Mercurial > repos > davidvanzessen > report_clonality_igg

comparison RScript.r @ 11:866d22e60e60 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Thu, 13 Nov 2014 10:33:04 -0500
parents 06777331fbd8
children 50260274967c
comparison
equal deleted inserted replaced
10:06777331fbd8 11:866d22e60e60
1 #options( show.error.messages=F, error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } ) 1 # ---------------------- load/install packages ----------------------
2
3 args <- commandArgs(trailingOnly = TRUE)
4
5 inFile = args[1]
6 outFile = args[2]
7 outDir = args[3]
8 clonalType = args[4]
9 species = args[5]
10 locus = args[6]
11 selection = args[7]
12
13
14 2
15 if (!("gridExtra" %in% rownames(installed.packages()))) { 3 if (!("gridExtra" %in% rownames(installed.packages()))) {
16 install.packages("gridExtra", repos="http://cran.xl-mirror.nl/") 4 install.packages("gridExtra", repos="http://cran.xl-mirror.nl/")
17 } 5 }
18 library(gridExtra) 6 library(gridExtra)
19 if (!("ggplot2" %in% rownames(installed.packages()))) { 7 if (!("ggplot2" %in% rownames(installed.packages()))) {
20 install.packages("ggplot2", repos="http://cran.xl-mirror.nl/") 8 install.packages("ggplot2", repos="http://cran.xl-mirror.nl/")
21 } 9 }
22 require(ggplot2) 10 library(ggplot2)
23 if (!("plyr" %in% rownames(installed.packages()))) { 11 if (!("plyr" %in% rownames(installed.packages()))) {
24 install.packages("plyr", repos="http://cran.xl-mirror.nl/") 12 install.packages("plyr", repos="http://cran.xl-mirror.nl/")
25 } 13 }
26 require(plyr) 14 library(plyr)
27 15
28 if (!("data.table" %in% rownames(installed.packages()))) { 16 if (!("data.table" %in% rownames(installed.packages()))) {
29 install.packages("data.table", repos="http://cran.xl-mirror.nl/") 17 install.packages("data.table", repos="http://cran.xl-mirror.nl/")
30 } 18 }
31 library(data.table) 19 library(data.table)
32 20
33 if (!("reshape2" %in% rownames(installed.packages()))) { 21 if (!("reshape2" %in% rownames(installed.packages()))) {
34 install.packages("reshape2", repos="http://cran.xl-mirror.nl/") 22 install.packages("reshape2", repos="http://cran.xl-mirror.nl/")
35 } 23 }
36 library(reshape2) 24 library(reshape2)
37 25
38 26 # ---------------------- parameters ----------------------
39 test = read.table(inFile, sep="\t", header=TRUE, fill=T, comment.char="") 27
40 28 args <- commandArgs(trailingOnly = TRUE)
41 test = test[test$Sample != "",] 29
42 30 infile = args[1] #path to input file
43 test$Top.V.Gene = gsub("[*]([0-9]+)", "", test$Top.V.Gene) 31 outfile = args[2] #path to output file
44 test$Top.D.Gene = gsub("[*]([0-9]+)", "", test$Top.D.Gene) 32 outdir = args[3] #path to output folder (html/images/data)
45 test$Top.J.Gene = gsub("[*]([0-9]+)", "", test$Top.J.Gene) 33 clonaltype = args[4] #clonaltype definition, or 'none' for no unique filtering
46 34 species = args[5] #human or mouse
47 #test$VDJCDR3 = do.call(paste, c(test[c("Top.V.Gene", "Top.D.Gene", "Top.J.Gene","CDR3.Seq.DNA")], sep = ":")) 35 locus = args[6] # IGH, IGK, IGL, TRB, TRA, TRG or TRD
48 test$VDJCDR3 = do.call(paste, c(test[unlist(strsplit(clonalType, ","))], sep = ":")) 36 filterproductive = ifelse(args[7] == "yes", T, F) #should unproductive sequences be filtered out? (yes/no)
49 37
50 PROD = test[test$VDJ.Frame != "In-frame with stop codon" & test$VDJ.Frame != "Out-of-frame" & test$CDR3.Found.How != "NOT_FOUND" , ] 38 # ---------------------- Data preperation ----------------------
51 if("Functionality" %in% colnames(test)) { 39
52 PROD = test[test$Functionality == "productive" | test$Functionality == "productive (see comment)", ] 40 inputdata = read.table(infile, sep="\t", header=TRUE, fill=T, comment.char="")
53 } 41
54 42 setwd(outdir)
55 NONPROD = test[test$VDJ.Frame == "In-frame with stop codon" | test$VDJ.Frame == "Out-of-frame" | test$CDR3.Found.How == "NOT_FOUND" , ] 43
56 44 # remove weird rows
57 #PRODF = PROD[ -1] 45 inputdata = inputdata[inputdata$Sample != "",]
58 46
59 PRODF = PROD 47 #remove the allele from the V,D and J genes
60 48 inputdata$Top.V.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.V.Gene)
61 #PRODF = unique(PRODF) 49 inputdata$Top.D.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.D.Gene)
62 50 inputdata$Top.J.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.J.Gene)
63 51 inputdata$clonaltype = 1:nrow(inputdata)
64 52 PRODF = inputdata
65 if(selection == "unique"){ 53 if(filterproductive){
66 PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ] 54 if("Functionality" %in% colnames(inputdata)) { # "Functionality" is an IMGT column
67 } 55 PRODF = inputdata[inputdata$Functionality == "productive" | inputdata$Functionality == "productive (see comment)", ]
68 56 } else {
69 PRODFV = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.V.Gene")]) 57 PRODF = inputdata[inputdata$VDJ.Frame != "In-frame with stop codon" & inputdata$VDJ.Frame != "Out-of-frame" & inputdata$CDR3.Found.How != "NOT_FOUND" , ]
70 PRODFV$Length = as.numeric(PRODFV$Length) 58 }
71 Total = 0 59 }
60
61 #remove duplicates based on the clonaltype
62 if(clonaltype != "none"){
63 PRODF$clonaltype = paste(PRODF[,unlist(strsplit(clonalType, ","))], sep=":")
64 PRODF = PRODF[!duplicated(PRODF$clonaltype), ]
65 }
66
67 PRODF$freq = 1
68
69 if(any(grepl(pattern="_", x=PRODF$ID))){ #the frequency can be stored in the ID with the pattern ".*_freq_.*"
70 PRODF$freq = gsub("^[0-9]+_", "", PRODF$ID)
71 PRODF$freq = gsub("_.*", "", PRODF$freq)
72 PRODF$freq = as.numeric(PRODF$freq)
