Skip to content

jshyunbin/protein-seq-design-RL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Image 1 Image 2

CS492(B) Project Team 4

Third-party libraries

  • Install omegafold
  • Install FoldX and place executable inside the working directory

Environment

  • Install PyTorch version 1.12.0 compatible with your CUDA version
  • Other dependencies can be found in requirements.txt

Data and Pretrained checkpoints

The dataset and pretrained omegafold checkpoint will be automatically downloaded when you run the code.

Code

  • baselines.py: test random mutation and genetic algorithm baseline
  • train.py: train function predictor GNN
  • optimize.py: optimize proteins using our definition of state and action
  • optimize_onehot.py: optimize proteins given one-hot encoded sequence as state (ablation)

About

Project directory for CS492. Contributers: Minji Lee, Hyunbin Lee

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages