Cargando…

Using graph convolutional neural networks to learn a representation for glycans

As the only nonlinear and the most diverse biological sequence, glycans offer substantial challenges for computational biology. These carbohydrates participate in nearly all biological processes—from protein folding to viral cell entry—yet are still not well understood. There are few computational m...

Descripción completa

Detalles Bibliográficos
Autores principales: Burkholz, Rebekka, Quackenbush, John, Bojar, Daniel
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9208909/
https://www.ncbi.nlm.nih.gov/pubmed/34133929
http://dx.doi.org/10.1016/j.celrep.2021.109251
_version_ 1784729815558914048
author Burkholz, Rebekka
Quackenbush, John
Bojar, Daniel
author_facet Burkholz, Rebekka
Quackenbush, John
Bojar, Daniel
author_sort Burkholz, Rebekka
collection PubMed
description As the only nonlinear and the most diverse biological sequence, glycans offer substantial challenges for computational biology. These carbohydrates participate in nearly all biological processes—from protein folding to viral cell entry—yet are still not well understood. There are few computational methods to link glycan sequences to functions, and they do not fully leverage all available information about glycans. SweetNet is a graph convolutional neural network that uses graph representation learning to facilitate a computational understanding of glycobiology. SweetNet explicitly incorporates the nonlinear nature of glycans and establishes a framework to map any glycan sequence to a representation. We show that SweetNet outperforms other computational methods in predicting glycan properties on all reported tasks. More importantly, we show that glycan representations, learned by SweetNet, are predictive of organismal phenotypic and environmental properties. Finally, we use glycan-focused machine learning to predict viral glycan binding, which can be used to discover viral receptors.
format Online
Article
Text
id pubmed-9208909
institution National Center for Biotechnology Information
language English
publishDate 2021
record_format MEDLINE/PubMed
spelling pubmed-92089092022-06-20 Using graph convolutional neural networks to learn a representation for glycans Burkholz, Rebekka Quackenbush, John Bojar, Daniel Cell Rep Article As the only nonlinear and the most diverse biological sequence, glycans offer substantial challenges for computational biology. These carbohydrates participate in nearly all biological processes—from protein folding to viral cell entry—yet are still not well understood. There are few computational methods to link glycan sequences to functions, and they do not fully leverage all available information about glycans. SweetNet is a graph convolutional neural network that uses graph representation learning to facilitate a computational understanding of glycobiology. SweetNet explicitly incorporates the nonlinear nature of glycans and establishes a framework to map any glycan sequence to a representation. We show that SweetNet outperforms other computational methods in predicting glycan properties on all reported tasks. More importantly, we show that glycan representations, learned by SweetNet, are predictive of organismal phenotypic and environmental properties. Finally, we use glycan-focused machine learning to predict viral glycan binding, which can be used to discover viral receptors. 2021-06-15 /pmc/articles/PMC9208909/ /pubmed/34133929 http://dx.doi.org/10.1016/j.celrep.2021.109251 Text en https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ).
spellingShingle Article
Burkholz, Rebekka
Quackenbush, John
Bojar, Daniel
Using graph convolutional neural networks to learn a representation for glycans
title Using graph convolutional neural networks to learn a representation for glycans
title_full Using graph convolutional neural networks to learn a representation for glycans
title_fullStr Using graph convolutional neural networks to learn a representation for glycans
title_full_unstemmed Using graph convolutional neural networks to learn a representation for glycans
title_short Using graph convolutional neural networks to learn a representation for glycans
title_sort using graph convolutional neural networks to learn a representation for glycans
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9208909/
https://www.ncbi.nlm.nih.gov/pubmed/34133929
http://dx.doi.org/10.1016/j.celrep.2021.109251
work_keys_str_mv AT burkholzrebekka usinggraphconvolutionalneuralnetworkstolearnarepresentationforglycans
AT quackenbushjohn usinggraphconvolutionalneuralnetworkstolearnarepresentationforglycans
AT bojardaniel usinggraphconvolutionalneuralnetworkstolearnarepresentationforglycans