Structured sparse canonical correlation analysis for brain imaging genetics: An improved GraphNet method

Lei Du, Heng Huang, Jingwen Yan, Sungeun Kim, Shannon L. Risacher, Mark Inlow, Jason H. Moore, Andrew Saykin, Li Shen

Research output: Contribution to journalArticle

32 Citations (Scopus)

Abstract

Motivation: Structured sparse canonical correlation analysis (SCCA) models have been used to identify imaging genetic associations. These models either use group lasso or graph-guided fused lasso to conduct feature selection and feature grouping simultaneously. The group lasso based methods require prior knowledge to define the groups, which limits the capability when prior knowledge is incomplete or unavailable. The graph-guided methods overcome this drawback by using the sample correlation to define the constraint. However, they are sensitive to the sign of the sample correlation, which could introduce undesirable bias if the sign is wrongly estimated. Results: We introduce a novel SCCA model with a new penalty, and develop an efficient optimization algorithm. Our method has a strong upper bound for the grouping effect for both positively and negatively correlated features. We show that our method performs better than or equally to three competing SCCA models on both synthetic and real data. In particular, our method identifies stronger canonical correlations and better canonical loading patterns, showing its promise for revealing interesting imaging genetic associations. Availability and implementation: The Matlab code and sample data are freely available at http://www.iu.edu/∼shenlab/tools/angscca/.

Original languageEnglish (US)
Pages (from-to)1544-1551
Number of pages8
JournalBioinformatics
Volume32
Issue number10
DOIs
StatePublished - May 15 2016

Fingerprint

Canonical Correlation Analysis
Neuroimaging
Brain
Imaging
Lasso
Imaging techniques
Genetic Association
Prior Knowledge
Grouping
Canonical Correlation
Feature extraction
Graph in graph theory
Model
Feature Selection
Availability
MATLAB
Penalty
Optimization Algorithm
Efficient Algorithms
Genetics

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Computational Mathematics
  • Statistics and Probability

Cite this

Structured sparse canonical correlation analysis for brain imaging genetics : An improved GraphNet method. / Du, Lei; Huang, Heng; Yan, Jingwen; Kim, Sungeun; Risacher, Shannon L.; Inlow, Mark; Moore, Jason H.; Saykin, Andrew; Shen, Li.

In: Bioinformatics, Vol. 32, No. 10, 15.05.2016, p. 1544-1551.

Research output: Contribution to journalArticle

Du, Lei ; Huang, Heng ; Yan, Jingwen ; Kim, Sungeun ; Risacher, Shannon L. ; Inlow, Mark ; Moore, Jason H. ; Saykin, Andrew ; Shen, Li. / Structured sparse canonical correlation analysis for brain imaging genetics : An improved GraphNet method. In: Bioinformatics. 2016 ; Vol. 32, No. 10. pp. 1544-1551.
@article{dceb637f17ab4b81ab8cf227b1c4dd56,
title = "Structured sparse canonical correlation analysis for brain imaging genetics: An improved GraphNet method",
abstract = "Motivation: Structured sparse canonical correlation analysis (SCCA) models have been used to identify imaging genetic associations. These models either use group lasso or graph-guided fused lasso to conduct feature selection and feature grouping simultaneously. The group lasso based methods require prior knowledge to define the groups, which limits the capability when prior knowledge is incomplete or unavailable. The graph-guided methods overcome this drawback by using the sample correlation to define the constraint. However, they are sensitive to the sign of the sample correlation, which could introduce undesirable bias if the sign is wrongly estimated. Results: We introduce a novel SCCA model with a new penalty, and develop an efficient optimization algorithm. Our method has a strong upper bound for the grouping effect for both positively and negatively correlated features. We show that our method performs better than or equally to three competing SCCA models on both synthetic and real data. In particular, our method identifies stronger canonical correlations and better canonical loading patterns, showing its promise for revealing interesting imaging genetic associations. Availability and implementation: The Matlab code and sample data are freely available at http://www.iu.edu/∼shenlab/tools/angscca/.",
author = "Lei Du and Heng Huang and Jingwen Yan and Sungeun Kim and Risacher, {Shannon L.} and Mark Inlow and Moore, {Jason H.} and Andrew Saykin and Li Shen",
year = "2016",
month = "5",
day = "15",
doi = "10.1093/bioinformatics/btw033",
language = "English (US)",
volume = "32",
pages = "1544--1551",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "10",

}

TY - JOUR

T1 - Structured sparse canonical correlation analysis for brain imaging genetics

T2 - An improved GraphNet method

AU - Du, Lei

AU - Huang, Heng

AU - Yan, Jingwen

AU - Kim, Sungeun

AU - Risacher, Shannon L.

AU - Inlow, Mark

AU - Moore, Jason H.

AU - Saykin, Andrew

AU - Shen, Li

PY - 2016/5/15

Y1 - 2016/5/15

N2 - Motivation: Structured sparse canonical correlation analysis (SCCA) models have been used to identify imaging genetic associations. These models either use group lasso or graph-guided fused lasso to conduct feature selection and feature grouping simultaneously. The group lasso based methods require prior knowledge to define the groups, which limits the capability when prior knowledge is incomplete or unavailable. The graph-guided methods overcome this drawback by using the sample correlation to define the constraint. However, they are sensitive to the sign of the sample correlation, which could introduce undesirable bias if the sign is wrongly estimated. Results: We introduce a novel SCCA model with a new penalty, and develop an efficient optimization algorithm. Our method has a strong upper bound for the grouping effect for both positively and negatively correlated features. We show that our method performs better than or equally to three competing SCCA models on both synthetic and real data. In particular, our method identifies stronger canonical correlations and better canonical loading patterns, showing its promise for revealing interesting imaging genetic associations. Availability and implementation: The Matlab code and sample data are freely available at http://www.iu.edu/∼shenlab/tools/angscca/.

AB - Motivation: Structured sparse canonical correlation analysis (SCCA) models have been used to identify imaging genetic associations. These models either use group lasso or graph-guided fused lasso to conduct feature selection and feature grouping simultaneously. The group lasso based methods require prior knowledge to define the groups, which limits the capability when prior knowledge is incomplete or unavailable. The graph-guided methods overcome this drawback by using the sample correlation to define the constraint. However, they are sensitive to the sign of the sample correlation, which could introduce undesirable bias if the sign is wrongly estimated. Results: We introduce a novel SCCA model with a new penalty, and develop an efficient optimization algorithm. Our method has a strong upper bound for the grouping effect for both positively and negatively correlated features. We show that our method performs better than or equally to three competing SCCA models on both synthetic and real data. In particular, our method identifies stronger canonical correlations and better canonical loading patterns, showing its promise for revealing interesting imaging genetic associations. Availability and implementation: The Matlab code and sample data are freely available at http://www.iu.edu/∼shenlab/tools/angscca/.

UR - http://www.scopus.com/inward/record.url?scp=84969940421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969940421&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btw033

DO - 10.1093/bioinformatics/btw033

M3 - Article

C2 - 26801960

AN - SCOPUS:84969940421

VL - 32

SP - 1544

EP - 1551

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 10

ER -