arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.01780stat.MLcs.LG
收藏

图典型相关分析

Graph Canonical Correlation Analysis

Institute of Physics(物理研究所)

Hongju Park, Shuyang Bai, Zhenyao Ye, Hwiyoung Lee, Tianzhou Ma, Shuo Chen

AI总结:

本文提出图典型相关分析(gCCA),利用互相关矩阵的图结构计算典型相关,并给出高效算法与有限样本理论保证,在模拟和多组学数据中均优于传统CCA方法。

摘要:

典型相关分析(CCA)是一种广泛用于估计两组多维变量之间关联的技术。近年来CCA方法的进展已将其应用扩展到解析多组学数据集、影像-组学数据集等之间的相互作用。然而,传统CCA方法在将互相关矩阵中的结构化模式纳入模型方面能力有限,可能导致次优估计。为解决这一局限,我们提出图典型相关分析(gCCA)方法,该方法基于两组变量之间互相关矩阵的图结构来计算典型相关。我们为gCCA开发了计算高效的算法,并通过引入基于鞅理论的集中不等式和停时规则,提供了最优子集选择与典型相关估计的有限样本分析理论结果。大量模拟表明,gCCA优于竞争的CCA方法。此外,我们将gCCA应用于DNA甲基化和RNA-seq转录组学的多组学数据集,识别出由DNA甲基化通路正调控和负调控的基因表达通路。

英文摘要:

Canonical correlation analysis (CCA) is a widely used technique for estimating associations between two sets of multi-dimensional variables. Recent advancements in CCA methods have expanded their application to decipher the interactions of multiomics datasets, imaging-omics datasets, and more. However, conventional CCA methods are limited in their ability to incorporate structured patterns in the cross-correlation matrix, potentially leading to suboptimal estimations. To address this limitation, we propose the graph Canonical Correlation Analysis (gCCA) approach, which calculates canonical correlations based on the graph structure of the cross-correlation matrix between the two sets of variables. We develop computationally efficient algorithms for gCCA, and provide theoretical results for finite sample analysis of best subset selection and canonical correlation estimation by introducing concentration inequalities and stopping time rule based on martingale theories. Extensive simulations demonstrate that gCCA outperforms competing CCA methods. Additionally, we apply gCCA to a multiomics dataset of DNA methylation and RNA-seq transcriptomics, identifying both positively and negatively regulated gene expression pathways by DNA methylation pathways.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