Integrating Neuroimaging, Multi-omics, and Clinical Data in Complex Disease

将神经影像、多组学和临床数据整合到复杂疾病中

• 批准号: 9916801
• 负责人: Dokyoon Kim
• 金额: $ 34.15万
• 依托单位: INDIANA UNIV-PURDUE UNIV AT INDIANAPOLIS
• 依托单位国家: 美国
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-07-01 至 2022-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9916801
• 关键词: Address; Advanced Development; Aging; Alzheimer' s Disease; Alzheimer’s disease biomarker; Beds; Behavioral; Big Data; Biological; Brain; Clinical; Clinical Data; Cohort Studies; Complex; Data; Data Set; Detection; Development; Diagnostic tests; Discipline; Disease; Disease Progression; Evaluation; Genes; Genetic; Genetic Variation; Genomics; Genotype; Health; Heterogeneity; Indiana; Individual; Informatics; Knowledge; Machine Learning; Magnetic Resonance Imaging; Mediating; Mediation; Medical Imaging; Memory; Meta-Analysis; Methods; Modeling; Molecular; Multiomic Data; Multivariate Analysis; Nerve Degeneration; Neurodegenerative Disorders; Outcome; Phenotype; Positron-Emission Tomography; Proteomics; Public Health; Science; Statistical Methods; Structure; Susceptibility Gene; Technology; Testing; Time; Validation; Variant; base; biomedical informatics; cohort; data integration; diagnostic biomarker; disease classification; diverse data; endophenotype; epigenomics; genetic association; genetic variant; high dimensionality; high risk; improved; insight; interest; learning strategy; mathematical model; metabolomics; multidimensional data; multimodality; multiple omics; neuroimaging; new therapeutic target; novel; novel diagnostics; predict clinical outcome; rare variant; risk variant; therapeutic target; transcriptomics; user friendly software

ABSTRACT Rapid progress in biomedical informatics has generated massive high-dimensional data sets (“big data”), ranging from clinical information and medical imaging to genomic sequence data. The scale and complexity of these data sets hold great promise, yet present substantial challenges. To fully exploit the potential informativeness of big data, there is an urgent need to find effective ways to integrate diverse data from different levels of informatics technologies. Existing approaches and methods for data integration to date have several important limitations. In this project, we propose novel statistical methods and strategies to integrate neuroimaging, multi-omics, and clinical/behavioral data sets. To increase power for association analysis compared to existing methods, we propose a novel multi-phenotype multi-variant association method that can evaluate the cumulative effect of common and rare variants in genes or regions of interest, incorporate prior biological knowledge on the multiple phenotype structure, identify associated phenotypes among multiple phenotypes, and be computationally efficient for high-dimensional phenotypes. To improve the prediction of clinical outcomes, we propose a novel machine learning strategy that can integrate multimodal neuroimaging and multi-omics data into a mathematical model and can incorporate prior biological knowledge to identify genomic interactions associated with clinical outcomes. The ongoing Alzheimer's Disease Neuroimaging Initiative (ADNI) and Indiana Memory and Aging Study (IMAS) projects as a test bed provide a unique opportunity to evaluate/validate the proposed methods. Specific Aims: Aim 1: to develop powerful statistical methods for multivariate tests of associations between multiple phenotypes and a single genetic variant or set of variants (common and rare) in regions of interest, and to develop methods for mediation analysis to integrate neuroimaging, genetic, and clinical data to test for direct and indirect genetic effects mediated through neuroimaging phenotypes on clinical outcomes; Aim 2: to develop a novel multivariate model that combines multi-omics and neuroimaging data using a machine learning strategy to predict individuals with disease or those at high-risk for developing disease, and to develop a novel multivariate model incorporating prior biological knowledge to identify genomic interactions associated with clinical outcomes; Aim 3: to evaluate and validate the proposed methods using real data from the ADNI and IMAS cohorts; and Aim 4: to disseminate and support publicly available user-friendly software that efficiently implements the proposed methods. RELEVANCE TO PUBLIC HEALTH: Alzheimer's disease (AD) as an exemplar is an increasingly common progressive neurodegenerative condition with no validated disease modifying treatment. The proposed multivariate methods are likely to help identify novel diagnostic biomarkers and therapeutic targets for AD. Identifying new susceptibility loci/biomarkers for AD has important implications for gaining greater insight into the molecular mechanisms underlying AD.

摘要 生物医学信息学的快速发展产生了大量的高维数据集(大数据)， 范围从临床信息、医学成像到基因组序列数据。规模和复杂性 在这些数据集中，有很大的希望，但也面临着巨大的挑战。充分挖掘潜力 大数据的信息性，迫切需要找到有效的方法来整合来自 不同层次的信息学技术。到目前为止用于数据集成的现有途径和方法 有几个重要的限制。在这个项目中，我们提出了新的统计方法和策略来 集成神经成像、多组学和临床/行为数据集。增加结社权 与已有方法相比，我们提出了一种新的多表型多变量关联方法 一种可以评估基因或感兴趣区域中常见和罕见变异的累积效应的方法， 整合关于多种表型结构的先验生物学知识，识别相关表型 在多个表型之间，并且对于高维表型计算效率很高。为了提高 对于临床结果的预测，我们提出了一种新的机器学习策略，它可以集成 将多模式神经成像和多组学数据整合到数学模型中，并可将之前 生物学知识，以确定与临床结果相关的基因组相互作用。正在进行的 阿尔茨海默病神经成像倡议(ADNI)和印第安纳州记忆和老龄化研究(IMAS)项目 作为试验台，提供了一个独特的机会来评估/验证所提出的方法。具体目标：目标1： 开发强大的统计方法，对多种表型之间的关联性进行多变量检验 以及感兴趣区域的单个遗传变异或一组变异(常见和罕见)，并开发 结合神经影像、遗传和临床数据的中介分析方法，以测试直接和 通过神经成像表型介导的间接遗传效应对临床结果的影响；目标2：发展 一种使用机器学习结合多组学和神经成像数据的新型多变量模型 预测患有疾病或罹患疾病的高危人群的策略，并制定 融合先验生物学知识的新型多变量模型用于识别相关的基因组相互作用 临床结果；目标3：使用ADNI的真实数据评估和验证所建议的方法 以及目标4：传播和支持公开提供的用户友好型软件， 有效地实现了所提出的方法。与公共健康相关：阿尔茨海默病 (AD)作为样本，是一种越来越常见的进行性神经退行性疾病，没有经过验证的 疾病调理疗法。建议的多变量方法可能有助于识别新的诊断方法 AD的生物标志物和治疗靶点。识别AD的新易感基因座/生物标记物 对于更深入地了解阿尔茨海默病的分子机制具有重要意义。