Inferring cellular and molecular processes in single-cell data with non-negative matrix factorization using Python, R, and GenePattern Notebook implementations of CoGAPS

All code and data needed to reproduce results of our workflow paper, "Inferring cellular and molecular processes in single-cell data with non-negative matrix factorization using Python, R, and GenePattern Notebook implementations of CoGAPS"

Can also be found in our CoGAPS and PyCoGAPS github repositories.

Abstract:

Non-negative matrix factorization (NMF) is an unsupervised learning method well suited to  high-throughput biology. Still, inferring biological processes requires additional post hoc statistics and annotation for interpretation of features learned from software packages developed for NMF implementation. Here, we aim to introduce a suite of computational tools that implement NMF and provide methods for accurate, clear biological interpretation and analysis. A generalized discussion of NMF covering its benefits, limitations, and open questions in the field is followed by three procedures for the Bayesian NMF algorithm CoGAPS (Coordinated Gene Activity across Pattern Subsets). Each procedure will demonstrate NMF analysis to quantify cell state transitions in public domain single-cell RNA-sequencing (scRNA-seq) data of 25,422 epithelial cells from pancreatic ductal adenocarcinoma (PDAC) tumors and control samples. The first demonstrates PyCoGAPS, our new Python implementation of CoGAPS that enhances runtime of Bayesian NMF for large datasets. The second procedure steps through the same single-cell NMF analysis using our R CoGAPS interface, and the third introduces a beginner-friendly CoGAPS platform using GenePattern Notebook. By providing Python support, cloud-based computing options, and relevant example workflows, we facilitate user-friendly interpretation and implementation of NMF for single-cell analyses.