</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.853259</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.508804</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.855787</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4.603909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1269</th>\n",
       "      <td>4.932514</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1270</th>\n",
       "      <td>6.694342</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1271</th>\n",
       "      <td>5.003534</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1272</th>\n",
       "      <td>7.159456</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1273</th>\n",
       "      <td>7.177065</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1274 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Y_pred\n",
       "0     6.338287\n",
       "1     4.853259\n",
       "2     5.508804\n",
       "3     5.855787\n",
       "4     4.603909\n",
       "...        ...\n",
       "1269  4.932514\n",
       "1270  6.694342\n",
       "1271  5.003534\n",
       "1272  7.159456\n",
       "1273  7.177065\n",
       "\n",
       "[1274 rows x 1 columns]"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_pred = model.predict(X_test)\n",
    "Y_pred1 = pd.DataFrame(Y_pred, columns=['Y_pred'])\n",
    "Y_pred1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1274"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(Y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "Y_test.to_csv('Y_test.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>pIC50</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6.744727</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.577903</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.552842</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4.380594</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1269</th>\n",
       "      <td>4.515700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1270</th>\n",
       "      <td>6.481486</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1271</th>\n",
       "      <td>4.898941</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1272</th>\n",
       "      <td>5.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1273</th>\n",
       "      <td>6.694649</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1274 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         pIC50\n",
       "0     6.744727\n",
       "1     4.577903\n",
       "2     5.000000\n",
       "3     5.552842\n",
       "4     4.380594\n",
       "...        ...\n",
       "1269  4.515700\n",
       "1270  6.481486\n",
       "1271  4.898941\n",
       "1272  5.000000\n",
       "1273  6.694649\n",
       "\n",
       "[1274 rows x 1 columns]"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_test = pd.read_csv('Y_test.csv')\n",
    "Y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1274"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(Y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>pIC50</th>\n",
       "      <th>Y_pred</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6.744727</td>\n",
       "      <td>6.338287</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.577903</td>\n",
       "      <td>4.853259</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.000000</td>\n",
       "      <td>5.508804</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5.552842</td>\n",
       "      <td>5.855787</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4.380594</td>\n",
       "      <td>4.603909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1269</th>\n",
       "      <td>4.515700</td>\n",
       "      <td>4.932514</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1270</th>\n",
       "      <td>6.481486</td>\n",
       "      <td>6.694342</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1271</th>\n",
       "      <td>4.898941</td>\n",
       "      <td>5.003534</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1272</th>\n",
       "      <td>5.000000</td>\n",
       "      <td>7.159456</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1273</th>\n",
       "      <td>6.694649</td>\n",
       "      <td>7.177065</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1274 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         pIC50    Y_pred\n",
       "0     6.744727  6.338287\n",
       "1     4.577903  4.853259\n",
       "2     5.000000  5.508804\n",
       "3     5.552842  5.855787\n",
       "4     4.380594  4.603909\n",
       "...        ...       ...\n",
       "1269  4.515700  4.932514\n",
       "1270  6.481486  6.694342\n",
       "1271  4.898941  5.003534\n",
       "1272  5.000000  7.159456\n",
       "1273  6.694649  7.177065\n",
       "\n",
       "[1274 rows x 2 columns]"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "table = pd.concat([Y_test, Y_pred1], axis=1)\n",
    "table"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "LoLgjePyUXcv"
   },
   "source": [
    "## **6. Scatter Plot of Experimental vs Predicted pIC50 Values**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 361
    },
    "colab_type": "code",
    "id": "hfqpfjxw3IAK",
    "outputId": "7206a3c7-eff9-4617-e9d9-d54dd0cfd29c"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "sns.set(color_codes=True)\n",
    "sns.set_style(\"white\")\n",
    "\n",
    "ax = sns.regplot(data=table, x='pIC50', y='Y_pred', scatter_kws={'alpha':0.4})\n",
    "ax.set_xlabel('Experimental pIC50', fontsize='large', fontweight='bold')\n",
    "ax.set_ylabel('Predicted pIC50', fontsize='large', fontweight='bold')\n",
    "ax.set_xlim(0, 12)\n",
    "ax.set_ylim(0, 12)\n",
    "ax.figure.set_size_inches(5, 5)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([4.71297258])"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "XF = X[2:3]\n",
    "Y_prediction = model.predict(XF)\n",
    "Y_prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "CDD-ML-Part-4-Acetylcholinesterase-Regression-Random-Forest.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}