Jan Lause

sc.pp.highly_variable does not always handle `subset` and `inplace` arguments consistently

1

Hey, while writing tests for #1715 I noted the following behavior: `output = sc.pp.highly_variable(adata,inplace=True,subset=False,n_top_genes=100)` --> Returns nothing :heavy_check_mark: --> `adata.var` fields are updated but shape stays the same :heavy_check_mark: `output...

Script: U-Net integration into python pipeline.

5

Hey all, I currently have my image processing pipeline for cell detection in python and I've been looking for ways to integrate your UNET implementation into it. More specifically, I...

Gene selection plot for Pearson Residuals

3

Hi @giovp @ivirshup, (also CCing @dkobak) as we discussed at #1715 and in https://github.com/theislab/scanpy-tutorials/pull/43, I prepared a function `pearson_residuals_hvg_scatter()` that wraps `sc.pl.scatter()` to reproduce the "gene selection plot" from the...

Poisson GLM PCA: Convergence issues with avagrad

1

Hey Will, I wanted to share a couple of observation we made when fitting a 50-component GLM PCA to a dataset with 33k cells and 16k genes. First we used...

Feature request: Sparsity support

2

Hey Will, in the R package, sparse matrices are supported under some circumstances. As far as I saw, the python version does not make use of sparsity yet - do...

anndata views do not work as expected for `obs` and `var` dataframes

3

After talking to @ivirshup on Zulip, opening this issue here to point out an inconsistency in how anndata views currently work. When I have a view of an anndata object,...