NMFClustering: Accessible NMF-based clustering utilizing GPU acceleration

• Published in: bioRxiv
• Main Authors: Liefeld, Ted, Huang, Edwin, Wenzel, Alexander T, Yoshimoto, Kenneth, Sharma, Ashwyn K, Sicklick, Jason K, Mesirov, Jill P, Reich, Michael
• Format: Journal Article Paper
• Language: English
• Published: United States Cold Spring Harbor Laboratory 27.06.2023
• Edition: 1.2
• Subjects: Bioinformatics
• ISSN: 2692-8205; 2692-8205
• DOI: 10.1101/2023.06.16.545370

Non-negative Matrix Factorization (NME) is an algorithm that can reduce high dimensional datasets of tens of thousands of genes to a handful of metagenes which are biologically easier to interpret. Application of NMF on gene expression data has been limited by its computationally intensive nature, which hinders its use on large datasets such as single-cell RNA sequencing (scRNA-seq) count matrices. We have implemented NMF based clustering to run on high performance GPU compute nodes using Cupy, a GPU backed python library, and the Message Passing Interface (MPI). This reduces the computation time by up to three orders of magnitude and makes the NMF Clustering analysis of large RNA-Seq and scRNA-seq datasets practical. We have made the method freely available through the GenePatten gateway, which provides free public access to hundreds of tools for the analysis and visualization of multiple 'omic data types. Its web-based interface gives easy access to these tools and allows the creation of multi-step analysis pipelnes on high performance computing (HPC) culsters that enable reproducible research for non-programmers.