rxnutils – A Cheminformatics Python Library for Manipulating Chemical Reaction Data

We introduce the Python package rxnutils that can be used to manipulate chemical reactions, reaction templates and reaction datasets. The package is built entirely on open-source software such as RDKit and is designed with robustness, extendibility, and reproducibility in mind. Currently, it consists of three sub-packages one for working with chemical entities, one provides pipelining capabilities, and one provides an end-to-end pipeline for preparing the US patent reaction dataset for modelling. In this software research note we discuss the design of the package and provide some code examples. The project is open-source with a Apache 2.0 license and available at GitHub: https://github.com/MolecularAI/rxnutils