A graph-convolutional neural network for addressing small-scale reaction prediction

Yejian Wu, Chengyun Zhang, Ling Wang, Hongliang Duan

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

We describe a graph-convolutional neural network (GCN) model, the reaction prediction capabilities of which are as potent as those of the transformer model based on sufficient data, and we adopt the Baeyer-Villiger oxidation reaction to explore their performance differences based on limited data. The top-1 accuracy of the GCN model (90.4%) is higher than that of the transformer model (58.4%).

Original languageEnglish
Pages (from-to)4114-4117
Number of pages4
JournalChemical Communications
Volume57
Issue number34
DOIs
Publication statusPublished - 30 Apr 2021
Externally publishedYes

Fingerprint

Dive into the research topics of 'A graph-convolutional neural network for addressing small-scale reaction prediction'. Together they form a unique fingerprint.

Cite this