Exploring Imaging Genetic Markers of Alzheimer's Disease Based on a Novel Nonlinear Correlation Analysis Algorithm

Alzheimer's disease (AD) is an irreversible neurological disorder characterized by insidious onset. Identifying potential markers in its emergence and progression is crucial for early diagnosis and treatment. Imaging genetics typically merges genetic variables with multiple imaging parameters, employing various association analysis algorithms to investigate the links between pathological phenotypes and genetic variations, and to unearth molecular-level insights from brain images. However, most existing imaging genetics algorithms based on sparse learning assume a linear relationship between genetic factors and brain functions, limiting their ability to discern complex nonlinear correlation patterns and resulting in reduced accuracy. To address these issues, we propose a novel nonlinear imaging genetic association analysis method, Deep Self-Reconstruction-based Adaptive Sparse Multi-view Deep Generalized Canonical Correlation Analysis (DSR-AdaSMDGCCA). This approach facilitates joint learning of the nonlinear relationships between pathological phenotypes and genetic variations by integrating three different types of data: structural magnetic resonance imaging (sMRI), single-nucleotide polymorphism (SNP), and gene expression data. By incorporating nonlinear transformations in DGCCA, our model effectively uncovers nonlinear associations across multiple data types. Additionally, the DSR algorithm clusters samples with identical labels, incorporating label information into the nonlinear feature extraction process and thus enhancing the performance of association analysis. The application of the DSR-AdaSMDGCCA algorithm on real data sets identified several AD risk regions (such as the hippocampus, parahippocampus, and fusiform gyrus) and risk genes (including VSIG4, NEDD4L, and PINK1), achieving maximum classification accuracy with the fewest selected features compared to baseline algorithms. Molecular biology enrichment analysis revealed that the pathways enriched by these top genes are intimately linked to AD progression, affirming that our algorithm not only improves correlation analysis performance but also identifies biologically significant markers.

Identifying frequency-dependent imaging genetic associations via hypergraph-structured multi-task sparse canonical correlation analysis

Identifying complex associations between genetic variations and imaging phenotypes is a challenging task in the research of brain imaging genetics. The previous study has proved that neuronal oscillations within distinct frequency bands are derived from frequency-dependent genetic modulation. Thus it is meaningful to explore frequency-dependent imaging genetic associations, which may give important insights into the pathogenesis of brain disorders. In this work, the hypergraph-structured multi-task sparse canonical correlation analysis (HS-MTSCCA) was developed to explore the associations between multi-frequency imaging phenotypes and single-nucleotide polymorphisms (SNPs). Specifically, we first created a hypergraph for the imaging phenotypes of each frequency and the SNPs, respectively. Then, a new hypergraph-structured constraint was proposed to learn high-order relationships among features in each hypergraph, which can introduce biologically meaningful information into the model. The frequency-shared and frequency-specific imaging phenotypes and SNPs could be identified using the multi-task learning framework. We also proposed a useful strategy to tackle this algorithm and then demonstrated its convergence. The proposed method was evaluated on four simulation datasets and a real schizophrenia dataset. The experimental results on synthetic data showed that HS-MTSCCA outperforms the other competing methods according to canonical correlation coefficients, canonical weights, and cosine similarity. And the results on real data showed that HS-MTSCCA could obtain superior canonical coefficients and canonical weights. Furthermore, the identified frequency-shared and frequency-specific biomarkers could provide more interesting and meaningful information, demonstrating that HS-MTSCCA is a powerful method for brain imaging genetics.

Effects of 3-month dapagliflozin on left atrial function in treatment-naïve patients with type 2 diabetes mellitus: Assessment using 4-dimensional echocardiography

BACKGROUND

The sodium-glucose transporter-2 (SGLT-2) inhibitor dapagliflozin can improve left ventricular (LV) performance in patients with type 2 diabetes mellitus (T2DM). However, the effects on left atrial (LA) function in treatment-naïve T2DM patients remain unclear. The aim of our study was 1) to investigate the effects of 3-month treatment with dapagliflozin on LA function in treatment-naïve patients with T2DM using 4-dimensional automated LA quantification (4D Auto LAQ) and 2) to explore linked covariation patterns of changes in clinical and LA echocardiographic variables.

