Clinical application of sparse canonical correlation analysis to detect genetic associations with cortical thickness in Alzheimer's disease.

Introduction: Alzheimer's disease (AD) is a progressive neurodegenerative disease characterized by cerebral cortex atrophy. In this study, we used sparse canonical correlation analysis (SCCA) to identify associations between single nucleotide polymorphisms (SNPs) and cortical thickness in the Korean population. We also investigated the role of the SNPs in neurological outcomes, including neurodegeneration and cognitive dysfunction. Methods: We recruited 1125 Korean participants who underwent neuropsychological testing, brain magnetic resonance imaging, positron emission tomography, and microarray genotyping. We performed group-wise SCCA in Aß negative (-) and Aß positive (+) groups. In addition, we performed mediation, expression quantitative trait loci, and pathway analyses to determine the functional role of the SNPs. Results: We identified SNPs related to cortical thickness using SCCA in Aß negative and positive groups and identified SNPs that improve the prediction performance of cognitive impairments. Among them, rs9270580 was associated with cortical thickness by mediating Aß uptake, and three SNPs (rs2271920, rs6859, rs9270580) were associated with the regulation of CHRNA2, NECTIN2, and HLA genes. Conclusion: Our findings suggest that SNPs potentially contribute to cortical thickness in AD, which in turn leads to worse clinical outcomes. Our findings contribute to the understanding of the genetic architecture underlying cortical atrophy and its relationship with AD.

Linked patterns of symptoms and cognitive covariation with functional brain controllability in major depressive disorder.

BACKGROUND: Controllability analysis is an approach developed for evaluating the ability of a brain region to modulate function in other regions, which has been found to be altered in major depressive disorder (MDD). Both depressive symptoms and cognitive impairments are prominent features of MDD, but the case-control differences of controllability between MDD and controls can not fully interpret the contribution of both clinical symptoms and cognition to brain controllability and linked patterns among them in MDD. METHODS: Sparse canonical correlation analysis was used to investigate the associations between resting-state functional brain controllability at the network level and clinical symptoms and cognition in 99 first-episode medication-naïve patients with MDD. FINDINGS: Average controllability was significantly correlated with clinical features. The average controllability of the dorsal attention network (DAN) and visual network had the highest correlations with clinical variables. Among clinical variables, depressed mood, suicidal ideation and behaviour, impaired work and activities, and gastrointestinal symptoms were significantly negatively associated with average controllability, and reduced cognitive flexibility was associated with reduced average controllability. INTERPRETATION: These findings highlight the importance of brain regions in modulating activity across brain networks in MDD, given their associations with symptoms and cognitive impairments observed in our study. Disrupted control of brain reconfiguration of DAN and visual network during their state transitions may represent a core brain mechanism for the behavioural impairments observed in MDD. FUNDING: National Natural Science Foundation of China (82001795 and 82027808), National Key R&D Program (2022YFC2009900), and Sichuan Science and Technology Program (2024NSFSC0653).

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.

Classifying breast cancer subtypes on multi-omics data via sparse canonical correlation analysis and deep learning.

BACKGROUND: Classifying breast cancer subtypes is crucial for clinical diagnosis and treatment. However, the early symptoms of breast cancer may not be apparent. Rapid advances in high-throughput sequencing technology have led to generating large number of multi-omics biological data. Leveraging and integrating the available multi-omics data can effectively enhance the accuracy of identifying breast cancer subtypes. However, few efforts focus on identifying the associations of different omics data to predict the breast cancer subtypes. RESULTS: In this paper, we propose a differential sparse canonical correlation analysis network (DSCCN) for classifying the breast cancer subtypes. DSCCN performs differential analysis on multi-omics expression data to identify differentially expressed (DE) genes and adopts sparse canonical correlation analysis (SCCA) to mine highly correlated features between multi-omics DE-genes. Meanwhile, DSCCN uses multi-task deep learning neural network separately to train the correlated DE-genes to predict breast cancer subtypes, which spontaneously tackle the data heterogeneity problem in integrating multi-omics data. CONCLUSIONS: The experimental results show that by mining the associations among multi-omics data, DSCCN is more capable of accurately classifying breast cancer subtypes than the existing methods.

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.

On statistical inference with high-dimensional sparse CCA.

We consider asymptotically exact inference on the leading canonical correlation directions and strengths between two high-dimensional vectors under sparsity restrictions. In this regard, our main contribution is developing a novel representation of the Canonical Correlation Analysis problem, based on which one can operationalize a one-step bias correction on reasonable initial estimators. Our analytic results in this regard are adaptive over suitable structural restrictions of the high-dimensional nuisance parameters, which, in this set-up, correspond to the covariance matrices of the variables of interest. We further supplement the theoretical guarantees behind our procedures with extensive numerical studies.

