Mercurial > repos > davidvanzessen > combined_immune_repertoire_imgt

comparison immunerepertoirecombined_imgt/RScript.r @ 0:e71c59b72669 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Mon, 09 Dec 2013 03:45:21 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:e71c59b72669
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
10 if (!("gridExtra" %in% rownames(installed.packages()))) {
11 install.packages("gridExtra", repos="http://cran.xl-mirror.nl/")
12 }
13 library(gridExtra)
14 if (!("ggplot2" %in% rownames(installed.packages()))) {
15 install.packages("ggplot2", repos="http://cran.xl-mirror.nl/")
16 }
17 require(ggplot2)
18 if (!("plyr" %in% rownames(installed.packages()))) {
19 install.packages("plyr", repos="http://cran.xl-mirror.nl/")
20 }
21 require(plyr)
22
23 if (!("data.table" %in% rownames(installed.packages()))) {
24 install.packages("data.table", repos="http://cran.xl-mirror.nl/")
25 }
26 library(data.table)
27
28
29 test = read.table(inFile, sep="\t", header=TRUE, fill=T)
30
31 test = test[test$Sample != "",]
32
33 test$Top.V.Gene = gsub("[*]([0-9]+)", "", test$Top.V.Gene)
34 test$Top.D.Gene = gsub("[*]([0-9]+)", "", test$Top.D.Gene)
35 test$Top.J.Gene = gsub("[*]([0-9]+)", "", test$Top.J.Gene)
36
37 #test$VDJCDR3 = do.call(paste, c(test[c("Top.V.Gene", "Top.D.Gene", "Top.J.Gene","CDR3.Seq.DNA")], sep = ":"))
38 test$VDJCDR3 = do.call(paste, c(test[unlist(strsplit(clonalType, ","))], sep = ":"))
39
40 PROD = test[test$VDJ.Frame != "In-frame with stop codon" & test$VDJ.Frame != "Out-of-frame" & test$CDR3.Found.How != "NOT_FOUND" , ]
41
42 NONPROD = test[test$VDJ.Frame == "In-frame with stop codon" | test$VDJ.Frame == "Out-of-frame" | test$CDR3.Found.How == "NOT_FOUND" , ]
43
44 #PRODF = PROD[ -1]
45
46 PRODF = PROD
47
48 #PRODF = unique(PRODF)
49 PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ]
50
51 PRODFV = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.V.Gene")])
52 PRODFV$Length = as.numeric(PRODFV$Length)
53 Total = 0
54 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
55 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
56 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
57
58 PRODFD = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.D.Gene")])
59 PRODFD$Length = as.numeric(PRODFD$Length)
60 Total = 0
61 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
62 PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
63 PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))
64
65 PRODFJ = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.J.Gene")])
66 PRODFJ$Length = as.numeric(PRODFJ$Length)
67 Total = 0
68 Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
69 PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
70 PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))
71
72 V = c("v.name\tchr.orderV\nIGHV7-81\t1\nIGHV3-74\t2\nIGHV3-73\t3\nIGHV3-72\t4\nIGHV2-70\t6\nIGHV1-69\t7\nIGHV3-66\t8\nIGHV3-64\t9\nIGHV4-61\t10\nIGHV4-59\t11\nIGHV1-58\t12\nIGHV3-53\t13\nIGHV5-a\t15\nIGHV5-51\t16\nIGHV3-49\t17\nIGHV3-48\t18\nIGHV1-46\t20\nIGHV1-45\t21\nIGHV3-43\t22\nIGHV4-39\t23\nIGHV3-35\t24\nIGHV4-34\t25\nIGHV3-33\t26\nIGHV4-31\t27\nIGHV4-30-4\t28\nIGHV4-30-2\t29\nIGHV3-30-3\t30\nIGHV3-30\t31\nIGHV4-28\t32\nIGHV2-26\t33\nIGHV1-24\t34\nIGHV3-23\t35\nIGHV3-21\t37\nIGHV3-20\t38\nIGHV1-18\t40\nIGHV3-15\t41\nIGHV3-13\t42\nIGHV3-11\t43\nIGHV3-9\t44\nIGHV1-8\t45\nIGHV3-7\t46\nIGHV2-5\t47\nIGHV7-4-1\t48\nIGHV4-4\t49\nIGHV4-b\t50\nIGHV1-3\t51\nIGHV1-2\t52\nIGHV6-1\t53")
73 tcV = textConnection(V)
74 Vchain = read.table(tcV, sep="\t", header=TRUE)
75 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
76 close(tcV)
77
78 D = c("v.name\tchr.orderD\nIGHD1-1\t1\nIGHD2-2\t2\nIGHD3-3\t3\nIGHD6-6\t4\nIGHD1-7\t5\nIGHD2-8\t6\nIGHD3-9\t7\nIGHD3-10\t8\nIGHD4-11\t9\nIGHD5-12\t10\nIGHD6-13\t11\nIGHD1-14\t12\nIGHD2-15\t13\nIGHD3-16\t14\nIGHD4-17\t15\nIGHD5-18\t16\nIGHD6-19\t17\nIGHD1-20\t18\nIGHD2-21\t19\nIGHD3-22\t20\nIGHD4-23\t21\nIGHD5-24\t22\nIGHD6-25\t23\nIGHD1-26\t24\nIGHD7-27\t25")
79 tcD = textConnection(D)
80 Dchain = read.table(tcD, sep="\t", header=TRUE)
81 PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
82 close(tcD)
83
84
85 J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6")
86 tcJ = textConnection(J)
87 Jchain = read.table(tcJ, sep="\t", header=TRUE)
88 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
89 close(tcJ)
90
91 setwd(outDir)
92
93 pV = ggplot(PRODFV)
94 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))
95 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
96
97 png("VPlot.png",width = 1280, height = 720)
98 pV
99 dev.off();
100
101 pD = ggplot(PRODFD)
102 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))
103 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
104
105 png("DPlot.png",width = 800, height = 600)
106 pD
107 dev.off();
108
109 pJ = ggplot(PRODFJ)
110 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))
111 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
112
113 png("JPlot.png",width = 800, height = 600)
114 pJ
115 dev.off();
116
117 revVchain = Vchain
118 revDchain = Dchain
119 revVchain$chr.orderV = rev(revVchain$chr.orderV)
120 revDchain$chr.orderD = rev(revDchain$chr.orderD)
121
122 plotVD <- function(dat){
123 if(length(dat[,1]) == 0){
124 return()
125 }
126 img = ggplot() +
127 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
128 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
129 scale_fill_gradient(low="gold", high="blue", na.value="white") +
130 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
131 xlab("D genes") +
