number_clusters: Function to determine the number of clusters to be used to...

In nlawlor/multiClust: multiClust: An R-package for Identifying Biologically Relevant Clusters in Cancer Transcriptome Profiles

Description

Function to determine the number of clusters to be used to cluster gene probes and samples.

Usage

number_clusters(data.exp, Fixed = 3, gap_statistic = NULL)

Arguments

data.exp	The numeric original gene expression matrix to be used for clustering of genes and samples. This object is an output of the input_file function.
Fixed	A positive integer used to represent the number of clusters the samples and probes will be divided into. The default cluster number is set to 3 clusters.
gap_statistic	A logical indicating whether to use the gap_statistic to determine the optimal number of clusters to divide samples into.

Value

An object with the determined number of clusters to use.

Note

The user should only choose either the fixed or gap_statistic option, not both. When using the gap_statistic option, change the argument to TRUE and "Fixed" to NULL.

Author(s)

Nathan Lawlor, Alec Fabbri

See Also

clusGap, probe_ranking

Examples

#Example 1: Using a fixed cluster number
# Load in a test file
data_file <- system.file("extdata", "GSE2034.normalized.expression.txt",
package="multiClust")
data <- input_file(data_file)
clust_num <- number_clusters(data.exp=data, Fixed=3, gap_statistic=NULL)

## Not run: 
# Example 2: Using the gap_statistic to determine the optimal cluster number
# Computation time is somewhat long
clust_num <- number_clusters(data.exp=data, Fixed=NULL, gap_statistic=TRUE)
 
## End(Not run)

nlawlor/multiClust documentation built on May 16, 2019, 8:12 p.m.