Skip to content

Conversation

@okraus
Copy link
Contributor

@okraus okraus commented Jan 21, 2025

What?

  • added line to filter gene_symbol and treatment from the truth dataframe to only whats in the map_data.metadata.perturbation column

Why?

  • Unfortunately our CellProfiler processing is missing a bunch of wells from the original dataset, so we need to apply these filters. Some stats:
CellProfiler_filter has 184,492 out of 222,601 original wells
CellProfiler_filter has 2080 out of 2921 relationships - missing 841 relationships
CellProfiler_filter has 1190 of 1674 compounds
CellProfiler_filter has 721 of 736 genes

@okraus okraus merged commit 60df3eb into trunk Jan 28, 2025
4 checks passed
@okraus okraus deleted the fix_for_cellprofiler_metadata branch January 28, 2025 02:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants