Predicting bond dissociation energies of cyclic hypervalent halogen reagents using DFT calculations and graph attention network model

• Yingbo Shao,
• Zhiyuan Ren,
• Zhihui Han,
• Li Chen,
• Yao Li and
• Xiao-Song Xue

Beilstein J. Org. Chem. 2024, 20, 1444–1452, doi:10.3762/bjoc.20.127

• results of this study could aid in estimating the chemical stability and functional group transfer capabilities of hypervalent bromine(III) and chlorine(III) reagents, thereby facilitating their development. Keywords: BDE; cyclic hypervalent halogen reagents; DFT calculation; graph attention network

• reagents, we can obtain a rough estimation of the BDEs for others with different halogen centers. With these homolytic and heterolytic BDEs in hand, we next attempted to develop a predictive model for BDEs of hypervalent halogen compounds using machine learning algorithms. Graph attention network (GAT) [85

• employing a graph attention network. We anticipate that the findings from our research will aid the design and development of new hypervalent bromine(III) and chlorine(III) reagents, an area that remains largely underexplored. Examples of cyclic hypervalent halogen reagents. Common cyclic hypervalent