simulatorZ (version 1.6.0)

simBootstrap: simBootstrap

Description

the driver function to perform three-step bootstrap resampling

to get independent genomic data sets

Usage

simBootstrap(obj, y.vars, n.samples, parstep, type = "two-steps", 
 balance.variables = NULL, funSimData = simData, funTrueModel = getTrueModel, 
 funSurvTime = simTime)

Arguments

obj

a list of ExpressionSet, matrix or RangedSummarizedExperiment

y.vars

a list of reponse variables, elements can be class Surv, matrix or data.frame

n.samples

number of samples to resample in each set

parstep

step number to fit CoxBoost

type

whether to include resampling set labels

balance.variables

covariate names to balance in the simulated sets

funSimData

function to perform non-parametric bootstrap

funTrueModel

function to construct true models in original sets

funSurvTime

function to perform parametric bootstrap

Value

obj.list = a list of simulated objects the same type as inputindices.list = a list of indices indicating which sample the simulated sample is in theoriginal setsetsID = a vector to indicate the original ID of simulated sets, iftype=="original", setsID should be 1,2,3,...lp.list = a list of true linear predictor of each original data setsbeta.list = a list of true coefficients used for simulating observationssurvH.list = list of cumulative survival hazardcensH.list = list of cumulative censoring hazardgrid.list = list of timeline grid corresponding to survH and censH respectivley

Examples

library(curatedOvarianData)


library(GenomicRanges)


data(GSE17260_eset)


data(E.MTAB.386_eset)


data(GSE14764_eset)


esets <- list(GSE17260=GSE17260_eset, E.MTAB.386=E.MTAB.386_eset, GSE14764=GSE14764_eset)


esets.list <- lapply(esets, function(eset){


  return(eset[1:500, 1:20])


})





## simulate on multiple ExpressionSets


set.seed(8) 





y.list <- lapply(esets.list, function(eset){


  time <- eset$days_to_death


  cens.chr <- eset$vital_status


  cens <- c()


  for(i in seq_along(cens.chr)){


    if(cens.chr[i] == "living") cens[i] <- 1


    else cens[i] <- 0


  }


  y <- Surv(time, cens)


  return(y)


})





simmodels <- simBootstrap(obj=esets.list, y.vars=y.list, 10, 100)


simmodels$obj.list[[1]]





# balance covariates


simmodels <- simBootstrap(obj=esets.list, y.vars=y.list, 10, 100,


                          balance.variables="tumorstage")





## Support RangedSummarizedExperiment


nrows <- 200; ncols <- 10


counts <- matrix(runif(nrows * ncols, 1, 1e4), nrows)


rowRanges <- GRanges(rep(c("chr1", "chr2"), c(50, 150)),


                     IRanges(floor(runif(200, 1e5, 1e6)), width=100),


                     strand=sample(c("+", "-"), 200, TRUE))


colData <- DataFrame(Treatment=rep(c("ChIP", "Input"), 5),


                     row.names=LETTERS[1:10])


sset <- SummarizedExperiment(assays=SimpleList(counts=counts),


                             rowRanges=rowRanges, colData=colData)





s.list <- list(sset[,1:5], sset[,6:10])


time <- c(540, 527, 668, 587, 620, 540, 527, 668, 587, 620)


cens <- c(1, 0, 0, 1, 0, 1, 0, 0, 1, 0)


y.vars <- Surv(time, cens)


y.vars <- list(y.vars[1:5,],y.vars[1:5,])


simmodels <- simBootstrap(obj=s.list, y.vars=y.vars, 100, 100)