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.
Hi @weiruo16 @tassicalim ,
Currently the functions
CreateCelestaObject and GetNeighborInfo have a "bandwidth" distance argument used in nearest neighbors calculation.
But this "bandwidth" parameter is always taking the default=100, because it's not being passed into GetNeighborInfo.
Hi @weiruo16 @tassicalim , Currently the functions
CreateCelestaObject
andGetNeighborInfo
have a "bandwidth" distance argument used in nearest neighbors calculation.But this "bandwidth" parameter is always taking the default=100, because it's not being passed into GetNeighborInfo.
Here is a proposed fix. thanks for your work!
cc: @dnadave @NicoleEO