STATegRa (version 1.0.0)

omicsCompAnalysis: Components analysis for the analysis of object wise data

Description

This function performs a components analysis of object wise omics data to understand the mechanisms that underlay all the data blocks under study (common mechanisms) and the mechanisms underlying each of the data block independently (distinctive mechanisms). This analysis include both, the preprocessing of data and the components analysis by using three different methodologies.

Usage

omicsCompAnalysis(Input,Names,method,Rcommon,Rspecific, convThres=10^(-10),maxIter=600,center=FALSE, scale=FALSE,weight=FALSE)

Arguments

Input

List of ExpressionSet objects, one for each block of data

Names

Vector indicating a distintive name for each block of data

method

Method used for components analysis. The methods included are DISCO_SCA, JIVE and O2PLS

Rcommon

Number of common components between all blocks

Rspecific

Vector indicating the individual components of each block of data

convThres

Maximum value for convergence (stop criterium. Default value: 0.0000001)

maxIter

Maximum number of iterations (stop criterium. Default value: 600)

center

Character indicating which type of centering must be applied to data before the analysis. Data can be centered considering all blocks together (PERBLOCKS) or each block separately (PERBLOCKS). If the parameter has a NULL (default) value, no center is applied

scale

Character indicating which type of scaling must be applied to data before the analysis. Data can be scaled considering all blocks together (PERBLOCKS) or each block separately (PERBLOCKS). If the parameter has a NULL (default) value, no scale is applied

weight

Logical indicating if the blocks has to be weighted before the analysis

Value

A object of class caClass-class

See Also

caClass-class

Examples

# Loading data
data("STATegRa_S3")
B1 <- createOmicsExpressionSet(Data=Block1.PCA,pData=ed.PCA,
                               pDataDescr=c("classname"))
B2 <- createOmicsExpressionSet(Data=Block2.PCA,
                               pData=ed.PCA,pDataDescr=c("classname"))
# Omics components analysis
discoRes <- omicsCompAnalysis(Input=list(B1,B2),Names=c("expr","mirna"),
                              method="DISCOSCA",Rcommon=2,Rspecific=c(2,2),
                              center=TRUE,scale=TRUE,weight=TRUE)
jiveRes <- omicsCompAnalysis(Input=list(B1,B2),Names=c("expr","mirna"),
                              method="JIVE",Rcommon=2,Rspecific=c(2,2),
                              center=TRUE,scale=TRUE,weight=TRUE)
o2plsRes <- omicsCompAnalysis(Input=list(B1,B2),Names=c("expr","mirna"),
                              method="O2PLS",Rcommon=2,Rspecific=c(2,2),
                              center=TRUE,scale=TRUE,weight=TRUE)