https://github.com/aksub99/moldqn-pytorch

A PyTorch Implementation of "Optimization of Molecules via Deep Reinforcement Learning".
https://github.com/aksub99/moldqn-pytorch

chemistry deep-learning dqn-pytorch drug-discovery inverse-design machine-learning materials-informatics materials-science molecule python pytorch pytorch-implementation pytorch-rl reinforcement-learning

Last synced: 2 months ago
JSON representation

A PyTorch Implementation of "Optimization of Molecules via Deep Reinforcement Learning".

• Host: GitHub
• URL: https://github.com/aksub99/moldqn-pytorch
• Owner: aksub99
• License: mit
• Created: 2019-10-19T20:09:32.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2023-03-24T23:37:44.000Z (over 1 year ago)
• Last Synced: 2024-09-26T08:41:16.534Z (3 months ago)
• Topics: chemistry, deep-learning, dqn-pytorch, drug-discovery, inverse-design, machine-learning, materials-informatics, materials-science, molecule, python, pytorch, pytorch-implementation, pytorch-rl, reinforcement-learning
• Language: Python
• Size: 3.05 MB
• Stars: 74
• Watchers: 3
• Forks: 28
• Open Issues: 7
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# MolDQN-pytorch

[![MIT

license](https://img.shields.io/badge/License-MIT-blue.svg)](https://lbesson.mit-license.org/)

[![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)

PyTorch implementation of MolDQN as described in [Optimization of Molecules via Deep Reinforcement Learning](https://www.nature.com/articles/s41598-019-47148-x)

by Zhenpeng Zhou, Steven Kearnes, Li Li, Richard N. Zare and Patrick Riley.

## Installation

## From source:

1) Install `rdkit`.  

   `conda create -c rdkit -n my-rdkit-env rdkit`  

   `conda activate my-rdkit-env`  

   `conda install -c conda-forge rdkit`  

   

2) Clone this repository.  

   `git clone https://github.com/aksub99/MolDQN-pytorch.git`  

   `cd MolDQN-pytorch`

   

3) Install the requirements given in `requirements.txt`.  

   `pip install -r requirements.txt`  

   

4) Install `baselines`.  

   `pip install "git+https://github.com/openai/baselines.git"`  

   

## From Docker:

Using a docker image requires an NVIDIA GPU.  If you do not have a GPU please follow the directions for [installing from source](#source)

In order to get GPU support you will have to use the [nvidia-docker](https://github.com/NVIDIA/nvidia-docker) plugin.

``` bash

# Build the Dockerfile in Dockerfiles/Dockerfile to create a Docker image.

cd Dockerfiles

docker build -t moldqn_pytorch:latest .

# This will create a container from the image we just created.

nvidia-docker run -[Options] moldqn_pytorch:latest python path/to/main.py

```

Please remember to modify the `TB_LOG_PATH` variable in `main.py` depending on where you wish to store your tensorboard runs file.

## Training the MolDQN:

`python main.py`

A simple example to train the model on a single property optimization task can be seen in `examples/MolDQN-pytorch.ipynb`.

## Results:

The following was the reward curve obtained when the model was trained for 5000 episodes on a single property optimization task (QED in this case).



## References:

The original tensorflow implementation can be found at https://github.com/google-research/google-research/tree/master/mol_dqn

This repository re-uses some code from the original implementation.