Home

###What is scLVM?

scLVM is a modelling framework for single-cell RNA-seq data that can be used to dissect the observed heterogeneity into different sources, thereby allowing for the correction of confounding sources of variation. scLVM can be used to:

• Estimate latent sources of gene expression variation such as cell cycle or differentiation
• Decompose the observed variance into different sources
• Correct for confounding factors such as cell cycle and generate cell-cycle corrected gene expression
• Perform a correlation analysis explicitly accounting for confounding factors

scLVM builds on Gaussian process latent variable models and mixed linear models. Our modelling approach is based on efficient inference algorithms implemented in limix. For easy usage, we recommend our R package which combines easy-to-use routines for preprocessing as well as inference. In addition, we also provide a python package (see installation section for both packages).

scLVM was primarily designed to account for cell-cycle induced heterogeneities in single-cell RNA-seq data where cell cycle is the primary soure of variability. For other use cases tutorials will follow shortly.

###Links

• FAQ
• Contact
• Installation