Installing chemper

The only way to install chemper right now is to clone or download the GitHub repo. When we’re ready to release version 1.0.0 we’ll also make it conda installable.


We currently test with Python 3.5, though we expect anything 3.5+ should work.

This is a python tool kit with a few dependencies. We recommend installing miniconda. Then you can create an environment with the following commands:

conda create -n [my env name] python=3.5 numpy networkx pytest
source activate [my env name]

This command will install all dependencies besides a toolkit for cheminformatics or storing of molecule information. We seek to keep this tool independent of cheminformatics toolkit, but currently only support RDKit and OpenEye Toolkits. If you wish to add support please feel free to submit a pull request. Make sure one of these tool kits is installed in your environment before installing chemper.

RDKit environment

Conda installation according to RDKit documentation:

conda install -c rdkit rdkit

OpenEye environment

Conda installation according to OpenEye documentation

cond install -c openeye openeye-toolkits


Hopefully chemper will be conda installable in the near future, but for now the best option is to download or clone from GitHub and then from inside the chemper directory install with the command:

pip install -e .