Cargando…

Harnessing the potential of artificial neural networks for predicting protein glycosylation

Kinetic models offer incomparable insight on cellular mechanisms controlling protein glycosylation. However, their ability to reproduce site-specific glycoform distributions depends on accurate estimation of a large number of protein-specific kinetic parameters and prior knowledge of enzyme and tran...

Descripción completa

Detalles Bibliográficos
Autores principales: Kotidis, Pavlos, Kontoravdi, Cleo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7256630/
https://www.ncbi.nlm.nih.gov/pubmed/32489858
http://dx.doi.org/10.1016/j.mec.2020.e00131
_version_ 1783539954137169920
author Kotidis, Pavlos
Kontoravdi, Cleo
author_facet Kotidis, Pavlos
Kontoravdi, Cleo
author_sort Kotidis, Pavlos
collection PubMed
description Kinetic models offer incomparable insight on cellular mechanisms controlling protein glycosylation. However, their ability to reproduce site-specific glycoform distributions depends on accurate estimation of a large number of protein-specific kinetic parameters and prior knowledge of enzyme and transport protein levels in the Golgi membrane. Herein we propose an artificial neural network (ANN) for protein glycosylation and apply this to four recombinant glycoproteins produced in Chinese hamster ovary (CHO) cells, two monoclonal antibodies and two fusion proteins. We demonstrate that the ANN model accurately predicts site-specific glycoform distributions of up to eighteen glycan species with an average absolute error of 1.1%, correctly reproducing the effect of metabolic perturbations as part of a hybrid, kinetic/ANN, glycosylation model (HyGlycoM), as well as the impact of manganese supplementation and glycosyltransferase knock out experiments as a stand-alone machine learning algorithm. These results showcase the potential of machine learning and hybrid approaches for rapidly developing performance-driven models of protein glycosylation.
format Online
Article
Text
id pubmed-7256630
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-72566302020-06-01 Harnessing the potential of artificial neural networks for predicting protein glycosylation Kotidis, Pavlos Kontoravdi, Cleo Metab Eng Commun Full Length Article Kinetic models offer incomparable insight on cellular mechanisms controlling protein glycosylation. However, their ability to reproduce site-specific glycoform distributions depends on accurate estimation of a large number of protein-specific kinetic parameters and prior knowledge of enzyme and transport protein levels in the Golgi membrane. Herein we propose an artificial neural network (ANN) for protein glycosylation and apply this to four recombinant glycoproteins produced in Chinese hamster ovary (CHO) cells, two monoclonal antibodies and two fusion proteins. We demonstrate that the ANN model accurately predicts site-specific glycoform distributions of up to eighteen glycan species with an average absolute error of 1.1%, correctly reproducing the effect of metabolic perturbations as part of a hybrid, kinetic/ANN, glycosylation model (HyGlycoM), as well as the impact of manganese supplementation and glycosyltransferase knock out experiments as a stand-alone machine learning algorithm. These results showcase the potential of machine learning and hybrid approaches for rapidly developing performance-driven models of protein glycosylation. Elsevier 2020-05-15 /pmc/articles/PMC7256630/ /pubmed/32489858 http://dx.doi.org/10.1016/j.mec.2020.e00131 Text en © 2020 The Authors http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Full Length Article
Kotidis, Pavlos
Kontoravdi, Cleo
Harnessing the potential of artificial neural networks for predicting protein glycosylation
title Harnessing the potential of artificial neural networks for predicting protein glycosylation
title_full Harnessing the potential of artificial neural networks for predicting protein glycosylation
title_fullStr Harnessing the potential of artificial neural networks for predicting protein glycosylation
title_full_unstemmed Harnessing the potential of artificial neural networks for predicting protein glycosylation
title_short Harnessing the potential of artificial neural networks for predicting protein glycosylation
title_sort harnessing the potential of artificial neural networks for predicting protein glycosylation
topic Full Length Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7256630/
https://www.ncbi.nlm.nih.gov/pubmed/32489858
http://dx.doi.org/10.1016/j.mec.2020.e00131
work_keys_str_mv AT kotidispavlos harnessingthepotentialofartificialneuralnetworksforpredictingproteinglycosylation
AT kontoravdicleo harnessingthepotentialofartificialneuralnetworksforpredictingproteinglycosylation