The Integrated Stress Response in Human Islets During Early T1D

早期 T1D 期间人体胰岛的综合应激反应

• 批准号: 10592566
• 负责人: Thomas O Metz
• 金额: $ 40.13万
• 依托单位: UNIVERSITY OF CHICAGO
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-15 至 2024-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10592566
• 关键词: Address; Affect; Area; Artificial Intelligence; Autoimmunity; Beta Cell; Biological; Biological Markers; Cell Survival; Cell physiology; Cellular Stress; Clinical; Collaborations; Communities; Community Networks; Computer software; Data; Data Set; Defect; Development; Development Plans; Experimental Designs; Feedback; Generations; Grant; Human; Immunologics; Individual; Inflammation; Ingestion; Insulin-Dependent Diabetes Mellitus; Knowledge; Lead; Learning; Machine Learning; Measurement; Messenger RNA; Metadata; Methods; Modeling; Molecular; Molecular Profiling; Monitor; Multiomic Data; Ontology; Pathogenesis; Pathway interactions; Physics; Production; Proteins; Proteomics; PubMed; Publications; Publishing; Readiness; Research; Research Design; Resources; Risk; Sample Size; Science; Signal Pathway; Standardization; Stress; Technology; TensorFlow; Testing; Traction; Translating; base; biological adaptation to stress; biomarker discovery; biomarker panel; biomarker validation; classical conditioning; computerized data processing; data repository; feature extraction; heterogenous data; improved; insulin dependent diabetes mellitus onset; islet; learning community; lipidomics; machine learning method; machine learning model; minimally invasive; multidisciplinary; multiple omics; neoantigens; novel; parent grant; parent project; phrases; predictive modeling; rapid growth; repository; response; software development; stress granule; trend

ABSTRACT The project, Integrated Stress Response in Human Islets During Early Type 1 Diabetes (T1D), hypothesizes that the activation of the integrated stress response and formation of stress granules is an early cellular response initiating β cell stress in T1D that determines cell survival and can be monitored in pre- and early-T1D individuals with minimal invasiveness. A multidisciplinary Team science approach is being taken to test this hypothesis, collecting a large suite of heterogenous data, such as mRNA, lipidomics, proteomics and immunologic measurements. Machine learning is being used to extract a multi-biomarker panel to aid in stratifying stress in human islets and translating these findings to individuals at-risk for T1D and new-onset T1D. Although we are formatting the multi-omics data for this specific machine learning task within the parent grant, the data being generated, as well as our data collected from prior collaborations, are not generally AI/ML-ready for general application of methods. They are however excellent candidates to be used as “flagship” datasets for AI/ML readiness, both to test novel AI/ML approaches to tackle data pre-processing challenges and to extract molecular signatures of T1D. These two gaps in analyses are the central themes of two aims. The first aim focuses on the generation of AI/ML ready omics datasets that are properly annotated to address challenges in sparsity and bias, such as imputation and batch correction. The second aim focuses AI/ML ready multi-omic datasets to enable new studies in using machine learning to elicit biomarkers and pathway-level molecular signatures from the data focused on standard AI/ML methods, as well as those specialized for small sample size. Dataset machine learning model cards will be utilized to better enable to AI/ML research communities to utilize these datasets in an efficient manner. For both aims there is a key focus on generating reusable software approaches to generate data packages that can be directly imported into the most common AI/ML packages and released to the AI/ML community through a variety of resources that enable feedback to continually improve and refine the AI/ML readiness software development plan.

抽象的 该项目“早期 1 型糖尿病 (T1D) 期间人体胰岛的综合应激反应”指出 整合应激反应的激活和应激颗粒的形成是早期细胞反应 在 T1D 中启动 β 细胞应激，该应激决定细胞存活，并且可以在 T1D 前期和早期个体中进行监测 正在采用多学科团队科学方法来测试这一假设， 收集大量异质数据，例如 mRNA、脂质组学、蛋白质组学和免疫学数据 机器学习被用来提取多生物标记物组，以帮助对压力进行分层。 人类胰岛并将这些发现转化为 T1D 和新发 T1D 风险的个体。 在父资助中格式化此特定机器学习任务的多组学数据，数据是 生成的数据以及我们从之前的合作中收集的数据通常不适合一般的 AI/ML 然而，它们是用作人工智能/机器学习“旗舰”数据集的优秀候选者。 准备就绪，既可以测试新的人工智能/机器学习方法来解决数据预处理的挑战，也可以提取分子 T1D 的两个特征是两个目标的中心主题。 生成 AI/ML 就绪的组学数据集，并对其进行适当注释，以解决稀疏性和偏差方面的挑战， 例如插补和批量校正，重点关注 AI/ML 就绪的多组学数据集。 使用机器学习从数据中提取生物标志物和通路水平分子特征的新研究 专注于标准 AI/ML 方法，以及专门针对小样本数据集机器的方法。 学习模型卡将用于更好地帮助 AI/ML 研究社区在以下领域利用这些数据集： 对于这两个目标，重点是生成可重用的软件方法来生成。 可以直接导入最常见的AI/ML包并发布到AI/ML的数据包 社区通过各种资源提供反馈，以不断改进和完善 AI/ML 准备软件开发计划。