Mercurial > repos > davidvanzessen > complete_immunerepertoire_igg

comparison RScript_t.r @ 1:778a9d130904 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Thu, 04 Sep 2014 07:46:23 -0400
parents
children
comparison
equal deleted inserted replaced
0:7d97fa9a0423 1:778a9d130904
1 #options( show.error.messages=F, error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )
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 if (!("gridExtra" %in% rownames(installed.packages()))) {
14 install.packages("gridExtra", repos="http://cran.xl-mirror.nl/")
15 }
16 library(gridExtra)
17 if (!("ggplot2" %in% rownames(installed.packages()))) {
18 install.packages("ggplot2", repos="http://cran.xl-mirror.nl/")
19 }
20 library(ggplot2)
21 if (!("plyr" %in% rownames(installed.packages()))) {
22 install.packages("plyr", repos="http://cran.xl-mirror.nl/")
23 }
24 library(plyr)
25
26 if (!("data.table" %in% rownames(installed.packages()))) {
27 install.packages("data.table", repos="http://cran.xl-mirror.nl/")
28 }
29 library(data.table)
30
31 if (!("reshape2" %in% rownames(installed.packages()))) {
32 install.packages("reshape2", repos="http://cran.xl-mirror.nl/")
33 }
34 library(reshape2)
35
36
37 test = read.table(inFile, sep="\t", header=TRUE, fill=T, comment.char="")
38
39 test = test[test$Sample != "",]
40
41 print("test1\n")
42
43 test$Top.V.Gene = gsub("[*]([0-9]+)", "", test$Top.V.Gene)
44 test$Top.D.Gene = gsub("[*]([0-9]+)", "", test$Top.D.Gene)
45 test$Top.J.Gene = gsub("[*]([0-9]+)", "", test$Top.J.Gene)
46
47 #test$VDJCDR3 = do.call(paste, c(test[c("Top.V.Gene", "Top.D.Gene", "Top.J.Gene","CDR3.Seq.DNA")], sep = ":"))
48 test$VDJCDR3 = do.call(paste, c(test[unlist(strsplit(clonalType, ","))], sep = ":"))
49
50 PROD = test[test$VDJ.Frame != "In-frame with stop codon" & test$VDJ.Frame != "Out-of-frame" & test$CDR3.Found.How != "NOT_FOUND" , ]
51 if("Functionality" %in% colnames(test)) {
52 PROD = test[test$Functionality == "productive" | test$Functionality == "productive (see comment)", ]
53 }
54
55 NONPROD = test[test$VDJ.Frame == "In-frame with stop codon" | test$VDJ.Frame == "Out-of-frame" | test$CDR3.Found.How == "NOT_FOUND" , ]
56
57 #PRODF = PROD[ -1]
58
59 PRODF = PROD
60 print("test2\n")
61 #PRODF = unique(PRODF)
62 if(any(grepl(pattern="_", x=PRODF$ID))){ #dumb and way to simple
63 PRODF$freq = gsub("^[0-9]+_", "", PRODF$ID)
64 PRODF$freq = gsub("_.*", "", PRODF$freq)
65 PRODF$freq = as.numeric(PRODF$freq)
66 if(any(is.na(PRODF$freq))){ #fix the dumbness if it fails
67 PRODF$freq = 1
68 if(selection == "unique"){
69 PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ]
70 }
71 }
72 } else {
73 PRODF$freq = 1
74 if(selection == "unique"){
75 PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ]
76 }
77 }
78
79 PRODFV = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.V.Gene")])
80 PRODFV$Length = as.numeric(PRODFV$Length)
81 Total = 0
82 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
83 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
84 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
85
86 PRODFD = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.D.Gene")])
87 PRODFD$Length = as.numeric(PRODFD$Length)
88 Total = 0
89 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
90 PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
91 PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))
92
93 PRODFJ = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.J.Gene")])
94 PRODFJ$Length = as.numeric(PRODFJ$Length)
95 Total = 0
96 Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
97 PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
98 PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))
99
100 V = c("v.name\tchr.orderV\n")
101 D = c("v.name\tchr.orderD\n")
102 J = c("v.name\tchr.orderJ\n")
103
104 print("test3\n")
105
106 if(species == "human"){
107 if(locus == "trb"){
108 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")
109 D = c("v.name\tchr.orderD\nTRBD1\t1\nTRBD2\t2\n")
110 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")
111 } else if (locus == "tra"){
112 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")
113 D = c("v.name\tchr.orderD\n")
114 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")
115 } else if (locus == "trg"){
116 V = c("v.name\tchr.orderV\nTRGV9\t1\nTRGV8\t2\nTRGV5\t3\nTRGV4\t4\nTRGV3\t5\nTRGV2\t6")
117 D = c("v.name\tchr.orderD\n")
118 J = c("v.name\tchr.orderJ\nTRGJ2\t1\nTRGJP2\t2\nTRGJ1\t3\nTRGJP1\t4")
119 } else if (locus == "trd"){
