University of Cambridge Cambridge quick links
Study at Cambridge About the University Research at Cambridge
Logo

MENU

Back to publications

Modelling Technical and Biological Effects in scRNA-seq Data with Scalable GPLVMs

Vidhi Lalchand, Aditya Ravuri, Emma Dann, Natsuhiko Kumasaka, Dinithi Sumanaweera, Rik G.H. Lindeboom, Shaista Madad, Sarah A. Teichmann, Neil D. Lawrence
, 2022.

Abstract

Single-cell RNA-seq datasets are growing in size and complexity, enabling the study of cellular composition changes in various biological/clinical contexts. Scalable dimensionality reduction techniques are in need to disentangle biological variation in them, while accounting for technical and biological confounders. In this work, we extend a popular approach for probabilistic non-linear dimensionality reduction, the Gaussian process latent variable model, to scale to massive single-cell datasets while explicitly accounting for technical and biological confounders. The key idea is to use an augmented kernel which preserves the factorisability of the lower bound allowing for fast stochastic variational inference. We demonstrate its ability to reconstruct latent signatures of innate immunity recovered in Kumasaka et al. (2021) with 9x lower training time. We further analyze a COVID dataset and demonstrate across a cohort of 130 individuals, that this framework enables data integration while capturing interpretable signatures of infection. Specifically, we explore COVID severity as a latent dimension to refine patient stratification and capture disease-specific gene expression.

Links

Home Page DOI Resource Locator arXiv version of this paper Edit this information on GitHub

Cite this Paper

BibTeX
@Misc{publications/modelling-technical-and-biological-effects-in-scrna-seq-data-with-scalable-gplvms, title = {Modelling Technical and Biological Effects in scRNA-seq Data with Scalable GPLVMs}, author = {Lalchand, Vidhi and Ravuri, Aditya and Dann, Emma and Kumasaka, Natsuhiko and Sumanaweera, Dinithi and Lindeboom, Rik G.H. and Madad, Shaista and Teichmann, Sarah A. and Lawrence, Neil D.}, year = {2022}, doi = {10.48550/arXiv.2209.06716}, url = {/publications/modelling-technical-and-biological-effects-in-scrna-seq-data-with-scalable-gplvms.html}, abstract = {Single-cell RNA-seq datasets are growing in size and complexity, enabling the study of cellular composition changes in various biological/clinical contexts. Scalable dimensionality reduction techniques are in need to disentangle biological variation in them, while accounting for technical and biological confounders. In this work, we extend a popular approach for probabilistic non-linear dimensionality reduction, the Gaussian process latent variable model, to scale to massive single-cell datasets while explicitly accounting for technical and biological confounders. The key idea is to use an augmented kernel which preserves the factorisability of the lower bound allowing for fast stochastic variational inference. We demonstrate its ability to reconstruct latent signatures of innate immunity recovered in Kumasaka et al. (2021) with 9x lower training time. We further analyze a COVID dataset and demonstrate across a cohort of 130 individuals, that this framework enables data integration while capturing interpretable signatures of infection. Specifically, we explore COVID severity as a latent dimension to refine patient stratification and capture disease-specific gene expression. } }
Endnote
%0 Generic %T Modelling Technical and Biological Effects in scRNA-seq Data with Scalable GPLVMs %A Vidhi Lalchand %A Aditya Ravuri %A Emma Dann %A Natsuhiko Kumasaka %A Dinithi Sumanaweera %A Rik G.H. Lindeboom %A Shaista Madad %A Sarah A. Teichmann %A Neil D. Lawrence %D 2022 %F publications/modelling-technical-and-biological-effects-in-scrna-seq-data-with-scalable-gplvms %R 10.48550/arXiv.2209.06716 %U /publications/modelling-technical-and-biological-effects-in-scrna-seq-data-with-scalable-gplvms.html %X Single-cell RNA-seq datasets are growing in size and complexity, enabling the study of cellular composition changes in various biological/clinical contexts. Scalable dimensionality reduction techniques are in need to disentangle biological variation in them, while accounting for technical and biological confounders. In this work, we extend a popular approach for probabilistic non-linear dimensionality reduction, the Gaussian process latent variable model, to scale to massive single-cell datasets while explicitly accounting for technical and biological confounders. The key idea is to use an augmented kernel which preserves the factorisability of the lower bound allowing for fast stochastic variational inference. We demonstrate its ability to reconstruct latent signatures of innate immunity recovered in Kumasaka et al. (2021) with 9x lower training time. We further analyze a COVID dataset and demonstrate across a cohort of 130 individuals, that this framework enables data integration while capturing interpretable signatures of infection. Specifically, we explore COVID severity as a latent dimension to refine patient stratification and capture disease-specific gene expression.
RIS
TY - GEN TI - Modelling Technical and Biological Effects in scRNA-seq Data with Scalable GPLVMs AU - Vidhi Lalchand AU - Aditya Ravuri AU - Emma Dann AU - Natsuhiko Kumasaka AU - Dinithi Sumanaweera AU - Rik G.H. Lindeboom AU - Shaista Madad AU - Sarah A. Teichmann AU - Neil D. Lawrence DA - 2022/09/14 ID - publications/modelling-technical-and-biological-effects-in-scrna-seq-data-with-scalable-gplvms DO - 10.48550/arXiv.2209.06716 UR - /publications/modelling-technical-and-biological-effects-in-scrna-seq-data-with-scalable-gplvms.html AB - Single-cell RNA-seq datasets are growing in size and complexity, enabling the study of cellular composition changes in various biological/clinical contexts. Scalable dimensionality reduction techniques are in need to disentangle biological variation in them, while accounting for technical and biological confounders. In this work, we extend a popular approach for probabilistic non-linear dimensionality reduction, the Gaussian process latent variable model, to scale to massive single-cell datasets while explicitly accounting for technical and biological confounders. The key idea is to use an augmented kernel which preserves the factorisability of the lower bound allowing for fast stochastic variational inference. We demonstrate its ability to reconstruct latent signatures of innate immunity recovered in Kumasaka et al. (2021) with 9x lower training time. We further analyze a COVID dataset and demonstrate across a cohort of 130 individuals, that this framework enables data integration while capturing interpretable signatures of infection. Specifically, we explore COVID severity as a latent dimension to refine patient stratification and capture disease-specific gene expression. ER -
APA
Lalchand, V., Ravuri, A., Dann, E., Kumasaka, N., Sumanaweera, D., Lindeboom, R.G., Madad, S., Teichmann, S.A. & Lawrence, N.D.. (2022). Modelling Technical and Biological Effects in scRNA-seq Data with Scalable GPLVMs. doi:10.48550/arXiv.2209.06716 Available from /publications/modelling-technical-and-biological-effects-in-scrna-seq-data-with-scalable-gplvms.html.