Sparse reduced-rank regression detects genetic associations with voxel-wise longitudinal phenotypes in Alzheimer's disease

Integration of genomic and transcriptomic layers in RNA-Seq data leads to protein interaction modules with improved Alzheimer's disease associations

Alzheimer's disease (AD) is the most common neurodegenerative disease, and it is currently untreatable. RNA sequencing (RNA-Seq) is commonly used in the literature to identify AD-associated molecular mechanisms by analysing changes in gene expression. RNA-Seq data can also be used to detect genomic variants, enabling the identification of the genes with a higher load of deleterious variants in patients compared with controls. Here, we analysed AD RNA-Seq datasets to obtain differentially expressed genes and genes with a higher load of pathogenic variants in AD, and we combined them in a single list. We mapped these genes on a human protein-protein interaction network to discover subnetworks perturbed by AD. Our results show that utilizing gene pathogenicity information from RNA-Seq data positively contributes to the disclosure of AD-related mechanisms. Moreover, dividing the discovered subnetworks into highly connected modules reveals a clearer picture of altered molecular pathways that, otherwise, would not be captured. Repeating the whole pipeline with human metabolic network genes led to results confirming the positive contribution of gene pathogenicity information and enabled a more detailed identification of altered metabolic pathways in AD.

A multivariate to multivariate approach for voxel-wise genome-wide association analysis

The joint analysis of imaging-genetics data facilitates the systematic investigation of genetic effects on brain structures and functions with spatial specificity. We focus on voxel-wise genome-wide association analysis, which may involve trillions of single nucleotide polymorphism (SNP)-voxel pairs. We attempt to identify underlying organized association patterns of SNP-voxel pairs and understand the polygenic and pleiotropic networks on brain imaging traits. We propose a bi-clique graph structure (ie, a set of SNPs highly correlated with a cluster of voxels) for the systematic association pattern. Next, we develop computational strategies to detect latent SNP-voxel bi-cliques and an inference model for statistical testing. We further provide theoretical results to guarantee the accuracy of our computational algorithms and statistical inference. We validate our method by extensive simulation studies, and then apply it to the whole genome genetic and voxel-level white matter integrity data collected from 1052 participants of the human connectome project. The results demonstrate multiple genetic loci influencing white matter integrity measures on splenium and genu of the corpus callosum.

Adenylyl cyclase 2 expression and function in neurological diseases

Adenylyl cyclases (Adcys) catalyze the formation of cAMP, a secondary messenger essential for cell survival and neurotransmission pathways in the CNS. Adcy2, one of ten Adcy isoforms, is highly expressed in the CNS. Abnormal Adcy2 expression and mutations have been reported in various neurological disorders in both rodents and humans. However, due to the lack of genetic tools, loss-of-function studies of Adcy2 are scarce. In this review, we summarize recent findings on Adcy2 expression and function in neurological diseases. Specifically, we first introduce the biochemistry, structure, and function of Adcy2 briefly. Next, the expression and association of Adcy2 in human patients and rodent models of neurodegenerative diseases (Alzheimer's disease and Parkinson's disease), psychiatric disorders (Tourette syndrome, schizophrenia, and bipolar disorder), and other neurological conditions (stress-associated disorders, stroke, epilepsy, and Lesch-Nyhan Syndrome) are elaborated. Furthermore, we discuss the pros and cons of current studies as well as key questions that need to be answered in the future. We hope to provide a focused review on Adcy2 that promotes future research in the field.

Statistical and Machine Learning Analysis in Brain-Imaging Genetics: A Review of Methods

Brain-imaging-genetic analysis is an emerging field of research that aims at aggregating data from neuroimaging modalities, which characterize brain structure or function, and genetic data, which capture the structure and function of the genome, to explain or predict normal (or abnormal) brain performance. Brain-imaging-genetic studies offer great potential for understanding complex brain-related diseases/disorders of genetic etiology. Still, a combined brain-wide genome-wide analysis is difficult to perform as typical datasets fuse multiple modalities, each with high dimensionality, unique correlational landscapes, and often low statistical signal-to-noise ratios. In this review, we outline the progress in brain-imaging-genetic methodologies starting from early massive univariate to current deep learning approaches, highlighting each approach's strengths and weaknesses and elongating it with the field's development. We conclude by discussing selected remaining challenges and prospects for the field.

Neurogenetics of Brain Connectivity: Current Approaches to the Study (Review)

Owing to the advances of neuroimaging techniques, a number of functional brain networks associated both with specific functions and the state of relative inactivity has been distinguished. A sufficient bulk of information has been accumulated on changes in connectivity (links between brain regions) in psychopathologies, for example, depression, schizophrenia, autism. Their genetic markers are being actively investigated using a candidate-gene approach or a genome-wide association study. At the same time, there is not much data considering connectivity as an intermediate link in the genotype-pathology chain, although it seems to be a reliable endophenotype, since it demonstrates a high stability and high heritability. In the present review, we consider the results of investigations devoted to the search for biomarkers, molecular and genetic associations of functional, partially anatomical, and effective connectivity. The main approaches to the evaluation of connectivity neurogenetics have been described, as well as specific genetic variants, for which the association with brain connectivity in psychiatric pathologies has been detected.

A genome-wide search for pleiotropy in more than 100,000 harmonized longitudinal cognitive domain scores

BACKGROUND

More than 75 common variant loci account for only a portion of the heritability for Alzheimer's disease (AD). A more complete understanding of the genetic basis of AD can be deduced by exploring associations with AD-related endophenotypes.

METHODS

We conducted genome-wide scans for cognitive domain performance using harmonized and co-calibrated scores derived by confirmatory factor analyses for executive function, language, and memory. We analyzed 103,796 longitudinal observations from 23,066 members of community-based (FHS, ACT, and ROSMAP) and clinic-based (ADRCs and ADNI) cohorts using generalized linear mixed models including terms for SNP, age, SNP × age interaction, sex, education, and five ancestry principal components. Significance was determined based on a joint test of the SNP's main effect and interaction with age. Results across datasets were combined using inverse-variance meta-analysis. Genome-wide tests of pleiotropy for each domain pair as the outcome were performed using PLACO software.

RESULTS

Individual domain and pleiotropy analyses revealed genome-wide significant (GWS) associations with five established loci for AD and AD-related disorders (BIN1, CR1, GRN, MS4A6A, and APOE) and eight novel loci. ULK2 was associated with executive function in the community-based cohorts (rs157405, P = 2.19 × 10-9). GWS associations for language were identified with CDK14 in the clinic-based cohorts (rs705353, P = 1.73 × 10-8) and LINC02712 in the total sample (rs145012974, P = 3.66 × 10-8). GRN (rs5848, P = 4.21 × 10-8) and PURG (rs117523305, P = 1.73 × 10-8) were associated with memory in the total and community-based cohorts, respectively. GWS pleiotropy was observed for language and memory with LOC107984373 (rs73005629, P = 3.12 × 10-8) in the clinic-based cohorts, and with NCALD (rs56162098, P = 1.23 × 10-9) and PTPRD (rs145989094, P = 8.34 × 10-9) in the community-based cohorts. GWS pleiotropy was also found for executive function and memory with OSGIN1 (rs12447050, P = 4.09 × 10-8) and PTPRD (rs145989094, P = 3.85 × 10-8) in the community-based cohorts. Functional studies have previously linked AD to ULK2, NCALD, and PTPRD.

