# Problem with training 18S classifier and assigning taxonomy
**URL:** https://forum.qiime2.org/t/problem-with-training-18s-classifier-and-assigning-taxonomy/6811
**Category:** User Support
**Tags:** pending-development
**Created:** [November 6, 2018, 12:52pm UTC](https://forum.qiime2.org/t/problem-with-training-18s-classifier-and-assigning-taxonomy/6811 "2018-11-06T12:52:54Z")
**Posts on this page:** 7
**Page:** 1
### Author:  [@bayegy](https://forum.qiime2.org/u/bayegy)
#### Post date: [November 6, 2018, 12:52pm UTC](https://forum.qiime2.org/t/problem-with-training-18s-classifier-and-assigning-taxonomy/6811/1 "2018-11-06T12:52:54Z")
Dear QIIME2 developers,
I am trying to use qiime feature-classifier to train a classifier for the use of 18S sequence.
here is the primer I used to extract the v4 target sequence:
_565F CCAGCASCYGCGGTAATTCC 948R ACTTTCGTTCTTGATYRA_
The confusing thing is that the length of sequences extracted by "qiime feature-classifier extract-reads" is far more than 948-565=383 (average 800 nt actually)
The even more confusing thing is that the taxonomy i got from "qiime feature-classifier classify-sklearn" is exactly all the same for all 330 features. Just for brief view:
_|Feature ID|Taxonomy|_
_|0b298f6d9f609ae27dff8397c6b5dfea|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|e49af68b1ed288f280740f1efd0f628a|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|4e798893271f5ecce40feed01c675957|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|42613dfbaf97fdcd05e4c7da6852390d|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|581e00979f3019eb8a88ea8f05be2110|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|9c0bddb2fa5aa59e7059faefdd81b161|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|c07c010e7f93e777d631ebf52b1c3809|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|d11b4aa67389d800c12dbfbb1abe8f62|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|f1d3bed5959ea9b11ec2a8ea15e4a0ac|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|1a254c4fdce63af73175a6caba4aae73|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|e3b005dbf7d747de71d29b8ebbcb5fdb|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|2de3cb6cd76a45c01ce5daf55122c28d|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|09e9fb7ab6765be1d52adb5b4bf37a94|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|160f27c869746e32d4924e18d2049c35|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|9fc64f6b75f145c4657e3b939231c7f9|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|1715e06abf6db633d7a01ab0122c31b4|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
_|90289e6e368fd01fbeee6d7562b32228|D\_0\_\_Eukaryota;D\_1\_\_Opisthokonta;D\_2\_\_Holozoa;D\_3\_\_Metazoa (Animalia);D\_8\_\_Arachnida;D\_9\_\_Opiliones;D\_10\_\_Karamea lobata australis|_
But if I use the full-length classifier, the taxonomy go back to normal, with different taxonomic names for every features.
here are the commands i used for training classifier:
\_qiime tools import --type 'FeatureData[Sequence]' --input-path SILVA\_132\_QIIME\_release/rep\_set/rep\_set\_18S\_only/99/silva\_132\_99\_18S.fna --output-path rep-set.qza&&\_
\_qiime tools import --type 'FeatureData[Taxonomy]' --input-format HeaderlessTSVTaxonomyFormat --input-path SILVA\_132\_QIIME\_release/taxonomy/18S\_only/99/consensus\_taxonomy\_7\_levels.txt --output-path ref-taxonomy.qza&&\_
\_qiime feature-classifier extract-reads --i-sequences rep-set.qza --p-f-primer CCAGCASCYGCGGTAATTCC --p-r-primer ACTTTCGTTCTTGATYRA --o-reads ref-seqs.qza&&\_
_qiime feature-classifier fit-classifier-naive-bayes --i-reference-reads ref-seqs.qza --i-reference-taxonomy ref-taxonomy.qza --o-classifier classifier.qza_
and here is the command i used for assign taxonomy:
_qiime feature-classifier classify-sklearn --p-n-jobs 16 --i-classifier classifier.qza --i-reads rep-seqs.qza --o-classification taxonomy.qza_
I am using the qiime2-2018.8 version of qiime2. I wonder if this is a common situation in qiime2, or if I was wrong about something. I would appreciate that if someone would like to help me figure this out.
Thanks
---
### Author:  [@Nicholas\_Bokulich](https://forum.qiime2.org/u/Nicholas_Bokulich)
#### Post date: [November 6, 2018, 1:09pm UTC](https://forum.qiime2.org/t/problem-with-training-18s-classifier-and-assigning-taxonomy/6811/2 "2018-11-06T13:09:52Z")
---
### Author:  [@Nicholas\_Bokulich](https://forum.qiime2.org/u/Nicholas_Bokulich)
#### Post date: [November 6, 2018, 1:26pm UTC](https://forum.qiime2.org/t/problem-with-training-18s-classifier-and-assigning-taxonomy/6811/3 "2018-11-06T13:26:35Z")
Hi @bayegy,
Thank you for reporting this! I know just what the problem is.
> [@bayegy](#):
>
> I wonder if this is a common situation in qiime2, or if I was wrong about something.
This is not a common situation and you did not do anything wrong. This is a known bug that occurs when you combine certain databases with certain primer sets, resulting in some extremely short sequences. See [this topic](https://forum.qiime2.org/t/wrong-taxonomy-qzv-file/5287) for a previous description and workaround.
The easiest thing to do would be to use the full-length 18S rRNA gene sequences, but another option is to remove the short sequences from the trimmed database (hint: `D_0 __Eukaryota;D_1__ Opisthokonta;D_2 __Holozoa;D_3__ Metazoa (Animalia);D_8 __Arachnida;D_9__ Opiliones;D_10__Karamea lobata australis` will be one of them! But there might be one or two others).
We have an [issue](https://github.com/qiime2/q2-feature-classifier/issues/110) to track this. This is on our radar to get fixed in the near future, so stay tuned for more details!
---
### Author:  [@Nicholas\_Bokulich](https://forum.qiime2.org/u/Nicholas_Bokulich)
#### Post date: [November 6, 2018, 1:26pm UTC](https://forum.qiime2.org/t/problem-with-training-18s-classifier-and-assigning-taxonomy/6811/4 "2018-11-06T13:26:37Z")
---
### Author:  [@bayegy](https://forum.qiime2.org/u/bayegy)
#### Post date: [November 7, 2018, 12:50pm UTC](https://forum.qiime2.org/t/problem-with-training-18s-classifier-and-assigning-taxonomy/6811/5 "2018-11-07T12:50:46Z")
Thanks for your quick and detailed reply, @Nicholas_Bokulich, looking forward to this bug being fixed.
---
### Author:  [@Nicholas\_Bokulich](https://forum.qiime2.org/u/Nicholas_Bokulich)
#### Post date: [November 7, 2018, 1:07pm UTC](https://forum.qiime2.org/t/problem-with-training-18s-classifier-and-assigning-taxonomy/6811/6 "2018-11-07T13:07:18Z")
It should be fixed in the next release of QIIME 2 (end of this week).
---
### Author:  [@system](https://forum.qiime2.org/u/system)
#### Post date: [December 8, 2018, 7:07pm UTC](https://forum.qiime2.org/t/problem-with-training-18s-classifier-and-assigning-taxonomy/6811/7 "2018-12-08T19:07:21Z")
This topic was automatically closed 31 days after the last reply. New replies are no longer allowed.