Alzheimer's MultiOme Data Repurposing: Artificial Intelligence, Network Medicine, and Therapeutics Discovery

项目总结 阿尔茨海默病的易感性涉及复杂的、多基因的和多效性的遗传结构；此外，还有 没有可以延缓阿尔茨海默病神经退化过程的疾病修饰治疗。传统简化论者 范式忽视了AD的内在复杂性，并往往导致缺乏临床治疗 有益的或充满不利影响的。现有的多组学数据资源，包括遗传学、基因组学、 转录组学、互作组学(蛋白质-蛋白质相互作用和染色质相互作用)尚未完全完成 利用和整合，探索AD的病理生物学和药物发现。了解阿尔茨海默病遗传学 以及基因组学从细胞系统和分子相互作用组扰动的角度来看 疾病(称为疾病模块)是网络医学的本质。系统的识别和 新的潜在发病机制和疾病模块的特征，将作为识别 以及验证AD的新风险基因和药物靶点。根据我们的初步结果，我们假设一个基因组- 广泛的多模式人工智能(AI)框架，可从人类识别新的风险基因和网络 基因组/外显子组测序和多组学发现使我们能够更全面地理解AD的发病机制 阿尔茨海默病的发病机制和靶向治疗干预发展迅速，取得了巨大成功。目标1 将通过全基因组/外显子组测序(WGS/WES)确定罕见的编码和非编码变体 利用基于序列和结构的深度技术在蛋白质功能和基因调控区获得丰富的蛋白质 学习模型。这些分析将汇集WGS/WES和阿尔茨海默病的临床数据 测序计划(ADSP)，公开提供的蛋白质结构(即蛋白质-蛋白质界面、蛋白质-配基 结合位点、翻译后修饰)和序列(表达数量性状基因座[eQTL]， 组蛋白-QTL和转录因子结合-QTL)信息来自PDB数据库、GTEx、NIH路线图、 FANTOM5、EPECENCODE和NIH4D基因组。目标2将确定Gwas是否存在常见的变种 与AD相关的病理生物学和内表型在细胞类型特异性的基因调控网络中是丰富的 使用贝叶斯框架的方式。我们将使用WGS/WES和 来自我们现有队列的蛋白质组表达数据：克利夫兰临床卢鲁沃脑健康中心 老龄化与神经退行性疾病生物库与克利夫兰阿尔茨海默病 研究中心(CADRC)。目标3将测试风险基因和网络可以通过 在硅胶药物再利用、基于群体的验证和功能测试中，以确定候选药物和药物 将修改AD的组合。该项目的成功完成将提供有能力和智慧的 基于计算机的工具箱，支持搜索、共享、可视化、查询和分析遗传学， 基因组学和多组学概况数据，用于AD和其他疾病的基因组知情治疗发现 如果广泛应用，神经退行性疾病。

PROJECT SUMMARY Predisposition to AD involves a complex, polygenic, and pleiotropic genetic architecture; furthermore, there are no disease modifying treatments that slow the neurodegenerative process for AD. Traditional reductionist paradigms overlook the inherent complexity of AD and have often led to treatments that are lack of clinical benefits or fraught with adverse effects. Existing multi-omics data resources, including genetics, genomics, transcriptomics, interactomics (protein-protein interactions and chromatin interactions), have not yet been fully utilized and integrated to explore the pathobiology and drug discovery for AD. Understanding AD genetics and genomics from the point-of-view of how cellular systems and molecular interactome perturbations underlie the disease (termed disease module) is the essence of network medicine. Systematic identification and characterization of novel underlying pathogenesis and disease module, will serve as a foundation for identifying and validating novel risk genes and drug targets in AD. Given our preliminary results, we posit that a genome- wide, multimodal artificial intelligence (AI) framework to identify new risk genes and networks from human genome/exome sequencing and multi-omics findings enable a more complete mechanistic understanding of AD pathogenesis and the rapid development of targeted therapeutic intervention for AD with great success. Aim 1 will determine whether rare coding and non-coding variants by whole-genome/exome sequencing (WGS/WES) are enriched in protein-functional and gene-regulatory regions using sequence and structure-based deep learning models. These analyses will assemble WGS/WES and clinical data from Alzheimer's Disease Sequencing Project (ADSP), publicly available protein structure (i.e., protein-protein interfaces, protein-ligand binding sites, post-translational modifications) and sequence (expression quantitative trait locus [eQTLs], histone-QTLs, and transcription factor binding-QTLs) information from the PDB database, GTEx, NIH RoadMap, FANTOM5, PsychENCODE, and NIH 4D Nucleome. Aim 2 will determine whether GWAS common variants linked to AD pathobiology and endophenotypes are enriched in gene regulatory networks in a cell-type specific manner using a Bayesian framework. We will validate risk gene and network findings using WGS/WES and protein panel expression data from our existing cohorts: The Cleveland Clinic Lou Ruvo Center for Brain Health Aging and Neurodegenerative Disease Biobank (CBH-Biobank) and the Cleveland Alzheimer's Disease Research Center (CADRC). Aim 3 will test the hypothesis that risk genes and networks can be modulated via in silico drug repurposing, population-based validation, and functional test, to identify candidate agents and drug combinations that will modify AD. The successful completion of this project will offer capable and intelligent computer-based toolboxes that enable searching, sharing, visualizing, querying, and analyzing genetics, genomics, and multi-omics profiling data for genome-informed therapeutic discoveries for AD and other neurodegenerative disease if broadly applied.