Thank you for developing the Cyanoseq database, which is very helpful for aquatic microbial research. I want to use Cyanoseq database on my 16S rRNA gene amplicon sequencing data. I downloaded CyanoSeq_1.2_SILVA138.1_QIIME2_classifier.qza and found it is a trained database. So, I run these codes in Qiime2:
qiime feature-classifier classify-sklearn \
--i-reads zotus.fa.qza \
--i-classifier CyanoSeq_1.2_SILVA138.1_QIIME2_classifier.qza \
--o-classification taxonomy.qza
But there is an error: Plugin error from feature-classifier: 0.
Here are messages in debug log file:
Traceback (most recent call last):
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/q2cli/commands.py", line 339, in call
results = action(**arguments)
File "", line 2, in classify_sklearn
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/qiime2/sdk/action.py", line 223, in bound_callable
callable_args[name] = artifact._view(
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/qiime2/sdk/result.py", line 373, in _view
result = transformation(self._archiver.data_dir)
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/qiime2/core/transform.py", line 70, in transformation
new_view = transformer(view)
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/q2_feature_classifier/_taxonomic_classifier.py", line 72, in _1
pipeline = joblib.load(os.path.join(dirname, 'sklearn_pipeline.pkl'))
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/joblib/numpy_pickle.py", line 587, in load
obj = _unpickle(fobj, filename, mmap_mode)
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/joblib/numpy_pickle.py", line 506, in _unpickle
obj = unpickler.load()
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/pickle.py", line 1212, in load
dispatchkey[0]
KeyError: 0
Qiime2 works well when using other reference database with the same data. So, I think there may be some problems with the file CyanoSeq_1.2_SILVA138.1_QIIME2_classifier.qza. Can you fix this?
Thank you very much for your reply and suggestions.
Thank you for developing the Cyanoseq database, which is very helpful for aquatic microbial research. I want to use Cyanoseq database on my 16S rRNA gene amplicon sequencing data. I downloaded CyanoSeq_1.2_SILVA138.1_QIIME2_classifier.qza and found it is a trained database. So, I run these codes in Qiime2:
qiime feature-classifier classify-sklearn \ --i-reads zotus.fa.qza \ --i-classifier CyanoSeq_1.2_SILVA138.1_QIIME2_classifier.qza \ --o-classification taxonomy.qza But there is an error: Plugin error from feature-classifier: 0.
Here are messages in debug log file:
Traceback (most recent call last): File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/q2cli/commands.py", line 339, in call results = action(**arguments) File "", line 2, in classify_sklearn
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/qiime2/sdk/action.py", line 223, in bound_callable
callable_args[name] = artifact._view(
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/qiime2/sdk/result.py", line 373, in _view
result = transformation(self._archiver.data_dir)
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/qiime2/core/transform.py", line 70, in transformation
new_view = transformer(view)
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/q2_feature_classifier/_taxonomic_classifier.py", line 72, in _1
pipeline = joblib.load(os.path.join(dirname, 'sklearn_pipeline.pkl'))
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/joblib/numpy_pickle.py", line 587, in load
obj = _unpickle(fobj, filename, mmap_mode)
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/site-packages/joblib/numpy_pickle.py", line 506, in _unpickle
obj = unpickler.load()
File "/share/soft/miniconda3/envs/qiime2202208/lib/python3.8/pickle.py", line 1212, in load
dispatchkey[0]
KeyError: 0
Qiime2 works well when using other reference database with the same data. So, I think there may be some problems with the file CyanoSeq_1.2_SILVA138.1_QIIME2_classifier.qza. Can you fix this?
Thank you very much for your reply and suggestions.