Hybrid Machine Learning Approach to Predict the Site Selectivity of Iridium-Catalyzed Arene Borylation
Гибридный подход на основе машинного обучения для прогнозирования региоселективности бори́лирования аренов, катализируемого иридием
2023-07-31
SCID: 54.1/bb8qqw3u
Discuss with AI
Site of Borylation (SoBo)density functional theoryhybrid computational modeliridium catalysissite-selective arene borylation
Figures from the paper
Abstract (AI)
The borylation of aryl and heteroaryl C–H bonds is valuable for the site-selective functionalization of C–H bonds in complex molecules. Iridium catalysts ligated by bipyridine ligands catalyze the borylation of the aryl C–H bonds that are most acidic and least sterically hindered, but predicting the site of borylation in molecules containing multiple arenes is difficult. To address this challenge, we report a hybrid computational model that predicts the Site of Borylation (SoBo) in complex molecules. The SoBo model combines density functional theory, semi-empirical quantum mechanics, cheminformatics, linear regression, and machine learning to predict site selectivity and to extrapolate these predictions to new chemical space. Experimental validation of SoBo showed that the model predicts the major site of borylation of pharmaceutical intermediates with higher accuracy than prior machine-learning models or human experts, demonstrating that SoBo will be useful to guide experiments for the borylation of specific C(sp2)–H bonds during pharmaceutical development.
Key Findings
1
A hybrid Site of Borylation (SoBo) model predicts regioselectivity in iridium-catalyzed arene and heteroarene C–H borylation.
2
Experimental validation showed higher accuracy than prior machine-learning models and human experts for identifying major borylation sites in pharmaceutical intermediates.
3
SoBo can guide experiments targeting specific C(sp2)–H bonds during pharmaceutical development.
4
SoBo integrates density functional theory, semiempirical quantum mechanics, cheminformatics, linear regression, and machine learning.
5
The model addresses difficult site prediction in molecules containing multiple arenes and extrapolates predictions to new chemical space.
Research Object
Iridium-catalyzed borylation of aryl and heteroaryl C–H bonds in complex molecules containing multiple arenes
Research Subject
Site selectivity of borylation, specifically prediction of the major borylation site based on C–H bond acidity and steric hindrance
Publication Details
Publication Date
2023-07-31
Journal
Publisher
ISSN
Cited by
72
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai8
Density-functional thermochemistry. III. The role of exact exchange1993
Scikit-learn: Machine Learning in Python2012
A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu2010
SciPy 1.0: fundamental algorithms for scientific computing in Python2020
Array programming with NumPy2020
Ab Initio Calculation of Vibrational Absorption and Circular Dichroism Spectra Using Density Functional Force Fields1994
SciPy 1.0: fundamental algorithms for scientific computing in Python2019
Extended tight‐binding quantum chemistry methods2020