Conversation
| - "fraction_heterotypic_overlap": pd.DataFrame | ||
| - "vertical_signal_integrity_per_cell": pd.DataFrame (only if vsi_map is not None) | ||
| """ | ||
| assert self.points_z_key is not None, ( |
There was a problem hiding this comment.
I would put this directly into vl.similarity_top_bottom to avoid asserts in the SegTraQ class
There was a problem hiding this comment.
need to still remove this
|
|
||
| > ⚠️ Note: SegTraQ is under active development. | ||
| > Features, interfaces, and functionality may change in upcoming releases. | ||
| > Features, interfaces, and functionality may change in upcoming releases. |
There was a problem hiding this comment.
Do you also want to add this to docs/index?
There was a problem hiding this comment.
I think it is enough to have it in the README for now.
|
|
||
|
|
||
| def test_neighbor_contamination_realdata_inplace_outputs(sdata_labeled, adata_ref): | ||
| markers = st.markers_from_reference(adata_ref.copy(), cell_type_key="celltype_major") |
There was a problem hiding this comment.
maybe we can change the default thresholds a bit such that we have enough cells for the tests?
|
While we're at it, we should have a better warning for if nucleus_boundaries aren't available in the constructor. |
|
Also: deprecated warning: This should not be |
|
We also have a ValueError in |
| - "fraction_heterotypic_overlap": pd.DataFrame | ||
| - "vertical_signal_integrity_per_cell": pd.DataFrame (only if vsi_map is not None) | ||
| """ | ||
| assert self.points_z_key is not None, ( |
There was a problem hiding this comment.
need to still remove this
3 participants
In the tests for the
supervisedmodule,markers_from_referenceresults in zero markers due to the small scRNA-seq subset. So tests are currently not doing anything. Once we have a larger scRNA-seq test dataset uploaded (that actually includes reference markers), we can uncommenttest_mutually_exclusive_coexpression_rate.py.