Projection Pursuit with Applications to scRNA Sequencing Data
This work addresses dimension reduction challenges in bioinformatics, specifically for scRNA-seq data analysis, but appears incremental as it applies existing PP methods without introducing new techniques.
The paper investigates the limitations of PCA and explores projection pursuit (PP) as an alternative linear dimension reduction method, applying both PCA and PP with negative standardized Shannon's entropy to single-cell RNA sequencing data.
In this paper, we explore the limitations of PCA as a dimension reduction technique and study its extension, projection pursuit (PP), which is a broad class of linear dimension reduction methods. We first discuss the relevant concepts and theorems and then apply PCA and PP (with negative standardized Shannon's entropy as the projection index) on single cell RNA sequencing data.