02_HIV_Dataset_GNN_Featurization.ipynb

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"mount_file_id":"16SwHfblfESQBMHBdCKBWQjm0VZCxveBj","authorship_tag":"ABX9TyMjztLwlPYjHn7Xc0+dStd2"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"gpuClass":"standard"},"cells":[{"cell_type":"markdown","source":["# Graph Neural Networks for Drug Discovery\n","\n","This project is inspired by DeepFindr GNN project: <br>\n","https://www.youtube.com/@DeepFindr/videos <br>\n","https://github.com/deepfindr/gnn-project"],"metadata":{"id":"4APNttty_oaI"}},{"cell_type":"markdown","source":["### Libraries' installation "],"metadata":{"id":"Od2ssGSTtdGf"}},{"cell_type":"code","source":["!python --version"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"K01msh5Stk2c","executionInfo":{"status":"ok","timestamp":1679399126968,"user_tz":-60,"elapsed":216,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}},"outputId":"4fb85378-6e13-4701-9570-115e786bface"},"execution_count":1,"outputs":[{"output_type":"stream","name":"stdout","text":["Python 3.9.16\n"]}]},{"cell_type":"code","source":["import os\n","import torch\n","os.environ['TORCH'] = torch.__version__\n","\n","!pip install -q torch-scatter -f https://data.pyg.org/whl/torch-${TORCH}.html\n","!pip install -q torch-sparse -f https://data.pyg.org/whl/torch-${TORCH}.html\n","!pip install -q git+https://github.com/pyg-team/pytorch_geometric.git"],"metadata":{"id":"NKubWmSQtlgg","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1679399166771,"user_tz":-60,"elapsed":39421,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}},"outputId":"45b7e6dd-d3c2-48ec-f883-0881bd99e909"},"execution_count":2,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.4/9.4 MB\u001b[0m \u001b[31m22.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.5/4.5 MB\u001b[0m \u001b[31m67.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n","  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n","  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n","  Building wheel for torch-geometric (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n"]}]},{"cell_type":"code","source":["!pip install rdkit"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Lkk4eBAqtoJh","executionInfo":{"status":"ok","timestamp":1679399179216,"user_tz":-60,"elapsed":12452,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}},"outputId":"558524cf-4949-4927-a8f4-2d179409e82e"},"execution_count":3,"outputs":[{"output_type":"stream","name":"stdout","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Collecting rdkit\n","  Downloading rdkit-2022.9.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (29.4 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m29.4/29.4 MB\u001b[0m \u001b[31m38.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: numpy in /usr/local/lib/python3.9/dist-packages (from rdkit) (1.22.4)\n","Requirement already satisfied: Pillow in /usr/local/lib/python3.9/dist-packages (from rdkit) (8.4.0)\n","Installing collected packages: rdkit\n","Successfully installed rdkit-2022.9.5\n"]}]},{"cell_type":"code","source":["!pip install deepchem==2.6.1"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Kgfr7ShkNBHZ","executionInfo":{"status":"ok","timestamp":1679399199651,"user_tz":-60,"elapsed":20446,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}},"outputId":"efb92870-7cd8-4ed2-a378-0fa623effe56"},"execution_count":4,"outputs":[{"output_type":"stream","name":"stdout","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Collecting deepchem==2.6.1\n","  Downloading deepchem-2.6.1-py3-none-any.whl (608 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m608.3/608.3 KB\u001b[0m \u001b[31m21.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: joblib in /usr/local/lib/python3.9/dist-packages (from deepchem==2.6.1) (1.1.1)\n","Collecting rdkit-pypi\n","  Downloading rdkit_pypi-2022.9.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (29.4 MB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m29.4/29.4 MB\u001b[0m \u001b[31m18.