Mercurial > repos > davidvanzessen > baseline_bayesian_estimation
comparison filter.r @ 3:38c038c17d0c draft
Uploaded
| author | davidvanzessen |
|---|---|
| date | Wed, 13 Aug 2014 09:07:54 -0400 |
| parents | |
| children | d8de51314d3f |
comparison
equal
deleted
inserted
replaced
| 2:94fada165724 | 3:38c038c17d0c |
|---|---|
| 1 arg = commandArgs(TRUE) | |
| 2 summaryfile = arg[1] | |
| 3 gappedfile = arg[2] | |
| 4 selection = arg[3] | |
| 5 output = arg[4] | |
| 6 print(paste("-----", selection, "------")) | |
| 7 | |
| 8 summarydat = read.table(summaryfile, header=T, sep="\t", fill=T, stringsAsFactors=F)[,c("Sequence.ID", "AA.JUNCTION")] | |
| 9 gappeddat = read.table(gappedfile, header=T, sep="\t", fill=T, stringsAsFactors=F) | |
| 10 head(summarydat) | |
| 11 head(gappeddat) | |
| 12 | |
| 13 dat = merge(gappeddat, summarydat, by="Sequence.ID") | |
| 14 head(dat) | |
| 15 | |
| 16 dat$VGene = gsub("^Homsap ", "", dat$V.GENE.and.allele) | |
| 17 dat$VGene = gsub("[*].*", "", dat$VGene) | |
| 18 | |
| 19 dat$DGene = gsub("^Homsap ", "", dat$D.GENE.and.allele) | |
| 20 dat$DGene = gsub("[*].*", "", dat$DGene) | |
| 21 | |
| 22 dat$JGene = gsub("^Homsap ", "", dat$J.GENE.and.allele) | |
| 23 dat$JGene = gsub("[*].*", "", dat$JGene) | |
| 24 | |
| 25 dat$past = do.call(paste, c(dat[unlist(strsplit(selection, ","))], sep = ":")) | |
| 26 | |
| 27 dat = dat[!duplicated(dat$past), ] | |
| 28 | |
| 29 write.table(x=dat, file=output, sep="\t",quote=F,row.names=F,col.names=T) |