HIBAG (version 1.8.3)

hlaPredMerge: Merge prediction results from multiple HIBAG models

Description

Return an object of hlaAlleleClass, which contains predicted HLA types.

Usage

hlaPredMerge(..., weight=NULL, equivalence=NULL)

Arguments

...

The object(s) of hlaAlleleClass, having a field of 'postprob', and returned by predict(..., type="response+prob", vote="majority")

weight

the weight used for each prediction; if NULL, equal weights

equivalence

a data.frame with two columns, the first column for new equivalent alleles, and the second for the alleles possibly existed in the object(s) passed to this function

Value

Return a hlaAlleleClass object.

Details

Calculate a new probability matrix for each pair of HLA alleles, by averaging (posterior) probabilities from all models with specified weights. If equivalence is specified, multiple alleles might be collapsed into one class.

See Also

hlaAttrBagging, hlaAllele, predict.hlaAttrBagClass

Examples

# make a "hlaAlleleClass" object
hla.id <- "A"
hla <- hlaAllele(HLA_Type_Table$sample.id,
    H1 = HLA_Type_Table[, paste(hla.id, ".1", sep="")],
    H2 = HLA_Type_Table[, paste(hla.id, ".2", sep="")],
    locus=hla.id, assembly="hg19")

# divide HLA types randomly
set.seed(100)
hlatab <- hlaSplitAllele(hla, train.prop=0.5)
names(hlatab)
# "training"   "validation"
summary(hlatab$training)
summary(hlatab$validation)

# SNP predictors within the flanking region on each side
region <- 500   # kb
snpid <- hlaFlankingSNP(HapMap_CEU_Geno$snp.id, HapMap_CEU_Geno$snp.position,
    hla.id, region*1000, assembly="hg19")
length(snpid)  # 275

# training and validation genotypes
train.geno <- hlaGenoSubset(HapMap_CEU_Geno,
    snp.sel=match(snpid, HapMap_CEU_Geno$snp.id),
    samp.sel=match(hlatab$training$value$sample.id,
    HapMap_CEU_Geno$sample.id))
test.geno <- hlaGenoSubset(HapMap_CEU_Geno,
    samp.sel=match(hlatab$validation$value$sample.id,
    HapMap_CEU_Geno$sample.id))

# train HIBAG models
set.seed(100)

# please use "nclassifier=100" when you use HIBAG for real data
m1 <- hlaAttrBagging(hlatab$training, train.geno, nclassifier=2,
    verbose.detail=TRUE)
m2 <- hlaAttrBagging(hlatab$training, train.geno, nclassifier=2,
    verbose.detail=TRUE)


# validation
pd1 <- predict(m1, test.geno, type="response+prob", vote="majority")
pd2 <- predict(m2, test.geno, type="response+prob", vote="majority")

hlaCompareAllele(hlatab$validation, pd1)$overall

hlaCompareAllele(hlatab$validation, pd2)$overall


# merge predictions from multiple models, by voting from all classifiers
pd <- hlaPredMerge(pd1, pd2, weight=c(1,1))

hlaCompareAllele(hlatab$validation, pd)$overall