Predicting glycosylation stereoselectivity using machine learning

Abstract

A random forest algorithm, trained on a concise dataset and validated experimentally, accurately predicts the stereoselectivity of a complex organic coupling varying all reaction parameters as well as previously unknown mechanistic influences.

Guidelines for O-Glycoside Formation from First Principles

“…Guideline 4: Big data approaches to predicting glycosylation 28 should not include glycosylations for which concentration is not specified in the training data set.…”

Flow synthesis kinetics for lomustine, an anti-cancer active pharmaceutical ingredient

“…A kinetic model is most often based on an assumed reaction mechanism whose rate equations are then to be validated via experimental data, possibly via similar reaction literature 61 for studying and analysing mechanisms related to stereoselectivity, 62 organocatalysis, 63 and provides valuable assistance to spectroscopic 64 and other relevant investigations. A DFT approach may provide additional insight, but is beyond the scope of our present study.…”

Towards a Systematic Understanding of the Influence of Temperature on Glycosylation Reactions

“…[3] Reported yields can be difficult to reproduce, and crucial reaction conditions often go unreported. Despite recent advances in the standardization of glycosidic bond formation, as well as an improved physical organic and mechanistic understanding of the factors governing the outcomes, [4][5][6][7][8][9] irreproducibility and poor transferability stymie progress. Here, we aim to decrypt the fundamental role of temperature, a key parameter influencing the yield and selectivity of glycosylations.…”