Napr is a Python package that takes a machine learning driven approach to navigate the natural products chemical space.

pip install napr

To update napr to the latest version, add -U or --upgrade flag, i.e. pip install -U napr.

The tutorials directory include:

• Terpene-explore: exploratory data analysis of terpenes (the COCONUT dataset) in the natural products chemical space
• Terpene-classification-classic: classification of terpenes with ML techniques such as kNN, random forest and xgboost

We welcome new contributors of all experience levels.

Launch the test suite, after installation:

pytest napr

If you use this package, please cite:

• Hosseini, Morteza, and David M. Pereira. "The chemical space of terpenes: insights from data science and AI." arXiv preprint arXiv:2110.15047 (2021).