Penalized mixture cure models for identifying genomic features associated with outcome in acute myeloid leukemia

用于识别与急性髓系白血病结果相关的基因组特征的惩罚混合治疗模型

基本信息

批准号：
10544523
负责人：
Kellie J. Archer
金额：
$ 25.93万
依托单位：
OHIO STATE UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2022
资助国家：
美国
起止时间：
2022-01-01 至 2025-12-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10544523
关键词：
Acute Myelocytic Leukemia American Cancer Society Archives Biological Biological Assay Cessation of life Characteristics Chronic Clinical Clinical Trials Clip Computer software Cox Proportional Hazards Models Data Data Science Data Set Decision Making Development Diagnosis Disease Disease-Free Survival Effectiveness Event Gene Expression Genes Genomics Malignant Neoplasms Methodology Methods Methylation MicroRNAs Modality Modeling Molecular Mutation Oncology Outcome Patients Performance Population Study Predisposition Probability Process Prognosis Property RUNX1 gene Research Research Personnel Research Project Grants Risk Sample Size Sampling Sampling Studies Statistical Methods Stem cell transplant Subgroup System Techniques Technology Testing The Cancer Genome Atlas Therapeutic Therapeutic Agents Time Tissue Sample United States National Library of Medicine aged biomedical informatics cancer type chemotherapy clinical practice experience follow-up hazard high dimensionality improved interest mRNA Expression multidimensional data new therapeutic target novel prognostic risk stratification semiparametric simulation software development survival outcome survivorship targeted treatment therapeutic target

项目摘要

Molecular features associated with time-to-event outcomes, such as overall or disease-free survival, may be prognostically relevant or potential therapeutic targets. Therefore, analyzing data from high-throughput genomic assays with clinical follow-up data has been of growing interest. The Cancer Genome Atlas (TCGA) Project has collected baseline demographic, clinical characteristics, and follow-up data for 11,125 patients for 32 different cancer types and corresponding tissue samples were processed for examining SNPs, copy number, methylation, miRNA expression, and mRNA expression. Because the number of variables (P ) exceeds the sample size (N), one strategy frequently employed when associating molecular features to survivorship data is to ﬁt univariable Cox proportional hazards (PH) models followed by adjustment for multiple hypothesis tests using a false discovery rate approach. However, most chronic conditions and diseases, including cancer, are likely caused by multiple dysregulated genes or mutations. It is therefore critical to ﬁt multivariable models in the presence of a high- dimensional covariate space. Traditional statistical methods cannot be used when the number of features exceeds the sample size (e.g., P > N), though penalized methods perform automatic variable selection and accommodate the P > N scenario. Penalized approaches including LASSO, smoothly clipped absolute deviation (SCAD), adaptive LASSO, and Bayesian LASSO have all been extended to Cox's PH model for handling high-dimensional covariate spaces. However, when modeling survival or other time-to-event outcomes, the Cox PH model assumes that all subjects will experience the event of interest, which is violated when a subset of subjects are cured. Instead, when a subset of subjects in the data are cured, mixture cure models should be ﬁt. Although mixture cure models have been described for traditional settings where the number of samples exceeds the number of covariates, limited variable selection methods and no methods for high-dimensional model ﬁtting currently exist for mixture cure models. Therefore, this project will overcome a critical barrier to progress in this ﬁeld by developing penalized parametric and semi-parametric mixture cure models applicable for high-dimensional datasets. The speciﬁc aims of this application are to: (1) Develop penalized parametric mixture cure models for high-dimensional datasets; and (2) Develop a penalized semi-parametric proportional hazards mixture cure model for high-dimensional datasets. For both aims we will characterize the performance of the methods using extensive simulation studies, develop software, and distribute R packages to CRAN. In aim (3) we will identify molecular features associated with cure and survival using our large unique AML dataset from the Alliance for Clinical Trials in Oncology and assess robustness of ﬁndings using AML datasets from Gene Expression Omnibus and The Cancer Genome Atlas project. This research will ﬁll a critical gap as there are currently no mixture cure models for high-dimensional data. We anticipate application of our methods to our AML data will enhance existing risk stratiﬁcation systems used in daily clinical practice that determine treatment intensity and modality.

与事件发生时间结果相关的分子特征，例如总体生存率或无病生存率，可能是因此，分析来自高通量基因组的数据。癌症基因组图谱 (TCGA) 项目越来越引起人们的兴趣。收集了 32 个不同领域 11,125 名患者的基线人口统计学、临床特征和随访数据处理癌症类型和相应的组织样本以检查 SNP、拷贝数、甲基化、 miRNA 表达和 mRNA 表达由于变量数量 (P ) 超过样本大小 (N)，将分子特征与生存数据相关联时经常采用的一种策略是拟合单变量 Cox 比例风险 (PH) 模型，然后使用错误发现对多个假设检验进行调整然而，大多数慢性病和疾病，包括癌症，可能是由多种原因引起的。因此，在存在高风险的情况下拟合多变量模型至关重要。当特征数量超过维度协变量空间时，无法使用传统的统计方法。样本大小（例如，P > N），尽管惩罚方法执行自动变量选择并适应 P > N 场景，包括 LASSO、平滑剪切绝对偏差 (SCAD)、自适应LASSO和贝叶斯LASSO都已扩展到Cox的PH模型以处理高维然而，在对生存或其他事件发生时间结果进行建模时，Cox PH 模型假设所有受试者都会经历感兴趣的事件，当一部分受试者被治愈时，就会违反这一点。相反，当数据中的一部分受试者得到治愈时，应该拟合混合治愈模型。已针对样本数量超过数量的传统设置描述了治愈模型协变量的数量、有限的变量选择方法以及目前没有高维模型拟合的方法因此，该项目将克服该领域进展的关键障碍。通过开发适用于高维的惩罚参数和半参数混合治愈模型该应用程序的具体目标是：（1）开发惩罚参数混合固化模型。对于高维数据集；(2) 开发惩罚半参数比例风险混合疗法对于这两个目标，我们将使用这些方法来表征方法的性能。在目标 (3) 中，我们将确定广泛的模拟研究、开发软件并将 R 包分发给 CRAN。使用来自联盟的大型独特 AML 数据集与治愈和生存相关的分子特征使用 Gene Expression Omnibus 的 AML 数据集进行肿瘤学临床试验并评估研究结果的稳健性这项研究将填补目前尚无混合疗法的关键空白。我们预计将我们的方法应用于 AML 数据将增强现有的能力。日常临床实践中使用的风险分层系统，用于确定治疗强度和方式。