A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis
- PMID: 19377034
- PMCID: PMC2697346
- DOI: 10.1093/biostatistics/kxp008
A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis
Abstract
We present a penalized matrix decomposition (PMD), a new framework for computing a rank-K approximation for a matrix. We approximate the matrix X as circumflexX = sigma(k=1)(K) d(k)u(k)v(k)(T), where d(k), u(k), and v(k) minimize the squared Frobenius norm of X - circumflexX, subject to penalties on u(k) and v(k). This results in a regularized version of the singular value decomposition. Of particular interest is the use of L(1)-penalties on u(k) and v(k), which yields a decomposition of X using sparse vectors. We show that when the PMD is applied using an L(1)-penalty on v(k) but not on u(k), a method for sparse principal components results. In fact, this yields an efficient algorithm for the "SCoTLASS" proposal (Jolliffe and others 2003) for obtaining sparse principal components. This method is demonstrated on a publicly available gene expression data set. We also establish connections between the SCoTLASS method for sparse principal component analysis and the method of Zou and others (2006). In addition, we show that when the PMD is applied to a cross-products matrix, it results in a method for penalized canonical correlation analysis (CCA). We apply this penalized CCA method to simulated data and to a genomic data set consisting of gene expression and DNA copy number measurements on the same set of samples.
Figures
Similar articles
-
Sparse canonical correlation analysis from a predictive point of view.Biom J. 2015 Sep;57(5):834-51. doi: 10.1002/bimj.201400226. Epub 2015 Jul 6. Biom J. 2015. PMID: 26147637
-
Extensions of sparse canonical correlation analysis with applications to genomic data.Stat Appl Genet Mol Biol. 2009;8(1):Article28. doi: 10.2202/1544-6115.1470. Epub 2009 Jun 9. Stat Appl Genet Mol Biol. 2009. PMID: 19572827 Free PMC article. Review.
-
An iterative penalized least squares approach to sparse canonical correlation analysis.Biometrics. 2019 Sep;75(3):734-744. doi: 10.1111/biom.13043. Epub 2019 Apr 9. Biometrics. 2019. PMID: 30714093
-
Robust Principal Component Analysis Regularized by Truncated Nuclear Norm for Identifying Differentially Expressed Genes.IEEE Trans Nanobioscience. 2017 Sep;16(6):447-454. doi: 10.1109/TNB.2017.2723439. Epub 2017 Jul 4. IEEE Trans Nanobioscience. 2017. PMID: 28692983
-
Clutter suppression in ultrasound: performance evaluation and review of low-rank and sparse matrix decomposition methods.Biomed Eng Online. 2020 May 28;19(1):37. doi: 10.1186/s12938-020-00778-z. Biomed Eng Online. 2020. PMID: 32466753 Free PMC article. Review.
Cited by
-
Contrastive Functional Connectivity Defines Neurophysiology-informed Symptom Dimensions in Major Depression.bioRxiv [Preprint]. 2024 Oct 7:2024.10.04.616707. doi: 10.1101/2024.10.04.616707. bioRxiv. 2024. PMID: 39416217 Free PMC article. Preprint.
-
Transparency and precision in the age of AI: evaluation of explainability-enhanced recommendation systems.Front Artif Intell. 2024 Sep 5;7:1410790. doi: 10.3389/frai.2024.1410790. eCollection 2024. Front Artif Intell. 2024. PMID: 39301478 Free PMC article.
-
Protocol to infer and analyze miRNA sponge modules in heterogeneous data using miRSM 2.0.STAR Protoc. 2024 Sep 17;5(4):103317. doi: 10.1016/j.xpro.2024.103317. Online ahead of print. STAR Protoc. 2024. PMID: 39292559 Free PMC article.
-
Stable biomarker discovery in multi-omics data via canonical correlation analysis.PLoS One. 2024 Sep 9;19(9):e0309921. doi: 10.1371/journal.pone.0309921. eCollection 2024. PLoS One. 2024. PMID: 39250478 Free PMC article.
-
Limited generalizability of multivariate brain-based dimensions of child psychiatric symptoms.Commun Psychol. 2024 Feb 28;2(1):16. doi: 10.1038/s44271-024-00063-y. Commun Psychol. 2024. PMID: 39242757 Free PMC article.
References
-
- Boyd S, Vandenberghe L. Convex Optimization. New York: Cambridge University Press; 2004.
-
- Chin K, DeVries S, Fridlyand J, Spellman P, Roydasgupta R, Kuo W-L, Lapuk A, Neve R, Qian Z, Ryder T. Genomic and transcriptional aberrations linked to breast cancer pathophysiologies. Cancer Cell. 2006;10:529–541. and others. - PubMed
-
- Dudoit S, Fridlyand J, Speed T. Comparison of discrimination methods for the classification of tumors using gene expression data. Journal of the American Statistical Association. 2001;96:1151–1160.
-
- Eckart C, Young G. The approximation of one matrix by another of low rank. Psychometrika. 1936;1:211.
-
- Friedman J, Hastie T, Hoefling H, Tibshirani R. Pathwise coordinate optimization. Annals of Applied Statistics. 2007;1:302–332.
Publication types
MeSH terms
Substances
Grants and funding
LinkOut - more resources
Full Text Sources
Other Literature Sources