The unity and diversity of verbal and visuospatial creativity: Dynamic changes in hemispheric lateralisation.

The investigation of similarities and differences in the mechanisms of verbal and visuospatial creative thinking has long been a controversial topic. Prior studies found that visuospatial creativity was primarily supported by the right hemisphere, whereas verbal creativity relied on the interaction between both hemispheres. However, creative thinking also involves abundant dynamic features that may have been ignored in the previous static view. Recently, a new method has been developed that measures hemispheric laterality from a dynamic perspective, providing new insight into the exploration of creative thinking. In the present study, dynamic lateralisation index was calculated with resting-state fMRI data. We combined the dynamic lateralisation index with sparse canonical correlation analysis to examine similarities and differences in the mechanisms of verbal and visuospatial creativity. Our results showed that the laterality reversal of the default mode network, fronto-parietal network, cingulo-opercular network and visual network contributed significantly to both verbal and visuospatial creativity and consequently could be considered the common neural mechanisms shared by these creative modes. In addition, we found that verbal creativity relied more on the language network, while visuospatial creativity relied more on the somatomotor network, which can be considered a difference in their mechanism. Collectively, these findings indicated that verbal and visuospatial creativity may have similar mechanisms to support the basic creative thinking process and different mechanisms to adapt to the specific task conditions. These findings may have significant implications for our understanding of the neural mechanisms of different types of creative thinking.

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.

Linked patterns of interhemispheric functional connectivity and microstructural characteristics of the corpus callosum in antipsychotic-naive first-episode schizophrenia.

OBJECTIVE: Many magnetic resonance imaging (MRI) studies have showed significant structural abnormalities of the corpus callosum (CC) and dysregulated interhemispheric functional connectivity (FC) in schizophrenia. Although the hemispheres are mainly linked through CC, few studies directly examined the relationship between aberrant interhemispheric FC and the white matter deficits of the CC in schizophrenia. METHODS: One hundred and sixty-nine antipsychotic-naive first-episode schizophrenia patients (AN-FES) and 214 healthy controls (HCs) were recruited. Diffusional and functional MRI data were obtained for each participant, and fractional anisotropy (FA) values of the five CC subregions and interhemispheric FC for each participant were acquired. Between-group differences in these metrics were compared using multivariate analysis of covariance (MANCOVA). Moreover, sparse canonical correlation analysis (sCCA) was conducted to explore correlations of fibers integrity of the CC subregions with dysregulated interhemispheric FC in patients. RESULTS: Compared with HCs, the patients with schizophrenia showed significantly reduced FA values of the CC subregions and dysregulated connectivity between two cerebral hemispheres. The canonical correlation coefficients identified five significant sCCA modes between FA and FC (r > 0.75, p < 0.001), suggesting strong relationships between FA values of the CC subregions and interhemispheric FC in patients. CONCLUSION: Our findings support a key role of CC in maintaining ongoing functional communication between two cerebral hemispheres, and suggest that microstructural changes of white matter fibers crossing different CC subregions may affect special interhemispheric FC in schizophrenia.

A multi-task SCCA method for brain imaging genetics and its application in neurodegenerative diseases.

BACKGROUND AND OBJECTIVES: In brain imaging genetics, multi-task sparse canonical correlation analysis (MTSCCA) is effective to study the bi-multivariate associations between genetic variations such as single nucleotide polymorphisms (SNPs) and multi-modal imaging quantitative traits (QTs). However, most existing MTSCCA methods are neither supervised nor capable of distinguishing the shared patterns of multi-modal imaging QTs from the specific patterns. METHODS: A new diagnosis-guided MTSCCA (DDG-MTSCCA) with parameter decomposition and graph-guided pairwise group lasso penalty was proposed. Specifically, the multi-tasking modeling paradigm enables us to comprehensively identify risk genetic loci by jointly incorporating multi-modal imaging QTs. The regression sub-task was raised to guide the selection of diagnosis-related imaging QTs. To reveal the diverse genetic mechanisms, the parameter decomposition and different constraints were utilized to facilitate the identification of modality-consistent and -specific genotypic variations. Besides, a network constraint was added to find out meaningful brain networks. The proposed method was applied to synthetic data and two real neuroimaging data sets respectively from Alzheimer's disease neuroimaging initiative (ADNI) and Parkinson's progression marker initiative (PPMI) databases. RESULTS: Compared with the competitive methods, the proposed method exhibited higher or comparable canonical correlation coefficients (CCCs) and better feature selection results. In particular, in the simulation study, DDG-MTSCCA showed the best anti-noise ability and achieved the highest average hit rate, about 25% higher than MTSCCA. On the real data of Alzheimer's disease (AD) and Parkinson's disease (PD), our method obtained the highest average testing CCCs, about 40% ∼ 50% higher than MTSCCA. Especially, our method could select more comprehensive feature subsets, and the top five SNPs and imaging QTs were all disease-related. The ablation experimental results also demonstrated the significance of each component in the model, i.e., the diagnosis guidance, parameter decomposition, and network constraint. CONCLUSIONS: These results on simulated data, ADNI and PPMI cohorts suggested the effectiveness and generalizability of our method in identifying meaningful disease-related markers. DDG-MTSCCA could be a powerful tool in brain imaging genetics, worthy of in-depth study.

