Sfaira accelerates data and model reuse in single cell genomics

single-cell
rna-seq
database
website
Authors

David S Fischer

Leander Dony

Martin König

Abdul Moeed

Luke Zappia

Lukas Heumos

Sophie Tritschler

Olle Holmberg

Hananeh Aliee

Fabian J Theis

Date

August 25, 2021

Links
Package Code DOI PDF Preprint Website
Citation stats
Abstract

Single-cell RNA-seq datasets are often first analyzed independently without harnessing model fits from previous studies, and are then contextualized with public data sets, requiring time-consuming data wrangling. We address these issues with sfaira, a single-cell data zoo for public data sets paired with a model zoo for executable pre-trained models. The data zoo is designed to facilitate contribution of data sets using ontologies for metadata. We propose an adaption of cross-entropy loss for cell type classification tailored to datasets annotated at different levels of coarseness. We demonstrate the utility of sfaira by training models across anatomic data partitions on 8 million cells.

Citation

BibTeX citation:
@article{fischer2021,
  author = {Fischer, David S and Dony, Leander and König, Martin and
    Moeed, Abdul and Zappia, Luke and Heumos, Lukas and Tritschler,
    Sophie and Holmberg, Olle and Aliee, Hananeh and Theis, Fabian J},
  title = {Sfaira Accelerates Data and Model Reuse in Single Cell
    Genomics},
  journal = {Genome biology},
  volume = {22},
  number = {1},
  pages = {248},
  date = {2021-08-25},
  url = {https://doi.org/10.1186/s13059-021-02452-6},
  doi = {10.1186/s13059-021-02452-6},
  issn = {1465-6906},
  langid = {en},
  abstract = {Single-cell RNA-seq datasets are often first analyzed
    independently without harnessing model fits from previous studies,
    and are then contextualized with public data sets, requiring
    time-consuming data wrangling. We address these issues with sfaira,
    a single-cell data zoo for public data sets paired with a model zoo
    for executable pre-trained models. The data zoo is designed to
    facilitate contribution of data sets using ontologies for metadata.
    We propose an adaption of cross-entropy loss for cell type
    classification tailored to datasets annotated at different levels of
    coarseness. We demonstrate the utility of sfaira by training models
    across anatomic data partitions on 8 million cells.}
}
For attribution, please cite this work as:
Fischer, D. S., Dony, L., König, M., Moeed, A., Zappia, L., Heumos, L., Tritschler, S., Holmberg, O., Aliee, H. & Theis, F. J. Sfaira accelerates data and model reuse in single cell genomics. Genome biology 22, 248 (2021).