Abstract
Single-cell sequencing technology holds the promise of unravelling cell heterogeneities hidden in ubiquitous bulk-level analyses. However, limitations of current experimental methods also pose new obstacles that prevent accurate conclusions from being drawn. To overcome this, researchers have developed computational methods which aim at extracting the biological signal of interest from the noisy observations. In this paper we focus on probabilistic models designed for this task. Particularly, we describe how variational inference constitutes a powerful inference mechanism for different sample sizes, and critically review two recent scRNA-seq models which use it.
Supported by the EU Horizon 2020 research and innovation program (grant No. 633974 – SOUND project), and the Portuguese Foundation for Science & Technology (FCT), through UID/EMS/50022/2019 (IDMEC,LAETA), UID/EEA/50008/2019 (IT), UID/CEC/50021/2019 (INESC-ID), PTDC/EMS-SIS/0642/2014, PTDC/CCI-CIF/29877/2017, PTDC/EEI-SII/1937/2014, IF/00653/2012, and by internal IT projects QBigData and RAPID.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For brevity, here we do not consider the sparse loadings of the original model. In our experiments the resulting performance did not change significantly.
- 2.
\(\alpha _{k1,2}\), \(\beta _{k1,2}\) and \(\pi _p\) are fixed hyperparameters which can be estimated in an Expectation-Maximization scheme. See the original paper for details.
- 3.
In these simplified descriptions we ignore the batch annotation observations, for brevity.
- 4.
\(l_{\mu }\) and \(l_{\sigma }^2\) are the observed log-library size mean and variance, respectively.
References
Kolodziejczyk, A.A., Kim, J.K., Svensson, V., Marioni, J.C., Teichmann, S.A.: The technology and biology of single-cell RNA sequencing. Mol. Cell 58(4), 610–620 (2015)
Hicks, S.C., et al.: Missing data and technical variability in single-cell RNA-sequencing experiments. Biostatistics 19, 562–578 (2017)
Murphy, K.: Machine Learning: A Probabilistic Approach. MIT Press, Cambridge (2012)
Durif, G., Modolo, L., Mold, J.E., Lambert-Lacroix, S., Picard, F.: Probabilistic count matrix factorization for single cell expression data analysis. arXiv (2018)
Lopez, R., Regier, J., Cole, M.B., Jordan, M., Yosef, N.: Bayesian inference for a generative model of transcriptome profiles from single-cell RNA sequencing. bioRxiv (2018)
Pierson, E., Yau, C.: ZIFA: dimensionality reduction for zero-inflated single-cell gene expression analysis. Genome Biol. 16(1), 241 (2015)
Blei, D.M., Kucukelbir, A., McAuliffe, J.D.: Variational inference: a review for statisticians. J. Am. Stat. Assoc. 112(518), 859–877 (2017)
Kingma, D., Welling, M.: Stochastic gradient VB and the variational auto-encoder. In: Second International Conference on Learning Representations, ICLR (2014)
Pollen, A.A., et al.: Low-coverage single-cell mRNA sequencing reveals cellular heterogeneity and activated signaling pathways in developing cerebral cortex. Nat. Biotechnol. 32, 1053–1058 (2014)
Zeisel, A., et al.: Cell types in the mouse cortex and hippocampus revealed by single-cell RNA-seq. Science 347(6226), 1138–1142 (2015)
Acknowledgements
The authors thank Ghislain Durif for the helpful discussions about pCMF.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ferreira, P.F., Carvalho, A.M., Vinga, S. (2020). Variational Inference in Probabilistic Single-cell RNA-seq Models. In: Raposo, M., Ribeiro, P., Sério, S., Staiano, A., Ciaramella, A. (eds) Computational Intelligence Methods for Bioinformatics and Biostatistics. CIBB 2018. Lecture Notes in Computer Science(), vol 11925. Springer, Cham. https://doi.org/10.1007/978-3-030-34585-3_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-34585-3_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-34584-6
Online ISBN: 978-3-030-34585-3
eBook Packages: Computer ScienceComputer Science (R0)