Data modeling and method analysis for brain imaging genetics

作者：Sheng, Jinhua^*

来源：International Journal of Imaging Systems and Technology, 2017, 27(2): 162-170.

DOI：10.1002/ima.22220

• data synthesis
• genotype
• linear model
• neuroimaging
• phenotype
• sparse canonical correlation analysis

Brain imaging genetics is a popular research topic on evaluating the association between genetic variations and neuroimaging quantitative traits (QTs). As a bi-multivariate analysis method, sparse canonical correlation analysis (CCA) is a useful technique which identifies efficiently genetic diseases on the brain with modeling dependencies between the variables of genotype data and phenotype data. The initial efforts on evaluating several space CCA methods are made for brain imaging genetics. A linear model is proposed to generate realistic imaging genomic data with selected genotype-phenotype associations from real data and effectively capture the sparsity underlying projects. Three space CCA algorithms are applied to the synthetic data, and show better or comparable performance on the synthetic data in terms of the estimated canonical correlations. They have successfully identified an important association between genotype and phenotype. Experiments on simulated and real imaging genetic data show that approximating covariance structure using an identity or diagonal matrix and the approach used in these space CCA algorithms could limit the space CCA capability in identifying the underlying imaging genetics associations. Further development depends largely on enhanced space CCA methods that effectively pay attention to the covariance structures in simulated and real imaging genetics data.

• 出版日期2017-6
• 单位杭州电子科技大学