AiZynthFinder
AiZynthFinder is a tool for retrosynthetic planning. The algorithm is based on a Monte Carlo tree search that recursively breaks down a molecule to purchasable precursors. The tree search is guided by a policy that suggests possible precursors by utilizing a neural network trained on a library of known reaction templates.
An introduction video can be found here: https://youtu.be/r9Dsxm-mcgA
Prerequisites
Before you begin, ensure you have met the following requirements:
-
Linux, Windows or macOS platforms are supported - as long as the dependencies are supported on these platforms.
-
You have installed anaconda or miniconda with python 3.8 - 3.9
The tool has been developed on a Linux platform, but the software has been tested on Windows 10 and macOS Catalina.
Installation
For end-users
First time, execute the following command in a console or an Anaconda prompt
conda create "python>=3.8,<3.10" -n aizynth-env
To install, activate the environment and install the package using pypi
conda activate aizynth-env
python -m pip install aizynthfinder[all]
for a smaller package, without all the functionality, you can also type
python -m pip install aizynthfinder
For developers
First clone the repository using Git.
Then execute the following commands in the root of the repository
conda env create -f env-dev.yml
conda activate aizynth-dev
poetry install -E all
the aizynthfinder package is now installed in editable mode.
Usage
The tool will install the aizynthcli and aizynthapp tools
as interfaces to the algorithm:
aizynthcli --config config.yml --smiles smiles.txt
aizynthapp --config config.yml
Consult the documentation here for more information.
To use the tool you need
1. A stock file
2. A trained rollout policy network (including the Keras model and the list of unique templates)
3. A trained filer policy network (optional)
Such files can be downloaded from figshare and here or they can be downloaded automatically using
download_public_data my_folder
where my_folder is the folder that you want download to.
This will create a config.yml file that you can use with either aizynthcli or aizynthapp.
Development
Testing
Tests uses the pytest package, and is installed by poetry
Run the tests using:
pytest -v
The full command run on the CI server is available through an invoke command
invoke full-tests
Documentation generation
The documentation is generated by Sphinx from hand-written tutorials and docstrings
The HTML documentation can be generated by
invoke build-docs
Contributing
We welcome contributions, in the form of issues or pull requests.
If you have a question or want to report a bug, please submit an issue.
To contribute with code to the project, follow these steps:
- Fork this repository.
- Create a branch:
git checkout -b <branch_name>. - Make your changes and commit them:
git commit -m '<commit_message>' - Push to the remote branch:
git push - Create the pull request.
Please use black package for formatting, and follow pep8 style guide.
Contributors
The contributors have limited time for support questions, but please do not hesitate to submit an issue (see above).
License
The software is licensed under the MIT license (see LICENSE file), and is free and provided as-is.
References
- Thakkar A, Kogej T, Reymond J-L, et al (2019) Datasets and their influence on the development of computer assisted synthesis planning tools in the pharmaceutical domain. Chem Sci. https://doi.org/10.1039/C9SC04944D
- Genheden S, Thakkar A, Chadimova V, et al (2020) AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning. J. Cheminf. https://jcheminf.biomedcentral.com/articles/10.1186/s13321-020-00472-1
- Genheden S, Engkvist O, Bjerrum E (2020) A Quick Policy to Filter Reactions Based on Feasibility in AI-Guided Retrosynthetic Planning. ChemRxiv. Preprint. https://doi.org/10.26434/chemrxiv.13280495.v1
- Genheden S, Engkvist O, Bjerrum E (2021) Clustering of synthetic routes using tree edit distance. J. Chem. Inf. Model. 61:3899β3907 https://doi.org/10.1021/acs.jcim.1c00232
- Genheden S, Engkvist O, Bjerrum E (2022) Fast prediction of distances between synthetic routes with deep learning. Mach. Learn. Sci. Technol. 3:015018 https://doi.org/10.1088/2632-2153/ac4a91