Patterns of brain dynamic functional connectivity are linked with attention-deficit/hyperactivity disorder-related behavioral and cognitive dimensions.

BACKGROUND: Attention-deficit/hyperactivity disorder (ADHD) is a clinically heterogeneous neurodevelopmental disorder defined by characteristic behavioral and cognitive features. Abnormal brain dynamic functional connectivity (dFC) has been associated with the disorder. The full spectrum of ADHD-related variation of brain dynamics and its association with behavioral and cognitive features remain to be established. METHODS: We sought to identify patterns of brain dynamics linked to specific behavioral and cognitive dimensions using sparse canonical correlation analysis across a cohort of children with and without ADHD (122 children in total, 63 with ADHD). Then, using mediation analysis, we tested the hypothesis that cognitive deficits mediate the relationship between brain dynamics and ADHD-associated behaviors. RESULTS: We identified four distinct patterns of dFC, each corresponding to a specific dimension of behavioral or cognitive function (r = 0.811-0.879). Specifically, the inattention/hyperactivity dimension was positively associated with dFC within the default mode network (DMN) and negatively associated with dFC between DMN and the sensorimotor network (SMN); the somatization dimension was positively associated with dFC within DMN and SMN; the inhibition and flexibility dimension and fluency and memory dimensions were both positively associated with dFC within DMN and between DMN and SMN, and negatively associated with dFC between DMN and the fronto-parietal network. Furthermore, we observed that cognitive functions of inhibition and flexibility mediated the relationship between brain dynamics and behavioral manifestations of inattention and hyperactivity. CONCLUSIONS: These findings document the importance of distinct patterns of dynamic functional brain activity for different cardinal behavioral and cognitive features related to ADHD.

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 pFDR < 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.

Controllability of Functional Brain Networks and Its Clinical Significance in First-Episode Schizophrenia.

BACKGROUND AND HYPOTHESIS: Disrupted control of brain state transitions may contribute to the diverse dysfunctions of cognition, emotion, and behavior that are fundamental to schizophrenia. Control theory provides the rationale for evaluating brain state transitions from a controllability perspective, which may help reveal the brain mechanism for clinical features such as cognitive control deficits associated with schizophrenia. We hypothesized that brain controllability would be altered in patients with schizophrenia, and that controllability of brain networks would be related to clinical symptomatology. STUDY DESIGN: Controllability measurements of functional brain networks, including average controllability and modal controllability, were calculated and compared between 125 first-episode never-treated patients with schizophrenia and 133 healthy controls (HCs). Associations between controllability metrics and clinical symptoms were evaluated using sparse canonical correlation analysis. STUDY RESULTS: Compared to HCs, patients showed significantly increased average controllability (PFDR = .023) and decreased modal controllability (PFDR = .023) in dorsal anterior cingulate cortex (dACC). General psychopathology symptoms and positive symptoms were positively correlated with average controllability in regions of default mode network and negatively associated with average controllability in regions of sensorimotor, dorsal attention, and frontoparietal networks. CONCLUSIONS: Our findings suggest that altered controllability of functional activity in dACC may play a critical role in the pathophysiology of schizophrenia, consistent with the importance of this region in cognitive and brain state control operations. The demonstration of associations of functional controllability with psychosis symptoms suggests that the identified alterations in average controllability of brain function may contribute to the severity of acute psychotic illness in schizophrenia.

Dimension-wise sparse low-rank approximation of a matrix with application to variable selection in high-dimensional integrative analyzes of association.

