Identification of image genetic biomarkers of Alzheimer's disease by orthogonal structured sparse canonical correlation analysis based on a diagnostic information fusion

Wei Yin; Tao Yang; GuangYu Wan; Xiong Zhou; Wei Yin; Tao Yang; GuangYu Wan; Xiong Zhou

doi:10.3934/mbe.2023741

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 9: 16648-16662. doi: 10.3934/mbe.2023741

Previous Article Next Article

Research article Special Issues

Identification of image genetic biomarkers of Alzheimer's disease by orthogonal structured sparse canonical correlation analysis based on a diagnostic information fusion

Department of Radiology, Xianning Central Hospital, The First Affiliated Hospital of Hubei University of Science and Technology, Hubei 437000, China

Academic Editor: Yang Kuang
† These two authors contributed equally.

Received: 31 March 2023 Revised: 08 June 2023 Accepted: 04 July 2023 Published: 18 August 2023

Alzheimer's disease (AD) is an irreversible neurodegenerative disease, and its incidence increases yearly. Because AD patients will have cognitive impairment and personality changes, it has caused a heavy burden on the family and society. Image genetics takes the structure and function of the brain as a phenotype and studies the influence of genetic variation on the structure and function of the brain. Based on the structural magnetic resonance imaging data and transcriptome data of AD and healthy control samples in the Alzheimer's Disease Neuroimaging Disease database, this paper proposed the use of an orthogonal structured sparse canonical correlation analysis for diagnostic information fusion algorithm. The algorithm added structural constraints to the region of interest (ROI) of the brain. Integrating the diagnostic information of samples can improve the correlation performance between samples. The results showed that the algorithm could extract the correlation between the two modal data and discovered the brain regions most affected by multiple risk genes and their biological significance. In addition, we also verified the diagnostic significance of risk ROIs and risk genes for AD. The code of the proposed algorithm is available at https://github.com/Wanguangyu111/OSSCCA-DIF.
- Alzheimer's disease,
- image genetics,
- canonical correlation analysis,
- structural constraints,
- diagnostic model
Citation: Wei Yin, Tao Yang, GuangYu Wan, Xiong Zhou. Identification of image genetic biomarkers of Alzheimer's disease by orthogonal structured sparse canonical correlation analysis based on a diagnostic information fusion[J]. Mathematical Biosciences and Engineering, 2023, 20(9): 16648-16662. doi: 10.3934/mbe.2023741

Related Papers:

Abstract

Alzheimer's disease (AD) is an irreversible neurodegenerative disease, and its incidence increases yearly. Because AD patients will have cognitive impairment and personality changes, it has caused a heavy burden on the family and society. Image genetics takes the structure and function of the brain as a phenotype and studies the influence of genetic variation on the structure and function of the brain. Based on the structural magnetic resonance imaging data and transcriptome data of AD and healthy control samples in the Alzheimer's Disease Neuroimaging Disease database, this paper proposed the use of an orthogonal structured sparse canonical correlation analysis for diagnostic information fusion algorithm. The algorithm added structural constraints to the region of interest (ROI) of the brain. Integrating the diagnostic information of samples can improve the correlation performance between samples. The results showed that the algorithm could extract the correlation between the two modal data and discovered the brain regions most affected by multiple risk genes and their biological significance. In addition, we also verified the diagnostic significance of risk ROIs and risk genes for AD. The code of the proposed algorithm is available at https://github.com/Wanguangyu111/OSSCCA-DIF.

References

[1]	R. Au, R. J. Piers, L. Lancashire, Back to the future: Alzheimer's disease heterogeneity revisited, Alzheimer's Dementia: Diagn. Assess. Dis. Monit., 1 (2015), 368–370. https://doi.org/10.1016/j.dadm.2015.05.006 doi: 10.1016/j.dadm.2015.05.006
[2]	J. Ha, C. Park, MLMD: Metric learning for predicting MiRNA-disease associations, IEEE Access, 9 (2021), 78847–78858, https://doi.org/10.1109/ACCESS.2021.3084148 doi: 10.1109/ACCESS.2021.3084148
[3]	J. Ha, MDMF: Predicting miRNA-Disease association based on matrix factorization with disease similarity constraint, J. Pers. Med., 12 (2022), 885. https://doi.org/10.3390/jpm12060885 doi: 10.3390/jpm12060885
[4]	J. Ha, SMAP: Similarity-based matrix factorization framework for inferring miRNA-disease association, Knowl.-Based Syst., 263 (2023), 110295. https://doi.org/10.1016/j.knosys.2023.110295 doi: 10.1016/j.knosys.2023.110295
[5]	J. Ha, S. Park, NCMD: Node2vec-based neural collaborative filtering for predicting MiRNA-disease association, IEEE/ACM Trans. Comput. Biol. Bioinf., 20 (2023), 1257–1268. https://doi.org/10.1109/TCBB.2022.3191972 doi: 10.1109/TCBB.2022.3191972
[6]	C. Park, J. Ha, S. Park, Prediction of Alzheimer's disease based on deep neural network by integrating gene expression and DNA methylation dataset, Expert Syst. Appl., 140 (2019), 112873. https://doi.org/10.1016/j.eswa.2019.112873 doi: 10.1016/j.eswa.2019.112873
[7]	S. Wang, H. Chen, W. Kong, F. Ke, K.Wei, Identify biomarkers of alzheimer's disease based on multi-task canonical correlation analysis and regression model, J. Mol. Neurosci., 72 (2022), 1749–1763. https://doi.org/10.1007/s12031-022-02031-9 doi: 10.1007/s12031-022-02031-9
[8]	D. M. Witten, R. Tibshirani, T. Hastie, A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis, Biostatistics, 10 (2009), 515–534. https://doi.org/10.1093/biostatistics/kxp008 doi: 10.1093/biostatistics/kxp008
[9]	L. Du, T. Zhang, K. Liu, J. Yan, X. Yao, S. L. Risacher, et al., Identifying associations between brain imaging phenotypes and genetic factors via a novel structured SCCA approach, in International Conference on Information Processing in Medical Imaging, 10265 (2017), 543–555. https://doi.org/10.1007/978-3-319-59050-9_43
[10]	L. Du, F. Liu, K. Liu, X. Yao, S. L. Risacher, J. Han, et al., Identifying diagnosis-specific genotype-phenotype associations via joint multitask sparse canonical correlation analysis and classification, Bioinformatics, 36 (2020), 371–379. https://doi.org/10.1093/bioinformatics/btaa434 doi: 10.1093/bioinformatics/btaa434
[11]	X. Hao, Q. Tan, Y. Guo, Y. Xiao, M. Yu, M. Wang, et al., Identifying modality-consistent and modality-specific features via label-guided multi-task sparse canonical correlation analysis for neuroimaging genetics, IEEE Trans. Biomed. Eng., 70 (2023), 831–840. https://doi.org/10.1109/TBME.2022.3203152 doi: 10.1109/TBME.2022.3203152
[12]	N. Q. K. Le, D. T. Do, T. T. Nguyen, Q. A. Le, A sequence-based prediction of Kruppel-like factors proteins using XGBoost and optimized features, Gene, 787 (2021), 145643. https://doi.org/10.1016/j.gene.2021.145643 doi: 10.1016/j.gene.2021.145643