120 V = c("v.name\tchr.orderV\nTRDV1\t1\nTRDV2\t2\nTRDV3\t3")
121 D = c("v.name\tchr.orderD\nTRDD1\t1\nTRDD2\t2\nTRDD3\t3")
122 J = c("v.name\tchr.orderJ\nTRDJ1\t1\nTRDJ4\t2\nTRDJ2\t3\nTRDJ3\t4")
123 }
124 } else if (species == "mouse"){
125 if(locus == "trb"){
126 cat("mouse trb not yet implemented")
127 } else if (locus == "tra"){
128 cat("mouse tra not yet implemented")
129 } else if (locus == "trg"){
130 cat("mouse trg not yet implemented")
131 } else if (locus == "trd"){
132 cat("mouse trd not yet implemented")
133 }
134 }
135 useD = TRUE
136 if(species == "human" && locus == "tra"){
137 useD = FALSE
138 cat("No D Genes in this species/locus")
139 }
140
141 print("test4\n")
142
143 tcV = textConnection(V)
144 Vchain = read.table(tcV, sep="\t", header=TRUE)
145 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
146 close(tcV)
147
148
149 tcD = textConnection(D)
150 Dchain = read.table(tcD, sep="\t", header=TRUE)
151 PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
152 close(tcD)
153
154
155
156 tcJ = textConnection(J)
157 Jchain = read.table(tcJ, sep="\t", header=TRUE)
158 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
159 close(tcJ)
160
161 setwd(outDir)
162
163 write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T)
164
165 pV = ggplot(PRODFV)
166 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))
167 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
168 write.table(x=PRODFV, file="VFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
169
170 png("VPlot.png",width = 1280, height = 720)
171 pV
172 dev.off();
173
174 pD = ggplot(PRODFD)
175 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))
176 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
177 write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
178
179 png("DPlot.png",width = 800, height = 600)
180 pD
181 dev.off();
182
183 pJ = ggplot(PRODFJ)
184 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))
185 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
186 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
187
188 png("JPlot.png",width = 800, height = 600)
189 pJ
190 dev.off();
191
192 print("test5\n")
193
194 VGenes = PRODF[,c("Sample", "Top.V.Gene", "freq")]
195 VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene)
196 VGenes = data.frame(data.table(VGenes)[, list(Count=sum(freq)), by=c("Sample", "Top.V.Gene")])
197 TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample])
198 VGenes = merge(VGenes, TotalPerSample, by="Sample")
199 VGenes$Frequency = VGenes$Count * 100 / VGenes$total
200 VPlot = ggplot(VGenes)
201 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)) +
202 ggtitle("Distribution of V gene families") +
203 ylab("Percentage of sequences")
204 png("VFPlot.png")
205 VPlot
206 dev.off();
207 write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
208
209 DGenes = PRODF[,c("Sample", "Top.D.Gene", "freq")]
210 DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene)
211 DGenes = data.frame(data.table(DGenes)[, list(Count=sum(freq)), by=c("Sample", "Top.D.Gene")])
212 TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample])
213 DGenes = merge(DGenes, TotalPerSample, by="Sample")
214 DGenes$Frequency = DGenes$Count * 100 / DGenes$total
215 DPlot = ggplot(DGenes)
216 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)) +
217 ggtitle("Distribution of D gene families") +
218 ylab("Percentage of sequences")
219 png("DFPlot.png")
220 DPlot
221 dev.off();
222 write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
223
224 JGenes = PRODF[,c("Sample", "Top.J.Gene", "freq")]
225 JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene)
226 JGenes = data.frame(data.table(JGenes)[, list(Count=sum(freq)), by=c("Sample", "Top.J.Gene")])
227 TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample])
228 JGenes = merge(JGenes, TotalPerSample, by="Sample")
229 JGenes$Frequency = JGenes$Count * 100 / JGenes$total
230 JPlot = ggplot(JGenes)
231 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)) +
232 ggtitle("Distribution of J gene families") +
233 ylab("Percentage of sequences")
234 png("JFPlot.png")
235 JPlot
236 dev.off();
237 write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
238
239 CDR3Length = data.frame(data.table(PRODF)[, list(Count=sum(freq)), by=c("Sample", "CDR3.Length.DNA")])
240 TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample])
241 CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample")
242 CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total
243 CDR3LengthPlot = ggplot(CDR3Length)
