GGtools (version 5.8.0)

collectBest: given a collection of All.cis outputs (cisRun instances) compute FDRs for various filterings

Description

given a collection of All.cis outputs (cisRun instances) compute FDRs for various filterings

Usage

collectBest(fns,  targetname = "harvest",  mafs = c(0.01, 0.02, 0.025, 0.03333, 0.05, 0.075, 0.1),  hidists = c(10000, 25000, 50000, 75000, 1e+05, 250000), interimSaves=FALSE)
collectFiltered( fns, targetname="harvest", mafs = c(.01, .02, .025, .03333, .05, .075, .1), hidists = c(10000, 25000, 50000, 75000, 100000, 250000), filterFun = cis.FDR.filter.best, filtApplier=lapply, interimSaves=FALSE)

Arguments

fns

names of .rda with the cisRun outputs

targetname

basename of rda file to be emitted

mafs

lower bounds on MAF for filtering

hidists

upper bounds on cis radius for filtering

filterFun

function like GGtools:::cis.FDR.filter.best

filtApplier

function like lapply

interimSaves

logical, if TRUE save list at each maf/dist transition

Value

a list of lists is written to disk incrementally, as the job can be long running

Details

pifdr is repeatedly used to generate conditional plugin FDR for different filtering criteria

Examples

## Not run: 
# #
# # contents of fns are two chromsomes of cis runs for CEU
# #
#   fns = dir(system.file("rdas", package="GGtools"), full=TRUE)
#   cc = collectBest(fns, mafs=c(.01, .05), hidists=c(10000, 50000))
#   sapply(cc, sapply, function(x) sum(x$fdr <= 0.01))
# #
# # this tells us which to keep
# #
#   kp = cc[["0.05"]][["50000"]]
#   kp = kp[kp$fdr <= 0.01,]
# #
# # the hits are in the table above; the following function
# # retrieves the initial scores giving rise to the filtered
# # hits
# #
#   pullHits = function(fns, atts) {
#     tmp = lapply(fns, function(x) get(load(x)))
#     kl = lapply(tmp, function(x) paste(names(x), x$snp, sep=":"))
#     attk = paste(atts$genes, atts$bestsnp, sep=":")
#     tmp = lapply(1:length(tmp), function(x) tmp[[x]][ match( attk, kl[[x]], nomatch=0 ) ])
#     curans = do.call(c, lapply(tmp, as, "GRanges"))
#     neword = match( attk, paste(names(curans), curans$snp, sep=":"))
#     newfdr = atts$fdr[neword]
#     curans$fdr = newfdr
#     curans
#     }
#   pullHits( fns, kp )
# #
# #
# #
# #   after executing code in example for All.cis (protected by dontrun)
# #   and running save(f1, file="f1.rda"), the following will work
# # genewise max score
#     cf1 = collectFiltered("f1.rda", mafs=.02, hidists=25000, targetname="gwise")
# # SNPwise scores, all
#     cf2 = collectFiltered("f1.rda", mafs=.02, hidists=25000, targetname="swise",
#          filterFun = cis.FDR.filter.SNPcentric.complete )
# # SNPwise scores, best per SNP when SNP is cis to multiple genes
#     cf3 = collectFiltered("f1.rda", mafs=.02, hidists=25000, targetname="swise2",
#          filterFun = cis.FDR.filter.SNPcentric )
#   ## End(Not run)  # end dontrun