Mercurial > repos > davidvanzessen > complete_immunerepertoire_igg

comparison RScript.r @ 0:7d97fa9a0423 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Fri, 09 May 2014 09:35:32 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:7d97fa9a0423
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
14
15 if (!("gridExtra" %in% rownames(installed.packages()))) {
16 install.packages("gridExtra", repos="http://cran.xl-mirror.nl/")
17 }
18 library(gridExtra)
19 if (!("ggplot2" %in% rownames(installed.packages()))) {
20 install.packages("ggplot2", repos="http://cran.xl-mirror.nl/")
21 }
22 require(ggplot2)
23 if (!("plyr" %in% rownames(installed.packages()))) {
24 install.packages("plyr", repos="http://cran.xl-mirror.nl/")
25 }
26 require(plyr)
27
28 if (!("data.table" %in% rownames(installed.packages()))) {
29 install.packages("data.table", repos="http://cran.xl-mirror.nl/")
30 }
31 library(data.table)
32
33 if (!("reshape2" %in% rownames(installed.packages()))) {
34 install.packages("reshape2", repos="http://cran.xl-mirror.nl/")
35 }
36 library(reshape2)
37
38
39 test = read.table(inFile, sep="\t", header=TRUE, fill=T, comment.char="")
40
41 test = test[test$Sample != "",]
42
43 test$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$CDR3.Found.How == "NOT_FOUND" , ]
56
57 #PRODF = PROD[ -1]
58
59 PRODF = PROD
60
61 #PRODF = unique(PRODF)
62
63
64
65 if(selection == "unique"){
66 PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ]
67 }
68
69 PRODFV = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.V.Gene")])
70 PRODFV$Length = as.numeric(PRODFV$Length)
71 Total = 0
72 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
73 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
74 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
75
76 PRODFD = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.D.Gene")])
77 PRODFD$Length = as.numeric(PRODFD$Length)
78 Total = 0
79 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
80 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))
82
83 PRODFJ = data.frame(data.table(PRODF)[, list(Length=.N), 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)))
87 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))
89
90
91 if(species == "human"){
92 if(locus == "igh"){
93 cat("human igh")
94 } else if (locus == "igk"){
95 cat("human igk")
96 } else if (locus == "igl"){
97 cat("human igl")
98 }
99 } else if (species == "mouse"){
100 if(locus == "igh"){
101 cat("mouse igh")
102 } else if (locus == "igk"){
103 cat("mouse igk")
104 } else if (locus == "igl"){
105 cat("mouse igl")
106 }
107 }
108
109 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")
110 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")
111 J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6")
112
113
114
115
116 tcV = textConnection(V)
117 Vchain = read.table(tcV, sep="\t", header=TRUE)
118 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
119 close(tcV)
120
121
122 tcD = textConnection(D)
123 Dchain = read.table(tcD, sep="\t", header=TRUE)
124 PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
125 close(tcD)
126
127
128
129 tcJ = textConnection(J)
130 Jchain = read.table(tcJ, sep="\t", header=TRUE)
131 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
132 close(tcJ)
133
134 setwd(outDir)
135
136 write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T)
137
138 pV = ggplot(PRODFV)
139 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))
140 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
141 write.table(x=PRODFV, file="VFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
142
143 png("VPlot.png",width = 1280, height = 720)
144 pV
145 dev.off();
146
147 pD = ggplot(PRODFD)
148 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))
149 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
150 write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
151
152 png("DPlot.png",width = 800, height = 600)
153 pD
154 dev.off();
155
156 pJ = ggplot(PRODFJ)
157 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))
158 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
159 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
160
161 png("JPlot.png",width = 800, height = 600)
162 pJ
163 dev.off();
164
165 VGenes = PRODF[,c("Sample", "Top.V.Gene")]
166 VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene)
167 VGenes = data.frame(data.table(VGenes)[, list(Count=.N), by=c("Sample", "Top.V.Gene")])
168 TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample])
169 VGenes = merge(VGenes, TotalPerSample, by="Sample")
170 VGenes$Frequency = VGenes$Count * 100 / VGenes$total
171 VPlot = ggplot(VGenes)
172 VPlot = VPlot + geom_bar(aes( x = Top.V.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
173 ggtitle("Distribution of V gene families") +
174 ylab("Percentage of sequences")
175 png("VFPlot.png")
176 VPlot
177 dev.off();
178 write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
179
180 DGenes = PRODF[,c("Sample", "Top.D.Gene")]
181 DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene)
182 DGenes = data.frame(data.table(DGenes)[, list(Count=.N), by=c("Sample", "Top.D.Gene")])
