scmapCell2Cluster {scmap} | R Documentation |
Each cell in the query dataset is assigned a cell-type if the similarity between its nearest neighbour exceeds a threshold AND its w nearest neighbours have the same cell-type.
scmapCell2Cluster(scmapCell_results = NULL, cluster_list = NULL, w = 3, threshold = 0.5) scmapCell2Cluster.SingleCellExperiment(scmapCell_results, cluster_list, w, threshold) ## S4 method for signature 'list' scmapCell2Cluster(scmapCell_results = NULL, cluster_list = NULL, w = 3, threshold = 0.5)
scmapCell_results |
the output of 'scmapCell()' with 'projection' as its input. |
cluster_list |
list of cell cluster labels correspondint to each index against which the 'projection' has been projected |
w |
an integer specifying the number of nearest neighbours to find |
threshold |
the threshold which the maximum similarity between the query and a reference cell must exceed for the cell-type to be assigned |
The query dataset with the predicted labels attached to colData(query_dat)$cell_type1
library(SingleCellExperiment) sce <- SingleCellExperiment(assays = list(normcounts = as.matrix(yan)), colData = ann) # this is needed to calculate dropout rate for feature selection # important: normcounts have the same zeros as raw counts (fpkm) counts(sce) <- normcounts(sce) logcounts(sce) <- log2(normcounts(sce) + 1) # use gene names as feature symbols rowData(sce)$feature_symbol <- rownames(sce) isSpike(sce, 'ERCC') <- grepl('^ERCC-', rownames(sce)) # remove features with duplicated names sce <- sce[!duplicated(rownames(sce)), ] sce <- selectFeatures(sce) sce <- indexCell(sce) scmapCell_results <- scmapCell(sce, list(metadata(sce)$scmap_cell_index)) sce <- scmapCell2Cluster(scmapCell_results, cluster_list = list(colData(sce)$cell_type1))