When I test this package in pbmc3k dataset. It showed a absurd result.
> table(TC_res$cell_type) normal tumor 20 2326
I don't know where the problem is. Here is my code
sc <- SeuratData::LoadData('pbmc3k') sc <- do_sc_pipeline(sc,resolution = 0.8,integration = NULL) sc[['RNA']] <- as(sc[['RNA']],Class = 'Assay') dat_count <- GetAssayData(sc,assay = 'RNA',slot = 'counts') dat_norm <- TCfinder::data_normalized(expr_data = dat_count) colnames(dat_norm) <- colnames(dat_count) dat_score <- TCfinder::pathway_score(expr_data = dat_norm) TC_res <- TCfinder::predict_cell(path_score = dat_score) table(TC_res$cell_type)
The function do_sc_pipline is a customed function to normalize and scale the seurat data.
Thanks for your time.
When I test this package in pbmc3k dataset. It showed a absurd result.
> table(TC_res$cell_type) normal tumor 20 2326I don't know where the problem is. Here is my code
sc <- SeuratData::LoadData('pbmc3k') sc <- do_sc_pipeline(sc,resolution = 0.8,integration = NULL) sc[['RNA']] <- as(sc[['RNA']],Class = 'Assay') dat_count <- GetAssayData(sc,assay = 'RNA',slot = 'counts') dat_norm <- TCfinder::data_normalized(expr_data = dat_count) colnames(dat_norm) <- colnames(dat_count) dat_score <- TCfinder::pathway_score(expr_data = dat_norm) TC_res <- TCfinder::predict_cell(path_score = dat_score) table(TC_res$cell_type)The function do_sc_pipline is a customed function to normalize and scale the seurat data.
Thanks for your time.