\name{TopCts} \alias{TopCts} %- Also NEED an '\alias' for EACH other topic documented here. \title{ Get FDR of Top Counts } \description{ } \usage{ TopCts(pvalue, PP = NULL, TrueNames, TopNum) } %- maybe also 'usage' for other objects documented here. \arguments{ \item{pvalue}{ A matrix contains the p values (Posterior probabilities) for each transcript and each method. Rows are for different methods and columns are for different transcripts. } \item{PP}{ The length of PP vector should be the same as the number of columns in pvalue matrix. The value in PP either 0 or 1. If the ith value of PP is 0, it means the ith method (the ith row of pvalue) provided p-values. If the ith value of PP is 1, it means the ith method (the ith row of pvalue) provided posterior probabilities. } \item{TrueNames}{ The names of the transcripts who defined to be DE. } \item{TopNum}{ The number of top counts we are interested in. For example, if TopNum=1000, we'll calculate the FDR's of each method if we pick the top 1, 2, ... 1000 genes. } } \details{ %% ~~ If necessary, more details than the description above ~~ } \value{ A metrix contains the FDR's. } \references{ %% ~put references to the literature/web site here ~ } \author{ %% ~~who you are~~ } \note{ %% ~~further notes~~ } %% ~Make other sections like Warning with \section{Warning }{....} ~ \seealso{ %% ~~objects to See Also as \code{\link{help}}, ~~~ } \examples{ ##---- Should be DIRECTLY executable !! ---- ##-- ==> Define data, use random, ##-- or do help(data=index) for the standard data sets. ## The function is currently defined as function(pvalue, PP=NULL, TrueNames, TopNum){ NumOfMethods=ncol(pvalue) puse=pvalue if(1\%in\%PP)puse[,PP==1]=1-pvalue[,PP==1] #puse.list=data.frame(puse) FD=matrix(rep(0,NumOfMethods*TopNum),ncol=NumOfMethods) # Rank=apply(puse,2,rank) # for(i in 1:TopNum) # FD[i,]=sapply(1:NumOfMethods, function(j)sum(!rownames(Rank)[Rank[,j]<=i]\%in\%TrueNames)) # FD=sapply(1:TopNum, function(i)sapply(1:NumOfMethods, function(j)sum(!rownames(Rank)[Rank[,j]<=i]\%in\%TrueNames))) for (s in 1:NumOfMethods){ tmp=puse[,s] names(tmp)=rownames(puse) sorttmp=sort(tmp) for( c in 2:TopNum) FD[c, s]=FD[(c-1),s]+as.numeric(!names(sorttmp)[c]\%in\%TrueNames) } FD #matplot(TopNum,FD,type="l",ylim=c(0,1),xlab="Top DE selected", ylab="FDR") #legend("rightbottom",col=1:TopNum, lty=1:TopNum, names) } } % Add one or more standard keywords, see file 'KEYWORDS' in the % R documentation directory. \keyword{ ~kwd1 } \keyword{ ~kwd2 }% __ONLY ONE__ keyword per line