Multivariate brain-behaviour associations in psychiatric disorders.

Mapping brain-behaviour associations is paramount to understand and treat psychiatric disorders. Standard approaches involve investigating the association between one brain and one behavioural variable (univariate) or multiple variables against one brain/behaviour feature ('single' multivariate). Recently, large multimodal datasets have propelled a new wave of studies that leverage on 'doubly' multivariate approaches capable of parsing the multifaceted nature of both brain and behaviour simultaneously. Within this movement, canonical correlation analysis (CCA) and partial least squares (PLS) emerge as the most popular techniques. Both seek to capture shared information between brain and behaviour in the form of latent variables. We provide an overview of these methods, review the literature in psychiatric disorders, and discuss the main challenges from a predictive modelling perspective. We identified 39 studies across four diagnostic groups: attention deficit and hyperactive disorder (ADHD, k = 4, N = 569), autism spectrum disorders (ASD, k = 6, N = 1731), major depressive disorder (MDD, k = 5, N = 938), psychosis spectrum disorders (PSD, k = 13, N = 1150) and one transdiagnostic group (TD, k = 11, N = 5731). Most studies (67%) used CCA and focused on the association between either brain morphology, resting-state functional connectivity or fractional anisotropy against symptoms and/or cognition. There were three main findings. First, most diagnoses shared a link between clinical/cognitive symptoms and two brain measures, namely frontal morphology/brain activity and white matter association fibres (tracts between cortical areas in the same hemisphere). Second, typically less investigated behavioural variables in multivariate models such as physical health (e.g., BMI, drug use) and clinical history (e.g., childhood trauma) were identified as important features. Finally, most studies were at risk of bias due to low sample size/feature ratio and/or in-sample testing only. We highlight the importance of carefully mitigating these sources of bias with an exemplar application of CCA.

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.

Multivariate canonical correlation analysis identifies additional genetic variants for chronic kidney disease.

Chronic kidney diseases (CKD) have genetic associations with kidney function. Univariate genome-wide association studies (GWAS) have identified single nucleotide polymorphisms (SNPs) associated with estimated glomerular filtration rate (eGFR) and blood urea nitrogen (BUN), two complementary kidney function markers. However, it is unknown whether additional SNPs for kidney function can be identified by multivariate statistical analysis. To address this, we applied canonical correlation analysis (CCA), a multivariate method, to two individual-level CKD genotype datasets, and metaCCA to two published GWAS summary statistics datasets. We identified SNPs previously associated with kidney function by published univariate GWASs with high replication rates, validating the metaCCA method. We then extended discovery and identified previously unreported lead SNPs for both kidney function markers, jointly. These showed expression quantitative trait loci (eQTL) colocalisation with genes having significant differential expression between CKD and healthy individuals. Several of these identified lead missense SNPs were predicted to have a functional impact, including in SLC14A2. We also identified previously unreported lead SNPs that showed significant correlation with both kidney function markers, jointly, in the European ancestry CKDGen, National Unified Renal Translational Research Enterprise (NURTuRE)-CKD and Salford Kidney Study (SKS) datasets. Of these, rs3094060 colocalised with FLOT1 gene expression and was significantly more common in CKD cases in both NURTURE-CKD and SKS, than in the general population. Overall, by using multivariate analysis by CCA, we identified additional SNPs and genes for both kidney function and CKD, that can be prioritised for further CKD analyses.

Exploring changes in brain function in IBD patients using SPCCA: a study of simultaneous EEG-fMRI.

