Skip to content

TheFutureLab/Mol-DQN

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Mol-DQN

Optimization of Molecules via Deep Reinforcement Learning https://arxiv.org/abs/1810.08678

##Model

1). logP

  • reward : penalized logP
  • ./models/logp_model/train.py

2). QED

  • reward : QED(Quantitative Estimate of Druglikeness)
  • ./models/qed_model/train.py

3). logP_constraint

  • reward : logP - w*(k-similarity)
  • ./models/logP_constraint/train.py

4). multiobjective

  • reward : w*similarity + (1-w)*QED
  • ./models/multi_logp_qed_model/train.py

##Result

Releases

No releases published

Packages

No packages published

Languages

  • Python 52.9%
  • HTML 23.8%
  • Jupyter Notebook 23.3%