svabaaddon {bapred}

Addon batch effect adjustment using frozen SVA

Description

Performs addon batch effect adjustment using frozen SVA. Takes the output of performing svaba on a training data set and new batch data and correspondingly adjusts the test data to better match the adjusted training data according to the SVA model.

Usage

svabaaddon(params, x)

Arguments

params

object of class svatrain. Contains parameters necessary for addon batch effect adjustment with frozen SVA.

x

matrix. The covariate matrix of the new data. Observations in rows, variables in columns.

Value

The adjusted covariate matrix of the test data.

Note

It is not recommended to perform frozen SVA in cross-study prediction settings, because it assumes similarity between training and test set and has been observed to (strongly) impair prediction performance in cases where this assumption is not given. Given a not too small test set, the following methods are recommended (Hornung et al., 2016): combatba, meancenter, ratioa, ratiog.

Author(s)

Roman Hornung

References

Leek, J. T., Storey, J. D. (2007). Capturing Heterogeneity in Gene Expression Studies by Surrogate Variable Analysis. PLoS Genetics 3:1724-1735, <doi: 10.1371/journal.pgen.0030161>.

Parker, H. S., Bravo, H. C., Leek, J. T. (2014). Removing batch effects for prediction problems with frozen surrogate variable analysis. PeerJ 2:e561, <doi: 10.7717/peerj.561>.

Hornung, R., Causeur, D., Bernau, C., Boulesteix, A.-L. (2017). Improving cross-study prediction through addon batch effect adjustment and addon normalization. Bioinformatics 33(3):397–404, <doi: 10.1093/bioinformatics/btw650>.

Examples

data(autism)

# Random subset of 150 variables:
set.seed(1234)
Xsub <- X[,sample(1:ncol(X), size=150)]

# In cases of batches with more than 20 observations
# select 20 observations at random:
subinds <- unlist(sapply(1:length(levels(batch)), function(x) {
  indbatch <- which(batch==x)
  if(length(indbatch) > 20)
    indbatch <- sort(sample(indbatch, size=20))
  indbatch
}))
Xsub <- Xsub[subinds,]
batchsub <- batch[subinds]
ysub <- y[subinds]



trainind <- which(batchsub %in% c(1,2))

Xsubtrain <- Xsub[trainind,]
ysubtrain <- ysub[trainind]
batchsubtrain <- factor(as.numeric(batchsub[trainind]), levels=c(1,2))


testind <- which(batchsub %in% c(3,4))

Xsubtest <- Xsub[testind,]
ysubtest <- ysub[testind]

batchsubtest <- as.numeric(batchsub[testind])
batchsubtest[batchsubtest==3] <- 1
batchsubtest[batchsubtest==4] <- 2
batchsubtest <- factor(batchsubtest, levels=c(1,2))



params <- svaba(x=Xsubtrain, y=ysubtrain, batch=batchsubtrain)

Xsubtestaddon <- svabaaddon(params, x=Xsubtest)