Constantin

Hey, I read through the documentation of tatami and rewrote the `fitBeta_one_group` using it (https://github.com/const-ae/glmGamPoi/commit/6476773f8766f70ccd2b39828ca02050453385fb). It seems to work fine, but there are some bits where I am not sure...

Thanks for the thorough explanation. > The amount of boilerplate should be equivalent to the old beachmat3 code with workspaces No, I don't think I used workspaces. Previously I did:...

Hey, sorry for the silence. I was traveling last week and am currently at ICML. I didn't manage to spend any more time on it. Maybe we can discuss next...

Hi, > I wonder if it is okay and **more** robust [...] 'More' compared with what? > A vs A+B A+C vs A+C+B A+C+D vs A+C+D+B All these three comparisons...

Hi Will, I just saw this issue. If you are interested, we could see if it is possible to call `glmGamPoi::overdispersion_mle()` from within glmpca. I recently worked on a similar...

Hey, thanks for the summary. > Constantin will add some features to glmGamPoi to facilitate integration: > > flag to allow optimizer to only do a single iteration instead of...

Hi Miriam, Sorry for the late reply. You are right to form pseudobulk sample to assess the effect of the genotype on the expression in your cell types. Your idea...

Great. I have already [adapted](https://github.com/const-ae/sparseMatrixStats/commits/change_useNames_default) my unit tests and all tests pass with `matrixStats` version 0.63.0-9011.