loading 'precise1k.json.gz'

[PaulVillain]

Hello,

I would like to compare my RNAseq data to Precise 1K, but I am struggling to load the 'precise1k.json.gz' using the jupyter notebook code.

When running this line in jupyter lab:
p1k = load_json_model(Path(DATA_PATH, 'precise1k.json.gz').as_posix())

I get this error:

ValueError Traceback (most recent call last)
Cell In[3], line 1
----> 1 p1k = load_json_model(Path(DATA_PATH, 'precise1k.json.gz').as_posix())
2 p1k_log_tpm_qc = pd.read_csv(Path(DATA_PATH, 'log_tpm_qc.csv'), index_col=0)

File ~/miniconda3/envs/Precise_bis-env/lib/python3.8/site-packages/pymodulon/io.py:124, in load_json_model(filename)
121 if arg in serial_data.keys():
122 serial_data.pop(arg)
--> 124 data = IcaData(**serial_data)
125 data._cutoff_optimized = cutoff_optimized
126 data._dagostino_cutoff = dagostino_cutoff

File ~/miniconda3/envs/Precise_bis-env/lib/python3.8/site-packages/pymodulon/core.py:108, in IcaData.init(self, M, A, X, log_tpm, gene_table, sample_table, imodulon_table, trn, dagostino_cutoff, optimize_cutoff, thresholds, threshold_method, motif_info, imodulondb_table, gene_links, tf_links)
106 # Convert column names of M to int if possible
107 try:
--> 108 M.columns = M.columns.astype(int)
109 except TypeError:
110 pass

File ~/miniconda3/envs/Precise_bis-env/lib/python3.8/site-packages/pandas/core/indexes/base.py:1027, in Index.astype(self, dtype, copy)
1023 new_values = cls._from_sequence(self, dtype=dtype, copy=copy)
1025 else:
1026 # GH#13149 specifically use astype_array instead of astype
-> 1027 new_values = astype_array(values, dtype=dtype, copy=copy)
1029 # pass copy=False because any copying will be done in the astype above
1030 result = Index(new_values, name=self.name, dtype=new_values.dtype, copy=False)

File ~/miniconda3/envs/Precise_bis-env/lib/python3.8/site-packages/pandas/core/dtypes/astype.py:187, in astype_array(values, dtype, copy)
184 values = values.astype(dtype, copy=copy)
186 else:
--> 187 values = _astype_nansafe(values, dtype, copy=copy)
189 # in pandas we don't store numpy str dtypes, so convert to object
190 if isinstance(dtype, np.dtype) and issubclass(values.dtype.type, str):

File ~/miniconda3/envs/Precise_bis-env/lib/python3.8/site-packages/pandas/core/dtypes/astype.py:138, in _astype_nansafe(arr, dtype, copy, skipna)
134 raise ValueError(msg)
136 if copy or is_object_dtype(arr.dtype) or is_object_dtype(dtype):
137 # Explicit copy, or required since NumPy can't view from / to object.
--> 138 return arr.astype(dtype, copy=True)
140 return arr.astype(dtype, copy=copy)

ValueError: invalid literal for int() with base 10: 'Sugar Diacid'

Could you please help me?