comparison imgt_loader/imgt_loader.r @ 0:afe85eb6572e draft

Uploaded
author davidvanzessen
date Mon, 29 Aug 2016 05:41:20 -0400
parents
children 9185c3dfc679
comparison
equal deleted inserted replaced
-1:000000000000 0:afe85eb6572e
1 args <- commandArgs(trailingOnly = TRUE)
2
3 summ.file = args[1]
4 aa.file = args[2]
5 junction.file = args[3]
6 out.file = args[4]
7
8 summ = read.table(summ.file, sep="\t", header=T, quote="", fill=T)
9 aa = read.table(aa.file, sep="\t", header=T, quote="", fill=T)
10 junction = read.table(junction.file, sep="\t", header=T, quote="", fill=T)
11
12 old_summary_columns=c('Sequence.ID','JUNCTION.frame','V.GENE.and.allele','D.GENE.and.allele','J.GENE.and.allele','CDR1.IMGT.length','CDR2.IMGT.length','CDR3.IMGT.length','Orientation')
13 old_sequence_columns=c('CDR1.IMGT','CDR2.IMGT','CDR3.IMGT')
14 old_junction_columns=c('JUNCTION')
15
16 added_summary_columns=c('Functionality','V.REGION.identity..','V.REGION.identity.nt','D.REGION.reading.frame','AA.JUNCTION','Functionality.comment','Sequence')
17 added_sequence_columns=c('FR1.IMGT','FR2.IMGT','FR3.IMGT','CDR3.IMGT','JUNCTION','J.REGION','FR4.IMGT')
18
19 added_junction_columns=c('P3.V.nt.nb','N.REGION.nt.nb','N1.REGION.nt.nb','P5.D.nt.nb','P3.D.nt.nb','N2.REGION.nt.nb','P5.J.nt.nb','X3.V.REGION.trimmed.nt.nb','X5.D.REGION.trimmed.nt.nb','X3.D.REGION.trimmed.nt.nb','X5.J.REGION.trimmed.nt.nb','N.REGION','N1.REGION','N2.REGION')
20 added_junction_columns=c(added_junction_columns, 'P5.D1.nt.nb', 'P3.D1.nt.nb', 'N2.REGION.nt.nb', 'P5.D2.nt.nb', 'P3.D2.nt.nb', 'N3.REGION.nt.nb', 'P5.D3.nt.nb', 'P3.D2.nt.nb', 'N4.REGION.nt.nb', 'X5.D1.REGION.trimmed.nt.nb', 'X3.D1.REGION.trimmed.nt.nb', 'X5.D2.REGION.trimmed.nt.nb', 'X3.D2.REGION.trimmed.nt.nb', 'X5.D3.REGION.trimmed.nt.nb', 'X3.D3.REGION.trimmed.nt.nb', 'D.REGION.nt.nb', 'D1.REGION.nt.nb', 'D2.REGION.nt.nb', 'D3.REGION.nt.nb')
21
22 out=summ[,c("Sequence.ID","JUNCTION.frame","V.GENE.and.allele","D.GENE.and.allele","J.GENE.and.allele")]
23
24 out[,"CDR1.Seq"] = aa[,"CDR1.IMGT"]
25 out[,"CDR1.Length"] = summ[,"CDR1.IMGT.length"]
26
27 out[,"CDR2.Seq"] = aa[,"CDR2.IMGT"]
28 out[,"CDR2.Length"] = summ[,"CDR2.IMGT.length"]
29
30 out[,"CDR3.Seq"] = aa[,"CDR3.IMGT"]
31 out[,"CDR3.Length"] = summ[,"CDR3.IMGT.length"]
32
33 out[,"CDR3.Seq.DNA"] = junction[,"JUNCTION"]
34 out[,"CDR3.Length.DNA"] = nchar(as.character(junction[,"JUNCTION"]))
35 out[,"Strand"] = summ[,"Orientation"]
36 out[,"CDR3.Found.How"] = "a"
37
38 out[,added_summary_columns] = summ[,added_summary_columns]
39
40 out[,added_sequence_columns] = aa[,added_sequence_columns]
41
42 out[,added_junction_columns] = junction[,added_junction_columns]
43
44 out[,"Top V Gene"] = gsub(".* ", "", gsub("\\*.*", "", summ[,"V.GENE.and.allele"]))
45 out[,"Top D Gene"] = gsub(".* ", "", gsub("\\*.*", "", summ[,"D.GENE.and.allele"]))
