Interpretable Deep Learning Methods to Investigate Genetics and Epigenetics of Alzheimer's Disease at a Single-Cell Resolution

可解释的深度学习方法以单细胞分辨率研究阿尔茨海默病的遗传学和表观遗传学

• 批准号: 10698166
• 负责人: JING ZHANG
• 金额: $ 63.43万
• 依托单位: UNIVERSITY OF CALIFORNIA-IRVINE
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-30 至 2027-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10698166
• 关键词: 3-Dimensional; Acceleration; Address; Adult; Affect; Age; Alzheimer' s Disease; Alzheimer' s disease related dementia; Alzheimer' s disease risk; Autopsy; Benchmarking; Biological Assay; Boundary Elements; Brain; Brain region; Cells; Chromatin; Clustered Regularly Interspaced Short Palindromic Repeats; Code; Collaborations; Communities; Complex; Computer Models; Computer software; Confusion; Data; Dimensions; Disease; Dropout; Elderly; Epigenetic Process; Etiology; Event; Excision; Family; Gender; Gene Expression Regulation; Genes; Genetic; Genome; Genome engineering; Genomics; Genotype; Graph; Health Care Costs; Heterogeneity; Hi-C; Hybrids; Impaired cognition; Individual; Knowledge; Learning; Life; Link; Memory Loss; Methods; Modality; Modeling; Molecular; Multiomic Data; Neurosciences; Patients; Pattern; Personal Satisfaction; Phenotype; Prevention strategy; Regulator Genes; Regulatory Element; Reporting; Research; Resolution; Risk Factors; Sampling; Scheme; Series; Software Tools; Specificity; System; Transcriptional Regulation; Variant; cell type; cognitive ability; computer science; deep learning; deep learning model; differential expression; effective therapy; epigenome; epigenomics; flexibility; functional genomics; genetic variant; genome annotation; genome wide association study; genomic data; high dimensionality; infancy; learning strategy; member; multimodal data; multimodality; multiple omics; neural; novel; open source; predictive modeling; reconstruction; risk variant; sequencing platform; single cell sequencing; supervised learning; tool; transcription factor; transcriptome; transcriptomics; treatment strategy

Alzheimer's disease and related dementias (ADRDs) are complex multifactorial disorders characterized by progressive memory loss, confusion, and impaired cognitive abilities in older adults. In addition to genetic variants, studies have reported that certain epigenetic, network, and genome organizational perturbations, and their complex interplay, contribute to ADRD progression, informing new cellular etiologies. The recent single-cell revolution, especially multimodal genomic profiling, makes it possible to scrutinize multi-scale dysregulations in ADRDs at the finest possible resolution. However, few methods have been developed to address this critical yet challenging task due to the high missingness, dimensionality, and complex feature interactions in single-cell data. In this project, we will develop interpretable deep learning methods and software tools to highlight multi-scale dysregulations contributing to ADRDs, including genetic, epigenetic, network, and chromatin structural alterations at a single-cell resolution. Distinct from previous efforts reporting a set of one-dimensional (1D) functional cis-regulatory elements (CREs) from only one genome and applying it to all samples, we aim to construct personal, compact, gene-centric, and cell-type-specific brain regulome from sc-multiome data. Specifically, we will first propose a scalable multimodal deep generative model to integrate large-scale, heterogeneous ADRD single-cell data with single-, multi-, and hybrid modalities. Distinct to existing methods, we will include an invariant representation learning scheme to derive latent cell representations uncorrelated with confounding factors (e.g., age, gender, read depth, and batch effects) for bias-free transcriptome and epigenome reconstruction (Aim 1). Then, we will go beyond the 1D genome annotation by deciphering the multi-scale gene regulation code (Aim 2), including cell-type- specific chromatin compartmentation, CREs and their target genes for functional interpretation, and transcription factor (TF) regulatory networks (TRNs). Lastly, we will develop interpretable deep learning models to link multi-scale dysregulations to ADRD with mechanistic explanation (Aim 3). This proposal is built on an existing multi-year collaboration among the Zhang, Won, and Gerstein labs that originated from the ENCODE and PsychENCODE projects, with diverse expertise in computer science, neuroscience, and genomics. Upon completion, our proposal will significantly accelerate research in a broader scientific community by providing essential tools to investigate functional regions in the genome and prioritize multi-scale risk factors for ADRD.

阿尔茨海默病和相关痴呆 (ADRD) 是一种复杂的多因素疾病，其特征是 老年人进行性记忆丧失、意识混乱和认知能力受损。此外 遗传变异，研究报告某些表观遗传、网络和基因组组织 扰动及其复杂的相互作用，有助于 ADRD 进展，为新的细胞提供信息 病因学。最近的单细胞革命，特别是多模式基因组分析，使之成为可能 以尽可能最好的分辨率仔细检查 ADRD 中的多尺度失调。然而，很少有 由于缺失率很高，已经开发出方法来解决这项关键但具有挑战性的任务， 单细胞数据中的维度和复杂特征交互。在这个项目中，我们将开发 可解释的深度学习方法和软件工具，以突出多尺度失调 导致 ADRD 的因素包括遗传、表观遗传、网络和染色质结构改变 单细胞分辨率。 与之前报告一组一维 (1D) 功能性顺式监管的工作不同 仅来自一个基因组的元素（CRE）并将其应用于所有样本，我们的目标是构建个人的、 来自 sc-multiome 数据的紧凑、以基因为中心、细胞类型特异性的大脑调节组。具体来说， 我们将首先提出一个可扩展的多模态深度生成模型来集成大规模、 具有单、多和混合模式的异质 ADRD 单细胞数据。与现有的不同 方法，我们将包括一个不变的表示学习方案来导出潜在细胞 与混杂因素（例如年龄、性别、阅读深度和批次效应）不相关的表示 用于无偏差转录组和表观基因组重建（目标 1）。然后，我们将超越一维 通过破译多尺度基因调控代码（目标 2）进行基因组注释，包括细胞类型 特定的染色质区室、CRE 及其用于功能解释的目标基因，以及 转录因子 (TF) 调控网络 (TRN)。最后，我们将开发可解释的深度学习 通过机制解释将多尺度失调与 ADRD 联系起来的模型（目标 3）。 该提案建立在张、Won 和 Gerstein 实验室源自 ENCODE 和 PsychENCODE 项目，在以下领域拥有不同的专业知识 计算机科学、神经科学和基因组学。完成后，我们的提案将显着 通过提供必要的调查工具来加速更广泛的科学界的研究 基因组中的功能区域，并优先考虑 ADRD 的多尺度风险因素。