IntClust (version 0.0.2)

Ultimate: Function that performs any aggregated data function

Description

The function Ultimate has the ability to perform multiple of the methods listed above simultaneously. The only necessary input are the data matrices and specification of the options. First, clustering is based on each data matrix separately after which the specified integrative analysis methods are conducted. A plot comparing the results is made automatically with ComparePlot. If weights are involved in the method, a comparison plot of the results for these weights is made as well.

Usage

Ultimate(List,type=c("data","dist","clusters"),distmeasure,normalize=FALSE,method=NULL,
StopRange=FALSE,NN = 20,mu = 0.5, T = 20, t = 10, r = NULL, nrclusters = NULL,
nrclusterssep = c(7, 7),nrclustersseq = NULL, weight = NULL, Clustweight = 0.5, 
clust = "agnes", linkage=c("ward","ward"),alpha=0.625, gap = FALSE, maxK = 50,
 IntClust = c("ADC", "ADECa", "ADECb","ADECc", "WonM", "CECa", "CECb", "CECc",
  "WeightedClust", "WeightedSim", "SNFa", "SNFb", "SNFc"), fusionsLog = TRUE,
 WeightClust= TRUE, PlotCompare = FALSE, cols = NULL, ...)

Arguments

List

A list of matrices of the same type. It is assumed that the rows are corresponding to the objects.

type

Type indicates whether the provided matrices in "List" are either data or distance matrices obtained from the data. If type="dist" the calculation of the distance matrices is skipped and the methods ADC ,ADECa, ADECb, ADECc, CECa, CECb and CECc are not performed. Type should be one of "data" or "dist".

distmeasure

A vector of the distance measures to be used on each data matrix.

normalize

Logical. Indicates whether to normalize the distance matrices or not. This is recommended if different distance types are used. More details on standardization in Distance.

method

A method of normalization. Should be one of "Quantile","Fisher-Yates", "standardize","Range" or any of the first letters of these names.

StopRange

Logical. Indicates whether the distance matrices with values not between zero and one should be standardized to have so. If FALSE the range normalization is performed. See Normalization. If TRUE, the distance matrices are not changed. This is recommended if different types of data are used such that these are comparable.

NN

The number of neighbours to be used in SNF.

mu

A parameter in SNF.

T

The number of iterations in SNF.

t

The number of iterations in ADEC and CEC.

r

Optional. The number of features to take for the random sample in ADEC and CEC.

nrclusters

The number of clusters to cut the dendrogram in for ADEC and the plot.

nrclusterssep

Optional. Vector of the number of clusters to cut the dendrogram in of each data source. If NULL, the value of nclusters is used for each.

nrclustersseq

The sequence of number of clusters to cut the dendrogram in for ADECb, CECb and WonM.

weight

The weights to be used in CEC and WeightedClust.

Clustweight

Optional. To be used for the outputs of CEC or WeightedClust. Then only the result of the Clust element is considered.

clust

Choice of clustering function (character). Defaults to "agnes".

linkage

A vector with the choice of inter group dissimilarity (character) for each data set.

alpha

The parameter alpha to be used in the "flexible" linkage of the agnes function. Defaults to 0.625 and is only used if the linkage is set to "flexible"

gap

Logical. Indicator if gap statistics should be computed. Setting to $FALSE$ will greatly reduce the computation time.

maxK

The maximum number of clusters to be considered during the gap.

IntClust

Specification of the methods to be applied.

fusionsLog

To be handed to MatrixFunction.

WeightClust

To be handed to MatrixFunction.

PlotCompare

Logical. Should the plot over the methods and weight be produced?

cols

Color scheme to be used in the plots.

…

Options to be given to ComparePlot.

Value

The output of Ultimate is a list . The first element contains the results of the clustering of the first data source and the last element on the second data source . In between are the results of the integrative methods.

Examples

# NOT RUN {
data(fingerprintMat)
data(targetMat)
data(Colors2)
L=list(fingerprintMat,targetMat)

MCF7_All=Ultimate(L,type="data",distmeasure=c("tanimoto","tanimoto"),normalize=FALSE,
method=NULL,StopRange=FALSE,NN=20,alpha=0.5,T=20,t=25,r=NULL,nrclusters=7,
nrclustersseq=c(5,25,1),weight=seq(1,0,-0.1),Clustweight=0.5,clust="agnes",
linkage=c("ward","ward"),alpha=0.625,gap=FALSE,IntClust=c("ADC","ADECa","ADECb",
"ADECc","WonM","CECa","CECb","CECc","WeightedClust","WeightedSim",
"SNFa","SNFb","SNFc"),fusionsLog=TRUE,WeightClust=TRUE,PlotCompare=TRUE,
cols=Colors2)
# }