Mining outcome-relevant brain imaging genetic associations via three-way sparse canonical correlation analysis in Alzheimer's disease

Xiaoke Hao, Chanxiu Li, Lei Du, Xiaohui Yao, Jingwen Yan, Shannon L. Risacher, Andrew Saykin, Li Shen, Daoqiang Zhang

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Neuroimaging genetics is an emerging field that aims to identify the associations between genetic variants (e.g., single nucleotide polymorphisms (SNPs)) and quantitative traits (QTs) such as brain imaging phenotypes. In recent studies, in order to detect complex multi-SNP-multi-QT associations, bi-multivariate techniques such as various structured sparse canonical correlation analysis (SCCA) algorithms have been proposed and used in imaging genetics studies. However, associations between genetic markers and imaging QTs identified by existing bi-multivariate methods may not be all disease specific. To bridge this gap, we propose an analytical framework, based on three-way sparse canonical correlation analysis (T-SCCA), to explore the intrinsic associations among genetic markers, imaging QTs, and clinical scores of interest. We perform an empirical study using the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort to discover the relationships among SNPs from AD risk gene APOE, imaging QTs extracted from structural magnetic resonance imaging scans, and cognitive and diagnostic outcomes. The proposed T-SCCA model not only outperforms the traditional SCCA method in terms of identifying strong associations, but also discovers robust outcome-relevant imaging genetic patterns, demonstrating its promise for improving disease-related mechanistic understanding.

Original languageEnglish (US)
Article number44272
JournalScientific Reports
Volume7
DOIs
StatePublished - Mar 14 2017

Fingerprint

Neuroimaging
Single Nucleotide Polymorphism
Alzheimer Disease
Genetic Markers
Magnetic Resonance Imaging
Phenotype
Genes

ASJC Scopus subject areas

  • General

Cite this

Mining outcome-relevant brain imaging genetic associations via three-way sparse canonical correlation analysis in Alzheimer's disease. / Hao, Xiaoke; Li, Chanxiu; Du, Lei; Yao, Xiaohui; Yan, Jingwen; Risacher, Shannon L.; Saykin, Andrew; Shen, Li; Zhang, Daoqiang.

In: Scientific Reports, Vol. 7, 44272, 14.03.2017.

Research output: Contribution to journalArticle

Hao, Xiaoke ; Li, Chanxiu ; Du, Lei ; Yao, Xiaohui ; Yan, Jingwen ; Risacher, Shannon L. ; Saykin, Andrew ; Shen, Li ; Zhang, Daoqiang. / Mining outcome-relevant brain imaging genetic associations via three-way sparse canonical correlation analysis in Alzheimer's disease. In: Scientific Reports. 2017 ; Vol. 7.
@article{d0bba5e7786840248b59fd314c922181,
title = "Mining outcome-relevant brain imaging genetic associations via three-way sparse canonical correlation analysis in Alzheimer's disease",
abstract = "Neuroimaging genetics is an emerging field that aims to identify the associations between genetic variants (e.g., single nucleotide polymorphisms (SNPs)) and quantitative traits (QTs) such as brain imaging phenotypes. In recent studies, in order to detect complex multi-SNP-multi-QT associations, bi-multivariate techniques such as various structured sparse canonical correlation analysis (SCCA) algorithms have been proposed and used in imaging genetics studies. However, associations between genetic markers and imaging QTs identified by existing bi-multivariate methods may not be all disease specific. To bridge this gap, we propose an analytical framework, based on three-way sparse canonical correlation analysis (T-SCCA), to explore the intrinsic associations among genetic markers, imaging QTs, and clinical scores of interest. We perform an empirical study using the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort to discover the relationships among SNPs from AD risk gene APOE, imaging QTs extracted from structural magnetic resonance imaging scans, and cognitive and diagnostic outcomes. The proposed T-SCCA model not only outperforms the traditional SCCA method in terms of identifying strong associations, but also discovers robust outcome-relevant imaging genetic patterns, demonstrating its promise for improving disease-related mechanistic understanding.",
author = "Xiaoke Hao and Chanxiu Li and Lei Du and Xiaohui Yao and Jingwen Yan and Risacher, {Shannon L.} and Andrew Saykin and Li Shen and Daoqiang Zhang",
year = "2017",
month = "3",
day = "14",
doi = "10.1038/srep44272",
language = "English (US)",
volume = "7",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Mining outcome-relevant brain imaging genetic associations via three-way sparse canonical correlation analysis in Alzheimer's disease

AU - Hao, Xiaoke

AU - Li, Chanxiu

AU - Du, Lei

AU - Yao, Xiaohui

AU - Yan, Jingwen

AU - Risacher, Shannon L.

AU - Saykin, Andrew

AU - Shen, Li

AU - Zhang, Daoqiang

PY - 2017/3/14

Y1 - 2017/3/14

N2 - Neuroimaging genetics is an emerging field that aims to identify the associations between genetic variants (e.g., single nucleotide polymorphisms (SNPs)) and quantitative traits (QTs) such as brain imaging phenotypes. In recent studies, in order to detect complex multi-SNP-multi-QT associations, bi-multivariate techniques such as various structured sparse canonical correlation analysis (SCCA) algorithms have been proposed and used in imaging genetics studies. However, associations between genetic markers and imaging QTs identified by existing bi-multivariate methods may not be all disease specific. To bridge this gap, we propose an analytical framework, based on three-way sparse canonical correlation analysis (T-SCCA), to explore the intrinsic associations among genetic markers, imaging QTs, and clinical scores of interest. We perform an empirical study using the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort to discover the relationships among SNPs from AD risk gene APOE, imaging QTs extracted from structural magnetic resonance imaging scans, and cognitive and diagnostic outcomes. The proposed T-SCCA model not only outperforms the traditional SCCA method in terms of identifying strong associations, but also discovers robust outcome-relevant imaging genetic patterns, demonstrating its promise for improving disease-related mechanistic understanding.

AB - Neuroimaging genetics is an emerging field that aims to identify the associations between genetic variants (e.g., single nucleotide polymorphisms (SNPs)) and quantitative traits (QTs) such as brain imaging phenotypes. In recent studies, in order to detect complex multi-SNP-multi-QT associations, bi-multivariate techniques such as various structured sparse canonical correlation analysis (SCCA) algorithms have been proposed and used in imaging genetics studies. However, associations between genetic markers and imaging QTs identified by existing bi-multivariate methods may not be all disease specific. To bridge this gap, we propose an analytical framework, based on three-way sparse canonical correlation analysis (T-SCCA), to explore the intrinsic associations among genetic markers, imaging QTs, and clinical scores of interest. We perform an empirical study using the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort to discover the relationships among SNPs from AD risk gene APOE, imaging QTs extracted from structural magnetic resonance imaging scans, and cognitive and diagnostic outcomes. The proposed T-SCCA model not only outperforms the traditional SCCA method in terms of identifying strong associations, but also discovers robust outcome-relevant imaging genetic patterns, demonstrating its promise for improving disease-related mechanistic understanding.

UR - http://www.scopus.com/inward/record.url?scp=85015386653&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015386653&partnerID=8YFLogxK

U2 - 10.1038/srep44272

DO - 10.1038/srep44272

M3 - Article

C2 - 28291242

AN - SCOPUS:85015386653

VL - 7

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 44272

ER -