METHODS

4D Auto LAQ was used to evaluate LA volumes, longitudinal and circumferential strains in treatment-naïve T2DM patients at baseline, at follow-up, and in healthy control (HC). Sparse canonical correlation analysis (sCCA) was performed to capture the linked covariation patterns between changes in clinical and LA echocardiographic variables within the treatment-naïve T2DM patient group.

RESULTS

This study finally included 61 treatment-naïve patients with T2DM without cardiovascular disease and 39 healthy controls (HC). Treatment-naïve T2DM patients showed reduced LA reservoir and conduit function at baseline compared to HC, independent of age, sex, BMI, and blood pressure (LASr: 21.11 ± 5.39 vs. 27.08 ± 5.31 %, padjusted = 0.017; LAScd: -11.51 ± 4.48 vs. -16.74 ± 4.51 %, padjusted = 0.013). After 3-month treatment with dapagliflozin, T2DM patients had significant improvements in LA reservoir and conduit function independent of BMI and blood pressure changes (LASr: 21.11 ± 5.39 vs. 23.84 ± 5.74 %, padjusted < 0.001; LAScd: -11.51 ± 4.48 vs. -12.75 ± 4.70 %, padjusted < 0.001). The clinical and LA echocardiographic parameters showed significant covariation (r = 0.562, p = 0.039). In the clinical dataset, changes in heart rate, insulin, and BMI were most associated with the LA echocardiographic variate. In the LA echocardiographic dataset, changes in LAScd, LASr, and LASr_c were most associated with the clinical variate.

CONCLUSION

Compared with HC, treatment-naïve patients with T2DM had lower LA function, and these patients benefited from dapagliflozin administration, particularly in LA function.

Preference matrix guided sparse canonical correlation analysis for mining brain imaging genetic associations in Alzheimer's disease

Investigating the relationship between genetic variation and phenotypic traits is a key issue in quantitative genetics. Specifically for Alzheimer's disease, the association between genetic markers and quantitative traits remains vague while, once identified, will provide valuable guidance for the study and development of genetics-based treatment approaches. Currently, to analyze the association of two modalities, sparse canonical correlation analysis (SCCA) is commonly used to compute one sparse linear combination of the variable features for each modality, giving a pair of linear combination vectors in total that maximizes the cross-correlation between the analyzed modalities. One drawback of the plain SCCA model is that the existing findings and knowledge cannot be integrated into the model as priors to help extract interesting correlations as well as identify biologically meaningful genetic and phenotypic markers. To bridge this gap, we introduce preference matrix guided SCCA (PM-SCCA) that not only takes priors encoded as a preference matrix but also maintains computational simplicity. A simulation study and a real-data experiment are conducted to investigate the effectiveness of the model. Both experiments demonstrate that the proposed PM-SCCA model can capture not only genotype-phenotype correlation but also relevant features effectively.

Linking negative affect, personality and social conditions to structural brain development during the transition from late adolescent to young adulthood

BACKGROUND

The transition from late adolescence to early adulthood is a period that experiences a surge of life changes and brain reorganization caused by internal and external factors, including negative affect, personality, and social conditions.

METHODS

Non-imaging phenotype and structural brain variables were available on 497 healthy participants (279 females and 218 males) between 17 and 22 years old. We used sparse canonical correlation analysis (sCCA) on the high-dimensional and longitudinal data to extract modes with maximum covariation between structural brain changes and negative affect, personality, and social conditions.

RESULTS

Separate sCCAs for cortical volume, cortical thickness, cortical surface area and subcortical volume confirmed that each imaging phenotype was correlated with non-imaging features (sCCA |r| range: 0.21-0.38, all p_FDR < 0.01). Bilateral superior frontal, left caudal anterior cingulate and bilateral caudate had the highest canonical cross-loadings (|ρ| = 0.15-0.32). In longitudinal data analysis, scan-interval, negative affect, and enthusiasm had the highest association with structural brain changes (|ρ| = 0.07-0.38); at baseline, intellect and politeness were associated with individual variability in the structural brain (|ρ| = 0.10-0.25).

LIMITATIONS

The present study used non-imaging variables only at baseline, making it impossible to explore the relationship between changing behavior and structural brain development.

CONCLUSIONS

Individual structural brain changes are associated with multiple factors. In addition to time-dependent variables, we find that negative affect, enthusiasm and social support play a numerically weak but significant role in structural brain development during the transition from late adolescence to young adulthood.

Preference Matrix Guided Sparse Canonical Correlation Analysis for Genetic Study of Quantitative Traits in Alzheimer's Disease

Investigating the relationship between genetic variation and phenotypic traits is a key issue in quantitative genetics. Specifically for Alzheimer's disease, the association between genetic markers and quantitative traits remains vague while, once identified, will provide valuable guidance for the study and development of genetic-based treatment approaches. Currently, to analyze the association of two modalities, sparse canonical correlation analysis (SCCA) is commonly used to compute one sparse linear combination of the variable features for each modality, giving a pair of linear combination vectors in total that maximizes the cross-correlation between the analyzed modalities. One drawback of the plain SCCA model is that the existing findings and knowledge cannot be integrated into the model as priors to help extract interesting correlation as well as identify biologically meaningful genetic and phenotypic markers. To bridge this gap, we introduce preference matrix guided SCCA (PM-SCCA) that not only takes priors encoded as a preference matrix but also maintains computational simplicity. A simulation study and a real-data experiment are conducted to investigate the effectiveness of the model. Both experiments demonstrate that the proposed PM-SCCA model can capture not only genotype-phenotype correlation but also relevant features effectively.

A review ofimaging genetics in Alzheimer's disease

Determining the association between genetic variation and phenotype is a key step to study the mechanism of Alzheimer's disease (AD), laying the foundation for studying drug therapies and biomarkers. AD is the most common type of dementia in the aged population. At present, three early-onset AD genes (APP, PSEN1, PSEN2) and one late-onset AD susceptibility gene apolipoprotein E (APOE) have been determined. However, the pathogenesis of AD remains unknown. Imaging genetics, an emerging interdisciplinary field, is able to reveal the complex mechanisms from the genetic level to human cognition and mental disorders via macroscopic intermediates. This paper reviews methods of establishing genotype-phenotype to explore correlations, including sparse canonical correlation analysis, sparse reduced rank regression, sparse partial least squares and so on. We found that most research work did poorly in supervised learning and exploring the nonlinear relationship between SNP-QT.

Multi-task learning based structured sparse canonical correlation analysis for brain imaging genetics

The advances in technologies for acquiring brain imaging and high-throughput genetic data allow the researcher to access a large amount of multi-modal data. Although the sparse canonical correlation analysis is a powerful bi-multivariate association analysis technique for feature selection, we are still facing major challenges in integrating multi-modal imaging genetic data and yielding biologically meaningful interpretation of imaging genetic findings. In this study, we propose a novel multi-task learning based structured sparse canonical correlation analysis (MTS2CCA) to deliver interpretable results and improve integration in imaging genetics studies. We perform comparative studies with state-of-the-art competing methods on both simulation and real imaging genetic data. On the simulation data, our proposed model has achieved the best performance in terms of canonical correlation coefficients, estimation accuracy, and feature selection accuracy. On the real imaging genetic data, our proposed model has revealed promising features of single-nucleotide polymorphisms and brain regions related to sleep. The identified features can be used to improve clinical score prediction using promising imaging genetic biomarkers. An interesting future direction is to apply our model to additional neurological or psychiatric cohorts such as patients with Alzheimer's or Parkinson's disease to demonstrate the generalizability of our method.

Identifying Biomarkers of Alzheimer's Disease via a Novel Structured Sparse Canonical Correlation Analysis Approach

Using correlation analysis to study the potential connection between brain genetics and imaging has become an effective method to understand neurodegenerative diseases. Sparse canonical correlation analysis (SCCA) makes it possible to study high-dimensional genetic information. The traditional SCCA methods can only process single-modal genetic and image data, which to some extent weaken the close connection of the brain's biological network. In some recently proposed multimodal SCCA methods, due to the limitations of penalty items, the pre-processed data needs to be further filtered to make the dimensions uniform, which may destroy the potential association of data in the same modal. In this research, in order to combine data between different modalities and to ensure that the chain relationship or graph network relationship within the same modality will not be destroyed, the original generalized fused lasso penalty was replaced with the fused pairwise group lasso (FGL) and the graph-guided pairwise group lasso (GGL) based on the method of joint sparse canonical correlation analysis (JSCCA). We used prior knowledge to construct a supervised bivariate learning model and use linear regression to select quantitative traits (QTs) of images that are strongly correlated with the Mini-mental State Examination (MMSE) scores. Compared with FGL-SCCA, the model we constructed obtained a higher gene-ROI correlation coefficient and identified more significant biomarkers, providing a theoretical basis for further understanding the complex pathology of neurodegenerative diseases.

Identifying associations among genomic, proteomic and imaging biomarkers via adaptive sparse multi-view canonical correlation analysis

To uncover the genetic underpinnings of brain disorders, brain imaging genomics usually jointly analyzes genetic variations and imaging measurements. Meanwhile, other biomarkers such as proteomic expressions can also carry valuable complementary information. Therefore, it is necessary yet challenging to investigate the underlying relationships among genetic variations, proteomic expressions, and neuroimaging measurements, which stands a chance of gaining new insights into the pathogenesis of brain disorders. Given multiple types of biomarkers, using sparse multi-view canonical correlation analysis (SMCCA) and its variants to identify the multi-way associations is straightforward. However, due to the gradient domination issue caused by the naive fusion of multiple SCCA objectives, SMCCA is suboptimal. In this paper, we proposed two adaptive SMCCA (AdaSMCCA) methods, i.e. the robustness-aware AdaSMCCA and the uncertainty-aware AdaSMCCA, to analyze the complicated associations among genetic, proteomic, and neuroimaging biomarkers. We also imposed a data-driven feature grouping penalty to the genetic data with aim to uncover the joint inheritance of neighboring genetic variations. An efficient optimization algorithm, which is guaranteed to converge, was provided. Using two state-of-the-art SMCCA as benchmarks, we evaluated robustness-aware AdaSMCCA and uncertainty-aware AdaSMCCA on both synthetic data and real neuroimaging, proteomics, and genetic data. Both proposed methods obtained higher associations and cleaner canonical weight profiles than comparison methods, indicating their promising capability for association identification and feature selection. In addition, the subsequent analysis showed that the identified biomarkers were related to Alzheimer's disease, demonstrating the power of our methods in identifying multi-way bi-multivariate associations among multiple heterogeneous biomarkers.

Relative contributions of lesion location and lesion size to predictions of varied language deficits in post-stroke aphasia

Despite the widespread use of lesion-symptom mapping (LSM) techniques to study associations between location of brain damage and language deficits, the prediction of language deficits from lesion location remains a substantial challenge. The present study examined several factors which may impact lesion-symptom prediction by (1) testing the relative predictive advantage of general language deficit scores compared to composite scores that capture specific deficit types, (2) isolating the relative contribution of lesion location compared to lesion size, and (3) comparing standard voxel-based lesion-symptom mapping (VLSM) with a multivariate method (sparse canonical correlation analysis, SCCAN). Analyses were conducted on data from 128 participants who completed a detailed battery of psycholinguistic tests and underwent structural neuroimaging (MRI or CT) to determine lesion location. For both VLSM and SCCAN, overall aphasia severity (Western Aphasia Battery Aphasia Quotient) and object naming deficits were primarily predicted by lesion size, whereas deficits in Speech Production and Speech Recognition were better predicted by a combination of lesion size and location. The implementation of both VLSM and SCCAN raises important considerations regarding controlling for lesion size in lesion-symptom mapping analyses. These findings suggest that lesion-symptom prediction is more accurate for deficits within neurally-localized cognitive systems when both lesion size and location are considered compared to broad functional deficits, which can be predicted by overall lesion size alone.

