# I have always had a question: do I need to scale my adata before running sc.tl.score\_genes?

**URL:** <https://discourse.scverse.org/t/i-have-always-had-a-question-do-i-need-to-scale-my-adata-before-running-sc-tl-score-genes/2305>\
**Category:** Help\
**Created:** [May 30, 2024, 10:21am UTC](https://discourse.scverse.org/t/i-have-always-had-a-question-do-i-need-to-scale-my-adata-before-running-sc-tl-score-genes/2305 "2024-05-30T10:21:53Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![tuhulab](https://yyz1.discourse-cdn.com/flex035/user_avatar/discourse.scverse.org/tuhulab/32/1103_2.png) [@tuhulab](https://discourse.scverse.org/u/tuhulab)\
**Post date:** [July 18, 2024, 8:01am UTC](https://discourse.scverse.org/t/i-have-always-had-a-question-do-i-need-to-scale-my-adata-before-running-sc-tl-score-genes/2305/2 "2024-07-18T08:01:01Z")

</div>

In my opinion, no.  
If you check the function [here](https://github.com/scverse/scanpy/blob/b918a23eb77462837df90d7b3a30a573989d4d48/src/scanpy/tools/_score_genes.py#L38-L44). The mean is calculated on `X`, which is the raw counts.

---

_[View the full topic](https://discourse.scverse.org/t/i-have-always-had-a-question-do-i-need-to-scale-my-adata-before-running-sc-tl-score-genes/2305)._