3_predict_on_new_data.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "3_predict_on_new_data.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-k976iTikGqm",
        "outputId": "6bb60418-6fc7-4486-c7c2-f0af309baff0"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cloning into 'gpHSP'...\n",
            "remote: Enumerating objects: 140, done.\u001b[K\n",
            "remote: Counting objects: 100% (102/102), done.\u001b[K\n",
            "remote: Compressing objects: 100% (72/72), done.\u001b[K\n",
            "remote: Total 140 (delta 60), reused 72 (delta 30), pack-reused 38\u001b[K\n",
            "Receiving objects: 100% (140/140), 32.98 MiB | 34.25 MiB/s, done.\n",
            "Resolving deltas: 100% (74/74), done.\n"
          ]
        }
      ],
      "source": [
        "! rm -rf gpHSP\n",
        "!git clone https://github.com/aspuru-guzik-group/gpHSP"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Assuming in a colab enviroment"
      ],
      "metadata": {
        "id": "p54WoW6RkOdK"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import sys\n",
        "if 'google.colab' in sys.modules:\n",
        "    print('In colab!')\n",
        "    sys.path.insert(0,'gpHSP')\n",
        "    !pip install rdkit-pypi mordred ml_collections ngboost gpflow"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qQyCA64AkN6w",
        "outputId": "26146883-97a0-4084-bb1f-d06e07da012c"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "In colab!\n",
            "Requirement already satisfied: rdkit-pypi in /usr/local/lib/python3.7/dist-packages (2021.9.5.1)\n",
            "Requirement already satisfied: mordred in /usr/local/lib/python3.7/dist-packages (1.2.0)\n",
            "Requirement already satisfied: ml_collections in /usr/local/lib/python3.7/dist-packages (0.1.1)\n",
            "Requirement already satisfied: ngboost in /usr/local/lib/python3.7/dist-packages (0.3.12)\n",
            "Requirement already satisfied: gpflow in /usr/local/lib/python3.7/dist-packages (2.4.0)\n",
            "Requirement already satisfied: numpy>=1.19 in /usr/local/lib/python3.7/dist-packages (from rdkit-pypi) (1.21.5)\n",
            "Requirement already satisfied: Pillow in /usr/local/lib/python3.7/dist-packages (from rdkit-pypi) (7.1.2)\n",
            "Requirement already satisfied: six==1.* in /usr/local/lib/python3.7/dist-packages (from mordred) (1.15.0)\n",
            "Requirement already satisfied: networkx==2.* in /usr/local/lib/python3.7/dist-packages (from mordred) (2.6.3)\n",
            "Requirement already satisfied: absl-py in /usr/local/lib/python3.7/dist-packages (from ml_collections) (1.0.0)\n",
            "Requirement already satisfied: contextlib2 in /usr/local/lib/python3.7/dist-packages (from ml_collections) (0.5.5)\n",
            "Requirement already satisfied: PyYAML in /usr/local/lib/python3.7/dist-packages (from ml_collections) (3.13)\n",
            "Requirement already satisfied: lifelines>=0.25 in /usr/local/lib/python3.7/dist-packages (from ngboost) (0.26.4)\n",
            "Requirement already satisfied: scipy>=1.3 in /usr/local/lib/python3.7/dist-packages (from ngboost) (1.4.1)\n",
            "Requirement already satisfied: scikit-learn>=0.21 in /usr/local/lib/python3.7/dist-packages (from ngboost) (1.0.2)\n",
            "Requirement already satisfied: tqdm>=4.3 in /usr/local/lib/python3.7/dist-packages (from ngboost) (4.63.0)\n",
            "Requirement already satisfied: pandas>=0.23.0 in /usr/local/lib/python3.7/dist-packages (from lifelines>=0.25->ngboost) (1.3.5)\n",
            "Requirement already satisfied: autograd-gamma>=0.3 in /usr/local/lib/python3.7/dist-packages (from lifelines>=0.25->ngboost) (0.5.0)\n",
            "Requirement already satisfied: formulaic<0.3,>=0.2.2 in /usr/local/lib/python3.7/dist-packages (from lifelines>=0.25->ngboost) (0.2.4)\n",
            "Requirement already satisfied: autograd>=1.3 in /usr/local/lib/python3.7/dist-packages (from lifelines>=0.25->ngboost) (1.3)\n",
            "Requirement already satisfied: matplotlib>=3.0 in /usr/local/lib/python3.7/dist-packages (from lifelines>=0.25->ngboost) (3.2.2)\n",
            "Requirement already satisfied: future>=0.15.2 in /usr/local/lib/python3.7/dist-packages (from autograd>=1.3->lifelines>=0.25->ngboost) (0.16.0)\n",
            "Requirement already satisfied: wrapt in /usr/local/lib/python3.7/dist-packages (from formulaic<0.3,>=0.2.2->lifelines>=0.25->ngboost) (1.13.3)\n",
            "Requirement already satisfied: interface-meta>=1.2 in /usr/local/lib/python3.7/dist-packages (from formulaic<0.3,>=0.2.2->lifelines>=0.25->ngboost) (1.2.4)\n",
            "Requirement already satisfied: astor in /usr/local/lib/python3.7/dist-packages (from formulaic<0.3,>=0.2.2->lifelines>=0.25->ngboost) (0.8.1)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0->lifelines>=0.25->ngboost) (1.3.2)\n",
