# Sc.pp.regress\_out() with large datasets

**URL:** <https://discourse.scverse.org/t/sc-pp-regress-out-with-large-datasets/2525>\
**Category:** scanpy\
**Created:** [September 19, 2024, 10:08pm UTC](https://discourse.scverse.org/t/sc-pp-regress-out-with-large-datasets/2525 "2024-09-19T22:08:11Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![sabrina\_tsai](https://avatars.discourse-cdn.com/v4/letter/s/f17d59/32.png) [@sabrina\_tsai](https://discourse.scverse.org/u/sabrina_tsai)\
**Post date:** [September 19, 2024, 10:08pm UTC](https://discourse.scverse.org/t/sc-pp-regress-out-with-large-datasets/2525/1 "2024-09-19T22:08:11Z")

</div>

I’m having trouble regressing out cell cycle genes in large datasets as this is taking hours or often getting out of memory errors (with 800G). I’ve tried increasing the n\_jobs parameter but it still takes quite long. Why is it faster to regress\_out cell cycle genes in Seurat (within an hour)? Is there a difference in these two functions where one might be converting sparse into a dense matrix?