an unexpected keyword argument 'summ_sc_data_args'

[renyuan1988]

I was trying to mapping multiple slides multiple slides using my own snRNA and Visium data, flowing the tutorials (https://cell2location.readthedocs.io/en/latest/notebooks/cell2location_short_demo.html).

When I use the code "r = cell2location.models.Cell2location"， it gave me an error: TypeError: LocationModelLinearDependentWMultiExperimentLocationBackgroundNormLevelGeneAlphaPyroModel.init() got an unexpected keyword argument 'summ_sc_data_args‘

Here are the code and outputs

sc.settings.set_figure_params(dpi = 100, color_map = 'viridis', dpi_save = 100,
                              vector_friendly = True, format = 'pdf',
                              facecolor='white')

r = cell2location.models.Cell2location(
      # Single cell reference signatures as pd.DataFrame
      # (could also be data as anndata object for estimating signatures
      #  as cluster average expression - `sc_data=adata_snrna_raw`)
      adata_vis,inf_aver,
      # Spatial data as anndata object

      # the column in sc_data.obs that gives cluster idenitity of each cell
      summ_sc_data_args={'cluster_col': "cell_type",
                        },

      train_args={'use_raw': True, # By default uses raw slots in both of the input datasets.
                  'n_iter': 40000, # Increase the number of iterations if needed (see QC below)

                  # Whe analysing the data that contains multiple experiments,
                  # cell2location automatically enters the mode which pools information across experiments
                  'sample_name_col': 'sample'}, # Column in sp_data.obs with experiment ID (see above)


      export_args={'path': results_folder, # path where to save results
                   'run_name_suffix': '' # optinal suffix to modify the name the run
                  },

      model_kwargs={ # Prior on the number of cells, cell types and co-located groups

                    'cell_number_prior': {
                        # - N - the expected number of cells per location:
                        'cells_per_spot': 8, # < - change this
                        # - A - the expected number of cell types per location (use default):
                        'factors_per_spot': 7,
                        # - Y - the expected number of co-located cell type groups per location (use default):
                        'combs_per_spot': 7
                    },

                     # Prior beliefs on the sensitivity of spatial technology:
                    'gene_level_prior':{
                        # Prior on the mean
                        'mean': 1/2,
                        # Prior on standard deviation,
                        # a good choice of this value should be at least 2 times lower that the mean
                        'sd': 1/4
                    }
      }
)

 
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[35], line 5
      1 sc.settings.set_figure_params(dpi = 100, color_map = 'viridis', dpi_save = 100,
      2                               vector_friendly = True, format = 'pdf',
      3                               facecolor='white')
----> 5 r = cell2location.models.Cell2location(
      6 
      7       # Single cell reference signatures as pd.DataFrame
      8       # (could also be data as anndata object for estimating signatures
      9       #  as cluster average expression - `sc_data=adata_snrna_raw`)
     10       adata_vis,inf_aver,
     11       # Spatial data as anndata object
     12 
     13       # the column in sc_data.obs that gives cluster idenitity of each cell
     14       summ_sc_data_args={'cluster_col': "cell_type",
     15                         },
     16 
     17       train_args={'use_raw': True, # By default uses raw slots in both of the input datasets.
     18                   'n_iter': 40000, # Increase the number of iterations if needed (see QC below)
     19 
     20                   # Whe analysing the data that contains multiple experiments,
     21                   # cell2location automatically enters the mode which pools information across experiments
     22                   'sample_name_col': 'sample'}, # Column in sp_data.obs with experiment ID (see above)
     23 
     24 
     25       export_args={'path': results_folder, # path where to save results
     26                    'run_name_suffix': '' # optinal suffix to modify the name the run
     27                   },
     28 
     29       model_kwargs={ # Prior on the number of cells, cell types and co-located groups
     30 
     31                     'cell_number_prior': {
     32                         # - N - the expected number of cells per location:
     33                         'cells_per_spot': 8, # < - change this
     34                         # - A - the expected number of cell types per location (use default):
     35                         'factors_per_spot': 7,
     36                         # - Y - the expected number of co-located cell type groups per location (use default):
     37                         'combs_per_spot': 7
     38                     },
     39 
     40                      # Prior beliefs on the sensitivity of spatial technology:
     41                     'gene_level_prior':{
     42                         # Prior on the mean
     43                         'mean': 1/2,
     44                         # Prior on standard deviation,
     45                         # a good choice of this value should be at least 2 times lower that the mean
     46                         'sd': 1/4
     47                     }
     48       }
     49 )

File ~/anaconda3/envs/cell2loc_env/lib/python3.10/site-packages/cell2location/models/_cell2location_model.py:115, in Cell2location.__init__(self, adata, cell_state_df, model_class, detection_mean_per_sample, detection_mean_correction, **model_kwargs)
    110         self.detection_alpha_ = pd.Series(detection_alpha)[batch_mapping]
    111         model_kwargs["detection_alpha"] = self.detection_alpha_.values.reshape(
    112             (self.summary_stats["n_batch"], 1)
    113         ).astype("float32")
--> 115 self.module = Cell2locationBaseModule(
    116     model=model_class,
    117     n_obs=self.summary_stats["n_cells"],
    118     n_vars=self.summary_stats["n_vars"],
    119     n_factors=self.n_factors_,
    120     n_batch=self.summary_stats["n_batch"],
    121     cell_state_mat=self.cell_state_df_.values.astype("float32"),
    122     **model_kwargs,
    123 )
    124 self._model_summary_string = f'cell2location model with the following params: \nn_factors: {self.n_factors_} \nn_batch: {self.summary_stats["n_batch"]} '
    125 self.init_params_ = self._get_init_params(locals())

File ~/anaconda3/envs/cell2loc_env/lib/python3.10/site-packages/cell2location/models/base/_pyro_base_loc_module.py:39, in Cell2locationBaseModule.__init__(self, model, amortised, encoder_mode, encoder_kwargs, data_transform, create_autoguide_kwargs, **kwargs)
     36 super().__init__()
     37 self.hist = []
---> 39 self._model = model(**kwargs)
     40 self._amortised = amortised
     41 if create_autoguide_kwargs is None:

TypeError: LocationModelLinearDependentWMultiExperimentLocationBackgroundNormLevelGeneAlphaPyroModel.__init__() got an unexpected keyword argument 'summ_sc_data_args'

[vitkl]

Please use latest tutorial for reference - it is mentioned in readme and is the only tutorial on the documentation website. The tutorial via the link you provided is from a very old 2020/2021 cell2location version.

[renyuan1988]

The latest tutorial ''https://cell2location.readthedocs.io/en/latest/notebooks/cell2location_tutorial.html'' was just where I found the link to the previous notebook. In the "Loading Visium and scRNA-seq reference data" section, the tutorial tells us "See this tutorial for a more extensive and practical example of data loading (multiple visium samples)." The link will directly lead you to the cell2location_short_demo tutorial.

I still have no clue on how to introduce the multi-sample mode, the "COMMON ERRORS" section says that "if you have multiple expreriments try analysing them jointly in the multi-sample mode (detected automatically based on 'sample_name_col': 'sample')." Could you tell me or give me an example on how to input the argument “'sample_name_col': 'sample'”?

Many thanks for your time!