[13]	Q. H. Kha, Q. T. Ho, N. Q. K. Le, Identifying SNARE proteins using an alignment-free method based on multiscan convolutional neural network and PSSM profiles, J. Chem. Inf. Model., 62 (2022), 4820–4826. https://doi.org/10.1021/acs.jcim.2c01034 doi: 10.1021/acs.jcim.2c01034
[14]	J. Zhan, M. Brys, L. Glodzik, W. Tsui, E. Javier, J. Wegiel, et al., An entorhinal cortex sulcal pattern is associated with Alzheimer's disease, Hum. Brain Mapp., 30 (2009), 874–882. https://doi.org/10.1002/hbm.20549 doi: 10.1002/hbm.20549
[15]	M. Zhou, F. Zhang, L. Zhao, J. Qian, C. Dong, Entorhinal cortex: a good biomarker of mild cognitive impairment and mild Alzheimer's disease, Rev. Neurosci., 27 (2016), 185–195. https://doi.org/10.1515/revneuro-2015-0019 doi: 10.1515/revneuro-2015-0019
[16]	A. A. Thaker, B. D. Weinberg, W. P. Dillon, C. P. Hess, H. J. Cabral, D. A. Fleischman, et al., Entorhinal cortex: Antemortem cortical thickness and postmortem neurofibrillary tangles and amyloid Pathology, Am. J. Neuroradiol., 38 (2017), 961–965. https://doi.org/10.3174/ajnr.A5133 doi: 10.3174/ajnr.A5133
[17]	D. Wang, P. Wang, X. Bian, S. Xu, Q. Zhou, Y. Zhang, et al., Elevated plasma levels of exosomal BACE1‑AS combined with the volume and thickness of the right entorhinal cortex may serve as a biomarker for the detection of Alzheimer's disease, Mol. Med. Rep., 22 (2020), 227–238. https://doi.org/10.3892/mmr.2020.11118 doi: 10.3892/mmr.2020.11118
[18]	T. H. L. G. Vereecken, O. J. M. Vogels, R. Nieuwenhuys, Neuron loss and shrinkage in the amygdala in Alzheimer's disease, Neurobiol. Aging, 15 (1994), 45–54. https://doi.org/10.1016/0197-4580(94)90143-0 doi: 10.1016/0197-4580(94)90143-0
[19]	C. L. Grady, M. L. Furey, P. Pietrini, B. Horwitz, S. I. Rapoport, Altered brain functional connectivity and impaired short-term memory in Alzheimer's disease, Brain, 124 (2001), 739–756. https://doi.org/10.1093/brain/124.4.739 doi: 10.1093/brain/124.4.739
[20]	D. Horínek, A. Varjassyová, J. Hort, Magnetic resonance analysis of amygdalar volume in Alzheimer's disease, Curr. Opin. Psychiatry, 20 (2007), 273–277. https://doi.org/10.1097/YCO.0b013e3280ebb613 doi: 10.1097/YCO.0b013e3280ebb613
[21]	D. W. Wang, S. L. Ding, X. L. Bian, S. Y. Zhou, H. Yang, P. Wang, Diagnostic value of amygdala volume on structural magnetic resonance imaging in Alzheimer's disease, World J. Clin. Cases, 9 (2021), 4627–4636. https://doi.org/10.12998/wjcc.v9.i18.4627 doi: 10.12998/wjcc.v9.i18.4627
[22]	J. Soldner, T. Meindl, W. Koch, A. L. W. Bokde, M. F. Reiser, H. Möller, et al., Strukturelle und funktionelle neuronale Konnektivität bei der Alzheimer-Krankheit, Nervenarzt, 83 (2012), 878–887. https://doi.org/10.1007/s00115-011-3326-3 doi: 10.1007/s00115-011-3326-3
[23]	G. H. Weissberger, R. J. Melrose, C. M. Fanale, J. V. Veliz, D. L. Sultzer, Cortical Metabolic and Cognitive Correlates of Disorientation in Alzheimer's Disease, J. Alzheimer's Dis., 60 (2017), 707–719. https://doi.org/10.3233/JAD-170420 doi: 10.3233/JAD-170420
