Molecular graph enhanced transformer for retrosynthesis prediction
Molecular graph enhanced transformer for retrosynthesis prediction
复制标题
DOI：
10.1016/j.neucom.2021.06.037
复制
发表时间：
2021-07-01
期刊：
影响因子：
6
通讯作者：
Zhao, Peilin
中科院分区：
文献类型：
--
作者：
Mao, Kelong;Xiao, Xi;Zhao, Peilin
由于化学合成途径的多样性，逆合成预测仍然是研究人员面临的一个挑战。最近，逆合成预测被公式化为机器翻译（MT）任务。也就是说，由于每个分子都可以表示为简化的分子输入行输入系统（SMILES）字符串，因此逆合成的过程被类比为从产物到反应物的语言翻译过程。然而，应用于SMILES数据的MT模型通常忽略了自然原子连接和分子拓扑结构的信息。为了在原子表示学习中加入更多的化学约束以提高性能，本文提出了一种图增强的Transformer（GET）框架，该框架同时采用了分子的序列信息和图形信息。提出了四种不同的GET设计，它们将SMILES表示与从我们改进的图神经网络（GNN）中学习的原子嵌入相融合。实证结果表明，我们的模型显着优于香草Transformer模型的测试精度。(c)2021爱思唯尔有限公司版权所有。
With massive possible synthetic routes in chemistry, retrosynthesis prediction is still a challenge for researchers. Recently, retrosynthesis prediction is formulated as a Machine Translation (MT) task. Namely, since each molecule can be represented as a Simplified Molecular-Input Line-Entry System (SMILES) string, the process of retrosynthesis is analogized to a process of language translation from the product to reactants. However, the MT models that applied on SMILES data usually ignore the information of natural atomic connections and the topology of molecules. To make more chemically plausible constrains on the atom representation learning for better performance, in this paper, we propose a Graph Enhanced Transformer (GET) framework, which adopts both the sequential and graphical information of molecules. Four different GET designs are proposed, which fuse the SMILES representations with atom embeddings learned from our improved Graph Neural Network (GNN). Empirical results show that our model significantly outperforms the vanilla Transformer model in test accuracy. (c) 2021 Elsevier B.V. All rights reserved.