Unexpected taxonomic assignment results from two classifiers trained on nearly identical sequences

[SoilRotifer (Mike Robeson)]

Hi @mammerlin,

The following forum threads should address why you are observing this outcome:

Issue with Taxonomic Classification of 16S Sequences Using GreenGenes2: Need Help!

HI @Daniela_Vargas, Can you re-run your original feature-classifier classify-sklearn command with the --p-read-orientation same option? The default for this is --p-read-orientation auto. For sklearn to work properly the reads must be in the same orientation as the reference database / classifier. Sometimes bad sequences can trick the orientation detector to map the reads as the reverse compliment, thus returning poor taxonomic assignment. It also explains why using different taxonomic results …

Inconsistent Taxonomic Assignments Between Two Datasets - Error with Classifier?

Welcome to the forum, @ncoots! The naive Bayes classifier in q2-feature-classifier should not exhibit random behavior. The only time it exhibits inconsistencies like this is when reads (or reference sequences) are in mixed orientations. The classifier determines the orientation of reads (relative to the reference database) by polling the first 100 or so seqs. So feeding the classifier a different set of sequences (e.g., unmerged vs. merged datasets) could lead to variable results if the sequenc…

If you know that your reads are in the same orientation as the classifier, then I agree, it is best to simply set --p-read-orientation 'same'.

-Cheers!