error running popularvote - popv
0
0
Entering edit mode
5 weeks ago
maria2019 ▴ 220

I am trying to run the cell labeling using Popular vote at https://colab.research.google.com/drive/1Yw4ZDMoPgXNiC1ZQo2eS75Sw8Y_23rrb?usp=sharing#scrollTo=h41Q6U5wMwyP.

When running the part of the code:

from popv import process_query adata = process_query(query_adata,
                      ref_adata,
                      save_folder=save_folder,
                      query_batch_key=query_batch_key,
                      query_labels_key=query_labels_key,
                      unknown_celltype_label=unknown_celltype_label,
                      pretrained_scvi_path=None,
                      ref_labels_key=ref_labels_key, 
                      ref_batch_key=ref_batch_key,
                      n_samples_per_label=n_samples_per_label)

I get the following error:

Sampling 100 per label
--------------------------------------------------------------------------- KeyError                                  Traceback (most recent call last) <ipython-input-11-6957ee90eda5> in <module>
     10                       ref_labels_key=ref_labels_key,
     11                       ref_batch_key=ref_batch_key,
---> 12                       n_samples_per_label=n_samples_per_label)

4 frames /usr/local/lib/python3.7/dist-packages/popv/annotation.py in process_query(query_adata, ref_adata, save_folder, ref_labels_key, ref_batch_key, ref_cell_ontology_key, query_labels_key, query_batch_key, pretrained_scvi_path, unknown_celltype_label, training_mode, hvg, n_samples_per_label)
    153 
    154     if training_mode == "online":
--> 155         query_adata = query_adata[:, ref_adata.var_names].copy()
    156         adata = anndata.concat((ref_adata, query_adata))
    157     elif training_mode == "offline":

/usr/local/lib/python3.7/dist-packages/anndata/_core/anndata.py in
__getitem__(self, index)    1114     def __getitem__(self, index: Index) -> "AnnData":    1115         """Returns a sliced view of the object."""
-> 1116         oidx, vidx = sel

Blockquote

f._normalize_indices(index)    1117         return AnnData(self, oidx=oidx, vidx=vidx, asview=True)    1118 

/usr/local/lib/python3.7/dist-packages/anndata/_core/anndata.py in
_normalize_indices(self, index)    1095     1096     def _normalize_indices(self, index: Optional[Index]) -> Tuple[slice, slice]:
-> 1097         return _normalize_indices(index, self.obs_names, self.var_names)    1098     1099     # TODO: this is not quite complete...

/usr/local/lib/python3.7/dist-packages/anndata/_core/index.py in
_normalize_indices(index, names0, names1)
     34     ax0, ax1 = unpack_index(index)
     35     ax0 = _normalize_index(ax0, names0)
---> 36     ax1 = _normalize_index(ax1, names1)
     37     return ax0, ax1
     38 

/usr/local/lib/python3.7/dist-packages/anndata/_core/index.py in
_normalize_index(indexer, index)
    100                 not_found = indexer[positions < 0]
    101                 raise KeyError(
--> 102                     f"Values {list(not_found)}, from {list(indexer)}, "
    103                     "are not valid obs/ var names or indices."
    104                 )

KeyError: "Values ['MIR1302-2HG', 'OR4G4P', 'OR4G11P', 'AL627309.1', 'AL627309.3', 'CICP27', 'AL627309.6', 'AL627309.7', 'AL627309.2', 'AL627309.5', 'RNU6-1100P', 'AL627309.4', 'FO538757.1', 'WASH9P', 'AP006222.1', 'RPL23AP24', 'AL732372.1', 'AL732372.2', 'WBP1LP7', 'CICP7', 'AL732372.3', 'RF00026', 'AL669831.3', 'AC114498.1', 'MTND1P23', 'MTND2P28', 'MTCO1P12', 'AC114498.2', 'MTCO2P12', 'MTATP8P1', 'MTATP6P1', 'MTCO3P12', 'WBP1LP6', 'CICP3', 'AL669831.1', 'RNU6-1199P', 'AL669831.2', 'AL669831.5', 'AL669831.7', 'AL669831.4', 'TUBB8P11', 'AL669831.6', 'AL645608.6', 'AL645608.2', 'AL645608.4', 'LINC02593', 'AL645608.7', 'AL645608.3', 'AL645608.1', 'AL645608.5', 'AL390719.1', 'AL645608.8', 'C1orf159', 'AL390719.3', 'AL390719.2', 'TTLL10-AS1', 'C1QTNF12', 'AL162741.1', 'LINC01786', 'INTS11', 'AL139287.1', 'NDUFB4P8', 'MRPL20-AS1', 'RN7SL657P', 'AL391244.2', 'AL391244.1', 'LINC01770', 'AL645728.2', 'AL645728.1', 'AL691432.3', 'FNDC10', 'AL691432.2', 'FO704657.1', 'AL691432.1', 'AL031282.2', 'AL031282.1', 'SLC35E2A', 'AL109917.1', 'AL391845.2', 'AL391845.1', 'AL590822.2', 'PRKCZ-AS1', 'AL590822.1', 'AL589739.1', 'AL513477.1', 'AL513477.2', 'AL139246.1', 'AL139246.4', 'AL139246.5', 'TNFRSF14-AS1', 'AL139246.2', 'AL139246.3', 'PRXL2B', 'AL831784.1', 'AC242022.2', 'AC242022.1', 'AL592464.2', 'AL592464.1', 'AL589702.1', 'AL008733.1', 'AL512383.1', 'AL590438.1', 'AL512413.1', 'AL513320.1', 'AL136528.1', 'AL136528.2', 'RF02197', 'RN7SL574P', 'AL365330.1', 'C1orf174', 'LINC0..

Also, below is the content of the data:

ref_adata.var_names

Index(['DDX11L1', 'WASH7P', 'MIR6859-1', 'MIR1302-2HG', 'MIR1302-2', 'FAM138A', 'OR4G4P', 'OR4G11P', 'OR4F5', 'AL627309.1', ... 'MT-ND4', 'MT-TH', 'MT-TS2', 'MT-TL2', 'MT-ND5', 'MT-ND6', 'MT-TE', 'MT-CYB', 'MT-TT', 'MT-TP'], dtype='object', length=58870)

query_adata.var_names

Index(['DDX11L1', 'WASH7P', 'MIR6859-1', 'MIR1302-2', 'FAM138A', 'OR4F5', 'MIR6859-2', 'OR4F29', 'OR4F16', 'FAM87B', ... 'BPY2B', 'DAZ3', 'DAZ4', 'BPY2C', 'TTTY4C', 'TTTY17C', 'GOLGA2P3Y', 'CSPG4P1Y', 'CDY1', 'TTTY3'], dtype='object', length=23681)

Looks similar to the following issue: https://githubhot.com/repo/theislab/scanpy/issues/2095

TabulaSapiens popularVote popv celllabeling • 193 views
ADD COMMENT
0
Entering edit mode

I was able to run it successfully with training_mode="online" but the offline mode gives the above error

ADD REPLY

Login before adding your answer.

Traffic: 684 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6