MethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks

Abstract DNA methylation (DNAm) alterations have been heavily implicated in carcinogenesis and the pathophysiology of diseases through upstream regulation of gene expression. DNAm deep-learning approaches are able to capture features associated with aging, cell type, and disease progression, but lac...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Joshua J. Levy, Youdinghuan Chen, Nasim Azizgolshani, Curtis L. Petersen, Alexander J. Titus, Erika L. Moen, Louis J. Vaickus, Lucas A. Salas, Brock C. Christensen
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/4f32c8343c1846d98fa3b43cf8e3aca6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4f32c8343c1846d98fa3b43cf8e3aca6
record_format	dspace
spelling	oai:doaj.org-article:4f32c8343c1846d98fa3b43cf8e3aca62021-12-02T17:08:35ZMethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks10.1038/s41540-021-00193-72056-7189https://doaj.org/article/4f32c8343c1846d98fa3b43cf8e3aca62021-08-01T00:00:00Zhttps://doi.org/10.1038/s41540-021-00193-7https://doaj.org/toc/2056-7189Abstract DNA methylation (DNAm) alterations have been heavily implicated in carcinogenesis and the pathophysiology of diseases through upstream regulation of gene expression. DNAm deep-learning approaches are able to capture features associated with aging, cell type, and disease progression, but lack incorporation of prior biological knowledge. Here, we present modular, user-friendly deep-learning methodology and software, MethylCapsNet and MethylSPWNet, that group CpGs into biologically relevant capsules—such as gene promoter context, CpG island relationship, or user-defined groupings—and relate them to diagnostic and prognostic outcomes. We demonstrate these models’ utility on 3,897 individuals in the classification of central nervous system (CNS) tumors. MethylCapsNet and MethylSPWNet provide an opportunity to increase DNAm deep-learning analyses’ interpretability by enabling a flexible organization of DNAm data into biologically relevant capsules.Joshua J. LevyYoudinghuan ChenNasim AzizgolshaniCurtis L. PetersenAlexander J. TitusErika L. MoenLouis J. VaickusLucas A. SalasBrock C. ChristensenNature PortfolioarticleBiology (General)QH301-705.5ENnpj Systems Biology and Applications, Vol 7, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Biology (General) QH301-705.5
spellingShingle	Biology (General) QH301-705.5 Joshua J. Levy Youdinghuan Chen Nasim Azizgolshani Curtis L. Petersen Alexander J. Titus Erika L. Moen Louis J. Vaickus Lucas A. Salas Brock C. Christensen MethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks
description	Abstract DNA methylation (DNAm) alterations have been heavily implicated in carcinogenesis and the pathophysiology of diseases through upstream regulation of gene expression. DNAm deep-learning approaches are able to capture features associated with aging, cell type, and disease progression, but lack incorporation of prior biological knowledge. Here, we present modular, user-friendly deep-learning methodology and software, MethylCapsNet and MethylSPWNet, that group CpGs into biologically relevant capsules—such as gene promoter context, CpG island relationship, or user-defined groupings—and relate them to diagnostic and prognostic outcomes. We demonstrate these models’ utility on 3,897 individuals in the classification of central nervous system (CNS) tumors. MethylCapsNet and MethylSPWNet provide an opportunity to increase DNAm deep-learning analyses’ interpretability by enabling a flexible organization of DNAm data into biologically relevant capsules.
format	article
author	Joshua J. Levy Youdinghuan Chen Nasim Azizgolshani Curtis L. Petersen Alexander J. Titus Erika L. Moen Louis J. Vaickus Lucas A. Salas Brock C. Christensen
author_facet	Joshua J. Levy Youdinghuan Chen Nasim Azizgolshani Curtis L. Petersen Alexander J. Titus Erika L. Moen Louis J. Vaickus Lucas A. Salas Brock C. Christensen
author_sort	Joshua J. Levy
title	MethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks
title_short	MethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks
title_full	MethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks
title_fullStr	MethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks
title_full_unstemmed	MethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks
title_sort	methylspwnet and methylcapsnet: biologically motivated organization of dnam neural networks, inspired by capsule networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/4f32c8343c1846d98fa3b43cf8e3aca6
work_keys_str_mv	AT joshuajlevy methylspwnetandmethylcapsnetbiologicallymotivatedorganizationofdnamneuralnetworksinspiredbycapsulenetworks AT youdinghuanchen methylspwnetandmethylcapsnetbiologicallymotivatedorganizationofdnamneuralnetworksinspiredbycapsulenetworks AT nasimazizgolshani methylspwnetandmethylcapsnetbiologicallymotivatedorganizationofdnamneuralnetworksinspiredbycapsulenetworks AT curtislpetersen methylspwnetandmethylcapsnetbiologicallymotivatedorganizationofdnamneuralnetworksinspiredbycapsulenetworks AT alexanderjtitus methylspwnetandmethylcapsnetbiologicallymotivatedorganizationofdnamneuralnetworksinspiredbycapsulenetworks AT erikalmoen methylspwnetandmethylcapsnetbiologicallymotivatedorganizationofdnamneuralnetworksinspiredbycapsulenetworks AT louisjvaickus methylspwnetandmethylcapsnetbiologicallymotivatedorganizationofdnamneuralnetworksinspiredbycapsulenetworks AT lucasasalas methylspwnetandmethylcapsnetbiologicallymotivatedorganizationofdnamneuralnetworksinspiredbycapsulenetworks AT brockcchristensen methylspwnetandmethylcapsnetbiologicallymotivatedorganizationofdnamneuralnetworksinspiredbycapsulenetworks
_version_	1718381549953482752

MethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks

Ejemplares similares