            "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0->lifelines>=0.25->ngboost) (3.0.7)\n",
            "Requirement already satisfied: python-dateutil>=2.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0->lifelines>=0.25->ngboost) (2.8.2)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0->lifelines>=0.25->ngboost) (0.11.0)\n",
            "Requirement already satisfied: pytz>=2017.3 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.23.0->lifelines>=0.25->ngboost) (2018.9)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn>=0.21->ngboost) (3.1.0)\n",
            "Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages (from scikit-learn>=0.21->ngboost) (1.1.0)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.7/dist-packages (from gpflow) (3.10.0.2)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.7/dist-packages (from gpflow) (21.3)\n",
            "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.7/dist-packages (from gpflow) (57.4.0)\n",
            "Requirement already satisfied: multipledispatch>=0.6 in /usr/local/lib/python3.7/dist-packages (from gpflow) (0.6.0)\n",
            "Requirement already satisfied: tabulate in /usr/local/lib/python3.7/dist-packages (from gpflow) (0.8.9)\n",
            "Requirement already satisfied: deprecated in /usr/local/lib/python3.7/dist-packages (from gpflow) (1.2.13)\n",
            "Requirement already satisfied: lark>=1.1.0 in /usr/local/lib/python3.7/dist-packages (from gpflow) (1.1.2)\n",
            "Requirement already satisfied: tensorflow>=2.2.0 in /usr/local/lib/python3.7/dist-packages (from gpflow) (2.8.0)\n",
            "Requirement already satisfied: tensorflow-probability>0.10.0 in /usr/local/lib/python3.7/dist-packages (from gpflow) (0.16.0)\n",
            "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (3.3.0)\n",
            "Requirement already satisfied: tf-estimator-nightly==2.8.0.dev2021122109 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (2.8.0.dev2021122109)\n",
            "Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (0.2.0)\n",
            "Requirement already satisfied: flatbuffers>=1.12 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (2.0)\n",
            "Requirement already satisfied: keras-preprocessing>=1.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (1.1.2)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (1.44.0)\n",
            "Requirement already satisfied: protobuf>=3.9.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (3.17.3)\n",
            "Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (3.1.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (1.1.0)\n",
            "Requirement already satisfied: keras<2.9,>=2.8.0rc0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (2.8.0)\n",
            "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (0.24.0)\n",
            "Requirement already satisfied: gast>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (0.5.3)\n",
            "Requirement already satisfied: libclang>=9.0.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (13.0.0)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (1.6.3)\n",
            "Requirement already satisfied: tensorboard<2.9,>=2.8 in /usr/local/lib/python3.7/dist-packages (from tensorflow>=2.2.0->gpflow) (2.8.0)\n",
            "Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.7/dist-packages (from astunparse>=1.6.0->tensorflow>=2.2.0->gpflow) (0.37.1)\n",
            "Requirement already satisfied: cached-property in /usr/local/lib/python3.7/dist-packages (from h5py>=2.9.0->tensorflow>=2.2.0->gpflow) (1.5.2)\n",
            "Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (0.6.1)\n",
            "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (1.8.1)\n",
            "Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (1.0.1)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (3.3.6)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (1.35.0)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (2.23.0)\n",
            "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (0.4.6)\n",
            "Requirement already satisfied: cachetools<5.0,>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (4.2.4)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (0.2.8)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (4.8)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.7/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (1.3.1)\n",
            "Requirement already satisfied: importlib-metadata>=4.4 in /usr/local/lib/python3.7/dist-packages (from markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (4.11.2)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (3.7.0)\n",
            "Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /usr/local/lib/python3.7/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (0.4.8)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (3.0.4)\n",
