Cargando…

Knowledge-Embedded Message-Passing Neural Networks: Improving Molecular Property Prediction with Human Knowledge

[Image: see text] The graph neural network (GNN) has become a promising method to predict molecular properties with end-to-end supervision, as it can learn molecular features directly from chemical graphs in a black-box manner. However, to achieve high prediction accuracy, it is essential to supervi...

Descripción completa

Detalles Bibliográficos
Autor principal: Hasebe, Tatsuya
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2021
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8552328/
https://www.ncbi.nlm.nih.gov/pubmed/34722995
http://dx.doi.org/10.1021/acsomega.1c03839