Mercurial > repos > rhpvorderman > shm_csr
comparison imgt_loader.r @ 0:64d74ba01a7c draft
"planemo upload commit 78d1fae87dbcf490e49a9f99e7a06de7328e16d4"
| author | rhpvorderman |
|---|---|
| date | Wed, 27 Oct 2021 12:34:47 +0000 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:64d74ba01a7c |
|---|---|
| 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 fix_column_names = function(df){ | |
| 13 if("V.DOMAIN.Functionality" %in% names(df)){ | |
| 14 names(df)[names(df) == "V.DOMAIN.Functionality"] = "Functionality" | |
| 15 print("found V.DOMAIN.Functionality, changed") | |
| 16 } | |
| 17 if("V.DOMAIN.Functionality.comment" %in% names(df)){ | |
| 18 names(df)[names(df) == "V.DOMAIN.Functionality.comment"] = "Functionality.comment" | |
| 19 print("found V.DOMAIN.Functionality.comment, changed") | |
| 20 } | |
| 21 return(df) | |
| 22 } | |
| 23 | |
| 24 summ = fix_column_names(summ) | |
| 25 aa = fix_column_names(aa) | |
| 26 junction = fix_column_names(junction) | |
| 27 | |
| 28 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') | |
| 29 old_sequence_columns=c('CDR1.IMGT','CDR2.IMGT','CDR3.IMGT') | |
| 30 old_junction_columns=c('JUNCTION') | |
| 31 | |
| 32 added_summary_columns=c('Functionality','V.REGION.identity..','V.REGION.identity.nt','D.REGION.reading.frame','AA.JUNCTION','Functionality.comment','Sequence') | |
| 33 added_sequence_columns=c('FR1.IMGT','FR2.IMGT','FR3.IMGT','CDR3.IMGT','JUNCTION','J.REGION','FR4.IMGT') | |
| 34 | |
| 35 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') | |
| 36 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') | |
| 37 | |
| 38 out=summ[,c("Sequence.ID","JUNCTION.frame","V.GENE.and.allele","D.GENE.and.allele","J.GENE.and.allele")] | |
| 39 | |
| 40 out[,"CDR1.Seq"] = aa[,"CDR1.IMGT"] | |
| 41 out[,"CDR1.Length"] = summ[,"CDR1.IMGT.length"] | |
| 42 | |
| 43 out[,"CDR2.Seq"] = aa[,"CDR2.IMGT"] | |
| 44 out[,"CDR2.Length"] = summ[,"CDR2.IMGT.length"] | |
| 45 | |
| 46 out[,"CDR3.Seq"] = aa[,"CDR3.IMGT"] | |
| 47 out[,"CDR3.Length"] = summ[,"CDR3.IMGT.length"] | |
| 48 | |
| 49 out[,"CDR3.Seq.DNA"] = junction[,"JUNCTION"] | |
| 50 out[,"CDR3.Length.DNA"] = nchar(as.character(junction[,"JUNCTION"])) | |
| 51 out[,"Strand"] = summ[,"Orientation"] | |
| 52 out[,"CDR3.Found.How"] = "a" | |
| 53 | |
| 54 out[,added_summary_columns] = summ[,added_summary_columns] | |
| 55 | |
| 56 out[,added_sequence_columns] = aa[,added_sequence_columns] | |
| 57 | |
| 58 out[,added_junction_columns] = junction[,added_junction_columns] | |
| 59 | |
| 60 out[,"Top V Gene"] = gsub(".* ", "", gsub("\\*.*", "", summ[,"V.GENE.and.allele"])) | |
| 61 out[,"Top D Gene"] = gsub(".* ", "", gsub("\\*.*", "", summ[,"D.GENE.and.allele"])) | |
| 62 out[,"Top J Gene"] = gsub(".* ", "", gsub("\\*.*", "", summ[,"J.GENE.and.allele"])) | |
| 63 | |
| 64 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')] | |
| 65 | |
| 66 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') | |
| 67 | |
| 68 out[,"VDJ Frame"] = as.character(out[,"VDJ Frame"]) | |
| 69 | |
| 70 fltr = out[,"VDJ Frame"] == "in-frame" | |
| 71 if(any(fltr, na.rm = T)){ | |
| 72 out[fltr, "VDJ Frame"] = "In-frame" | |
| 73 } | |
| 74 | |
| 75 fltr = out[,"VDJ Frame"] == "null" | |
| 76 if(any(fltr, na.rm = T)){ | |
| 77 out[fltr, "VDJ Frame"] = "Out-of-frame" | |
| 78 } | |
| 79 | |
| 80 fltr = out[,"VDJ Frame"] == "out-of-frame" | |
| 81 if(any(fltr, na.rm = T)){ | |
| 82 out[fltr, "VDJ Frame"] = "Out-of-frame" | |
| 83 } | |
| 84 | |
| 85 fltr = out[,"VDJ Frame"] == "" | |
| 86 if(any(fltr, na.rm = T)){ | |
| 87 out[fltr, "VDJ Frame"] = "Out-of-frame" | |
| 88 } | |
| 89 | |
| 90 for(col in c('Top V Gene','Top D Gene','Top J Gene')){ | |
| 91 out[,col] = as.character(out[,col]) | |
| 92 fltr = out[,col] == "" | |
| 93 if(any(fltr, na.rm = T)){ | |
| 94 out[fltr,col] = "NA" | |
| 95 } | |
| 96 } | |
| 97 | |
| 98 write.table(out, out.file, sep="\t", quote=F, row.names=F, col.names=T) |
