Compressed spectral screening for large-scale differential correlation analysis with application in selecting glioblastoma gene modules
From MaRDI portal
Publication:6138655
DOI10.1214/23-AOAS1771arXiv2111.03721MaRDI QIDQ6138655FDOQ6138655
Tianxi Li, Xiwei Tang, Ajay Chatrath
Publication date: 16 January 2024
Published in: The Annals of Applied Statistics (Search for Journal in Brave)
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 -- 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.
Full work available at URL: https://arxiv.org/abs/2111.03721
spectral methodsgene coexpressionhigh-dimensional correlation matricesdifferential correlation analysis
Cites Work
- Inferring multiple graphical structures
- Stability Selection
- Spectral clustering and the high-dimensional stochastic blockmodel
- Bootstrap methods: another look at the jackknife
- Sparse inverse covariance estimation with the graphical lasso
- Two sample tests for high-dimensional covariance matrices
- Network cross-validation by edge sampling
- Matrix estimation by universal singular value thresholding
- Consistency of spectral clustering in stochastic block models
- Direct estimation of differential networks
- Two-Sample Covariance Matrix Testing and Support Recovery in High-Dimensional and Sparse Settings
- On Consistency and Sparsity for Principal Components Analysis in High Dimensions
- Testing differential networks with applications to the detection of gene-gene interactions
- Hierarchical Community Detection by Recursive Partitioning
- Exact matrix completion via convex optimization
- Joint estimation of multiple graphical models
- The Joint Graphical Lasso for Inverse Covariance Estimation Across Multiple Classes
- Adjusting batch effects in microarray expression data using empirical Bayes methods
- High dimensional inverse covariance matrix estimation via linear programming
- A Constrainedℓ1Minimization Approach to Sparse Precision Matrix Estimation
- High-Dimensional Sparse Factor Modeling: Applications in Gene Expression Genomics
- Estimation of high-dimensional graphical models using regularized score matching
- A test for the equality of covariance matrices when the dimension is large relative to the sample sizes
- Entrywise eigenvector analysis of random matrices with low expected rank
- Title not available (Why is that?)
- Title not available (Why is that?)
- Numerical Methods for Large Eigenvalue Problems
- Scale-Free Networks: A Decade and Beyond
- Detecting Differential Expressions in GeneChip Microarray Studies
- Joint estimation of precision matrices in heterogeneous populations
- Nonparametric Bayesian sparse factor models with application to gene expression modeling
- An adaptively weighted statistic for detecting differential gene expression when combining multiple transcriptomic studies
- A spectral algorithm for learning hidden Markov models
- BNP-Seq: Bayesian Nonparametric Differential Expression Analysis of Sequencing Count Data
- Finding large average submatrices in high dimensional data
- Model free estimation of graphical model using gene expression data
- Statistical-computational tradeoffs in planted problems and submatrix localization with a growing number of clusters and submatrices
- The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics
- Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization
- A spectral algorithm for latent Dirichlet allocation
- Cross-Validation With Confidence
- Comparing large covariance matrices under weak conditions on the dependence structure and its application to gene clustering
- Inference for high-dimensional differential correlation matrices
- Sparse latent factor models with interactions: analysis of gene expression data
- Testing high-dimensional covariance matrices, with application to detecting schizophrenia risk genes
- Exact and Efficient Generation of Geometric Random Variates and Random Graphs
- Sharp variable selection of a sparse submatrix in a high-dimensional noisy matrix
- Robust high-dimensional factor models with applications to statistical machine learning
- An $\ell_{\infty}$ Eigenvector Perturbation Bound and Its Application to Robust Covariance Estimation
- Computational and statistical boundaries for submatrix localization in a large noisy matrix
- Network differential connectivity analysis
- Differential network analysis via lasso penalized D-trace loss
- Removing technical variability in RNA-seq data using conditional quantile normalization
- Linear Regression and Its Inference on Noisy Network-Linked Data
This page was built for publication: Compressed spectral screening for large-scale differential correlation analysis with application in selecting glioblastoma gene modules
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6138655)
