Abstract
Imaging genetics combines neuroimaging and genetics to assess the relationships between genetic variants and changes in brain structure and metabolism. Sparse canonical correlation analysis (SCCA) models are well-known tools for identifying meaningful biomarkers in imaging genetics. However, most SCCA models incorporate only diagnostic status information, which poses challenges for finding disease-specific biomarkers. In this study, we proposed a multi-task sparse canonical correlation analysis and regression (MT-SCCAR) model to reveal disease-specific associations between single nucleotide polymorphisms and quantitative traits derived from multi-modal neuroimaging data in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. MT-SCCAR uses complementary information carried by multiple-perspective cognitive scores and encourages group sparsity on genetic variants. In contrast with two other multi-modal SCCA models, MT-SCCAR embedded more accurate neuropsychological assessment information through linear regression and enhanced the correlation coefficients, leading to increased identification of high-risk brain regions. Furthermore, MT-SCCAR identified primary genetic risk factors for Alzheimer’s disease (AD), including rs429358, and found some association patterns between genetic variants and brain regions. Thus, MT-SCCAR contributes to deciphering genetic risk factors of brain structural and metabolic changes by identifying potential risk biomarkers.
Highlights
Imaging genetics has recently emerged as a method for investigating imaging and genetic biomarkers related to diseases such as Alzheimer’s disease (AD) (Bogdan et al, 2017)
Assuming that X ∈ Rn × p,Y ∈ Rn × q, and Z ∈ Rn × q denote single nucleotide polymorphisms (SNPs), magnetic resonance imaging (MRI), and positron emission tomography (PET) for all synthetic data sets, respectively
X was generated by X = ul + e,Y was generated by Y = vl + e, and Z was generated by Z = wl + e, where u, v, and ware known loading vectors, l is a latent vector with a 3-component Gaussian distribution to simulate the disease course (Yan et al, 2018), and e is derived from the Gaussian distribution N 0, σe2 with σe2 as the noise variance
Summary
Imaging genetics has recently emerged as a method for investigating imaging and genetic biomarkers related to diseases such as Alzheimer’s disease (AD) (Bogdan et al, 2017). Identified neuroimaging and genetics biomarkers can provide a complementary understanding of the brain’s structure and metabolism (Zhang et al, 2011). The vast amounts of diagnostic and neuropsychological information from various perspectives enable the discovery of disease-specific biomarkers. It is essential to simultaneously analyze multiple neuroimaging techniques, such as magnetic resonance imaging (MRI), fluorodeoxyglucose positron emission tomography (FDG-PET), genotyping, and clinical diagnostic data. We aimed to build a model to identify disease-specific biomarkers across multiple imaging modalities, which can be used as an effective clue for disease diagnosis and targeted therapy.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
