ChemCNet: An Explainable Integrated Model for Intelligent Analyzing Chemistry Synthesis Reactions

Henan Engineering Research Center For Artificial Intelligence Theory And Algorithms, School Of Mathematics And Statistics, Henan University, China ,Henan Engineering Research Center For Artificial Intelligence Theory And Algorithms, School Of Mathematics And Statistics, Henan University, China ,Zixin Li,Henan Engineering Research Center For Artificial Intelligence Theory And Algorithms, School Of Mathematics And Statistics, Henan University, China ,Yaping Yu,College Of Chemistry And Chemical Engineering, Henan University, China ,Shuoshi Liu,Henan Engineering Research Center For Artificial Intelligence Theory And Algorithms, School Of Mathematics And Statistics, Henan University, China ,Lanfeng Wang,Henan Engineering Research Center For Artificial Intelligence Theory And Algorithms, School Of Mathematics And Statistics, Henan University, China ,School Of Mathematics And Statistics, Anyang Normal Unieversity, Anyang, China ,Xiaohui Yang,Hengzhe Wang,Yun Chai

doi:10.46793/match.91-1.041w

Henan Engineering Research Center For Artificial Intelligence Theory And Algorithms, School Of Mathematics And Statistics, Henan University, China , Henan Engineering Research Center For Artificial Intelligence Theory And Algorithms, School Of Mathematics And Statistics, Henan University, China + Show 12 more

Open Access

https://doi.org/10.46793/match.91-1.041w

Copy DOI

Abstract

Palladium (Pd)-catalyzed cross coupling reactions are of great significance in organic synthesis. However, the reaction route is more complex, time-consuming and costly. For addressing the above problems, a model-related feature selection strategy is introduced, focusing on iterative optimization of feature description and prediction to guide and strengthen each other. Then, we combine the lightweight convolution neural network (CNN) driven by attention mechanism with CatBoost to build an intelligent chemical synthesis reaction analysis model-ChemCNet. Moreover, we conduct the interpretability analysis based on ChemCNet model. The results show that ChemCNet model has achieved relatively high prediction accuracy and generalization, and it is helpful to provide reliable decision-making information for the experimenter or institution.

Full Text