Plug in error- qiime feature-classifier classify-sklearn


Iam just running new data but this the first time to experinse this error during the taxonomic analysis.
Plugin error from feature-classifier:

The scikit-learn version (0.19.1) used to generate this artifact does not match the current version of scikit-learn installed (0.20.2). Please retrain your classifier for your current deployment to prevent data-corruption errors.

Debug info has been saved to /var/folders/cg/l_hcc6js1zz035s7m04kwyxdjyd_1j/T/qiime2-q2cli-err-c5zkfw_e.log

I dont know how to deal with it. I just use the code in the tutorial.
qiime feature-classifier classify-sklearn
–i-classifier gg-13-8-99-515-806-nb-classifier.qza
–i-reads rep-seqs.qza
–o-classification taxonomy.qza

Could you please advice?
Thank you

Hey there @zeineldn!

This error means that you have an old version of the greengenes pre-trained classifier on hand. The fix is to download again from the 2019.1 docs:

Keep us posted! :qiime2:

Thank you Matthew,

You are right. but what is the case if I would like to work on ITS. I downloaded the UNITE database file in fasta format then convertwed it to .qza file using qiime import tool
qiime tools import --type ‘FeatureData[Sequence]’ -input-path UNITE_public_10.10.2017.fasta --output-path UNIT_2017_database.qza
I did that and got the same error.
What do you think?

Thank you again for your help !

Not sure, but:

  1. If you are using Qiime2 2019, you can use 2018 version and proceed with your classifier;
  2. Or you can train classifier yourself and use 2019 version for it.

Thank you for your help

This topic was automatically closed 31 days after the last reply. New replies are no longer allowed.