Abstract
Brain imaging genetics can demonstrate the complicated relationship between genetic factors and the structure or function of the humankind brain. Therefore, it has become an important research topic and attracted more and more attention from scholars. The structured sparse canonical correlation analysis (SCCA) model has been widely used to identify the association between brain image data and genetic data in imaging genetics. To investigate the intricate genetic basis of cerebrum imaging phenotypes, a great deal of other standard SCCA methods combining different interested structed have now appeared. For example, some models use group lasso penalty, and some use the fused lasso or the graph/network guided fused lasso for feature selection. However, prior knowledge may not be completely available and the group lasso methods have limited capabilities in practical applications. The graph/network guided approaches can use sample correlation to define constraints, thereby overcoming this problem. Unfortunately, this also has certain limitations. The graph/network conducted methods are susceptible to the sign of the sample correlation of the data, which will affect the stability of the model. To improve the efficiency and stability of SCCA, a sparse canonical correlation analysis model with GraphNet regularization (FGLGNSCCA) is proposed in this manuscript. Based on the FGLSCCA model, the GraphNet regularization penalty is imposed in our study and an optimization algorithm is presented to optimize the model. The structural Magnetic Resonance Imaging (sMRI) and gene expression data are used in this study to find the genotype and characteristics of brain regions associated with Alzheimer’s disease (AD). Experiment results shown that the new FGLGNSCCA model proposed in this manuscript is superior or equivalent to traditional methods in both artificially synthesized neuroimaging genetics data or actual neuroimaging genetics data. It can select essential features more powerfully compared with other multivariate methods and identify significant canonical correlation coefficients as well as captures more significant typical weight patterns which demonstrated its excellent ability in finding biologically important imaging genetic relations.
Highlights
Alzheimer’s disease (AD) is an irreversible long-time neurodegenerative disease and brings misfortune to the patient, and brings a heavy economic and emotional burden to the family (Alzheimer’s Association, 2013)
We compared with the proposed model with FGLSCCA, L1-sparse canonical correlation analysis (SCCA), an improved GNSCCA method (AGNSCCA) as shown in Figure 2 which shown the influence of different noise levels on the sample correlation results under 100 times of fivefold cross-validation
In the research using artificially synthesized highly correlated data sets for testing, these findings indicate that the algorithm in this manuscript has better anti-noise capability than the three methods (L1-SCCA, FGLSCCA, and AGNSCCA)
Summary
Alzheimer’s disease (AD) is an irreversible long-time neurodegenerative disease and brings misfortune to the patient, and brings a heavy economic and emotional burden to the family (Alzheimer’s Association, 2013). In the past ten years, image genetics has become a crucial research topic in biomedicine and bioinformatics. The reason is that the potential influence of genes on brain structure and function can be found by genetic research. As a powerful tool for data-driven association analysis, statistical learning methods can make full use of the inherent structural information of biomarker data to build models to analyze the correlation between susceptible genes and brain structure or function which can indicate the pathogenesis of brain cognitive behavior or related diseases well. Imaging genetics has become a hot research topic in biomedicine and bioinformatics research
Sign-in/Register to view highlights & summary 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.
