Lukas Heumos

We could then also consider extending it with rapids single cell @Intron7 . More of a `scverse reproducibility` page and maybe also bring in scvi tools

I assume `cuml` is based on atomic operations which are non-deterministic. Just documenting the behavior would be good enough for now @Intron7 . I would suggest that this is something...

We decided not to add more packages to `external` but you are more than welcome to add your own package to the scverse ecosystem: https://scverse.org/packages/#ecosystem

I'd like to CC @AnnaChristina here who's also been working on this AFAIK.

@grst we're discussing this now and might get back with an update here

@Pedramto89 you need to provide more details, please.

Closing this as we'll do it with pertpy-datasets

I wonder whether you changed your Python versions inbetween or something? I'll close this for now.

TODO list - [x] Implement DIALOGUE 2 - [x] Add DIALOGUE 3 - [ ] Separate load and calculate_multifactor_PMD calculation -> have two separate function calls for these; load should...

> 716.87s call tests/tools/test_augur.py::test_differential_prioritization > 265.23s call tests/tools/_distances/test_distance_tests.py::test_distancetest[wasserstein] > 91.72s call tests/tools/test_mixscape.py::test_perturbation_signature > 88.49s call tests/metadata/test_cell_line.py::test_bulk_rna_expression_annotation > 48.50s call tests/tools/test_mixscape.py::test_lda > 46.60s call tests/tools/test_augur.py::test_random_forest_classifier > 44.65s setup tests/tools/_distances/test_distances.py::test_distance_axioms > 42.71s...