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

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

展开

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.

抽象的从大型患者队列获得的RNA测序分析（RNASEQ）数据可以揭示转录组与复杂疾病相关并促进疾病亚型鉴定的扰动。这通常是在RNASEQ矩阵中发现潜在结构的无监督学习任务基于基因表达或局部剪接变异（LSV）的定量。但是，有几个因素使分析这种异质数据挑战。首先，此类数据集包括在处理的样本中多个机构可能会雇用不同的测序协议和质量控制步骤。这将混杂因素引入数据中，例如不一致的样本质量或可变单元格类型属性这可以阻止检测真正的生物学信号。第二，在急性髓样白血病（AML）中，突变剪接因子基因出现在一部分患者中，可能只会导致一部分的核心策略改变剪接事件。这不是基于所有转录组的样品之间的全局相似性功能，需要有效地识别“瓷砖”，这是由样本的子集和拼接事件定义的异常信号。尽管已经提出了几种算法，但他们未能克服许多与剪接数据建模相关的计算挑战，并且不适合处理丢失值。通过减少误报发现并提升，促进异质剪接数据集的分析真正的生物学信号，我们将首先开发一个模型，以校正RNA降解和细胞类型的影响混合物。然后，为了有效识别以拼接事件为特征的AML子类型并说明我们提出了针对特定建模的挑战，我们提出了棋盘（表征异质性的通过搜索RNA数据集中的异常和异常值的块来表达和剪接），一种非 - 无监督发现的参数贝叶斯模型。我们将把模型应用于合成数据集并显示出优于几种基线方法。接下来，我们将证明它恢复了以特征为特征的瓷砖已知且新颖的剪接畸变，可在多个AML患者队列中再现。最后，我们会的表明发现的瓷砖与药物对治疗的反应相关，指向翻译我们发现的影响。