A Caltech Library Service

Interpretable factor models of single-cell RNA-seq via variational autoencoders

Svensson, Valentine and Gayoso, Adam and Yosef, Nir and Pachter, Lior (2020) Interpretable factor models of single-cell RNA-seq via variational autoencoders. Bioinformatics, 36 (11). pp. 3418-3421. ISSN 1367-4803. PMCID PMC7267837. doi:10.1093/bioinformatics/btaa169.

[img] PDF - Published Version
Creative Commons Attribution.

[img] PDF - Submitted Version
See Usage Policy.

[img] Archive (ZIP) (Supplementary data) - Supplemental Material
Creative Commons Attribution.


Use this Persistent URL to link to this item:


Motivation: Single-cell RNA-seq makes possible the investigation of variability in gene expression among cells, and dependence of variation on cell type. Statistical inference methods for such analyses must be scalable, and ideally interpretable. Results: We present an approach based on a modification of a recently published highly scalable variational autoencoder framework that provides interpretability without sacrificing much accuracy. We demonstrate that our approach enables identification of gene programs in massive datasets. Our strategy, namely the learning of factor models with the auto-encoding variational Bayes framework, is not domain specific and may be useful for other applications. Availability and implementation: The factor model is available in the scVI package hosted at

Item Type:Article
Related URLs:
URLURL TypeDescription Paper CentralArticle ItemCode
Svensson, Valentine0000-0002-9217-2330
Gayoso, Adam0000-0001-9537-0845
Pachter, Lior0000-0002-9164-6231
Additional Information:© 2020 The Author(s). Published by Oxford University Press. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (, which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. Received: 13 September 2019; Revision received: 03 February 2020; Accepted: 20 February 2020; Published: 16 March 2020. We thank Eduardo da Veiga Beltrame and Romain Lopez for helpful feedback on the manuscript. Sina Booeshaghi provided useful comments on the LDVAE software. Additionally, we thank the users of scVI who provided helpful discussion about the implementation on Github. Funding: This work was supported by the National Institutes of Health [U19MH114830 to V.S. and L.P.]; and Error! Hyperlink reference not valid. [CZF2019-002454 to A.G. and N.Y.]. Conflict of Interest: none declared.
Funding AgencyGrant Number
Chan Zuckerberg FoundationCZF2019-002454
Issue or Number:11
PubMed Central ID:PMC7267837
Record Number:CaltechAUTHORS:20190816-135915873
Persistent URL:
Official Citation:Valentine Svensson, Adam Gayoso, Nir Yosef, Lior Pachter, Interpretable factor models of single-cell RNA-seq via variational autoencoders, Bioinformatics, 36(11): 3418-3421. June 2020; doi: 10.1093/bioinformatics/btaa169
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:97957
Deposited By: Tony Diaz
Deposited On:16 Aug 2019 21:03
Last Modified:15 Feb 2022 21:07

Repository Staff Only: item control page