R: Plot heatmap of cross-tabs of 2 clusterings

plotClustersTable {clusterExperiment}

R Documentation

Plot heatmap of cross-tabs of 2 clusterings

Description

Plot heatmap of cross-tabulations of two clusterings

Usage

## S4 method for signature 'ClusterExperiment'
plotClustersTable(object, whichClusters,
  ignoreUnassigned = FALSE, margin = NA, ...)

## S4 method for signature 'table'
plotClustersTable(object, clusterLegend = NULL,
  cluster = FALSE, plotType = c("heatmap", "bubble"), sizeTable = object,
  ...)

## S4 method for signature 'ClusterExperiment,character'
tableClusters(object, whichClusters,
  ...)

## S4 method for signature 'ClusterExperiment,missing'
tableClusters(object, whichClusters, ...)

## S4 method for signature 'ClusterExperiment,numeric'
tableClusters(object, whichClusters,
  useNames = TRUE, tableMethod = c("intersect", "union"), ...)

## S4 method for signature 'table,table'
bubblePlot(propTable, sizeTable, gridColor = rgb(0, 0,
  0, 0.05), maxCex = 8, cexFactor, ylab, xlab, legend = TRUE, las = 2,
  colorScale = RColorBrewer::brewer.pal(11, "Spectral")[-6])

Arguments

`object`	ClusterExperiment object (or matrix with table result)
`whichClusters`	argument that can be either numeric or character value indicating the clusters to be used. If numeric, gives the indices of the `clusterMatrix` to return; this can also be used to defined an ordering for the clusterings (as relevant). `whichClusters` can be a character value identifying the `clusterTypes` to be used, or if not matching `clusterTypes` then `clusterLabels`; alternatively `whichClusters` can be either 'all' or 'workflow' or 'primary' to indicate choosing all clusterings or choosing all `workflowClusters` clusterings or choosing the 'primary' clustering, respectively. If missing, the entire matrix of all clusterings is returned.
`ignoreUnassigned`	logical as to whether to ignore unassigned clusters in the plotting. This means they will also be ignored in the calculations of the proportions (if `margin` not NA).
`margin`	if NA, the counts from `tableClusters` will be plotted. Otherwise, `prop.table` will be called and the argument `margin` will be passed to `prop.table` to determine whether proportions should be calculated. If '1', then the proportions in the rows sum to 1, if '2' the proportions in the columns sum to 1. If 'NULL' then the proportion across the entire matrix will sum to 1. For a symmetric version, you can set `margin=0`, and the entry displayed in each cell will be the proportion equal to the size of the intersection over the size of the union of the clusters (a Jaccard similarity between the clusters), in which case each entry is a proportion but no combination of the entries sum to 1.
`...`	arguments passed on to `plotHeatmap` or `bubblePlot` depending on choice of `plotType`
`clusterLegend`	list in `clusterLegend` format that gives colors for the clusters tabulated.
`cluster`	logical, whether to cluster the rows and columns of the table. Passed to arguments `clusterFeatures` AND `clusterSamples` of `plotHeatmap`.
`plotType`	type of plot. If "heatmap", then a heatmap will be created of the values of the contingency table of the two clusters (calculated as determined by the argument "margin") using `plotHeatmap`. If "bubble", then a plot will be created using `bubblePlot`, which will create circles for each cell of the contingencey table whose size corresponds to the number of samples shared and the color based on the value of the proportion (as chosen by the argument `margin`).
`sizeTable`	table of sizes
`useNames`	for `tableClusters`, whether the output should be tabled with names (`useNames=TRUE`) or ids (`useNames=FALSE`)
`tableMethod`	the type of table calculation to perform. "intersect" refers to the standard contingency table (`table`), where each entry of the resulting table is the number of objects in both clusters. "union" instead gives for each entry the number of objects that are in the union of both clusters.
`propTable`	table of proportions
`gridColor`	color for grid lines
`maxCex`	largest value of cex for any point (others will scale proportionally smaller).
`cexFactor`	factor to multiple by to get values of circles. If missing, finds value automatically, namely by using the maxCex value default. Overrides value of maxCex.
`ylab`	label for y-axis. If missing, uses the name for rows in sizeTable. If set to `NULL` no y-axis label will be plotted.
`xlab`	label for x-axis. If missing, uses the name for columns in sizeTable. If set to `NULL` no y-axis label will be plotted.
`legend`	whether to draw legend along top
`las`	the value for the las value in the call to `axis` in labeling the clusters in the bubble plot. Determines whether parallel or perpindicular labels to the axis (see `par`).
`colorScale`	the color scale for the values of the proportion table

Details

For plotClustersTable whichClusters should define 2 clusters, for tableClusters can indicate arbitrary number.

Note that the cluster labels in plotClustersTable and tableClusters are converted to "proper" R names via make.names. This is because tableClusters calls the R function table, which makes this conversion

bubblePlot is mainly used internally by plotClustersTable but is made public for users who want more control and to allow documentation of the arguments. bubblePlot plots a circle for each intersection of two clusters, where the color of the circle is based on the value in propTable and the size of the circle is based on the value in sizeTable. The size is determined by setting the cex value of the point as $sqrt(sizeTable[i,j])/sqrt(max(sizeTable))*cexFactor$.

Examples

#clustering using pam: try using different dimensions of pca and different k
data(simData)

cl <- clusterMany(simData, nReducedDims=c(5, 10, 50), reducedDim="PCA",
clusterFunction="pam", ks=2:4, findBestK=c(TRUE,FALSE),
removeSil=c(TRUE,FALSE))
#give arbitrary names to clusters for demonstration
cl<-renameClusters(cl,value=letters[1:nClusters(cl)[1]],whichCluster=1)
tableClusters(cl,whichClusters=1:2)
#heatmap of the counts in each entry of table:
plotClustersTable(cl,whichClusters=1:2, ignoreUnassigned=TRUE)