# over 70 % of reads are assigned as d\_\_Bacteria;\_\_;\_\_;\_\_;\_\_;\_\_;\_\_ qiime feature-classifier classify-sklearn

**URL:** https://forum.qiime2.org/t/over-70-of-reads-are-assigned-as-d-bacteria-qiime-feature-classifier-classify-sklearn/31035
**Category:** User Support
**Created:** [August 2, 2024, 5:59pm UTC](https://forum.qiime2.org/t/over-70-of-reads-are-assigned-as-d-bacteria-qiime-feature-classifier-classify-sklearn/31035 "2024-08-02T17:59:59Z")
**Posts on this page:** 1
**Showing post:** 2

<div class="post-metadata">

### Author: ![SoilRotifer](https://forum.qiime2.org/user_avatar/forum.qiime2.org/soilrotifer/32/21071_2.png) [@SoilRotifer](https://forum.qiime2.org/u/SoilRotifer)
#### Post date: [August 2, 2024, 9:03pm UTC](https://forum.qiime2.org/t/over-70-of-reads-are-assigned-as-d-bacteria-qiime-feature-classifier-classify-sklearn/31035/2 "2024-08-02T21:03:20Z")

</div>

Hi @jrhaulung,

Two things,

It could be that the premade curated database does not contain the V1V2 sequences, as they've been excluded during strict curation, due to being at the end of the sequence. Which means many reference sequences may have been removed. You can make your own database as outlined [here](https://forum.qiime2.org/t/using-silva-138-pre-trained-classifier/30857/5).

Otherwise I suspect a read orientation issue... if you [search the forum](https://forum.qiime2.org/search?q=unassigned%20reads%20orientation), you'll see many solutions to this problem. I'd suggest starting with [this approach](https://forum.qiime2.org/t/only-2-two-taxa-from-18s-taxa-barplot/30891/5).

---

_[View the full topic](https://forum.qiime2.org/t/over-70-of-reads-are-assigned-as-d-bacteria-qiime-feature-classifier-classify-sklearn/31035)._