Assessing Alzheimer disease risk and heterogeneity using multimodal machine learning approaches

使用多模式机器学习方法评估阿尔茨海默病风险和异质性

• 批准号: 10655876
• 负责人: ANITA L DESTEFANO
• 金额: $ 64万
• 依托单位: UNIV OF MASSACHUSETTS MED SCH WORCESTER
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-15 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10655876
• 关键词: Accounting; Alzheimer' s Disease; Alzheimer' s disease risk; Alzheimer’s disease biomarker; Autopsy; Biological Markers; Blood; Brain; Cerebrospinal Fluid; Characteristics; Clinical; Cognitive; Collection; Communities; Complex; Data; Data Storage and Retrieval; Dementia; Development; Diagnosis; Disease; Elderly; Ethnic group; European; Future; Gene Expression Regulation; Genes; Genetic; Genetic Predisposition to Disease; Heterogeneity; Human; Image; Impaired cognition; Individual; Intervention; Machine Learning; Measures; Medicine; Methods; Modality; Modeling; Molecular; Multiomic Data; National Institute on Aging; Nature; Nerve Degeneration; Non-linear Models; Ontology; Participant; Pathogenesis; Pattern; Persons; Plasma; Population Heterogeneity; Prevention strategy; Regulator Genes; Resources; Sampling; Statistical Models; Symptoms; Therapeutic; Therapeutic Clinical Trial; Tissues; Weight; base; clinical risk; cognitive function; combinatorial; deep learning; disease heterogeneity; disease phenotype; disorder subtype; effective therapy; endophenotype; ethnic diversity; feature selection; follow-up; gene interaction; gene regulatory network; genetic risk factor; high risk; innovation; insight; learning network; machine learning algorithm; machine learning framework; machine learning method; machine learning model; multimodal data; multimodality; neuroimaging; phenotypic data; risk stratification; supervised learning; therapeutic target; unsupervised learning

PROJECT SUMMARY/ABSTRACT Alzheimer's disease (AD) is the most common form of dementia characterized by progressive loss of cognitive function. Unfortunately, currently there is no effective treatment for AD and clinical interventions of AD have largely failed despite enormous efforts. For the current application, we seek to develop multimodal machine learning models by leveraging the rich collection of AD-related omics data and phenotypical data recently generated from large-scale collaborative projects such as Alzheimer Disease Neuroimaging Initiative (ADNI), Accelerating Medicines Partnership-AD (AMP-AD) and the Alzheimer's Disease Sequencing Project (ADSP). Three aims will be pursued in the current application. Aim 1. We will build an expandable multimodal unsupervised machine learning framework to investigate AD heterogeneity. Given the multifactorial nature of AD, we will perform AD subtyping by harnessing the rich information across multiple spectrum of data. Aim 2. We will build an expandable multimodal supervised machine learning framework to quantify AD risk from longitudinal follow up of cognitively normal elders. The models will be built from genetic susceptibility and gene regulatory information as well as endophenotypes measured when participants were cognitive normal. Aim 3. We will build AD-related gene interaction networks in post-mortem human brain samples. We will examine the association of multiple omics data with AD in brain samples, and build tissue-specific interaction networks to understand potential molecular mechanisms underlying AD pathogenesis. The present application represents an innovative approach to identify individuals at high risk of AD from both clinical and genetic risk factors in ethnically diverse populations. The outlined strategy will provide new insights into the risk stratification and prevention strategies for AD. We also commit to share our methods through GitHub or CRAN for free access across the scientific community.

项目摘要/摘要 阿尔茨海默病(AD)是最常见的痴呆形式，其特征是进行性认知能力丧失 功能。不幸的是，目前尚无有效的治疗AD的方法，临床上对AD的干预措施 尽管付出了巨大的努力，但基本上还是失败了。针对目前的应用，我们寻求开发多模式机器 利用最近收集的丰富的AD相关组学数据和表型数据建立学习模型 由阿尔茨海默病神经成像倡议(ADNI)等大型合作项目产生， 加速药物伙伴关系-AD(AMP-AD)和阿尔茨海默病测序项目(ADSP)。 目前的申请将追求三个目标。目标1.我们将构建一个可扩展的多式联运 用于调查AD异质性的无监督机器学习框架。鉴于多因素的性质， AD，我们将通过利用跨多个数据频谱的丰富信息来执行AD亚型。目标2. 我们将构建一个可扩展的多模式监督机器学习框架，以量化AD风险 认知正常老年人的纵向随访。这些模型将根据遗传易感性和基因 当参与者认知正常时，测量的监管信息以及内表型。目标3. 我们将在死后的人脑样本中建立AD相关基因相互作用网络。我们将研究 将多个组学数据与大脑样本中的AD联系起来，并建立组织特异性相互作用网络 了解AD发病的潜在分子机制。本申请代表 一种创新的方法，从临床和遗传风险因素中识别AD高危个体 不同种族的人口。概述的战略将提供对风险分层和 AD的预防策略。我们还承诺通过GitHub或CRAN共享我们的方法以供免费访问 整个科学界。