# Best Feature-Classifier?

**URL:** https://forum.qiime2.org/t/best-feature-classifier/4541
**Category:** User Support
**Tags:** taxonomy
**Created:** [June 12, 2018, 6:30pm UTC](https://forum.qiime2.org/t/best-feature-classifier/4541 "2018-06-12T18:30:37Z")
**Posts on this page:** 1
**Showing post:** 4

<div class="post-metadata">

### Author: ![Nicholas\_Bokulich](https://forum.qiime2.org/user_avatar/forum.qiime2.org/nicholas_bokulich/32/19937_2.png) [@Nicholas\_Bokulich](https://forum.qiime2.org/u/Nicholas_Bokulich)
#### Post date: [June 12, 2018, 6:47pm UTC](https://forum.qiime2.org/t/best-feature-classifier/4541/4 "2018-06-12T18:47:30Z")

</div>

> [@Kenneth](#):
>
> My question is which one of these methods is the best?

There is no "best" — but `classify-sklearn` in general performs better out of the box, and is our general recommendation for 16S and ITS sequences. All are very accurate at genus level, however, and reasonably accurate at species level (which is to say the defaults are optimized to NOT classify at species level if a confident hit cannot be determined).

See [this article](https://microbiomejournal.biomedcentral.com/articles/10.1186/s40168-018-0470-z) for a comparison of these and other classification methods, and some discussion of pros/cons and how to fiddle with the parameters. 🎻

> [@Kenneth](#):
>
> My objective is to minimize the number of unclassified features in my artifacts.

Check out that article — look at the "high-recall" classifiers listed in Table 2. Note that minimizing unclassified and underclassified sequences with a "high-recall" classifier means that you are essentially increasing the likelihood of getting false positive hits.

If you are getting unclassified sequences with any of these methods, chances are you are either not using a good reference database, or that sequence has no hits against the current database.

> [@Kenneth](#):
>
> I would like to start with the best classifier and if there are a lot features still unclassified I will perform a BLAST search on each one.

Good plan. BLASTing against the NCBI database can help determine if, e.g., you have non-target hits (e.g., host DNA) present in your reads.

> [@Kenneth](#):
>
> I tried to look on the forum before posting but couldn’t find any post that really answered this question.

Thanks 😄

> [@Kenneth](#):
>
> Thank you for your time and q2 is great.

😍

I hope that helps!

---

_[View the full topic](https://forum.qiime2.org/t/best-feature-classifier/4541)._