scFeatures: Multi-view representations of single-cell and spatial data for disease outcome prediction


[Up] [Top]

Documentation for package ‘scFeatures’ version 1.7.0

Help Pages

example_scrnaseq Example of scRNA-seq data
get_num_cell_per_spot Estimate a relative number of cells per spot for spatial transcriptomics data
remove_mito_ribo Remove mitochondrial and ribosomal genes, and other highly correlated genes
run_association_study_report Create an association study report in HTML format
run_CCI Generate cell cell communication score
run_celltype_interaction Generate cell type interaction
run_gene_cor Generate overall aggregated gene correlation
run_gene_cor_celltype Generate cell type specific gene expression correlation
run_gene_mean Generate overall aggregated mean expression
run_gene_mean_celltype Generate cell type specific gene mean expression
run_gene_prop Generate overall aggregated gene proportion expression
run_gene_prop_celltype Generate cell type specific gene proportion expression
run_L_function Generate L stats
run_Morans_I Generate Moran's I
run_nn_correlation Generate nearest neighbour correlation
run_pathway_gsva Generate pathway score using gene set enrichement analysis
run_pathway_mean Generate pathway score using expression level
run_pathway_prop Generate pathway score using proportion of expression
run_proportion_logit Generate cell type proportions, with logit transformation
run_proportion_ratio Generate cell type proportion ratio
run_proportion_raw Generate cell type proportion raw
scFeatures Wrapper function to run all feature types in scFeatures
scfeatures_result Example of scFeatures() output