183 TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample])
184 DGenes = merge(DGenes, TotalPerSample, by="Sample")
185 DGenes$Frequency = DGenes$Count * 100 / DGenes$total
186 DPlot = ggplot(DGenes)
187 DPlot = DPlot + geom_bar(aes( x = Top.D.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
188 ggtitle("Distribution of D gene families") +
189 ylab("Percentage of sequences")
190 png("DFPlot.png")
191 DPlot
192 dev.off();
193 write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
194
195 JGenes = PRODF[,c("Sample", "Top.J.Gene")]
196 JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene)
197 JGenes = data.frame(data.table(JGenes)[, list(Count=.N), by=c("Sample", "Top.J.Gene")])
198 TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample])
199 JGenes = merge(JGenes, TotalPerSample, by="Sample")
200 JGenes$Frequency = JGenes$Count * 100 / JGenes$total
201 JPlot = ggplot(JGenes)
202 JPlot = JPlot + geom_bar(aes( x = Top.J.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
203 ggtitle("Distribution of J gene families") +
204 ylab("Percentage of sequences")
205 png("JFPlot.png")
206 JPlot
207 dev.off();
208 write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
209
210 CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length.DNA")])
211 TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample])
212 CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample")
213 CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total
214 CDR3LengthPlot = ggplot(CDR3Length)
215 CDR3LengthPlot = CDR3LengthPlot + geom_bar(aes( x = CDR3.Length.DNA, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
216 ggtitle("Length distribution of CDR3") +
217 xlab("CDR3 Length") +
218 ylab("Percentage of sequences")
219 png("CDR3LengthPlot.png",width = 1280, height = 720)
220 CDR3LengthPlot
221 dev.off()
222 write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T)
223
224 revVchain = Vchain
225 revDchain = Dchain
226 revVchain$chr.orderV = rev(revVchain$chr.orderV)
227 revDchain$chr.orderD = rev(revDchain$chr.orderD)
228
229 plotVD <- function(dat){
230 if(length(dat[,1]) == 0){
231 return()
232 }
233 img = ggplot() +
234 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
235 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
236 scale_fill_gradient(low="gold", high="blue", na.value="white") +
237 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
238 xlab("D genes") +
239 ylab("V Genes")
240
241 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
242 print(img)
243
244 dev.off()
245 write.table(x=acast(dat, Top.V.Gene~Top.D.Gene, value.var="Length"), file=paste("HeatmapVD_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
246 }
247
248 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
249
250 VandDCount$l = log(VandDCount$Length)
251 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
252 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
253 VandDCount$relLength = VandDCount$l / VandDCount$max
254
255 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(test$Sample))
256
257 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
258 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
259 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
260 VDList = split(completeVD, f=completeVD[,"Sample"])
261
262 lapply(VDList, FUN=plotVD)
263
264
265
266 plotVJ <- function(dat){
267 if(length(dat[,1]) == 0){
268 return()
269 }
270 img = ggplot() +
271 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
272 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
273 scale_fill_gradient(low="gold", high="blue", na.value="white") +
274 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
275 xlab("J genes") +
276 ylab("V Genes")
277
278 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
279 print(img)
280 dev.off()
281 write.table(x=acast(dat, Top.V.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapVJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
282 }
283
284 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
285
286 VandJCount$l = log(VandJCount$Length)
287 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
288 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
289 VandJCount$relLength = VandJCount$l / VandJCount$max
290
291 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
292
293 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
294 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
295 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
296 VJList = split(completeVJ, f=completeVJ[,"Sample"])
297 lapply(VJList, FUN=plotVJ)
298
299 plotDJ <- function(dat){
300 if(length(dat[,1]) == 0){
301 return()
302 }
303 img = ggplot() +
304 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
305 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
306 scale_fill_gradient(low="gold", high="blue", na.value="white") +
307 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
308 xlab("J genes") +
309 ylab("D Genes")
310
311 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
312 print(img)
313 dev.off()
