Emma Dann

Hi @jflusche, you should be able to run milopy using a neighbor graph built on the scVI embedding with no problem, the function picks the same representation used for KNN...

statsmodels https://www.statsmodels.org/stable/generated/statsmodels.formula.api.negativebinomial.html#statsmodels.formula.api.negativebinomial

batchGLM / diffxpy from theislab

Hi @Zethson, thanks for the heads up. I actually have some bandwidth now to look into this and try a few options out.

Definitely default to genomic location (chr+start), option to use another column?

- Add option to subset only to canonical transcripts (as indicated in genes table), and add gene ID

Notes on filtering behaviour: in bioconductor the filtering is done at the level of transcripts, before the promoter sequences are defined. Example: if promoter is within filtered range, but the...

Outstanding issues: - Dealing with common column names between var table and annotation table. Throw error?

@ivirshup wrt Ensembl version matching, the pbmc3k data was mapped with cellranger 1.1, but I am having a hard time matching this version to a Ensembl release. I'm gonna use...

Insertion/deletion accuracy results are saved in: ``` /nfs/team205/ed6/bin/Genes2Genes/notebooks/data/match_accuracy_pancreas.insertion.csv /nfs/team205/ed6/bin/Genes2Genes/notebooks/data/match_accuracy_pancreas.deletion.csv ```