Skip to content

A repository containing the work for the pre-print Adversarial learning enables unbiased organism-wide cross-species alignment of single-cell RNA data

Notifications You must be signed in to change notification settings

PhenomicAI/bascvi

Repository files navigation

BAscVI

This repo accompanies the paper "Adversarial learning enables unbiased organism-wide cross-species alignment of single-cell RNA data at scale"

https://www.biorxiv.org/content/10.1101/2024.08.11.607498v2.full

This repo contains three installable modules:

pai: An API for inference of cell-type embeddings and cell-types labels from scRNA datasets - supports H5AD formats downloadable from cellxcgene

pai_soma_data: A wrapper for TileDB needed for exploring the scREF atlas we provide here on the example notebooks we provide on TileDB in the public notebooks at Phenomic/Reading from scREF and scREF-mu

ml_benchmarking: Code needed to run and evaluate ML models on the scREF and scREF-mu banchmark

License

Everything is released under an MIT license, please feel free to use it, but please cite us as we have cited others.

About

A repository containing the work for the pre-print Adversarial learning enables unbiased organism-wide cross-species alignment of single-cell RNA data

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •