Causal graphical methods for high-dimensional heterogeneous biomedical data

高维异构生物医学数据的因果图方法

• 批准号: 10388447
• 负责人: Tyler Lovelace
• 金额: $ 4.68万
• 依托单位: UNIVERSITY OF PITTSBURGH AT PITTSBURGH
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-03-21 至 2025-03-20
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10388447
• 关键词: Address; Algorithms; Automobile Driving; Biological; Categories; Cells; Clinical; Complex; Data; Data Analytics; Data Set; Development; Dimensions; Event; Explosion; Generations; Genes; Graph; Heterogeneity; Immunologics; Individual; Intensive Care Units; Intervention; Investigation; Learning; Life; Malignant Neoplasms; Measures; Medical; Medicine; Methodology; Methods; Mining; Modeling; Mortality Determinants; Motivation; Outcome; Patients; Performance; Periodicity; Phenotype; Process; Property; RNA; Research; Research Personnel; Resolution; Skeleton; Structure; System; Testing; The Cancer Genome Atlas; Time; Validation; Ventilator; Work; analytical method; cancer care; causal model; cell type; clinically relevant; cohort; complex data; design; experimental study; flexibility; gene regulatory network; graph learning; high dimensionality; learning algorithm; learning strategy; machine learning method; malignant breast neoplasm; method development; mortality; multiple omics; novel; predictive modeling; prognostic model; single-cell RNA sequencing; tool; vector

In the past decade, there has been an explosion of data collected from biological and biomedical systems, both in terms of type and volume. Mining these high-dimensional, heterogeneous, and often dynamic datasets to make biologically or medically important inferences or develop predictive models requires new sophisticated data analytics methods. New machine learning methods have begun filling this gap, but most of these methods generate “black box” models that lack clear interpretability. Additionally, these methods are associative, and are thus incapable of teasing out the complex cause-effect relationships among features in the dataset. Directed causal graphical models (DCGMs) are a powerful tool for filling this gap. DCGMs, learned from observational datasets, can represent causal relationships between variables. This allows DCGMs to generate hypotheses of mechanisms and construct parsimonious, causally informed predictive models. However, biomedical datasets often have features that make it difficult to construct causal graphical models over the full dataset. Examples include: data type heterogeneity, high dimensionality, multicollinearity, cyclicity, and nonstationarity. To address these problems, I propose to develop methods for learning causal graphs in datasets containing (1) a heterogeneous mixture of continuous, categorical, and censored variables, (2) high dimensionality and multicollinearity, and (3) cyclicity and nonstationarity. In Aim 1, I will develop a new causal discovery algorithm that accommodates continuous, categorical and censored variables (e.g., survival). In Aim 2, I will test and compare various methods for matrix decomposition and dimensionality reduction in their ability to learn a meaningful low-dimensional latent feature space to be used in graph learning methods. In Aim 3, I will develop a new method for causal discovery in dynamic, possibly cyclic, gene regulatory networks at single cell resolution. In all cases, testing and validation will be performed on synthetic and real-life publicly available datasets. These methodological improvements constitute important steps forward in the field of causal discovery and they can be utilized together or independently to provide a flexible and powerful platform for analysis of a wide range of biomedical datasets. Once made available, they will enable researchers to make inferences about causal mechanisms, generate hypotheses, and build robust, parsimonious predictive models.

在过去的十年中，从生物和生物医学系统中收集的数据爆炸了 在类型和音量方面。将这些高维，异质和通常动态数据集挖掘到 制作生物学或医学上重要的信息或开发预测模型需要新的复杂 数据分析方法。新的机器学习方法已经开始填补这一空白，但是大多数方法 生成缺乏明显可解释性的“黑匣子”模型。此外，这些方法是关联的，并且是 因此，无法逗弄数据集中特征之间复杂的因果关系。指导 因果图形模型（DCGM）是填补此空白的强大工具。 DCGM，从观测中学到的 数据集，可以代表变量之间的因果关系。这允许DCGM生成 机制和构建了简约的，有时是知情的预测模型。但是，生物医学数据集 通常具有使得在完整数据集上构建因果图形模型变得困难的功能。例子 包括：数据类型异质性，高维度，多重共线性，周期性和非平稳性。解决 这些问题，我建议开发在包含（1）a的数据集中学习因果图的方法 连续，分类和公民变量的异质混合物，（2）高维和 多重共线性以及（3）环境和非平稳性。在AIM 1中，我将开发一种新的因果发现算法 这种住宿继续，分类和公民变量（例如生存）。在AIM 2中，我将测试和 比较矩阵分解和降低维度的各种方法的学习能力 有意义的低维度潜在特征空间可用于图形学习方法。在AIM 3中，我会发展 在单细胞分辨率下，动态，可能的循环，基因调节网络中因果发现的新方法。 在所有情况下，测试和验证都将对合成和现实生活的公开数据集执行。这些 方法论改进构成了因果发现领域的重要步骤，它们可以 一起使用或独立利用，以提供一个灵活而强大的平台，以分析广泛的范围 生物医学数据集。一旦提供，他们将使研究人员能够推断出有关CASUSAL 机制，产生假设并建立强大的，简约的预测模型。