Training feature classifiers

Hi,

I am going to train my classifier. Based on this I need two elements: the reference sequences and the corresponding taxonomic classifications. I downloaded the reference sequences (Greengenes 13_8 most recent) from here

1- I was wondering where can I obtain the corresponding taxonomic classification. Can I use the one provided here?

2- The file I downloaded (Greengenes 13_8 most recent), after decompressing it I notice that there are many files in it. Which one should I use? Or I guess I should import it as a compressed file for traning my classifier?

Sorry for my silly questions

Hi, @ptalebic :wave:

Applying the workflow documented in Feature classifier tutorial can be a bit confusing at first. Luckily, there are already some discussions here on the forum about these points of confusion! Searching the forum for terms like “Greengenes” and “taxonomic classification” etc. will yield some helpful results:

Here are a few links with discussion relevant to your specific questions to get you started:

Best of luck!
Andrew

3 Likes