•

Lesion location improves prediction for speech production and speech recognition.

•

Broad deficits, aphasia severity and naming, are primarily predicted by lesion size.

•

Lesion location may be more informative for neurally-localized cognitive systems.

•

Predictive inference is an alternative way to control for lesion size.

Multi-Table Differential Correlation Analysis of Neuroanatomical and Cognitive Interactions in Turner Syndrome

Girls and women with Turner syndrome (TS) have a completely or partially missing X chromosome. Extensive studies on the impact of TS on neuroanatomy and cognition have been conducted. The integration of neuroanatomical and cognitive information into one consistent analysis through multi-table methods is difficult and most standard tests are underpowered. We propose a new two-sample testing procedure that compares associations between two tables in two groups. The procedure combines multi-table methods with permutation tests. In particular, we construct cluster size test statistics that incorporate spatial dependencies. We apply our new procedure to a newly collected dataset comprising of structural brain scans and cognitive test scores from girls with TS and healthy control participants (age and sex matched). We measure neuroanatomy with Tensor-Based Morphometry (TBM) and cognitive function with Wechsler IQ and NEuroPSYchological tests (NEPSY-II). We compare our multi-table testing procedure to a single-table analysis. Our new procedure reports differential correlations between two voxel clusters and a wide range of cognitive tests whereas the single-table analysis reports no differences. Our findings are consistent with the hypothesis that girls with TS have a different brain-cognition association structure than healthy controls.

DATA SYNTHESIS AND METHOD EVALUATION FOR BRAIN IMAGING GENETICS

Brain imaging genetics is an emergent research field where the association between genetic variations such as single nucleotide polymorphisms (SNPs) and neuroimaging quantitative traits (QTs) is evaluated. Sparse canonical correlation analysis (SCCA) is a bi-multivariate analysis method that has the potential to reveal complex multi-SNP-multi-QT associations. We present initial efforts on evaluating a few SCCA methods for brain imaging genetics. This includes a data synthesis method to create realistic imaging genetics data with known SNP-QT associations, application of three SCCA algorithms to the synthetic data, and comparative study of their performances. Our empirical results suggest, approximating covariance structure using an identity or diagonal matrix, an approach used in these SCCA algorithms, could limit the SCCA capability in identifying the underlying imaging genetics associations. An interesting future direction is to develop enhanced SCCA methods that effectively take into account the covariance structures in the imaging genetics data.

Sparse canonical correlation analysis relates network-level atrophy to multivariate cognitive measures in a neurodegenerative population

This study establishes that sparse canonical correlation analysis (SCCAN) identifies generalizable, structural MRI-derived cortical networks that relate to five distinct categories of cognition. We obtain multivariate psychometrics from the domain-specific sub-scales of the Philadelphia Brief Assessment of Cognition (PBAC). By using a training and separate testing stage, we find that PBAC-defined cognitive domains of language, visuospatial functioning, episodic memory, executive control, and social functioning correlate with unique and distributed areas of gray matter (GM). In contrast, a parallel univariate framework fails to identify, from the training data, regions that are also significant in the left-out test dataset. The cohort includes164 patients with Alzheimer's disease, behavioral-variant frontotemporal dementia, semantic variant primary progressive aphasia, non-fluent/agrammatic primary progressive aphasia, or corticobasal syndrome. The analysis is implemented with open-source software for which we provide examples in the text. In conclusion, we show that multivariate techniques identify biologically-plausible brain regions supporting specific cognitive domains. The findings are identified in training data and confirmed in test data.