Methods for Enhancing Polygenic Risk Prediction Models for Complex Disease

增强复杂疾病多基因风险预测模型的方法

• 批准号: 10717244
• 负责人: Dokyoon Kim
• 金额: $ 80.48万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-07-01 至 2027-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10717244
• 关键词: Address; Adopted; African ancestry; Area; Atrial Fibrillation; Cardiomyopathies; Cardiovascular Diseases; Cardiovascular system; Clinical; Complex; Coronary Arteriosclerosis; DNA; Data; Development; Disease; Early Diagnosis; Early identification; Electronic Health Record; Electronic Medical Records and Genomics Network; Emerging Technologies; European ancestry; Genetic; Genetic Predisposition to Disease; Genetic Risk; Genome; Goals; Health Personnel; Heart failure; Incidence; Individual; Informatics; Investigation; Life; Machine Learning; Mathematics; Medicine; Methods; Modeling; Morbidity - disease rate; Phenotype; Precision Health; Prevention; Prevention strategy; Preventive therapy; Public Health; Research; Risk; Risk Factors; Scoring Method; Surveys; Testing; Translating; Translations; Variant; Vascular Diseases; Veterans; biobank; cardiac muscle disease; cardiovascular disorder risk; cardiovascular risk factor; clinical care; clinical decision support; clinical implementation; clinical risk; cohort; data integration; deep learning model; design; disorder prevention; disorder risk; early screening; effective therapy; exome; genetic information; genetic risk factor; genetic variant; genome-wide; heart rhythm; high risk population; improved; innovation; machine learning method; mortality; non-genetic; novel; polygenic risk score; predictive modeling; pressure; programs; prototype; rare variant; response; risk prediction; risk prediction model; social; social health determinants; statistics; trait; translational impact; translational potential; whole genome

PROJECT SUMMARY Early screening and prevention of individuals at risk of complex diseases are important strategies for reducing morbidity and mortality. Polygenic risk scores (PRS) are the cumulative, mathematical aggregation of risk derived from the contributions of many DNA variants across the genome. PRS are an emerging technology in the field of disease risk prediction and have been shown to be correlated with disease incidence. While PRS have shown great promise for complex diseases, current PRS models are overly simplistic and have limited predictive power and clinical utility. PRS do not account for the effects of rare genetic variants or other risk factors (clinical, environmental, social determinants of health) on disease risk. Rare variants generally have greater effects on disease risk due to selective pressure, but only a small number of individuals carry any single rare variant. The sparsity of rare variants makes it difficult to directly incorporate them into PRS. Additionally, while it is known that clinical, environmental, and social risk factors also influence risk, few analyses have successfully integrated PRS with these important non-genetic factors. To address this issue, we will develop novel translational informatics methods that integrate clinical, environmental, and genetic data to improve disease risk prediction. We will assess the clinical utility of these integrated risk prediction models using cardiovascular disease (CVD) to evaluate the potential for translation to clinical use. Based on the complexity of CVD, we hypothesize that a comprehensive range of risk factors along with rare variants need to be incorporated into PRS to improve the risk prediction and maximize the clinical utility of PRS for CVD. To achieve our goal, our specific aims are: 1) To develop novel methods that incorporate rare genetic variants into Polygenic Risk Scores (PRS); 2) To evaluate Integrated Risk Models that combine clinical, environmental, and social risk factors with PRS; 3) To develop and evaluate deep learning models integrating genetic, clinical, environmental, and social risk factors; 4) To translate our integrated models into the electronic health record (EHR). If these specific aims are achieved, we will have a set of integrated models that can be used in downstream clinical implementation programs to ultimately have a translational impact on disease treatment and prevention. Using these novel computational risk prediction models for precision health, along with our EHR integration approaches, will allow for the translation of integrated risk prediction into routine clinical care.

项目概要 对有复杂疾病风险的个体进行早期筛查和预防是减少疾病风险的重要策略 发病率和死亡率。多基因风险评分 (PRS) 是衍生风险的累积数学聚合 来自整个基因组中许多 DNA 变体的贡献。 PRS是该领域的一项新兴技术 疾病风险预测，并已被证明与疾病发生率相关。虽然 PRS 已经表明 对于复杂疾病的前景广阔，目前的 PRS 模型过于简单化且预测能力有限 和临床实用性。 PRS 不考虑罕见遗传变异或其他危险因素（临床、 健康的环境、社会决定因素）对疾病风险的影响。罕见的变体通常会产生更大的影响 由于选择压力，存在疾病风险，但只有少数人携带单一罕见变异。这 稀有变异的稀疏性使得很难将它们直接纳入 PRS。此外，虽然已知 临床、环境和社会风险因素也会影响风险，但很少有分析成功整合 PRS 与这些重要的非遗传因素有关。 为了解决这个问题，我们将开发新的转化信息学方法，整合临床、 环境和遗传数据可改善疾病风险预测。我们将评估这些的临床效用 使用心血管疾病（CVD）的综合风险预测模型来评估转化为 临床使用。基于 CVD 的复杂性，我们假设一系列全面的风险因素 需要将罕见变异纳入 PRS 中，以改善风险预测并最大化临床效用 CVD 的 PRS。 为了实现我们的目标，我们的具体目标是：1）开发融合罕见遗传变异的新方法 纳入多基因风险评分 (PRS)； 2) 评估结合临床、环境、 以及 PRS 的社会风险因素； 3）开发和评估整合遗传、临床、 环境和社会风险因素； 4）将我们的集成模型转化为电子健康记录 （电子病历）。如果这些具体目标实现了，我们将拥有一套可以用于以下方面的集成模型： 下游临床实施计划最终对疾病治疗和治疗产生转化影响 预防。使用这些新颖的计算风险预测模型以及我们的 EHR 来实现精准健康 整合方法将允许将综合风险预测转化为常规临床护理。