# Scanpy cell-based normalization

**URL:** <https://discourse.scverse.org/t/scanpy-cell-based-normalization/1355>\
**Category:** Help\
**Created:** [April 26, 2023, 4:31pm UTC](https://discourse.scverse.org/t/scanpy-cell-based-normalization/1355 "2023-04-26T16:31:30Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![cagey-squirrel](https://avatars.discourse-cdn.com/v4/letter/c/f14d63/32.png) [@cagey-squirrel](https://discourse.scverse.org/u/cagey-squirrel)\
**Post date:** [April 26, 2023, 4:31pm UTC](https://discourse.scverse.org/t/scanpy-cell-based-normalization/1355/1 "2023-04-26T16:31:30Z")

</div>

I am just starting with Bioinformatics so feel free to tell me if this topic doesn’t belong here.  
I am wondering why is normalization function in scnapy (pp.normalize\_total) based on total counts in single cell?

My goal is to find SVGs in a given dataset and I am not sure if normalizing by cell is helpful (or even harmful) for my task. It seems logical to me that I should normalize by gene column. It seems to me that each cell should have same sequencing depth so there is no reason to normalize by cell or am I wrong?