73 if(any(is.na(PRODF$freq))){ #if there was an "_" in the ID, but not the frequency, go back to frequency of 1 for every sequence
74 PRODF$freq = 1
75 }
76 }
77
78
79
80 #write the complete dataset that is left over, will be the input if 'none' for clonaltype and 'no' for filterproductive
81 write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T)
82
83 #write the samples to a file
84 sampleFile <- file("samples.txt")
85 un = unique(inputdata$Sample)
86 un = paste(un, sep="\n")
87 writeLines(un, sampleFile)
88 close(sampleFile)
89
90 # ---------------------- Frequency calculation for V, D and J ----------------------
91
92 PRODFV = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.V.Gene")])
72 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length))) 93 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
73 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE) 94 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
74 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total)) 95 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
75 96
76 PRODFD = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.D.Gene")]) 97 PRODFD = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.D.Gene")])
77 PRODFD$Length = as.numeric(PRODFD$Length)
78 Total = 0
79 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length))) 98 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
80 PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE) 99 PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
81 PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total)) 100 PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))
82 101
83 PRODFJ = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.J.Gene")]) 102 PRODFJ = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.J.Gene")])
84 PRODFJ$Length = as.numeric(PRODFJ$Length)
85 Total = 0
86 Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length))) 103 Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
87 PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE) 104 PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
88 PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total)) 105 PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))
89 106
90 V = c("v.name\tchr.orderV") 107 # ---------------------- Setting up the gene names for the different T/B, human/mouse and locus ----------------------
91 D = c("v.name\tchr.orderD") 108
92 J = c("v.name\tchr.orderJ") 109 V = c("v.name\tchr.orderV\n")
110 D = c("v.name\tchr.orderD\n")
111 J = c("v.name\tchr.orderJ\n")
93 112
94 if(species == "human"){ 113 if(species == "human"){
95 if(locus == "igh"){ 114 if(locus == "trb"){
96 V = c("v.name\tchr.orderV\nIGHV3-74\t1\nIGHV3-73\t2\nIGHV3-72\t3\nIGHV2-70\t4\nIGHV1-69D\t5\nIGHV1-69-2\t6\nIGHV2-70D\t7\nIGHV1-69\t8\nIGHV3-66\t9\nIGHV3-64\t10\nIGHV4-61\t11\nIGHV4-59\t12\nIGHV1-58\t13\nIGHV3-53\t14\nIGHV5-51\t15\nIGHV3-49\t16\nIGHV3-48\t17\nIGHV1-46\t18\nIGHV1-45\t19\nIGHV3-43\t20\nIGHV4-39\t21\nIGHV3-43D\t22\nIGHV4-38-2\t23\nIGHV4-34\t24\nIGHV3-33\t25\nIGHV4-31\t26\nIGHV3-30-5\t27\nIGHV4-30-4\t28\nIGHV3-30-3\t29\nIGHV4-30-2\t30\nIGHV4-30-1\t31\nIGHV3-30\t32\nIGHV4-28\t33\nIGHV2-26\t34\nIGHV1-24\t35\nIGHV3-23D\t36\nIGHV3-23\t37\nIGHV3-21\t38\nIGHV3-20\t39\nIGHV1-18\t40\nIGHV3-15\t41\nIGHV3-13\t42\nIGHV3-11\t43\nIGHV5-10-1\t44\nIGHV3-9\t45\nIGHV1-8\t46\nIGHV3-64D\t47\nIGHV3-7\t48\nIGHV2-5\t49\nIGHV7-4-1\t50\nIGHV4-4\t51\nIGHV1-3\t52\nIGHV1-2\t53\nIGHV6-1\t54") 115 V = c("v.name\tchr.orderV\nTRBV2\t1\nTRBV3-1\t2\nTRBV4-1\t3\nTRBV5-1\t4\nTRBV6-1\t5\nTRBV4-2\t6\nTRBV6-2\t7\nTRBV4-3\t8\nTRBV6-3\t9\nTRBV7-2\t10\nTRBV6-4\t11\nTRBV7-3\t12\nTRBV9\t13\nTRBV10-1\t14\nTRBV11-1\t15\nTRBV10-2\t16\nTRBV11-2\t17\nTRBV6-5\t18\nTRBV7-4\t19\nTRBV5-4\t20\nTRBV6-6\t21\nTRBV5-5\t22\nTRBV7-6\t23\nTRBV5-6\t24\nTRBV6-8\t25\nTRBV7-7\t26\nTRBV6-9\t27\nTRBV7-8\t28\nTRBV5-8\t29\nTRBV7-9\t30\nTRBV13\t31\nTRBV10-3\t32\nTRBV11-3\t33\nTRBV12-3\t34\nTRBV12-4\t35\nTRBV12-5\t36\nTRBV14\t37\nTRBV15\t38\nTRBV16\t39\nTRBV18\t40\nTRBV19\t41\nTRBV20-1\t42\nTRBV24-1\t43\nTRBV25-1\t44\nTRBV27\t45\nTRBV28\t46\nTRBV29-1\t47\nTRBV30\t48")
97 D = c("v.name\tchr.orderD\nIGHD1-7\t1\nIGHD2-8\t2\nIGHD3-9\t3\nIGHD3-10\t4\nIGHD5-12\t5\nIGHD6-13\t6\nIGHD2-15\t7\nIGHD3-16\t8\nIGHD4-17\t9\nIGHD5-18\t10\nIGHD6-19\t11\nIGHD1-20\t12\nIGHD2-21\t13\nIGHD3-22\t14\nIGHD5-24\t15\nIGHD6-25\t16\nIGHD1-26\t17\nIGHD7-27\t18") 116 D = c("v.name\tchr.orderD\nTRBD1\t1\nTRBD2\t2\n")
98 J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6") 117 J = c("v.name\tchr.orderJ\nTRBJ1-1\t1\nTRBJ1-2\t2\nTRBJ1-3\t3\nTRBJ1-4\t4\nTRBJ1-5\t5\nTRBJ1-6\t6\nTRBJ2-1\t7\nTRBJ2-2\t8\nTRBJ2-3\t9\nTRBJ2-4\t10\nTRBJ2-5\t11\nTRBJ2-6\t12\nTRBJ2-7\t13")
99 } else if (locus == "igk"){ 118 } else if (locus == "tra"){
100 V = c("v.name\tchr.orderV\nIGKV3D-7\t1\nIGKV1D-8\t2\nIGKV1D-43\t3\nIGKV3D-11\t4\nIGKV1D-12\t5\nIGKV1D-13\t6\nIGKV3D-15\t7\nIGKV1D-16\t8\nIGKV1D-17\t9\nIGKV3D-20\t10\nIGKV2D-26\t11\nIGKV2D-28\t12\nIGKV2D-29\t13\nIGKV2D-30\t14\nIGKV1D-33\t15\nIGKV1D-39\t16\nIGKV2D-40\t17\nIGKV2-40\t18\nIGKV1-39\t19\nIGKV1-33\t20\nIGKV2-30\t21\nIGKV2-29\t22\nIGKV2-28\t23\nIGKV1-27\t24\nIGKV2-24\t25\nIGKV3-20\t26\nIGKV1-17\t27\nIGKV1-16\t28\nIGKV3-15\t29\nIGKV1-13\t30\nIGKV1-12\t31\nIGKV3-11\t32\nIGKV1-9\t33\nIGKV1-8\t34\nIGKV1-6\t35\nIGKV1-5\t36\nIGKV5-2\t37\nIGKV4-1\t38") 119 V = c("v.name\tchr.orderVTRAV1-1\t1\nTRAV1-2\t2\nTRAV2\t3\nTRAV3\t4\nTRAV4\t5\nTRAV5\t6\nTRAV6\t7\nTRAV7\t8\nTRAV8-1\t9\nTRAV9-1\t10\nTRAV10\t11\nTRAV12-1\t12\nTRAV8-2\t13\nTRAV8-3\t14\nTRAV13-1\t15\nTRAV12-2\t16\nTRAV8-4\t17\nTRAV13-2\t18\nTRAV14/DV4\t19\nTRAV9-2\t20\nTRAV12-3\t21\nTRAV8-6\t22\nTRAV16\t23\nTRAV17\t24\nTRAV18\t25\nTRAV19\t26\nTRAV20\t27\nTRAV21\t28\nTRAV22\t29\nTRAV23/DV6\t30\nTRAV24\t31\nTRAV25\t32\nTRAV26-1\t33\nTRAV27\t34\nTRAV29/DV5\t35\nTRAV30\t36\nTRAV26-2\t37\nTRAV34\t38\nTRAV35\t39\nTRAV36/DV7\t40\nTRAV38-1\t41\nTRAV38-2/DV8\t42\nTRAV39\t43\nTRAV40\t44\nTRAV41\t45\n")
101 D = c("v.name\tchr.orderD\n") 120 D = c("v.name\tchr.orderD\n")
102 J = c("v.name\tchr.orderJ\nIGKJ1\t1\nIGKJ2\t2\nIGKJ3\t3\nIGKJ4\t4\nIGKJ5\t5") 121 J = c("v.name\tchr.orderJ\nTRAJ57\t1\nTRAJ56\t2\nTRAJ54\t3\nTRAJ53\t4\nTRAJ52\t5\nTRAJ50\t6\nTRAJ49\t7\nTRAJ48\t8\nTRAJ47\t9\nTRAJ46\t10\nTRAJ45\t11\nTRAJ44\t12\nTRAJ43\t13\nTRAJ42\t14\nTRAJ41\t15\nTRAJ40\t16\nTRAJ39\t17\nTRAJ38\t18\nTRAJ37\t19\nTRAJ36\t20\nTRAJ34\t21\nTRAJ33\t22\nTRAJ32\t23\nTRAJ31\t24\nTRAJ30\t25\nTRAJ29\t26\nTRAJ28\t27\nTRAJ27\t28\nTRAJ26\t29\nTRAJ24\t30\nTRAJ23\t31\nTRAJ22\t32\nTRAJ21\t33\nTRAJ20\t34\nTRAJ18\t35\nTRAJ17\t36\nTRAJ16\t37\nTRAJ15\t38\nTRAJ14\t39\nTRAJ13\t40\nTRAJ12\t41\nTRAJ11\t42\nTRAJ10\t43\nTRAJ9\t44\nTRAJ8\t45\nTRAJ7\t46\nTRAJ6\t47\nTRAJ5\t48\nTRAJ4\t49\nTRAJ3\t50")
103 } else if (locus == "igl"){ 122 } else if (locus == "trg"){
104 V = c("v.name\tchr.orderV\nIGLV4-69\t1\nIGLV8-61\t2\nIGLV4-60\t3\nIGLV6-57\t4\nIGLV5-52\t5\nIGLV1-51\t6\nIGLV9-49\t7\nIGLV1-47\t8\nIGLV7-46\t9\nIGLV5-45\t10\nIGLV1-44\t11\nIGLV7-43\t12\nIGLV1-41\t13\nIGLV1-40\t14\nIGLV5-39\t15\nIGLV5-37\t16\nIGLV1-36\t17\nIGLV3-27\t18\nIGLV3-25\t19\nIGLV2-23\t20\nIGLV3-22\t21\nIGLV3-21\t22\nIGLV3-19\t23\nIGLV2-18\t24\nIGLV3-16\t25\nIGLV2-14\t26\nIGLV3-12\t27\nIGLV2-11\t28\nIGLV3-10\t29\nIGLV3-9\t30\nIGLV2-8\t31\nIGLV4-3\t32\nIGLV3-1\t33") 123 V = c("v.name\tchr.orderV\nTRGV9\t1\nTRGV8\t2\nTRGV5\t3\nTRGV4\t4\nTRGV3\t5\nTRGV2\t6")
105 D = c("v.name\tchr.orderD\n") 124 D = c("v.name\tchr.orderD\n")
106 J = c("v.name\tchr.orderJ\nIGLJ1\t1\nIGLJ2\t2\nIGLJ3\t3\nIGLJ6\t4\nIGLJ7\t5") 125 J = c("v.name\tchr.orderJ\nTRGJ2\t1\nTRGJP2\t2\nTRGJ1\t3\nTRGJP1\t4")
107 } 126 } else if (locus == "trd"){
127 V = c("v.name\tchr.orderV\nTRDV1\t1\nTRDV2\t2\nTRDV3\t3")
128 D = c("v.name\tchr.orderD\nTRDD1\t1\nTRDD2\t2\nTRDD3\t3")
129 J = c("v.name\tchr.orderJ\nTRDJ1\t1\nTRDJ4\t2\nTRDJ2\t3\nTRDJ3\t4")
130 } else if(locus == "igh"){
131 V = c("v.name\tchr.orderV\nIGHV3-74\t1\nIGHV3-73\t2\nIGHV3-72\t3\nIGHV2-70\t4\nIGHV1-69D\t5\nIGHV1-69-2\t6\nIGHV2-70D\t7\nIGHV1-69\t8\nIGHV3-66\t9\nIGHV3-64\t10\nIGHV4-61\t11\nIGHV4-59\t12\nIGHV1-58\t13\nIGHV3-53\t14\nIGHV5-51\t15\nIGHV3-49\t16\nIGHV3-48\t17\nIGHV1-46\t18\nIGHV1-45\t19\nIGHV3-43\t20\nIGHV4-39\t21\nIGHV3-43D\t22\nIGHV4-38-2\t23\nIGHV4-34\t24\nIGHV3-33\t25\nIGHV4-31\t26\nIGHV3-30-5\t27\nIGHV4-30-4\t28\nIGHV3-30-3\t29\nIGHV4-30-2\t30\nIGHV4-30-1\t31\nIGHV3-30\t32\nIGHV4-28\t33\nIGHV2-26\t34\nIGHV1-24\t35\nIGHV3-23D\t36\nIGHV3-23\t37\nIGHV3-21\t38\nIGHV3-20\t39\nIGHV1-18\t40\nIGHV3-15\t41\nIGHV3-13\t42\nIGHV3-11\t43\nIGHV5-10-1\t44\nIGHV3-9\t45\nIGHV1-8\t46\nIGHV3-64D\t47\nIGHV3-7\t48\nIGHV2-5\t49\nIGHV7-4-1\t50\nIGHV4-4\t51\nIGHV1-3\t52\nIGHV1-2\t53\nIGHV6-1\t54")
132 D = c("v.name\tchr.orderD\nIGHD1-7\t1\nIGHD2-8\t2\nIGHD3-9\t3\nIGHD3-10\t4\nIGHD5-12\t5\nIGHD6-13\t6\nIGHD2-15\t7\nIGHD3-16\t8\nIGHD4-17\t9\nIGHD5-18\t10\nIGHD6-19\t11\nIGHD1-20\t12\nIGHD2-21\t13\nIGHD3-22\t14\nIGHD5-24\t15\nIGHD6-25\t16\nIGHD1-26\t17\nIGHD7-27\t18")
133 J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6")
134 } else if (locus == "igk"){
135 V = c("v.name\tchr.orderV\nIGKV3D-7\t1\nIGKV1D-8\t2\nIGKV1D-43\t3\nIGKV3D-11\t4\nIGKV1D-12\t5\nIGKV1D-13\t6\nIGKV3D-15\t7\nIGKV1D-16\t8\nIGKV1D-17\t9\nIGKV3D-20\t10\nIGKV2D-26\t11\nIGKV2D-28\t12\nIGKV2D-29\t13\nIGKV2D-30\t14\nIGKV1D-33\t15\nIGKV1D-39\t16\nIGKV2D-40\t17\nIGKV2-40\t18\nIGKV1-39\t19\nIGKV1-33\t20\nIGKV2-30\t21\nIGKV2-29\t22\nIGKV2-28\t23\nIGKV1-27\t24\nIGKV2-24\t25\nIGKV3-20\t26\nIGKV1-17\t27\nIGKV1-16\t28\nIGKV3-15\t29\nIGKV1-13\t30\nIGKV1-12\t31\nIGKV3-11\t32\nIGKV1-9\t33\nIGKV1-8\t34\nIGKV1-6\t35\nIGKV1-5\t36\nIGKV5-2\t37\nIGKV4-1\t38")
136 D = c("v.name\tchr.orderD\n")
137 J = c("v.name\tchr.orderJ\nIGKJ1\t1\nIGKJ2\t2\nIGKJ3\t3\nIGKJ4\t4\nIGKJ5\t5")
138 } else if (locus == "igl"){
139 V = c("v.name\tchr.orderV\nIGLV4-69\t1\nIGLV8-61\t2\nIGLV4-60\t3\nIGLV6-57\t4\nIGLV5-52\t5\nIGLV1-51\t6\nIGLV9-49\t7\nIGLV1-47\t8\nIGLV7-46\t9\nIGLV5-45\t10\nIGLV1-44\t11\nIGLV7-43\t12\nIGLV1-41\t13\nIGLV1-40\t14\nIGLV5-39\t15\nIGLV5-37\t16\nIGLV1-36\t17\nIGLV3-27\t18\nIGLV3-25\t19\nIGLV2-23\t20\nIGLV3-22\t21\nIGLV3-21\t22\nIGLV3-19\t23\nIGLV2-18\t24\nIGLV3-16\t25\nIGLV2-14\t26\nIGLV3-12\t27\nIGLV2-11\t28\nIGLV3-10\t29\nIGLV3-9\t30\nIGLV2-8\t31\nIGLV4-3\t32\nIGLV3-1\t33")
140 D = c("v.name\tchr.orderD\n")
141 J = c("v.name\tchr.orderJ\nIGLJ1\t1\nIGLJ2\t2\nIGLJ3\t3\nIGLJ6\t4\nIGLJ7\t5")
142 }
108 } else if (species == "mouse"){ 143 } else if (species == "mouse"){
109 if(locus == "igh"){ 144 if(locus == "trb"){
110 cat("mouse igh not yet implemented") 145 V = c("v.name\tchr.orderV\nTRBV1\t1\nTRBV2\t2\nTRBV3\t3\nTRBV4\t4\nTRBV5\t5\nTRBV12-1\t6\nTRBV13-1\t7\nTRBV12-2\t8\nTRBV13-2\t9\nTRBV13-3\t10\nTRBV14\t11\nTRBV15\t12\nTRBV16\t13\nTRBV17\t14\nTRBV19\t15\nTRBV20\t16\nTRBV23\t17\nTRBV24\t18\nTRBV26\t19\nTRBV29\t20\nTRBV30\t21\nTRBV31\t22")
111 } else if (locus == "igk"){ 146 D = c("v.name\tchr.orderD\nTRBD1\t1\nTRBD2\t2")
112 cat("mouse igk not yet implemented") 147 J = c("v.name\tchr.orderJ\nTRBJ1-1\t1\nTRBJ1-2\t2\nTRBJ1-3\t3\nTRBJ1-4\t4\nTRBJ1-5\t5\nTRBJ2-1\t6\nTRBJ2-2\t7\nTRBJ2-3\t8\nTRBJ2-4\t9\nTRBJ2-5\t10\nTRBJ2-6\t11\nTRBJ2-7\t12")
113 } else if (locus == "igl"){ 148 } else if (locus == "tra"){
114 cat("mouse igl not yet implemented") 149 cat("mouse tra not yet implemented")
115 } 150 } else if (locus == "trg"){
151 cat("mouse trg not yet implemented")
152 } else if (locus == "trd"){
153 cat("mouse trd not yet implemented")
154 } else if(locus == "igh"){
155 cat("mouse igh not yet implemented")
156 } else if (locus == "igk"){
157 cat("mouse igk not yet implemented")
158 } else if (locus == "igl"){
159 cat("mouse igl not yet implemented")
160 }
116 } 161 }
117 162
118 useD = TRUE 163 useD = TRUE
119 if(species == "human" && (locus == "igk" || locus == "igl")){ 164 if(species == "human" && locus == "tra"){
120 useD = FALSE 165 useD = FALSE
121 } 166 cat("No D Genes in this species/locus")
167 }
168
169 # ---------------------- load the gene names into a data.frame and merge with the frequency count ----------------------
122 170
123 tcV = textConnection(V) 171 tcV = textConnection(V)
124 Vchain = read.table(tcV, sep="\t", header=TRUE) 172 Vchain = read.table(tcV, sep="\t", header=TRUE)
125 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE) 173 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
126 close(tcV) 174 close(tcV)
133 tcJ = textConnection(J) 181 tcJ = textConnection(J)
134 Jchain = read.table(tcJ, sep="\t", header=TRUE) 182 Jchain = read.table(tcJ, sep="\t", header=TRUE)
135 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE) 183 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
136 close(tcJ) 184 close(tcJ)
137 185
138 setwd(outDir) 186 # ---------------------- Create the V, D and J frequency plots and write the data.frame for every plot to a file ----------------------
139
140 write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T)
141 187
142 pV = ggplot(PRODFV) 188 pV = ggplot(PRODFV)
143 pV = pV + geom_bar( aes( x=factor(reorder(Top.V.Gene, chr.orderV)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1)) 189 pV = pV + geom_bar( aes( x=factor(reorder(Top.V.Gene, chr.orderV)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
144 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage") 190 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
145 write.table(x=PRODFV, file="VFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) 191 write.table(x=PRODFV, file="VFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
146 192
147 png("VPlot.png",width = 1280, height = 720) 193 png("VPlot.png",width = 1280, height = 720)
148 pV 194 pV
149 dev.off(); 195 dev.off();
150 196
151 pD = ggplot(PRODFD) 197 if(useD){
152 pD = pD + geom_bar( aes( x=factor(reorder(Top.D.Gene, chr.orderD)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1)) 198 pD = ggplot(PRODFD)
153 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage") 199 pD = pD + geom_bar( aes( x=factor(reorder(Top.D.Gene, chr.orderD)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
154 write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) 200 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
155 201 write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
156 png("DPlot.png",width = 800, height = 600) 202
157 pD 203 png("DPlot.png",width = 800, height = 600)
158 dev.off(); 204 print(pD)
205 dev.off();
206 }
159 207
160 pJ = ggplot(PRODFJ) 208 pJ = ggplot(PRODFJ)
161 pJ = pJ + geom_bar( aes( x=factor(reorder(Top.J.Gene, chr.orderJ)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1)) 209 pJ = pJ + geom_bar( aes( x=factor(reorder(Top.J.Gene, chr.orderJ)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
162 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage") 210 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
163 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) 211 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
164 212
165 png("JPlot.png",width = 800, height = 600) 213 png("JPlot.png",width = 800, height = 600)
166 pJ 214 pJ
167 dev.off(); 215 dev.off();
216
217 pJ = ggplot(PRODFJ)
218 pJ = pJ + geom_bar( aes( x=factor(reorder(Top.J.Gene, chr.orderJ)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
219 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
220 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
221
222 png("JPlot.png",width = 800, height = 600)
223 pJ
224 dev.off();
225
226 # ---------------------- Now the frequency plots of the V, D and J families ----------------------
168 227
169 VGenes = PRODF[,c("Sample", "Top.V.Gene")] 228 VGenes = PRODF[,c("Sample", "Top.V.Gene")]
170 VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene) 229 VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene)
171 VGenes = data.frame(data.table(VGenes)[, list(Count=.N), by=c("Sample", "Top.V.Gene")]) 230 VGenes = data.frame(data.table(VGenes)[, list(Count=.N), by=c("Sample", "Top.V.Gene")])
172 TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample]) 231 TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample])
173 VGenes = merge(VGenes, TotalPerSample, by="Sample") 232 VGenes = merge(VGenes, TotalPerSample, by="Sample")
174 VGenes$Frequency = VGenes$Count * 100 / VGenes$total 233 VGenes$Frequency = VGenes$Count * 100 / VGenes$total
175 VPlot = ggplot(VGenes) 234 VPlot = ggplot(VGenes)
176 VPlot = VPlot + geom_bar(aes( x = Top.V.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 235 VPlot = VPlot + geom_bar(aes( x = Top.V.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
177 ggtitle("Distribution of V gene families") + 236 ggtitle("Distribution of V gene families") +
178 ylab("Percentage of sequences") 237 ylab("Percentage of sequences")
179 png("VFPlot.png") 238 png("VFPlot.png")
180 VPlot 239 VPlot
181 dev.off(); 240 dev.off();
182 write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) 241 write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
183 242
184 DGenes = PRODF[,c("Sample", "Top.D.Gene")] 243 if(useD){
185 DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene) 244 DGenes = PRODF[,c("Sample", "Top.D.Gene")]
186 DGenes = data.frame(data.table(DGenes)[, list(Count=.N), by=c("Sample", "Top.D.Gene")]) 245 DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene)
187 TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample]) 246 DGenes = data.frame(data.table(DGenes)[, list(Count=.N), by=c("Sample", "Top.D.Gene")])
188 DGenes = merge(DGenes, TotalPerSample, by="Sample") 247 TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample])
189 DGenes$Frequency = DGenes$Count * 100 / DGenes$total 248 DGenes = merge(DGenes, TotalPerSample, by="Sample")
190 DPlot = ggplot(DGenes) 249 DGenes$Frequency = DGenes$Count * 100 / DGenes$total
191 DPlot = DPlot + geom_bar(aes( x = Top.D.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 250 DPlot = ggplot(DGenes)
192 ggtitle("Distribution of D gene families") + 251 DPlot = DPlot + geom_bar(aes( x = Top.D.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
193 ylab("Percentage of sequences") 252 ggtitle("Distribution of D gene families") +
194 png("DFPlot.png") 253 ylab("Percentage of sequences")
195 DPlot 254 png("DFPlot.png")
196 dev.off(); 255 print(DPlot)
197 write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) 256 dev.off();
257 write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
258 }
198 259
199 JGenes = PRODF[,c("Sample", "Top.J.Gene")] 260 JGenes = PRODF[,c("Sample", "Top.J.Gene")]
200 JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene) 261 JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene)
201 JGenes = data.frame(data.table(JGenes)[, list(Count=.N), by=c("Sample", "Top.J.Gene")]) 262 JGenes = data.frame(data.table(JGenes)[, list(Count=.N), by=c("Sample", "Top.J.Gene")])
202 TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample]) 263 TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample])
203 JGenes = merge(JGenes, TotalPerSample, by="Sample") 264 JGenes = merge(JGenes, TotalPerSample, by="Sample")
204 JGenes$Frequency = JGenes$Count * 100 / JGenes$total 265 JGenes$Frequency = JGenes$Count * 100 / JGenes$total
205 JPlot = ggplot(JGenes) 266 JPlot = ggplot(JGenes)
206 JPlot = JPlot + geom_bar(aes( x = Top.J.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 267 JPlot = JPlot + geom_bar(aes( x = Top.J.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
207 ggtitle("Distribution of J gene families") + 268 ggtitle("Distribution of J gene families") +
208 ylab("Percentage of sequences") 269 ylab("Percentage of sequences")
209 png("JFPlot.png") 270 png("JFPlot.png")
210 JPlot 271 JPlot
211 dev.off(); 272 dev.off();
212 write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) 273 write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
274
275 # ---------------------- Plotting the cdr3 length ----------------------
213 276
214 CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length.DNA")]) 277 CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length.DNA")])
215 TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample]) 278 TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample])
216 CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample") 279 CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample")
217 CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total 280 CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total
218 CDR3LengthPlot = ggplot(CDR3Length) 281 CDR3LengthPlot = ggplot(CDR3Length)
219 CDR3LengthPlot = CDR3LengthPlot + geom_bar(aes( x = CDR3.Length.DNA, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 282 CDR3LengthPlot = CDR3LengthPlot + geom_bar(aes( x = CDR3.Length.DNA, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
220 ggtitle("Length distribution of CDR3") + 283 ggtitle("Length distribution of CDR3") +
221 xlab("CDR3 Length") + 284 xlab("CDR3 Length") +
222 ylab("Percentage of sequences") 285 ylab("Percentage of sequences")
223 png("CDR3LengthPlot.png",width = 1280, height = 720) 286 png("CDR3LengthPlot.png",width = 1280, height = 720)
224 CDR3LengthPlot 287 CDR3LengthPlot
225 dev.off() 288 dev.off()
226 write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T) 289 write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T)
227 290
291 # ---------------------- Plot the heatmaps ----------------------
292
293
294 #get the reverse order for the V and D genes
228 revVchain = Vchain 295 revVchain = Vchain
229 revDchain = Dchain 296 revDchain = Dchain
230 revVchain$chr.orderV = rev(revVchain$chr.orderV) 297 revVchain$chr.orderV = rev(revVchain$chr.orderV)
231 revDchain$chr.orderD = rev(revDchain$chr.orderD) 298 revDchain$chr.orderD = rev(revDchain$chr.orderD)
232 299
233 plotVD <- function(dat){ 300 if(useD){
234 if(length(dat[,1]) == 0){ 301 plotVD <- function(dat){
235 return() 302 if(length(dat[,1]) == 0){
236 } 303 return()
237 img = ggplot() + 304 }
238 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) + 305 img = ggplot() +
239 theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 306 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
240 scale_fill_gradient(low="gold", high="blue", na.value="white") + 307 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
