计算机科学
代表(政治)
斯迈尔斯重排
回顾性分析
序列(生物学)
人工智能
词根(语言学)
图形
理论计算机科学
自然语言处理
机器学习
化学
立体化学
语言学
政治
政治学
哲学
法学
生物化学
全合成
作者
Zipeng Zhong,Jie Song,Zunlei Feng,Tiantao Liu,Lingxiang Jia,Shaolun Yao,Min Wang,Tingjun Hou,Mingli Song
出处
期刊:Chemical Science
[The Royal Society of Chemistry]
日期:2022-01-01
卷期号:13 (31): 9023-9034
被引量:17
摘要
Chemical reaction prediction, involving forward synthesis and retrosynthesis prediction, is a fundamental problem in organic synthesis. A popular computational paradigm formulates synthesis prediction as a sequence-to-sequence translation problem, where the typical SMILES is adopted for molecule representations. However, the general-purpose SMILES neglects the characteristics of chemical reactions, where the molecular graph topology is largely unaltered from reactants to products, resulting in the suboptimal performance of SMILES if straightforwardly applied. In this article, we propose the root-aligned SMILES (R-SMILES), which specifies a tightly aligned one-to-one mapping between the product and the reactant SMILES for more efficient synthesis prediction. Due to the strict one-to-one mapping and reduced edit distance, the computational model is largely relieved from learning the complex syntax and dedicated to learning the chemical knowledge for reactions. We compare the proposed R-SMILES with various state-of-the-art baselines and show that it significantly outperforms them all, demonstrating the superiority of the proposed method.
科研通智能强力驱动
Strongly Powered by AbleSci AI