setwd("Desktop") annoT=read.table("annoarray.txt") head(annoT) colnames(annoT)<-c("name","symbol","chr","strand","start","end","name2 ","affy","expr") head(annoT) ordering<-as.matrix(annoT[,"expr"]) head(ordering) Top25Expr<-logical(length=nrow(ordering)) head(Top25Expr) peak=read.table("top7000peaks.csv") head(peak) colnames(peak)=c("name") Top25Expr[which(annoT[,"symbol"]==as.character(peak[1,]) | annoT[,"symbol"]==as.character(peak[2,]) |annoT[,"symbol"]==as.character(peak[3,]) | annoT[,"symbol"]==as.character(peak[4,]) | annoT[,"symbol"]==as.character(peak[5,]) | annoT[,"symbol"]==as.character(peak[6,]) | annoT[,"symbol"]==as.character(peak[7,]) | annoT[,"symbol"]==as.character(peak[8,]) ............ )]<-TRUE #The gene names in "top7000peaks.csv" is a subset of "annoarray.txt", what I want to do is to find the gene names that exist in both "annoarray.txt" and "top7000peaks.csv", and return Top25Expr as TRUE(in default it is FALSE): Top25Expr[which(annoT[,"symbol"]==as.character(peak[1,]) | annoT[,"symbol"]==as.character(peak[2,]) |annoT[,"symbol"]==as.character(peak[3,]) | annoT[,"symbol"]==as.character(peak[4,]) | annoT[,"symbol"]==as.character(peak[5,]) | annoT[,"symbol"]==as.character(peak[6,]) | annoT[,"symbol"]==as.character(peak[7,]) | annoT[,"symbol"]==as.character(peak[8,]) ............ )]<-TRUE But there are 901 genes in "top7000peaks.csv", it is not so convenient to do as above until peak[901,], do you know if there is any easier script to do the same thing? Thank you in advance for your help. -- output of sessionInfo(): R version 2.14.1 (2011-12-22) Platform: x86_64-apple-darwin9.8.0/x86_64 (64-bit) locale: [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8 attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] Repitools_1.0.11 loaded via a namespace (and not attached): [1] Biostrings_2.22.0 BSgenome_1.22.0 GenomicRanges_1.6.7 IRanges_1.12.6 -- Sent via the guest posting facility at bioconductor.org.