davi1893.bsky.social
16 posts
534 followers
98 following
Regular Contributor
comment in response to
post
The package is general and can be used with any distribution of the exponential dispersion family, which includes the Gaussian, Poisson, negative binomial, and many others.
More to come soon, including a @bioconductor.bsky.social wrapper to make it easier to work with single-cell RNA-seq data.
comment in response to
post
8. It is difficult to overstate what a catastrophe this will be for the US research and education systems, particular in biomedical fields.
It is deliberate and wanton devastation entirely out of scale with any concern about DEI activities on campuses.
The goal is destroy US universities.
comment in response to
post
This is a great chance to learn from long-term Bioconductor developers (including three founding members!). Registration opens on February 1st. All the info here: csama2025.bioconductor.eu
comment in response to
post
I fail to see how this is unusual, it's a standard model. As for reliability and stability, I believe that we make a good case for them in the paper for our model. I have my own thoughts on ZI models but I'll save them for another time as here we do not model ZI.
comment in response to
post
Of course it could be useful in other applications (e.g., DE) to have genewise dispersions and it's something that we could add in a future version of the package.
comment in response to
post
Right. We currently have a global dispersion parameter. In our comparisons, this is enough to correctly estimate the latent factors (see also www.nature.com/articles/s41...).
comment in response to
post
Sure. If I understand your question, w_{ij} in eq.2 are optional known weights (as in weighted regression) that can be used if appropriate in the application or can be safely ignored (that's what we do in our single-cell examples in the paper). This isn't different from the basic lm() function.
comment in response to
post
This work was driven by Cristian Castiglione and was a great collaboration with Lieven Clement and Alex Segers
comment in response to
post
I am now :)