patpy.datasets.combat

Contents

patpy.datasets.combat#

patpy.datasets.combat(kind='processed', overwrite=False, load_metadata=False, return_dataset_info=False)#

COvid-19 Multi-omics Blood ATlas (COMBAT) dataset.

The processed version was prepared with the standard scanpy pipeline; cells annotated as “nan” were removed; PCA, scVI, scANVI, and scPoli dimensionality reduction were applied. The dataset contains 783,677 cells and 3,000 features. The processed download is approximately 1.5 GB compressed and ~5 GB unzipped.

Parameters:

  • kind (Literal['raw', 'processed'] (default: 'processed')) – Either "processed" (default) or "raw". Currently only "processed" is available; "raw" raises NotImplementedError.

  • overwrite (bool (default: False)) – If True, re-download the dataset even when a cached copy exists.

  • load_metadata (bool (default: False)) – If True, also download the ~4 MB sample-metadata AnnData and return it as an extra element.

  • return_dataset_info (bool (default: False)) – If True, append a DatasetInfo describing the dataset’s standard schema (sample / cell-type keys, cell counts, etc.) to the return value.

Return type:

AnnData | tuple[AnnData, ...]

Returns:

By default the AnnData object alone. When load_metadata and/or return_dataset_info are set, a tuple is returned in this fixed order: (adata, meta_adata, info) (omitting any element that was not requested).

References

Ahern, D. J., Ai, Z., Ainsworth, M., Allan, C., Allcock, A., Angus, B., … & Salio, M. (2022). A blood atlas of COVID-19 defines hallmarks of disease severity and specificity. Cell, 185(5), 916-938. https://doi.org/10.1016/j.cell.2022.01.012. COvid-19 Multi-omics Blood ATlas (COMBAT) Consortium. (2021). A blood atlas of COVID-19 defines hallmarks of disease severity and specificity: Associated data (1.0.1) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.6120249

Examples

>>> import patpy
>>> adata = patpy.datasets.combat()
>>> adata, meta_adata = patpy.datasets.combat(load_metadata=True)
>>> adata, info = patpy.datasets.combat(return_dataset_info=True)
>>> adata, meta_adata, info = patpy.datasets.combat(load_metadata=True, return_dataset_info=True)
Contents