Lukas Heumos comments

Results 522 comments of


                                            Lukas Heumos

`regress_out` does not capture PerfectSeparation with statsmodels >= 0.14

Dear @jeskowagner, would you be willing to file a PR for this, please?

Catch PerfectSeparationWarning during regress_out

Thanks! I'll check it out soon.

Import error with anndata 0.10.9 on Python 3.9

I'll leave it to @gtca to answer the rest but in general, scverse follows https://scientific-python.org/specs/spec-0000/ where Python 3.9 is already EOL and even 3.10 is getting there. Numpy, Pandas, Scipy,...

Import error with anndata 0.10.9 on Python 3.9

@jflusche what are your anndata and mudata versions? Please ensure that they are the latest. Also upgrade scvi-tools

Import error with anndata 0.10.9 on Python 3.9

The latest mudata version is 0.3.1 https://pypi.org/project/mudata/ Please upgrade it.

Using `Pint` for units

This is also a use-case for ehrapy, where we're constantly dealing with various units for measurements

Support for Awkward Arrays in AnnData's X

@grst > Personally, I'd suggest you set adata.X = None and just put it in a layer. This'd mean that people that load in complex EHR data will have an...

Support for Awkward Arrays in AnnData's X

> > I want everything in layers but scverse is not there yet. > > and why repeat the old mistake for new packages Because it builds upon scanpy which...

Proposing to add mLLMCelltype as a best practice for cell type annotation

Dear @cafferychen777, thank you very much for getting this discussion started! Generally, I see value in LLM based annotation as a first automatic cell type annotation step that must be...

Proposing to add mLLMCelltype as a best practice for cell type annotation

I'll keep this open to remind me to add a few notes on LLM based curation in the chapter.