Celltypist symbol col assignmnet fix #222
Draft
+40
−1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
nf-core/scrnaseq saves the scanvi compatable symbols in the column "gene_symbols" (index is the ensbl IDs). So to be compatible with nf-core/scdownstream You must define "symbol_col" in the sample sheet and "gene_symbol" as the value for each sample in the column. However, the .h5ad from nf-core/scrnaseq this column as categorical. in line 50 of celltypist.py is simple replaces the ver_names (index, type = Object) with the categorical column. However, in line 60 celltypist.annotate will attempt to make the var_names unique. This will error as it cannot handle categorical restructuring. It must be converted to a different column type, To fix this simple, call .to_list() for the reassignment.
…. It's possible this comes from an error somewhere else and should be fixed there..
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR Notes
I fully do NOT intend for this PR to be merged as is.
Problem 1: When using the .h5ed from scrnaseq pipeline, you must set symbol_col to a column that is
categorical, but this is incompatible with anndata objects's var_names (when calling the function to make unique indexes). The first fix is to simply cast the pd.Series to a list when assigning it to adata.var_names.Problem 2: This gets a little more dicey, When trying to boot strap scanvi from celltypist, it's hard to know/non-obvious the name of the celltypist column before hand that's needed for Celltypist labels, as it expect them to be in the 'label_col' column, which is empty. I still believe this can be changed elsewhere, or maybe I'm just wrong in my approach, Please correct me, im not an expert with scrnaseq.
Problem 3: Similar to 1, adata.var_names becomes categorical again, There should be a nicer place to change this upstream, but I cant find it right now.
Additional: I couldn't the debug profile to behave nicely, maybe something is wrong?
PR checklist
nf-core pipelines lint).nextflow run . -profile test,docker --outdir <OUTDIR>).nextflow run . -profile debug,test,docker --outdir <OUTDIR>).docs/usage.mdis updated.docs/output.mdis updated.CHANGELOG.mdis updated.README.mdis updated (including new tool citations and authors/contributors).