How to use classify_samples to predict metadata category?

[CWills (Catie Williams)]

Hi,

I’ve tried the tutorial on classify_samples that says it predicts a categorical sample metadata category using a supervised learning classifier, however all this seems to do is test how good it is at classifying samples into metadata categories - I can’t find an option to take a sample that is genuinely “unknown” and use the classifier to predict it’s category.

Is this possible to do, and if so, how?

Thanks!

[Nicholas_Bokulich]

Hi @CWills,
Thanks for your question. In the current release it is not possible to save a classifier and re-use it to classify a sample that is “genuinely unknown” — this is planned for a future release, but there are security/format issues that we must resolve first.

If you are familiar with python, this is possible with QIIME2’s Artifact API interface. You would train a classifier and then feed in additional samples for classification.

Do you have a specific application in mind? You are welcome to submit a new feature request, though an issue already exists for saving classifiers.

Hope that helps!

[CWills (Catie Williams)]

Thanks for your help - what you describe Artifact API interface as being able to do is exactly what I’m interested in trying out, so that’s perfect, I’ll have a play around with this!