Last data update: 2014.03.03

 R: Sparse canonical correlation analysis
mPhen.ccaR Documentation

Sparse canonical correlation analysis

Description

Carries out a sparse canonical correlation analysis

Usage

mPhen.cca(genoData, phenoObject, opts =mPhen.options("regression"), 
		         subinds = 1:(dim(genoData)[1]),
		vs.G = opts$mPhen.variable.selection,
                 vs.P = opts$mPhen.variable.selection
)

Arguments

genoData

A 2 dimensional array. The first dimension (rows) corresponds to individuals, and row.names are inidividual IDs. The second dimension corresponds to SNPS, with col.names equal to the snp identifiers. The entries are either genotypes, or expected genotypes.

phenoObject

A phenotype object prepared by mPhen.preparePheno.

opts

A list of options, which is obtained from mPhen.options("regression"). To get more information about these options, type mPhen.options("regression",descr=TRUE).

vs.G

If true performs variable selection on genotypes. Is equal to opts$mPhen.variable_selection by default

vs.P

If true performs variable selection on phenotypes. Is equal to opts$mPhen.variable_selection by default

subinds

This indicates the indices of individuals to include in the analysis. It is possible to have repeat indices (i.e. for bootstrap)

Value

A list with following elements

betasp

Phenotype weights

betasg

Genotype weights

resultsGeno

Single (combined) phenotype analysis results against all genotypes

resultsPheno

Multiple phenotype analysis results against single (combined) genotype

Results


Created & Maintained by Osamu Ogasawara (osamu.ogasawara@gmail.com) and IMSBIO