132 ylab("V Genes")
133
134 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
135 print(img)
136 dev.off()
137 }
138
139 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
140
141 VandDCount$l = log(VandDCount$Length)
142 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
143 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
144 VandDCount$relLength = VandDCount$l / VandDCount$max
145
146 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(test$Sample))
147
148 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
149 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
150 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
151 VDList = split(completeVD, f=completeVD[,"Sample"])
152
153 lapply(VDList, FUN=plotVD)
154
155
156
157 plotVJ <- function(dat){
158 if(length(dat[,1]) == 0){
159 return()
160 }
161 img = ggplot() +
162 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
163 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
164 scale_fill_gradient(low="gold", high="blue", na.value="white") +
165 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
166 xlab("J genes") +
167 ylab("V Genes")
168
169 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
170 print(img)
171 dev.off()
172 }
173
174 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
175
176 VandJCount$l = log(VandJCount$Length)
177 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
178 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
179 VandJCount$relLength = VandJCount$l / VandJCount$max
180
181 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
182
183 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
184 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
185 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
186 VJList = split(completeVJ, f=completeVJ[,"Sample"])
187 lapply(VJList, FUN=plotVJ)
188
189 plotDJ <- function(dat){
190 if(length(dat[,1]) == 0){
191 return()
192 }
193 img = ggplot() +
194 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
195 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
196 scale_fill_gradient(low="gold", high="blue", na.value="white") +
197 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
198 xlab("J genes") +
199 ylab("D Genes")
200
201 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
202 print(img)
203 dev.off()
204 }
205
206 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
207
208 DandJCount$l = log(DandJCount$Length)
209 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
210 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
211 DandJCount$relLength = DandJCount$l / DandJCount$max
212
213 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
214
215 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
216 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
217 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
218 DJList = split(completeDJ, f=completeDJ[,"Sample"])
219 lapply(DJList, FUN=plotDJ)
220
221
222 sampleFile <- file("samples.txt")
223 un = unique(test$Sample)
224 un = paste(un, sep="\n")
225 writeLines(un, sampleFile)
226 close(sampleFile)
227
228
229 if("Replicate" %in% colnames(test))
230 {
231 clonalityFrame = PROD
232 clonalityFrame$ReplicateConcat = do.call(paste, c(clonalityFrame[c("VDJCDR3", "Sample", "Replicate")], sep = ":"))
233 clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ]
234 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "VDJCDR3")])
235 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
236 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
237 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
238 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
239
240 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
241 tcct = textConnection(ct)
242 CT = read.table(tcct, sep="\t", header=TRUE)
243 close(tcct)
244 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
245 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
246
247 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "VDJCDR3")])
248 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
249 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
250
251 ReplicatePrint <- function(dat){
252 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
253 }
254
255 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
256 lapply(ReplicateSplit, FUN=ReplicatePrint)
257
258 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")])
259 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
260
261
262 ReplicateSumPrint <- function(dat){
263 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
264 }
265
266 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
267 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
268
269 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
270 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
271
272 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
273 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
274
275 ClonalityScorePrint <- function(dat){
276 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
277 }
278
279 clonalityScore = clonalFreqCount[c("Sample", "Result")]
280 clonalityScore = unique(clonalityScore)
281
282 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
283 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
284
285 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
286
287
288
289 ClonalityOverviewPrint <- function(dat){
290 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
291 }
292
293 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
294 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
295 }