Pancancer survival prediction using a deep learning architecture with multimodal representation and integration

The clinical data, gene expression (mRNA) data, and microRNA expression (miRNA) data were downloaded from the PanCanAtlas TCGA project (https://gdc.cancer.gov/about-data/publications/pancanatlas). The gene copy number variation (CNV) data was downloaded from UCSC Xena (http://xena.ucsc.edu/public/).

Files prefixed with 'Pre' represent the preprocessed datasets. The preprocessing details can be found in 'Datasets and data preprocessing' subsection.