-
Notifications
You must be signed in to change notification settings - Fork 2
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
Precompute clustering #18
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Clustering code looks good, with just minor requests. In order for the metrics to recognise the precomputed clusters, I updated the scib version and adjusted the metrics to look for the precomputed clusters, asuming they are stored in .obs
I addressed most of my comments. The only thing that is missing are tests for the clustering component and for checking that the metrics actually use the precomputed values |
Hi @mumichae. Thanks for you help with this! We would like to try and merge it this week. I can help with the code but I wanted to make sure I understood everything first. At the moment the clustering is being pre-computed on the raw, unintegrated data. Is this correct or should we be doing it on the embedding output? |
Hi @lazappi , thanks for catching that detail, I didn't notice it when I was going through the code. The clustering should of course be done for each integration, i.e. after the transformation step, when the kNN graph has been computed. |
Thanks! I thought that would be the cases so I've made some changes already. Should be able to push them soon. |
Describe your changes
.obsm["clustering"]
to the solution so it can be used by the metricsExample:
Running the process_dataset workflow results in:
Checklist before requesting a review
I have performed a self-review of my code
Check the correct box. Does this PR contain:
Proposed changes are described in the CHANGELOG.md
CI Tests succeed and look good!