Research on functional changes in the brain of inflammatory bowel disease (IBD) patients is emerging around the world, which brings new perspectives to medical research. In this paper, the methods of canonical correlation analysis (CCA), kernel canonical correlation analysis (KCCA), and sparsity preserving canonical correlation analysis (SPCCA) were applied to the fusion of simultaneous EEG-fMRI data from 25 IBD patients and 15 healthy individuals. The CCA, KCCA and SPCCA fusion methods were used for data processing to compare the results obtained by the three methods. The results clearly show that there is a significant difference in the activation intensity between IBD and healthy control (HC), not only in the frontal lobe (p < 0.01) and temporal lobe (p < 0.01) regions, but also in the posterior cingulate gyrus (p < 0.01), gyrus rectus (p < 0.01), and amygdala (p < 0.01) regions, which are usually neglected. The mean difference in the SPCCA activation intensity was 60.1. However, the mean difference in activation intensity was only 36.9 and 49.8 by using CCA and KCCA. In addition, the correlation of the relevant components selected during the SPCCA calculation was high, with correlation components of up to 0.955; alternatively, the correlations obtained from CCA and KCCA calculations were only 0.917 and 0.926, respectively. It can be seen that SPCCA is indeed superior to CCA and KCCA in processing high-dimensional multimodal data. This work reveals the process of analyzing the brain activation state in IBD disease, provides a further perspective for the study of brain function, and opens up a new avenue for studying the SPCCA method and the change in the intensity of brain activation in IBD disease.

Modelling-based joint embedding of histology and genomics using canonical correlation analysis for breast cancer survival prediction.

Traditional approaches to predicting breast cancer patients' survival outcomes were based on clinical subgroups, the PAM50 genes, or the histological tissue's evaluation. With the growth of multi-modality datasets capturing diverse information (such as genomics, histology, radiology and clinical data) about the same cancer, information can be integrated using advanced tools and have improved survival prediction. These methods implicitly exploit the key observation that different modalities originate from the same cancer source and jointly provide a complete picture of the cancer. In this work, we investigate the benefits of explicitly modelling multi-modality data as originating from the same cancer under a probabilistic framework. Specifically, we consider histology and genomics as two modalities originating from the same breast cancer under a probabilistic graphical model (PGM). We construct maximum likelihood estimates of the PGM parameters based on canonical correlation analysis (CCA) and then infer the underlying properties of the cancer patient, such as survival. Equivalently, we construct CCA-based joint embeddings of the two modalities and input them to a learnable predictor. Real-world properties of sparsity and graph-structures are captured in the penalized variants of CCA (pCCA) and are better suited for cancer applications. For generating richer multi-dimensional embeddings with pCCA, we introduce two novel embedding schemes that encourage orthogonality to generate more informative embeddings. The efficacy of our proposed prediction pipeline is first demonstrated via low prediction errors of the hidden variable and the generation of informative embeddings on simulated data. When applied to breast cancer histology and RNA-sequencing expression data from The Cancer Genome Atlas (TCGA), our model can provide survival predictions with average concordance-indices of up to 68.32% along with interpretability. We also illustrate how the pCCA embeddings can be used for survival analysis through Kaplan-Meier curves.

Sparse multiway canonical correlation analysis for multimodal stroke recovery data.

Conventional canonical correlation analysis (CCA) measures the association between two datasets and identifies relevant contributors. However, it encounters issues with execution and interpretation when the sample size is smaller than the number of variables or there are more than two datasets. Our motivating example is a stroke-related clinical study on pigs. The data are multimodal and consist of measurements taken at multiple time points and have many more variables than observations. This study aims to uncover important biomarkers and stroke recovery patterns based on physiological changes. To address the issues in the data, we develop two sparse CCA methods for multiple datasets. Various simulated examples are used to illustrate and contrast the performance of the proposed methods with that of the existing methods. In analyzing the pig stroke data, we apply the proposed sparse CCA methods along with dimension reduction techniques, interpret the recovery patterns, and identify influential variables in recovery.

On the stability of canonical correlation analysis and partial least squares with application to brain-behavior associations.

Associations between datasets can be discovered through multivariate methods like Canonical Correlation Analysis (CCA) or Partial Least Squares (PLS). A requisite property for interpretability and generalizability of CCA/PLS associations is stability of their feature patterns. However, stability of CCA/PLS in high-dimensional datasets is questionable, as found in empirical characterizations. To study these issues systematically, we developed a generative modeling framework to simulate synthetic datasets. We found that when sample size is relatively small, but comparable to typical studies, CCA/PLS associations are highly unstable and inaccurate; both in their magnitude and importantly in the feature pattern underlying the association. We confirmed these trends across two neuroimaging modalities and in independent datasets with n ≈ 1000 and n = 20,000, and found that only the latter comprised sufficient observations for stable mappings between imaging-derived and behavioral features. We further developed a power calculator to provide sample sizes required for stability and reliability of multivariate analyses. Collectively, we characterize how to limit detrimental effects of overfitting on CCA/PLS stability, and provide recommendations for future studies.

Penalized canonical correlation analysis reveals a relationship between temperament traits and brain oscillations during mind wandering.

INTRODUCTION: There has been a growing interest in studying brain activity under naturalistic conditions. However, the relationship between individual differences in ongoing brain activity and psychological characteristics is not well understood. We investigated this connection, focusing on the association between oscillatory activity in the brain and individually characteristic dispositional traits. Given the variability of unconstrained resting states among individuals, we devised a paradigm that could harmonize the state of mind across all participants. METHODS: We constructed task contrasts that included focused attention (FA), self-centered future planning, and rumination on anxious thoughts triggered by visual imagery. Magnetoencephalography was recorded from 28 participants under these 3 conditions for a duration of 16 min. The oscillatory power in the alpha and beta bands was converted into spatial contrast maps, representing the difference in brain oscillation power between the two conditions. We performed permutation cluster tests on these spatial contrast maps. Additionally, we applied penalized canonical correlation analysis (CCA) to study the relationship between brain oscillation patterns and behavioral traits. RESULTS: The data revealed that the FA condition, as compared to the other conditions, was associated with higher alpha and beta power in the temporal areas of the left hemisphere and lower alpha and beta power in the parietal areas of the right hemisphere. Interestingly, the penalized CCA indicated that behavioral inhibition was positively correlated, whereas anxiety was negatively correlated, with a pattern of high oscillatory power in the bilateral precuneus and low power in the bilateral temporal regions. This unique association was found in the anxious-thoughts condition when contrasted with the focused-attention condition. CONCLUSION: Our findings suggest individual temperament traits significantly affect brain engagement in naturalistic conditions. This research underscores the importance of considering individual traits in neuroscience and offers an effective method for analyzing brain activity and psychological differences.

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.

Multivariate Relationships Between Health Outcomes and Health System Performance Indicators: An Integrated Factor Analysis With Canonical Correlations.

OBJECTIVES: This study aimed to investigate the relationships between sets of variables related to health system performance indicators and health outcomes. METHODS: The relationships between a set of health outcomes and a set of health system performance indicators of a developing country were examined using multivariate statistical analysis techniques. A combinative strategy of explanatory factor analysis and the canonical correlation coefficient was used to define linear structural relationships between study variables. Province-based data were gathered from2 official statistical records of the Turkish Statistical Institute for the year 2019. Life expectancy at birth, infant mortality rate, and crude death rate were accepted as health outcome indicators. RESULTS: The explanatory factor analysis indicated 2 independent variable groups, namely (1) health-related human resources and capacity and (2) health service utilization characteristics. The results of the canonical correlation analysis illustrated good performance to define sparse linear combinations of the 2 groups of variables. There existed strong positive correlations between health outcomes and health-related human resources and capacity indicators (rc = 0.83; P < .001) and health service utilization indicators (rc = 0.59; P < .001). CONCLUSIONS: The results of this study support the view that there is a linear and strong positive relationship between health outcomes and health-related human resources and capacity indicators. Further studies will combine big data analytics with multivariate statistical analysis techniques by studying large health system performance data sets.

Data integration through canonical correlation analysis and its application to OMICs research.

The subject of the paper is a review of multidimensional data analysis methods, which is the canonical analysis with its various variants and its use in omics data research. The dynamic development of high-throughput methods, and with them the availability of large and constantly growing data resources, forces the development of new analytical approaches that allow the review of the analyzed processes, taking into account data from various levels of the organization of living organisms. The multidimensional perspective allows for the assessment of the analyzed phenomenon in a more realistic way, as it generally takes into account much more data (including OMICs data). Without omitting the complexity of an organism, the method simplifies the multidimensional view, finally giving the result so that the researcher can draw practical conclusions. This is particularly important in medical sciences, where the study of pathological processes is usually aimed at developing treatment regimens. One of the primary methods for studying biomedical processes in a multidimensional approach is the canonical correlation analysis (CCA) with various variants. The use of CCA unique methodologies for simultaneous analysis of multiset biomolecular data opens up new avenues for studying previously undiscovered processes and interdependencies such as e.g. in the tumor microenvironment (TME) connected to intercellular communication. Because of the huge and still untapped potential of canonical correlation, in this review available implementations of CCA techniques are presented. In particular, the possibility of using the technique of canonical correlation analysis for OMICs data is emphasized.

Evaluation of Diagnostic Values of a Gender Discrimination Function, Based on Mandibular Dimorphic Parameters in Iranian Population

Abstract Objective: To evaluate mandibular dimorphic parameters for sex determination by using panoramic radiographs and comparing the results with another equation. Material and Methods: In this analytical-descriptive study, the mandible variables, including the ramus height, the coronoid height, the mental height, and the distance between the right and left condyle, were measured in 326 panoramic radiographs. The discriminant function of the statistical method has previously been used to evaluate the diagnostic value of sex. The level of significance was considered 0.05. Results: The detection function obtained was statistically significant in quantitative correlation (p<0.001) with 99% agreement. Moreover, good sensitivity (81.72%), specify (80.25%), and moderate to good predictive values (PPV: 62.29 and NPV:91.6) were found. Among the mandibular parameters, chin height, ramus height, coronoid height, and distance between two condyles showed the highest gender dimorphism. Conclusion: Chin height, and ramus height have the most quality in gender dimorphism. A unique gender discrimination function has been obtained from the results.

ReGeNNe: genetic pathway-based deep neural network using canonical correlation regularizer for disease prediction.

MOTIVATION: Common human diseases result from the interplay of genes and their biologically associated pathways. Genetic pathway analyses provide more biological insight as compared to conventional gene-based analysis. In this article, we propose a framework combining genetic data into pathway structure and using an ensemble of convolutional neural networks (CNNs) along with a Canonical Correlation Regularizer layer for comprehensive prediction of disease risk. The novelty of our approach lies in our two-step framework: (i) utilizing the CNN's effectiveness to extract the complex gene associations within individual genetic pathways and (ii) fusing features from ensemble of CNNs through Canonical Correlation Regularization layer to incorporate the interactions between pathways which share common genes. During prediction, we also address the important issues of interpretability of neural network models, and identifying the pathways and genes playing an important role in prediction. RESULTS: Implementation of our methodology into three real cancer genetic datasets for different prediction tasks validates our model's generalizability and robustness. Comparing with conventional models, our methodology provides consistently better performance with AUC improvement of 11% on predicting early/late-stage kidney cancer, 10% on predicting kidney versus liver cancer type and 7% on predicting survival status in ovarian cancer as compared to the next best conventional machine learning model. The robust performance of our deep learning algorithm indicates that disease prediction using neural networks in multiple functionally related genes across different pathways improves genetic data-based prediction and understanding molecular mechanisms of diseases. AVAILABILITY AND IMPLEMENTATION: https://github.com/divya031090/ReGeNNe.

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

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.

The association between quality of life and subjective wellbeing among older adults based on canonical correlation analysis.

Introduction: The study explored the relationship between subjective well-being and the quality of life among older adults. It highlights the importance of understanding how these factors are interconnected in the context of an aging population. Methods: Descriptive statistics were used to analyze the scores of general demographic characteristics, subjective wellbeing and quality of life. Simple correlation analysis and canonical correlation analysis were employed to analyze the relationship between subjective wellbeing and quality of life among older adults. Results: Data from 892 older adults were collected. Canonical correlation analysis revealed four pairs of canonical variables, with the first four pairs of canonical correlation coefficients all being statistically significant (0.695, 0.179, 0.147, 0.121) (p < 0.05), and the first pair of canonical variables explaining 93.03% of the information content. From the canonical loading coefficients, Vitality and mental health contributed the most to the quality of life (U1) canonical variable. The canonical variable V1, which corresponded to subjective wellbeing, was reflected by a combination of positive affect, negative affect, positive experience and negative experience. X1 (physical functioning), X2 (role-physical), X3 (bodily pain), X4 (general health), X5 (vitality), X6 (social functioning), X7 (role-emotional) and X8 (mental health) were positively correlated with Y1 (positive affect) and Y3 (positive experience), negatively correlated with Y2 (negative affect) and Y4 (negative experience). Cross-loadings revealed that physical functioning, bodily pain, general health, vitality, social functioning and mental health were the main factors reflecting the subjective wellbeing of older adults. Discussion: As quality of life among older adults was highly correlated with subjective wellbeing, appropriate measures should be taken to account for individual characteristics of older adults, and various factors should be integrated to improve their subjective wellbeing.

