Add BreastInvasiveCarcinoma dataset

CHANGELOG.md

@@ -7,6 +7,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 ### Added
 
+- Added the `BrcaTcga` dataset ([#7905](https://github.com/pyg-team/pytorch_geometric/pull/7905))
 - Added the `MyketDataset` ([#7959](https://github.com/pyg-team/pytorch_geometric/pull/7959))
 - Added a multi-GPU `ogbn-papers100M` example ([#7921](https://github.com/pyg-team/pytorch_geometric/pull/7921))
 - Added `group_argsort` implementation ([#7948](https://github.com/pyg-team/pytorch_geometric/pull/7948))

torch_geometric/datasets/__init__.py

@@ -73,6 +73,7 @@
 from .jodie import JODIEDataset
 from .wikidata import Wikidata5M
 from .myket import MyketDataset
+from .brca_tgca import BrcaTcga
 
 from .dbp15k import DBP15K
 from .aminer import AMiner
@@ -178,6 +179,7 @@
     'JODIEDataset',
     'Wikidata5M',
     'MyketDataset',
+    'BrcaTcga',
 ]
 
 hetero_datasets = [

torch_geometric/datasets/brca_tgca.py

@@ -0,0 +1,104 @@
+import os
+import os.path as osp
+import shutil
+from typing import Callable, List, Optional
+
+import numpy as np
+import torch
+
+from torch_geometric.data import (
+    Data,
+    InMemoryDataset,
+    download_url,
+    extract_zip,
+)
+
+
+class BrcaTcga(InMemoryDataset):
+    r"""The breast cancer (BRCA TCGA) dataset from the `cBioPortal
+    <https://www.cbioportal.org>`_ and the biological network for node
+    connections from `Pathway Commons <https://www.pathwaycommons.org>`_.
+    The dataset contains the gene features of 1,082 patients, and the overall
+    survival time (in months) of each patient as label.
+
+    Pre-processing and example model codes on how to use this dataset can be
+    found `here <https://github.com/cannin/pyg_pathway_commons_cbioportal>`_.
+
+    Args:
+        root (str): Root directory where the dataset should be saved.
+        transform (callable, optional): A function/transform that takes in an
+            :obj:`torch_geometric.data.Data` object and returns a transformed
+            version. The data object will be transformed before every access.
+            (default: :obj:`None`)
+        pre_transform (callable, optional): A function/transform that takes in
+            an :obj:`torch_geometric.data.Data` object and returns a
+            transformed version. The data object will be transformed before
+            being saved to disk. (default: :obj:`None`)
+        pre_filter (callable, optional): A function that takes in an
+            :obj:`torch_geometric.data.Data` object and returns a boolean
+            value, indicating whether the data object should be included in the
+            final dataset. (default: :obj:`None`)
+
+    **STATS:**
+
+    .. list-table::
+        :widths: 10 10 10 10
+        :header-rows: 1
+
+        * - #graphs
+          - #nodes
+          - #edges
+          - #features
+        * - 1,082
+          - 9,288
+          - 271,771
+          - 1,082
+    """
+    url = 'https://zenodo.org/record/8251328/files/brca_tcga.zip?download=1'
+
+    def __init__(
+        self,
+        root: str,
+        transform: Optional[Callable] = None,
+        pre_transform: Optional[Callable] = None,
+        pre_filter: Optional[Callable] = None,
+    ):
+        super().__init__(root, transform, pre_transform, pre_filter)
+        self.load(self.processed_paths[0])
+
+    @property
+    def raw_file_names(self) -> List[str]:
+        return ['graph_idx.csv', 'graph_labels.csv', 'edge_index.pt']
+
+    @property
+    def processed_file_names(self) -> str:
+        return 'data.pt'
+
+    def download(self):
+        path = download_url(self.url, self.root)
+        extract_zip(path, self.root)
+        os.unlink(path)
+        shutil.rmtree(self.raw_dir)
+        os.rename(osp.join(self.root, 'brca_tcga'), self.raw_dir)
+
+    def process(self):
+        import pandas as pd
+
+        graph_feat = pd.read_csv(self.raw_paths[0], index_col=0).values
+        graph_feat = torch.from_numpy(graph_feat).to(torch.float)
+        graph_label = np.loadtxt(self.raw_paths[1], delimiter=',')
+        graph_label = torch.from_numpy(graph_label).to(torch.float)
+        edge_index = torch.load(self.raw_paths[2])
+
+        data_list = []
+        for x, y in zip(graph_feat, graph_label):
+            data = Data(x=x, edge_index=edge_index, y=y)
+
+            if self.pre_filter is not None and not self.pre_filter(data):
+                continue
+            if self.pre_transform is not None:
+                data = self.pre_transform(data)
+
+            data_list.append(data)
+
+        self.save(data_list, self.processed_paths[0])