Chemical-Intuition-Based Machine-Learning (ML) yield prediction for Mizoroki-Heck C-glycosylation

Machine-learning (ML) algorithms have emerged as a powerful tool in the field of organic chemistry. While these algorithms have proven to be highly efficient, they are often constrained by the availability of data. In addressing this limitation, we propose a ML-based yield prediction algorithm that operates in a low data regime, leveraging knowledge-based chemical descriptors without requiring extensive computational resources. This model has been utilized to predict Mizoroki-Heck C-glycosylation outcomes.