Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking

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 are not ne...

Descripción completa

Detalles Bibliográficos
Autores principales: Wu, Zhenxing, Wang, Jike, Du, Hongyan, Jiang, Dejun, Kang, Yu, Li, Dan, Pan, Peichen, Deng, Yafeng, Cao, Dongsheng, Hsieh, Chang-Yu, Hou, Tingjun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10160109/
https://www.ncbi.nlm.nih.gov/pubmed/37142585
http://dx.doi.org/10.1038/s41467-023-38192-3

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10160109/
https://www.ncbi.nlm.nih.gov/pubmed/37142585
http://dx.doi.org/10.1038/s41467-023-38192-3

Ejemplares similares