Reproducibility issue

[evaham1]

Hello and thanks for a great tool!

I would like to re-open this closed issue #16 - I am also seeing different initialized archetypes and therefore SEACells when I repeat the analysis with the same parameters on the same data. I would really like to avoid this randomness as I am computing SEACells as part of a wider pipeline which I would like to make totally reproducible from start to finish. I was wondering if anyone had been able to pinpoint where the randomness is coming from and where we could fix it to get reproducible results?

Thanks very much,
Eva

[ManuSetty]

We have recently updated the Palantir package (https://github.com/dpeerlab/Palantir) which is most likely the source of this issue. We recommend updating our Palantir package and then setting a random seed before you run SEACells - please try this and let us know if this solves the issue.

[evaham1]

Sorry for the delayed reply and thank you for the response! I have just checked and updating Palantir works to get reproducible SEACells which is great!

Just a note that I ended up installing this commit of Palantir, as just installing it directly using pip created some errors in my SEACells computation which caused it to fail. The Palantir commit with the bug fix that I used is here: dpeerlab/Palantir@d6f93f4