241 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + 308 scale_fill_gradient(low="gold", high="blue", na.value="white") +
242 xlab("D genes") + 309 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
243 ylab("V Genes") 310 xlab("D genes") +
244 311 ylab("V Genes")
245 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name))) 312
246 print(img) 313 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
247 314 print(img)
248 dev.off() 315 dev.off()
249 write.table(x=acast(dat, Top.V.Gene~Top.D.Gene, value.var="Length"), file=paste("HeatmapVD_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA) 316 write.table(x=acast(dat, Top.V.Gene~Top.D.Gene, value.var="Length"), file=paste("HeatmapVD_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
250 } 317 }
251 318
252 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")]) 319 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
253 320
254 VandDCount$l = log(VandDCount$Length) 321 VandDCount$l = log(VandDCount$Length)
255 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")]) 322 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
256 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T) 323 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
257 VandDCount$relLength = VandDCount$l / VandDCount$max 324 VandDCount$relLength = VandDCount$l / VandDCount$max
258 325
259 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(test$Sample)) 326 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(inputdata$Sample))
260 327
261 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE) 328 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
262 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE) 329 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
263 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE) 330 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
264 VDList = split(completeVD, f=completeVD[,"Sample"]) 331 VDList = split(completeVD, f=completeVD[,"Sample"])
265 332
266 lapply(VDList, FUN=plotVD) 333 lapply(VDList, FUN=plotVD)
334 }
267 335
268 plotVJ <- function(dat){ 336 plotVJ <- function(dat){
269 if(length(dat[,1]) == 0){ 337 if(length(dat[,1]) == 0){
270 return() 338 return()
271 } 339 }
272 img = ggplot() + 340 cat(paste(unique(dat[3])[1,1]))
273 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) + 341 img = ggplot() +
274 theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 342 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
275 scale_fill_gradient(low="gold", high="blue", na.value="white") + 343 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
276 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + 344 scale_fill_gradient(low="gold", high="blue", na.value="white") +
277 xlab("J genes") + 345 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
278 ylab("V Genes") 346 xlab("J genes") +
279 347 ylab("V Genes")
280 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name))) 348
281 print(img) 349 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
282 dev.off() 350 print(img)
283 write.table(x=acast(dat, Top.V.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapVJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA) 351 dev.off()
352 write.table(x=acast(dat, Top.V.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapVJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
284 } 353 }
285 354
286 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")]) 355 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
287 356
288 VandJCount$l = log(VandJCount$Length) 357 VandJCount$l = log(VandJCount$Length)
289 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")]) 358 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
290 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T) 359 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
291 VandJCount$relLength = VandJCount$l / VandJCount$max 360 VandJCount$relLength = VandJCount$l / VandJCount$max
292 361
293 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample)) 362 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(inputdata$Sample))
294 363
295 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE) 364 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
296 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE) 365 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
297 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE) 366 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
298 VJList = split(completeVJ, f=completeVJ[,"Sample"]) 367 VJList = split(completeVJ, f=completeVJ[,"Sample"])
299 lapply(VJList, FUN=plotVJ) 368 lapply(VJList, FUN=plotVJ)
300 369
301 plotDJ <- function(dat){ 370 if(useD){
302 if(length(dat[,1]) == 0){ 371 plotDJ <- function(dat){
303 return() 372 if(length(dat[,1]) == 0){
304 } 373 return()
305 img = ggplot() + 374 }
306 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) + 375 img = ggplot() +
307 theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 376 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
308 scale_fill_gradient(low="gold", high="blue", na.value="white") + 377 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
309 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + 378 scale_fill_gradient(low="gold", high="blue", na.value="white") +
310 xlab("J genes") + 379 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
311 ylab("D Genes") 380 xlab("J genes") +
312 381 ylab("D Genes")
313 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name))) 382
314 print(img) 383 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
