diff filter.r @ 5:d8de51314d3f draft

Uploaded

--- a/filter.r	Wed Aug 13 09:09:56 2014 -0400
+++ b/filter.r	Thu Aug 14 07:17:26 2014 -0400
@@ -1,17 +1,21 @@
-arg = commandArgs(TRUE)                       
+arg = commandArgs(TRUE)
 summaryfile = arg[1]
 gappedfile = arg[2]
 selection = arg[3]
 output = arg[4]
-print(paste("-----", selection, "------"))
+print(paste("selection = ", selection))
 
-summarydat = read.table(summaryfile, header=T, sep="\t", fill=T, stringsAsFactors=F)[,c("Sequence.ID", "AA.JUNCTION")]
+
+summarydat = read.table(summaryfile, header=T, sep="\t", fill=T, stringsAsFactors=F)
 gappeddat = read.table(gappedfile, header=T, sep="\t", fill=T, stringsAsFactors=F)
-head(summarydat)
-head(gappeddat)
+
+
 
-dat = merge(gappeddat, summarydat, by="Sequence.ID")
-head(dat)
+#dat = data.frame(merge(gappeddat, summarydat, by="Sequence.ID", all.x=T))
+
+dat = cbind(gappeddat, summarydat$AA.JUNCTION)
+
+colnames(dat)[length(dat)] = "AA.JUNCTION"
 
 dat$VGene = gsub("^Homsap ", "", dat$V.GENE.and.allele)
 dat$VGene = gsub("[*].*", "", dat$VGene)
@@ -22,6 +26,8 @@
 dat$JGene = gsub("^Homsap ", "", dat$J.GENE.and.allele)
 dat$JGene = gsub("[*].*", "", dat$JGene)
 
+print(str(dat))
+
 dat$past = do.call(paste, c(dat[unlist(strsplit(selection, ","))], sep = ":"))
 
 dat = dat[!duplicated(dat$past), ]