FDR-Corrected Sparse Canonical Correlation Analysis With Applications to Imaging Genomics

Modality-Aware Discriminative Fusion Network for Integrated Analysis of Brain Imaging Genomics

Mild cognitive impairment (MCI) represents an early stage of Alzheimer's disease (AD), characterized by subtle clinical symptoms that pose challenges for accurate diagnosis. The quest for the identification of MCI individuals has highlighted the importance of comprehending the underlying mechanisms of disease causation. Integrated analysis of brain imaging and genomics offers a promising avenue for predicting MCI risk before clinical symptom onset. However, most existing methods face challenges in: 1) mining the brain network-specific topological structure and addressing the single nucleotide polymorphisms (SNPs)-related noise contamination and 2) extracting the discriminative properties of brain imaging genomics, resulting in limited accuracy for MCI diagnosis. To this end, a modality-aware discriminative fusion network (MA-DFN) is proposed to integrate the complementary information from brain imaging genomics to diagnose MCI. Specifically, we first design two modality-specific feature extraction modules: the graph convolutional network with edge-augmented self-attention module (GCN-EASA) and the deep adversarial denoising autoencoder module (DAD-AE), to capture the topological structure of brain networks and the intrinsic distribution of SNPs. Subsequently, a discriminative-enhanced fusion network with correlation regularization module (DFN-CorrReg) is employed to enhance inter-modal consistency and between-class discrimination in brain imaging and genomics. Compared to other state-of-the-art approaches, MA-DFN not only exhibits superior performance in stratifying cognitive normal (CN) and MCI individuals but also identifies disease-related brain regions and risk SNPs locus, which hold potential as putative biomarkers for MCI diagnosis.

Semisynthetic simulation for microbiome data analysis

High-throughput sequencing data lie at the heart of modern microbiome research. Effective analysis of these data requires careful preprocessing, modeling, and interpretation to detect subtle signals and avoid spurious associations. In this review, we discuss how simulation can serve as a sandbox to test candidate approaches, creating a setting that mimics real data while providing ground truth. This is particularly valuable for power analysis, methods benchmarking, and reliability analysis. We explain the probability, multivariate analysis, and regression concepts behind modern simulators and how different implementations make trade-offs between generality, faithfulness, and controllability. Recognizing that all simulators only approximate reality, we review methods to evaluate how accurately they reflect key properties. We also present case studies demonstrating the value of simulation in differential abundance testing, dimensionality reduction, network analysis, and data integration. Code for these examples is available in an online tutorial (https://go.wisc.edu/8994yz) that can be easily adapted to new problem settings.

Potential drug targets for tumors identified through Mendelian randomization analysis

According to the latest cancer research data, there are a significant number of new cancer cases and a substantial mortality rate each year. Although a substantial number of clinical patients are treated with existing cancer drugs each year, the efficacy is unsatisfactory. The incidence is still high and the effectiveness of most cancer drugs remains unsatisfactory. Therefore, we evaluated the human proteins for their causal relationship to for cancer risk and therefore also their potential as drug targets. We used summary tumors data from the FinnGen and cis protein quantitative trait loci (cis-pQTL) data from a genome-wide association study, and employed Mendelian randomization (MR) to explore the association between potential drug targets and nine tumors, including breast, colorectal, lung, liver, bladder, prostate, kidney, head and neck, pancreatic caners. Furthermore, we conducted MR analysis on external cohort. Moreover, Bidirectional MR, Steiger filtering, and colocalization were employed to validate the main results. The DrugBank database was used to discover potential drugs of tumors. Under the threshold of False discovery rate (FDR) < 0.05, results showed that S100A16 was protective protein and S100A14 was risk protein for human epidermal growth factor receptor 2-positive (HER-positive) breast cancer, phosphodiesterase 5A (PDE5A) was risk protein for colorectal cancer, and melanoma inhibitory activity (MIA) was protective protein for non-small cell lung carcinoma (NSCLC). And there was no reverse causal association between them. Colocalization analysis showed that S100A14 (PP.H4.abf = 0.920) and S100A16 (PP.H4.abf = 0.932) shared causal variation with HER-positive breast cancer, and PDE5A (PP.H4.abf = 0.857) shared causal variation with colorectal cancer (CRC). The MR results of all pQTL of PDE5A and MIA were consistent with main results. In addition, the MR results of MIA and external outcome cohort were consistent with main results. In this study, genetic predictions indicate that circulating S100 calcium binding protein A14 (S100A14) and S100 calcium binding protein A16 (S100A16) are associated with increase and decrease in the risk of HER-positive breast cancer, respectively. Circulating PDE5A is associated with increased risk of CRC, while circulating MIA is associated with decreased risk of NSCLC. These findings suggest that four proteins may serve as biomarkers for cancer prevention and as potential drug targets that could be expected for approval.

