# I am seeing a cluster in the query that is not alligning with ref (SEA-AD snRNAseq MTG)

**URL:** <https://community.brain-map.org/t/i-am-seeing-a-cluster-in-the-query-that-is-not-alligning-with-ref-sea-ad-snrnaseq-mtg/4781>\
**Category:** Science\
**Tags:** celltype, atlas-reference-maps\
**Created:** [November 25, 2025, 4:06pm UTC](https://community.brain-map.org/t/i-am-seeing-a-cluster-in-the-query-that-is-not-alligning-with-ref-sea-ad-snrnaseq-mtg/4781 "2025-11-25T16:06:43Z")\
**Posts on this page:** 1\
**Showing post:** 5

<div class="post-metadata">

**Author:** ![ashaypatel](https://yyz1.discourse-cdn.com/flex027/user_avatar/community.brain-map.org/ashaypatel/32/1785_2.png) [@ashaypatel](https://community.brain-map.org/u/ashaypatel)\
**Post date:** [November 25, 2025, 6:39pm UTC](https://community.brain-map.org/t/i-am-seeing-a-cluster-in-the-query-that-is-not-alligning-with-ref-sea-ad-snrnaseq-mtg/4781/5 "2025-11-25T18:39:23Z")

</div>

Here are the plots. I was wondering if I should at pct\_counts\_mt as a categorical covariate in scVI? Additionally n\_genes\_by\_counts does show lower gene detection in the problematic quadrant of the UMAP however, it is only “removed“ when I do data = adata[adata.obs[‘n\_genes\_by\_counts’] \>= 2000, :] in the same latent space, which is really stringent.

 ![Screenshot 2025-11-25 at 10.35.01 AM](https://canada1.discourse-cdn.com/flex027/uploads/brainobservatory/original/2X/c/cb8c9d307ee89f1fb1c4a18422a719c09f197bf3.jpeg)

---

_[View the full topic](https://community.brain-map.org/t/i-am-seeing-a-cluster-in-the-query-that-is-not-alligning-with-ref-sea-ad-snrnaseq-mtg/4781)._