314 write.table(x=acast(dat, Top.D.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapDJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
315 }
316
317 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
318
319 DandJCount$l = log(DandJCount$Length)
320 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
321 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
322 DandJCount$relLength = DandJCount$l / DandJCount$max
323
324 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
325
326 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
327 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
328 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
329 DJList = split(completeDJ, f=completeDJ[,"Sample"])
330 lapply(DJList, FUN=plotDJ)
331
332
333 sampleFile <- file("samples.txt")
334 un = unique(test$Sample)
335 un = paste(un, sep="\n")
336 writeLines(un, sampleFile)
337 close(sampleFile)
338
339
340 if("Replicate" %in% colnames(test))
341 {
342 clonalityFrame = PROD
343 clonalityFrame$ReplicateConcat = do.call(paste, c(clonalityFrame[c("VDJCDR3", "Sample", "Replicate")], sep = ":"))
344 clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ]
345 write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T)
346
347 ClonalitySampleReplicatePrint <- function(dat){
348 write.table(dat, paste("clonality_", unique(dat$Sample) , "_", unique(dat$Replicate), ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
349 }
350
351 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,c("Sample", "Replicate")])
352 #lapply(clonalityFrameSplit, FUN=ClonalitySampleReplicatePrint)
353
354 ClonalitySamplePrint <- function(dat){
355 write.table(dat, paste("clonality_", unique(dat$Sample) , ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
356 }
357
358 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,"Sample"])
359 #lapply(clonalityFrameSplit, FUN=ClonalitySamplePrint)
360
361 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "VDJCDR3")])
362 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
363 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
364 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
365 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
366
367 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
368 tcct = textConnection(ct)
369 CT = read.table(tcct, sep="\t", header=TRUE)
370 close(tcct)
371 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
372 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
373
374 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "VDJCDR3")])
375 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
376 clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads)
377 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
378
379 ReplicatePrint <- function(dat){
380 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
381 }
382
383 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
384 lapply(ReplicateSplit, FUN=ReplicatePrint)
385
386 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")])
387 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
388
389
390 ReplicateSumPrint <- function(dat){
391 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
392 }
393
394 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
395 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
396
397 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
398 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
399 clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow
400 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
401 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
402
403 ClonalityScorePrint <- function(dat){
404 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
405 }
406
407 clonalityScore = clonalFreqCount[c("Sample", "Result")]
408 clonalityScore = unique(clonalityScore)
409
410 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
411 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
412
413 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
414
415
416
417 ClonalityOverviewPrint <- function(dat){
418 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
419 }
420
421 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
422 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
423 }
424
425 if("Functionality" %in% colnames(test))
426 {
427 newData = data.frame(data.table(PROD)[,list(unique=.N,
428 VH.DEL=mean(X3V.REGION.trimmed.nt.nb),
429 P1=mean(P3V.nt.nb),
430 N1=mean(N1.REGION.nt.nb),
431 P2=mean(P5D.nt.nb),
432 DEL.DH=mean(X5D.REGION.trimmed.nt.nb),
433 DH.DEL=mean(X3D.REGION.trimmed.nt.nb),
434 P3=mean(P3D.nt.nb),
435 N2=mean(N2.REGION.nt.nb),
436 P4=mean(P5J.nt.nb),
437 DEL.JH=mean(X5J.REGION.trimmed.nt.nb),
438 Total.Del=( mean(X3V.REGION.trimmed.nt.nb) +
439 mean(X5D.REGION.trimmed.nt.nb) +
440 mean(X3D.REGION.trimmed.nt.nb) +
441 mean(X5J.REGION.trimmed.nt.nb)),
442
443 Total.N=( mean(N1.REGION.nt.nb) +
444 mean(N2.REGION.nt.nb)),
445
446 Total.P=( mean(P3V.nt.nb) +
447 mean(P5D.nt.nb) +
448 mean(P3D.nt.nb) +
449 mean(P5J.nt.nb))),
450 by=c("Sample")])
451 write.table(newData, "junctionAnalysis.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
452 }