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.

Multi-Group Tensor Canonical Correlation Analysis

Tensor Canonical Correlation Analysis (TCCA) is a commonly employed statistical method utilized to examine linear associations between two sets of tensor datasets. However, the existing TCCA models fail to adequately address the heterogeneity present in real-world tensor data, such as brain imaging data collected from diverse groups characterized by factors like sex and race. Consequently, these models may yield biased outcomes. In order to surmount this constraint, we propose a novel approach called Multi-Group TCCA (MG-TCCA), which enables the joint analysis of multiple subgroups. By incorporating a dual sparsity structure and a block coordinate ascent algorithm, our MG-TCCA method effectively addresses heterogeneity and leverages information across different groups to identify consistent signals. This novel approach facilitates the quantification of shared and individual structures, reduces data dimensionality, and enables visual exploration. To empirically validate our approach, we conduct a study focused on investigating correlations between two brain positron emission tomography (PET) modalities (AV-45 and FDG) within an Alzheimer's disease (AD) cohort. Our results demonstrate that MG-TCCA surpasses traditional TCCA in identifying sex-specific cross-modality imaging correlations. This heightened performance of MG-TCCA provides valuable insights for the characterization of multimodal imaging biomarkers in AD.

Identifying miRNA-Gene Common and Specific Regulatory Modules for Cancer Subtyping by a High-Order Graph Matching Model

Identifying regulatory modules between miRNAs and genes is crucial in cancer research. It promotes a comprehensive understanding of the molecular mechanisms of cancer. The genomic data collected from subjects usually relate to different cancer statuses, such as different TNM Classifications of Malignant Tumors (TNM) or histological subtypes. Simple integrated analyses generally identify the core of the tumorigenesis (common modules) but miss the subtype-specific regulatory mechanisms (specific modules). In contrast, separate analyses can only report the differences and ignore important common modules. Therefore, there is an urgent need to develop a novel method to jointly analyze miRNA and gene data of different cancer statuses to identify common and specific modules. To that end, we developed a High-Order Graph Matching model to identify Common and Specific modules (HOGMCS) between miRNA and gene data of different cancer statuses. We first demonstrate the superiority of HOGMCS through a comparison with four state-of-the-art techniques using a set of simulated data. Then, we apply HOGMCS on stomach adenocarcinoma data with four TNM stages and two histological types, and breast invasive carcinoma data with four PAM50 subtypes. The experimental results demonstrate that HOGMCS can accurately extract common and subtype-specific miRNA-gene regulatory modules, where many identified miRNA-gene interactions have been confirmed in several public databases.

sJIVE: Supervised Joint and Individual Variation Explained

Analyzing multi-source data, which are multiple views of data on the same subjects, has become increasingly common in molecular biomedical research. Recent methods have sought to uncover underlying structure and relationships within and/or between the data sources, and other methods have sought to build a predictive model for an outcome using all sources. However, existing methods that do both are presently limited because they either (1) only consider data structure shared by all datasets while ignoring structures unique to each source, or (2) they extract underlying structures first without consideration to the outcome. The proposed method, supervised joint and individual variation explained (sJIVE), can simultaneously (1) identify shared (joint) and source-specific (individual) underlying structure and (2) build a linear prediction model for an outcome using these structures. These two components are weighted to compromise between explaining variation in the multi-source data and in the outcome. Simulations show sJIVE to outperform existing methods when large amounts of noise are present in the multi-source data. An application to data from the COPDGene study explores gene expression and proteomic patterns associated with lung function.

