brca_tcga_pyg_dataset

This is a dataset that was gotten by integrating the breast cancer(tcga) dataset from the cBioportal and data that shows node connections from Pathway commons. They were preprocessed together to form one huge dataset that could be converted to Pytorch geometric data objects. This data is in the CSV format and can be downloaded, the processed to form a graph dataset comprising different graphs if it is to be used to train Graph Neural Networks(GNN). It could also be used as is for training Deep Neural Networks(DNN) for situations where you want to compare the performance of these two types of networks. The dataset contains the gene features of each patient in graph_idx and the overall survival time(in months) of each patient, which are the labels.