Error Training Classifier in V3-V4 SILVA

I’ve been trying to train this classifier using SILVA in the V3 V4 regions. I’m only using forward reads (whereas the original data included both forward and reverse paired end reads). I trimmed by data between 90-210 bps, therefore 120 length.

(qiime2-2018.2) helpdeskadmins-iMac-2:shoosein qiime2$ qiime feature-classifier extract-reads \

–i-sequences 80_otus.qza
–p-f-primer CCTAYGGGRBGCASCAG
–p-r-primer GGACTACNNGGGTATCTAAT
–p-trunc-len 120
–o-reads ref_seqs_120v2.qza
Saved FeatureData[Sequence] to: ref_seqs_120v2.qza
(qiime2-2018.2) helpdeskadmins-iMac-2:shoosein qiime2$ qiime feature-classifier fit-classifier-naive-bayes
–i-reference-reads ref_seqs_120v2.qza
–i-reference-taxonomy ref_taxonomy.qza
–o-classifier classifier120v2.qza
Saved TaxonomicClassifier to: classifier120v2.qza
(qiime2-2018.2) helpdeskadmins-iMac-2:shoosein qiime2$ qiime feature-classifier classify-sklearn
–i-classifier classifier120v2.qza
–i-reads rep-seqs-dada2.qza
–o-classification taxonomy120v2.qza
Plugin error from feature-classifier:

this classifier does not support confidence values

Debug info has been saved to /var/folders/jk/4cm8m3mj58x1zh027dvn94jw0000gr/T/qiime2-q2cli-err-nurntpca.log
(qiime2-2018.2) helpdeskadmins-iMac-2:shoosein qiime2$


I’ve tried two different primer sets for 341f/806r and keep getting this error. Any insight as to why I keep getting this error?

1 Like

Hi @Shabana_Louise,

Wild guess: using the 80 % OTUs could be related to this issue. What happens if you run the same command but use the 90% OTUs? Note that we recommend using 99% OTUs for classification of real data, 80% likely would not give very sensitive classifications even if it could be used to train a classifier.

If that does not work, could you please post the full error output, found in this file: /var/folders/jk/4cm8m3mj58x1zh027dvn94jw0000gr/T/qiime2-q2cli-err-nurntpca.log

Or re-run the command with the --verbose flag appended to the end of your command, and post the full error traceback.

Thanks!

Here is the error using --verbose:

(qiime2-2018.2) helpdeskadmins-iMac-2:shoosein qiime2$ qiime feature-classifier classify-sklearn \

–i-classifier classifier120v2.qza
–i-reads rep-seqs-dada2.qza
–o-classification taxonomy120v2.qza
–verbose
Plugin error from feature-classifier:

this classifier does not support confidence values

When running with Greengenes 99_otus_gg.qza, I got the following error:

(qiime2-2018.2) helpdeskadmins-iMac-2:shoosein qiime2$ qiime taxa barplot \

–i-table table-dada2.qza
–i-taxonomy ref_seqs_120_gg.qza
–m-metadata-file Metadata_Forward_Valid.tsv
–o-visualization taxa-bar-plots_gg.qzv
–verbose
Plugin error from taxa:

Argument to parameter ‘taxonomy’ is not a subtype of FeatureData[Taxonomy].

Hi @Shabana_Louise,

It looks like you got qiime feature-classifier classify-sklearn working with the 99% OTUs, possibly confirming my hunch from above.

Looks like you’ve moved onto a different command and a new problem. This one is even easier to fix.

You are not giving the barplot command a FeatureData[Taxonomy] artifact as input to the taxonomy parameter. It looks like you are using a sequence file. You need to use the output of classify-sklearn. E.g., the output named taxonomy120v2.qza in the first command example that you have.

I hope that helps!

Yes! It did. SILVA’s standard 80 just wasn’t working for me, but GG’s 99 did. And yes, I skipped a few steps. Ran the following code and it worked:

qiime feature-classifier fit-classifier-naive-bayes
–i-reference-reads ref_seqs_120_gg.qza
–i-reference-taxonomy ref_taxonomy_gg.qza
–o-classifier classifier_gg.qza

#############TEST##################
qiime feature-classifier classify-sklearn
–i-classifier classifier_gg.qza
–i-reads rep-seqs-dada2.qza
–o-classification taxonomy_gg.qza

qiime metadata tabulate
–m-input-file taxonomy_gg.qza
–o-visualization taxonomy_gg.qzv

###################################

qiime taxa barplot
–i-table table-dada2.qza
–i-taxonomy taxonomy_gg.qza
–m-metadata-file Metadata_Forward_Valid.tsv
–o-visualization taxa-bar-plots_gg.qzv

Thanks for your help! :grinning:

1 Like

Hi @Shabana_Louise,

Thanks very much for posting. I’m slightly concerned about the error that you saw originally (“this classifier does not support confidence values”). You shouldn’t have seen that error with those commands, so it means that there is probably a bug somewhere.

If it’s not too much trouble and you don’t mind sharing your data, would you mind please sharing the 80_otus.qza, ref_taxonomy.qza, and the rep-seqs-dada2.qza files that gave you that initial error with me? You could DM me if you don’t want to share them publicly.

Thanks again!

1 Like

@BenKaehler

Sure! I would just have to ask my advisor because its his data. And yes, I’ll DM it to you.

1 Like

Great! Thanks @Shabana_Louise.

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