I am having an issue trying to obtain get the sample-classifier heatmap output annotated with taxonomy intead of feature IDs.
I tried collapsing the feature table and using this collapsed table as input but it does not work.
The command I am running is this one:
qiime sample-classifier heatmap /
–i-table collapsed-table-species-level.qza /
–i-importance sample-classifier-prediction-results/feature_importance.qza / --m-metadata-file metadata-comb-rep1-rep2.tsv /
–m-metadata-column Diagnostic /
–p-feature-count 100 /
–o-heatmap heatmap.qzv /
And then the output is this:
Plugin error from sample-classifier:
Cannot group an empty table.
Debug info has been saved to /tmp/qiime2-q2cli-err-dzsqdsrz.log
Any ideas what might be going wrong?
you need to use the same feature table that you provided as input to
classify-samples. If you collapse your feature table, the feature IDs no longer match what is in the importances file.
Thnaks for your input. However, I wanted the heatmap to show the actual taxonomy IDs and not the feature IDs. I read somewhere else in the forum that I needed to collapse the feature table and then use that table with sample-classifier heatmap.
Is this correct?
That is a solution for
feature-classifier heatmap and perhaps what you read. For
sample-classifier heatmap see this solution:
Thanks for reminding me,
@LenaLapidot. This is something I’ve been meaning to do this release.
I just made the changes to allow this, but my gut feeling is it will not make it into the 2019.7 release (out at the end of this month). Keep an eye on the changelog that comes out with that release, and/or this pull request to keep track of this feature.
In the meantime, here is a convoluted workaround (no guarantees it will work “as is”!):
export your taxonomy classifications
concatenate your fea…