Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models

Experimental data on enzyme turnover numbers is sparse and noisy. Here, the authors use machine learning to successfully predict enzyme turnover numbers for E. coli, and show that using these to parameterize mechanistic genome-scale models enhances their predictive accuracy.

Bibliographic Details
Main Authors:	David Heckmann, Colton J. Lloyd, Nathan Mih, Yuanchi Ha, Daniel C. Zielinski, Zachary B. Haiman, Abdelmoneim Amer Desouki, Martin J. Lercher, Bernhard O. Palsson
Format:	Article
Language:	English
Published:	Nature Publishing Group 2018-12-01
Series:	Nature Communications
Online Access:	https://doi.org/10.1038/s41467-018-07652-6

id	doaj-4253a943492247b28ad5cd46f32d93b3
record_format	Article
spelling	doaj-4253a943492247b28ad5cd46f32d93b32021-05-11T10:24:26ZengNature Publishing GroupNature Communications2041-17232018-12-019111010.1038/s41467-018-07652-6Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic modelsDavid Heckmann0Colton J. Lloyd1Nathan Mih2Yuanchi Ha3Daniel C. Zielinski4Zachary B. Haiman5Abdelmoneim Amer Desouki6Martin J. Lercher7Bernhard O. Palsson8Department of Bioengineering, University of California, San DiegoDepartment of Bioengineering, University of California, San DiegoDepartment of Bioengineering, University of California, San DiegoDepartment of Bioengineering, University of California, San DiegoDepartment of Bioengineering, University of California, San DiegoDepartment of Bioengineering, University of California, San DiegoInstitute for Computer Science and Department of Biology, Heinrich Heine UniversityInstitute for Computer Science and Department of Biology, Heinrich Heine UniversityDepartment of Bioengineering, University of California, San DiegoExperimental data on enzyme turnover numbers is sparse and noisy. Here, the authors use machine learning to successfully predict enzyme turnover numbers for E. coli, and show that using these to parameterize mechanistic genome-scale models enhances their predictive accuracy.https://doi.org/10.1038/s41467-018-07652-6
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	David Heckmann Colton J. Lloyd Nathan Mih Yuanchi Ha Daniel C. Zielinski Zachary B. Haiman Abdelmoneim Amer Desouki Martin J. Lercher Bernhard O. Palsson
spellingShingle	David Heckmann Colton J. Lloyd Nathan Mih Yuanchi Ha Daniel C. Zielinski Zachary B. Haiman Abdelmoneim Amer Desouki Martin J. Lercher Bernhard O. Palsson Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models Nature Communications
author_facet	David Heckmann Colton J. Lloyd Nathan Mih Yuanchi Ha Daniel C. Zielinski Zachary B. Haiman Abdelmoneim Amer Desouki Martin J. Lercher Bernhard O. Palsson
author_sort	David Heckmann
title	Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models
title_short	Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models
title_full	Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models
title_fullStr	Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models
title_full_unstemmed	Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models
title_sort	machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models
publisher	Nature Publishing Group
series	Nature Communications
issn	2041-1723
publishDate	2018-12-01
description	Experimental data on enzyme turnover numbers is sparse and noisy. Here, the authors use machine learning to successfully predict enzyme turnover numbers for E. coli, and show that using these to parameterize mechanistic genome-scale models enhances their predictive accuracy.
url	https://doi.org/10.1038/s41467-018-07652-6
work_keys_str_mv	AT davidheckmann machinelearningappliedtoenzymeturnovernumbersrevealsproteinstructuralcorrelatesandimprovesmetabolicmodels AT coltonjlloyd machinelearningappliedtoenzymeturnovernumbersrevealsproteinstructuralcorrelatesandimprovesmetabolicmodels AT nathanmih machinelearningappliedtoenzymeturnovernumbersrevealsproteinstructuralcorrelatesandimprovesmetabolicmodels AT yuanchiha machinelearningappliedtoenzymeturnovernumbersrevealsproteinstructuralcorrelatesandimprovesmetabolicmodels AT danielczielinski machinelearningappliedtoenzymeturnovernumbersrevealsproteinstructuralcorrelatesandimprovesmetabolicmodels AT zacharybhaiman machinelearningappliedtoenzymeturnovernumbersrevealsproteinstructuralcorrelatesandimprovesmetabolicmodels AT abdelmoneimamerdesouki machinelearningappliedtoenzymeturnovernumbersrevealsproteinstructuralcorrelatesandimprovesmetabolicmodels AT martinjlercher machinelearningappliedtoenzymeturnovernumbersrevealsproteinstructuralcorrelatesandimprovesmetabolicmodels AT bernhardopalsson machinelearningappliedtoenzymeturnovernumbersrevealsproteinstructuralcorrelatesandimprovesmetabolicmodels
_version_	1721448266834378752

Machine learning applied to enzyme turnover numbers reveals protein structural correlates and improves metabolic models

Similar Items