Node-Structured Integrative Gaussian Graphical Model Guided by Pathway Information

Sung Hwan Kim, Jae Hwan Jhong, Jung Jun Lee, Ja Yong Koo, Byung Yong Lee, Sung Won Han

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Up to date, many biological pathways related to cancer have been extensively applied thanks to outputs of burgeoning biomedical research. This leads to a new technical challenge of exploring and validating biological pathways that can characterize transcriptomic mechanisms across different disease subtypes. In pursuit of accommodating multiple studies, the joint Gaussian graphical model was previously proposed to incorporate nonzero edge effects. However, this model is inevitably dependent on post hoc analysis in order to confirm biological significance. To circumvent this drawback, we attempt not only to combine transcriptomic data but also to embed pathway information, well-ascertained biological evidence as such, into the model. To this end, we propose a novel statistical framework for fitting joint Gaussian graphical model simultaneously with informative pathways consistently expressed across multiple studies. In theory, structured nodes can be prespecified with multiple genes. The optimization rule employs the structured input-output lasso model, in order to estimate a sparse precision matrix constructed by simultaneous effects of multiple studies and structured nodes. With an application to breast cancer data sets, we found that the proposed model is superior in efficiently capturing structures of biological evidence (e.g., pathways). An R software package nsiGGM is publicly available at author's webpage.

Original languageEnglish
Article number8520480
JournalComputational and Mathematical Methods in Medicine
Volume2017
DOIs
Publication statusPublished - 2017 Jan 1

Fingerprint

Gaussian Model
Graphical Models
Pathway
Joints
Vertex of a graph
Biomedical Research
Software
Breast Neoplasms
Edge Effects
Lasso
Genes
Output
Pursuit
Neoplasms
Breast Cancer
Software Package
Model
Cancer
Software packages
Gene

ASJC Scopus subject areas

  • Modelling and Simulation
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Applied Mathematics

Cite this

Node-Structured Integrative Gaussian Graphical Model Guided by Pathway Information. / Kim, Sung Hwan; Jhong, Jae Hwan; Lee, Jung Jun; Koo, Ja Yong; Lee, Byung Yong; Han, Sung Won.

In: Computational and Mathematical Methods in Medicine, Vol. 2017, 8520480, 01.01.2017.

Research output: Contribution to journalArticle

Kim, Sung Hwan ; Jhong, Jae Hwan ; Lee, Jung Jun ; Koo, Ja Yong ; Lee, Byung Yong ; Han, Sung Won. / Node-Structured Integrative Gaussian Graphical Model Guided by Pathway Information. In: Computational and Mathematical Methods in Medicine. 2017 ; Vol. 2017.
@article{444be8aaa6664ede90b1e85a974aca48,
title = "Node-Structured Integrative Gaussian Graphical Model Guided by Pathway Information",
abstract = "Up to date, many biological pathways related to cancer have been extensively applied thanks to outputs of burgeoning biomedical research. This leads to a new technical challenge of exploring and validating biological pathways that can characterize transcriptomic mechanisms across different disease subtypes. In pursuit of accommodating multiple studies, the joint Gaussian graphical model was previously proposed to incorporate nonzero edge effects. However, this model is inevitably dependent on post hoc analysis in order to confirm biological significance. To circumvent this drawback, we attempt not only to combine transcriptomic data but also to embed pathway information, well-ascertained biological evidence as such, into the model. To this end, we propose a novel statistical framework for fitting joint Gaussian graphical model simultaneously with informative pathways consistently expressed across multiple studies. In theory, structured nodes can be prespecified with multiple genes. The optimization rule employs the structured input-output lasso model, in order to estimate a sparse precision matrix constructed by simultaneous effects of multiple studies and structured nodes. With an application to breast cancer data sets, we found that the proposed model is superior in efficiently capturing structures of biological evidence (e.g., pathways). An R software package nsiGGM is publicly available at author's webpage.",
author = "Kim, {Sung Hwan} and Jhong, {Jae Hwan} and Lee, {Jung Jun} and Koo, {Ja Yong} and Lee, {Byung Yong} and Han, {Sung Won}",
year = "2017",
month = "1",
day = "1",
doi = "10.1155/2017/8520480",
language = "English",
volume = "2017",
journal = "Computational and Mathematical Methods in Medicine",
issn = "1748-670X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Node-Structured Integrative Gaussian Graphical Model Guided by Pathway Information

AU - Kim, Sung Hwan

AU - Jhong, Jae Hwan

AU - Lee, Jung Jun

AU - Koo, Ja Yong

AU - Lee, Byung Yong

AU - Han, Sung Won

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Up to date, many biological pathways related to cancer have been extensively applied thanks to outputs of burgeoning biomedical research. This leads to a new technical challenge of exploring and validating biological pathways that can characterize transcriptomic mechanisms across different disease subtypes. In pursuit of accommodating multiple studies, the joint Gaussian graphical model was previously proposed to incorporate nonzero edge effects. However, this model is inevitably dependent on post hoc analysis in order to confirm biological significance. To circumvent this drawback, we attempt not only to combine transcriptomic data but also to embed pathway information, well-ascertained biological evidence as such, into the model. To this end, we propose a novel statistical framework for fitting joint Gaussian graphical model simultaneously with informative pathways consistently expressed across multiple studies. In theory, structured nodes can be prespecified with multiple genes. The optimization rule employs the structured input-output lasso model, in order to estimate a sparse precision matrix constructed by simultaneous effects of multiple studies and structured nodes. With an application to breast cancer data sets, we found that the proposed model is superior in efficiently capturing structures of biological evidence (e.g., pathways). An R software package nsiGGM is publicly available at author's webpage.

AB - Up to date, many biological pathways related to cancer have been extensively applied thanks to outputs of burgeoning biomedical research. This leads to a new technical challenge of exploring and validating biological pathways that can characterize transcriptomic mechanisms across different disease subtypes. In pursuit of accommodating multiple studies, the joint Gaussian graphical model was previously proposed to incorporate nonzero edge effects. However, this model is inevitably dependent on post hoc analysis in order to confirm biological significance. To circumvent this drawback, we attempt not only to combine transcriptomic data but also to embed pathway information, well-ascertained biological evidence as such, into the model. To this end, we propose a novel statistical framework for fitting joint Gaussian graphical model simultaneously with informative pathways consistently expressed across multiple studies. In theory, structured nodes can be prespecified with multiple genes. The optimization rule employs the structured input-output lasso model, in order to estimate a sparse precision matrix constructed by simultaneous effects of multiple studies and structured nodes. With an application to breast cancer data sets, we found that the proposed model is superior in efficiently capturing structures of biological evidence (e.g., pathways). An R software package nsiGGM is publicly available at author's webpage.

UR - http://www.scopus.com/inward/record.url?scp=85018822947&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018822947&partnerID=8YFLogxK

U2 - 10.1155/2017/8520480

DO - 10.1155/2017/8520480

M3 - Article

C2 - 28487748

AN - SCOPUS:85018822947

VL - 2017

JO - Computational and Mathematical Methods in Medicine

JF - Computational and Mathematical Methods in Medicine

SN - 1748-670X

M1 - 8520480

ER -