Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates

Organic reactions can readily be learned by deep learning models, however, stereochemistry is still a challenge. Here, the authors fine tune a general model using a small dataset, then predict and validate experimentally regio- and stereo-selectivity for various carbohydrates transformations.

Guardado en:

Detalles Bibliográficos
Autores principales:	Giorgio Pesciullesi, Philippe Schwaller, Teodoro Laino, Jean-Louis Reymond
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/5d394ff268c64ce3b0faabdee491f557
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5d394ff268c64ce3b0faabdee491f557
record_format	dspace
spelling	oai:doaj.org-article:5d394ff268c64ce3b0faabdee491f5572021-12-02T17:27:20ZTransfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates10.1038/s41467-020-18671-72041-1723https://doaj.org/article/5d394ff268c64ce3b0faabdee491f5572020-09-01T00:00:00Zhttps://doi.org/10.1038/s41467-020-18671-7https://doaj.org/toc/2041-1723Organic reactions can readily be learned by deep learning models, however, stereochemistry is still a challenge. Here, the authors fine tune a general model using a small dataset, then predict and validate experimentally regio- and stereo-selectivity for various carbohydrates transformations.Giorgio PesciullesiPhilippe SchwallerTeodoro LainoJean-Louis ReymondNature PortfolioarticleScienceQENNature Communications, Vol 11, Iss 1, Pp 1-8 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Giorgio Pesciullesi Philippe Schwaller Teodoro Laino Jean-Louis Reymond Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates
description	Organic reactions can readily be learned by deep learning models, however, stereochemistry is still a challenge. Here, the authors fine tune a general model using a small dataset, then predict and validate experimentally regio- and stereo-selectivity for various carbohydrates transformations.
format	article
author	Giorgio Pesciullesi Philippe Schwaller Teodoro Laino Jean-Louis Reymond
author_facet	Giorgio Pesciullesi Philippe Schwaller Teodoro Laino Jean-Louis Reymond
author_sort	Giorgio Pesciullesi
title	Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates
title_short	Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates
title_full	Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates
title_fullStr	Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates
title_full_unstemmed	Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates
title_sort	transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/5d394ff268c64ce3b0faabdee491f557
work_keys_str_mv	AT giorgiopesciullesi transferlearningenablesthemoleculartransformertopredictregioandstereoselectivereactionsoncarbohydrates AT philippeschwaller transferlearningenablesthemoleculartransformertopredictregioandstereoselectivereactionsoncarbohydrates AT teodorolaino transferlearningenablesthemoleculartransformertopredictregioandstereoselectivereactionsoncarbohydrates AT jeanlouisreymond transferlearningenablesthemoleculartransformertopredictregioandstereoselectivereactionsoncarbohydrates
_version_	1718380790312599552

Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates

Ejemplares similares