Dylan Kotliar

Yes, like @michelle-curtis said, either can work. I think using the Z-score output by default seems to work the best. And also as Michelle said, good to subset to high...

Adjusted in commit https://github.com/dylkot/cNMF/commit/c94962d60490896361c0e8b659a29862145f3672

Hi, I am finally having some time to work on this again. If this problem is still active, please let me know. Thanks!

Just an update on this topic that the method to batch correct the data prior to cNMF is in the development branch at this time with an example of its...

Hey Christopher, are you looking in the development branch? GitHub - dylkot/cNMF at development Cheers, Dylan From: Christopher-Dall ***@***.***> Date: Tuesday, November 14, 2023 at 6:11 PM To: dylkot/cNMF ***@***.***>...

Awesome. We plan to push this to the main branch soon. Cheers, Dylan From: Christopher-Dall ***@***.***> Date: Wednesday, November 15, 2023 at 7:13 AM To: dylkot/cNMF ***@***.***> Cc: Kotliar, Dylan...

Hi, I was wondering if there is any chance this will be available sometime soon? Thank you.

Hi All, I [fixed this issue](https://github.com/dylkot/cNMF/commit/994b5fa819f31434948e33602ea85b47c554c676) on the development branch using sc.pp.normalize_total() as was suggested. Sorry for being so slow to get to this. I will update on this thread...

OK closing it now since it is updated on the main branch and in pypi version 1.5.2

Yes, I'll just add that choosing K is hard and I recommend to look at the results for a few values of K (as you would do with clustering). Usually...