Analyzing Single Cell RNA Sequencing with Topological Nonnegative Matrix Factorization

TL;DR

This paper introduces two novel topological regularized NMF methods, TNMF and rTNMF, for analyzing single-cell RNA sequencing data, demonstrating superior performance and improved visualization capabilities over existing NMF approaches.

Contribution

The paper proposes two new topological Laplacian regularized NMF methods, addressing multiscale analysis limitations in scRNA-seq data analysis.

Findings

TNMF and rTNMF outperform other NMF methods on 12 datasets.

The methods enhance visualization with UMAP and t-SNE.

Significant improvement in capturing data structure.

Abstract

Single-cell RNA sequencing (scRNA-seq) is a relatively new technology that has stimulated enormous interest in statistics, data science, and computational biology due to the high dimensionality, complexity, and large scale associated with scRNA-seq data. Nonnegative matrix factorization (NMF) offers a unique approach due to its meta-gene interpretation of resulting low-dimensional components. However, NMF approaches suffer from the lack of multiscale analysis. This work introduces two persistent Laplacian regularized NMF methods, namely, topological NMF (TNMF) and robust topological NMF (rTNMF). By employing a total of 12 datasets, we demonstrate that the proposed TNMF and rTNMF significantly outperform all other NMF-based methods. We have also utilized TNMF and rTNMF for the visualization of popular Uniform Manifold Approximation and Projection (UMAP) and t-distributed stochastic neighbor embedding (t-SNE).