46 out[,"Top J Gene"] = gsub(".* ", "", gsub("\\*.*", "", summ[,"J.GENE.and.allele"]))
47
48 out = out[!grepl("Less than", summ[,"V.GENE.and.allele"]),]
49 out = out[!grepl("Less than", summ[,"D.GENE.and.allele"]),]
50 out = out[!grepl("Less than", summ[,"J.GENE.and.allele"]),]
51
52 out = out[,c('Sequence.ID','JUNCTION.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','V.REGION.identity..','V.REGION.identity.nt','D.REGION.reading.frame','AA.JUNCTION','Functionality.comment','Sequence','FR1.IMGT','FR2.IMGT','FR3.IMGT','CDR3.IMGT','JUNCTION','J.REGION','FR4.IMGT','P3.V.nt.nb','N.REGION.nt.nb','N1.REGION.nt.nb','P5.D.nt.nb','P3.D.nt.nb','N2.REGION.nt.nb','P5.J.nt.nb','X3.V.REGION.trimmed.nt.nb','X5.D.REGION.trimmed.nt.nb','X3.D.REGION.trimmed.nt.nb','X5.J.REGION.trimmed.nt.nb','N.REGION','N1.REGION','N2.REGION', 'P5.D1.nt.nb', 'P3.D1.nt.nb', 'N2.REGION.nt.nb', 'P5.D2.nt.nb', 'P3.D2.nt.nb', 'N3.REGION.nt.nb', 'P5.D3.nt.nb', 'P3.D2.nt.nb', 'N4.REGION.nt.nb', 'X5.D1.REGION.trimmed.nt.nb', 'X3.D1.REGION.trimmed.nt.nb', 'X5.D2.REGION.trimmed.nt.nb', 'X3.D2.REGION.trimmed.nt.nb', 'X5.D3.REGION.trimmed.nt.nb', 'X3.D3.REGION.trimmed.nt.nb', 'D.REGION.nt.nb', 'D1.REGION.nt.nb', 'D2.REGION.nt.nb', 'D3.REGION.nt.nb')]
53
54 names(out) = 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','Functionality','V-REGION identity %','V-REGION identity nt','D-REGION reading frame','AA JUNCTION','Functionality comment','Sequence','FR1-IMGT','FR2-IMGT','FR3-IMGT','CDR3-IMGT','JUNCTION','J-REGION','FR4-IMGT','P3V-nt nb','N-REGION-nt nb','N1-REGION-nt nb','P5D-nt nb','P3D-nt nb','N2-REGION-nt nb','P5J-nt nb','3V-REGION trimmed-nt nb','5D-REGION trimmed-nt nb','3D-REGION trimmed-nt nb','5J-REGION trimmed-nt nb','N-REGION','N1-REGION','N2-REGION', 'P5.D1.nt.nb', 'P3.D1.nt.nb', 'N2.REGION.nt.nb', 'P5.D2.nt.nb', 'P3.D2.nt.nb', 'N3.REGION.nt.nb', 'P5.D3.nt.nb', 'P3.D2.nt.nb', 'N4.REGION.nt.nb', 'X5.D1.REGION.trimmed.nt.nb', 'X3.D1.REGION.trimmed.nt.nb', 'X5.D2.REGION.trimmed.nt.nb', 'X3.D2.REGION.trimmed.nt.nb', 'X5.D3.REGION.trimmed.nt.nb', 'X3.D3.REGION.trimmed.nt.nb', 'D.REGION.nt.nb', 'D1.REGION.nt.nb', 'D2.REGION.nt.nb', 'D3.REGION.nt.nb')
55
56 out[,"VDJ Frame"] = as.character(out[,"VDJ Frame"])
57
58 fltr = out[,"VDJ Frame"] == "in-frame"
59 if(any(fltr)){
60 out[fltr, "VDJ Frame"] = "In-frame"
61 }
62
63 fltr = out[,"VDJ Frame"] == "null"
64 if(any(fltr)){
65 out[fltr, "VDJ Frame"] = "Out-of-frame"
66 }
67
68 fltr = out[,"VDJ Frame"] == "out-of-frame"
69 if(any(fltr)){
70 out[fltr, "VDJ Frame"] = "Out-of-frame"
71 }
72
73 fltr = out[,"VDJ Frame"] == ""
74 if(any(fltr)){
75 out[fltr, "VDJ Frame"] = "Out-of-frame"
76 }
77
78 for(col in c('Top V Gene','Top D Gene','Top J Gene')){
79 out[,col] = as.character(out[,col])
80 fltr = out[,col] == ""
81 fltr[is.na(fltr)] = T
82 if(any(fltr)){
83 out[fltr,col] = "NA"
84 }
85 }
86
87 write.table(out, out.file, sep="\t", quote=F, row.names=F, col.names=T)