Counting 2,987 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Chainer Chemistry: A Library for Deep Learning in Biology and Chemistry

PyPI GitHub license travis Read the Docs

Chainer Chemistry Overview

Chainer Chemistry is a collection of tools to train and run neural networks for tasks in biology and chemistry using Chainer[1].

It supports various state-of-the-art deep learning neural network models (especially Graph Convolution Neural Network) for chemical molecule property prediction.

For more information, you can refer to documentation. Also, a gentle introduction to deep learning for molecules and Chainer Chemistry is available here (SlideShare)).

Quick start

1. Installation

Chainer Chemistry can be installed by pip command.

Note that it uses rdkit, Open-Source Cheminformatics Software. Below code is an example to install rdkit by conda command provided by anaconda.

pip install chainer-chemistry
conda install -c rdkit rdkit

2. Run example training code

The official repository provides examples several graph convolution networks with the Tox21 and QM9 datasets (the Tox21 example has inference code as well). You can obtain the code 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


Usual users can install this library via PyPI:

pip install chainer-chemistry

Chainer Chemistry is still in experimental development. If you would like to use latest sources. please install master branch with the command:

git clone
pip install -e chainer-chemistry


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

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

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

conda install -c rdkit rdkit==2017.09.3.0

Note that we support specified version of RdKit. Latest version RdKit behavior may be different from supported version, and it is not supported.

Version table

Chainer Chemistry is tested under following version of other library.

Chainer Chemistry Chainer RdKit
v0.1.0 ~ v0.3.0 v2.0 ~ v3.0 2017.09.3.0
v0.4.0 v3.0 ~ v4.0 *1 2017.09.3.0
master branch v3.0 ~ v4.0 2017.09.3.0


*1: We used FunctionNode in this PR, which is introduced after chainer v3. See this issue for details.

Supported model

Currently, following graph convolutional neural networks are implemented.

  • NFP: Neural fingerprint [2, 3]
  • GGNN: Gated Graph Neural Network [4, 3]
  • WeaveNet: [5, 3]
  • SchNet: [6]
  • RSGCN: Renormalized Spectral Graph Convolutional Network [10]
    * The name is not from original paper, see PR #89 for the naming

Supported dataset

Currently, following dataset is supported.

  • QM9 [7, 8]
  • Tox21 [9]
  • MoleculeNet [11]



This image is the result of examples/tox21/ Note that we do not guarantee reproducibility of papers in which each model is proposed and hence this result doesn't imply the performance of models themselves.


MIT License.

We provide no warranty or support for this implementation. Each model performance is not guaranteed, and may not achieve the score reported in each paper. Use it at your own risk.

Please see the LICENSE file for details.


Links for Chainer Chemistry:

Links for other Chainer projects:

If you are new to chainer, here is a tutorial to start with:


[1] Seiya Tokui, Kenta Oono, Shohei Hido, and Justin Clayton. Chainer: a next-generation open source framework for deep learning. In Proceedings of Workshop on Machine Learning Systems (LearningSys) in Advances in Neural Information Processing System (NIPS) 28, 2015.

[2] David K Duvenaud, Dougal Maclaurin, Jorge Iparraguirre, Rafael Bombarell, Timothy Hirzel, Alan Aspuru-Guzik, and Ryan P Adams. Convolutional networks on graphs for learning molecular fingerprints. In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems (NIPS) 28, pages 2224–2232. Curran Asso- ciates, Inc., 2015.

[3] Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. Neural message passing for quantum chemistry. arXiv preprint arXiv:1704.01212, 2017.

[4] Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard Zemel. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493, 2015.

[5] Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, and Patrick Riley. Molecular graph convolutions: moving beyond fingerprints. Journal of computer-aided molecular design, 30(8):595–608, 2016.

[6] Kristof Schütt, Pieter-Jan Kindermans, Huziel Enoc Sauceda Felix, Stefan Chmiela, Alexandre Tkatchenko, and Klaus-Rober Müller. Schnet: A continuous-filter convolutional neural network for modeling quantum interactions. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems (NIPS) 30, pages 992–1002. Curran Associates, Inc., 2017.

[7] Lars Ruddigkeit, Ruud Van Deursen, Lorenz C Blum, and Jean-Louis Reymond. Enumeration of 166 billion organic small molecules in the chemical universe database gdb-17. Journal of chemical information and modeling, 52(11):2864–2875, 2012.

[8] Raghunathan Ramakrishnan, Pavlo O Dral, Matthias Rupp, and O Anatole Von Lilienfeld. Quantum chemistry structures and properties of 134 kilo molecules. Scientific data, 1:140022, 2014.

[9] Ruili Huang, Menghang Xia, Dac-Trung Nguyen, Tongan Zhao, Srilatha Sakamuru, Jinghua Zhao, Sampada A Shahane, Anna Rossoshek, and Anton Simeonov. Tox21challenge to build predictive models of nuclear receptor and stress response pathways as mediated by exposure to environmental chemicals and drugs. Frontiers in Environmental Science, 3:85, 2016.

[10] Kipf, Thomas N. and Welling, Max. Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR), 2017.

[11] Zhenqin Wu, Bharath Ramsundar, Evan N. Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S. Pappu, Karl Leswing, Vijay Pande, MoleculeNet: A Benchmark for Molecular Machine Learning, arXiv preprint, arXiv: 1703.00564, 2017.

Latest Releases
 Jul. 19 2018
 Apr. 24 2018
 Mar. 1 2018
 Dec. 14 2017