Skip to content
A biologically interpretable integrative deep learning model that integrates PAthological images and GEnomic data
Python Jupyter Notebook
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Aggregation Rename Aggeragation1.py to Aggergation.py Aug 13, 2019
Integration Add files via upload Aug 14, 2019
Pretrain Rename pretrain/match_sample_survival_info.csv to Pretrain/match_samp… Aug 14, 2019
README.md Update README.md Aug 14, 2019

README.md

PAGE-Net

A biologically interpretable integrative deep learning model that integrates PAthological images and GEnomic data

PAGE-Net has three phrases:

  • Patch-wise pre-trained CNN
  • Two-stage Aggeragation
  • Integration of aggregated pathological images and genomic data

Get Started

Patch-wise pre-trained CNN (see pretrain folder)

  1. patch_extraction : it extracts valid patchs from WSI by removing background and stains.
  2. Datagenerator.py : it makes the data ready for Keras image data loaders. (As data is large we used keras dataloaders for loading data)
  3. PAGE_net_pretrain : code for pretraining and saving the pretrained model.

Two-stage aggregation (see aggregation folder)

  1. Aggergation.py : it generates the aggregated score and saves in csv.
  2. DataMatching.py : it splits the aggregated data in train, test, and validation

Integration of aggregated pathological images and genomic data

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.

You can’t perform that action at this time.