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: numpy>=1.21 in /usr/local/lib/python3.9/dist-packages (from deepchem==2.6.1) (1.22.4)\n","Requirement already satisfied: scikit-learn in /usr/local/lib/python3.9/dist-packages (from deepchem==2.6.1) (1.2.2)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.9/dist-packages (from deepchem==2.6.1) (1.4.4)\n","Requirement already satisfied: scipy in /usr/local/lib/python3.9/dist-packages (from deepchem==2.6.1) (1.10.1)\n","Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.9/dist-packages (from pandas->deepchem==2.6.1) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.9/dist-packages (from pandas->deepchem==2.6.1) (2022.7.1)\n","Requirement already satisfied: Pillow in /usr/local/lib/python3.9/dist-packages (from rdkit-pypi->deepchem==2.6.1) (8.4.0)\n","Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.9/dist-packages (from scikit-learn->deepchem==2.6.1) (3.1.0)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.9/dist-packages (from python-dateutil>=2.8.1->pandas->deepchem==2.6.1) (1.15.0)\n","Installing collected packages: rdkit-pypi, deepchem\n","Successfully installed deepchem-2.6.1 rdkit-pypi-2022.9.5\n"]}]},{"cell_type":"markdown","source":["### Imports"],"metadata":{"id":"cF0CNy3StzX-"}},{"cell_type":"code","source":["import os\n","import torch\n","import torch_geometric\n","from torch_geometric.datasets import MoleculeNet\n","from torch_geometric.data import Dataset\n","\n","import rdkit\n","from rdkit import Chem\n","from rdkit.Chem import Draw\n","from rdkit.Chem.Draw import IPythonConsole\n","\n","import deepchem as dc\n","\n","import numpy as np\n","import pandas as pd\n","import matplotlib.pyplot as plt\n","from matplotlib.ticker import MaxNLocator\n","from tqdm import tqdm "],"metadata":{"id":"4BN8MRuPtyQ-","executionInfo":{"status":"ok","timestamp":1679399209679,"user_tz":-60,"elapsed":10042,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}}},"execution_count":5,"outputs":[]},{"cell_type":"code","source":["print(f\"Torch version: {torch.__version__}\")\n","print(f\"Cuda available: {torch.cuda.is_available()}\")\n","print(f\"Torch geometric version: {torch_geometric.__version__}\")\n","print(f\"RDKit version: {rdkit.__version__}\")\n","print(f\"DeepChem version: {dc.__version__}\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Zp7VYviiIsuA","executionInfo":{"status":"ok","timestamp":1679399209682,"user_tz":-60,"elapsed":23,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}},"outputId":"34403eb8-97f7-411e-be66-5dbb73da835d"},"execution_count":6,"outputs":[{"output_type":"stream","name":"stdout","text":["Torch version: 1.13.1+cu116\n","Cuda available: False\n","Torch geometric version: 2.3.0\n","RDKit version: 2022.09.5\n","DeepChem version: 2.6.1\n"]}]},{"cell_type":"markdown","source":["### Parameters Setting"],"metadata":{"id":"sRW5LuQW9WcD"}},{"cell_type":"code","source":["dataset_path = '/content/drive/MyDrive/COLAB_NOTEBOOKS/Graph_Neural_Network_Drug_Discovery_HIV_Dataset'\n","molecule_data_path = os.path.join(dataset_path, 'hiv/')\n","dataset_df_path = os.path.join(dataset_path, 'hiv/raw/HIV.csv')"],"metadata":{"id":"5ptUy8829qaX","executionInfo":{"status":"ok","timestamp":1679399209683,"user_tz":-60,"elapsed":18,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}}},"execution_count":7,"outputs":[]},{"cell_type":"markdown","source":["### Featurization of molecules"],"metadata":{"id":"EbsjCwWr1XXb"}},{"cell_type":"code","execution_count":8,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":206},"id":"wvldTpbjpbe5","executionInfo":{"status":"ok","timestamp":1679399210229,"user_tz":-60,"elapsed":560,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}},"outputId":"5c9d66b2-ad0a-4527-a717-9aab08dc6618"},"outputs":[{"output_type":"display_data","data":{"text/plain":["                                              smiles activity  HIV_active\n","0  CCC1=[O+][Cu-3]2([O+]=C(CC)C1)[O+]=C(CC)CC(CC)...       CI           0\n","1  C(=Cc1ccccc1)C1=[O+][Cu-3]2([O+]=C(C=Cc3ccccc3...       CI           0\n","2                   CC(=O)N1c2ccccc2Sc2c1ccc1ccccc21       CI           0\n","3    Nc1ccc(C=Cc2ccc(N)cc2S(=O)(=O)O)c(S(=O)(=O)O)c1       CI           0\n","4                             O=S(=O)(O)CCS(=O)(=O)O       CI           0"],"text/html":["\n","  <div id=\"df-67ce88b1-2067-458f-be9a-4366991672e6\">\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>smiles</th>\n","      <th>activity</th>\n","      <th>HIV_active</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>CCC1=[O+][Cu-3]2([O+]=C(CC)C1)[O+]=C(CC)CC(CC)...</td>\n","      <td>CI</td>\n","      <td>0</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>C(=Cc1ccccc1)C1=[O+][Cu-3]2([O+]=C(C=Cc3ccccc3...