DeepSigSurvNet is a not-fully connected deep learning model used for survival analysis and pathway analysis.
To run the code, you need first download TCGA dataset from below following link and process it into coresspoding format:
The model is implemented by Keras=2.2.4
. To analysis pathways, you need also install Innvestigate package
To train the model, open train.py
file and set apporiate parameters for data load path, save path, model parameters, etc. Then run the file.
To investigate pathway, open pathway_analysis.py
file and set apporiate parameters for model and data load path(save path when you train the model), model parameters, etc. Then run the file.
if you find it is helpful in your research, please cite:
https://www.biorxiv.org/content/10.1101/2020.04.13.039487v1.abstract Investigate the relevance of major signaling pathways in cancer survival using a biologically meaningful deep learning model