Compressed spectral screening for large-scale differential correlation analysis with application in selecting Glioblastoma gene modules

Abstract

Differential co-expression analysis has been widely applied by scientists in understanding the biological mechanisms of diseases. However, the unknown differential patterns are often complicated; thus, models based on simplified parametric assumptions can be ineffective in identifying the differences. Meanwhile, the gene expression data involved in such analysis are in extremely high dimensions by nature, whose correlation matrices may not even be computable. Such a large scale seriously limits the application of most well-studied statistical methods. This paper introduces a simple yet powerful approach to the differential correlation analysis problem called compressed spectral screening. By leveraging spectral structures and random sampling techniques, our approach could achieve a highly accurate screening of features with complicated differential patterns while maintaining the scalability to analyze correlation matrices of $10^4$--$10^5$ variables within a few minutes on a standard personal computer. We have applied this screening approach in comparing a TCGA data set about Glioblastoma with normal subjects. Our analysis successfully identifies multiple functional modules of genes that exhibit different co-expression patterns. The findings reveal new insights about Glioblastoma's evolving mechanism. The validity of our approach is also justified by a theoretical analysis, showing that the compressed spectral analysis can achieve variable screening consistency.

References in corpus (13)

• Matrix estimation by Universal Singular Value Thresholding
• Two sample tests for high-dimensional covariance matrices
• Finding large average submatrices in high dimensional data
• A Spectral Algorithm for Latent Dirichlet Allocation
• Statistical-Computational Tradeoffs in Planted Problems and Submatrix Localization with a Growing Number of Clusters and Submatrices
• An adaptively weighted statistic for detecting differential gene expression when combining multiple transcriptomic studies
• Comparing large covariance matrices under weak conditions on the dependence structure and its application to gene clustering
• Entrywise Eigenvector Analysis of Random Matrices with Low Expected Rank
• Inference for High-dimensional Differential Correlation Matrices
• Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization
• Linear regression and its inference on noisy network-linked data
• Informative core identification in complex networks
• Community models for networks observed through edge nominations