Machine learning methods to impute and annotate epigenomic maps

用于估算和注释表观基因组图谱的机器学习方法

• 批准号: 8925082
• 负责人: William Stafford Noble
• 金额: $ 28.29万
• 依托单位: UNIVERSITY OF WASHINGTON
• 依托单位国家: 美国
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-09-10 至 2017-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8925082
• 关键词: Accounting; Adult; Architecture; Big Data; Biochemical; Biological Assay; Biological Process; Cell Nucleus; Cells; ChIP-seq; Chromatin; Collection; Computer software; Computing Methodologies; DNA; DNase I hypersensitive sites sequencing; Data; Data Analyses; Data Set; Dependency; Disease; Elements; Evolution; Exhibits; Future; Generations; Genome; Genomics; Goals; Graph; Health; Human; Human Genome; In Vitro; Investigation; Joints; Label; Link; Machine Learning; Maps; Measures; Methodology; Methods; Modeling; Pattern; Phenotype; Positron-Emission Tomography; Process; Recording of previous events; Resources; Role; Scheme; System; Techniques; Time; Tissues; United States National Institutes of Health; Virtual Library; Work; assay development; base; cell type; computer based statistical methods; epigenome; epigenomics; fetal; functional genomics; genome annotation; histone modification; human disease; improved; insight; markov model; novel; pressure; programs; research study; three dimensional structure; transcriptome sequencing; virtual

DESCRIPTION (provided by applicant): The NIH Roadmap Epigenomics Program has produced reference epigenomic maps derived from a variety of human primary cells and tissues, including pluripotent cell types and in vitro differentiated forms, highly purified primar cells, and a range of fetal and adult tissues. The goal of the proposed project is to develop, validate and apply unsupervised machine learning methods to the joint analysis of these epigenomic maps along with (1) data generated by the NIH ENCODE Consortium, (2) a variety of publicly available data sets that characterize the three-dimensional structure of DNA in the nucleus, and (3) information about evolutionary conservation, represented by cross-species DNA alignments. The first aim of the project will use data imputation methods to carry out virtual functional genomics experiments. The proposed method is based on techniques developed in the context of recommender systems, but is extended to model dependencies along the genomic axis. By simultaneously analyzing the pattern of biochemical activity across a range of cell types and assay types, the proposed imputation method will accurately predict the results of an assay, such as ChIP-seq for a particular histone modification in a particular cell type, that has not yet been carried out. We will systematically apply this method to Roadmap Epigenomics and ENCODE data, filling in missing experiments in the matrix of cell types and assay types. The remaining three specific aims extend and apply our existing system for semi-automated genome annotation, Segway, which integrates a wide variety of functional genomics data into a human interpretable labeling of genomic elements. These analyses will be performed on real data as well as the virtual experiments from Aim 1. We propose a novel, graph-based regularization scheme and show how, using this approach, we can use Segway to perform integrated analysis of data across cell types and integrate 3D genome architecture information from assays such as Hi-C. We also propose a post-processing method to exploit patterns of evolutionary conservation to identify functionally important labels in the resulting annotations. The primary deliverables will include novel software for imputation and annotation, as well as publicly available sets of virtual experiments and genome annotations.

描述（由申请人提供）：NIH 表观基因组路线图计划已制作了源自多种人类原代细胞和组织的参考表观基因组图谱，包括多能细胞类型和体外分化形式、高度纯化的原代细胞以及一系列胎儿和成人组织。拟议项目的目标是开发、验证和应用无监督机器学习方法来联合分析这些表观基因组图谱以及 (1) NIH ENCODE 联盟生成的数据，(2) 各种公开可用的数据集，这些数据集表征细胞核中 DNA 的三维结构，以及（3）有关进化保守的信息，以跨物种 DNA 比对表示。该项目的第一个目标将使用数据插补方法进行虚拟功能基因组学实验。所提出的方法基于在推荐系统背景下开发的技术，但扩展到沿基因组轴建模依赖关系。通过同时分析一系列细胞类型和检测类型的生化活性模式，所提出的插补方法将准确预测检测结果，例如针对特定细胞类型中特定组蛋白修饰的 ChIP-seq尚未进行。我们将系统地将这种方法应用于路线图表观基因组学和编码数据，填补细胞类型和分析类型矩阵中缺失的实验。其余三个具体目标扩展并应用我们现有的半自动基因组注释系统 Segway，该系统将各种功能基因组学数据集成到人类可解释的基因组元素标记中。这些分析将在真实数据以及目标 1 的虚拟实验上进行。我们提出了一种新颖的、基于图形的正则化方案，并展示了如何使用这种方法，使用 Segway 对跨细胞类型和数据进行综合分析。整合来自 Hi-C 等检测的 3D 基因组架构信息。我们还提出了一种后处理方法，利用进化保守模式来识别结果注释中功能重要的标签。主要交付成果将包括用于插补和注释的新颖软件，以及公开可用的虚拟实验和基因组注释集。