---
myst:
  html_meta:
    description: Convert CytePool cubes to and from AnnData and MuData, the pseudobulk layouts of scanpy, decoupler and LIANA, keeping every value, table and the provenance, with anndata and mudata as optional dependencies.
---

# AnnData and MuData

scverse keeps pseudobulk profiles in two layouts, and CytePool reads and writes both.
{func}`~cytepool.io.anndata.to_anndata` and {func}`~cytepool.io.anndata.from_anndata`
convert a cube to and from a long AnnData, with a row per sample and cell type, as
`scanpy.get.aggregate` and `decoupler.pp.pseudobulk` make it;
{func}`~cytepool.io.anndata.to_mudata` and {func}`~cytepool.io.anndata.from_mudata`
convert it to and from a MuData with a modality per cell type and the samples as its
rows, as LIANA's `adata_to_views` makes it. An import takes only sums and counts of
cells, so a cube made from aggregated profiles holds what one made from the cells
would hold, and a cube exported and read back has the same fingerprint. anndata and
mudata are optional: install CytePool's `anndata` or `mudata` extra.

```{eval-rst}
.. automodule:: cytepool.io.anndata
```