Format

Send to

Choose Destination
Nat Commun. 2019 Jan 23;10(1):390. doi: 10.1038/s41467-018-07931-2.

Single-cell RNA-seq denoising using a deep count autoencoder.

Author information

1
Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany.
2
TUM School of Life Sciences Weihenstephan, Technische Universität München, Freising, Germany.
3
Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany. fabian.theis@helmholtz-muenchen.de.
4
TUM School of Life Sciences Weihenstephan, Technische Universität München, Freising, Germany. fabian.theis@helmholtz-muenchen.de.
5
Department of Mathematics, Technische Universität München, Garching, Germany. fabian.theis@helmholtz-muenchen.de.

Abstract

Single-cell RNA sequencing (scRNA-seq) has enabled researchers to study gene expression at a cellular resolution. However, noise due to amplification and dropout may obstruct analyses, so scalable denoising methods for increasingly large but sparse scRNA-seq data are needed. We propose a deep count autoencoder network (DCA) to denoise scRNA-seq datasets. DCA takes the count distribution, overdispersion and sparsity of the data into account using a negative binomial noise model with or without zero-inflation, and nonlinear gene-gene dependencies are captured. Our method scales linearly with the number of cells and can, therefore, be applied to datasets of millions of cells. We demonstrate that DCA denoising improves a diverse set of typical scRNA-seq data analyses using simulated and real datasets. DCA outperforms existing methods for data imputation in quality and speed, enhancing biological discovery.

PMID:
30674886
PMCID:
PMC6344535
DOI:
10.1038/s41467-018-07931-2
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center