[24]	M. A. Busche, B. T. Hyman, Synergy between amyloid-β and tau in Alzheimer's disease, Nat. Neurosci., 23 (2020), 1183–1193. https://doi.org/10.1038/s41593-020-0687-6 doi: 10.1038/s41593-020-0687-6
[25]	C. W. Chang, E. Shao, L. Mucke, Tau: Enabler of diverse brain disorders and target of rapidly evolving therapeutic strategies, Science, 371 (2021). https://doi.org/10.1126/science.abb8255 doi: 10.1126/science.abb8255
[26]	K. Stefanoska, M. Gajwani, A. R. P. Tan, H. I. Ahel, P. R. Asih, A. Volkerling, et al., Alzheimer's disease: Ablating single master site abolishes tau hyperphosphorylation, Sci. Adv., 8 (2022). https://doi.org/10.1126/sciadv.abl8809 doi: 10.1126/sciadv.abl8809
[27]	B. Decourt, D. K. Lahiri, M. N. Sabbagh, Targeting tumor necrosis factor alpha for Alzheimer's disease, Curr. Alzheimer Res., 14 (2017), 412–425. https://doi.org/10.2174/1567205013666160930110551 doi: 10.2174/1567205013666160930110551
[28]	M. Aliashrafi, M. Nasehi, M. R. Zarrindast, M. T. Joghataei, H. Zali, S. D. Siadat, Association of microbiota-derived propionic acid and Alzheimer's disease bioinformatics analysis, J. Diabetes Metab. Disord., 19 (2020), 783–804, https://doi.org/10.1007/s40200-020-00564-7 doi: 10.1007/s40200-020-00564-7
[29]	P. Zeng, H. F Su., C. Y. Ye, S. W. Qiu, Q. Tian, Therapeutic mechanism and key alkaloids of uncaria rhynchophylla in alzheimer's disease from the perspective of pathophysiological processes, Front. Pharmacol., 12 (2021), 806984. https://doi.org/10.3389/fphar.2021.806984 doi: 10.3389/fphar.2021.806984
[30]	B. Wang, W. Liu, F. Sun, Nucleosome assembly protein 1-like 5 alleviates Alzheimer's disease-like pathological characteristics in a cell model, Front. Mol. Neurosci., 15 (2022), 1034766. https://doi.org/10.3389/fnmol.2022.1034766 doi: 10.3389/fnmol.2022.1034766
[31]	K. M. McKibben, E. Rhoades, Independent tubulin binding and polymerization by the proline-rich region of Tau is regulated by Tau's N-terminal domain, J. Biol. Chem., 294 (2019), 19381–19394. https://doi.org/10.1074/jbc.RA119.010172 doi: 10.1074/jbc.RA119.010172
[32]	E. Grünblatt, P. Riederer, Aldehyde dehydrogenase (ALDH) in Alzheimer's and Parkinson's disease, J. Neural Transm., 123 (2016), 83–90. https://doi.org/10.1007/s00702-014-1320-1 doi: 10.1007/s00702-014-1320-1
[33]	R. Tao, M. Liao, Y. Wang, H. Wang, Y. Tan, S. Qin, et al., In situ imaging of formaldehyde in live mice with high spatiotemporal resolution reveals aldehyde dehydrogenase-2 as a potential target for Alzheimer's disease treatment, Anal. Chem., 94 (2022), 1308–1317. https://doi.org/10.1021/acs.analchem.1c04520 doi: 10.1021/acs.analchem.1c04520
[34]	M. Song, Y. A. Kwon, Y. Lee, H. Kim, J. H. Yun, S. Kim, et al., G1/S cell cycle checkpoint defect in lymphocytes from patients with Alzheimer's disease, Psychiatry Invest., 9 (2012), 413–417. https://doi.org/10.4306/pi.2012.9.4.413 doi: 10.4306/pi.2012.9.4.413
[35]	A. S. Bhounsule, L. K. Bhatt, K. S. Prabhavalkar, M. Oza, Cyclin dependent kinase 5: A novel avenue for Alzheimer's disease, Brain Res. Bull., 132 (2017), 28–38. https://doi.org/10.1016/j.brainresbull.2017.05.006 doi: 10.1016/j.brainresbull.2017.05.006

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)