Abstract
Motivation Statistical analyses of high-throughput sequencing data have re-shaped the biological sciences. In spite of myriad advances, recovering interpretable biological signal from data corrupted by technical noise remains a prevalent open problem. Several classes of procedures, among them classical dimensionality reduction techniques and others incorporating subject-matter knowledge, have provided effective advances; however, no procedure currently satisfies the dual objectives of recovering stable and relevant features simultaneously.
Results Inspired by recent proposals for making use of control data in the removal of unwanted variation, we propose a variant of principal component analysis, sparse contrastive principal component analysis, that extracts sparse, stable, interpretable, and relevant biological signal. The new methodology is compared to competing dimensionality reduction approaches through a simulation study as well as via analyses of several publicly available protein expression, microarray gene expression, and single-cell transcriptome sequencing datasets.
Availability A free and open-source software implementation of the methodology, the scPCA R package, is made available via the Bioconductor Project. Code for all analyses presented in the paper is also available via GitHub.
Footnotes
Portions of the methods section have been expanded upon in both the main text and the supplement, additional biological validation of the results have been performed, competing methods are discussed in greater detail, and an additional competing method's results are compared to that of the proposed method.
