Daniel Dimitrov

Hi @mainharryHR, So, I think the point is that this analysis doesn't necessarily do that as the tensor decomposition is an unsupervised process indepedent of the condition labels. You can...

Hi @rikfor, Indeed, this is where the warning is raised: https://github.com/saezlab/liana-py/blob/e0c86b15cc2731dde8f4caf63e7918c032f4f2b3/liana/multi/df_to_lr.py#L101 The intersection of the two is used either way. PS. I believe I have made a mistake in the...

Hi @Peevin, The way that we generated the initial liana network is described in the first liana manuscritpt - so it's a frozen version of this procedure: OmniPath’s version used...

Hi @estherwon, This seems to be a recurring issue when trying to install the automatically setup environment by liana. I will try to resolve it, in the meantime, you could...

Hi @rcannood, It looks like a silly edgecase. Basically, in the AnnData we have a column called `feature_name` which is the same as the name of the index, so when...

Hi @ThibaultFy, Thanks for opening an issue. Hmm, this is strange - given that this is an optional dependency and hence I wouldn't expect it to be installed via `pip...

Hi @alexanderchang1 I have it on my todo to upload liana to conda. I will do it on next release. I currently have a bunch of deadlines, but I will...

Hi, It's very likely that you are not passing your desired cell_type label to `idents_col `. So, I assume it should be okay, if you pass `idents_col='cell_type'` to liana_wrap. Hope...

Hi @Marwansha, it seems like this is a bug with mofapy2 0.7.0, if you update to `0.7.1` it should be resolved. Works for me at least :)

Hi @schroeme, Sorry for the delayed response. You can modify the ggplot2 object that liana returns as any other object. So, indeed you could modify/rotate the text from the `facet`...