Adaptive Machine Learning-Powered, Context-Matching Tool for Single-Cell and Spatial Transcriptomics Annotation
Calculate Cluster Variability (Use in package)
Calculate Expression Distribution Skewness (Use in package)
Counts average expression of gene set (Use in package)
Calculate gene set expression and infer probabilities with control dat...
Uses "marker_list" from Cellmarker2 for cell annotation
Uses "marker_list" to generate combined plot for cell annotation
Uses "marker_list" from Excel input for cell annotation
Annotate cell types using features plot with different marker database...
Uses "marker_list" to generate heatmap for cell annotation
Uses "marker_list" from PanglaoDB for cell annotation
Annotate Seurat Object with Per-Cell SlimR Predictions
Uses "marker_list" from Seurat object for cell annotation
Annotate Seurat Object with SlimR Cell Type Predictions
Per-cell annotation using marker expression and optional UMAP spatial ...
Uses "marker_list" to calculate probability, prediction results, AUC a...
Verify per-cell annotations with marker expression dotplot
Perform cell type verification and generate the validation dotplot
Compute Adaptive Parameters Based on Dataset Features (Use in package)
Apply UMAP-based spatial smoothing to scores
Compute AUCell-like rank-based scores
Compute weighted scores for per-cell annotation
Estimate Batch Effect Strength (Use in package)
Extract Dataset Characteristics for Adaptive Parameter Calculation (Us...
Create Marker_list from the Cellmarkers2 database
Create Marker_list from the PanglaoDB database
Adaptive Parameter Tuning for Single-Cell Data Annotation in SlimR
Per-Cell Annotation Workflow Example
Plot Method for pheatmap Objects
Create "Marker_list" from Excel files ".xlsx"
Create "Marker_list" from Seurat object
Annotates single-cell and spatial-transcriptomic (ST) data using context-matching marker datasets. It creates a unified marker list (`Markers_list`) from multiple sources: built-in curated databases ('Cellmarker2', 'PanglaoDB', 'scIBD', 'TCellSI', 'PCTIT', 'PCTAM'), Seurat objects with cell labels, or user-provided Excel tables. SlimR first uses adaptive machine learning for parameter optimization, and then offers two automated annotation approaches: 'cluster-based' and 'per-cell'. Cluster-based annotation assigns one label per cluster, expression-based probability calculation, and AUC validation. Per-cell annotation assigns labels to individual cells using three scoring methods with adaptive thresholds and ratio-based confidence filtering, plus optional UMAP spatial smoothing, making it ideal for heterogeneous clusters and rare cell types. The package also supports semi-automated workflows with heatmaps, feature plots, and combined visualizations for manual annotation. For more details, see Kabacoff (2020, ISBN:9787115420572).