CONCLUSION

Our results provide some insight into biological pathways underlying processes leading to domain-specific cognitive impairment and AD, as well as a conduit toward a syndrome-specific precision medicine approach to AD. Increasing the number of participants with harmonized cognitive domain scores will enhance the discovery of additional genetic factors of cognitive decline leading to AD and related dementias.

LARGE-SCALE MULTIVARIATE SPARSE REGRESSION WITH APPLICATIONS TO UK BIOBANK

In high-dimensional regression problems, often a relatively small subset of the features are relevant for predicting the outcome, and methods that impose sparsity on the solution are popular. When multiple correlated outcomes are available (multitask), reduced rank regression is an effective way to borrow strength and capture latent structures that underlie the data. Our proposal is motivated by the UK Biobank population-based cohort study, where we are faced with large-scale, ultrahigh-dimensional features, and have access to a large number of outcomes (phenotypes)-lifestyle measures, biomarkers, and disease outcomes. We are hence led to fit sparse reduced-rank regression models, using computational strategies that allow us to scale to problems of this size. We use a scheme that alternates between solving the sparse regression problem and solving the reduced rank decomposition. For the sparse regression component we propose a scalable iterative algorithm based on adaptive screening that leverages the sparsity assumption and enables us to focus on solving much smaller subproblems. The full solution is reconstructed and tested via an optimality condition to make sure it is a valid solution for the original problem. We further extend the method to cope with practical issues, such as the inclusion of confounding variables and imputation of missing values among the phenotypes. Experiments on both synthetic data and the UK Biobank data demonstrate the effectiveness of the method and the algorithm. We present multiSnpnet package, available at http://github.com/junyangq/multiSnpnet that works on top of PLINK2 files, which we anticipate to be a valuable tool for generating polygenic risk scores from human genetic studies.

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.

Decoding Genetic Markers of Multiple Phenotypic Layers Through Biologically Constrained Genome-To-Phenome Bayesian Sparse Regression

The applicability of multivariate approaches for the joint analysis of genomics and phenomics information is currently limited by the lack of scalability, and by the difficulty of interpreting the related findings from a biological perspective. To tackle these limitations, we present Bayesian Genome-to-Phenome Sparse Regression (G2PSR), a novel multivariate regression method based on sparse SNP-gene constraints. The statistical framework of G2PSR is based on a Bayesian neural network, were constraints on SNPs-genes associations are integrated by incorporating a priori knowledge linking variants to their respective genes, to then reconstruct the phenotypic data in the output layer. Interpretability is promoted by inducing sparsity on the genes through variational dropout, allowing to estimate the uncertainty associated with each gene, and related SNPs, in the reconstruction task. Ultimately, G2PSR is conceived to prevent multiple testing correction and to assess the combined effect of SNPs, thus increasing the statistical power in detecting genome-to-phenome associations. The effectiveness of G2PSR was demonstrated on synthetic and real data, with respect to state-of-the-art methods based on group-wise sparsity constraints. The application on real data consisted in an imaging-genetics analysis on the Alzheimer's Disease Neuroimaging Initiative data, relating SNPs from more than 3,500 genes to clinical and multi-variate brain volumetric information. The experimental results show that our method can provide accurate selection of relevant genes in dataset with large SNPs-to-samples ratio, thus overcoming the main limitations of current genome-to-phenome association methods.

Machine Learning Based Multimodal Neuroimaging Genomics Dementia Score for Predicting Future Conversion to Alzheimer's Disease

BACKGROUND

The increasing availability of databases containing both magnetic resonance imaging (MRI) and genetic data allows researchers to utilize multimodal data to better understand the characteristics of dementia of Alzheimer's type (DAT).

OBJECTIVE

The goal of this study was to develop and analyze novel biomarkers that can help predict the development and progression of DAT.

METHODS

We used feature selection and ensemble learning classifier to develop an image/genotype-based DAT score that represents a subject's likelihood of developing DAT in the future. Three feature types were used: MRI only, genetic only, and combined multimodal data. We used a novel data stratification method to better represent different stages of DAT. Using a pre-defined 0.5 threshold on DAT scores, we predicted whether a subject would develop DAT in the future.

RESULTS

Our results on Alzheimer's Disease Neuroimaging Initiative (ADNI) database showed that dementia scores using genetic data could better predict future DAT progression for currently normal control subjects (Accuracy = 0.857) compared to MRI (Accuracy = 0.143), while MRI can better characterize subjects with stable mild cognitive impairment (Accuracy = 0.614) compared to genetics (Accuracy = 0.356). Combining MRI and genetic data showed improved classification performance in the remaining stratified groups.

CONCLUSION

MRI and genetic data can contribute to DAT prediction in different ways. MRI data reflects anatomical changes in the brain, while genetic data can detect the risk of DAT progression prior to the symptomatic onset. Combining information from multimodal data appropriately can improve prediction performance.

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.

Multivariate Analysis and Modelling of multiple Brain endOphenotypes: Let's MAMBO!

Imaging genetic studies aim to test how genetic information influences brain structure and function by combining neuroimaging-based brain features and genetic data from the same individual. Most studies focus on individual correlation and association tests between genetic variants and a single measurement of the brain. Despite the great success of univariate approaches, given the capacity of neuroimaging methods to provide a multiplicity of cerebral phenotypes, the development and application of multivariate methods become crucial. In this article, we review novel methods and strategies focused on the analysis of multiple phenotypes and genetic data. We also discuss relevant aspects of multi-trait modelling in the context of neuroimaging data.

Emerging evidence implicating a role for neurexins in neurodegenerative and neuropsychiatric disorders

Synaptopathies are brain disorders characterized by dysfunctional synapses, which are specialized junctions between neurons that are essential for the transmission of information. Synaptic dysfunction can occur due to mutations that alter the structure and function of synaptic components or abnormal expression levels of a synaptic protein. One class of synaptic proteins that are essential to their biology are cell adhesion proteins that connect the pre- and post-synaptic compartments. Neurexins are one type of synaptic cell adhesion molecule that have, recently, gained more pathological interest. Variants in both neurexins and their common binding partners, neuroligins, have been associated with several neuropsychiatric disorders. In this review, we summarize some of the key physiological functions of the neurexin protein family and the protein networks they are involved in. Furthermore, examination of published literature has implicated neurexins in both neuropsychiatric and neurodegenerative disorders. There is a clear link between neurexins and neuropsychiatric disorders, such as autism spectrum disorder and schizophrenia. However, multiple expression studies have also shown changes in neurexin expression in several neurodegenerative disorders, including Alzheimer's disease and Parkinson's disease. Therefore, this review highlights the potential importance of neurexins in brain disorders and the importance of doing more targeted studies on these genes and proteins.

