--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/baseline/filter.r	Thu Oct 13 10:52:24 2016 -0400
@@ -0,0 +1,35 @@
+arg = commandArgs(TRUE)
+summaryfile = arg[1]
+gappedfile = arg[2]
+selection = arg[3]
+output = arg[4]
+print(paste("selection = ", selection))
+
+
+summarydat = read.table(summaryfile, header=T, sep="\t", fill=T, stringsAsFactors=F)
+gappeddat = read.table(gappedfile, header=T, sep="\t", fill=T, stringsAsFactors=F)
+
+#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$VGene)
+
+dat$DGene = gsub("^Homsap ", "", dat$D.GENE.and.allele)
+dat$DGene = gsub("[*].*", "", dat$DGene)
+
+dat$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$past), ]
+
+dat = dat[dat$Functionality != "No results" & dat$Functionality != "unproductive",]
+
+write.table(x=dat, file=output, sep="\t",quote=F,row.names=F,col.names=T)