Ultra-high dimensional variable selection with application to normative aging study: DNA methylation and metabolic syndrome

Grace Yoon; Yinan Zheng; Zhou Zhang; Haixiang Zhang; Tao Gao; Brian Joyce; Wei Zhang; Weihua Guan; Andrea A. Baccarelli; Wenxin Jiang; Joel Schwartz; Pantel S. Vokonas; Lifang Hou; Lei Liu

doi:10.1186/s12859-017-1568-1

Ultra-high dimensional variable selection with application to normative aging study: DNA methylation and metabolic syndrome

Grace Yoon, Yinan Zheng, Zhou Zhang, Haixiang Zhang, Tao Gao, Brian Joyce, Wei Zhang, Weihua Guan, Andrea A. Baccarelli, Wenxin Jiang, Joel Schwartz, Pantel S. Vokonas, Lifang Hou, Lei Liu

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

Background: Metabolic syndrome has become a major public health challenge worldwide. The association between metabolic syndrome and DNA methylation is of great research interest. Results: We constructed a binomial model to investigate the association between a metabolic syndrome index and DNA methylation in the Normative Aging Study. We applied the Iterative Sure Independence Screening (ISIS) method with elastic net penalty to DNA methylation levels at 484,548 CpG markers from 659 human subjects, and demonstrated that the screening step in ISIS can significantly improve the performance of the elastic net. Conclusion: The proposed method identifies four CpGs which can be mapped to two biologically relevant and functional genes. Identification of significant CpG markers may potentially have practical implications for disease prevention and treatment.

Original language	English
Article number	156
Journal	BMC bioinformatics
Volume	18
Issue number	1
DOIs	https://doi.org/10.1186/s12859-017-1568-1
State	Published - Mar 7 2017

Keywords

Bootstrap
Elastic net
ISIS
Metabolic syndrome
Methylation
Ultra-high dimensional variable selection

Access to Document

10.1186/s12859-017-1568-1

Cite this

Yoon, G., Zheng, Y., Zhang, Z., Zhang, H., Gao, T., Joyce, B., Zhang, W., Guan, W., Baccarelli, A. A., Jiang, W., Schwartz, J., Vokonas, P. S., Hou, L., & Liu, L. (2017). Ultra-high dimensional variable selection with application to normative aging study: DNA methylation and metabolic syndrome. BMC bioinformatics, 18(1), Article 156. https://doi.org/10.1186/s12859-017-1568-1

@article{ae8b725ad84341d99673acb4ab555a43,

title = "Ultra-high dimensional variable selection with application to normative aging study: DNA methylation and metabolic syndrome",

abstract = "Background: Metabolic syndrome has become a major public health challenge worldwide. The association between metabolic syndrome and DNA methylation is of great research interest. Results: We constructed a binomial model to investigate the association between a metabolic syndrome index and DNA methylation in the Normative Aging Study. We applied the Iterative Sure Independence Screening (ISIS) method with elastic net penalty to DNA methylation levels at 484,548 CpG markers from 659 human subjects, and demonstrated that the screening step in ISIS can significantly improve the performance of the elastic net. Conclusion: The proposed method identifies four CpGs which can be mapped to two biologically relevant and functional genes. Identification of significant CpG markers may potentially have practical implications for disease prevention and treatment.",

keywords = "Bootstrap, Elastic net, ISIS, Metabolic syndrome, Methylation, Ultra-high dimensional variable selection",

author = "Grace Yoon and Yinan Zheng and Zhou Zhang and Haixiang Zhang and Tao Gao and Brian Joyce and Wei Zhang and Weihua Guan and Baccarelli, {Andrea A.} and Wenxin Jiang and Joel Schwartz and Vokonas, {Pantel S.} and Lifang Hou and Lei Liu",

note = "Publisher Copyright: {\textcopyright} 2017 The Author(s).",

year = "2017",

month = mar,

day = "7",

doi = "10.1186/s12859-017-1568-1",

language = "English",

volume = "18",

journal = "BMC bioinformatics",

issn = "1471-2105",

number = "1",

}

TY - JOUR

T1 - Ultra-high dimensional variable selection with application to normative aging study

T2 - DNA methylation and metabolic syndrome

AU - Yoon, Grace

AU - Zheng, Yinan

AU - Zhang, Zhou

AU - Zhang, Haixiang

AU - Gao, Tao

AU - Joyce, Brian

AU - Zhang, Wei

AU - Guan, Weihua

AU - Baccarelli, Andrea A.

AU - Jiang, Wenxin

AU - Schwartz, Joel

AU - Vokonas, Pantel S.

AU - Hou, Lifang

AU - Liu, Lei

PY - 2017/3/7

Y1 - 2017/3/7

N2 - Background: Metabolic syndrome has become a major public health challenge worldwide. The association between metabolic syndrome and DNA methylation is of great research interest. Results: We constructed a binomial model to investigate the association between a metabolic syndrome index and DNA methylation in the Normative Aging Study. We applied the Iterative Sure Independence Screening (ISIS) method with elastic net penalty to DNA methylation levels at 484,548 CpG markers from 659 human subjects, and demonstrated that the screening step in ISIS can significantly improve the performance of the elastic net. Conclusion: The proposed method identifies four CpGs which can be mapped to two biologically relevant and functional genes. Identification of significant CpG markers may potentially have practical implications for disease prevention and treatment.

AB - Background: Metabolic syndrome has become a major public health challenge worldwide. The association between metabolic syndrome and DNA methylation is of great research interest. Results: We constructed a binomial model to investigate the association between a metabolic syndrome index and DNA methylation in the Normative Aging Study. We applied the Iterative Sure Independence Screening (ISIS) method with elastic net penalty to DNA methylation levels at 484,548 CpG markers from 659 human subjects, and demonstrated that the screening step in ISIS can significantly improve the performance of the elastic net. Conclusion: The proposed method identifies four CpGs which can be mapped to two biologically relevant and functional genes. Identification of significant CpG markers may potentially have practical implications for disease prevention and treatment.

KW - Bootstrap

KW - Elastic net

KW - ISIS

KW - Metabolic syndrome

KW - Methylation

KW - Ultra-high dimensional variable selection

UR - http://www.scopus.com/inward/record.url?scp=85014607478&partnerID=8YFLogxK

U2 - 10.1186/s12859-017-1568-1

DO - 10.1186/s12859-017-1568-1

M3 - Article

C2 - 28264653

AN - SCOPUS:85014607478

SN - 1471-2105

VL - 18

JO - BMC bioinformatics

JF - BMC bioinformatics

IS - 1

M1 - 156

ER -

Ultra-high dimensional variable selection with application to normative aging study: DNA methylation and metabolic syndrome

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this