Canonical Correlation Analysis of Imaging Genetics Data Based on Statistical Independence and Structural Sparsity

Overview

Journal IEEE J Biomed Health Inform

Specialties Biomedical Engineering
Medical Informatics

Date 2020 Feb 20

PMID 32071012

Authors

Yipu Zhang

Peng Peng

Yongfeng Ju

Gang Li

Vince D Calhoun

Yu-Ping Wang

Affiliations

Soon will be listed here.

Abstract

Current developments of neuroimaging and genetics promote an integrative and compressive study of schizophrenia. However, it is still difficult to explore how gene mutations are related to brain abnormalities due to the high dimension but low sample size of these data. Conventional approaches reduce the dimension of dataset separately and then calculate the correlation, but ignore the effects of the response variables and the structure of data. To improve the identification of risk genes and abnormal brain regions on schizophrenia, in this paper, we propose a novel method called Independence and Structural sparsity Canonical Correlation Analysis (ISCCA). ISCCA combines independent component analysis (ICA) and Canonical Correlation Analysis (CCA) to reduce the collinear effects, which also incorporate graph structure of the data into the model to improve the accuracy of feature selection. The results from simulation studies demonstrate its higher accuracy in discovering correlations compared with other competing methods. Moreover, applying ISCCA to a real imaging genetics dataset collected by Mind Clinical Imaging Consortium (MCIC), a set of distinct gene-ROI interactions are identified, which are verified to be both statistically and biologically significant.

References

Calhoun V, Adali T, Kiehl K, Astur R, Pekar J, Pearlson G . A method for multitask fMRI data fusion applied to schizophrenia. Hum Brain Mapp. 2005; 27(7):598-610. PMC: 2751648. DOI: 10.1002/hbm.20204. View

Chen X, He C, Jane Wang Z, McKeown M . An IC-PLS framework for group corticomuscular coupling analysis. IEEE Trans Biomed Eng. 2013; 60(7):2022-33. DOI: 10.1109/TBME.2013.2248059. View

Lu J, Zhang H, Hameed N, Zhang J, Yuan S, Qiu T . An automated method for identifying an independent component analysis-based language-related resting-state network in brain tumor subjects for surgical planning. Sci Rep. 2017; 7(1):13769. PMC: 5653800. DOI: 10.1038/s41598-017-14248-5. View

Gossmann A, Zille P, Calhoun V, Wang Y . FDR-Corrected Sparse Canonical Correlation Analysis With Applications to Imaging Genomics. IEEE Trans Med Imaging. 2018; 37(8):1761-1774. DOI: 10.1109/TMI.2018.2815583. View

Grozeva D, Kirov G, Ivanov D, Jones I, Jones L, Green E . Rare copy number variants: a point of rarity in genetic risk for bipolar disorder and schizophrenia. Arch Gen Psychiatry. 2010; 67(4):318-27. PMC: 4476027. DOI: 10.1001/archgenpsychiatry.2010.25. View

Kamburov A, Stelzl U, Lehrach H, Herwig R . The ConsensusPathDB interaction database: 2013 update. Nucleic Acids Res. 2012; 41(Database issue):D793-800. PMC: 3531102. DOI: 10.1093/nar/gks1055. View

Kanehisa M, Goto S . KEGG: kyoto encyclopedia of genes and genomes. Nucleic Acids Res. 1999; 28(1):27-30. PMC: 102409. DOI: 10.1093/nar/28.1.27. View

Liu J, Pearlson G, Windemuth A, Ruano G, Perrone-Bizzozero N, Calhoun V . Combining fMRI and SNP data to investigate connections between brain function and genetics using parallel ICA. Hum Brain Mapp. 2007; 30(1):241-55. PMC: 2668960. DOI: 10.1002/hbm.20508. View

Witten D, Tibshirani R, Hastie T . A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis. Biostatistics. 2009; 10(3):515-34. PMC: 2697346. DOI: 10.1093/biostatistics/kxp008. View

10.

Akiyama M, Okada Y, Kanai M, Takahashi A, Momozawa Y, Ikeda M . Genome-wide association study identifies 112 new loci for body mass index in the Japanese population. Nat Genet. 2017; 49(10):1458-1467. DOI: 10.1038/ng.3951. View

11.

Du Y, Fryer S, Fu Z, Lin D, Sui J, Chen J . Dynamic functional connectivity impairments in early schizophrenia and clinical high-risk for psychosis. Neuroimage. 2017; 180(Pt B):632-645. PMC: 5899692. DOI: 10.1016/j.neuroimage.2017.10.022. View

12.

Lefebvre S, Demeulemeester M, Leroy A, Delmaire C, Lopes R, Pins D . Network dynamics during the different stages of hallucinations in schizophrenia. Hum Brain Mapp. 2016; 37(7):2571-86. PMC: 6867493. DOI: 10.1002/hbm.23197. View

13.

Lin D, Zhang J, Li J, Calhoun V, Deng H, Wang Y . Group sparse canonical correlation analysis for genomic data integration. BMC Bioinformatics. 2013; 14:245. PMC: 3751310. DOI: 10.1186/1471-2105-14-245. View

14.

Alam M, Fukumizu K, Wang Y . Influence Function and Robust Variant of Kernel Canonical Correlation Analysis. Neurocomputing (Amst). 2018; 304:12-29. PMC: 6223640. DOI: 10.1016/j.neucom.2018.04.008. View

15.

Hu W, Lin D, Calhoun V, Wang Y . Integration of SNPs-FMRI-methylation data with sparse multi-CCA for schizophrenia study. Annu Int Conf IEEE Eng Med Biol Soc. 2017; 2016:3310-3313. DOI: 10.1109/EMBC.2016.7591436. View

16.

Lin S, Liu C, Liu Y, Shen-Jang Fann C, Hsiao P, Wu J . Clustering by neurocognition for fine mapping of the schizophrenia susceptibility loci on chromosome 6p. Genes Brain Behav. 2009; 8(8):785-94. PMC: 4286260. DOI: 10.1111/j.1601-183X.2009.00523.x. View

17.

Hertzberg L, Katsel P, Roussos P, Haroutunian V, Domany E . Integration of gene expression and GWAS results supports involvement of calcium signaling in Schizophrenia. Schizophr Res. 2015; 164(1-3):92-9. DOI: 10.1016/j.schres.2015.02.001. View

18.

Kinoshita M, Numata S, Tajima A, Shimodera S, Imoto I, Ohmori T . Plasma total homocysteine is associated with DNA methylation in patients with schizophrenia. Epigenetics. 2013; 8(6):584-90. PMC: 3857338. DOI: 10.4161/epi.24621. View

19.

Xu W, Cohen-Woods S, Chen Q, Noor A, Knight J, Hosang G . Genome-wide association study of bipolar disorder in Canadian and UK populations corroborates disease loci including SYNE1 and CSMD1. BMC Med Genet. 2014; 15:2. PMC: 3901032. DOI: 10.1186/1471-2350-15-2. View

20.

Du Y, Liu J, Sui J, He H, Pearlson G, Calhoun V . Exploring difference and overlap between schizophrenia, schizoaffective and bipolar disorders using resting-state brain functional networks. Annu Int Conf IEEE Eng Med Biol Soc. 2015; 2014:1517-20. DOI: 10.1109/EMBC.2014.6943890. View