Plugin error from feature-classifier (this classifier does not support confidence values)


I know that there are pre - trained classifiers for SILVA but I was attempting to run a 16S vs 18S only comparison. I downloaded the package from SILVA’s website and began training the classifier. They provided me rep - set FASTA files for 16S and 18S only along with taxonomy (consensus, majority and all taxonomy) files for 16S and 18S only. Once I assembled one, I attempted to apply it to my rep-seqs.qza but obtain this error:

this classifier does not support confidence values.


Traceback (most recent call last):
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/q2cli/”, line 328, in call
results = action(**arguments)
File “</home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/>”, line 2, in classify_sklearn
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/qiime2/sdk/”, line 240, in bound_callable
output_types, provenance)
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/qiime2/sdk/”, line 383, in callable_executor
output_views = self._callable(**view_args)
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/q2_feature_classifier/”, line 215, in classify_sklearn
reads, classifier, read_orientation=read_orientation)
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/q2_feature_classifier/”, line 170, in _autodetect_orientation
result = list(zip(*predict(first_n_reads, classifier, confidence=0.)))
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/q2_feature_classifier/”, line 45, in predict
for chunk in _chunks(reads, chunk_size)) for m in c)
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/joblib/”, line 1003, in call
if self.dispatch_one_batch(iterator):
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/joblib/”, line 834, in dispatch_one_batch
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/joblib/”, line 753, in _dispatch
job = self._backend.apply_async(batch, callback=cb)
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/joblib/”, line 201, in apply_async
result = ImmediateResult(func)
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/joblib/”, line 582, in init
self.results = batch()
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/joblib/”, line 256, in call
for func, args, kwargs in self.items]
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/joblib/”, line 256, in
for func, args, kwargs in self.items]
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/q2_feature_classifier/”, line 52, in _predict_chunk
return _predict_chunk_with_conf(pipeline, separator, confidence, chunk)
File “/home/sabasu/miniconda2/envs/qiime2-2019.10/lib/python3.6/site-packages/q2_feature_classifier/”, line 68, in _predict_chunk_with_conf
raise ValueError(‘this classifier does not support confidence values’)
ValueError: this classifier does not support confidence values

My commands:

qiime tools import
–type ‘FeatureData[Sequence]’
–input-path silva_132_99_16S.fna
–output-path silva-16s.qza

qiime tools import
–type ‘FeatureData[Taxonomy]’
–input-format HeaderlessTSVTaxonomyFormat
–input-path 16S_consensus_taxonomy_7_levels.txt
–output-path silva-16s-txt-taxonomy.qza

qiime feature-classifier extract-reads
–i-sequences silva-16s.qza
–o-reads silva-16s-ref-seqs.qza

qiime feature-classifier classify-sklearn
–i-classifier silva-16s-classifier.qza
–i-reads rep-seqs-dada2.qza
–o-classification 16s-taxonomy.qza

The last command ends in an error. Any help would be much appreciated.

1 Like

Hi @sabasu,
This error is usually caused by formatting issues, often if the taxonomies do not have even levels. Since you are combining 16S + 18S, I suspect that may be the case — e.g., the 16S is 7 levels but the 18S is not.

This topic has a bash command to figure out the number of ranks on each line of the taxonomy file:

Please take a look and let us know what you find.