# pre-trained UNITE ITS classifiers for QIIME 2026.10 and scikit-learn=1.7.1
**URL:** https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140
**Category:** Data resources
**Tags:** taxonomy, feature-classifier, its, fungi, unite
**Created:** [March 9, 2025, 5:00am UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140 "2025-03-09T05:00:00Z")
**Posts on this page:** 18
**Page:** 1
### Author:  [@colinbrislawn](https://forum.qiime2.org/u/colinbrislawn)
#### Post date: [March 9, 2025, 5:00am UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/1 "2025-03-09T05:00:00Z")
UNITE version 10.0 was updated on 2025-02-19, and I've built classifiers for it compatible with the newest version of Qiime2:
> **[Releases ยท colinbrislawn/unite-train](https://github.com/colinbrislawn/unite-train/releases)**
>
> ๐ Qiime2 ITS classifiers for the UNITE database. Contribute to colinbrislawn/unite-train development by creating an account on GitHub.
### New in 2026
- Runs the `qiime2-workshop:2026.10` image or Pixi on OSX
- I've rewritten the pipeline in Nextflow, instead of Snakemake. ๐
- I now use RESCRIPt to get the data, edit the taxonomy, and collate reports! ๐
- I've added a simple reclassification step to measure best-case performance. ๐
- this shows how the singleton classifiers perform slightly worse ๐
- and using all Eukaryotes performs slightly better! ๐
Not what you are looking for? Please send me a [direct message](https://forum.qiime2.org/u/colinbrislawn) or [open an issue](https://github.com/colinbrislawn/unite-train/issues/new).
Colin ๐ ๐ฆ
---
### Author:  [@Zango](https://forum.qiime2.org/u/Zango)
#### Post date: [March 9, 2025, 2:10pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/2 "2025-03-09T14:10:29Z")
Thank you very much Sir
---
### Author:  [@Sam\_Degregori](https://forum.qiime2.org/u/Sam_Degregori)
#### Post date: [March 9, 2025, 2:10pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/3 "2025-03-09T14:10:29Z")
I see "all" eukaryotes? Does this mean CO1?
---
### Author:  [@colinbrislawn](https://forum.qiime2.org/u/colinbrislawn)
#### Post date: [March 9, 2025, 2:10pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/4 "2025-03-09T14:10:29Z")
Good question! I think UNITE is ITS only (so, no CO1 to my knowledge)
You can read more on their page: [UNITE - Resources](https://unite.ut.ee/repository.php)
---
### Author:  [@Taylor\_Akers](https://forum.qiime2.org/u/Taylor_Akers)
#### Post date: [March 9, 2025, 2:10pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/5 "2025-03-09T14:10:29Z")
Hello @colinbrislawn - I have a novice question about using this pre-trained classifier.
The qza files available in the GitHub link you posted, can these be used directly in the "test the classifier" portion of [this q2-feature-classifier tutorial](https://docs.qiime2.org/2022.8/tutorials/feature-classifier/)?
Ex:
qiime feature-classifier classify-sklearn
--i-classifier unite\_ver9\_dynamic\_25.07.2023-Q2-2023.9.qza
--i-reads rep-seqs.qza
--o-classification taxonomy.qza
---
### Author:  [@cherman2](https://forum.qiime2.org/u/cherman2)
#### Post date: [March 9, 2025, 2:10pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/6 "2025-03-09T14:10:29Z")
Hi @Taylor_Akers,
From what I understand, this should work!
---
### Author:  [@Taylor\_Akers](https://forum.qiime2.org/u/Taylor_Akers)
#### Post date: [March 9, 2025, 2:10pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/7 "2025-03-09T14:10:29Z")
Great, thank you @cherman2 ! It worked!
---
### Author:  [@cherman2](https://forum.qiime2.org/u/cherman2)
#### Post date: [March 9, 2025, 2:10pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/8 "2025-03-09T14:10:29Z")
An off-topic reply has been split into a new topic: [qiime2 does not recognize classifier as a .qza artifact](https://forum.qiime2.org/t/qiime2-does-not-recognize-classifier-as-a-qza-artifact/28799)
Please keep replies on-topic in the future.
---
### Author:  [@emmlemore](https://forum.qiime2.org/u/emmlemore)
#### Post date: [March 9, 2025, 2:10pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/9 "2025-03-09T14:10:29Z")
Hi @colinbrislawn thank you for creating this classifier!
I downloaded the latest version and tried it with my data. However, it runs for about 20 minutes before the job is killed. I am assuming this is due to insufficient RAM (I have 16GB)?
In that case, I should likely create my own classifier using RESCRIPt? Thank you.
---
### Author:  [@colinbrislawn](https://forum.qiime2.org/u/colinbrislawn)
#### Post date: [March 9, 2025, 2:10pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/10 "2025-03-09T14:10:29Z")
> [@emmlemore](#):
>
> I am assuming this is due to insufficient RAM (I have 16GB)?
>
> In that case, I should likely create my own classifier using RESCRIPt? Thank you.
Making a new classifier takes more memory then using an existing classifier. Using one of these pre-made ones still probably your best option with limited memory...
I would try using a smaller number of reads per batch, say
`--p-reads-per-batch 5000` or `1000`.
Also consider using a search-based classifier like
[`qiime feature-classifier classify-consensus-blast`](https://amplicon-docs.qiime2.org/en/latest/references/plugins/feature-classifier.html#q2-action-feature-classifier-classify-consensus-blast)
---
### Author:  [@Steven\_Criollo](https://forum.qiime2.org/u/Steven_Criollo)
#### Post date: [May 7, 2025, 9:15pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/12 "2025-05-07T21:15:04Z")
I have the same issueโafter updating QIIME2 to version 2025.4, the classifiers no longer work. When I try to use them, the execution gets interrupted. I donโt think itโs a RAM issue since I have 16GB, and I had no problems with the previous classifiers and QIIME2 version 2023.9. What could be the cause?
---
### Author:  [@gregcaporaso](https://forum.qiime2.org/u/gregcaporaso)
#### Post date: [May 7, 2025, 9:57pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/13 "2025-05-07T21:57:22Z")
Hi @Steven_Criollo, Are you using newly trained classifiers, or classifiers that were trained for QIIME 2 2023.9? The classifiers need to be updated every time we update to a new version of scikit-learn, and we did that in 2024.10, so pre-2024.10 classifiers won't work with 2025.4. @colinbrislawn has new ones trained which you can download from his git repository.
---
### Author:  [@Nicholas\_Bokulich](https://forum.qiime2.org/u/Nicholas_Bokulich)
#### Post date: [May 9, 2025, 4:39pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/17 "2025-05-09T16:39:47Z")
2 off-topic replies have been split into a new topic: [Can I use the UNITE database for LSU data?](https://forum.qiime2.org/t/can-i-use-the-unite-database-for-lsu-data/33116)
Please keep replies on-topic in the future.
---
### Author:  [@MBugay](https://forum.qiime2.org/u/MBugay)
#### Post date: [January 20, 2026, 4:16am UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/18 "2026-01-20T04:16:34Z")
I may have re-read this and confused myself, so this does mean that the pre-trained [UNITE v10.0 2025-02-18 for qiime2-2024.10](https://github.com/colinbrislawn/unite-train/releases/tag/v10.0-2025-02-19-qiime2-2024.10) would be compatible with qiime2 2025.4, 2025.7, or 2025.10 until UNITE releases another update or when a new version of scikit-learn is included in the updates? Thank you.
---
### Author:  [@colinbrislawn](https://forum.qiime2.org/u/colinbrislawn)
#### Post date: [January 20, 2026, 6:18am UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/19 "2026-01-20T06:18:59Z")
> [@MBugay](#):
>
> would be compatible [until] a new version of scikit-learn is included in the updates
Yes! I trained these with skl-1.4.2 so as long as the Qiime2 conda environment uses sci-kit learn version 1.4.2, these will work!
---
### Author:  [@MBugay](https://forum.qiime2.org/u/MBugay)
#### Post date: [January 20, 2026, 9:05pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/20 "2026-01-20T21:05:14Z")
Great! Thank you for clarifying. Based on the other replies, it did seem that they would be compatible, but I didn't want to assume.
Also, thanks for sharing the pre-trained classifiers. I do have a suggestion for the github. I think it would be great to include in the notes which versions of qiime2 are compatible with which classifiers in order to make it more obvious, especially for those who may get overwhelmed with all the new qiime2 version that get rolled out.
---
### Author:  [@kranderson](https://forum.qiime2.org/u/kranderson)
#### Post date: [August 29, 2026, 8:48pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/21 "2026-08-29T20:48:49Z")
Thank you for providing links for us to find the citation information for UNITE. But, how do we cite YOU for your generous work on the pre-trained classifiers?
---
### Author:  [@colinbrislawn](https://forum.qiime2.org/u/colinbrislawn)
#### Post date: [August 31, 2026, 6:59pm UTC](https://forum.qiime2.org/t/pre-trained-unite-its-classifiers-for-qiime-2026-10-and-scikit-learn-1-7-1/24140/22 "2026-08-31T18:59:19Z")
I'm just processing the Unite database so I'm not sure it warrants a citation.
**You should still site the upstream UNITE database version!**
My [code for this is under the BSD 3-clause license](https://github.com/colinbrislawn/unite-train/blob/main/LICENSE) which includes a section about where you CAN'T use my name! If you are not familiar with the BSD 2-clause and 3-clause versions, now is a great time to learn!