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 install chainer-chemistry
Install from source¶
The tarball of the source tree is available via
pip download chainer-chemistry.
You can use
setup.py to install Chainer Chemistry from the tarball:
$ tar zxf chainer-chemistry-x.x.x.tar.gz $ cd chainer-chemistry-x.x.x $ python setup.py install
Install from the latest source from the master branch:
$ git clone https://github.com/pfnet-research/chainer-chemistry.git $ 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 https://github.com/pfnet-research/chainer-chemistry.git
The following code is how to train Neural Fingerprint (NFP) with the Tox21 dataset on CPU:
$ cd chainer-chemistry/examples/tox21 $ python train_tox21.py --method=nfp --gpu=-1 # set --gpu=0 if you have GPU