Exploratory Projection to Latent Structure Models for use in Transcriptomic Analysis

Abstract

In this paper, we ask if it is possible to increase the interpretability in multivariate analysis by aligning and projecting covariates onto comparative subspaces. We demonstrate our method as well as the interpretative power of PLS decomposed models and how robust interpretability can lead to quantitative insights. We discuss the statistical properties of the PLS weights, $p$-values associated with specific axes, as well as their alignment properties. The applicability of this approach within life science is also demonstrated by applying it to three use cases of publically available datasets. Further we present hierarchical pathway enrichment results stemming from aligned $p$-values, which are compared with results derived from enrichment analysis, as an external validation of our method. We find that the method can uncover known results from genomics for all of the studied use cases, i.e. microarray data from multiple sclerosis and diabetes patients as well as RNA sequencing data from breast cancer patients.