Interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma
- Pathway image: Grid structure conversion for biological array data (a non-grid structured format) for CNNs.
- Interpretation of the CNN model using GradCAM.
Source code: https://github.com/mskspi/PathCNN
Jung Hun Oh, Wookjin Choi, Euiseong Ko, Mingon Kang, Allen Tannenbaum, Joseph O Deasy, PathCNN: interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma, Bioinformatics, Volume 37, Issue Supplement_1, July 2021, Pages i443–i450, https://doi.org/10.1093/bioinformatics/btab285
- Model Building
- PathCNN_GradCAM_modeling.py: to generate a model for GradCAM (PathCNN_model.h5)
- PathCNN_GradCAM.py: to generate GradCAM images and a resultant file (pathcnn_gradcam.csv)
- Multi-omics data
- GBM multi-omics data including mRNA expression, CNV, and DNA methylation were downloaded from the CBioPortal database.
- Pathway information was downloaded from the KEGG database.
- PCA was performed for each pathway in individual omics types.
- PCA_EXP.xlsx, PCA_CNV.xlsx, PCA_MT.xlsx