bfurtwa

The biggest advantage would be the possibility to create such panels as shown in the example, where e.g. quality metrics have different cmaps as gene expression. Another advantage would be...

Ok, makes sense. What if I implement that `cmap `in `embedding` also accepts a `dict ` of `{variable: colormap}`? `{'n_counts_all': 'copper', 'n_genes_cmap': matplotlib.colors.Colormap}` It maps variable names to `str `...

I think a problem with a list would be that is would need to be the same length as `color`, and therefore, each colormap would need to be specifically defined,...

This works for me: ``` def _fdr_de_prediction(posterior_probas: pd.Series, fdr: float = 0.05) -> pd.Series: """Compute posterior expected FDR and tag features as DE.""" if not posterior_probas.ndim == 1: raise ValueError("posterior_probas...

Hi @matq007, performing multiple group comparisons will result in genes tested multiple times. So it generates a new row with the same index for each group comparison.

I'm using a big dataset with around 300,000 peptides. So each iteration is one batch? That means I did 4*16=64 samples/s with batch size 16. With batch size 2000 I...

I tried pytorch-cpu 0.4.1 and pytorch 0.4.0 from `conda install pytorch-cpu=0.x.0 -c pytorch` With 0.4.0 and a new git clone it looks like that: ``` D:\Benni\Code\DeepRT\DeepRTplus>python capsule_network_emb_cpu.py 0 -> *...

This is my minimal python environment ``` (DeepRT) D:\Benni\Code\DeepRT\DeepRTplus>conda list # packages in environment at D:\Programs\anaconda3\envs\DeepRT: # # Name Version Build Channel blas 1.0 mkl certifi 2018.10.15 py36_0 cffi 1.11.5...