Efficiency Determinants in Healthcare: A Systematic Review With an Integrated Canonical Correlation Analysis-Data Envelopment Analysis/Assurance Region Model.

GOAL: Instead of considering many variables for the accurate measurement of healthcare efficiency, working with the select few variables that really affect efficiency will provide more accurate efficiency scores. In addition, calculating the efficiency by weighting the inputs and outputs according to their effect and severity levels will give more realistic results. In this article, a three-step hybrid system with a two-stage CCA (canonical correlation analysis)-DEA/AR (data envelopment analysis/assurance region) model is proposed to obtain results of health efficiency. METHODS: Healthcare efficiency studies conducted between 2000 and 2020 were reviewed. In this examination of the input and output variables used in the DEA of 63 previous studies, the 6 inputs and 5 outputs preferred by previous researchers were determined. Afterward, the health efficiency scores of countries represented in the research were calculated with weight-restricted DEA, and CCA was used for a priori statistical analysis in determining the weights. Thus, in this analysis of the preferred outputs and inputs with the help of CCA to estimate the relationship between multiple input and output sets, the variables that had no effect were eliminated and the ones that had an effect were included in DEA/AR with their degree of effectiveness. PRINCIPAL FINDINGS: For the model proposed here, three inputs and three outputs were identified by following a five-item variable reduction procedure. The numbers of doctors and nurses were identified as the most effective inputs, and infant mortality rates were found to be the most effective outputs. Therefore, health efficiency scores obtained with the proposed CCA-DEA/AR model and the basic DEA are presented together. A review of the results found fewer health-efficient countries with the weight-restricted DEA. This is proof that weighting the variables into the DEA increases the discriminating power of the method. PRACTICAL APPLICATIONS: By applying the proposed model, healthcare administrators can analyze healthcare efficiency accurately and thus improve efficiency by transferring limited resources to the right places according to deficiencies or surpluses identified by the model's inputs. Resources can be allocated at both private and public hospitals in a way that increases healthcare efficiency outputs.

A Canonical Correlation Analysis Study on the Association Between Neighborhood Green Space and Residents' Mental Health.

Based on survey data conducted in Guangzhou in 2021, this study employs canonical correlation analysis (CCA) to evaluate the relationship between neighborhood green space, residents' green space use behavior, and their mental health. The results show that compared with the objectively measured accessibility, residents' subjective perceived accessibility of neighborhood green space plays a greater role in promoting green space use behavior and mental health. Meanwhile, the plant diversity, safety, and the number of recreational facilities in a green space can promote the frequency of green space use, improve residents' mental health status and reduce their perceived stress. Although perceived accessibility is more related to green space use behavior than green space quality indicators, green space safety and recreational facilities have many more benefits on mental health than perceived accessibility. In addition, residents' green space use behavior, especially green space visit frequency, can promote mental health and reduce perceived stress.

Effect of the Fermented Soy Q-CAN® Product on Biomarkers of Inflammation and Oxidation in Adults with Cardiovascular Risk, and Canonical Correlations between the Inflammation Biomarkers and Blood Lipids.