244 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)) +
245 ggtitle("Length distribution of CDR3") +
246 xlab("CDR3 Length") +
247 ylab("Percentage of sequences")
248 png("CDR3LengthPlot.png",width = 1280, height = 720)
249 CDR3LengthPlot
250 dev.off()
251 write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T)
252
253 revVchain = Vchain
254 revDchain = Dchain
255 revVchain$chr.orderV = rev(revVchain$chr.orderV)
256 revDchain$chr.orderD = rev(revDchain$chr.orderD)
257
258 print("test6\n")
259
260 plotVD <- function(dat){
261 if(length(dat[,1]) == 0){
262 return()
263 }
264 img = ggplot() +
265 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
266 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
267 scale_fill_gradient(low="gold", high="blue", na.value="white") +
268 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
269 xlab("D genes") +
270 ylab("V Genes")
271
272 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
273 print(img)
274
275 dev.off()
276 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)
277 }
278
279 VandDCount = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
280
281 VandDCount$l = log(VandDCount$Length)
282 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
283 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
284 VandDCount$relLength = VandDCount$l / VandDCount$max
285
286 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(test$Sample))
287
288 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
289 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
290 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
291 VDList = split(completeVD, f=completeVD[,"Sample"])
292
293 lapply(VDList, FUN=plotVD)
294
295 plotVJ <- function(dat){
296 if(length(dat[,1]) == 0){
297 return()
298 }
299 img = ggplot() +
300 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
301 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
302 scale_fill_gradient(low="gold", high="blue", na.value="white") +
303 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
304 xlab("J genes") +
305 ylab("V Genes")
306
307 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
308 print(img)
309 dev.off()
310 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)
311 }
312
313 VandJCount = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
314
315 VandJCount$l = log(VandJCount$Length)
316 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
317 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
318 VandJCount$relLength = VandJCount$l / VandJCount$max
319
320 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
321
322 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
323 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
324 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
325 VJList = split(completeVJ, f=completeVJ[,"Sample"])
326 lapply(VJList, FUN=plotVJ)
327
328 plotDJ <- function(dat){
329 if(length(dat[,1]) == 0){
330 return()
331 }
332 img = ggplot() +
333 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
334 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
335 scale_fill_gradient(low="gold", high="blue", na.value="white") +
336 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
337 xlab("J genes") +
338 ylab("D Genes")
339
340 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
341 print(img)
342 dev.off()
343 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)
344 }
345
346 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
347
348 DandJCount$l = log(DandJCount$Length)
349 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
350 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
351 DandJCount$relLength = DandJCount$l / DandJCount$max
352
353 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
354
355 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
356 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
357 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
358 DJList = split(completeDJ, f=completeDJ[,"Sample"])
359 lapply(DJList, FUN=plotDJ)
360
361 sampleFile <- file("samples.txt")
362 un = unique(test$Sample)
363 un = paste(un, sep="\n")
364 writeLines(un, sampleFile)
365 close(sampleFile)
366
367 print("test7\n")
368
369 if("Replicate" %in% colnames(test))
370 {
371 clonalityFrame = PROD
372 clonalityFrame$ReplicateConcat = do.call(paste, c(clonalityFrame[c("VDJCDR3", "Sample", "Replicate")], sep = ":"))
373 clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ]
374 write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T)
375
