Developing Machine Learning Models for the Analysis of Splicing Data in Large Heterogeneous Cohorts

开发机器学习模型来分析大型异构队列中的拼接数据

基本信息

批准号：
10506326
负责人：
David Wang
金额：
$ 4.68万
依托单位：
UNIVERSITY OF PENNSYLVANIA
依托单位国家：
美国
项目类别：
财政年份：
2021
资助国家：
美国
起止时间：
2021-08-01 至 2024-07-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10506326
关键词：
Acute Myelocytic Leukemia Address Affect Aftercare Algorithms Alternative Splicing B-Cell Acute Lymphoblastic Leukemia Bayesian Modeling Biological Blast Cell Cancer Patient Caring Catalogs Cells Characteristics Clinic Code Complex Computer software Computing Methodologies Data Data Set Detection Disease Event Excision Follow-Up Studies Gene Expression Genes Genetic Goals Hematologic Neoplasms Heterogeneity Individual Institution Letters Malignant Neoplasms Masks Measures Methods Minority Missense Mutation Modeling Modification Multiomic Data Mutation Patients Pharmaceutical Preparations Process Prognostic Marker Protocols documentation Quality Control RNA RNA Degradation RNA Splicing RNA analysis Relapse Reproducibility Resources Reverse Transcriptase Polymerase Chain Reaction Sampling Signal Transduction Source Statistical Models Structure Techniques The Cancer Genome Atlas Therapeutic Time Tissue Procurements Training Validation Variant Xenograft procedure acute care base biobank bioinformatics tool cell type clinically relevant cohort computerized tools data integration disease phenotype disorder subtype drug sensitivity experience heterogenous data improved leukemia leukemogenesis machine learning model multiple data sources multiple omics new therapeutic target non-Gaussian model novel patient subsets personalized medicine precision medicine prognostic tool response tool transcriptome sequencing transcriptomics translational impact unsupervised learning

项目摘要

Abstract Analysis of RNA sequencing (RNASeq) data obtained from large patient cohorts can reveal transcriptomic perturbations that are associated with complex disease and facilitate the identification of disease subtypes. This is typically framed as an unsupervised learning task to discover latent structure in a matrix of RNASeq based quantification of gene expression or local splicing variations (LSVs). However, several factors make analysis of such heterogeneous data challenging. First, such datasets are comprised of samples processed at multiple institutions which might employ different sequencing protocols and quality control steps. This introduces confounding factors into the data like inconsistent sample quality or variable cell type proportions which can hinder detection of true biological signal. Second, in acute myeloid leukemia (AML), mutations in splice factor genes occurring in a subset of the patients may only result in alteration of a subset of coregulated splicing events. Thus, instead of measuring global similarity between samples based on all transcriptomic features, there is a need to efficiently identify “tiles”, defined by a subset of samples and splicing events with abnormal signals. Although several algorithms have been proposed for this task, they fail to overcome many of the computational challenges associated with modeling splicing data and are not well suited to handle missing values. To facilitate analysis of heterogeneous splicing datasets by reducing false positive discoveries and boosting true biological signal, we will first develop a model to correct for the effects of RNA degradation and cell type mixtures. Then in order to efficiently identify AML subtypes characterized by splicing events and account for splicing specific modeling challenges, we propose CHESSBOARD (Characterizing Heterogeneity of Expression and Splicing by Search for Blocks of Abnormalities and Outliers in RNA Datasets), a non- parametric Bayesian model for unsupervised discovery of tiles. We will apply our models to synthetic datasets and show it outperforms several baseline approaches. Next, we will show that it recovers tiles characterized by known and novel splicing aberrations which are reproducible in multiple AML patient cohorts. Finally, we will show that tiles discovered are correlated with drug response to therapeutics, pointing to the translational impact of our findings.

抽象的对从大型患者队列中获得的 RNA 测序 (RNASeq) 数据进行分析可以揭示转录组学与复杂疾病相关并有助于疾病亚型识别的扰动。这通常被视为一项无监督学习任务，旨在发现 RNASeq 矩阵中的潜在结构然而，有几个因素会影响基因表达或局部剪接变异（LSV）的定量。首先，此类数据集由处理的样本组成。多个机构可能采用不同的测序方案和质量控制步骤。将混杂因素引入数据中，例如不一致的样本质量或可变的细胞类型比例其次，在急性髓系白血病 (AML) 中，突变会阻碍真正的生物信号的检测。发生在一部分患者中的剪接因子基因可能只会导致一部分共调节基因的改变因此，不是根据所有转录组来测量样本之间的全局相似性。功能，需要有效地识别“图块”，由样本子集和拼接事件定义尽管已经针对此任务提出了几种算法，但它们未能克服许多问题。与拼接数据建模相关的计算挑战，并且不太适合处理缺失价值观。通过减少误报发现和提升来促进异质剪接数据集的分析真正的生物信号，我们将首先开发一个模型来纠正 RNA 降解和细胞类型的影响然后为了有效地识别以剪接事件为特征的 AML 亚型并解释。拼接特定的建模挑战，我们提出了 CHESSBOARD（Characterizing Heterogeneity of 通过在 RNA 数据集中搜索异常块和异常值来进行表达和剪接），一种非用于无监督发现图块的参数贝叶斯模型我们将把我们的模型应用于合成数据集。并证明它优于几种基线方法接下来，我们将证明它可以恢复具有以下特征的图块。最后，我们将研究在多个 AML 患者群体中可重现的已知和新颖的剪接畸变。显示发现的瓷砖与药物对治疗的反应相关，指出转化我们的研究结果的影响。