Interpretable factor models of single-cell RNA-seq via variational autoencoders
Open Access
- 1 June 2020
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 36 (11) , 3418-3421
Abstract
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. 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. The factor model is available in the scVI package hosted at https://github.com/YosefLab/scVI/. v@nxn.se Supplementary data are available at Bioinformatics online.Keywords
All Related Versions
Funding Information
- National Institutes of Health (U19MH114830, CZF2019-002454)
This publication has 30 references indexed in Scilit:
- Comparative Analysis of Gene Regulatory Networks: From Network Reconstruction to EvolutionAnnual Review of Cell and Developmental Biology, 2015
- ZIFA: Dimensionality reduction for zero-inflated single-cell gene expression analysisGenome Biology, 2015
- Geometry of the Gene Expression Space of Individual CellsPLOS Computational Biology, 2015
- Role of Oct4 in the early embryo developmentCell Regeneration, 2014
- Comparative studies of gene expression and the evolution of gene regulationNature Reviews Genetics, 2012
- Characterization of the single-cell transcriptional landscape by highly multiplex RNA-seqGenome Research, 2011
- Resolution of Cell Fate Decisions Revealed by Single-Cell Gene Expression Analysis from Zygote to BlastocystDevelopmental Cell, 2010
- Metagenes and molecular pattern discovery using matrix factorizationProceedings of the National Academy of Sciences, 2004
- A Gene-Coexpression Network for Global Discovery of Conserved Genetic ModulesScience, 2003
- Cripto-1 Activates Nodal- and ALK4-Dependent and -Independent Signaling Pathways in Mammary Epithelial CellsMolecular and Cellular Biology, 2002