Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking
Abstract Graph neural networks (GNNs) have been widely used in molecular property prediction, but explaining their black-box predictions is still a challenge. Most existing explanation methods for GNNs in chemistry focus on attributing model predictions to individual nodes, edges or fragments that a...
Main Authors: | Zhenxing Wu, Jike Wang, Hongyan Du, Dejun Jiang, Yu Kang, Dan Li, Peichen Pan, Yafeng Deng, Dongsheng Cao, Chang-Yu Hsieh, Tingjun Hou |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-05-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-023-38192-3 |
Similar Items
-
Proteome-Wide Profiling of the Covalent-Druggable Cysteines with a Structure-Based Deep Graph Learning Network
by: Hongyan Du, et al.
Published: (2022-01-01) -
ReMODE: a deep learning-based web server for target-specific drug design
by: Mingyang Wang, et al.
Published: (2022-12-01) -
Generic Interpretable Reaction Condition Predictions with Open Reaction Condition Datasets and Unsupervised Learning of Reaction Center
by: Xiaorui Wang, et al.
Published: (2023-01-01) -
Structure and substructure connectivity of circulant graphs and hypercubes
by: T. Tamizh Chelvam, et al.
Published: (2021-04-01) -
Enumeration of substructure patterns from large graphs
by: Chu, Shumo.
Published: (2013)