Linked matrix factorization

DOI10.1111/BIOM.13010zbMATH Open1436.62611OpenAlexW3104286051WikidataQ90269454 ScholiaQ90269454MaRDI QIDQ5214518FDOQ5214518

Authors Michael J. O'Connell, Eric F. Lock 

Publication date 7 February 2020

Published in Biometrics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1710.02931

zbMATH Keywords

dimension reductiondata integrationprincipal components analysismassive data setsmissing data imputation

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10) Statistical aspects of big data and data science (62R07) Missing data (62D10)

Abstract: In recent years, a number of methods have been developed for the dimension reduction and decomposition of multiple linked high-content data matrices. Typically these methods assume that just one dimension, rows or columns, is shared among the data sources. This shared dimension may represent common features that are measured for different sample sets (i.e., horizontal integration) or a common set of samples with measurements for different feature sets (i.e., vertical integration). In this article we introduce an approach for simultaneous horizontal and vertical integration, termed Linked Matrix Factorization (LMF), for the more general situation where some matrices share rows (e.g., features) and some share columns (e.g., samples). Our motivating application is a cytotoxicity study with accompanying genomic and molecular chemical attribute data. In this data set, the toxicity matrix (cell lines $imes$ chemicals) shares its sample set with a genotype matrix (cell lines $imes$ SNPs), and shares its feature set with a chemical molecular attribute matrix (chemicals $imes$ attributes). LMF gives a unified low-rank factorization of these three matrices, which allows for the decomposition of systematic variation that is shared among the three matrices and systematic variation that is specific to each matrix. This may be used for efficient dimension reduction, exploratory visualization, and the imputation of missing data even when entire rows or columns are missing from a constituent data matrix. We present theoretical results concerning the uniqueness, identifiability, and minimal parametrization of LMF, and evaluate it with extensive simulation studies.

Recommendations

• Integrative factorization of bidimensionally linked matrices
• scientific article; zbMATH DE number 5938998
• Link prediction via convex nonnegative matrix factorization on multiscale blocks
• Learning latent factors in linked multi-modality data

Cited In (7)

• Integrative factorization of bidimensionally linked matrices
• Bidimensional linked matrix factorization for pan-omics pan-cancer analysis
• Learning latent factors in linked multi-modality data
• Dimension-wise sparse low-rank approximation of a matrix with application to variable selection in high-dimensional integrative analyzes of association
• Data fusion using factor analysis and low-rank matrix completion
• Double-Matched Matrix Decomposition for Multi-View Data
• Bayesian joint modeling of chemical structure and dose response curves

This page was built for publication: Linked matrix factorization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5214518)