</td>\n","      <td>CI</td>\n","      <td>0</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>CC(=O)N1c2ccccc2Sc2c1ccc1ccccc21</td>\n","      <td>CI</td>\n","      <td>0</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>Nc1ccc(C=Cc2ccc(N)cc2S(=O)(=O)O)c(S(=O)(=O)O)c1</td>\n","      <td>CI</td>\n","      <td>0</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>O=S(=O)(O)CCS(=O)(=O)O</td>\n","      <td>CI</td>\n","      <td>0</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-67ce88b1-2067-458f-be9a-4366991672e6')\"\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-67ce88b1-2067-458f-be9a-4366991672e6 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-67ce88b1-2067-458f-be9a-4366991672e6');\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":{}}],"source":["# HIV CSV file\n","dataset_df = pd.read_csv(dataset_df_path)\n","display(dataset_df.head())"]},{"cell_type":"code","source":["# from https://github.com/deepfindr/gnn-project/blob/main/dataset_featurizer.py\n","\n","class MoleculeDataset(Dataset):\n","    def __init__(self, root, filename, test=False, transform=None, pre_transform=None):\n","        \"\"\"\n","        root = Where the dataset should be stored. This folder is split\n","        into raw_dir (downloaded dataset) and processed_dir (processed data). \n","        \"\"\"\n","        self.test = test\n","        self.filename = filename\n","        super(MoleculeDataset, self).__init__(root, transform, pre_transform)\n","        \n","    @property\n","    def raw_file_names(self):\n","        \"\"\" If this file exists in raw_dir, the download is not triggered.\n","            (The download func. is not implemented here)  \n","        \"\"\"\n","        return self.filename\n","\n","    @property\n","    def processed_file_names(self):\n","        \"\"\" If these files are found in raw_dir, processing is skipped\"\"\"\n","        self.data = pd.read_csv(self.raw_paths[0]).reset_index()\n","\n","        if self.test:\n","            return [f'data_test_{i}.pt' for i in list(self.data.index)]\n","        else:\n","            return [f'data_{i}.pt' for i in list(self.data.index)]\n","        \n","\n","    def download(self):\n","        pass\n","\n","    def process(self):\n","        self.data = pd.read_csv(self.raw_paths[0]).reset_index()\n","        featurizer = dc.feat.MolGraphConvFeaturizer(use_edges=True)\n","        for index, row in tqdm(self.data.iterrows(), total=self.data.shape[0]):\n","            # Featurize molecule\n","            mol = Chem.MolFromSmiles(row[\"smiles\"])\n","            f = featurizer._featurize(mol)\n","            data = f.to_pyg_graph()\n","            data.y = self._get_label(row[\"HIV_active\"])\n","            data.smiles = row[\"smiles\"]\n","            if self.test:\n","                torch.save(data, \n","                    os.path.join(self.processed_dir, \n","                                 f'data_test_{index}.pt'))\n","            else:\n","                torch.save(data, \n","                    os.path.join(self.processed_dir, \n","                                 f'data_{index}.pt'))\n","            \n","\n","    def _get_label(self, label):\n","        label = np.asarray([label])\n","        return torch.tensor(label, dtype=torch.int64)\n","\n","    def len(self):\n","        return self.data.shape[0]\n","\n","    def get(self, idx):\n","        \"\"\" - Equivalent to __getitem__ in pytorch\n","            - Is not needed for PyG's InMemoryDataset\n","        \"\"\"\n","        if self.test:\n","            data = torch.load(os.path.join(self.processed_dir, \n","                                 f'data_test_{idx}.pt'))\n","        else:\n","            data = torch.load(os.path.join(self.processed_dir, \n","                                 f'data_{idx}.pt'))        \n","        return data\n"],"metadata":{"id":"SIQO2HxQ75y1","executionInfo":{"status":"ok","timestamp":1679399210230,"user_tz":-60,"elapsed":7,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}}},"execution_count":9,"outputs":[]},{"cell_type":"code","source":["dataset = MoleculeDataset(root=molecule_data_path, filename='HIV.csv')"],"metadata":{"id":"F4kmGzsV752d","executionInfo":{"status":"ok","timestamp":1679399485211,"user_tz":-60,"elapsed":274986,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}}},"execution_count":10,"outputs":[]},{"cell_type":"code","source":["example_molecule = Chem.MolFromSmiles(dataset_df.loc[0, \"smiles\"])\n","example_molecule"],"metadata":{"id":"v8B1NLKFJWzi","colab":{"base_uri":"https://localhost:8080/","height":167},"executionInfo":{"status":"ok","timestamp":1679399485215,"user_tz":-60,"elapsed":29,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}},"outputId":"12df4311-e40e-4410-e8e2-9e4928a492a9"},"execution_count":11,"outputs":[{"output_type":"execute_result","data":{"text/plain":["<rdkit.Chem.rdchem.Mol at 0x7f58eb0dc0b0>"],"image/png":"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\n"},"metadata":{},"execution_count":11}]},{"cell_type":"code","source":["print(type(dataset[0]))\n","print('Example molecule: Edge index (graph connections)')\n","print(dataset[0].edge_index.t())\n","print('Example molecule: Node embeddings')\n","print(dataset[0].x)\n","print('Example molecule: Edge attributes')\n","print(dataset[0].edge_attr)\n","print('Example molecule: HIV attributes')\n","print(dataset[0].y)"],"metadata":{"id":"HjEPzE0q756E","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1679399485215,"user_tz":-60,"elapsed":24,"user":{"displayName":"Sylwia Nowakowska","userId":"00746351251013148788"}},"outputId":"5c11b6ec-451c-4831-f1b7-7f55af2ddd5a"},"execution_count":12,"outputs":[{"output_type":"stream","name":"stdout","text":["<class 'torch_geometric.data.data.Data'>\n","Example molecule: Edge index (graph connections)\n","tensor([[ 0,  1],\n","        [ 1,  0],\n","        [ 1,  2],\n","        [ 2,  1],\n","        [ 2,  3],\n","        [ 3,  2],\n","        [ 3,  4],\n","        [ 4,  3],\n","        [ 4,  5],\n","        [ 5,  4],\n","        [ 5,  6],\n","        [ 6,  5],\n","        [ 6,  7],\n","        [ 7,  6],\n","        [ 7,  8],\n","        [ 8,  7],\n","        [ 6,  9],\n","        [ 9,  6],\n","        [ 4, 10],\n","        [10,  4],\n","        [10, 11],\n","        [11, 10],\n","        [11, 12],\n","        [12, 11],\n","        [12, 13],\n","        [13, 12],\n","        [11, 14],\n","        [14, 11],\n","        [14, 15],\n","        [15, 14],\n","        [15, 16],\n","        [16, 15],\n","        [16, 17],\n","        [17, 16],\n","        [15, 18],\n","        [18, 15],\n","        [ 9,  2],\n","        [ 2,  9],\n","        [18,  4],\n","        [ 4, 18]])\n","Example molecule: Node embeddings\n","tensor([[ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.,  0.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,\n","          0.,  0.],\n","        [ 0.,  0.,  1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  1.,  0.,\n","          0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,\n","          0.,  0.],\n","        [ 0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1., -3.,  0.,  0.,  0.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  1.,  0.,  0.,  0.,\n","          0.,  0.],\n","        [ 0.,  0.,  1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  1.,  0.,\n","          0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.,  0.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.,  0.,\n","          0.,  0.],\n","        [ 0.,  0.,  1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  1.,  0.,\n","          0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.,  0.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.,  0.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.,  0.,\n","          0.,  0.],\n","        [ 1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  0.,  1.,\n","          0.,  0.],\n","        [ 0.,  0.,  1.,  0.,  0.,  0.,  0.,  0.,  0.,  0.,  1.,  0.,  1.,  0.,\n","          0.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,  0.,  1.,  0.,  0.,  0.,\n","          0.,  0.]])\n","Example molecule: Edge attributes\n","tensor([[1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [0., 1., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [0., 1., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [0., 1., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [0., 1., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [0., 1., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [0., 1., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n","        [0., 1., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [0., 1., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.],\n","        [1., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.]])\n","Example molecule: HIV attributes\n","tensor([0])\n"]}]}]}