Strategies for multivariate analyses of imaging genetics study in Alzheimer's disease

Alzheimer's disease (AD) is an incurable neurodegenerative disease primarily affecting the elderly population. Early diagnosis of AD is critical for the management of this disease. Imaging genetics examines the influence of genetic variants (i.e., single nucleotide polymorphisms (SNPs)) on brain structure and function and many novel approaches of imaging genetics are proposed for studying AD. We review and synthesize the Alzheimer's Disease Neuroimaging Initiative (ADNI) genetic associations with quantitative disease endophenotypes including structural and functional neuroimaging, diffusion tensor imaging (DTI), positron emission tomography (PET), and fluid biomarker assays. In this review, we survey recent publications using neuroimaging and genetic data of AD, with a focus on methods capturing multivariate effects accommodating the large number variables from both imaging data and genetic data. We review methods focused on bridging the imaging and genetic data by establishing genotype-phenotype association, including sparse canonical correlation analysis, parallel independent component analysis, sparse reduced rank regression, sparse partial least squares, genome-wide association study, and so on. The broad availability and wide scope of ADNI genetic and phenotypic data has advanced our understanding of the genetic basis of AD and has nominated novel targets for future pharmaceutical therapy and biomarker development.

Dual Attention Multi-Instance Deep Learning for Alzheimer's Disease Diagnosis With Structural MRI

Structural magnetic resonance imaging (sMRI) is widely used for the brain neurological disease diagnosis, which could reflect the variations of brain. However, due to the local brain atrophy, only a few regions in sMRI scans have obvious structural changes, which are highly correlative with pathological features. Hence, the key challenge of sMRI-based brain disease diagnosis is to enhance the identification of discriminative features. To address this issue, we propose a dual attention multi-instance deep learning network (DA-MIDL) for the early diagnosis of Alzheimer's disease (AD) and its prodromal stage mild cognitive impairment (MCI). Specifically, DA-MIDL consists of three primary components: 1) the Patch-Nets with spatial attention blocks for extracting discriminative features within each sMRI patch whilst enhancing the features of abnormally changed micro-structures in the cerebrum, 2) an attention multi-instance learning (MIL) pooling operation for balancing the relative contribution of each patch and yield a global different weighted representation for the whole brain structure, and 3) an attention-aware global classifier for further learning the integral features and making the AD-related classification decisions. Our proposed DA-MIDL model is evaluated on the baseline sMRI scans of 1689 subjects from two independent datasets (i.e., ADNI and AIBL). The experimental results show that our DA-MIDL model can identify discriminative pathological locations and achieve better classification performance in terms of accuracy and generalizability, compared with several state-of-the-art methods.

A Latent Gaussian Copula Model for Mixed Data Analysis in Brain Imaging Genetics

Recent advances in imaging genetics make it possible to combine different types of data including medical images like functional magnetic resonance imaging (fMRI) and genetic data like single nucleotide polymorphisms (SNPs) for comprehensive diagnosis of mental disorders. Understanding complex interactions among these heterogeneous data may give rise to a new perspective, while at the same time demand statistical models for their integration. Various graphical models have been proposed for the study of interaction or association networks with continuous, binary, and count data as well as the mixture of them. However, limited efforts have been made for the multinomial case, for instance, SNP data. Our goal is therefore to fill the void by developing a graphical model for the integration of fMRI image and SNP data, which can provide deeper understanding of the unknown neurogenetic mechanism. In this article, we propose a latent Gaussian copula model for mixed data containing multinomial components. We assume that the discrete variable is obtained by discretizing a latent (unobserved) continuous variable and then create a semi-rank based estimator of the graph structure. The simulation results demonstrate that the proposed latent correlation has more steady and accurate performance than several existing methods in detecting graph structure. When applying to a real schizophrenia data consisting of SNP array and fMRI image collected by the Mind Clinical Imaging Consortium (MCIC), the proposed method reveals a set of distinct SNP-brain associations, which are verified to be biologically significant. The proposed model is statistically promising in handling mixed types of data including multinomial components, which can find widespread applications. To promote reproducible research, the R code is available at https://github.com/Aiying0512/LGCM.

Multiclass diagnosis of stages of Alzheimer's disease using linear discriminant analysis scoring for multimodal data

Alzheimer's disease (AD) is a progressive neurodegenerative disease, and mild cognitive impairment (MCI) is a transitional stage between normal control (NC) and AD. A multiclass classification of AD is a difficult task because there are multiple similarities between neighboring groups. The performance of classification can be improved by using multimodal data, but the improvement could be limited with inefficient fusion of multimodal data. This study aims to develop a framework for AD multiclass diagnosis with a linear discriminant analysis (LDA) scoring method to fuse multimodal data more efficiently. Magnetic resonance imaging, positron emission tomography, cerebrospinal fluid biomarkers, and genetic features were first preprocessed by performing age correction, feature selection, and feature reduction. Then, they were individually scored using LDA, and the scores that represent the AD pathological progress in different modalities were obtained. Finally, an extreme learning machine-based decision tree was established to perform multiclass diagnosis using these scores. The experiments were conducted on the AD Neuroimaging Initiative dataset, and accuracies of 66.7% and 57.3% and F1-scores of 64.9% and 55.7% were achieved in three- and four-way classifications, respectively. The results also showed that the proposed framework achieved a better performance than the method that did not score multimodal data and the methods in previous studies, thereby indicating that the LDA scoring strategy is an efficient way for multimodalities fusion in AD multiclass classification.

A Bayesian spatial model for imaging genetics

We develop a Bayesian bivariate spatial model for multivariate regression analysis applicable to studies examining the influence of genetic variation on brain structure. Our model is motivated by an imaging genetics study of the Alzheimer's Disease Neuroimaging Initiative (ADNI), where the objective is to examine the association between images of volumetric and cortical thickness values summarizing the structure of the brain as measured by magnetic resonance imaging (MRI) and a set of 486 single nucleotide polymorphism (SNPs) from 33 Alzheimer's disease (AD) candidate genes obtained from 632 subjects. A bivariate spatial process model is developed to accommodate the correlation structures typically seen in structural brain imaging data. First, we allow for spatial correlation on a graph structure in the imaging phenotypes obtained from a neighborhood matrix for measures on the same hemisphere of the brain. Second, we allow for correlation in the same measures obtained from different hemispheres (left/right) of the brain. We develop a mean-field variational Bayes algorithm and a Gibbs sampling algorithm to fit the model. We also incorporate Bayesian false discovery rate (FDR) procedures to select SNPs. We implement the methodology in a new release of the R package bgsmtr. We show that the new spatial model demonstrates superior performance over a standard model in our application. Data used in the preparation of this article were obtained from the ADNI database (https://adni.loni.usc.edu).

Pursuing sources of heterogeneity in modeling clustered population

Researchers often have to deal with heterogeneous population with mixed regression relationships, increasingly so in the era of data explosion. In such problems, when there are many candidate predictors, it is not only of interest to identify the predictors that are associated with the outcome, but also to distinguish the true sources of heterogeneity, that is, to identify the predictors that have different effects among the clusters and thus are the true contributors to the formation of the clusters. We clarify the concepts of the source of heterogeneity that account for potential scale differences of the clusters and propose a regularized finite mixture effects regression to achieve heterogeneity pursuit and feature selection simultaneously. We develop an efficient algorithm and show that our approach can achieve both estimation and selection consistency. Simulation studies further demonstrate the effectiveness of our method under various practical scenarios. Three applications are presented, namely, an imaging genetics study for linking genetic factors and brain neuroimaging traits in Alzheimer's disease, a public health study for exploring the association between suicide risk among adolescents and their school district characteristics, and a sport analytics study for understanding how the salary levels of baseball players are associated with their performance and contractual status.

An Efficient Combination among sMRI, CSF, Cognitive Score, and APOE ε4 Biomarkers for Classification of AD and MCI Using Extreme Learning Machine

Alzheimer's disease (AD) is the most common cause of dementia and a progressive neurodegenerative condition, characterized by a decline in cognitive function. Symptoms usually appear gradually and worsen over time, becoming severe enough to interfere with individual daily tasks. Thus, the accurate diagnosis of both AD and the prodromal stage (i.e., mild cognitive impairment (MCI)) is crucial for timely treatment. As AD is inherently dynamic, the relationship between AD indicators is unclear and varies over time. To address this issue, we first aimed at investigating differences in atrophic patterns between individuals with AD and MCI and healthy controls (HCs). Then we utilized multiple biomarkers, along with filter- and wrapper-based feature selection and an extreme learning machine- (ELM-) based approach, with 10-fold cross-validation for classification. Increasing efforts are focusing on the use of multiple biomarkers, which can be useful for the diagnosis of AD and MCI. However, optimum combinations have yet to be identified and most multimodal analyses use only volumetric measures obtained from magnetic resonance imaging (MRI). Anatomical structural MRI (sMRI) measures have also so far mostly been used separately. The full possibilities of using anatomical MRI for AD detection have thus yet to be explored. In this study, three measures (cortical thickness, surface area, and gray matter volume), obtained from sMRI through preprocessing for brain atrophy measurements; cerebrospinal fluid (CSF), for quantification of specific proteins; cognitive score, as a measure of cognitive performance; and APOE ε4 allele status were utilized. Our results show that a combination of specific biomarkers performs well, with accuracies of 97.31% for classifying AD vs. HC, 91.72% for MCI vs. HC, 87.91% for MCI vs. AD, and 83.38% for MCIs vs. MCIc, respectively, when evaluated using the proposed algorithm. Meanwhile, the areas under the curve (AUC) from the receiver operating characteristic (ROC) curves combining multiple biomarkers provided better classification performance. The proposed features combination and selection algorithm effectively classified AD and MCI, and MCIs vs. MCIc, the most challenging classification task, and therefore could increase the accuracy of AD classification in clinical practice. Furthermore, we compared the performance of the proposed method with SVM classifiers, using a cross-validation method with Alzheimer's Disease Neuroimaging Initiative (ADNI) datasets.

A survey on machine and statistical learning for longitudinal analysis of neuroimaging data in Alzheimer's disease

BACKGROUND AND OBJECTIVES

Recently, longitudinal studies of Alzheimer's disease have gathered a substantial amount of neuroimaging data. New methods are needed to successfully leverage and distill meaningful information on the progression of the disease from the deluge of available data. Machine learning has been used successfully for many different tasks, including neuroimaging related problems. In this paper, we review recent statistical and machine learning applications in Alzheimer's disease using longitudinal neuroimaging.

METHODS

We search for papers using longitudinal imaging data, focused on Alzheimer's Disease and published between 2007 and 2019 on four different search engines.

RESULTS

After the search, we obtain 104 relevant papers. We analyze their approach to typical challenges in longitudinal data analysis, such as missing data and variability in the number and extent of acquisitions.

CONCLUSIONS

Reviewed works show that machine learning methods using longitudinal data have potential for disease progression modelling and computer-aided diagnosis. We compare results and models, and propose future research directions in the field.

L2RM: Low-rank Linear Regression Models for High-dimensional Matrix Responses

The aim of this paper is to develop a low-rank linear regression model (L2RM) to correlate a high-dimensional response matrix with a high dimensional vector of covariates when coefficient matrices have low-rank structures. We propose a fast and efficient screening procedure based on the spectral norm of each coefficient matrix in order to deal with the case when the number of covariates is extremely large. We develop an efficient estimation procedure based on the trace norm regularization, which explicitly imposes the low rank structure of coefficient matrices. When both the dimension of response matrix and that of covariate vector diverge at the exponential order of the sample size, we investigate the sure independence screening property under some mild conditions. We also systematically investigate some theoretical properties of our estimation procedure including estimation consistency, rank consistency and non-asymptotic error bound under some mild conditions. We further establish a theoretical guarantee for the overall solution of our two-step screening and estimation procedure. We examine the finite-sample performance of our screening and estimation methods using simulations and a large-scale imaging genetic dataset collected by the Philadelphia Neurodevelopmental Cohort (PNC) study.

Predicting Alzheimer's Disease Conversion From Mild Cognitive Impairment Using an Extreme Learning Machine-Based Grading Method With Multimodal Data

Identifying patients with mild cognitive impairment (MCI) who are at high risk of progressing to Alzheimer's disease (AD) is crucial for early treatment of AD. However, it is difficult to predict the cognitive states of patients. This study developed an extreme learning machine (ELM)-based grading method to efficiently fuse multimodal data and predict MCI-to-AD conversion. First, features were extracted from magnetic resonance (MR) images, and useful features were selected using a feature selection method. Second, multiple modalities of MCI subjects, including MRI, positron emission tomography, cerebrospinal fluid biomarkers, and gene data, were individually graded using the ELM method. Finally, these grading scores calculated from different modalities were fed into a classifier to discriminate subjects with progressive MCI from those with stable MCI. The proposed approach has been validated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, and an accuracy of 84.7% was achieved for an AD prediction within 3 years. Experiments on predicting AD conversion from MCI within different periods showed similar results with the 3-year prediction. The experimental results demonstrate that the proposed approach benefits from the efficient fusion of four modalities, resulting in an accurate prediction of MCI-to-AD conversion.

Identifying Autism Spectrum Disorder With Multi-Site fMRI via Low-Rank Domain Adaptation

Autism spectrum disorder (ASD) is a neurodevelopmental disorder that is characterized by a wide range of symptoms. Identifying biomarkers for accurate diagnosis is crucial for early intervention of ASD. While multi-site data increase sample size and statistical power, they suffer from inter-site heterogeneity. To address this issue, we propose a multi-site adaption framework via low-rank representation decomposition (maLRR) for ASD identification based on functional MRI (fMRI). The main idea is to determine a common low-rank representation for data from the multiple sites, aiming to reduce differences in data distributions. Treating one site as a target domain and the remaining sites as source domains, data from these domains are transformed (i.e., adapted) to a common space using low-rank representation. To reduce data heterogeneity between the target and source domains, data from the source domains are linearly represented in the common space by those from the target domain. We evaluated the proposed method on both synthetic and real multi-site fMRI data for ASD identification. The results suggest that our method yields superior performance over several state-of-the-art domain adaptation methods.

Bayesian GWAS with Structured and Non-Local Priors

MOTIVATION

The flexibility of a Bayesian framework is promising for GWAS, but current approaches can benefit from more informative prior models. We introduce a novel Bayesian approach to GWAS, called Structured and Non-Local Priors (SNLPs) GWAS, that improves over existing methods in two important ways. First, we describe a model that allows for a marker's gene-parent membership and other characteristics to influence its probability of association with an outcome. Second, we describe a non-local alternative model for differential minor allele rates at each marker, in which the null and alternative hypotheses have no common support.

RESULTS

We employ a non-parametric model that allows for clustering of the genes in tandem with a regression model for marker-level covariates, and demonstrate how incorporating these additional characteristics can improve power. We further demonstrate that our non-local alternative model gives symmetric rates of convergence for the null and alternative hypotheses, whereas commonly used local alternative models have asymptotic rates that favor the alternative hypothesis over the null. We demonstrate the robustness and flexibility of our structured and non-local model for different data generating scenarios and signal-to-noise ratios. We apply our Bayesian GWAS method to single nucleotide polymorphisms data collected from a pool of Alzheimer's disease and cognitively normal patients from the Alzheimer's Database Neuroimaging Initiative.

AVAILABILITY AND IMPLEMENTATION

R code to perform the SNLPs method is available at https://github.com/lockEF/BayesianScreening.

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.

Variants of the Aggression-Related RBFOX1 Gene in a Population Representative Birth Cohort Study: Aggressiveness, Personality, and Alcohol Use Disorder

Background: Recently, RBFOX1, a gene encoding an RNA binding protein, has consistently been associated with aggressive and antisocial behavior. Several loci in the gene have been nominally associated with aggression in genome-wide association studies, the risk alleles being more frequent in the general population. We have hence examined the association of four RBFOX1 single nucleotide polymorphisms, previously found related to aggressive traits, with aggressiveness, personality, and alcohol use disorder in birth cohort representative samples. Methods: We used both birth cohorts of the Estonian Children Personality Behavior and Health Study (ECPBHS; original n = 1,238). Aggressiveness was assessed using the Buss-Perry Aggression Questionnaire and the Lifetime History of Aggressiveness structured interview at age 25 (younger cohort) or 33 (older cohort). Big Five personality at age 25 was measured with self-reports and the lifetime occurrence of alcohol use disorder assessed with the MINI interview. RBFOX1 polymorphisms rs809682, rs8062784, rs12921846, and rs6500744 were genotyped in all participants. Given the restricted size of the sample, correction for multiple comparisons was not applied. Results: Aggressiveness was not significantly associated with the RBFOX1 genotype. RBFOX1 rs8062784 was associated with neuroticism and rs809682 with extraversion. Two out of four analyzed RBFOX1 variants, rs8062784 and rs12921846, were associated with the occurrence of alcohol use disorder. Conclusions: In the birth cohort representative sample of the ECPBHS, no association of RBFOX1 with aggressiveness was found, but RBFOX1 variants affected basic personality traits and the prevalence of alcohol use disorder. Future studies on RBFOX1 should consider the moderating role of personality and alcohol use patterns in aggressiveness.

RBFOX1, encoding a splicing regulator, is a candidate gene for aggressive behavior

The RBFOX1 gene (or A2BP1) encodes a splicing factor important for neuronal development that has been related to autism spectrum disorder and other neurodevelopmental phenotypes. Evidence from complementary sources suggests that this gene contributes to aggressive behavior. Suggestive associations with RBFOX1 have been identified in genome-wide association studies (GWAS) of anger, conduct disorder, and aggressive behavior. Nominal association signals in RBFOX1 were also found in an epigenome-wide association study (EWAS) of aggressive behavior. Also, variants in this gene affect temporal lobe volume, a brain area that is altered in several aggression-related phenotypes. In animals, this gene has been shown to modulate aggressive behavior in Drosophila. RBFOX1 has also been associated with canine aggression and is upregulated in mice that show increased aggression after frustration of an expected reward. Associated common genetic variants as well as rare duplications and deletions affecting RBFOX1 have been identified in several psychiatric and neurodevelopmental disorders that are often comorbid with aggressive behaviors. In this paper, we comprehensively review the cumulative evidence linking RBFOX1 to aggression behavior and provide new results implicating RBFOX1 in this phenotype. Most of these studies (genetic and epigenetic analyses in humans, neuroimaging genetics, gene expression and animal models) are hypothesis-free, which strengthens the validity of the findings, although all the evidence is nominal and should therefore be taken with caution. Further studies are required to clarify in detail the role of this gene in this complex phenotype.

Robust and Discriminative Brain Genome Association Study

Brain Genome Association (BGA) study, which investigates the associations between brain structure/function (characterized by neuroimaging phenotypes) and genetic variations (characterized by Single Nucleotide Polymorphisms (SNPs)), is important in pathological analysis of neurological disease. However, the current BGA studies are limited as they did not explicitly consider the disease labels, source importance, and sample importance in their formulations. We address these issues by proposing a robust and discriminative BGA formulation. Specifically, we learn two transformation matrices for mapping two heterogeneous data sources (i.e., neuroimaging data and genetic data) into a common space, so that the samples from the same subject (but diffrent sources) are close to each other, and also the samples with diffrent labels are separable. In addition, we add a sparsity constraint on the transformation matrices to enable feature selection on both data sources. Furthermore, both sample importance and source importance are also considered in the formulation via adaptive parameter-free sample and source weightings. We have conducted various experiments, using Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, to test how well the neuroimaging phenotypes and SNPs can represent each other in the common space.

Identifying progressive imaging genetic patterns via multi-task sparse canonical correlation analysis: a longitudinal study of the ADNI cohort

MOTIVATION

Identifying the genetic basis of the brain structure, function and disorder by using the imaging quantitative traits (QTs) as endophenotypes is an important task in brain science. Brain QTs often change over time while the disorder progresses and thus understanding how the genetic factors play roles on the progressive brain QT changes is of great importance and meaning. Most existing imaging genetics methods only analyze the baseline neuroimaging data, and thus those longitudinal imaging data across multiple time points containing important disease progression information are omitted.

