Collect classes from ConsensusPartitionList object

# S4 method for ConsensusPartitionList
collect_classes(object, k, show_column_names = FALSE,
    column_names_gp = gpar(fontsize = 8),
    anno = get_anno(object), anno_col = get_anno_col(object),
    simplify = FALSE, ...)

Arguments

object: A ConsensusPartitionList-class object returned by run_all_consensus_partition_methods.
k: Number of subgroups.
show_column_names: Whether to show column names in the heatmap (which is the column name in the original matrix).
column_names_gp: Graphics parameters for column names.
anno: A data frame of annotations for the original matrix columns. By default it uses the annotations specified in run_all_consensus_partition_methods.
anno_col: A list of colors (color is defined as a named vector) for the annotations. If anno is a data frame, anno_col should be a named list where names correspond to the column names in anno.
simplify: Internally used.
...: Pass to draw,HeatmapList-method.

Details

There are following panels in the plot:

a heatmap showing partitions predicted from all methods where the top annotation is the consensus partition summarized from partitions from all methods, weighted by mean silhouette scores in every single method.
a row barplot annotation showing the mean silhouette scores for different methods.

The row clustering is applied on the dissimilarity matrix calculated by cl_dissimilarity with the comembership method.

The brightness of the color corresponds to the silhouette scores for the consensus partition in each method.

Value

No value is returned.

Author

Zuguang Gu <z.gu@dkfz.de>

Examples

data(golub_cola)
collect_classes(golub_cola, k = 3)