computeStat: Compute a test statistic based on smoothed whole-genome...
In bsseq: Analyze, manage and store bisulfite sequencing data

Description Usage Arguments Details Value Author(s) See Also Examples

Compute a test statistic based on smoothed whole-genome bisulfite sequencing data.

1	computeStat(BSseqStat, coef = NULL)

`BSseqStat`	An object of class `BSseqStat`, typically an object returned by `smoothSds(...)` and not constructed by the user.
`coef`	A vector indicating for which coefficients the statistic is to be computed (`coef = NULL` corresponds to testing all coefficients). If the length of the `coef` is 1 then the corresponding t-statistic is computed, otherwise the corresponding F-statistic is computed.

TODO

An object of class BSseqStat. More speciically, the input BSseqStat object with the computed statistics added to the stats slot (accessible with getStats).

Kasper Daniel Hansen khansen@jhsph.edu

smoothSds for the function to create the appropriate BSseqStat input object. BSseqStat also describes the return class. This function is likely to be followed by the use of dmrFinder.

  
    if(require(bsseqData)) {
        data(keepLoci.ex)
        data(BS.cancer.ex.fit)
        BS.cancer.ex.fit <- updateObject(BS.cancer.ex.fit)
        ## Remember to subset the BSseq object, see vignette for explanation
        ## TODO: Kind of a forced example
        design <- model.matrix(~0 + BS.cancer.ex.fit$Type)
        colnames(design) <- gsub("BS\\.cancer\\.ex\\.fit\\$Type", "",
                                 colnames(design))
        contrasts <- makeContrasts(
            cancer_vs_normal = cancer - normal,
            levels = design
        )
        BS.stat <- BSmooth.fstat(BS.cancer.ex.fit[keepLoci.ex,],
                                  design,
                                  contrasts)
        BS.stat <- smoothSds(BS.stat)
        BS.stat <- computeStat(BS.stat)
        BS.stat
    }