# SILVA 138 Classifiers
**URL:** https://forum.qiime2.org/t/silva-138-classifiers/13131
**Category:** Data resources
**Created:** [January 9, 2020, 6:24pm UTC](https://forum.qiime2.org/t/silva-138-classifiers/13131 "2020-01-09T18:24:53Z")
**Posts on this page:** 8
**Page:** 3
### Author:  [@kbitenieks](https://forum.qiime2.org/u/kbitenieks)
#### Post date: [May 18, 2020, 2:13pm UTC](https://forum.qiime2.org/t/silva-138-classifiers/13131/43 "2020-05-18T14:13:58Z")
Hi Mike!
Thank you for sharing your pipeline and these classifiers! I also took full lenght sequences with species labels (ver0.02) and trained them for V4-V5 (515f and 926r) classifier.
> #Extract reference reads:
> --i-sequences SILVA-138-SSURef-Full-Seqs.qza
> --p-f-primer GTGYCAGCMGCCGCGGTAA
> --p-r-primer CCGYCAATTYMTTTRAGTTT
> --p-trunc-len 0
> --p-min-length 100
> --p-max-length 450
> --o-reads ref-seqs-v138-V4V5.qza
>
> #Train the classifier:
> qiime feature-classifier fit-classifier-naive-bayes
> --i-reference-reads ref-seqs.qza
> --i-reference-taxonomy Silva-v138-full-length-seq-taxonomy.qza
> --o-classifier SILVA-138-SSURef-V4V5-classifier.qza
A closer look at taxa barplots ([taxa-bar-plots\_16S-V4V5-35.qzv](https://forum.qiime2.org/uploads/short-url/1nmfPVHuKe2QnBqUV3jgkcNZiOC.qzv) (2.7 MB) ) shows that I have many weird named phyla in my samples (10bav-F6,LCP-89, AncK6, WPS-2, DTB120, FCPU426, MBNT15, NKB15, Sva0485, WS1, CK-2C2-2, RCP2-54, TA06, WS2, GN01, PAUC34f, NB1-j, SAR324\_clade(Marine\_group\_B), WS4 and others).
Have I done something wrong or it just needs some additional filtering? I will filter out chloroplast and mitochondria sequences.
Thanks!
Kriss
---
### Author:  [@SoilRotifer](https://forum.qiime2.org/u/SoilRotifer)
#### Post date: [May 18, 2020, 2:55pm UTC](https://forum.qiime2.org/t/silva-138-classifiers/13131/44 "2020-05-18T14:55:16Z")
You're welcome @kbitenieks!
The phyla names you see are normal. You can investigate this on the [SILVA Taxonomy browser](https://www.arb-silva.de/browser/). If you click on `Bacteria` you'll see all sorts of odd names. Many of these groups (at the phyla-level and lower) are still being defined and are considered to be at the candidate (i.e. _Candidatus_) status.
The field of bacterial taxonomy is undergoing many changes due to leveraging genomic data to aid in taxonomic identification. Many of these taxa have no culture-type specimen and are only defined by genome sequence (or other) data. This has caused quite a bit of debate in the field of bacterial taxonomy 🗣. Anyway, this has resulted in many [Candidate Phyla](https://en.wikipedia.org/wiki/Candidate_phyla_radiation), and other proposed groupings.
-Best wishes!
-Mike
---
### Author:  [@farhad1990](https://forum.qiime2.org/u/farhad1990)
#### Post date: [July 28, 2020, 2:23pm UTC](https://forum.qiime2.org/t/silva-138-classifiers/13131/45 "2020-07-28T14:23:52Z")
Hi Mike,
Thanks for uploading this classifier here, I am trying to make my own classifer but it seems very memory-intensive and not possible atm. In the meantime I tired to use your pre-trained classifier for 341F-805R primer set but I have an error which I couldn't solve based on the previous discussions in the forum. I would appreciate any help.
Here is the error:
_qiime feature-classifier classify-sklearn --i-classifier classifier-consensus.qza --i-reads repseqs.qza --o-classification taxonomy_
**Plugin error from feature-classifier:**
\*\* The scikit-learn version (0.21.2) used to generate this artifact does not match the current version of scikit-learn installed (0.23.1). Please retrain your classifier for your current deployment to prevent data-corruption errors.\*\*
**Debug info has been saved to /tmp/qiime2-q2cli-err-w3yust9p.log**
I am using qiime2.2020.6 and it seems that the version of the pluging I am using is higher than what had been used for training this classifier?
Bests,
Farhad
---
### Author:  [@SoilRotifer](https://forum.qiime2.org/u/SoilRotifer)
#### Post date: [July 28, 2020, 2:57pm UTC](https://forum.qiime2.org/t/silva-138-classifiers/13131/46 "2020-07-28T14:57:09Z")
Hi @farhad1990,
Sadly, if you would like to run the classifier in 2020.6, then you'll have to re-train them for that version of QIIME 2, as the sklearn version changes with each update. The best option in your case might be to make use of `qiime2-2020.2` for the classification step.
See this post for more details:
> [@update scikit-learn version](https://forum.qiime2.org/t/update-scikit-learn-version/15804/4):
>
> Hey @rparadiso! I will address this by answering some of the questions raised by @the_dummy & @devonorourke: Check this part of the error message to see which version the classifier was trained with: This is the right answer: if you're using an old version of QIIME 2 (which you might be, @rparadiso), then you just need to use the version of the pretrained classifier that was released with that version of QIIME 2. The easiest way to do that is to go to [docs.qiime2.org](http://docs.qiime2.org), and in the upper left…
Finally, check out initial post of this thread, it has been updated to redirect you to a new plugin. This should make it much easier for you to make a SILVA classifier.
-Best wishes
-Mike
---
### Author:  [@16sIceland](https://forum.qiime2.org/u/16sIceland)
#### Post date: [July 28, 2020, 7:31pm UTC](https://forum.qiime2.org/t/silva-138-classifiers/13131/47 "2020-07-28T19:31:46Z")
When training the classifier, should one use the Moving Pictures data, or their own data? And if their own, should it be a subset of their own data or the entire data set?
Thanks!
---
### Author:  [@SoilRotifer](https://forum.qiime2.org/u/SoilRotifer)
#### Post date: [July 28, 2020, 8:46pm UTC](https://forum.qiime2.org/t/silva-138-classifiers/13131/48 "2020-07-28T20:46:55Z")
Hi @16sIceland,
You train the classifiers with standard reference data, typically from a curated database, e.g. SILVA, or of your own making. For example, you can use the input files [here](https://docs.qiime2.org/2020.6/data-resources/#marker-gene-reference-databases) to construct your own classifier. For more details on how to do this, take a look at the RESCRIPt tutorial linked at the top of this thread.
Finally, you can simply make use of the [pre-made classifiers](https://docs.qiime2.org/2020.6/data-resources/#taxonomy-classifiers-for-use-with-q2-feature-classifier).
-Mike
---
### Author:  [@farhad1990](https://forum.qiime2.org/u/farhad1990)
#### Post date: [July 29, 2020, 11:37am UTC](https://forum.qiime2.org/t/silva-138-classifiers/13131/49 "2020-07-29T11:37:33Z")
Thanks Mike. It is working now 🙂
---
### Author:  [@SoilRotifer](https://forum.qiime2.org/u/SoilRotifer)
#### Post date: [July 29, 2020, 2:21pm UTC](https://forum.qiime2.org/t/silva-138-classifiers/13131/51 "2020-07-29T14:21:09Z")
[Previous page](https://forum.qiime2.org/t/silva-138-classifiers/13131.md?page=2)