TY - JOUR
T1 - DGL-LifeSci
T2 - An Open-Source Toolkit for Deep Learning on Graphs in Life Science
AU - Li, Mufei
AU - Zhou, Jinjing
AU - Hu, Jiajing
AU - Fan, Wenxuan
AU - Zhang, Yangkang
AU - Gu, Yaxin
AU - Karypis, George
N1 - Publisher Copyright:
© 2021 The Authors. Published by American Chemical Society.
PY - 2021/10/19
Y1 - 2021/10/19
N2 - Graph neural networks (GNNs) constitute a class of deep learning methods for graph data. They have wide applications in chemistry and biology, such as molecular property prediction, reaction prediction, and drug-target interaction prediction. Despite the interest, GNN-based modeling is challenging as it requires graph data preprocessing and modeling in addition to programming and deep learning. Here, we present Deep Graph Library (DGL)-LifeSci, an open-source package for deep learning on graphs in life science. Deep Graph Library (DGL)-LifeSci is a python toolkit based on RDKit, PyTorch, and Deep Graph Library (DGL). DGL-LifeSci allows GNN-based modeling on custom datasets for molecular property prediction, reaction prediction, and molecule generation. With its command-line interfaces, users can perform modeling without any background in programming and deep learning. We test the command-line interfaces using standard benchmarks MoleculeNet, USPTO, and ZINC. Compared with previous implementations, DGL-LifeSci achieves a speed up by up to 6×. For modeling flexibility, DGL-LifeSci provides well-optimized modules for various stages of the modeling pipeline. In addition, DGL-LifeSci provides pretrained models for reproducing the test experiment results and applying models without training. The code is distributed under an Apache-2.0 License and is freely accessible at https://github.com/awslabs/dgl-lifesci.
AB - Graph neural networks (GNNs) constitute a class of deep learning methods for graph data. They have wide applications in chemistry and biology, such as molecular property prediction, reaction prediction, and drug-target interaction prediction. Despite the interest, GNN-based modeling is challenging as it requires graph data preprocessing and modeling in addition to programming and deep learning. Here, we present Deep Graph Library (DGL)-LifeSci, an open-source package for deep learning on graphs in life science. Deep Graph Library (DGL)-LifeSci is a python toolkit based on RDKit, PyTorch, and Deep Graph Library (DGL). DGL-LifeSci allows GNN-based modeling on custom datasets for molecular property prediction, reaction prediction, and molecule generation. With its command-line interfaces, users can perform modeling without any background in programming and deep learning. We test the command-line interfaces using standard benchmarks MoleculeNet, USPTO, and ZINC. Compared with previous implementations, DGL-LifeSci achieves a speed up by up to 6×. For modeling flexibility, DGL-LifeSci provides well-optimized modules for various stages of the modeling pipeline. In addition, DGL-LifeSci provides pretrained models for reproducing the test experiment results and applying models without training. The code is distributed under an Apache-2.0 License and is freely accessible at https://github.com/awslabs/dgl-lifesci.
UR - http://www.scopus.com/inward/record.url?scp=85117838172&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85117838172&partnerID=8YFLogxK
U2 - 10.1021/acsomega.1c04017
DO - 10.1021/acsomega.1c04017
M3 - Article
C2 - 34693143
AN - SCOPUS:85117838172
SN - 2470-1343
VL - 6
SP - 27233
EP - 27238
JO - ACS Omega
JF - ACS Omega
IS - 41
ER -