Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 17;25(1):287.
doi: 10.1186/s12880-025-01782-2.

Exploration of biomarkers of Alzheimer's disease based on orthogonal multi-task canonical correlation analysis

Tao Yang #  1 , GuangYu Wan #  1 , Xiong Zhou  2
Affiliations

Exploration of biomarkers of Alzheimer's disease based on orthogonal multi-task canonical correlation analysis

Tao Yang et al. BMC Med Imaging. .

Abstract

As a neurodegenerative disease, Alzheimer's disease (AD) has many symptoms, such as memory impairment, cognitive decline, and personality change. Image genetics is the correlation analysis between imageology and genetics, and image genetics research can effectively detect the biomarkers of AD. This paper proposed an orthogonal multi-task sparse canonical correlation analysis (MTOSCCA) algorithm. Based on the multi-task canonical correlation analysis, this algorithm added orthogonal constraints to the weight vectors U and V, which can effectively prevent the influence of redundant features on the results. In this paper, the MTOSCCA algorithm was applied to structural magnetic resonance imaging, single nucleotide polymorphism, and gene expression data integration. The results showed that the proposed algorithm has better correlation performance, and the obtained markers have diagnostic significance for AD and mild cognitive impairment (MCI).

Keywords: Alzheimer's disease; Biomarkers; Canonical correlation analysis; Image genetics; Orthogonal constraint.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethical approval: Not applicable. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
The overall flow chart of the paper
Fig. 2
Fig. 2
Selection of optimal parameters. A and B were the change line charts of CCC1 and CCC2 under different parameter combinations, respectively. C was the change line chart of the mean value of CCC1 and CCC2 under different parameter combinations
Fig. 3
Fig. 3
Weighted heat map of formula image, formula image and formula image
Fig. 4
Fig. 4
Performance comparison results of two algorithms on simulated data sets. A and B were the comparisons of CCC1 and CCC2 of the two algorithms under different noises, respectively
Fig. 5
Fig. 5
The ROC curve of the Top biomarker. A-C were the ROC curves of the Top 10 ROI, SNP, and gene, respectively
Fig. 6
Fig. 6
Visualization of the Top brain region
Fig. 7
Fig. 7
Enrichment and analysis results of GO and KEGG of the Top gene
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Weller J, Budson A. Current understanding of Alzheimer’s disease diagnosis and treatment[J]. F1000Res, 2018, 7: F1000 Faculty Rev-1161.
    1. Kikuchi M, Hara N, Hasegawa M, et al. Enhancer variants associated with alzheimer’s disease affect gene expression via chromatin looping[J]. BMC Med Genom. 2019;12(1):128. - PMC - PubMed
    1. Stein J, Hua X, Lee S, et al. Voxelwise genome-wide association study (vGWAS)[J]. NeuroImage. 2010;53:1160–74. - PMC - PubMed
    1. Hao X, Yao X, Risacher S, et al. Identifying candidate genetic associations with MRI-Derived AD-Related ROI via Tree-Guided sparse Learning[J]. IEEE/ACM Trans Comput Biol Bioinf. 2018;16(6):1986–96. - PMC - PubMed
    1. Fang J, Lin D, Schulz SC, et al. Joint sparse canonical correlation analysis for detecting differential imaging genetics modules[J]. Bioinformatics. 2016;32(22):3480–8. - PMC - PubMed