Ok I understand the issue.
In the notebook you shared you can replace
adata.obsm["protein_expression"] = mdata["adt"].layers["counts"].A.copy()
with
adata.obsm["protein_expression"] = mdata["adt"].to_df("counts")
The issue arises due to the first line giving a numpy array, so our library generates integer based index for the protein names. This causes an issue with accessing a pandas series in your traceback.
We will push a fix soon. In the meantime, the recommended workflow is to use dataframes. Alternatively, you can use mudata throughout by following this tutorial:
Finally, it’s important to note that the differential expression function may give strange results due to cells with missing proteins. You can filter these cells and supply a custom adata to vae.differential_expression(new_adata)
Alternatively, advanced usage can alter the batchid1 and batchid2 arguments.