            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (1.24.3)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (2.10)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (2021.10.8)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.7/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.9,>=2.8->tensorflow>=2.2.0->gpflow) (3.2.0)\n",
            "Requirement already satisfied: dm-tree in /usr/local/lib/python3.7/dist-packages (from tensorflow-probability>0.10.0->gpflow) (0.1.6)\n",
            "Requirement already satisfied: cloudpickle>=1.3 in /usr/local/lib/python3.7/dist-packages (from tensorflow-probability>0.10.0->gpflow) (1.3.0)\n",
            "Requirement already satisfied: decorator in /usr/local/lib/python3.7/dist-packages (from tensorflow-probability>0.10.0->gpflow) (4.4.2)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "from tqdm.auto import tqdm\n",
        "import scipy.stats as stats\n",
        "\n",
        "import ngboost\n",
        "import tensorflow as tf\n",
        "import gpflow as gpf\n",
        "import gphsp\n",
        "\n",
        "gphsp.notebook_context()\n",
        "gphsp.print_modules([ngboost, tf , gpf])"
      ],
      "metadata": {
        "id": "IO5wJqsskd1t",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "e9f7d289-eb89-4c75-e49a-83838af3381a"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "ngboost    = 0.3.12\n",
            "tensorflow = 2.8.0\n",
            "gpflow     = 2.4.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Utilities"
      ],
      "metadata": {
        "id": "HVDbXSZAliP3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "at_data_dir = lambda x: os.path.join('gpHSP/data', x)\n",
        "at_model_dir = lambda x: os.path.join('gpHSP/models', x)"
      ],
      "metadata": {
        "id": "wseewPpTCGHD"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Load data and get all smiles"
      ],
      "metadata": {
        "id": "_wvvTIsMldgt"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv('LMU_Molecules.csv')\n",
        "df['smiles'] = df['smiles'].apply(gphsp.get_isomeric_smiles)\n",
        "gphsp.peek_df(df)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 115
        },
        "id": "izpVJD2Ws1g_",
        "outputId": "dfa285f0-e69c-47c8-d7b9-abc67815aef8"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Index(['names', 'smiles'], dtype='object')\n",
            "(8, 2)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-8eab88dc-30ec-46d2-8da6-be90f366d0b9\">\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>names</th>\n",
              "      <th>smiles</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>PCBM</td>\n",
              "      <td>COC(=O)CCC[C@]1(c2ccccc2)[C@]23c4c5c6c7c8c9c5c...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-8eab88dc-30ec-46d2-8da6-be90f366d0b9')\"\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-8eab88dc-30ec-46d2-8da6-be90f366d0b9 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-8eab88dc-30ec-46d2-8da6-be90f366d0b9');\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",
              "  "
            ],
            "text/plain": [
              "  names                                             smiles\n",
              "0  PCBM  COC(=O)CCC[C@]1(c2ccccc2)[C@]23c4c5c6c7c8c9c5c..."
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Create proxy dataset"
      ],
      "metadata": {
        "id": "3voognqj-Zlk"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.DataFrame()\n",
        "df['names'] =['PTB7_Th']\n",
        "df['smiles'] = ['C(C)CC[C@H](Cc1sc(c2c3c(sc(c4sc(C)c5sc(c(c45)F)C(=O)OC[C@@H](CCCC)CC)c3)c(c3ccc(C[C@@H](CCCC)CC)s3)c3cc(sc23)C)cc1)CC']\n",
        "df['smiles'] = df['smiles'].apply(gphsp.get_isomeric_smiles)\n",
        "gphsp.peek_df(df)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 115
        },
        "id": "-whLt_rv-OF1",
        "outputId": "3a7bc3b3-00ac-4604-f900-9f0b2935fc3b"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Index(['names', 'smiles'], dtype='object')\n",
            "(1, 2)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-0df7075d-7df2-40e2-b7f5-ae6439ecf3e6\">\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>names</th>\n",
              "      <th>smiles</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>PTB7_Th</td>\n",
              "      <td>CCCC[C@@H](CC)COC(=O)c1sc2c(C)sc(-c3cc4c(-c5cc...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0df7075d-7df2-40e2-b7f5-ae6439ecf3e6')\"\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-0df7075d-7df2-40e2-b7f5-ae6439ecf3e6 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-0df7075d-7df2-40e2-b7f5-ae6439ecf3e6');\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",
              "  "
            ],
            "text/plain": [
              "     names                                             smiles\n",
              "0  PTB7_Th  CCCC[C@@H](CC)COC(=O)c1sc2c(C)sc(-c3cc4c(-c5cc..."
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Load features"
      ],
      "metadata": {
        "id": "w1s-j6DgtpgV"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "features = gphsp.SmilesMap(at_data_dir('mordred_features.npz'))"
      ],
      "metadata": {
        "id": "jq0x70z9l-_G"
      },
      "execution_count": 27,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "smi  = df['smiles'].to_numpy(str)\n",
        "needs_update = np.array([not s in features.index for s in smi])\n",
        "print(f'Found {needs_update.sum()} smiles not found in SmilesMap')\n",
        "if needs_update.sum():\n",
        "    new_smi = smi[needs_update]\n",
        "    new_values = gphsp.calculate_mordred(new_smi)\n",
        "    features.update(new_smi, new_values)\n",
        "    values = features(smi)\n",
        "    assert np.isnan(values).sum()==0, 'Found nan, recalcualte mask and model (colab 0 & 2)'"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "X-lA8Yw77AfI",
        "outputId": "e5a0755d-a9ea-43d3-cd95-da19672d0b4c"
      },
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 1 smiles not found in SmilesMap\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 1/1 [00:05<00:00,  5.88s/it]\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/numpy/core/fromnumeric.py:86: RuntimeWarning: overflow encountered in reduce\n",
            "  return ufunc.reduce(obj, axis, dtype, out, **passkwargs)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Train gpHSP model on polymers"
      ],
      "metadata": {
        "id": "vgARDFB55pUB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "model_suffix = 'HSP_ngboost_mol.pkl'\n",
        "names = gphsp.Y_COLS\n",
        "models = {name: gphsp.load_model(at_model_dir(f\"{name}_{model_suffix}\")) for name in names}\n",
        "model_suffix = 'ngboost_polymer.pkl'\n",
        "poly_models = {name: gphsp.load_model(at_model_dir(f\"{name}_{model_suffix}\")) for name in names}"
      ],
      "metadata": {
        "id": "pxa6v3QwjsgE"
      },
      "execution_count": 29,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "smi = df['smiles'].to_numpy(str)\n",
        "mol_x = features(smi)\n",
        "poly_x = gphsp.predictions_as_features(mol_x, models)"
      ],
      "metadata": {
        "id": "NtitMoEWkZiL"
      },
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "for name, model in models.items():\n",
        "    df[f'{name}_mol'] = model.pred_dist(mol_x).mean()\n",
        "for name, model in poly_models.items():\n",
        "    df[f'{name}_poly'] = model.pred_dist(poly_x).mean()\n",
        "df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 125
        },
        "id": "ghPthqErmHJl",
        "outputId": "bf2299eb-0ea0-480c-8dff-7efbf3f4e4e6"
      },
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-7d36962f-66fa-4a54-acc0-13a6171f8e49\">\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>names</th>\n",
              "      <th>smiles</th>\n",
              "      <th>δd_mol</th>\n",
              "      <th>δp_mol</th>\n",
              "      <th>δh_mol</th>\n",
              "      <th>δd_poly</th>\n",
              "      <th>δp_poly</th>\n",
              "      <th>δh_poly</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>PTB7_Th</td>\n",
              "      <td>CCCC[C@@H](CC)COC(=O)c1sc2c(C)sc(-c3cc4c(-c5cc...</td>\n",
              "      <td>21.528</td>\n",
              "      <td>6.067</td>\n",
              "      <td>5.677</td>\n",
              "      <td>18.635</td>\n",
              "      <td>2.367</td>\n",
              "      <td>3.719</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7d36962f-66fa-4a54-acc0-13a6171f8e49')\"\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-7d36962f-66fa-4a54-acc0-13a6171f8e49 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-7d36962f-66fa-4a54-acc0-13a6171f8e49');\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",
              "  "
            ],
            "text/plain": [
              "     names                                             smiles  δd_mol  δp_mol  \\\n",
              "0  PTB7_Th  CCCC[C@@H](CC)COC(=O)c1sc2c(C)sc(-c3cc4c(-c5cc...  21.528   6.067   \n",
              "\n",
              "   δh_mol  δd_poly  δp_poly  δh_poly  \n",
              "0   5.677   18.635    2.367    3.719  "
            ]
          },
          "metadata": {},
          "execution_count": 31
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.to_csv('hsp_calculations.csv', index=False)"
      ],
      "metadata": {
        "id": "bMPi5GSOm3kS"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}