An Explainable Unified AI Strategy for Efficient and Robust Integrative Analysis of Multi-omics Data from Highly Heterogeneous Multiple Studies

一种可解释的统一人工智能策略，用于对来自高度异质性多项研究的多组学数据进行高效、稳健的综合分析

• 批准号: 10729965
• 负责人: Gregory W Carter
• 金额: $ 55.2万
• 依托单位: JACKSON LABORATORY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-15 至 2025-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10729965
• 关键词: Address; Age; Aging; Algorithms; Biological Markers; Blindness; Centenarian; Cognitive aging; Complex; Computer software; Data; Data Analyses; Data Reporting; Data Set; Dementia; Deposition; Detection; Dimensions; Disease; Equilibrium; Family Study; Funding Opportunities; Gene Expression; Genetic; Health; Heterogeneity; Human; Individual; Knowledge; Learning; Life; Longevity; Methods; Modality; Modeling; Multiomic Data; Mus; Orthologous Gene; Outcome; Pathway interactions; Phase; Phenotype; Population; Sampling; Structure; Testing; Therapeutic Intervention; Training; Work; age related; computerized tools; data integration; differential expression; disorder risk; graph neural network; high dimensionality; human data; human old age (65+); improved; interest; mouse model; offspring; programs; protective allele; prototype; response; risk variant; supervised learning; tool

Healthy centenarians carry protective variants that counteract age-related disease risk variants, the former of which are mostly rare. Therefore, markers associated with exceptional longevity (EL) need be discovered through integrative multi-omics data analysis to improve detection power. However, existing integrative analysis method for multi-omics data do not model the relationships among markers in a modality and among studies, muddying the efficient use of pertinent information provided by multi-omics data from heterogeneous studies. We propose a unified AI strategy that models the relationships among markers, modalities, and studies, and learns nonlinear low-dimensional representations of data in a common space via graph neural networks (GNN). We achieve deep integration by enforcing the maximization of similarities between study representations and the phenotype prediction accuracy in a single GNN. The proposal has three specific aims: 1) Develop an explainable unified AI strategy and software for efficient and robust integrative analysis of multi-omics data from highly heterogeneous multiple studies. 2) Apply the methods developed in Aim 1 to Long-Life Family Study (LLFS) and Integrative Longevity Omics (ILO) data provided by the EL consortium to identify EL-associated pathways and biomarkers. 3) Apply the methods developed in Aim 1 to omics data from human and 100 species of diverse lifespan provided by the EL consortium to identify conserved and species-specific EL-associated pathways and markers. The outcome of this work will result in a publicly available integrative omics data analysis software which not only is able to identify robust longevity-associated pathways and biomarkers, but will also be applicable to any complex disease study with similar omics data analysis demands. Our work will contribute significantly to identify therapeutic interventions for improving human health.

健康的百岁老人携带保护性变异，可以抵消与年龄相关的疾病风险变异，而前者大多罕见。因此，需要通过综合多组学数据分析来发现与超长寿命（EL）相关的标志物，以提高检测能力。然而，现有的多组学数据综合分析方法并没有对一种模式和研究之间的标记之间的关系进行建模，从而使异构研究的多组学数据提供的相关信息的有效利用变得混乱。我们提出了一种统一的人工智能策略，对标记、模式和研究之间的关系进行建模，并通过图神经网络（GNN）学习公共空间中数据的非线性低维表示。我们通过在单个 GNN 中实现研究表示和表型预测准确性之间相似性的最大化来实现深度集成。该提案有三个具体目标：1）开发可解释的统一人工智能策略和软件，用于对来自高度异质性多项研究的多组学数据进行高效、稳健的综合分析。 2) 将目标 1 中开发的方法应用于 EL 联盟提供的长寿家庭研究 (LLFS) 和综合长寿组学 (ILO) 数据，以识别 EL 相关途径和生物标志物。 3) 将目标 1 中开发的方法应用于 EL 联盟提供的来自人类和 100 个不同寿命物种的组学数据，以识别保守的和物种特异性的 EL 相关途径和标记。这项工作的成果将产生一个公开的综合组学数据分析软件，该软件不仅能够识别强大的长寿相关途径和生物标志物，而且还适用于具有类似组学数据分析需求的任何复杂疾病研究。我们的工作将为确定改善人类健康的治疗干预措施做出重大贡献。