A Deep Generative-Discriminative Learning for Multimodal Representation in Imaging Genetics

Imaging genetics, one of the foremost emerging topics in the medical imaging field, analyzes the inherent relations between neuroimaging and genetic data. As deep learning has gained widespread acceptance in many applications, pioneering studies employed deep learning frameworks for imaging genetics. However, existing approaches suffer from some limitations. First, they often adopt a simple strategy for joint learning of phenotypic and genotypic features. Second, their findings have not been extended to biomedical applications, e.g., degenerative brain disease diagnosis and cognitive score prediction. Finally, existing studies perform insufficient and inappropriate analyses from the perspective of data science and neuroscience. In this work, we propose a novel deep learning framework to simultaneously tackle the aforementioned issues. Our proposed framework learns to effectively represent the neuroimaging and the genetic data jointly, and achieves state-of-the-art performance when used for Alzheimer's disease and mild cognitive impairment identification. Furthermore, unlike the existing methods, the framework enables learning the relation between imaging phenotypes and genotypes in a nonlinear way without any prior neuroscientific knowledge. To demonstrate the validity of our proposed framework, we conducted experiments on a publicly available dataset and analyzed the results from diverse perspectives. Based on our experimental results, we believe that the proposed framework has immense potential to provide new insights and perspectives in deep learning-based imaging genetics studies.

A methylation-based prognostic model predicts survival in patients with colorectal cancer

Background

To construct a model that could effectively predict the prognosis of colorectal cancer (CRC) by searching for methylated-differentially expressed genes (MDEGs).

Methods

We identified MDEGs through four databases from Gene Expression Omnibus (GEO) and annotated their functions via bioinformatics analysis. Subsequently, after adjusting for gender, age, and grading, multivariate Cox hazard analysis was utilized to select MDEGs interrelated with the prognosis of CRC, and LASSO analysis was utilized to fit the prediction model in the training set. Furthermore, another independent dataset was harnessed to verify the effectiveness of the model in predicting prognosis.

Results

In total, 252 hypomethylated and up-regulated genes and 132 hypermethylated and down-regulated genes were identified, 27 of which were correlated with the prognosis of CRC, and a 10-gene prognostic model was established after LASSO analysis. The overall survival rate could be effectively grouped into different risks by the median score of this model in the training set [risk ratio (HR) =2.27, confidence interval (95% CI), 1.69-3.13, P=8.15×10^-8], and the validity of its effect in predicting prognosis in CRC was verified in the validation dataset (HR =1.75, 95% CI, 1.15-2.70, P=9.32×10^-3).

Conclusions

Our model could effectively predict the overall survival rate of patients with CRC and provides potential application guidelines for its clinically personalized treatment.

A Study on the Therapeutic Efficacy of San Zi Yang Qin Decoction for Non-Alcoholic Fatty Liver Disease and the Underlying Mechanism Based on Network Pharmacology

OBJECTIVE

This study aims to explore the therapeutic efficacy of San Zi Yang Qin Decoction (SZ) and its potential mechanism in the treatment of non-alcoholic fatty liver disease (NAFLD) based on network pharmacology and in vivo experiments.

METHODS

Effective chemicals and targets of SZ were searched in online databases, according to the drug-likeness of compounds and the binomial distribution of targets. A disease-target-chemical network was established using NAFLD-associated genes screened through GeneCards database, Gene Ontology (GO) terms, and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways. Furthermore, animal experiments were conducted to verify the efficacy and mechanism of SZ predicted by network pharmacology. The NAFLD mouse model was established with C57BL/6J mice fed with a high-fat diet for 22 weeks. The mice in the control group were fed with a chow diet. From the 23rd week, the NAFLD mice were treated with intragastric SZ or normal saline for 8 weeks. After the glucose tolerance was measured, the mice were sacrificed, followed by the collection of serum and liver tissues. Pathological changes in liver tissues were examined by H&E staining. Additionally, alanine aminotransferase (ALT), aspartate aminotransferase (AST), serum fast blood glucose, and insulin levels were detected. Expression levels of TNF-α of serum and liver tissues were determined by ELISA and qRT-PCR, respectively. Western blot was used to detect the activation of AKT in liver tissues.

RESULTS

A total of 27 effective compounds and 20 targets of SZ were screened. GO analysis uncovered a significant correlation between the targets of SZ and those of NAFLD. KEGG analysis presented the signaling pathways enriched in SZ and NAFLD, including NAFLD, TNF-α, and apoptosis pathways. The area under the curve of major GO and KEGG pathways indicated the potential role of SZ in improving NAFLD. In vivo experiments demonstrated that SZ significantly alleviated hepatosteatosis and inflammatory cell infiltration in liver tissues, reduced serum transaminases, and improved insulin resistance and glucose tolerance of NAFLD mice. The protein level of phospho-AKT was upregulated by SZ. Additionally, SZ treatment obviously impaired the TNF-α level in the serum and liver tissue of NAFLD mice.

CONCLUSIONS

According to the network pharmacology analysis and in vivo experiments, SZ could have therapeutic efficacy for NALFD. The mechanism mainly involves pathways relative to insulin resistance, TNF-α, and apoptosis. Our results provide a scientific basis for SZ in the clinical treatment of NAFLD.

Brain Functional Network in Chronic Asymptomatic Carotid Artery Stenosis and Occlusion: Changes and Compensation

Asymptomatic carotid artery stenosis (CAS) and occlusion (CAO) disrupt cerebral hemodynamics. There are few studies on the brain network changes and compensation associated with the progression from chronic CAS to CAO. In the current study, our goal is to improve the understanding of the specific abnormalities and compensatory phenomena associated with the functional connection in patients with CAS and CAO. In this prospective study, 27 patients with CAO, 29 patients with CAS, and 15 healthy controls matched for age, sex, education, handedness, and risk factors underwent neuropsychological testing and resting-state functional magnetic resonance (rs-fMRI) imaging simultaneously; graph theoretical analysis of brain networks was performed to determine the relationship between changes in brain network connectivity and the progression from internal CAS to CAO. The global properties of the brain network assortativity (p = 0.002), hierarchy (p = 0.002), network efficiency (p = 0.011), and small-worldness (p = 0.009) were significantly more abnormal in the CAS group than in the control and CAO groups. In patients with CAS and CAO, the nodal efficiency of key nodes in multiple brain regions decreased, while the affected hemisphere lost many key functional connections. In this study, we found that patients with CAS showed grade reconstruction, invalid connections, and other phenomena that impaired the efficiency of information transmission in the brain network. A compensatory functional connection in the contralateral cerebral hemisphere of patients with CAS and CAO may be an important mechanism that maintains clinical asymptomatic performance. This study not only reveals the compensation mechanism of cerebral hemisphere ischemia but also validates previous explanations for brain function connectivity, which can help provide interventions in advance and reduce the impairment of higher brain functions. This trial is registered with Clinical Trial Registration-URL http://www.chictr.org.cn and Unique identifier ChiCTR1900023610.

A technical review of canonical correlation analysis for neuroscience applications

Collecting comprehensive data sets of the same subject has become a standard in neuroscience research and uncovering multivariate relationships among collected data sets have gained significant attentions in recent years. Canonical correlation analysis (CCA) is one of the powerful multivariate tools to jointly investigate relationships among multiple data sets, which can uncover disease or environmental effects in various modalities simultaneously and characterize changes during development, aging, and disease progressions comprehensively. In the past 10 years, despite an increasing number of studies have utilized CCA in multivariate analysis, simple conventional CCA dominates these applications. Multiple CCA-variant techniques have been proposed to improve the model performance; however, the complicated multivariate formulations and not well-known capabilities have delayed their wide applications. Therefore, in this study, a comprehensive review of CCA and its variant techniques is provided. Detailed technical formulation with analytical and numerical solutions, current applications in neuroscience research, and advantages and limitations of each CCA-related technique are discussed. Finally, a general guideline in how to select the most appropriate CCA-related technique based on the properties of available data sets and particularly targeted neuroscience questions is provided.

