Following packages are required to install Chainer Chemistry and are automatically installed when you install the library by pip command.

Also, it uses following library, which you need to manually install.

See the official document for installation. If you have setup anaconda, you may install rdkit by following command:

$ conda install -c rdkit rdkit

Install via pip

It can be installed by pip command:

$ pip install chainer-chemistry

Install from source

The tarball of the source tree is available via pip download chainer-chemistry. You can use to install Chainer Chemistry from the tarball:

$ tar zxf chainer-chemistry-x.x.x.tar.gz
$ cd chainer-chemistry-x.x.x
$ python install

Install from the latest source from the master branch:

$ git clone
$ pip install -e chainer-chemistry

Run example training code

The official repository provides examples of training several graph convolution networks. The code can be obtained by cloning the repository:

$ git clone

The following code is how to train Neural Fingerprint (NFP) with the Tox21 dataset on CPU:

$ cd chainer-chemistry/examples/tox21
$ python --method=nfp  --gpu=-1  # set --gpu=0 if you have GPU