Skip to content
/ RAMP Public

RAMP: Response-Aware Multi-task Learning with Contrastive Regularization for Cancer Drug Response Prediction

Notifications You must be signed in to change notification settings

hvcl/RAMP

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

31 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RAMP

This is an official implementation of "RAMP: Response-Aware Multi-task Learning with Contrastive Regularization for Cancer Drug Response Prediction" by Kanggeun Lee, Dongbin Cho, Jinho Jang, Hyoung-oh Jeong, Jiwon Seo, Won-Ki Jeong and Semin Lee.

Environment Setup

  • The environment settings for RA-NS are described in here.

  • Building docker images to test 10-fold nested cross validation using extracted embedding vectors.

  • Choose your environment either tensorflow or pytorch.

cd src/response_prediction/docker/tensorflow
./build.sh 
or
cd src/response_prediction/docker/pytorch
./build.sh 

Quick Test

  • You should ensure that a global "PATH" variable have to be modified to your environment path in demo_tf.py and demo_torch.py

  • All experiments in the manuscript were done in Tensorflow.

cd src/response_prediction/scripts
./demo_tf.sh or ./demo_torch.sh 

About

RAMP: Response-Aware Multi-task Learning with Contrastive Regularization for Cancer Drug Response Prediction

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published