Novel Hybrid Computational Models to Disentangle Complex Immune Responses

新型混合计算模型可解开复杂的免疫反应

基本信息

批准号：
10794448
负责人：
Esteban Aberlardo Hernandez Vargas
金额：
$ 17.18万
依托单位：
UNIVERSITY OF IDAHO
依托单位国家：
美国
项目类别：
财政年份：
2023
资助国家：
美国
起止时间：
2023-09-26 至 2026-08-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10794448
关键词：
2019-nCoV Address Antigen-Antibody Complex Biological Biological Sciences Biology Biomedical Research COVID-19 pandemic Cell model Collaborations Computational algorithm Computer Models Computing Methodologies Dangerousness Data Differential Equation Dimensions Disease Educational process of instructing Equation Equilibrium Etiology Europe Event Family Generations Hybrids Idaho Immune Immune Targeting Immune response Immune system Immunologic Factors Immunotherapy Infection Influenza Innate Immune System Knowledge Laboratory Finding Machine Learning Mathematics Measures Mediating Methods Modeling Molecular Morbidity - disease rate Mus Parameter Estimation Pathology Play Predictive Value Public Health Public Policy Rhinovirus Role Science Scientist Severities Severity of illness System Techniques Testing Therapeutic Time Training Universities Viral Viral Respiratory Tract Infection Virus Virus Diseases attenuation biological systems co-infection complex biological systems computational suite computerized tools data integration design experimental study fictional works high dimensionality high reward high risk human disease immunoregulation improved influenza infection innovation large datasets machine learning algorithm machine learning method mathematical methods mathematical model mathematical sciences mortality novel pandemic influenza pathogenic virus predictive modeling prevent respiratory sound theories

2019-nCoV Address Antigen-Antibody Complex Biological Biological Sciences Biology Biomedical Research COVID-19 pandemic Cell model Collaborations Computational algorithm Computer Models Computing Methodologies Dangerousness Data Differential Equation Dimensions Disease Educational process of instructing Equation Equilibrium Etiology Europe Event Family Generations Hybrids Idaho Immune Immune Targeting Immune response Immune system Immunologic Factors Immunotherapy Infection Influenza Innate Immune System Knowledge Laboratory Finding Machine Learning Mathematics Measures Mediating Methods Modeling Molecular Morbidity - disease rate Mus Parameter Estimation Pathology Play Predictive Value Public Health Public Policy Rhinovirus Role Science Scientist Severities Severity of illness System Techniques Testing Therapeutic Time Training Universities Viral Viral Respiratory Tract Infection Virus Virus Diseases attenuation biological systems co-infection complex biological systems computational suite computerized tools data integration design experimental study fictional works high dimensionality high reward high risk human disease immunoregulation improved influenza infection innovation large datasets machine learning algorithm machine learning method mathematical methods mathematical model mathematical sciences mortality novel pandemic influenza pathogenic virus predictive modeling prevent respiratory sound theories

展开

项目摘要

Most quantitative models in biomedical research have been formulated by ordinary differential equations (ODEs). Despite the great contributions ODEs have made to biology and beyond, the high-dimensional, time-dependent factors of the immune system still pose a significant challenge to the predictive value of ODEs as it would require several hundred equations and thousands of parameters to be estimated. The recent rise of machine learning as a powerful computational tool to integrate large datasets presents a special opportunity to deal with the inherent complexity of biological systems. However, machine learning approaches do not consider the mechanistic knowledge of the underlying interactions. Preliminary studies that combine ODEs and machine learning highlight that these computational algorithms could be on the cusp of a major revolution. Remarkably enough, however, no parameter estimation theory exists to integrate simultaneously both approaches. We propose to create new hybrid models and test their predictions in a mouse viral coinfection system to address a central vexation for infection biology which is how and when to modulate immune responses to mitigate mortality during lethal respiratory viral infection. At the interface between mathematical and life sciences, we will develop and analyze a novel suite of computational models that will integrate the underlying biological mechanisms to manage ill-posed problems and explore massive design spaces, allowing for robust predictions from complex biological systems. To validate and test our novel and foundational mathematical approaches, we will generate the biological data from a mouse infection system with a mild viral pathogen (rhinovirus) two days before infection with a lethal viral pathogen (influenza) that results in reduced disease compared to single infection alone. We hypothesize that this system can train our mathematical models in a natural way how the innate immune system can be manipulated to reduce mortality to lethal infections and beyond. Key model predictions will be tested by targeted immune system manipulation during lethal infection, paving the way to understanding the role of complex immune interactions in respiratory viral disease pathology.

生物医学研究中的大多数定量模型都是由普通微分方程提出的（ODES）。尽管OD对生物学及其他地区做出了巨大贡献，但高维，但免疫系统的时间依赖性因素仍然对预测值构成重大挑战 ODE需要估计数百个方程和数千个参数。这机器学习作为一种强大的计算工具的最新兴起，用于集成大型数据集处理生物系统固有复杂性的特殊机会。但是，机器学习方法不考虑基本相互作用的机械知识。初步研究结合ODE和机器学习的强调，这些计算算法可能位于大革命的尖峰。然而，非常重要的是，没有参数估计理论存在同时整合这两种方法。我们建议创建新的混合模型并测试他们小鼠病毒共同感染系统中的预测，以解决感染生物学的中心烦恼在致命呼吸道病毒感染期间，如何以及何时调节对减轻死亡率的免疫反应。在数学和生命科学之间的界面上，我们将开发和分析一套新颖的套件计算模型将整合基本的生物学机制以管理不足问题并探索庞大的设计空间，从系统。为了验证和测试我们的小说和基础数学方法，我们将生成来自温和病毒病原体（Rhinovirus）的小鼠感染系统的生物数据前两天与单一感染相比，致死性病毒病原体（流感）的感染导致疾病降低独自的。我们假设该系统可以自然而然地训练我们的数学模型可以操纵免疫系统以降低致命感染的死亡率。关键模型预测将通过靶向免疫系统在致命感染期间进行测试，从而铺平了通往的道路了解复杂的免疫相互作用在呼吸道病毒疾病病理学中的作用。