Hybrid Machine Learning Approach to Predict the Site Selectivity of Iridium-Catalyzed Arene Borylation

Abstract

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 C−H bond that is most acidic and least sterically hindered in an arene, 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, semiempirical 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(sp 2 )−H bonds during pharmaceutical development.

Dataset Design for Building Models of Chemical Reactivity

“…most often corresponds to the difference between enantio-determining transition states with the general reaction mechanism otherwise being the same, allowing one to neglect factors that confound modeling yield as an output, such as side reactions or differences in turnover rates of a catalyst. Likewise, regioselectivity is an internally consistent metric that relies only on direct comparisons between candidate atom sites. − …”

Leveraging Language Model Multitasking To Predict C–H Borylation Selectivity

“…For a comparison with the prior art, the model finetune 2 was tested on the validation set of six pharmaceutical intermediates from the SoBo model paper . The finetune 2 model correctly predicted the products for two molecules out of six (Figure ).…”

Extraction yield prediction for the large-scale recovery of cannabinoids

“…Most efforts in chemical synthesis rely on data sets extracted from the literature, 5,12–14 produced by high throughput experimentation, 4,15,16 or a combination of the two. 17 However, these data sources do not exist or are in limited supply for training robust ML models for extraction processes. One potential explanation is that these separations are generally performed on large scale (input > 1 kg) making the process conditions more expensive to evaluate.…”