scVAE: variational auto-encoders for single-cell gene expression data

Research output: Contribution to journalJournal articlepeer-review

Standard

scVAE : variational auto-encoders for single-cell gene expression data. / Grønbech, Christopher Heje; Vording, Maximillian Fornitz; Timshel, Pascal; Sønderby, Casper Kaae; Pers, Tune H; Winther, Ole.

In: Bioinformatics, Vol. 36, No. 16, 2020, p. 4415-4422.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Grønbech, CH, Vording, MF, Timshel, P, Sønderby, CK, Pers, TH & Winther, O 2020, 'scVAE: variational auto-encoders for single-cell gene expression data', Bioinformatics, vol. 36, no. 16, pp. 4415-4422. https://doi.org/10.1093/bioinformatics/btaa293

APA

Grønbech, C. H., Vording, M. F., Timshel, P., Sønderby, C. K., Pers, T. H., & Winther, O. (2020). scVAE: variational auto-encoders for single-cell gene expression data. Bioinformatics, 36(16), 4415-4422. https://doi.org/10.1093/bioinformatics/btaa293

Vancouver

Grønbech CH, Vording MF, Timshel P, Sønderby CK, Pers TH, Winther O. scVAE: variational auto-encoders for single-cell gene expression data. Bioinformatics. 2020;36(16):4415-4422. https://doi.org/10.1093/bioinformatics/btaa293

Author

Grønbech, Christopher Heje ; Vording, Maximillian Fornitz ; Timshel, Pascal ; Sønderby, Casper Kaae ; Pers, Tune H ; Winther, Ole. / scVAE : variational auto-encoders for single-cell gene expression data. In: Bioinformatics. 2020 ; Vol. 36, No. 16. pp. 4415-4422.

Bibtex

@article{fd8f8ca128114e65a3876d973906ee09,
title = "scVAE: variational auto-encoders for single-cell gene expression data",
abstract = "MOTIVATION: Models for analysing and making relevant biological inferences from massive amounts of complex single-cell transcriptomic data typically require several individual data-processing steps, each with their own set of hyperparameter choices. With deep generative models one can work directly with count data, make likelihood-based model comparison, learn a latent representation of the cells and capture more of the variability in different cell populations.RESULTS: We propose a novel method based on variational auto-encoders (VAEs) for analysis of single-cell RNA sequencing (scRNA-seq) data. It avoids data preprocessing by using raw count data as input and can robustly estimate the expected gene expression levels and a latent representation for each cell. We tested several count likelihood functions and a variant of the VAE that has a priori clustering in the latent space. We show for several scRNA-seq data sets that our method outperforms recently proposed scRNA-seq methods in clustering cells and that the resulting clusters reflect cell types.AVAILABILITY AND IMPLEMENTATION: Our method, called scVAE, is implemented in Python using the TensorFlow machine-learning library, and it is freely available at https://github.com/scvae/scvae.SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.",
author = "Gr{\o}nbech, {Christopher Heje} and Vording, {Maximillian Fornitz} and Pascal Timshel and S{\o}nderby, {Casper Kaae} and Pers, {Tune H} and Ole Winther",
note = "{\textcopyright} The Author(s) (2020). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.",
year = "2020",
doi = "10.1093/bioinformatics/btaa293",
language = "English",
volume = "36",
pages = "4415--4422",
journal = "Computer Applications in the Biosciences",
issn = "1471-2105",
publisher = "Oxford University Press",
number = "16",

}

RIS

TY - JOUR

T1 - scVAE

T2 - variational auto-encoders for single-cell gene expression data

AU - Grønbech, Christopher Heje

AU - Vording, Maximillian Fornitz

AU - Timshel, Pascal

AU - Sønderby, Casper Kaae

AU - Pers, Tune H

AU - Winther, Ole

N1 - © The Author(s) (2020). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

PY - 2020

Y1 - 2020

N2 - MOTIVATION: Models for analysing and making relevant biological inferences from massive amounts of complex single-cell transcriptomic data typically require several individual data-processing steps, each with their own set of hyperparameter choices. With deep generative models one can work directly with count data, make likelihood-based model comparison, learn a latent representation of the cells and capture more of the variability in different cell populations.RESULTS: We propose a novel method based on variational auto-encoders (VAEs) for analysis of single-cell RNA sequencing (scRNA-seq) data. It avoids data preprocessing by using raw count data as input and can robustly estimate the expected gene expression levels and a latent representation for each cell. We tested several count likelihood functions and a variant of the VAE that has a priori clustering in the latent space. We show for several scRNA-seq data sets that our method outperforms recently proposed scRNA-seq methods in clustering cells and that the resulting clusters reflect cell types.AVAILABILITY AND IMPLEMENTATION: Our method, called scVAE, is implemented in Python using the TensorFlow machine-learning library, and it is freely available at https://github.com/scvae/scvae.SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

AB - MOTIVATION: Models for analysing and making relevant biological inferences from massive amounts of complex single-cell transcriptomic data typically require several individual data-processing steps, each with their own set of hyperparameter choices. With deep generative models one can work directly with count data, make likelihood-based model comparison, learn a latent representation of the cells and capture more of the variability in different cell populations.RESULTS: We propose a novel method based on variational auto-encoders (VAEs) for analysis of single-cell RNA sequencing (scRNA-seq) data. It avoids data preprocessing by using raw count data as input and can robustly estimate the expected gene expression levels and a latent representation for each cell. We tested several count likelihood functions and a variant of the VAE that has a priori clustering in the latent space. We show for several scRNA-seq data sets that our method outperforms recently proposed scRNA-seq methods in clustering cells and that the resulting clusters reflect cell types.AVAILABILITY AND IMPLEMENTATION: Our method, called scVAE, is implemented in Python using the TensorFlow machine-learning library, and it is freely available at https://github.com/scvae/scvae.SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

U2 - 10.1093/bioinformatics/btaa293

DO - 10.1093/bioinformatics/btaa293

M3 - Journal article

C2 - 32415966

VL - 36

SP - 4415

EP - 4422

JO - Computer Applications in the Biosciences

JF - Computer Applications in the Biosciences

SN - 1471-2105

IS - 16

ER -

ID: 241358708