moscot
moscot copied to clipboard
theislab
Multi-omic single-cell optimal transport tools
I got the following future warning: ```FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead if not (is_categorical_dtype(col) and is_numeric_dtype(col.cat.categories)):``` We should update...
We need to clean the logic in the `test_pass_arguments` tests in the quadratic applications. The way it is now is a bit messy.
At the moment, we cannot reproduce the multimodality tutorial, as the `cell_transition` doesn't work any more. A non-scalable work around is the following code ``` def aggregate_transport_matrix(adata_source, adata_target, tmat, aggregation_key...
batch_size has no influence on memory consumption
Hi there! For a simple `TemporalProblem`, I've held out some genes (from the embedding computation, simple PCA) and computed the coupling. I would now like to use the coupling to...
> @michalk8 I unjitted the `_apply` function for now, see [42601e2](https://github.com/theislab/moscot/commit/42601e2ee855dd74a7b90270c94fbcb26944bef7). How would you like to proceed with this? Second major thing is pulling/pushing which I reverted for the moment,...
@michalk8 I unjitted the `_apply` function for now, see https://github.com/theislab/moscot/pull/515/commits/42601e2ee855dd74a7b90270c94fbcb26944bef7. How would you like to proceed with this? _Originally posted by @MUCDK in https://github.com/theislab/moscot/issues/515#issuecomment-1623894101_
_Originally posted by @MUCDK in https://github.com/theislab/moscot/pull/515#discussion_r1238213294_
Hi, I am using TemporalProblem to compute couplings between different timepoints for my atlassing project. In particular, I am working with brain organoid data from multiple time points across >25...
- [x] passing custom cost matrices - [ ] `LineageProblem`: passing barcodes - [ ] `problem_stage` - [ ] `plot_cell_transition`