You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Describe the goals of the changes to the analysis module.
Following #610, we will want to look at one or more metacell results to see how well the method is performing on our data sets. To do this, we will create a notebook (Jupyter most likely) that will include calculating statistics such as compactness and separation to look at how well the metacells cover the original cell types. This will also include a visualization of the metacells overlaid on the original cells in a UMAP.
This notebook will also include a summary computational requirements that were required for calculating the metacells.
The ultimate goal here is to allow comparisons among different metacell methods, but at this stage we will still be restricted to just the one, though perhaps with a range of input parameters.
What will your pull request contain?
A Jupyter notebook, as well as a script to allow rendering the notebook with different input AnnData objects.
Will you require additional software beyond what is already in the analysis module?
Not expected
Will you require different computational resources beyond what the analysis module already uses?
Unknown at this time.
If known, when do you expect to file the pull request?
By July 26
The text was updated successfully, but these errors were encountered:
If you are filing this issue based on a specific GitHub Discussion, please link to the relevant Discussion.
#362
Describe the goals of the changes to the analysis module.
Following #610, we will want to look at one or more metacell results to see how well the method is performing on our data sets. To do this, we will create a notebook (Jupyter most likely) that will include calculating statistics such as compactness and separation to look at how well the metacells cover the original cell types. This will also include a visualization of the metacells overlaid on the original cells in a UMAP.
This notebook will also include a summary computational requirements that were required for calculating the metacells.
The ultimate goal here is to allow comparisons among different metacell methods, but at this stage we will still be restricted to just the one, though perhaps with a range of input parameters.
What will your pull request contain?
A Jupyter notebook, as well as a script to allow rendering the notebook with different input AnnData objects.
Will you require additional software beyond what is already in the analysis module?
Not expected
Will you require different computational resources beyond what the analysis module already uses?
Unknown at this time.
If known, when do you expect to file the pull request?
By July 26
The text was updated successfully, but these errors were encountered: