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: 10296695
• 负责人: ANITA L DESTEFANO
• 金额: $ 61.69万
• 依托单位: BOSTON UNIVERSITY MEDICAL CAMPUS
• 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 2021-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10296695
• 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; 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; genetic risk factor; high risk; innovation; insight; learning network; machine learning algorithm; machine learning method; 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.

项目概要/摘要 阿尔茨海默病 (AD) 是最常见的痴呆症，其特征是认知能力进行性丧失 功能。不幸的是，目前AD尚无有效的治疗方法，AD的临床干预措施也较多。 尽管付出了巨大的努力，但基本上还是失败了。针对当前的应用，我们寻求开发多模式机器 最近利用丰富的 AD 相关组学数据和表型数据收集学习模型 由阿尔茨海默病神经影像计划（ADNI）等大型合作项目产生， 加速药物合作伙伴关系-AD (AMP-AD) 和阿尔茨海默病测序项目 (ADSP)。 当前的应用将追求三个目标。目标 1. 我们将建立一个可扩展的多式联运 用于研究 AD 异质性的无监督机器学习框架。鉴于其多因素性质 AD，我们将通过利用跨多个数据范围的丰富信息来执行 AD 子类型分析。目标2。 我们将建立一个可扩展的多模式监督机器学习框架来量化 AD 风险 对认知正常的老年人进行纵向随访。这些模型将根据遗传易感性和基因建立 当参与者认知正常时测量的调节信息以及内表型。目标3。 我们将在死后人类大脑样本中构建 AD 相关基因相互作用网络。我们将检查 将多个组学数据与大脑样本中的 AD 关联起来，并构建组织特异性相互作用网络 了解 AD 发病机制的潜在分子机制。本申请代表 一种从临床和遗传风险因素中识别 AD 高风险个体的创新方法 种族多样化的人口。概述的策略将为风险分层和风险分层提供新的见解 AD 的预防策略。我们还承诺通过 GitHub 或 CRAN 分享我们的方法以供免费访问 整个科学界。