Mercurial > repos > davidvanzessen > argalaxy_tools

comparison igblast/igblast.r @ 0:afe85eb6572e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Mon, 29 Aug 2016 05:41:20 -0400
parents
children 124b7fd92a3e
comparison
equal deleted inserted replaced
-1:000000000000 0:afe85eb6572e
1 args <- commandArgs(trailingOnly = TRUE)
2
3 infile=args[1]
4 outfile=args[2]
5
6 blasted = read.table(infile, header=T, sep="\t", fill=T, stringsAsFactors=F, comment.char="")
7
8 blasted$ID = 1:nrow(blasted)
9 blasted$VDJ.Frame = "Out-of-frame"
10
11 search = blasted$inFrame == "true" & blasted$noStop == "false"
12 if(sum(search) > 0){
13 blasted[search ,]$VDJ.Frame = "In-frame with stop codon"
14 }
15
16 search = blasted$inFrame == "true" & blasted$noStop == "true"
17 if(sum(search) > 0){
18 blasted[search ,]$VDJ.Frame = "In-frame"
19 }
20
21 blasted$Top.V.Gene = blasted$vSegment
22 blasted$Top.D.Gene = blasted$dSegment
23 blasted$Top.J.Gene = blasted$jSegment
24 blasted$CDR1.Seq = blasted$cdr1aa
25 blasted$CDR1.Length = nchar(blasted$CDR1.Seq)
26 blasted$CDR2.Seq = blasted$cdr2aa
27 blasted$CDR2.Length = nchar(blasted$CDR2.Seq)
28 blasted$CDR3.Seq = blasted$cdr3aa
29 blasted$CDR3.Length = nchar(blasted$CDR3.Seq)
30 blasted$CDR3.Seq.DNA = blasted$cdr3nt
31 blasted$CDR3.Length.DNA = nchar(blasted$CDR3.Seq.DNA)
32 blasted$Strand = "+/-"
33 blasted$CDR3.Found.How = "found"
34
35 search = blasted$cdr3nt == ""
36 if(sum(search) > 0){
37 blasted[search,]$CDR3.Found.How = "NOT_FOUND"
38 }
39
40 blasted$AA.JUNCTION = blasted$CDR3.Seq
41
42 n = c("X.reads_count", "ID", "VDJ.Frame", "Top.V.Gene", "Top.D.Gene", "Top.J.Gene", "CDR1.Seq", "CDR1.Length", "CDR2.Seq", "CDR2.Length", "CDR3.Seq", "CDR3.Length", "CDR3.Seq.DNA", "CDR3.Length.DNA", "Strand", "CDR3.Found.How", "Functionality", "AA.JUNCTION")
43
44 n[!(n %in% names(blasted))]
45
46 blasted = blasted[,c("X.reads_count", "ID", "VDJ.Frame", "Top.V.Gene", "Top.D.Gene", "Top.J.Gene", "CDR1.Seq", "CDR1.Length", "CDR2.Seq", "CDR2.Length", "CDR3.Seq", "CDR3.Length", "CDR3.Seq.DNA", "CDR3.Length.DNA", "Strand", "CDR3.Found.How", "AA.JUNCTION")]
47
48 names(blasted) = c("frequency.count", "ID", "VDJ Frame", "Top V Gene", "Top D Gene", "Top J Gene", "CDR1 Seq", "CDR1 Length", "CDR2 Seq", "CDR2 Length", "CDR3 Seq", "CDR3 Length", "CDR3 Seq DNA", "CDR3 Length DNA", "Strand", "CDR3 Found How", "AA JUNCTION")
49
50 #duplicate rows based on frequency.count
51 blasted = blasted[rep(seq_len(nrow(blasted)), blasted$frequency.count),]
52 blasted$ID = 1:nrow(blasted)
53
54 blasted = blasted[,c("ID", "VDJ Frame", "Top V Gene", "Top D Gene", "Top J Gene", "CDR1 Seq", "CDR1 Length", "CDR2 Seq", "CDR2 Length", "CDR3 Seq", "CDR3 Length", "CDR3 Seq DNA", "CDR3 Length DNA", "Strand", "CDR3 Found How", "AA JUNCTION")]
55
56 write.table(blasted, outfile, quote=F, sep="\t", row.names=F, col.names=T)