Chainer Chemistry: A Library for Deep Learning in Biology and Chemistry
Chainer Chemistry is a collection of tools to train and run neural networks for tasks in biology and chemistry using Chainer.
It supports various state-of-the-art deep learning neural network models (especially Graph Convolution Neural Network) for chemical molecule property prediction.
Chainer Chemistry can be installed by
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 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
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 https://github.com/pfnet-research/chainer-chemistry.git pip install -e chainer-chemistry
Following packages are required to install Chainer Chemistry and are automatically
installed when you install it by
Also, it uses following library, you need to manually install it.
See the official document
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.
Chainer Chemistry is tested under following version of other library.
|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|
Currently, following graph convolutional neural networks are implemented.
- NFP: Neural fingerprint [2, 3]
- GGNN: Gated Graph Neural Network [4, 3]
- WeaveNet: [5, 3]
- SchNet: 
- RSGCN: Renormalized Spectral Graph Convolutional Network 
* The name is not from original paper, see PR #89 for the naming
Currently, following dataset is supported.
- QM9 [7, 8]
- Tox21 
- MoleculeNet 
This image is the result of
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.
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:
- Document: https://chainer-chemistry.readthedocs.io
- Blog: Release Chainer Chemistry: A library for Deep Learning in Biology and Chemistry
Links for other Chainer projects:
- Chainer: A flexible framework of neural networks for deep learning
- ChainerRL: Deep reinforcement learning library built on top of Chainer - chainer/chainerrl
- ChainerCV: A Library for Deep Learning in Computer Vision - chainer/chainercv
- ChainerMN: Scalable distributed deep learning with Chainer - chainer/chainermn
- ChainerUI: User Interface for Chainer - chainer/chainerui
- PaintsChainer: Line drawing colorization using chainer
- CuPy: NumPy-like API accelerated with CUDA
If you are new to chainer, here is a tutorial to start with:
- Chainer Notebooks: hands on tutorial - mitmul/chainer-handson
 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.
 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.
 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.
 Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard Zemel. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493, 2015.
 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.
 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.
 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.
 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.
 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.
 Kipf, Thomas N. and Welling, Max. Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR), 2017.
 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.