| scmapCluster {scmap} | R Documentation |
Projection of one dataset to another
scmapCluster(projection = NULL, index_list = NULL, threshold = 0.7) scmapCluster.SingleCellExperiment(projection, index_list, threshold) ## S4 method for signature 'SingleCellExperiment' scmapCluster(projection = NULL, index_list = NULL, threshold = 0.7)
projection |
'SingleCellExperiment' object to project |
index_list |
list of index objects each coming from the output of 'indexCluster' |
threshold |
threshold on similarity (or probability for SVM and RF) |
The projection object of SingleCellExperiment class with labels calculated by 'scmap' and stored in
the scmap_labels column of the rowData(object) slot.
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)$feature_symbol <- rownames(sce)
isSpike(sce, 'ERCC') <- grepl('^ERCC-', rownames(sce))
# remove features with duplicated names
sce <- sce[!duplicated(rownames(sce)), ]
sce <- selectFeatures(sce)
sce <- indexCluster(sce)
sce <- scmapCluster(sce, list(metadata(sce)$scmap_cluster_index))