Deep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space

Abstract GPCR proteins belong to diverse families of proteins that are defined at multiple hierarchical levels. Inspecting relationships between GPCR proteins on the hierarchical structure is important, since characteristics of the protein can be inferred from proteins in similar hierarchical inform...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Taeheon Lee, Sangseon Lee, Minji Kang, Sun Kim
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/84143de8168042d6864cb0ea665b6216
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:84143de8168042d6864cb0ea665b6216
record_format	dspace
spelling	oai:doaj.org-article:84143de8168042d6864cb0ea665b62162021-12-02T16:49:12ZDeep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space10.1038/s41598-021-88623-82045-2322https://doaj.org/article/84143de8168042d6864cb0ea665b62162021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88623-8https://doaj.org/toc/2045-2322Abstract GPCR proteins belong to diverse families of proteins that are defined at multiple hierarchical levels. Inspecting relationships between GPCR proteins on the hierarchical structure is important, since characteristics of the protein can be inferred from proteins in similar hierarchical information. However, modeling of GPCR families has been performed separately for each of the family, subfamily, and sub-subfamily level. Relationships between GPCR proteins are ignored in these approaches as they process the information in the proteins with several disconnected models. In this study, we propose DeepHier, a deep learning model to simultaneously learn representations of GPCR family hierarchy from the protein sequences with a unified single model. Novel loss term based on metric learning is introduced to incorporate hierarchical relations between proteins. We tested our approach using a public GPCR sequence dataset. Metric distances in the deep feature space corresponded to the hierarchical family relation between GPCR proteins. Furthermore, we demonstrated that further downstream tasks, like phylogenetic reconstruction and motif discovery, are feasible in the constructed embedding space. These results show that hierarchical relations between sequences were successfully captured in both of technical and biological aspects.Taeheon LeeSangseon LeeMinji KangSun KimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Taeheon Lee Sangseon Lee Minji Kang Sun Kim Deep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space
description	Abstract GPCR proteins belong to diverse families of proteins that are defined at multiple hierarchical levels. Inspecting relationships between GPCR proteins on the hierarchical structure is important, since characteristics of the protein can be inferred from proteins in similar hierarchical information. However, modeling of GPCR families has been performed separately for each of the family, subfamily, and sub-subfamily level. Relationships between GPCR proteins are ignored in these approaches as they process the information in the proteins with several disconnected models. In this study, we propose DeepHier, a deep learning model to simultaneously learn representations of GPCR family hierarchy from the protein sequences with a unified single model. Novel loss term based on metric learning is introduced to incorporate hierarchical relations between proteins. We tested our approach using a public GPCR sequence dataset. Metric distances in the deep feature space corresponded to the hierarchical family relation between GPCR proteins. Furthermore, we demonstrated that further downstream tasks, like phylogenetic reconstruction and motif discovery, are feasible in the constructed embedding space. These results show that hierarchical relations between sequences were successfully captured in both of technical and biological aspects.
format	article
author	Taeheon Lee Sangseon Lee Minji Kang Sun Kim
author_facet	Taeheon Lee Sangseon Lee Minji Kang Sun Kim
author_sort	Taeheon Lee
title	Deep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space
title_short	Deep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space
title_full	Deep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space
title_fullStr	Deep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space
title_full_unstemmed	Deep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space
title_sort	deep hierarchical embedding for simultaneous modeling of gpcr proteins in a unified metric space
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/84143de8168042d6864cb0ea665b6216
work_keys_str_mv	AT taeheonlee deephierarchicalembeddingforsimultaneousmodelingofgpcrproteinsinaunifiedmetricspace AT sangseonlee deephierarchicalembeddingforsimultaneousmodelingofgpcrproteinsinaunifiedmetricspace AT minjikang deephierarchicalembeddingforsimultaneousmodelingofgpcrproteinsinaunifiedmetricspace AT sunkim deephierarchicalembeddingforsimultaneousmodelingofgpcrproteinsinaunifiedmetricspace
_version_	1718383406354530304

Deep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space

Ejemplares similares