fuzzyCell - Bootstrap Classification Confidence for Spatial Cell-Type Analysis

Cell type labels in spatial single-cell data are uncertain, particularly between closely related subtypes. fuzzyCell estimates a per-cell classification confidence by bootstrapping (multinomial resampling of each cell's counts followed by re-classification) and uses the resulting confidences as soft cell type weights. The weights are propagated through downstream analyses: cell type proportions, co-localisation (spicyR's L-function, and Statial's Kontextual test for relative co-localisation) and niche identification (lisaClust), each compared to the same analysis using hard labels. Cell types are organised with a user-supplied hierarchy of lineages, groups and subtypes. Helpers for testing against sample-level outcomes and for plotting are included.