Changes in version 1.7.2 (2025-07-23)                  

    o   BREAKING CHANGE: Removed UCell dependency - integrated UCell
	scoring algorithm directly into scGate

    o   Seurat V4 priority: All functions now prioritize Seurat V4
	compatibility (tested with 4.4.0)

    o   Seurat V5 compatible: Also works with Seurat V5 through
	compatibility layer

    o   New internal functions: .AddModuleScore_UCell(), .SmoothKNN()
	for signature scoring and kNN smoothing

    o   Uses Seurat::GetAssayData() instead of SeuratObject::Layers()
	for V4 compatibility

    o   Added BiocNeighbors and Matrix as dependencies (replacing
	UCell)

    o   Cross-platform compatibility: replaced system("rm -r") with
	unlink() for Windows support

    o   Numerical stability: improved MCC calculation to handle edge
	cases (log(0), integer overflow)

    o   Performance optimization: vectorized operations (rowSums, pmax,
	max.col)

    o   Code quality: fixed potential bugs with 1:length() loops,
	improved parameter validation

    o   New maintainer: Zaoqu Liu

                 Changes in version 1.7.0 (2025-04-24)                  

    o   Update maintainer emails

    o   Bug fixes

                 Changes in version 1.6.2 (2024-04-23)                  

    o   Enable parallelization over a list of scGate models (in
	multi-classifier mode)

    o   Fix bug on parallelization when specifying BPPARAM

    o   Added cell ontology links for controlled cell type dictionary

    o   Update accessor functions for compatibility with Seurat v5

                        Changes in version 1.4.0                        

    o   Use function SmoothKNN() from the UCell package for nearest
	neighbor smoothing of signature scores

    o   Clean up code for CRAN submission

                        Changes in version 1.2.0                        

    o   Simultaneously evaluate multiple gating models, given as a list
	to model parameter. This returns individual gatings as well as
	a combined cell type annotation from all the models
	(scGate_multi metadata column), and allows running scGate as a
	multi-class classifier and annotate cell types in a dataset.

    o   New reduction parameter: this i) Allows nearest-neighbor
	smoothing on an existing dimensionality reduction (e.g. "pca"
	or "harmony") and ii) Can significantly speed up computation
	time and annotation of integrated objects