Affordable Access

Access to the full text

A fast and efficient count-based matrix factorization method for detecting cell types from single-cell RNAseq data

Authors
  • Sun, Shiquan1, 2, 3, 4
  • Chen, Yabo1
  • Liu, Yang1
  • Shang, Xuequn1, 2
  • 1 School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, 710129, People’s Republic of China , Xi’an, Shaanxi (China)
  • 2 Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi’an, Shaanxi, 710129, People’s Republic of China , Xi’an, Shaanxi (China)
  • 3 Centre for Multidisciplinary Convergence Computing (CMCC), School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, 710129, People’s Republic of China , Xi’an, Shaanxi (China)
  • 4 Department of Biostatistics, University of Michigan, Ann Arbor, MI 48109, USA , Ann Arbor (United States)
Type
Published Article
Journal
BMC Systems Biology
Publisher
Springer (Biomed Central Ltd.)
Publication Date
Apr 05, 2019
Volume
13
Issue
Suppl 2
Identifiers
DOI: 10.1186/s12918-019-0699-6
Source
Springer Nature
Keywords
License
Green

Abstract

BackgroundSingle-cell RNA sequencing (scRNAseq) data always involves various unwanted variables, which would be able to mask the true signal to identify cell-types. More efficient way of dealing with this issue is to extract low dimension information from high dimensional gene expression data to represent cell-type structure. In the past two years, several powerful matrix factorization tools were developed for scRNAseq data, such as NMF, ZIFA, pCMF and ZINB-WaVE. But the existing approaches either are unable to directly model the raw count of scRNAseq data or are really time-consuming when handling a large number of cells (e.g. n>500).ResultsIn this paper, we developed a fast and efficient count-based matrix factorization method (single-cell negative binomial matrix factorization, scNBMF) based on the TensorFlow framework to infer the low dimensional structure of cell types. To make our method scalable, we conducted a series of experiments on three public scRNAseq data sets, brain, embryonic stem, and pancreatic islet. The experimental results show that scNBMF is more powerful to detect cell types and 10 - 100 folds faster than the scRNAseq bespoke tools.ConclusionsIn this paper, we proposed a fast and efficient count-based matrix factorization method, scNBMF, which is more powerful for detecting cell type purposes. A series of experiments were performed on three public scRNAseq data sets. The results show that scNBMF is a more powerful tool in large-scale scRNAseq data analysis. scNBMF was implemented in R and Python, and the source code are freely available at https://github.com/sqsun.

Report this publication

Statistics

Seen <100 times