Canonical Correlation Analysis of Imaging Genetics Data Based on Statistical Independence and Structural Sparsity

Current developments of neuroimaging and genetics promote an integrative and compressive study of schizophrenia. However, it is still difficult to explore how gene mutations are related to brain abnormalities due to the high dimension but low sample size of these data. Conventional approaches reduce the dimension of dataset separately and then calculate the correlation, but ignore the effects of the response variables and the structure of data. To improve the identification of risk genes and abnormal brain regions on schizophrenia, in this paper, we propose a novel method called Independence and Structural sparsity Canonical Correlation Analysis (ISCCA). ISCCA combines independent component analysis (ICA) and Canonical Correlation Analysis (CCA) to reduce the collinear effects, which also incorporate graph structure of the data into the model to improve the accuracy of feature selection. The results from simulation studies demonstrate its higher accuracy in discovering correlations compared with other competing methods. Moreover, applying ISCCA to a real imaging genetics dataset collected by Mind Clinical Imaging Consortium (MCIC), a set of distinct gene-ROI interactions are identified, which are verified to be both statistically and biologically significant.

Multimodal Sparse Classifier for Adolescent Brain Age Prediction

The study of healthy brain development helps to better understand both brain transformation and connectivity patterns, which happen during childhood to adulthood. This study presents a sparse machine learning solution across whole-brain functional connectivity measures of three datasets, derived from resting state functional magnetic resonance imaging (rs-fMRI) and two task fMRI data including a working memory n-back task (nb-fMRI) and an emotion identification task (em-fMRI). The fMRI data are collected from the Philadelphia Neurodevelopmental Cohort (PNC) for the prediction of brain age in adolescents. Due to extremely large variable-to-instance ratio of PNC data, a high-dimensional matrix with several irrelevant and highly correlated features is generated, and hence a sparse learning approach is necessary to extract effective features from fMRI data. We propose a sparse learner based on the residual errors along the estimation of an inverse problem for extreme learning machine (ELM). Our proposed method is able to overcome the overlearning problem by pruning several redundant features and their corresponding output weights. The proposed multimodal sparse ELM classifier based on residual errors is highly competitive in terms of classification accuracy compared to its counterparts such as conventional ELM, and sparse Bayesian learning ELM.

Brain Imaging Genomics: Integrated Analysis and Machine Learning

Brain imaging genomics is an emerging data science field, where integrated analysis of brain imaging and genomics data, often combined with other biomarker, clinical and environmental data, is performed to gain new insights into the phenotypic, genetic and molecular characteristics of the brain as well as their impact on normal and disordered brain function and behavior. It has enormous potential to contribute significantly to biomedical discoveries in brain science. Given the increasingly important role of statistical and machine learning in biomedicine and rapidly growing literature in brain imaging genomics, we provide an up-to-date and comprehensive review of statistical and machine learning methods for brain imaging genomics, as well as a practical discussion on method selection for various biomedical applications.

A Projection CCA Method for Effective fMRI Data Analysis

OBJECTIVE

Canonical correlation analysis (CCA) is a data-driven method that has been successfully used in functional magnetic resonance imaging (fMRI) data analysis. Standard CCA extracts meaningful information from a pair of data sets by seeking pairs of linear combinations from two sets of variables with maximum pairwise correlation. So far, however, this method has been used without incorporating prior information available for fMRI data. In this paper, we address this issue by proposing a new CCA method named pCCA (for projection CCA).

METHODS

The proposed method is obtained by projection onto a set of basis vectors that better characterize temporal information in the fMRI data set. A methodology is presented to describe the basis selection process using discrete cosine transform (DCT) basis functions. Employing DCT guides the estimated canonical variates, yielding a more computationally efficient CCA procedure.

RESULTS

The performance gain of the proposed pCCA algorithm over standard and regularized CCA is illustrated on both simulated and real fMRI datasets from resting state, block paradigm task-related and event-related experiments. The results have shown that the proposed pCCA successfully extracts latent components from the task as well as resting-state datasets with increased specificity of the activated voxels.

CONCLUSION

In addition to offering a new CCA approach, when applied on fMRI data, the proposed algorithm adapts to variations of brain activity patterns and reveals the functionally connected brain regions.

SIGNIFICANCE

The proposed method can be seen as a regularized CCA method where regularization is introduced via basis expansion, which has the advantage of enforcing smoothness on canonical components.