Mercurial > repos > davidvanzessen > report_clonality_tcell_igg

comparison RScript.r @ 0:1d429107cd26 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Fri, 07 Mar 2014 05:42:31 -0500
parents
children fd1b76816395
comparison
equal deleted inserted replaced
-1:000000000000 0:1d429107cd26
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
11 if (!("gridExtra" %in% rownames(installed.packages()))) {
12 install.packages("gridExtra", repos="http://cran.xl-mirror.nl/")
13 }
14 library(gridExtra)
15 if (!("ggplot2" %in% rownames(installed.packages()))) {
16 install.packages("ggplot2", repos="http://cran.xl-mirror.nl/")
17 }
18 require(ggplot2)
19 if (!("plyr" %in% rownames(installed.packages()))) {
20 install.packages("plyr", repos="http://cran.xl-mirror.nl/")
21 }
22 require(plyr)
23
24 if (!("data.table" %in% rownames(installed.packages()))) {
25 install.packages("data.table", repos="http://cran.xl-mirror.nl/")
26 }
27 library(data.table)
28
29
30 test = read.table(inFile, sep="\t", header=TRUE, fill=T, comment.char="")
31
32 test = test[test$Sample != "",]
33
34 test$Top.V.Gene = gsub("[*]([0-9]+)", "", test$Top.V.Gene)
35 test$Top.D.Gene = gsub("[*]([0-9]+)", "", test$Top.D.Gene)
36 test$Top.J.Gene = gsub("[*]([0-9]+)", "", test$Top.J.Gene)
37
38 #test$VDJCDR3 = do.call(paste, c(test[c("Top.V.Gene", "Top.D.Gene", "Top.J.Gene","CDR3.Seq.DNA")], sep = ":"))
39 test$VDJCDR3 = do.call(paste, c(test[unlist(strsplit(clonalType, ","))], sep = ":"))
40
41 PROD = test[test$VDJ.Frame != "In-frame with stop codon" & test$VDJ.Frame != "Out-of-frame" & test$CDR3.Found.How != "NOT_FOUND" , ]
42 if("Functionality" %in% colnames(test)) {
43 PROD = test[test$Functionality == "productive" | test$Functionality == "productive (see comment)", ]
44 }
45
46 NONPROD = test[test$VDJ.Frame == "In-frame with stop codon" | test$VDJ.Frame == "Out-of-frame" | test$CDR3.Found.How == "NOT_FOUND" , ]
47
48 #PRODF = PROD[ -1]
49
50 PRODF = PROD
51
52 #PRODF = unique(PRODF)
53 PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ]
54
55 PRODFV = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.V.Gene")])
56 PRODFV$Length = as.numeric(PRODFV$Length)
57 Total = 0
58 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
59 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
60 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
61
62 PRODFD = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.D.Gene")])
63 PRODFD$Length = as.numeric(PRODFD$Length)
64 Total = 0
65 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
66 PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
67 PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))
68
69 PRODFJ = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.J.Gene")])
70 PRODFJ$Length = as.numeric(PRODFJ$Length)
71 Total = 0
72 Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
73 PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
74 PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))
75
76 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\n")
77 tcV = textConnection(V)
78 Vchain = read.table(tcV, sep="\t", header=TRUE)
79 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
80 close(tcV)
81
82 D = c("v.name\tchr.orderD\nTRBD1\t1\nTRBD2\t2\n")
83 tcD = textConnection(D)
84 Dchain = read.table(tcD, sep="\t", header=TRUE)
85 PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
86 close(tcD)
87
88
89 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\n")
90 tcJ = textConnection(J)
91 Jchain = read.table(tcJ, sep="\t", header=TRUE)
92 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
93 close(tcJ)
94
95 setwd(outDir)
96
97 write.table(PRODF, "allUnique.tsv", sep="\t",quote=F,row.names=F,col.names=T)
98
99 pV = ggplot(PRODFV)
100 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))
101 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
102
103 png("VPlot.png",width = 1280, height = 720)
104 pV
105 dev.off();
106
107 pD = ggplot(PRODFD)
108 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))
109 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
110
111 png("DPlot.png",width = 800, height = 600)
112 pD
113 dev.off();
114
115 pJ = ggplot(PRODFJ)
116 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))
117 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
118
119 png("JPlot.png",width = 800, height = 600)
120 pJ
121 dev.off();
122
123 revVchain = Vchain
124 revDchain = Dchain
125 revVchain$chr.orderV = rev(revVchain$chr.orderV)
126 revDchain$chr.orderD = rev(revDchain$chr.orderD)
127
128 cat("before VD", "\n")
129
130 plotVD <- function(dat){
131 if(length(dat[,1]) == 0){
132 return()
133 }
134 img = ggplot() +
135 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
136 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
137 scale_fill_gradient(low="gold", high="blue", na.value="white") +
138 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
139 xlab("D genes") +
140 ylab("V Genes")
141
142 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
143 print(img)
144 dev.off()
145 }
146
147 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
148
149 VandDCount$l = log(VandDCount$Length)
150 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
151 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
152 VandDCount$relLength = VandDCount$l / VandDCount$max
153
154 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(test$Sample))
155
156 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
157 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
158 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
159 VDList = split(completeVD, f=completeVD[,"Sample"])
160
161 lapply(VDList, FUN=plotVD)
162
163 cat("after VD", "\n")
164
165 cat("before VJ", "\n")
166
167 plotVJ <- function(dat){
168 if(length(dat[,1]) == 0){
169 return()
170 }
171 img = ggplot() +
172 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
173 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
174 scale_fill_gradient(low="gold", high="blue", na.value="white") +
175 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
176 xlab("J genes") +
177 ylab("V Genes")
178
179 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
180 print(img)
181 dev.off()
182 }
183