315 dev.off() 384 print(img)
316 write.table(x=acast(dat, Top.D.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapDJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA) 385 dev.off()
317 } 386 write.table(x=acast(dat, Top.D.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapDJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
318 387 }
319 388
320 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")]) 389
321 390 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
322 DandJCount$l = log(DandJCount$Length) 391
323 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")]) 392 DandJCount$l = log(DandJCount$Length)
324 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T) 393 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
325 DandJCount$relLength = DandJCount$l / DandJCount$max 394 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
326 395 DandJCount$relLength = DandJCount$l / DandJCount$max
327 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample)) 396
328 397 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(inputdata$Sample))
329 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE) 398
330 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE) 399 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
331 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE) 400 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
332 DJList = split(completeDJ, f=completeDJ[,"Sample"]) 401 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
333 lapply(DJList, FUN=plotDJ) 402 DJList = split(completeDJ, f=completeDJ[,"Sample"])
334 403 lapply(DJList, FUN=plotDJ)
335 sampleFile <- file("samples.txt") 404 }
336 un = unique(test$Sample) 405
337 un = paste(un, sep="\n") 406
338 writeLines(un, sampleFile) 407 # ---------------------- calculating the clonality score ----------------------
339 close(sampleFile) 408
340 409 if("Replicate" %in% colnames(inputdata)) #can only calculate clonality score when replicate information is available
341
342 if("Replicate" %in% colnames(test))
343 { 410 {
344 clonalityFrame = PROD 411 clonalityFrame = inputdata
345 clonalityFrame$ReplicateConcat = do.call(paste, c(clonalityFrame[c("VDJCDR3", "Sample", "Replicate")], sep = ":")) 412 if(clonaltype != "none"){
346 clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ] 413 clonalityFrame$ReplicateConcat = paste(clonalityFrame$clonaltype, clonalityFrame$Sample, clonalityFrame$Replicate, sep = ":")
347 write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T) 414 clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ]
348 415 }
349 ClonalitySampleReplicatePrint <- function(dat){ 416 write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T)
350 write.table(dat, paste("clonality_", unique(dat$Sample) , "_", unique(dat$Replicate), ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T) 417
351 } 418 ClonalitySampleReplicatePrint <- function(dat){
352 419 write.table(dat, paste("clonality_", unique(inputdata$Sample) , "_", unique(dat$Replicate), ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
353 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,c("Sample", "Replicate")]) 420 }
354 #lapply(clonalityFrameSplit, FUN=ClonalitySampleReplicatePrint) 421
355 422 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,c("Sample", "Replicate")])
356 ClonalitySamplePrint <- function(dat){ 423 #lapply(clonalityFrameSplit, FUN=ClonalitySampleReplicatePrint)
357 write.table(dat, paste("clonality_", unique(dat$Sample) , ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T) 424
358 } 425 ClonalitySamplePrint <- function(dat){
359 426 write.table(dat, paste("clonality_", unique(inputdata$Sample) , ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
360 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,"Sample"]) 427 }
361 #lapply(clonalityFrameSplit, FUN=ClonalitySamplePrint) 428
362 429 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,"Sample"])
363 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "VDJCDR3")]) 430 #lapply(clonalityFrameSplit, FUN=ClonalitySamplePrint)
364 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")]) 431
365 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count 432 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "clonaltype")])
366 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")]) 433 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
367 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample") 434 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
368 435 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
369 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15') 436 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
370 tcct = textConnection(ct) 437
371 CT = read.table(tcct, sep="\t", header=TRUE) 438 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
372 close(tcct) 439 tcct = textConnection(ct)
373 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T) 440 CT = read.table(tcct, sep="\t", header=TRUE)
374 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight 441 close(tcct)
375 442 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
376 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "VDJCDR3")]) 443 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
377 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")]) 444
378 clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads) 445 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "clonaltype")])
379 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads 446 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
380 447 clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads)
381 ReplicatePrint <- function(dat){ 448 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
382 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F) 449
383 } 450 ReplicatePrint <- function(dat){
384 451 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
385 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"]) 452 }
386 lapply(ReplicateSplit, FUN=ReplicatePrint) 453
387 454 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
388 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")]) 455 lapply(ReplicateSplit, FUN=ReplicatePrint)
389 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T) 456
390 457 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")])
391 458 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
392 ReplicateSumPrint <- function(dat){ 459
393 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F) 460
394 } 461 ReplicateSumPrint <- function(dat){
395 462 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
396 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"]) 463 }
397 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint) 464
398 465 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
399 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")]) 466 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
400 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T) 467
401 clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow 468 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
402 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2) 469 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
403 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1) 470 clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow
404 471 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
405 ClonalityScorePrint <- function(dat){ 472 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
406 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F) 473
407 } 474 ClonalityScorePrint <- function(dat){
408 475 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
409 clonalityScore = clonalFreqCount[c("Sample", "Result")] 476 }
410 clonalityScore = unique(clonalityScore) 477
411 478 clonalityScore = clonalFreqCount[c("Sample", "Result")]
412 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"]) 479 clonalityScore = unique(clonalityScore)
413 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint) 480
414 481 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
415 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")] 482 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
416 483
417 484 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
418 485
419 ClonalityOverviewPrint <- function(dat){ 486
420 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F) 487
421 } 488 ClonalityOverviewPrint <- function(dat){
422 489 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
423 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample) 490 }
424 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint) 491
425 } 492 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
426 493 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
427 if("Functionality" %in% colnames(test)) 494 }
495
496 imgtcolumns = c("X3V.REGION.trimmed.nt.nb","P3V.nt.nb", "N1.REGION.nt.nb", "P5D.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "P3D.nt.nb", "N2.REGION.nt.nb", "P5J.nt.nb", "X5J.REGION.trimmed.nt.nb", "X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb")
497 if(all(imgtcolumns %in% colnames(inputdata)))
428 { 498 {
429 newData = data.frame(data.table(PROD)[,list(unique=.N, 499 newData = data.frame(data.table(inputdata)[,list(unique=.N,
430 VH.DEL=mean(X3V.REGION.trimmed.nt.nb), 500 VH.DEL=mean(X3V.REGION.trimmed.nt.nb, na.rm=T),
431 P1=mean(P3V.nt.nb), 501 P1=mean(P3V.nt.nb, na.rm=T),
432 N1=mean(N1.REGION.nt.nb), 502 N1=mean(N1.REGION.nt.nb, na.rm=T),
433 P2=mean(P5D.nt.nb), 503 P2=mean(P5D.nt.nb, na.rm=T),
434 DEL.DH=mean(X5D.REGION.trimmed.nt.nb), 504 DEL.DH=mean(X5D.REGION.trimmed.nt.nb, na.rm=T),
435 DH.DEL=mean(X3D.REGION.trimmed.nt.nb), 505 DH.DEL=mean(X3D.REGION.trimmed.nt.nb, na.rm=T),
436 P3=mean(P3D.nt.nb), 506 P3=mean(P3D.nt.nb, na.rm=T),
437 N2=mean(N2.REGION.nt.nb), 507 N2=mean(N2.REGION.nt.nb, na.rm=T),
438 P4=mean(P5J.nt.nb), 508 P4=mean(P5J.nt.nb, na.rm=T),
439 DEL.JH=mean(X5J.REGION.trimmed.nt.nb), 509 DEL.JH=mean(X5J.REGION.trimmed.nt.nb, na.rm=T),
440 Total.Del=( mean(X3V.REGION.trimmed.nt.nb) + 510 Total.Del=( mean(X3V.REGION.trimmed.nt.nb, na.rm=T) +
441 mean(X5D.REGION.trimmed.nt.nb) + 511 mean(X5D.REGION.trimmed.nt.nb, na.rm=T) +
442 mean(X3D.REGION.trimmed.nt.nb) + 512 mean(X3D.REGION.trimmed.nt.nb, na.rm=T) +
443 mean(X5J.REGION.trimmed.nt.nb)), 513 mean(X5J.REGION.trimmed.nt.nb, na.rm=T)),
444 514
445 Total.N=( mean(N1.REGION.nt.nb) + 515 Total.N=( mean(N1.REGION.nt.nb, na.rm=T) +
446 mean(N2.REGION.nt.nb)), 516 mean(N2.REGION.nt.nb, na.rm=T)),
447 517
448 Total.P=( mean(P3V.nt.nb) + 518 Total.P=( mean(P3V.nt.nb, na.rm=T) +
449 mean(P5D.nt.nb) + 519 mean(P5D.nt.nb, na.rm=T) +
450 mean(P3D.nt.nb) + 520 mean(P3D.nt.nb, na.rm=T) +
451 mean(P5J.nt.nb))), 521 mean(P5J.nt.nb, na.rm=T))),
452 by=c("Sample")]) 522 by=c("Sample")])
453 write.table(newData, "junctionAnalysis.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) 523 write.table(newData, "junctionAnalysis.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
454 } 524 }