Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

KBET (without labels) to BatchCorrection #150

Open
lebelm opened this issue Feb 27, 2024 · 1 comment
Open

KBET (without labels) to BatchCorrection #150

lebelm opened this issue Feb 27, 2024 · 1 comment
Labels
enhancement New feature or request

Comments

@lebelm
Copy link

lebelm commented Feb 27, 2024

Description of feature

Hello,

I was wondering if it would be possible to add KBET to the list of metrics that can be selected in the BatchCorrection object ? Or maybe it is already possible and I didn't figure out how.

I saw that the function scib_metrics.kbet() is present in the API list and I would be interested in running it as it is label-free, though it would make sense to have it off by default.
Currently, it can be run it by itself but this is not as practical as it takes a NeighborsResults as input.

scib_metrics.benchmark.BatchCorrection(silhouette_batch=True, ilisi_knn=True, kbet_per_label=True, graph_connectivity=True, pcr_comparison=True)

Thank you for the nice package in any case !

@lebelm lebelm added the enhancement New feature or request label Feb 27, 2024
@QqQss
Copy link

QqQss commented Apr 8, 2024

Similar question here.
I'm wondering if there's a function that can automatically convert the graph in adata (adatar.obsp['connectivities'] and adata.obsp['distances']) to NeighborsResults?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants