I'm trying to train the SILVA 132 V4 reference database with the animal-distal-gut.qza as the class-weight within qiime feature-classifier fit-classifier-naive-bayes. The command provided on the readytowear GitHub page worked just fine generating the correct classifier artifact:
qiime feature-classifier fit-classifier-naive-bayes \
--i-reference-reads readytowear/data/gg_13_8/515f-806r/ref-seqs-v4.qza \
--i-reference-taxonomy readytowear/data/gg_13_8/515f-806r/ref-tax.qza \
--i-class-weight readytowear/data/gg_13_8/515f-806r/soil-non-saline.qza \
--o-classifier gg138_v4_soil-non-saline_classifier.qza
When I modify this to the SILVA 132 database and a different weight as below:
'''
qiime feature-classifier fit-classifier-naive-bayes \
--i-reference-reads readytowear/data/silva_132/515f-806r/ref-seqs.qza \
--i-reference-taxonomy readytowear/data/silva_132/515f-806r/ref-tax.qza \
--i-class-weight readytowear/data/silva_132/515f-806r/animal-distal-gut.qza \
--o-classifier silva132_v4_animal-distal-gut_classifier.qza
'''
It throws the following error:
'''
Plugin error from feature-classifier:
Number of priors must match number of classes.
'''
Anyone have any ideas how to resolve this?