Predicting Regioselectivity in Radical C−H Functionalization of Heterocycles through Machine Learning
- 2 May 2020
- journal article
- research article
- Published by Wiley in Angewandte Chemie International Edition
- Vol. 59 (32) , 13253-13259
Abstract
Radical C−H bond functionalization provides a versatile approach for elaborating heterocyclic compounds. The synthetic design of this transformation relies heavily on the knowledge of regioselectivity, while a quantified and efficient regioselectivity prediction approach is still elusive. Herein, we report the feasibility of using a machine learning model to predict the transition state barrier from the computed properties of isolated reactants. This enables rapid and reliable regioselectivity prediction for radical C−H bond functionalization of heterocycles. The Random Forest model with physical organic features achieved 94.2 % site accuracy and 89.9 % selectivity accuracy in the out‐of‐sample test set. The prediction performance was further validated by comparing the machine learning results with additional substituents, heteroarene scaffolds and experimental observations. This work revealed that the combination of mechanism‐based computational statistics and machine learning model can serve as a useful strategy for selectivity prediction of organic transformations.Keywords
Funding Information
- National Natural Science Foundation of China (21702182, 21873081)
- Fundamental Research Funds for the Central Universities (2019QNA3009)
- Postdoctoral Research Foundation of China (2018M640546)
- Zhejiang University (Gold Experts Project (GEP))
This publication has 89 references indexed in Scilit:
- Optimization of parameters for semiempirical methods VI: more modifications to the NDDO approximations and re-optimization of parametersJournal of Molecular Modeling, 2012
- Practical and innate carbon–hydrogen functionalization of heterocyclesNature, 2012
- A New Reagent for Direct DifluoromethylationJournal of the American Chemical Society, 2012
- Innate C-H trifluoromethylation of heterocyclesProceedings of the National Academy of Sciences, 2011
- Direct C−H Arylation of Electron-Deficient Heterocycles with Arylboronic AcidsJournal of the American Chemical Society, 2010
- Palladium-Catalyzed Ligand-Directed C−H Functionalization ReactionsChemical Reviews, 2010
- Palladium(II)‐Catalyzed C-H Activation/C-C Cross‐Coupling Reactions: Versatility and PracticalityAngewandte Chemie International Edition, 2009
- Rhodium-Catalyzed C−C Bond Formation via Heteroatom-Directed C−H Bond ActivationChemical Reviews, 2009
- Merck molecular force field. II. MMFF94 van der Waals and electrostatic parameters for intermolecular interactionsJournal of Computational Chemistry, 1996
- Merck molecular force field. I. Basis, form, scope, parameterization, and performance of MMFF94Journal of Computational Chemistry, 1996