Skip to content

dcjones/vanity

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Vanity

This is a straightforward "normalization" method for scRNA-Seq and similar data, based on Sanity

Breda, Jérémie, Mihaela Zavolan, and Erik van Nimwegen. "Bayesian inference of gene expression states from single-cell RNA-seq data." Nature Biotechnology 39.8 (2021): 1008-1016.

Vanity implements this model in jax using standard mean-field variational inference to dramatically speed up inference, particularly when running on a GPU, and it works nicely with the anndata/scanpy ecosystem. Overall the goal is a faster more convenient Sanity for my own use, and hopefully of some interest to others.

Vanity seems to largely agree with with Sanity, with a slight tendency to produce lower values. This hasn't been exhaustively tested yet, so proceed with some caution.

plot comparing estimates produced by sanity and vanity

Basic usage:

from vanity import normalize_vanity

normalize_vanity(adata) # where adata is an anndata.AnnData object

About

scRNA-Seq normalization for the vain

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages