一种用于解决小规模反应预测问题的图卷积神经网络。
A graph-convolutional neural network for addressing small-scale reaction prediction.
作者信息
Wu Yejian, Zhang Chengyun, Wang Ling, Duan Hongliang
机构信息
Artificial Intelligence Aided Drug Discovery Institute, College of Pharmaceutical Sciences, Zhejiang University of Technology, Hangzhou 310014, China.
出版信息
Chem Commun (Camb). 2021 Apr 27;57(34):4114-4117. doi: 10.1039/d1cc00586c.
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%).
我们描述了一种图卷积神经网络（GCN）模型，基于足够的数据，其反应预测能力与变压器模型相当，并且我们采用拜耳-维利格氧化反应来基于有限的数据探索它们的性能差异。GCN模型的top-1准确率（90.4%）高于变压器模型（58.4%）。
Zotero 插件