Many research proposals involve collecting multiple sources of information from a set of common samples, with the goal of performing an integrative analysis describing the associations between sources. We propose a method that characterizes the dominant modes of co-variation between the variables in two datasets while simultaneously performing variable selection. Our method relies on a sparse, low rank approximation of a matrix containing pairwise measures of association between the two sets of variables. We show that the proposed method shares a close connection with another group of methods for integrative data analysis - sparse canonical correlation analysis (CCA). Under some assumptions, the proposed method and sparse CCA aim to select the same subsets of variables. We show through simulation that the proposed method can achieve better variable selection accuracies than two state-of-the-art sparse CCA algorithms. Empirically, we demonstrate through the analysis of DNA methylation and gene expression data that the proposed method selects variables that have as high or higher canonical correlation than the variables selected by sparse CCA methods, which is a rather surprising finding given that objective function of the proposed method does not actually maximize the canonical correlation.

Exploring Brain Structural and Functional Biomarkers in Schizophrenia via Brain-Network-Constrained Multi-View SCCA.

Recent studies have proved that dynamic regional measures extracted from the resting-state functional magnetic resonance imaging, such as the dynamic fractional amplitude of low-frequency fluctuation (d-fALFF), could provide a great insight into brain dynamic characteristics of the schizophrenia. However, the unimodal feature is limited for delineating the complex patterns of brain deficits. Thus, functional and structural imaging data are usually analyzed together for uncovering the neural mechanism of schizophrenia. Investigation of neural function-structure coupling enables to find the potential biomarkers and further helps to understand the biological basis of schizophrenia. Here, a brain-network-constrained multi-view sparse canonical correlation analysis (BN-MSCCA) was proposed to explore the intrinsic associations between brain structure and dynamic brain function. Specifically, the d-fALFF was first acquired based on the sliding window method, whereas the gray matter map was computed based on voxel-based morphometry analysis. Then, the region-of-interest (ROI)-based features were extracted and further selected by performing the multi-view sparse canonical correlation analysis jointly with the diagnosis information. Moreover, the brain-network-based structural constraint was introduced to prompt the detected biomarkers more interpretable. The experiments were conducted on 191 patients with schizophrenia and 191 matched healthy controls. Results showed that the BN-MSCCA could identify the critical ROIs with more sparse canonical weight patterns, which are corresponding to the specific brain networks. These are biologically meaningful findings and could be treated as the potential biomarkers. The proposed method also obtained a higher canonical correlation coefficient for the testing data, which is more consistent with the results on training data, demonstrating its promising capability for the association identification. To demonstrate the effectiveness of the potential clinical applications, the detected biomarkers were further analyzed on a schizophrenia-control classification task and a correlation analysis task. The experimental results showed that our method had a superior performance with a 5-8% increment in accuracy and 6-10% improvement in area under the curve. Furthermore, two of the top-ranked biomarkers were significantly negatively correlated with the positive symptom score of Positive and Negative Syndrome Scale (PANSS). Overall, the proposed method could find the association between brain structure and dynamic brain function, and also help to identify the biological meaningful biomarkers of schizophrenia. The findings enable our further understanding of this disease.

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.

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.

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.

Associating brain imaging phenotypes and genetic in Alzheimer's disease via JSCCA approach with autocorrelation constraints.

Imaging genetics research can explore the potential correlation between imaging and genomics. Most association analysis methods cannot effectively use the prior knowledge of the original data. In this respect, we add the prior knowledge of each original data to mine more effective biomarkers. The study of imaging genetics based on the sparse canonical correlation analysis (SCCA) is helpful to mine the potential biomarkers of neurological diseases. To improve the performance and interpretability of SCCA, we proposed a penalty method based on the autocorrelation matrix for discovering the possible biological mechanism between single nucleotide polymorphisms (SNP) variations and brain regions changes of Alzheimer's disease (AD). The addition of the penalty allows the proposed algorithm to analyze the correlation between different modal features. The proposed algorithm obtains more biologically interpretable ROIs and SNPs that are significantly related to AD, which has better anti-noise performance. Compared with other SCCA-based algorithms (JCB-SCCA, JSNMNMF), the proposed algorithm can still maintain a stronger correlation with ground truth even when the noise is larger. Then, we put the regions of interest (ROI) selected by the three algorithms into the SVM classifier. The proposed algorithm has higher classification accuracy. Also, we use ridge regression with SNPs selected by three algorithms and four AD risk ROIs. The proposed algorithm has a smaller root mean square error (RMSE). It shows that proposed algorithm has a good ability in association recognition and feature selection. Furthermore, it selects important features more stably, improving the clinical diagnosis of new potential biomarkers.