Does anyone trained the naive-bayes classifier based on Silva reference database (V3-V4 region) ? I ran taxonomy classification using full length pre-trained classifier from qiime2 resource page and it was killed due to memory error. I tried to train self-customized classifier as well, but the action was killed due to memory error as well. Thus, I would like to ask the good deed from qiime 2 users to provide the Silva-based classifier by which the reference reads were extracted by 341F & 805R degenerate primers.
Hi @Benedict,
That would be useful indeed, but in the meantime if you are unable to get the specific classifier you need, you can always use the full-length classifier available and play around with the parameters as suggested here. Basically leaving the --p-n-jobs to its default 1 and starting with smaller chunk size using --p-reads-per-batch INTEGER RANGE of say 1000. It’ll take longer but you may not run into the memory issue. Sorry in advance if you’ve already tried these and they haven’t worked.