Synthetic data generation with probabilistic Bayesian Networks

Bayesian Network (BN) modeling is a prominent and increasingly popular computational systems biology method. It aims to construct network graphs from the large heterogeneous biological datasets that reflect the underlying biological relationships. Currently, a variety of strategies exist for evaluat...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Grigoriy Gogoshin, Sergio Branciamore, Andrei S. Rodin
Formato:	article
Lenguaje:	EN
Publicado:	AIMS Press 2021
Materias:	bayesian networks synthetic data generation directed acyclic graph probabilistic graphical models markov blanket central limit Biotechnology TP248.13-248.65 Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/02b13fa56cb2452892c55bbe03f653a3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:02b13fa56cb2452892c55bbe03f653a3
record_format	dspace
spelling	oai:doaj.org-article:02b13fa56cb2452892c55bbe03f653a32021-11-29T01:23:02ZSynthetic data generation with probabilistic Bayesian Networks10.3934/mbe.20214261551-0018https://doaj.org/article/02b13fa56cb2452892c55bbe03f653a32021-10-01T00:00:00Zhttps://www.aimspress.com/article/doi/10.3934/mbe.2021426?viewType=HTMLhttps://doaj.org/toc/1551-0018Bayesian Network (BN) modeling is a prominent and increasingly popular computational systems biology method. It aims to construct network graphs from the large heterogeneous biological datasets that reflect the underlying biological relationships. Currently, a variety of strategies exist for evaluating BN methodology performance, ranging from utilizing artificial benchmark datasets and models, to specialized biological benchmark datasets, to simulation studies that generate synthetic data from predefined network models. The last is arguably the most comprehensive approach; however, existing implementations often rely on explicit and implicit assumptions that may be unrealistic in a typical biological data analysis scenario, or are poorly equipped for automated arbitrary model generation. In this study, we develop a purely probabilistic simulation framework that addresses the demands of statistically sound simulations studies in an unbiased fashion. Additionally, we expand on our current understanding of the theoretical notions of causality and dependence / conditional independence in BNs and the Markov Blankets within.Grigoriy GogoshinSergio BranciamoreAndrei S. RodinAIMS Pressarticlebayesian networkssynthetic data generationdirected acyclic graphprobabilistic graphical modelsmarkov blanketcentral limitBiotechnologyTP248.13-248.65MathematicsQA1-939ENMathematical Biosciences and Engineering, Vol 18, Iss 6, Pp 8603-8621 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	bayesian networks synthetic data generation directed acyclic graph probabilistic graphical models markov blanket central limit Biotechnology TP248.13-248.65 Mathematics QA1-939
spellingShingle	bayesian networks synthetic data generation directed acyclic graph probabilistic graphical models markov blanket central limit Biotechnology TP248.13-248.65 Mathematics QA1-939 Grigoriy Gogoshin Sergio Branciamore Andrei S. Rodin Synthetic data generation with probabilistic Bayesian Networks
description	Bayesian Network (BN) modeling is a prominent and increasingly popular computational systems biology method. It aims to construct network graphs from the large heterogeneous biological datasets that reflect the underlying biological relationships. Currently, a variety of strategies exist for evaluating BN methodology performance, ranging from utilizing artificial benchmark datasets and models, to specialized biological benchmark datasets, to simulation studies that generate synthetic data from predefined network models. The last is arguably the most comprehensive approach; however, existing implementations often rely on explicit and implicit assumptions that may be unrealistic in a typical biological data analysis scenario, or are poorly equipped for automated arbitrary model generation. In this study, we develop a purely probabilistic simulation framework that addresses the demands of statistically sound simulations studies in an unbiased fashion. Additionally, we expand on our current understanding of the theoretical notions of causality and dependence / conditional independence in BNs and the Markov Blankets within.
format	article
author	Grigoriy Gogoshin Sergio Branciamore Andrei S. Rodin
author_facet	Grigoriy Gogoshin Sergio Branciamore Andrei S. Rodin
author_sort	Grigoriy Gogoshin
title	Synthetic data generation with probabilistic Bayesian Networks
title_short	Synthetic data generation with probabilistic Bayesian Networks
title_full	Synthetic data generation with probabilistic Bayesian Networks
title_fullStr	Synthetic data generation with probabilistic Bayesian Networks
title_full_unstemmed	Synthetic data generation with probabilistic Bayesian Networks
title_sort	synthetic data generation with probabilistic bayesian networks
publisher	AIMS Press
publishDate	2021
url	https://doaj.org/article/02b13fa56cb2452892c55bbe03f653a3
work_keys_str_mv	AT grigoriygogoshin syntheticdatagenerationwithprobabilisticbayesiannetworks AT sergiobranciamore syntheticdatagenerationwithprobabilisticbayesiannetworks AT andreisrodin syntheticdatagenerationwithprobabilisticbayesiannetworks
_version_	1718407626933403648

Synthetic data generation with probabilistic Bayesian Networks

Ejemplares similares