plotHeatmapPretrained: Plots rectangular AUROC heatmap, clustering train cell types...

In MetaNeighbor: Single cell replicability analysis

Description

Plots rectangular AUROC heatmap, clustering train cell types (columns) by similarity, and ordering test cell types (rows) according to similarity to train cell types..

Usage

plotHeatmapPretrained(
  aurocs,
  alpha_col = 1,
  alpha_row = 10,
  cex = 1,
  margins = c(8, 8)
)

Arguments

aurocs	A rectangular AUROC matrix as returned by MetaNeighborUS,
alpha_col	Parameter controling column clustering: a higher value of alpha_col gives more weight to extreme AUROC values (close to 1).
alpha_row	Parameter controling row ordering: a higher value of alpha_row gives more weight to extreme AUROC values (close to 1).
cex	Size factor for row and column labels.
margins	Size of margins (for row and column labels).

Examples

data(mn_data)
var_genes = variableGenes(dat = mn_data, exp_labels = mn_data$study_id)
celltype_NV = MetaNeighborUS(var_genes = var_genes,
                             dat = mn_data,
                             study_id = mn_data$study_id,
                             cell_type = mn_data$cell_type,
                             symmetric_output = FALSE)
keep_col = getStudyId(colnames(celltype_NV)) == "GSE71585"
keep_row = getStudyId(rownames(celltype_NV)) != "GSE71585"
plotHeatmapPretrained(celltype_NV[keep_row, keep_col])

MetaNeighbor documentation built on Nov. 8, 2020, 5:40 p.m.