Substrate specific closed-loop optimization of carbohydrate protective group chemistry using Bayesian optimization and transfer learning

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Substrate specific closed-loop optimization of carbohydrate protective group chemistry using Bayesian optimization and transfer learning. / Faurschou, Natasha Videcrantz; Taaning, Rolf Hejle; Pedersen, Christian Marcus.

I: Chemical Science, Bind 14, Nr. 23, 2023, s. 6319–6329.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Faurschou, NV, Taaning, RH & Pedersen, CM 2023, 'Substrate specific closed-loop optimization of carbohydrate protective group chemistry using Bayesian optimization and transfer learning', Chemical Science, bind 14, nr. 23, s. 6319–6329. https://doi.org/10.1039/D3SC01261A

APA

Faurschou, N. V., Taaning, R. H., & Pedersen, C. M. (2023). Substrate specific closed-loop optimization of carbohydrate protective group chemistry using Bayesian optimization and transfer learning. Chemical Science, 14(23), 6319–6329. https://doi.org/10.1039/D3SC01261A

Vancouver

Faurschou NV, Taaning RH, Pedersen CM. Substrate specific closed-loop optimization of carbohydrate protective group chemistry using Bayesian optimization and transfer learning. Chemical Science. 2023;14(23):6319–6329. https://doi.org/10.1039/D3SC01261A

Author

Faurschou, Natasha Videcrantz ; Taaning, Rolf Hejle ; Pedersen, Christian Marcus. / Substrate specific closed-loop optimization of carbohydrate protective group chemistry using Bayesian optimization and transfer learning. I: Chemical Science. 2023 ; Bind 14, Nr. 23. s. 6319–6329.

Bibtex

@article{4f6c0a2a10d5422096e6dffb0194c939,
title = "Substrate specific closed-loop optimization of carbohydrate protective group chemistry using Bayesian optimization and transfer learning",
abstract = "A new way of performing reaction optimization within carbohydrate chemistry is presented. This is done by performing closed-loop optimization of regioselective benzoylation of unprotected glycosides using Bayesian optimization. Both 6-O-monobenzoylations and 3,6-O-dibenzoylations of three different monosaccharides are optimized. A novel transfer learning approach, where data from previous optimizations of different substrates is used to speed up the optimizations, has also been developed. The optimal conditions found by the Bayesian optimization algorithm provide new insight into substrate specificity, as the conditions found are significantly different. In most cases, the optimal conditions include Et3N and benzoic anhydride, a new reagent combination for these reactions, discovered by the algorithm, demonstrating the power of this concept to widen the chemical space. Further, the developed procedures include ambient conditions and short reaction times.",
author = "Faurschou, {Natasha Videcrantz} and Taaning, {Rolf Hejle} and Pedersen, {Christian Marcus}",
year = "2023",
doi = "10.1039/D3SC01261A",
language = "English",
volume = "14",
pages = "6319–6329",
journal = "Chemical Science",
issn = "2041-6520",
publisher = "Royal Society of Chemistry",
number = "23",

}

RIS

TY - JOUR

T1 - Substrate specific closed-loop optimization of carbohydrate protective group chemistry using Bayesian optimization and transfer learning

AU - Faurschou, Natasha Videcrantz

AU - Taaning, Rolf Hejle

AU - Pedersen, Christian Marcus

PY - 2023

Y1 - 2023

N2 - A new way of performing reaction optimization within carbohydrate chemistry is presented. This is done by performing closed-loop optimization of regioselective benzoylation of unprotected glycosides using Bayesian optimization. Both 6-O-monobenzoylations and 3,6-O-dibenzoylations of three different monosaccharides are optimized. A novel transfer learning approach, where data from previous optimizations of different substrates is used to speed up the optimizations, has also been developed. The optimal conditions found by the Bayesian optimization algorithm provide new insight into substrate specificity, as the conditions found are significantly different. In most cases, the optimal conditions include Et3N and benzoic anhydride, a new reagent combination for these reactions, discovered by the algorithm, demonstrating the power of this concept to widen the chemical space. Further, the developed procedures include ambient conditions and short reaction times.

AB - A new way of performing reaction optimization within carbohydrate chemistry is presented. This is done by performing closed-loop optimization of regioselective benzoylation of unprotected glycosides using Bayesian optimization. Both 6-O-monobenzoylations and 3,6-O-dibenzoylations of three different monosaccharides are optimized. A novel transfer learning approach, where data from previous optimizations of different substrates is used to speed up the optimizations, has also been developed. The optimal conditions found by the Bayesian optimization algorithm provide new insight into substrate specificity, as the conditions found are significantly different. In most cases, the optimal conditions include Et3N and benzoic anhydride, a new reagent combination for these reactions, discovered by the algorithm, demonstrating the power of this concept to widen the chemical space. Further, the developed procedures include ambient conditions and short reaction times.

U2 - 10.1039/D3SC01261A

DO - 10.1039/D3SC01261A

M3 - Journal article

VL - 14

SP - 6319

EP - 6329

JO - Chemical Science

JF - Chemical Science

SN - 2041-6520

IS - 23

ER -

ID: 347977671