Predicting glycosylation stereoselectivity using machine learning

Sooyeon Moon, Sourav Chatterjee, Peter H. Seeberger, Kerry Gilmore

Research output: Contribution to journalArticlepeer-review

34 Citations (SciVal)

Abstract

Predicting the stereochemical outcome of chemical reactions is challenging in mechanistically ambiguous transformations. The stereoselectivity of glycosylation reactions is influenced by at least eleven factors across four chemical participants and temperature. A random forest algorithm was trained using a highly reproducible, concise dataset to accurately predict the stereoselective outcome of glycosylations. The steric and electronic contributions of all chemical reagents and solvents were quantified by quantum mechanical calculations. The trained model accurately predicts stereoselectivities for unseen nucleophiles, electrophiles, acid catalyst, and solvents across a wide temperature range (overall root mean square error 6.8%). All predictions were validated experimentally on a standardized microreactor platform. The model helped to identify novel ways to control glycosylation stereoselectivity and accurately predicts previously unknown means of stereocontrol. By quantifying the degree of influence of each variable, we begin to gain a better general understanding of the transformation, for example that environmental factors influence the stereoselectivity of glycosylations more than the coupling partners in this area of chemical space.

Original languageEnglish
Pages (from-to)2931-2939
Number of pages9
JournalChemical Science
Volume12
Issue number8
Early online date26 Dec 2020
DOIs
Publication statusPublished - 28 Feb 2021

Bibliographical note

Funding Information:
We gratefully acknowledge the generous nancial support of the Max-Planck Society and the DFG InCHeM (FOR 2177). We sincerely thank Ms Tansitha Gupta of GlycoUniverse for providing the fucose precursor, Dr Christoph Rademacher, Prof. Dr Andrea Volkamer, and Prof. Bartosz Grzybowski for valuable discussions and Ms Eva Settels for support.

Electronic supplementary information (ESI) available: Detailed experimental procedures, complete datasets, additional graphs and control studies, details regarding automation and instrumentation. Microsoft Excel worksheets listing of descriptors, the training set, and holdout datasets 1 and 2. Code availability: software available at https://github.com/DrSouravChemEng/GlyMecH. See DOI: 10.1039/d0sc06222g

ASJC Scopus subject areas

  • Chemistry(all)

Fingerprint

Dive into the research topics of 'Predicting glycosylation stereoselectivity using machine learning'. Together they form a unique fingerprint.

Cite this