plevritis-lab / CELESTA

Automate unsupervised machine learning cell type identification using both protein expressions and cell spatial neighborhood information for multiplexed in situ imaging data. No training dataset with cell type labels is required.
Apache License 2.0
27 stars 9 forks source link

AssignCells user input thresholds #23

Open mcaponegro opened 5 months ago

mcaponegro commented 5 months ago

Hello, thank you for an easy to use package for spatial data. We have been using it a lot and it works very well.

One question I have is for the AssignCells() function, if a user wanted to input a lower bound expression value for each protein marker, for example CD3 expression >= 0.6, which parameter for AssignCells() would this be?

high_expression_threshold_anchor low_expression_threshold_anchor high_expression_threshold_index low_expression_threshold_index

I cannot seem to find out what each of these inputs mean from the ?AssignCells(). Any information you could provide would be helpful.

Thanks