Jian Fang1,2, Dongdong Lin3, S Charles Schulz4, Zongben Xu2, Vince D Calhoun3, Yu-Ping Wang1. 1. Biomedical Engineering Department, Tulane University, New Orleans, LA 70118, USA. 2. School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, ShaanXi 710049, China. 3. The Mind Research Network, Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, NM 87131, USA. 4. Department of Psychiatry, University of Minnesota, Minneapolis, MN 55455, USA.
Abstract
MOTIVATION: Imaging genetics combines brain imaging and genetic information to identify the relationships between genetic variants and brain activities. When the data samples belong to different classes (e.g. disease status), the relationships may exhibit class-specific patterns that can be used to facilitate the understanding of a disease. Conventional approaches often perform separate analysis on each class and report the differences, but ignore important shared patterns. RESULTS: In this paper, we develop a multivariate method to analyze the differential dependency across multiple classes. We propose a joint sparse canonical correlation analysis method, which uses a generalized fused lasso penalty to jointly estimate multiple pairs of canonical vectors with both shared and class-specific patterns. Using a data fusion approach, the method is able to detect differentially correlated modules effectively and efficiently. The results from simulation studies demonstrate its higher accuracy in discovering both common and differential canonical correlations compared to conventional sparse CCA. Using a schizophrenia dataset with 92 cases and 116 controls including a single nucleotide polymorphism (SNP) array and functional magnetic resonance imaging data, the proposed method reveals a set of distinct SNP-voxel interaction modules for the schizophrenia patients, which are verified to be both statistically and biologically significant. AVAILABILITY AND IMPLEMENTATION: The Matlab code is available at https://sites.google.com/site/jianfang86/JSCCA CONTACT: wyp@tulane.eduSupplementary information: Supplementary data are available at Bioinformatics online.
MOTIVATION: Imaging genetics combines brain imaging and genetic information to identify the relationships between genetic variants and brain activities. When the data samples belong to different classes (e.g. disease status), the relationships may exhibit class-specific patterns that can be used to facilitate the understanding of a disease. Conventional approaches often perform separate analysis on each class and report the differences, but ignore important shared patterns. RESULTS: In this paper, we develop a multivariate method to analyze the differential dependency across multiple classes. We propose a joint sparse canonical correlation analysis method, which uses a generalized fused lasso penalty to jointly estimate multiple pairs of canonical vectors with both shared and class-specific patterns. Using a data fusion approach, the method is able to detect differentially correlated modules effectively and efficiently. The results from simulation studies demonstrate its higher accuracy in discovering both common and differential canonical correlations compared to conventional sparse CCA. Using a schizophrenia dataset with 92 cases and 116 controls including a single nucleotide polymorphism (SNP) array and functional magnetic resonance imaging data, the proposed method reveals a set of distinct SNP-voxel interaction modules for the schizophrenia patients, which are verified to be both statistically and biologically significant. AVAILABILITY AND IMPLEMENTATION: The Matlab code is available at https://sites.google.com/site/jianfang86/JSCCA CONTACT: wyp@tulane.eduSupplementary information: Supplementary data are available at Bioinformatics online.
Authors: H Le-Niculescu; Y Balaraman; S Patel; J Tan; K Sidhu; R E Jerome; H J Edenberg; R Kuczenski; M A Geyer; J I Nurnberger; S V Faraone; M T Tsuang; A B Niculescu Journal: Am J Med Genet B Neuropsychiatr Genet Date: 2007-03-05 Impact factor: 3.568
Authors: J I Friedman; T Vrijenhoek; S Markx; I M Janssen; W A van der Vliet; B H W Faas; N V Knoers; W Cahn; R S Kahn; L Edelmann; K L Davis; J M Silverman; H G Brunner; A Geurts van Kessel; C Wijmenga; R A Ophoff; J A Veltman Journal: Mol Psychiatry Date: 2007-07-24 Impact factor: 15.992
Authors: Nicholas B Larson; Gregory D Jenkins; Melissa C Larson; Robert A Vierkant; Thomas A Sellers; Catherine M Phelan; Joellen M Schildkraut; Rebecca Sutphen; Paul P D Pharoah; Simon A Gayther; Nicolas Wentzensen; Ellen L Goode; Brooke L Fridley Journal: Eur J Hum Genet Date: 2013-04-17 Impact factor: 4.246
Authors: Ye Tian; Bai Zhang; Eric P Hoffman; Robert Clarke; Zhen Zhang; Ie-Ming Shih; Jianhua Xuan; David M Herrington; Yue Wang Journal: BMC Syst Biol Date: 2014-07-24
Authors: Lei Du; Fang Liu; Kefei Liu; Xiaohui Yao; Shannon L Risacher; Junwei Han; Andrew J Saykin; Li Shen Journal: IEEE Trans Med Imaging Date: 2020-10-28 Impact factor: 10.048
Authors: Pascal Zille; Vince D Calhoun; Julia M Stephen; Tony W Wilson; Yu-Ping Wang Journal: IEEE Trans Med Imaging Date: 2017-06-29 Impact factor: 10.048
Authors: Li Xiao; Junqi Wang; Peyman H Kassani; Yipu Zhang; Yuntong Bai; Julia M Stephen; Tony W Wilson; Vince D Calhoun; Yu-Ping Wang Journal: IEEE Trans Med Imaging Date: 2019-12-02 Impact factor: 10.048