Deep Reinforcement Library for Conformer Generation
Project description
conformer-rl
An open-source deep reinforcement learning library for conformer generation.
Documentation
Documentation can be found at https://conformer-rl.readthedocs.io/.
Platform Support
Since conformer-rl can be run within a Conda environment, it should work on all platforms (Windows, MacOS, Linux).
Installation
-
We recommend installing in a new Conda environment.
-
Install dependencies
- Install PyTorch. PyTorch version of 1.8.0 or greater is required for conformer-rl.
- Install PyTorch Geometric.
-
Important Note: Please make sure to use the same package installer for installing both PyTorch and PyTorch geometric.
For example, if you installed PyTorch with pip, use the pip instructions for installing PyTorch Geometric. Similarly, if you installed PyTorch with Conda, use the Conda instructions for installing PyTorch Geometric. Otherwise you may run into errors such as "undefined symbol" when using PyTorch Geometric.
-
- Install RDKit by running the following command
conda install -c conda-forge rdkit
-
Install conformer-rl
pip install conformer-rl
- This will automatically install the additional dependencies needed for conformer-rl. Note that conformer-rl requires Python >= 3.7.
Verify Installation:
As a quick check to verify the installation has succeeded, navigate to the examples directory
and run base_example.py
. The script should finish running in a few minutes or less. If no errors ware encountered then most likely the installation has succeeded.
Additional Installation for Analysis/Visualization Tools
Some additional dependencies are required for visualizing molecules in Jupyter/IPython notebooks.
Firstly, install jupyterlab
, py3Dmol
, and seaborn
(these should already be installed after installing conformer-rl):
pip install jupyterlab py3Dmol seaborn
Install nodejs
. This is only required for creating interactive molecule visualizations in Jupyter:
conda install nodejs
Install the jupyterlab_3dmol extension for visualizing molecules interactively in Jupyter:
jupyter labextension install jupyterlab_3dmol
You should now be able to use the analysis components of conformer-rl for generating figures and visualizing molecule in Jupyter. To test that the installation was succesful, try running the example Jupyter notebook:
jupyter-lab examples/example_analysis.ipynb
Features
-
Agents -
conformer_rl
contains implementations of agents for several deep reinforcement learning algorithms, including recurrent and non-recurrent versions of A2C and PPO.conformer_rl
also includes a base agent interface BaseAgent for constructing new agents. -
Models - Implementations of various graph neural network models are included. Each model is compatible with any molecule.
-
Environments - Implementations for several pre-built environments that are compatible with any molecule. Environments are built on top of the modularized ConformerEnv interface, making it easy to create custom environments and max-and-match different environment components.
-
Analysis -
conformer_rl
contains a module for visualizing metrics and molecule conformers in Jupyter/IPython notebooks. The example notebook in the examples directory shows some examples on how the visualizing tools can be used.
Quick Start
The examples directory contain several scripts for training on pre-built agents and environments. Visit Quick Start to get started.
Issues and Feature Requests
We are actively adding new features to this project and are open to all suggestions. If you believe you have encountered a bug, or if you have a feature that you would like to see implemented, please feel free to file an issue.
Developer Documentation
Pull requests are always welcome for suggestions to improve the code or to add additional features. We encourage new developers to document new features and write unit tests (if applicable). For more information on writing documentation and unit tests, see the developer documentation.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for conformer_rl-0.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | df49b6a363f1cf6d81573a05f877f87f8f635a39e4a36dc3c8d5d4b30119c3a8 |
|
MD5 | fbc7e0ba37e872fb4a931388bc1705ff |
|
BLAKE2b-256 | 4d11e3ccd4835ca9d0a6122e99f9fef9438e697f93d82dc7f765f5ad7c1efa8f |