184 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
185
186 VandJCount$l = log(VandJCount$Length)
187 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
188 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
189 VandJCount$relLength = VandJCount$l / VandJCount$max
190
191 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
192
193 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
194 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
195 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
196 VJList = split(completeVJ, f=completeVJ[,"Sample"])
197 lapply(VJList, FUN=plotVJ)
198
199 cat("after VJ", "\n")
200
201 cat("before DJ", "\n")
202
203 plotDJ <- function(dat){
204 if(length(dat[,1]) == 0){
205 return()
206 }
207 img = ggplot() +
208 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
209 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
210 scale_fill_gradient(low="gold", high="blue", na.value="white") +
211 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
212 xlab("J genes") +
213 ylab("D Genes")
214
215 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
216 print(img)
217 dev.off()
218 }
219
220 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
221
222 DandJCount$l = log(DandJCount$Length)
223 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
224 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
225 DandJCount$relLength = DandJCount$l / DandJCount$max
226
227 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
228
229 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
230 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
231 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
232 DJList = split(completeDJ, f=completeDJ[,"Sample"])
233 lapply(DJList, FUN=plotDJ)
234
235 cat("after DJ", "\n")
236
237 sampleFile <- file("samples.txt")
238 un = unique(test$Sample)
239 un = paste(un, sep="\n")
240 writeLines(un, sampleFile)
241 close(sampleFile)
242
243
244
245 if("Replicate" %in% colnames(test))
246 {
247 clonalityFrame = PROD
248 clonalityFrame$ReplicateConcat = do.call(paste, c(clonalityFrame[c("VDJCDR3", "Sample", "Replicate")], sep = ":"))
249 clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ]
250 write.table(clonalityFrame, "clonalityComplete.tsv", sep="\t",quote=F,row.names=F,col.names=T)
251
252 ClonalitySampleReplicatePrint <- function(dat){
253 write.table(dat, paste("clonality_", unique(dat$Sample) , "_", unique(dat$Replicate), ".tsv", sep=""), sep="\t",quote=F,row.names=F,col.names=T)
254 }
255
256 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,c("Sample", "Replicate")])
257 lapply(clonalityFrameSplit, FUN=ClonalitySampleReplicatePrint)
258
259 ClonalitySamplePrint <- function(dat){
260 write.table(dat, paste("clonality_", unique(dat$Sample) , ".tsv", sep=""), sep="\t",quote=F,row.names=F,col.names=T)
261 }
262
263 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,"Sample"])
264 lapply(clonalityFrameSplit, FUN=ClonalitySamplePrint)
265
266 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "VDJCDR3")])
267 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
268 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
269 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
270 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
271
272 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
273 tcct = textConnection(ct)
274 CT = read.table(tcct, sep="\t", header=TRUE)
275 close(tcct)
276 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
277 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
278
279 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "VDJCDR3")])
280 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
281 clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads)
282 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
283
284 ReplicatePrint <- function(dat){
285 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
286 }
287
288 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
289 lapply(ReplicateSplit, FUN=ReplicatePrint)
290
291 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")])
292 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
293
294
295 ReplicateSumPrint <- function(dat){
296 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
297 }
298
299 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
300 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
301
302 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
303 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
304 clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow
305 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
306 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
307
308 ClonalityScorePrint <- function(dat){
309 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
310 }
311
312 clonalityScore = clonalFreqCount[c("Sample", "Result")]
313 clonalityScore = unique(clonalityScore)
314
315 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
316 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
317
318 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
319
320
321
322 ClonalityOverviewPrint <- function(dat){
323 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
324 }
325
326 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
327 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
328 }
329
330 if("Functionality" %in% colnames(test))
331 {
332 newData = data.frame(data.table(PROD)[,list(unique=.N,
333 VH.DEL=mean(X3V.REGION.trimmed.nt.nb),
334 P1=mean(P3V.nt.nb),
335 N1=mean(N1.REGION.nt.nb),
336 P2=mean(P5D.nt.nb),
337 DEL.DH=mean(X5D.REGION.trimmed.nt.nb),
338 DH.DEL=mean(X3D.REGION.trimmed.nt.nb),
339 P3=mean(P3D.nt.nb),
340 N2=mean(N2.REGION.nt.nb),
341 P4=mean(P5J.nt.nb),
342 DEL.JH=mean(X5J.REGION.trimmed.nt.nb),
343 Total.Del=( mean(X3V.REGION.trimmed.nt.nb) +
344 mean(X5D.REGION.trimmed.nt.nb) +
345 mean(X3D.REGION.trimmed.nt.nb) +
346 mean(X5J.REGION.trimmed.nt.nb)),
347
348 Total.N=( mean(N1.REGION.nt.nb) +
349 mean(N2.REGION.nt.nb)),
350
351 Total.P=( mean(P3V.nt.nb) +
352 mean(P5D.nt.nb) +
353 mean(P3D.nt.nb) +
354 mean(P5J.nt.nb))),
355 by=c("Sample")])
356 write.table(newData, "junctionAnalysis.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
357 }