Academic Journal of Materials & Chemistry, 2020, 1(1); doi: 10.25236/AJMC.2020.010101.
Chao Liu1, Yifei Wang2
1.Department of Chemistry, Southern University of Science and Technology of China, Guangdong, Shenzhen, 518055, China
2.Shenzhen College of International Education, Guangdong, Shenzhen, 51800, China
Aiming at developing the most suitable method based on machine learning to predict the results of C-H activation reaction of indoles (CARI), we constructed the database by using ortho-substitution and meta-substitution to collect 2000 different CARI. DFT method is employed to calculate energy barrier and selectivity of all reactions.7 algorithms are involved -Random forest (RF), Kernel Ridge Regression (KRR), K Nearest Neighbor (KNN), Support Vector Regression (SVR), Neural Network (NN), Gaussian Process (GP) and LASSO Regression (LASSO)-to make predictions. Meanwhile, the results of the reactions give us the guidance to predict the energy barrier and selectivity of new reactions for experimentalists. According to the data, Random forest is the most suitable way to make predictions. Superior to random forest, KNN and NN also demonstrates good performance.
Machine learning, C-H activation, Indoles, Ortho-substitution, Meta- substitution
Jinhui Duan. Machine Learning of C-H Activation Reaction of Indoles. Academic Journal of Materials & Chemistry (2020) Vol. 1 Issue 1: 1-10. https://doi.org/10.25236/AJMC.2020.010101.
 Junfei Lu, Xing Xu, Junliang Zheng.Research progress of indole C - H arylation reaction [J].Organic Chemistry,2018(02):363-377.
 Beili Lu, Xianyan Li, Yongmei, Lin, Research progress in the formation of indole structure by c-H bond group catalyzed by transition metals [J].Organic Chemistry,2015,35(011):2275-2290.
 Lalit K, Shashi B, Kamal J. The diverse pharmacological importance of indole derivatives: a review[J]. International Journal of Research in Pharmacy & Science, 2012, 2(2): 22-33.
 Yidi Liu, Qi Yang, Yao Li.Application of machine learning in organic chemistry [J].Organic Chemistry,2020(0823):1-16.
 Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5 - 32.