Skip to content

Generative Tensorial Reinforcement Learning (GENTRL) model

Notifications You must be signed in to change notification settings

insilicomedicine/GENTRL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Generative Tensorial Reinforcement Learning (GENTRL)

Supporting Information for the paper "Deep learning enables rapid identification of potent DDR1 kinase inhibitors".

The GENTRL model is a variational autoencoder with a rich prior distribution of the latent space. We used tensor decompositions to encode the relations between molecular structures and their properties and to learn on data with missing values. We train the model in two steps. First, we learn a mapping of a chemical space on the latent manifold by maximizing the evidence lower bound. We then freeze all the parameters except for the learnable prior and explore the chemical space to find molecules with a high reward.

GENTRL

Repository

In this repository, we provide an implementation of a GENTRL model with an example trained on a MOSES dataset.

To run the training procedure,

  1. Install RDKit to process molecules
  2. Install GENTRL model: python setup.py install
  3. Install MOSES from the repository
  4. Run the pretrain.ipynb to train an autoencoder
  5. Run the train_rl.ipynb to optimize a reward function

About

Generative Tensorial Reinforcement Learning (GENTRL) model

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages