WeixianHuang / MiNet

Gene- and Pathway-based Framework for Multi-omics Data Intergration

MiNet

MiNet is a gene- and pathway-based deep neural netowrk for multi-omics data intergration to predict cancer survival outcomes.

Get Started

Example Datasets

To get started, you need to download example datasets from URLs as below:

Train data

Validation data

Test data

Gene Sparse Mask

Pathway Sparse Mask

Training, Validation and Evaluation of MiNet

Run.py: to train the model with the inputs from train.csv. Hyperparmeters are optimized by grid search automatically with validation.csv. C-index is used to evaluate the model performance with test.csv.