Federated and transfer learning methods for cross-ancestry and cross-phenotype integration of genomic datasets

用于基因组数据集跨血统和跨表型整合的联合和迁移学习方法

• 批准号: 10564023
• 负责人: Rui Duan
• 金额: $ 43.15万
• 依托单位: HARVARD SCHOOL OF PUBLIC HEALTH
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-12-20 至 2027-11-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10564023
• 关键词: Accounting; Address; African ancestry; Algorithms; All of Us Research Program; Assessment tool; Biological; Cardiovascular Diseases; Cloud Computing; Communication; Community Medicine; Complex; Computer software; Data; Data Collection; Data Commons; Disease; Disparity; Disparity population; Electronic Health Record; Environment; European ancestry; Genetic; Genetic Risk; Genotype; Goals; Healthcare; Heritability; Heterogeneity; High Performance Computing; Inequity; Institution; Joints; Knowledge; Learning; Link; Major Depressive Disorder; Mental disorders; Meta-Analysis; Methodology; Methods; Minority Groups; Modeling; Participant; Patients; Performance; Phenotype; Population; Population Heterogeneity; Rare Diseases; Reproducibility; Risk Assessment; Risk Factors; Sample Size; Sampling; Source; Techniques; Testing; Trans-Omics for Precision Medicine; Translating; Underrepresented Populations; United States National Institutes of Health; Variant; biobank; clinical risk; cloud platform; cluster computing; computerized tools; cost effective; data integration; data privacy; disorder risk; diverse data; federated learning; genetic architecture; genome wide association study; genomic data; graph knowledge base; health disparity; high dimensionality; improved; insight; knowledge graph; learning algorithm; learning strategy; multi-ethnic; multi-task learning; novel; open source; participant enrollment; pleiotropism; polygenic risk score; precision medicine; privacy preservation; privacy protection; programs; risk prediction; risk prediction model; risk stratification; statistics; trait; transfer learning; user friendly software

Abstract This proposal aims to develop advanced data integration methods for improving genetic risk prediction in under-represented non-European populations. Genome-Wide Association Studies (GWAS) have yielded important biological insights into the heritable basis of many complex traits and diseases, and polygenic risk scores (PRS) have shown promising potentials for disease risk stratification. However, since the vast majority of participants in large-scale genomic datasets are from European ancestry (EA) populations, the performance of current PRS is much poorer in non-EA populations than in EA populations, which may exacerbate existing health disparities. Despite some recent inclusive data collection efforts, current risk prediction methods cannot effectively address the heavily unbalanced sample sizes across populations. Robust data integration methods are needed to leverage similarities in genetic architectures across ancestral populations, phenotypic correlations and pleiotropy, and variant functional annotations while accounting for different sources of heterogeneity. Moreover, as various national and institutional biobanks become available, efficient information-sharing strategies with data privacy considerations are needed for combining data across biobanks to improve sample diversity and sample size. This proposal will address these needs by developing a methodological framework with advanced transfer learning (TL) and federated learning (FL) techniques for integrating various sources of data to bridge the gap of risk prediction across populations. Specifically, in Aim 1, we will develop a TL method to integrate ancestrally diverse data based on high-dimensional models with a distance-based regularization to characterize the similarities across populations, and a communication-efficient FL algorithm that jointly fits the TL model across multiple biobanks with only summary-level statistics. In Aim 2, we will develop methods that enable joint analyses of multiple phenotypes in association tests and risk prediction models. We will develop an FL algorithm to combine data from multiple biobanks for cross-phenotype association test, and a TL method with an angle-based regularization to leverage genetic correlations among mixed types of phenotypes in risk prediction. In Aim 3, we will develop knowledge- graph-based TL methods that leverage the shared latent spaces between phenotype-genotype knowledge graphs constructed from different ancestral populations and enable the incorporation of functional annotations. In Aim 4, we will develop open-access statistical software capable of implementing the proposed methods in both offline and cloud computing environments, and apply the proposed methods to the analysis of major depressive disorder and cardiovascular diseases using data from the All of Us program, eMERGE, and the UK biobank.

摘要 该提案旨在开发先进的数据整合方法，以改善遗传风险预测 在非欧洲人口中，全基因组关联研究（GWAS） 对许多复杂性状和疾病的遗传基础以及多基因风险的重要生物学见解 评分（PRS）已显示出疾病风险分层的良好潜力。然而，由于绝大多数 大规模基因组数据集的参与者来自欧洲血统（EA）人群， 目前的PRS在非EA人群中比EA人群差得多，这可能会加剧现有的健康状况 差距。尽管最近进行了一些包容性的数据收集工作，但目前的风险预测方法不能有效地 解决人口之间样本量严重不平衡的问题。需要强大的数据集成方法， 利用祖先群体之间遗传结构的相似性、表型相关性和多效性， 和变体功能注释，同时考虑异质性的不同来源。此外，由于各种 国家和机构生物库成为可用的，有效的信息共享战略，数据隐私 需要考虑合并生物库的数据，以提高样本多样性和样本量。这 该提案将通过开发一个具有高级迁移学习（TL）的方法框架来满足这些需求 以及联邦学习（FL）技术，用于整合各种数据源，以弥合风险预测的差距 在人群中。具体而言，在目标1中，我们将开发一种TL方法来整合祖先多样性数据 基于高维模型，采用基于距离的正则化来表征 群体，以及通信高效的FL算法，该算法联合拟合多个生物库的TL模型， 只是统计数据的摘要。在目标2中，我们将开发能够联合分析多种表型的方法 关联测试和风险预测模型。我们将开发一种FL算法，以联合收割机从多个 用于交叉表型关联测试的生物库，以及具有基于角度的正则化的TL方法，以利用 风险预测中混合型表型间的遗传相关性。在目标3中，我们将开发知识- 基于图的TL方法，利用表型-基因型知识图之间的共享潜在空间 从不同的祖先群体构建，并能够纳入功能注释。在目标4中， 我们将开发开放获取的统计软件，能够在离线和离线两种情况下实施所提出的方法。 和云计算环境，并将所提出的方法应用于重性抑郁症的分析 和心血管疾病的研究，使用的数据来自All of Us项目、eMERGE和英国生物银行。