Towards perturbation prediction of biological networks using deep learning

Abstract The mapping of the physical interactions between biochemical entities enables quantitative analysis of dynamic biological living systems. While developing a precise dynamical model on biological entity interaction is still challenging due to the limitation of kinetic parameter detection of...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Diya Li, Jianxi Gao
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2019
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/2276c93b000442c8a1ca26ef5fa7ff00
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2276c93b000442c8a1ca26ef5fa7ff00
record_format	dspace
spelling	oai:doaj.org-article:2276c93b000442c8a1ca26ef5fa7ff002021-12-02T15:09:53ZTowards perturbation prediction of biological networks using deep learning10.1038/s41598-019-48391-y2045-2322https://doaj.org/article/2276c93b000442c8a1ca26ef5fa7ff002019-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-019-48391-yhttps://doaj.org/toc/2045-2322Abstract The mapping of the physical interactions between biochemical entities enables quantitative analysis of dynamic biological living systems. While developing a precise dynamical model on biological entity interaction is still challenging due to the limitation of kinetic parameter detection of the underlying biological system. This challenge promotes the needs of topology-based models to predict biochemical perturbation patterns. Pure topology-based model, however, is limited on the scale and heterogeneity of biological networks. Here we propose a learning based model that adopts graph convolutional networks to learn the implicit perturbation pattern factors and thus enhance the perturbation pattern prediction on the basic topology model. Our experimental studies on 87 biological models show an average of 73% accuracy on perturbation pattern prediction and outperforms the best topology-based model by 7%, indicating that the graph-driven neural network model is robust and beneficial for accurate prediction of the perturbation spread modeling and giving an inspiration of the implementation of the deep neural networks on biological network modeling.Diya LiJianxi GaoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 9, Iss 1, Pp 1-9 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Diya Li Jianxi Gao Towards perturbation prediction of biological networks using deep learning
description	Abstract The mapping of the physical interactions between biochemical entities enables quantitative analysis of dynamic biological living systems. While developing a precise dynamical model on biological entity interaction is still challenging due to the limitation of kinetic parameter detection of the underlying biological system. This challenge promotes the needs of topology-based models to predict biochemical perturbation patterns. Pure topology-based model, however, is limited on the scale and heterogeneity of biological networks. Here we propose a learning based model that adopts graph convolutional networks to learn the implicit perturbation pattern factors and thus enhance the perturbation pattern prediction on the basic topology model. Our experimental studies on 87 biological models show an average of 73% accuracy on perturbation pattern prediction and outperforms the best topology-based model by 7%, indicating that the graph-driven neural network model is robust and beneficial for accurate prediction of the perturbation spread modeling and giving an inspiration of the implementation of the deep neural networks on biological network modeling.
format	article
author	Diya Li Jianxi Gao
author_facet	Diya Li Jianxi Gao
author_sort	Diya Li
title	Towards perturbation prediction of biological networks using deep learning
title_short	Towards perturbation prediction of biological networks using deep learning
title_full	Towards perturbation prediction of biological networks using deep learning
title_fullStr	Towards perturbation prediction of biological networks using deep learning
title_full_unstemmed	Towards perturbation prediction of biological networks using deep learning
title_sort	towards perturbation prediction of biological networks using deep learning
publisher	Nature Portfolio
publishDate	2019
url	https://doaj.org/article/2276c93b000442c8a1ca26ef5fa7ff00
work_keys_str_mv	AT diyali towardsperturbationpredictionofbiologicalnetworksusingdeeplearning AT jianxigao towardsperturbationpredictionofbiologicalnetworksusingdeeplearning
_version_	1718387739669299200

Towards perturbation prediction of biological networks using deep learning

Ejemplares similares