Scrublet runs into an endless loop

[aditinarsale]

Hi,

I am really struggling to try and run scrublet on my h5 files from some 10X genomics data. I am a novice at any sort of coding and in all possibility this is because some very obvious mistake on my part and I would really appreciate any help.

I am running scrub let on python 3.10 and I am loading h5 files as the input files.
After loading the h5 file I get the following AnnData object:

AnnData object with n_obs × n_vars = 5542 × 36601
var: 'gene_ids', 'feature_types', 'genome'

So I assume the data is in the correct format with rows being # of cells and columns being # of genes.

But if run the scrub code on this object it runs into a loop. If I interrupt the code it give the following error. Is there a step I am missing between loading the .h5 file in python and getting scrublet to process it?

Thanks,
Aditi

---

KeyboardInterrupt Traceback (most recent call last)
Cell In[8], line 1
----> 1 scrub = scr.Scrublet(count_matrix, expected_doublet_rate=0.06)

File ~/anaconda3/envs/scRNA_Diabetes/lib/python3.10/site-packages/scrublet/scrublet.py:101, in Scrublet.init(self, counts_matrix, total_counts, sim_doublet_ratio, n_neighbors, expected_doublet_rate, stdev_doublet_rate, random_state)
7 ''' Initialize Scrublet object with counts matrix and doublet prediction parameters
8
9 Parameters
(...)
97 the doublet neighbors of transcriptome i).
98 '''
100 if not scipy.sparse.issparse(counts_matrix):
--> 101 counts_matrix = scipy.sparse.csc_matrix(counts_matrix)
102 elif not scipy.sparse.isspmatrix_csc(counts_matrix):
103 counts_matrix = counts_matrix.tocsc()

File ~/anaconda3/envs/scRNA_Diabetes/lib/python3.10/site-packages/scipy/sparse/_compressed.py:79, in _cs_matrix.init(self, arg1, shape, dtype, copy)
76 else:
77 # must be dense
78 try:
---> 79 arg1 = np.asarray(arg1)
80 except Exception as e:
81 raise ValueError("unrecognized {}_matrix constructor usage"
82 "".format(self.format)) from e

File ~/anaconda3/envs/scRNA_Diabetes/lib/python3.10/site-packages/anndata/_core/anndata.py:1171, in AnnData.getitem(self, index)
1169 """Returns a sliced view of the object."""
1170 oidx, vidx = self._normalize_indices(index)
-> 1171 return AnnData(self, oidx=oidx, vidx=vidx, asview=True)

File ~/anaconda3/envs/scRNA_Diabetes/lib/python3.10/site-packages/anndata/_core/anndata.py:360, in AnnData.init(self, X, obs, var, uns, obsm, varm, layers, raw, dtype, shape, filename, filemode, asview, obsp, varp, oidx, vidx)
358 if not isinstance(X, AnnData):
359 raise ValueError("X has to be an AnnData object.")
--> 360 self._init_as_view(X, oidx, vidx)
361 else:
362 self._init_as_actual(
363 X=X,
364 obs=obs,
(...)
376 filemode=filemode,
377 )

File ~/anaconda3/envs/scRNA_Diabetes/lib/python3.10/site-packages/anndata/_core/anndata.py:408, in AnnData._init_as_view(self, adata_ref, oidx, vidx)
406 # views on attributes of adata_ref
407 obs_sub = adata_ref.obs.iloc[oidx]
--> 408 var_sub = adata_ref.var.iloc[vidx]
409 self._obsm = adata_ref.obsm._view(self, (oidx,))
410 self._varm = adata_ref.varm._view(self, (vidx,))

File ~/anaconda3/envs/scRNA_Diabetes/lib/python3.10/site-packages/pandas/core/indexing.py:1153, in _LocationIndexer.getitem(self, key)
1150 axis = self.axis or 0
1152 maybe_callable = com.apply_if_callable(key, self.obj)
-> 1153 return self._getitem_axis(maybe_callable, axis=axis)

File ~/anaconda3/envs/scRNA_Diabetes/lib/python3.10/site-packages/pandas/core/indexing.py:1691, in _iLocIndexer._getitem_axis(self, key, axis)
1685 raise IndexError(
1686 "DataFrame indexer is not allowed for .iloc\n"
1687 "Consider using .loc for automatic alignment."
1688 )
1690 if isinstance(key, slice):
-> 1691 return self._get_slice_axis(key, axis=axis)
1693 if is_iterator(key):
1694 key = list(key)

File ~/anaconda3/envs/scRNA_Diabetes/lib/python3.10/site-packages/pandas/core/indexing.py:1727, in _iLocIndexer._get_slice_axis(self, slice_obj, axis)
1725 labels = obj._get_axis(axis)
1726 labels._validate_positional_slice(slice_obj)
-> 1727 return self.obj._slice(slice_obj, axis=axis)

File ~/anaconda3/envs/scRNA_Diabetes/lib/python3.10/site-packages/pandas/core/generic.py:4304, in NDFrame._slice(self, slobj, axis)
4302 assert isinstance(slobj, slice), type(slobj)
4303 axis = self._get_block_manager_axis(axis)
-> 4304 new_mgr = self._mgr.get_slice(slobj, axis=axis)
4305 result = self._constructor_from_mgr(new_mgr, axes=new_mgr.axes)
4306 result = result.finalize(self)

File internals.pyx:929, in pandas._libs.internals.BlockManager.get_slice()

File internals.pyx:913, in pandas._libs.internals.BlockManager._slice_mgr_rows()

File ~/anaconda3/envs/scRNA_Diabetes/lib/python3.10/site-packages/pandas/core/indexes/base.py:5391, in Index._getitem_slice(self, slobj)
5387 # NB: Using _constructor._simple_new would break if MultiIndex
5388 # didn't override getitem
5389 return self._constructor._simple_new(result, name=self._name)
-> 5391 def _getitem_slice(self, slobj: slice) -> Self:
5392 """
5393 Fastpath for getitem when we know we have a slice.
5394 """
5395 res = self._data[slobj]

KeyboardInterrupt: