Predicting Phenotype by Deep Learning Heterogeneous Multi-Omics Data

通过深度学习异构多组学数据预测表型

• 批准号: 10318084
• 负责人: Zhongming Zhao
• 金额: $ 33.26万
• 依托单位: UNIVERSITY OF TEXAS HLTH SCI CTR HOUSTON
• 依托单位国家: 美国
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-14 至 2025-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10318084
• 关键词: 3-Dimensional; Affect; Automobile Driving; Bioinformatics; Biological; Brain Diseases; Cell physiology; Cells; Code; Communities; Complex; Computerized Medical Record; Computing Methodologies; DNA; Data; Data Science; Data Set; Databases; Development; Dimensions; Disease; Elements; Environmental Risk Factor; Epigenetic Process; Gene Expression; Genes; Genetic; Genetic Transcription; Genetic study; Genome; Genomics; Genotype; Genotype-Tissue Expression Project; Human; Human Genome; Individual; Informatics; Link; Maps; Medical Informatics; Messenger RNA; Methods; Mining; Multiomic Data; Neurodegenerative Disorders; Neurodevelopmental Disorder; Other Genetics; Phenotype; Play; Population; Proteins; Regulation; Reporting; Research; Research Personnel; Resolution; Role; Sampling; Signal Transduction; Single Nucleotide Polymorphism; Statistical Methods; Technology; Time; Tissue-Specific Gene Expression; Tissues; Untranslated RNA; Variant; base; biobank; cell type; cohort; computerized tools; data mining; deep learning; disease phenotype; disorder risk; epigenomics; functional genomics; gene environment interaction; gene interaction; genetic architecture; genetic variant; genome wide association study; genome-wide; heterogenous data; human study; innovation; learning strategy; neural network; neuropsychiatric disorder; novel; programs; single cell sequencing; single-cell RNA sequencing; spatiotemporal; trait; transcriptome; web server

Project Summary Complex disease and traits are caused by dynamic genetic regulation and environmental interactions. Numerous genetic, genomic, and phenotypic datasets have been generated, including genotypes, gene expression, epigenetic changes, and electronic medical records (EMRs). Currently, there is main challenge on development of novel informatic approaches to effectively link phenotype with genomic information. Specifically, genome-wide association studies (GWAS) have reported several thousand single nucleotide polymorphisms (SNPs) that are significantly associated with the disease and traits; however, more than 80% of them are noncoding variants, making it difficult to interpret their potential disease-causal roles. We and others have systematically examined how phenotypic variability in disease risk for a broad spectrum of disease phenotypes can be explained by regulatory variants. Now, we hypothesize that such regulation will be in a tissue-specific, cell type-specific and developmental stage-specific (TCD-specific) manner. Importantly, large genomic consortia, like ENCODE, FANTOM5, the Roadmap Epigenomics, and GTEx have continuously generated high-quality functional data for annotating genome-wide variants. The emerging single-cell sequencing technologies have enabled us to examine how genetic variants affect cellular functions within individual cells or specific cell types. This brings us an unprecedented opportunity to develop novel statistical and computational approaches for deep understanding of the genetic architecture of phenotype. In this proposal, we combine bioinformatics, single cell omics, deep learning, and phenotype and EMR data mining to develop novel analytical strategies that maximally leverage information from both genotype and expression from massive heterogeneous data, aiming to predict phenotype by functional assessment of DNA variation at the TCD-specific levels. We propose the following three specific aims. (1) To develop a deep learning method for variant impact predictor, DeepVIP, that maximally utilizes functional and regulatory data to predict the causal roles of variants in complex disease and traits. (2) To develop phenotype-specific network approaches to resolve genotype-phenotype relationships in the spatiotemporal manner and single-cell resolution. We will develop a novel method, single cell dense module search of GWAS signals (scGWAS) and also a graphical neural network approach, GNN-scTP, to detect driving roles of genes from single cell RNA-seq data. These methods can effectively identify critical regulatory modules and genes in complex disease in the TCD-specific manner. (3) To apply the methods to 16 neurodevelopmental and neurodegenerative disorders and related traits, as well as broad phenotypes using Vanderbilt biobank (BioVU) and UK Biobank data – both have genotypes linked with rich phenotypic information. Our proposal is timely and innovative to study the genetic architecture in human complex diseases and traits by dissecting important genetic components, especially noncoding variants, at the functional, regulatory, spatial, temporal, and single cell levels.

项目摘要 复杂的疾病和性状是由动态遗传调控和环境相互作用引起的。 已经生成了许多遗传、基因组和表型数据集，包括基因型、基因组和表型数据集。 表达、表观遗传变化和电子病历（EMR）。目前，主要挑战是 开发新的信息学方法，以有效地将表型与基因组信息联系起来。 具体来说，全基因组关联研究（GWAS）已经报道了数千个单核苷酸多态性。 多态性（SNP）与疾病和性状显著相关;然而，超过80%的 它们是非编码变异体，因此很难解释其潜在的致病作用。我们和其他人 系统地研究了疾病风险的表型变异性如何导致广泛的疾病 表型可以通过调节变体来解释。现在，我们假设这种监管将在一个 组织特异性、细胞类型特异性和发育阶段特异性（TCD特异性）方式。重要的是，大 基因组联盟，如ENCODE，FANTOM 5，路线图表观基因组学，和GTEx不断 生成高质量的功能数据，用于注释全基因组变异。新兴的单细胞 测序技术使我们能够研究遗传变异如何影响细胞功能， 单个细胞或特定细胞类型。这给我们带来了前所未有的发展新的统计学的机遇 和计算方法，以深入了解表型的遗传结构。在这 我们结合联合收割机、生物信息学、单细胞组学、深度学习、表型和EMR数据挖掘， 开发新的分析策略，最大限度地利用来自基因型和表达的信息 从大量的异质性数据，旨在通过DNA变异的功能评估预测表型， TCD特异性水平。我们提出以下三个具体目标。(1)开发一种深度学习方法 对于变体影响预测器DeepVIP，它最大限度地利用功能和监管数据来预测 变异在复杂疾病和性状中的因果作用。(2)开发表型特异性网络方法 以时空方式和单细胞分辨率解析基因型-表型关系。我们将 开发了一种新的方法，单细胞密集模块搜索GWAS信号（scGWAS），也是一个图形化的 神经网络方法，GNN-scTP，从单细胞RNA-seq数据中检测基因的驱动作用。这些 方法可以有效地确定关键的调控模块和基因在复杂的疾病，在TCD特异性 方式(3)将这些方法应用于16种神经发育和神经退行性疾病及相关疾病 性状，以及广泛的表型使用范德比尔特生物银行（BioVU）和英国生物银行的数据-两者都有 与丰富的表型信息相关的基因型。我们的建议是及时和创新的研究遗传 通过解剖重要的遗传成分，特别是 非编码变体，在功能，调节，空间，时间和单细胞水平。