Deep learning allows genome-scale prediction of Michaelis constants from structural features.

The Michaelis constant KM describes the affinity of an enzyme for a specific substrate and is a central parameter in studies of enzyme kinetics and cellular physiology. As measurements of KM are often difficult and time-consuming, experimental estimates exist for only a minority of enzyme-substrate...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Alexander Kroll, Martin K M Engqvist, David Heckmann, Martin J Lercher
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/e744724226e24f99b89ce9de3626d7c7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e744724226e24f99b89ce9de3626d7c7
record_format	dspace
spelling	oai:doaj.org-article:e744724226e24f99b89ce9de3626d7c72021-11-25T05:34:15ZDeep learning allows genome-scale prediction of Michaelis constants from structural features.1544-91731545-788510.1371/journal.pbio.3001402https://doaj.org/article/e744724226e24f99b89ce9de3626d7c72021-10-01T00:00:00Zhttps://doi.org/10.1371/journal.pbio.3001402https://doaj.org/toc/1544-9173https://doaj.org/toc/1545-7885The Michaelis constant KM describes the affinity of an enzyme for a specific substrate and is a central parameter in studies of enzyme kinetics and cellular physiology. As measurements of KM are often difficult and time-consuming, experimental estimates exist for only a minority of enzyme-substrate combinations even in model organisms. Here, we build and train an organism-independent model that successfully predicts KM values for natural enzyme-substrate combinations using machine and deep learning methods. Predictions are based on a task-specific molecular fingerprint of the substrate, generated using a graph neural network, and on a deep numerical representation of the enzyme's amino acid sequence. We provide genome-scale KM predictions for 47 model organisms, which can be used to approximately relate metabolite concentrations to cellular physiology and to aid in the parameterization of kinetic models of cellular metabolism.Alexander KrollMartin K M EngqvistDavid HeckmannMartin J LercherPublic Library of Science (PLoS)articleBiology (General)QH301-705.5ENPLoS Biology, Vol 19, Iss 10, p e3001402 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Biology (General) QH301-705.5
spellingShingle	Biology (General) QH301-705.5 Alexander Kroll Martin K M Engqvist David Heckmann Martin J Lercher Deep learning allows genome-scale prediction of Michaelis constants from structural features.
description	The Michaelis constant KM describes the affinity of an enzyme for a specific substrate and is a central parameter in studies of enzyme kinetics and cellular physiology. As measurements of KM are often difficult and time-consuming, experimental estimates exist for only a minority of enzyme-substrate combinations even in model organisms. Here, we build and train an organism-independent model that successfully predicts KM values for natural enzyme-substrate combinations using machine and deep learning methods. Predictions are based on a task-specific molecular fingerprint of the substrate, generated using a graph neural network, and on a deep numerical representation of the enzyme's amino acid sequence. We provide genome-scale KM predictions for 47 model organisms, which can be used to approximately relate metabolite concentrations to cellular physiology and to aid in the parameterization of kinetic models of cellular metabolism.
format	article
author	Alexander Kroll Martin K M Engqvist David Heckmann Martin J Lercher
author_facet	Alexander Kroll Martin K M Engqvist David Heckmann Martin J Lercher
author_sort	Alexander Kroll
title	Deep learning allows genome-scale prediction of Michaelis constants from structural features.
title_short	Deep learning allows genome-scale prediction of Michaelis constants from structural features.
title_full	Deep learning allows genome-scale prediction of Michaelis constants from structural features.
title_fullStr	Deep learning allows genome-scale prediction of Michaelis constants from structural features.
title_full_unstemmed	Deep learning allows genome-scale prediction of Michaelis constants from structural features.
title_sort	deep learning allows genome-scale prediction of michaelis constants from structural features.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/e744724226e24f99b89ce9de3626d7c7
work_keys_str_mv	AT alexanderkroll deeplearningallowsgenomescalepredictionofmichaelisconstantsfromstructuralfeatures AT martinkmengqvist deeplearningallowsgenomescalepredictionofmichaelisconstantsfromstructuralfeatures AT davidheckmann deeplearningallowsgenomescalepredictionofmichaelisconstantsfromstructuralfeatures AT martinjlercher deeplearningallowsgenomescalepredictionofmichaelisconstantsfromstructuralfeatures
_version_	1718414611670106112

Deep learning allows genome-scale prediction of Michaelis constants from structural features.

Ejemplares similares