376 ClonalitySampleReplicatePrint <- function(dat){
377 write.table(dat, paste("clonality_", unique(dat$Sample) , "_", unique(dat$Replicate), ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
378 }
379
380 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,c("Sample", "Replicate")])
381 #lapply(clonalityFrameSplit, FUN=ClonalitySampleReplicatePrint)
382
383 ClonalitySamplePrint <- function(dat){
384 write.table(dat, paste("clonality_", unique(dat$Sample) , ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
385 }
386
387 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,"Sample"])
388 #lapply(clonalityFrameSplit, FUN=ClonalitySamplePrint)
389
390 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "VDJCDR3")])
391 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
392 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
393 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
394 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
395
396 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
397 tcct = textConnection(ct)
398 CT = read.table(tcct, sep="\t", header=TRUE)
399 close(tcct)
400 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
401 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
402
403 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "VDJCDR3")])
404 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
405 clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads)
406 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
407
408 ReplicatePrint <- function(dat){
409 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
410 }
411
412 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
413 lapply(ReplicateSplit, FUN=ReplicatePrint)
414
415 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")])
416 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
417
418
419 ReplicateSumPrint <- function(dat){
420 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
421 }
422
423 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
424 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
425
426 writeClonalitySequences <- function(dat){
427 for(i in c(2,3,4,5,6)){
428 fltr = dat[dat$Type == i,]
429 if(length(fltr[,1]) == 0){
430 next
431 }
432 tmp = clonalityFrame[clonalityFrame$Sample == fltr$Sample[1] & clonalityFrame$VDJCDR3 %in% fltr$VDJCDR3,]
433 tmp = tmp[order(tmp$VDJCDR3),]
434 write.table(tmp, paste("ClonalitySequences_", unique(dat[1])[1,1] , "_", i, ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=T)
435 }
436 }
437 freqsplt = split(clonalFreq[clonalFreq$Type > 1,], clonalFreq[clonalFreq$Type > 1,]$Sample)
438 lapply(freqsplt, FUN=writeClonalitySequences)
439
440 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
441 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
442 clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow
443 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
444 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
445
446 ClonalityScorePrint <- function(dat){
447 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
448 }
449
450 clonalityScore = clonalFreqCount[c("Sample", "Result")]
451 clonalityScore = unique(clonalityScore)
452
453 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
454 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
455
456 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
457
458
459
460 ClonalityOverviewPrint <- function(dat){
461 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
462 }
463
464 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
465 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
466 }
467
468 print("test8\n")
469
470 if("Functionality" %in% colnames(test))
471 {
472 newData = data.frame(data.table(PROD)[,list(unique=.N,
473 VH.DEL=mean(X3V.REGION.trimmed.nt.nb),
474 P1=mean(P3V.nt.nb),
475 N1=mean(N1.REGION.nt.nb),
476 P2=mean(P5D.nt.nb),
477 DEL.DH=mean(X5D.REGION.trimmed.nt.nb),
478 DH.DEL=mean(X3D.REGION.trimmed.nt.nb),
479 P3=mean(P3D.nt.nb),
480 N2=mean(N2.REGION.nt.nb),
481 P4=mean(P5J.nt.nb),
482 DEL.JH=mean(X5J.REGION.trimmed.nt.nb),
483 Total.Del=( mean(X3V.REGION.trimmed.nt.nb) +
484 mean(X5D.REGION.trimmed.nt.nb) +
485 mean(X3D.REGION.trimmed.nt.nb) +
486 mean(X5J.REGION.trimmed.nt.nb)),
487
488 Total.N=( mean(N1.REGION.nt.nb) +
489 mean(N2.REGION.nt.nb)),
490
491 Total.P=( mean(P3V.nt.nb) +
492 mean(P5D.nt.nb) +
493 mean(P3D.nt.nb) +
494 mean(P5J.nt.nb))),
495 by=c("Sample")])
496 write.table(newData, "junctionAnalysis.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
497 }
498
499 print("test9\n")