scGate version 1.6.2

New in this version:

• Enable parallelization over a list of scGate models (in multi-classifier mode)
• Fix bug on parallelization when specifying BPPARAM
• Added cell ontology links for controlled cell type dictionary
• Update accessor functions to improve compatibility with Seurat v5

scGate version 1.6

New in this version:

• Addresses compatibility with Assay5 Seurat assays.
• Enables parallelization over a list of models, in multi-classifier mode (see BPPARAM)
• Uses new implementation of UCell::SmoothKNN() to smooth signature scores between neighboring cells. Neighbor cells are weighted by $(1-smooth.decay)^n$, where n is the n-th neighbor in PCA space, and smooth.decay is a parameter between 0 and 1.

scGate version 1.4

New in this version:

• scGate is now on CRAN! it can be installed using install.packages("scGate")
• The function get_scGateDB() now writes to tempdir() by default. To recover the behavior of previous versions, set destination="./scGateDB" or to some other local directory
• Log out fraction of "Pure" cells instead of "Impure" cells
• Fixed bug on kNN smoothing with too few remaining cells
• Improved documentation and examples

scGate version 1.2

New features in version 1.2.0

• Simultaneously evaluate multiple gating models, given as a list to model parameter
  • Returns individual gatings as well as a combined cell type annotation from all the models (scGate_multi metadata column)
  • Allows running scGate as a multi-class classifier and annotate cell types in a dataset
• New reduction parameter
  • Allows nearest-neighbor smoothing on an existing dimensionality reduction (e.g. "pca" or "harmony")
  • Can significantly speed up computation time and annotation of integrated objects
• Uses Bioconductor version of UCell

Zenodo preservation and DOI citation in journal publication

v1.0.1

in README include links to atac & adt demos

v1.0.0

First stable release of scGate