Integration of Network-Based Biological Knowledge With White Matter Features in Preterm Infants Using the Graph-Guided Group Lasso

Michelle L. Krishnan; Zi Wang; Matt Silver; James P. Boardman; Gareth Ball; Serena J. Counsell; Andrew J. Walley; David Edwards; Giovanni Montana

doi:10.1016/B978-0-12-813968-4.00003-1

Integration of Network-Based Biological Knowledge With White Matter Features in Preterm Infants Using the Graph-Guided Group Lasso

Michelle L. Krishnan^*, Zi Wang, Matt Silver, James P. Boardman, Gareth Ball, Serena J. Counsell, Andrew J. Walley, David Edwards, Giovanni Montana

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

The effect of prematurity on normal developmental programs of white and gray matter as evaluated with magnetic resonance imaging indicates global changes in white and gray matter with functional implications. We have previously identified an association between lipids and diffusion tensor imaging features in preterm infants, both through a candidate gene approach and a data-driven statistical genetics method. Here we apply a penalized linear regression model, the graph-guided group lasso (GGGL), that can utilize prior knowledge and select single nucleotide polymorphisms (SNPs) within functionally related genes associated with the trait. GGGL incorporates prior information from SNP-gene mapping as well as from the gene functional interaction network to guide variable selection.

Original language	English
Title of host publication	Imaging Genetics
Publisher	Elsevier Inc.
Pages	45-59
Number of pages	15
ISBN (Electronic)	9780128139691
ISBN (Print)	9780128139684
DOIs	https://doi.org/10.1016/B978-0-12-813968-4.00003-1
Publication status	Published - 26 Sept 2017

Keywords

Brain development
Machine learning
Magnetic resonance imaging
PPARG
Sparse regression

Access to Document

10.1016/B978-0-12-813968-4.00003-1

Cite this

@inbook{79f7f63f8573424594c1d841c2b1e7fb,

title = "Integration of Network-Based Biological Knowledge With White Matter Features in Preterm Infants Using the Graph-Guided Group Lasso",

abstract = "The effect of prematurity on normal developmental programs of white and gray matter as evaluated with magnetic resonance imaging indicates global changes in white and gray matter with functional implications. We have previously identified an association between lipids and diffusion tensor imaging features in preterm infants, both through a candidate gene approach and a data-driven statistical genetics method. Here we apply a penalized linear regression model, the graph-guided group lasso (GGGL), that can utilize prior knowledge and select single nucleotide polymorphisms (SNPs) within functionally related genes associated with the trait. GGGL incorporates prior information from SNP-gene mapping as well as from the gene functional interaction network to guide variable selection.",

keywords = "Brain development, Machine learning, Magnetic resonance imaging, PPARG, Sparse regression",

author = "Krishnan, {Michelle L.} and Zi Wang and Matt Silver and Boardman, {James P.} and Gareth Ball and Counsell, {Serena J.} and Walley, {Andrew J.} and David Edwards and Giovanni Montana",

year = "2017",

month = sep,

day = "26",

doi = "10.1016/B978-0-12-813968-4.00003-1",

language = "English",

isbn = "9780128139684",

pages = "45--59",

booktitle = "Imaging Genetics",

publisher = "Elsevier Inc.",

address = "United States",

}

TY - CHAP

T1 - Integration of Network-Based Biological Knowledge With White Matter Features in Preterm Infants Using the Graph-Guided Group Lasso

AU - Krishnan, Michelle L.

AU - Wang, Zi

AU - Silver, Matt

AU - Boardman, James P.

AU - Ball, Gareth

AU - Counsell, Serena J.

AU - Walley, Andrew J.

AU - Edwards, David

AU - Montana, Giovanni

PY - 2017/9/26

Y1 - 2017/9/26

N2 - The effect of prematurity on normal developmental programs of white and gray matter as evaluated with magnetic resonance imaging indicates global changes in white and gray matter with functional implications. We have previously identified an association between lipids and diffusion tensor imaging features in preterm infants, both through a candidate gene approach and a data-driven statistical genetics method. Here we apply a penalized linear regression model, the graph-guided group lasso (GGGL), that can utilize prior knowledge and select single nucleotide polymorphisms (SNPs) within functionally related genes associated with the trait. GGGL incorporates prior information from SNP-gene mapping as well as from the gene functional interaction network to guide variable selection.

AB - The effect of prematurity on normal developmental programs of white and gray matter as evaluated with magnetic resonance imaging indicates global changes in white and gray matter with functional implications. We have previously identified an association between lipids and diffusion tensor imaging features in preterm infants, both through a candidate gene approach and a data-driven statistical genetics method. Here we apply a penalized linear regression model, the graph-guided group lasso (GGGL), that can utilize prior knowledge and select single nucleotide polymorphisms (SNPs) within functionally related genes associated with the trait. GGGL incorporates prior information from SNP-gene mapping as well as from the gene functional interaction network to guide variable selection.

KW - Brain development

KW - Machine learning

KW - Magnetic resonance imaging

KW - PPARG

KW - Sparse regression

UR - http://www.scopus.com/inward/record.url?scp=85054208064&partnerID=8YFLogxK

U2 - 10.1016/B978-0-12-813968-4.00003-1

DO - 10.1016/B978-0-12-813968-4.00003-1

M3 - Chapter

SN - 9780128139684

SP - 45

EP - 59

BT - Imaging Genetics

PB - Elsevier Inc.

ER -

Integration of Network-Based Biological Knowledge With White Matter Features in Preterm Infants Using the Graph-Guided Group Lasso

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this