RESULTS

We propose a novel temporal imaging genetic model which performs the multi-task sparse canonical correlation analysis (T-MTSCCA). Our model uses longitudinal neuroimaging data to uncover that how single nucleotide polymorphisms (SNPs) play roles on affecting brain QTs over the time. Incorporating the relationship of the longitudinal imaging data and that within SNPs, T-MTSCCA could identify a trajectory of progressive imaging genetic patterns over the time. We propose an efficient algorithm to solve the problem and show its convergence. We evaluate T-MTSCCA on 408 subjects from the Alzheimer's Disease Neuroimaging Initiative database with longitudinal magnetic resonance imaging data and genetic data available. The experimental results show that T-MTSCCA performs either better than or equally to the state-of-the-art methods. In particular, T-MTSCCA could identify higher canonical correlation coefficients and capture clearer canonical weight patterns. This suggests that T-MTSCCA identifies time-consistent and time-dependent SNPs and imaging QTs, which further help understand the genetic basis of the brain QT changes over the time during the disease progression.

AVAILABILITY AND IMPLEMENTATION

The software and simulation data are publicly available at https://github.com/dulei323/TMTSCCA.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Effects of pioglitazone on mnemonic hippocampal function: A blood oxygen level-dependent functional magnetic resonance imaging study in elderly adults

Introduction

Mitochondrial dysfunction is implicated in the pathophysiology of Alzheimer's disease (AD). Accordingly, drugs that positively influence mitochondrial function are being evaluated in delay-of-onset clinical trials with at-risk individuals. Such ongoing clinical research can be advanced by developing a better understanding of how these drugs affect intermediate brain phenotypes associated with both AD risk and pathophysiology.

Methods

Using a randomized, parallel-group, placebo-controlled design in 55 healthy elderly volunteers, we explored the effects of oral, low-dose pioglitazone, a thiazolidinedione with promitochondrial effects, on hippocampal activity measured with functional magnetic resonance imaging during the encoding of novel face–name pairs.

Results

Compared with placebo, 0.6 mg of pioglitazone (but not 2.1 mg, 3.9 mg, or 6.0 mg) administered daily for 14 days was associated with significant increases in right hippocampal activation during encoding of novel face–name pairs at day 7 and day 14, relative to baseline.

Discussion

Our exploratory analyses suggest that low-dose pioglitazone has measurable effects on mnemonic brain function associated with AD risk and pathophysiology.

•

Right hippocampal activity increased after 7 and 14 days of 0.6 mg of oral pioglitazone administration.

•

Pioglitazone-associated hippocampal effects were not manifested at the level of memory performance.

•

Nonspecific increases in distributed brain activity at higher pioglitazone doses (>0.6 mg).

Brain-Wide Genome-Wide Association Study for Alzheimer's Disease via Joint Projection Learning and Sparse Regression Model

Brain-wide and genome-wide association (BW-GWA) study is presented in this paper to identify the associations between the brain imaging phenotypes (i.e., regional volumetric measures) and the genetic variants [i.e., single nucleotide polymorphism (SNP)] in Alzheimer's disease (AD). The main challenges of this study include the data heterogeneity, complex phenotype-genotype associations, high-dimensional data (e.g., thousands of SNPs), and the existence of phenotype outliers. Previous BW-GWA studies, while addressing some of these challenges, did not consider the diagnostic label information in their formulations, thus limiting their clinical applicability. To address these issues, we present a novel joint projection and sparse regression model to discover the associations between the phenotypes and genotypes. Specifically, to alleviate the negative influence of data heterogeneity, we first map the genotypes into an intermediate imaging-phenotype-like space. Then, to better reveal the complex phenotype-genotype associations, we project both the mapped genotypes and the original imaging phenotypes into a diagnostic-label-guided joint feature space, where the intraclass projected points are constrained to be close to each other. In addition, we use l2,1-norm minimization on both the regression loss function and the transformation coefficient matrices, to reduce the effect of phenotype outliers and also to encourage sparse feature selections of both the genotypes and phenotypes. We evaluate our method using AD neuroimaging initiative dataset, and the results show that our proposed method outperforms several state-of-the-art methods in term of the average root-mean-square error of genome-to-phenotype predictions. Besides, the associated SNPs and brain regions identified in this study have also been shown in the previous AD-related studies, thus verifying the effectiveness and potential of our proposed method in AD pathogenesis study.

Discovering heritable modes of MEG spectral power

Brain structure and many brain functions are known to be genetically controlled, but direct links between neuroimaging measures and their underlying cellular-level determinants remain largely undiscovered. Here, we adopt a novel computational method for examining potential similarities in high-dimensional brain imaging data between siblings. We examine oscillatory brain activity measured with magnetoencephalography (MEG) in 201 healthy siblings and apply Bayesian reduced-rank regression to extract a low-dimensional representation of familial features in the participants' spectral power structure. Our results show that the structure of the overall spectral power at 1-90 Hz is a highly conspicuous feature that not only relates siblings to each other but also has very high consistency within participants' own data, irrespective of the exact experimental state of the participant. The analysis is extended by seeking genetic associations for low-dimensional descriptions of the oscillatory brain activity. The observed variability in the MEG spectral power structure was associated with SDK1 (sidekick cell adhesion molecule 1) and suggestively with several other genes that function, for example, in brain development. The current results highlight the potential of sophisticated computational methods in combining molecular and neuroimaging levels for exploring brain functions, even for high-dimensional data limited to a few hundred participants.

A structural equation model for imaging genetics using spatial transcriptomics

Imaging genetics deals with relationships between genetic variation and imaging variables, often in a disease context. The complex relationships between brain volumes and genetic variants have been explored with both dimension reduction methods and model-based approaches. However, these models usually do not make use of the extensive knowledge of the spatio-anatomical patterns of gene activity. We present a method for integrating genetic markers (single nucleotide polymorphisms) and imaging features, which is based on a causal model and, at the same time, uses the power of dimension reduction. We use structural equation models to find latent variables that explain brain volume changes in a disease context, and which are in turn affected by genetic variants. We make use of publicly available spatial transcriptome data from the Allen Human Brain Atlas to specify the model structure, which reduces noise and improves interpretability. The model is tested in a simulation setting and applied on a case study of the Alzheimer's Disease Neuroimaging Initiative.

A Robust Reduced Rank Graph Regression Method for Neuroimaging Genetic Analysis

To characterize associations between genetic and neuroimaging data, a variety of analytic methods have been proposed in neuroimaging genetic studies. These methods have achieved promising performance by taking into account inherent correlation in either the neuroimaging data or the genetic data alone. In this study, we propose a novel robust reduced rank graph regression based method in a linear regression framework by considering correlations inherent in neuroimaging data and genetic data jointly. Particularly, we model the association analysis problem in a reduced rank regression framework with the genetic data as a feature matrix and the neuroimaging data as a response matrix by jointly considering correlations among the neuroimaging data as well as correlations between the genetic data and the neuroimaging data. A new graph representation of genetic data is adopted to exploit their inherent correlations, in addition to robust loss functions for both the regression and the data representation tasks, and a square-root-operator applied to the robust loss functions for achieving adaptive sample weighting. The resulting optimization problem is solved using an iterative optimization method whose convergence has been theoretically proved. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset have demonstrated that our method could achieve competitive performance in terms of regression performance between brain structural measures and the Single Nucleotide Polymorphisms (SNPs), compared with state-of-the-art alternative methods.

Low-Rank Representation for Multi-center Autism Spectrum Disorder Identification

Effective utilization of multi-center data for autism spectrum disorder (ASD) diagnosis recently has attracted increasing attention, since a large number of subjects from multiple centers are beneficial for investigating the pathological changes of ASD. To better utilize the multi-center data, various machine learning methods have been proposed. However, most previous studies do not consider the problem of data heterogeneity (e.g., caused by different scanning parameters and subject populations) among multi-center datasets, which may degrade the diagnosis performance based on multi-center data. To address this issue, we propose a multi-center low-rank representation learning (MCLRR) method for ASD diagnosis, to seek a good representation of subjects from different centers. Specifically, we first choose one center as the target domain and the remaining centers as source domains. We then learn a domain-specific projection for each source domain to transform them into an intermediate representation space. To further suppress the heterogeneity among multiple centers, we disassemble the learned projection matrices into a shared part and a sparse unique part. With the shared matrix, we can project target domain to the common latent space, and linearly represent the source domain datasets using data in the transformed target domain. Based on the learned low-rank representation, we employ the k-nearest neighbor (KNN) algorithm to perform disease classification. Our method has been evaluated on the ABIDE database, and the superior classification results demonstrate the effectiveness of our proposed method as compared to other methods.

Strategies for integrated analysis in imaging genetics studies

Imaging Genetics (IG) integrates neuroimaging and genomic data from the same individual, deepening our knowledge of the biological mechanisms behind neurodevelopmental domains and neurological disorders. Although the literature on IG has exponentially grown over the past years, the majority of studies have mainly analyzed associations between candidate brain regions and individual genetic variants. However, this strategy is not designed to deal with the complexity of neurobiological mechanisms underlying behavioral and neurodevelopmental domains. Moreover, larger sample sizes and increased multidimensionality of this type of data represents a challenge for standardizing modeling procedures in IG research. This review provides a systematic update of the methods and strategies currently used in IG studies, and serves as an analytical framework for researchers working in this field. To complement the functionalities of the Neuroconductor framework, we also describe existing R packages that implement these methodologies. In addition, we present an overview of how these methodological approaches are applied in integrating neuroimaging and genetic data.

Williams Syndrome neuroanatomical score associates with GTF2IRD1 in large-scale magnetic resonance imaging cohorts: a proof of concept for multivariate endophenotypes

Despite great interest in using magnetic resonance imaging (MRI) for studying the effects of genes on brain structure in humans, current approaches have focused almost entirely on predefined regions of interest and had limited success. Here, we used multivariate methods to define a single neuroanatomical score of how William's Syndrome (WS) brains deviate structurally from controls. The score is trained and validated on measures of T1 structural brain imaging in two WS cohorts (training, n = 38; validating, n = 60). We then associated this score with single nucleotide polymorphisms (SNPs) in the WS hemi-deleted region in five cohorts of neurologically and psychiatrically typical individuals (healthy European descendants, n = 1863). Among 110 SNPs within the 7q11.23 WS chromosomal region, we found one associated locus (p = 5e-5) located at GTF2IRD1, which has been implicated in animal models of WS. Furthermore, the genetic signals of neuroanatomical scores are highly enriched locally in the 7q11.23 compared with summary statistics based on regions of interest, such as hippocampal volumes (n = 12,596), and also globally (SNP-heritability = 0.82, se = 0.25, p = 5e-4). The role of genetic variability in GTF2IRD1 during neurodevelopment extends to healthy subjects. Our approach of learning MRI-derived phenotypes from clinical populations with well-established brain abnormalities characterized by known genetic lesions may be a powerful alternative to traditional region of interest-based studies for identifying genetic variants regulating typical brain development.

Identification of associations between genotypes and longitudinal phenotypes via temporally-constrained group sparse canonical correlation analysis

Motivation

Neuroimaging genetics identifies the relationships between genetic variants (i.e., the single nucleotide polymorphisms) and brain imaging data to reveal the associations from genotypes to phenotypes. So far, most existing machine-learning approaches are widely used to detect the effective associations between genetic variants and brain imaging data at one time-point. However, those associations are based on static phenotypes and ignore the temporal dynamics of the phenotypical changes. The phenotypes across multiple time-points may exhibit temporal patterns that can be used to facilitate the understanding of the degenerative process. In this article, we propose a novel temporally constrained group sparse canonical correlation analysis (TGSCCA) framework to identify genetic associations with longitudinal phenotypic markers.

Results

The proposed TGSCCA method is able to capture the temporal changes in brain from longitudinal phenotypes by incorporating the fused penalty, which requires that the differences between two consecutive canonical weight vectors from adjacent time-points should be small. A new efficient optimization algorithm is designed to solve the objective function. Furthermore, we demonstrate the effectiveness of our algorithm on both synthetic and real data (i.e., the Alzheimer’s Disease Neuroimaging Initiative cohort, including progressive mild cognitive impairment, stable MCI and Normal Control participants). In comparison with conventional SCCA, our proposed method can achieve strong associations and discover phenotypic biomarkers across multiple time-points to guide disease-progressive interpretation.

Availability and implementation

The Matlab code is available at https://sourceforge.net/projects/ibrain-cn/files/.

Three-dimensional cardiovascular imaging-genetics: a mass univariate framework

Motivation

Left ventricular (LV) hypertrophy is a strong predictor of cardiovascular outcomes, but its genetic regulation remains largely unexplained. Conventional phenotyping relies on manual calculation of LV mass and wall thickness, but advanced cardiac image analysis presents an opportunity for high-throughput mapping of genotype-phenotype associations in three dimensions (3D).

Results

High-resolution cardiac magnetic resonance images were automatically segmented in 1124 healthy volunteers to create a 3D shape model of the heart. Mass univariate regression was used to plot a 3D effect-size map for the association between wall thickness and a set of predictors at each vertex in the mesh. The vertices where a significant effect exists were determined by applying threshold-free cluster enhancement to boost areas of signal with spatial contiguity. Experiments on simulated phenotypic signals and SNP replication show that this approach offers a substantial gain in statistical power for cardiac genotype-phenotype associations while providing good control of the false discovery rate. This framework models the effects of genetic variation throughout the heart and can be automatically applied to large population cohorts.

Availability and implementation

The proposed approach has been coded in an R package freely available at https://doi.org/10.5281/zenodo.834610 together with the clinical data used in this work.

Contact

declan.oregan@imperial.ac.uk.

Supplementary information

Supplementary data are available at Bioinformatics online.

Machine learning shows association between genetic variability in PPARG and cerebral connectivity in preterm infants

Preterm birth affects 11% of births globally; 35% of infants develop long-term neurocognitive problems, and prematurity leads to the loss of 75 million disability adjusted life years per annum worldwide. Imaging studies have shown that these infants have extensive alterations in brain development, but little is known about the molecular or cellular mechanisms involved. This imaging genetics study found a strong association between abnormal cerebral connectivity and variability in the PPARG gene, implicating PPARG signaling in abnormal white-matter development in preterm infants and suggesting a tractable new target for therapeutic research.

Preterm infants show abnormal structural and functional brain development, and have a high risk of long-term neurocognitive problems. The molecular and cellular mechanisms involved are poorly understood, but novel methods now make it possible to address them by examining the relationship between common genetic variability and brain endophenotype. We addressed the hypothesis that variability in the Peroxisome Proliferator Activated Receptor (PPAR) pathway would be related to brain development. We employed machine learning in an unsupervised, unbiased, combined analysis of whole-brain diffusion tractography together with genomewide, single-nucleotide polymorphism (SNP)-based genotypes from a cohort of 272 preterm infants, using Sparse Reduced Rank Regression (sRRR) and correcting for ethnicity and age at birth and imaging. Empirical selection frequencies for SNPs associated with cerebral connectivity ranged from 0.663 to zero, with multiple highly selected SNPs mapping to genes for PPARG (six SNPs), ITGA6 (four SNPs), and FXR1 (two SNPs). SNPs in PPARG were significantly overrepresented (ranked 7–11 and 67 of 556,000 SNPs; P < 2.2 × 10⁻⁷), and were mostly in introns or regulatory regions with predicted effects including protein coding and nonsense-mediated decay. Edge-centric graph-theoretic analysis showed that highly selected white-matter tracts were consistent across the group and important for information transfer (P < 2.2 × 10⁻¹⁷); they most often connected to the insula (P < 6 × 10⁻¹⁷). These results suggest that the inhibited brain development seen in humans exposed to the stress of a premature extrauterine environment is modulated by genetic factors, and that PPARG signaling has a previously unrecognized role in cerebral development.

Pattern Discovery in Brain Imaging Genetics via SCCA Modeling with a Generic Non-convex Penalty

Brain imaging genetics intends to uncover associations between genetic markers and neuroimaging quantitative traits. Sparse canonical correlation analysis (SCCA) can discover bi-multivariate associations and select relevant features, and is becoming popular in imaging genetic studies. The L1-norm function is not only convex, but also singular at the origin, which is a necessary condition for sparsity. Thus most SCCA methods impose [Formula: see text]-norm onto the individual feature or the structure level of features to pursuit corresponding sparsity. However, the [Formula: see text]-norm penalty over-penalizes large coefficients and may incurs estimation bias. A number of non-convex penalties are proposed to reduce the estimation bias in regression tasks. But using them in SCCA remains largely unexplored. In this paper, we design a unified non-convex SCCA model, based on seven non-convex functions, for unbiased estimation and stable feature selection simultaneously. We also propose an efficient optimization algorithm. The proposed method obtains both higher correlation coefficients and better canonical loading patterns. Specifically, these SCCA methods with non-convex penalties discover a strong association between the APOE e4 rs429358 SNP and the hippocampus region of the brain. They both are Alzheimer's disease related biomarkers, indicating the potential and power of the non-convex methods in brain imaging genetics.

Low-Rank Graph-Regularized Structured Sparse Regression for Identifying Genetic Biomarkers

In this paper, we propose a novel sparse regression method for Brain-Wide and Genome-Wide association study. Specifically, we impose a low-rank constraint on the weight coefficient matrix and then decompose it into two low-rank matrices, which find relationships in genetic features and in brain imaging features, respectively. We also introduce a sparse acyclic digraph with sparsity-inducing penalty to take further into account the correlations among the genetic variables, by which it can be possible to identify the representative SNPs that are highly associated with the brain imaging features. We optimize our objective function by jointly tackling low-rank regression and variable selection in a framework. In our method, the low-rank constraint allows us to conduct variable selection with the low-rank representations of the data; the learned low-sparsity weight coefficients allow discarding unimportant variables at the end. The experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset showed that the proposed method could select the important SNPs to more accurately estimate the brain imaging features than the state-of-the-art methods.

Data-driven regions of interest for longitudinal change in three variants of frontotemporal lobar degeneration

INTRODUCTION

Longitudinal imaging of neurodegenerative disorders is a potentially powerful biomarker for use in clinical trials. In Alzheimer's disease, studies have demonstrated that empirically derived regions of interest (ROIs) can provide more reliable measurement of disease progression compared with anatomically defined ROIs.

METHODS

We set out to derive ROIs with optimal effect size for quantifying longitudinal change in a hypothetical clinical trial by comparing atrophy rates in 44 patients with behavioral variant of frontotemporal dementia (bvFTD), 30 with the semantic variant primary progressive aphasia (svPPA), and 26 with the nonfluent variant PPA (nfvPPA) to atrophy in 97 cognitively healthy controls.

RESULTS

The regions identified for each variant were generally what would be expected from prior studies of frontotemporal lobar degeneration (FTLD). Sample size estimates for detecting a 40% reduction in annual rate of ROI atrophy varied substantially across groups, being 103 per arm in bvFTD, 31 in nfvPPA, and 10 in svPPA, but in all groups were less than those estimated for a priori ROIs and clinical measures. The variability in location of peak regions of atrophy across individuals was highest in bvFTD and lowest in svPPA, likely relating to the differences in effect size.

CONCLUSIONS

These findings suggest that, while cross-validated maps of change can improve sensitivity to change in FTLD compared with a priori regions, the reliability of these maps differs considerably across syndromes. Future studies can utilize these maps to design clinical trials, and should try to identify factors accounting for the variability in patterns of atrophy across individuals, particularly those with bvFTD.

Mining Outcome-relevant Brain Imaging Genetic Associations via Three-way Sparse Canonical Correlation Analysis in Alzheimer's Disease

Neuroimaging genetics is an emerging field that aims to identify the associations between genetic variants (e.g., single nucleotide polymorphisms (SNPs)) and quantitative traits (QTs) such as brain imaging phenotypes. In recent studies, in order to detect complex multi-SNP-multi-QT associations, bi-multivariate techniques such as various structured sparse canonical correlation analysis (SCCA) algorithms have been proposed and used in imaging genetics studies. However, associations between genetic markers and imaging QTs identified by existing bi-multivariate methods may not be all disease specific. To bridge this gap, we propose an analytical framework, based on three-way sparse canonical correlation analysis (T-SCCA), to explore the intrinsic associations among genetic markers, imaging QTs, and clinical scores of interest. We perform an empirical study using the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort to discover the relationships among SNPs from AD risk gene APOE, imaging QTs extracted from structural magnetic resonance imaging scans, and cognitive and diagnostic outcomes. The proposed T-SCCA model not only outperforms the traditional SCCA method in terms of identifying strong associations, but also discovers robust outcome-relevant imaging genetic patterns, demonstrating its promise for improving disease-related mechanistic understanding.