Systemic low-grade inflammation plays a key role in the development of cardiovascular disease (CVD) but the process may be modulated by consuming fermented soy foods. Here, we aim to evaluate the effect of a fermented soy powder Q-CAN® on inflammatory and oxidation biomarkers in subjects with cardiovascular risk. In a randomized crossover trial, 27 adults (mean age ± SD, 51.6 ± 13.5 y) with a mean BMI ± SD of 32.3 ± 7.3 kg/m2 consumed 25 g daily of the fermented soy powder or an isoenergic control powder of sprouted brown rice for 12 weeks each. Between-treatment results showed a 12% increase in interleukin-1 receptor agonist (IL-1Ra) in the treatment group, whereas within-treatment results showed 23% and 7% increases in interleukin-6 (IL-6) and total antioxidant status (TAS), respectively. The first canonical correlation coefficient (r = 0.72) between inflammation markers and blood lipids indicated a positive association between high-sensitivity C-reactive protein (hsCRP) and IL-1Ra with LDL-C and a negative association with HDL-C that explained 62% of the variability in the biomarkers. These outcomes suggest that blood lipids and inflammatory markers are highly correlated and that ingestion of the fermented soy powder Q-CAN® may increase IL-1Ra, IL-6, and TAS in individuals with CVD risk factors.

Canonical correlation analysis of depression and anxiety symptoms among college students and their relationship with physical activity.

To explore the association between depression and anxiety symptoms among college students and the relationship between the two and physical activity. A cross-sectional study design was used to survey 1790 enrolled university students using the Depression Self-Rating Scale, Anxiety Self-Rating Scale and Physical Activity Rating Scale. 37.75% of male students and 39.73% of female students detected depressive symptoms, 17.65% of male students and 17.86% of female students detected anxiety symptoms, 11.89% of male students and 11.75% of female students detected both depressive and anxiety symptoms. Canonical correlation between depression and anxiety symptoms of college students were significant. The depression and anxiety score of college students in the high level group was significantly lower than that in the low and medium level groups, and no significant difference was found between the low and medium level groups. Affective disorder and anxious mood of male students correlated most closely with intensity, while somatic disorder, psychomotor disorder and depressive psychological disorder correlated most closely with duration. Affective disorder of female students correlated most closely with frequency, depressive psychological disorder and anxious mood correlated most closely with intensity, while premonition of misfortune and frequent urination correlated most closely with duration. Depression and anxiety symptoms of college students were closely related and co-occurrence was common. Students with high level of physical activity had milder symptoms. Different exercise interventions are recommended for different symptoms.

inMTSCCA: An Integrated Multi-task Sparse Canonical Correlation Analysis for Multi-omic Brain Imaging Genetics.

Identifying genetic risk factors for Alzheimer's disease (AD) is an important research topic. To date, different endophenotypes, such as imaging-derived endophenotypes and proteomic expression-derived endophenotypes, have shown the great value in uncovering risk genes compared to case-control studies. Biologically, a co-varying pattern of different omics-derived endophenotypes could result from the shared genetic basis. However, existing methods mainly focus on the effect of endophenotypes alone; the effect of cross-endophenotype (CEP) associations remains largely unexploited. In this study, we used both endophenotypes and their CEP associations of multi-omic data to identify genetic risk factors, and proposed two integrated multi-task sparse canonical correlation analysis (inMTSCCA) methods, i.e., pairwise endophenotype correlation-guided MTSCCA (pcMTSCCA) and high-order endophenotype correlation-guided MTSCCA (hocMTSCCA). pcMTSCCA employed pairwise correlations between magnetic resonance imaging (MRI)-derived, plasma-derived, and cerebrospinal fluid (CSF)-derived endophenotypes as an additional penalty. hocMTSCCA used high-order correlations among these multi-omic data for regularization. To figure out genetic risk factors at individual and group levels, as well as altered endophenotypic markers, we introduced sparsity-inducing penalties for both models. We compared pcMTSCCA and hocMTSCCA with three related methods on both simulation and real (consisting of neuroimaging data, proteomic analytes, and genetic data) datasets. The results showed that our methods obtained better or comparable canonical correlation coefficients (CCCs) and better feature subsets than benchmarks. Most importantly, the identified genetic loci and heterogeneous endophenotypic markers showed high relevance. Therefore, jointly using multi-omic endophenotypes and their CEP associations is promising to reveal genetic risk factors. The source code and manual of inMTSCCA are available at https://ngdc.cncb.ac.cn/biocode/tools/BT007330.