survJamda (version 1.1.4)

main.single.indep.valid: Independent validation of the performance of the gene signatures derived from single data sets.

Description

Assess the performance of the gene signatures derived from the single data sets in pair-wise manner.

Usage

main.single.indep.valid(geno.files, surv.data,normalization = "zscore", method = "none",gn.nb=100, perf.eval = "auc")

Arguments

geno.files

A vector of character strings containing the names of expression files.

surv.data

The list of two vectors, survival time and censoring status. In the censoring status vector, 1 = event occurred, 0 = censored.

normalization

A character string, "combat" or "zscore".

method

A character string specifying the feature selection method: "none" for top-ranking or one of the adjusting methods specified by the p.adjust function.

gn.nb

Number of genes to select for gene signature when method="none".

perf.eval

A string taking one the values, "auc", "cindex", "bsc".

Value

AUC, HR(CI) and p-value.

Details

If the user wants to apply his own feature selection method, he should define his function with the same number of parameters as the defined feature selection function of the package, i.e. featureselection.

The p.adjust function in the R stats package is used and all adjusted p-values not greater than 0.05 are retained if method != "none".

If perf.eval == "auc", time-dependent AUC and hazard ratio are used as the measure of performance, perf.eval == "cindex", concordance index defined in the survcomp package or perf.eval == "bsc", brier score defined in the survcomp package is used.

References

Yasrebi H, Sperisen P, Praz V, Bucher P, 2009 Can Survival Prediction Be Improved By Merging Gene Expression Data Sets?. PLoS ONE 4(10): e7431. doi:10.1371/journal.pone.0007431.

See Also

znorm, ComBat

Examples

require(survJamda.data)

data(gse4335)
data(gse3143)
data(gse1992)

data(gse4335pheno)
data(gse3143pheno)
data(gse1992pheno)

geno.files = c("gse4335", "gse3143","gse1992")
surv.data = list(c(gse4335pheno[,6],gse3143pheno[,4],gse1992pheno[,19]),
                 c(gse4335pheno[,5],gse3143pheno[,3],gse1992pheno[,18]))

#The following script might  take some time
#main.single.indep.valid(geno.files, surv.data)
## The function is currently defined as
function(geno.files, surv.data,normalization = "zscore", method = "none", perf.eval = "auc")
{
       require(survival)
       require(survivalROC)
        
       if (!is.element(normalization, c("zscore","combat")))
                stop("\rnormalization = \"zscore\" or normalization = \"combat\"", 
                call.=FALSE)
	
       if(normalization == "combat")
                batchID = det.batchID()
  
        for (i in 1:length(geno.files)){
              for (j in 1:length(geno.files))
                     if (i != j){	
                            common.gene = intersect(colnames(get(geno.files[i])), 
                            colnames(get(geno.files[j])))
                            ds1 = excl.missing.single.indep(geno.files[i],
                            surv.data,common.gene)
                            ds2 = excl.missing.single.indep(geno.files[j],
                            surv.data,common.gene)
                            if (normalization == "combat")
                                   mat = prepcombat.single.indep(ds1$mat,ds2$mat)
                            else
                                   mat = prepzscore(ds1$mat,ds2$mat)	
				
                            i.adj = mat[1:nrow(ds1$mat),]
                            j.adj = mat[(nrow(ds1$mat)+1):nrow(mat),]
                            cat ("Train data set: ", geno.files[j], " Test data set: ", 
                            geno.files[i], "\n")
                            calPerformance.single.indep(list(mat=j.adj,phyno=ds2$phyno,perf.eval),
                            list(mat=i.adj,phyno=ds1$phyno), method=method,perf.eval)
                     }
       }
}