Skip to content

Deep learning-based multimodal integration of histology and genomics to improves cancer origin prediction

Notifications You must be signed in to change notification settings

mahmoodlab/multimodal-cancer-origin-prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 

Repository files navigation

Multimodal Primary Site of Cancer Origin Prediction

© This code is made available only for manuscript reviewers.

Pre-requisites:

  • Linux (Tested on Ubuntu 20.04.4 LTS)
  • NVIDIA GPU (Tested on Nvidia GeForce RTX 3090)
  • Python (3.9.12), h5py (3.6.0), numpy (1.21.5), pandas (1.4.2), PyTorch (1.11.0), scikit-learn (1.1.1)

Dataset

We have provided the data of publicaly available cases (TCGA and CPTAC) in our dataset to seamlessly run and validate the code.

Training

python train_valid_test.py --classification_type='MM' --exec_mode='train' --exp_name='exp_01'

Evaluation

python train_valid_test.py --classification_type='MM' --exec_mode='eval' --exp_name='exp_01' --split_name='test'

About

Deep learning-based multimodal integration of histology and genomics to improves cancer origin prediction

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published