Deep generative modeling for single-cell transcriptomics

Romain Lopez; Jeffrey Regier; Michael B. Cole; Michael I. Jordan; Nir Yosef

doi:10.1038/s41592-018-0229-2

Back

Deep generative modeling for single-cell transcriptomics

Journal article

an open version is available

Peer reviewed

Deep generative modeling for single-cell transcriptomics

Romain Lopez, Jeffrey Regier, Michael B. Cole, Michael I. Jordan and Nir Yosef

Nature methods, Vol.15(12), pp.1053-1058

01/Dec/2018

DOI: https://doi.org/10.1038/s41592-018-0229-2

PMCID: PMC6289068

PMID: 30504886

Files and links (1)

url

https://europepmc.org/article/PMC/6289068View

AcceptedFree to read and download, Open Access

Abstract

Single-cell transcriptome measurements can reveal unexplored biological diversity, but they suffer from technical noise and bias that must be modeled to account for the resulting uncertainty in downstream analyses. Here we introduce single-cell variational inference (scVI), a ready-to-use scalable framework for the probabilistic representation and analysis of gene expression in single cells(https:github.com/YosefLab/scVI). scVI uses stochastic optimization and deep neural networks to aggregate information across similar cells and genes and to approximate the distributions that underlie observed expression values, while accounting for batch effects and limited sensitivity. We used scVI for a range of fundamental analysis tasks including batch correction, visualization, clustering, and differential expression, and achieved high accuracy for each task.

Biochemical Research Methods

Biochemistry & Molecular Biology

Life Sciences & Biomedicine

Science & Technology

Details

Title: Deep generative modeling for single-cell transcriptomics
Creators: Romain Lopez - University of California, Berkeley
Jeffrey Regier - University of California, Berkeley
Michael B. Cole - University of California, Berkeley
Michael I. Jordan - University of California, Berkeley
Nir Yosef (Corresponding Author) - University of California, Berkeley
Resource Type: Journal article
Publication Details: Nature methods, Vol.15(12), pp.1053-1058; 01/Dec/2018
Number of pages: 9
Publisher: Springer Nature
Language: English
DOI: https://doi.org/10.1038/s41592-018-0229-2
PMID: 30504886
PMCID: PMC6289068
Grant note: N.Y. and R.L. were supported by NIH–NIAID (grant U19 AI090023). We thank A. Klein, S. Dudoit, and J. Listgarten for helpful discussions. Author contributions - R.L., J.R., and N.Y. conceived the statistical model. R.L. developed the software. R.L. and M.B.C. applied the software to real data analysis. R.L., J.R., N.Y., and M.I.J. wrote the manuscript. N.Y. and M.I.J. supervised the work.
Record Identifier: 993423582403596

Metrics

11 Record Views

See more details