Mercurial > repos > davidvanzessen > complete_immunerepertoire_igg

comparison RScript_b.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
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 library(ggplot2)
23 if (!("plyr" %in% rownames(installed.packages()))) {
24 install.packages("plyr", repos="http://cran.xl-mirror.nl/")
25 }
26 library(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 V = c("v.name\tchr.orderV")
91 D = c("v.name\tchr.orderD")
92 J = c("v.name\tchr.orderJ")
93
94 if(species == "human"){
95 if(locus == "igh"){
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")
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")
98 J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6")
99 } else if (locus == "igk"){
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")
101 D = c("v.name\tchr.orderD\n")
102 J = c("v.name\tchr.orderJ\nIGKJ1\t1\nIGKJ2\t2\nIGKJ3\t3\nIGKJ4\t4\nIGKJ5\t5")
103 } else if (locus == "igl"){
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")
105 D = c("v.name\tchr.orderD\n")
106 J = c("v.name\tchr.orderJ\nIGLJ1\t1\nIGLJ2\t2\nIGLJ3\t3\nIGLJ6\t4\nIGLJ7\t5")
107 }
108 } else if (species == "mouse"){
109 if(locus == "igh"){
110 cat("mouse igh not yet implemented")
111 } else if (locus == "igk"){
112 cat("mouse igk not yet implemented")
113 } else if (locus == "igl"){
114 cat("mouse igl not yet implemented")
115 }
116 }
117
118 useD = TRUE
119 if(species == "human" && (locus == "igk" || locus == "igl")){
120 useD = FALSE
121 }
122
123 tcV = textConnection(V)
124 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)
126 close(tcV)
127
128 tcD = textConnection(D)
129 Dchain = read.table(tcD, sep="\t", header=TRUE)
130 PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
131 close(tcD)
132
133 tcJ = textConnection(J)
134 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)
136 close(tcJ)
137
138 setwd(outDir)
139
140 write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T)
141
142 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))
144 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)
146
147 png("VPlot.png",width = 1280, height = 720)
148 pV
149 dev.off();
150
151 if(useD){
152 pD = ggplot(PRODFD)
153 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 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
155 write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
156
157 png("DPlot.png",width = 800, height = 600)
158 print(pD)
159 dev.off();
160 }
161
162 pJ = ggplot(PRODFJ)
163 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))
164 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
165 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
166
167 png("JPlot.png",width = 800, height = 600)
168 pJ
169 dev.off();
170
171 VGenes = PRODF[,c("Sample", "Top.V.Gene")]
172 VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene)
173 VGenes = data.frame(data.table(VGenes)[, list(Count=.N), by=c("Sample", "Top.V.Gene")])
174 TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample])
175 VGenes = merge(VGenes, TotalPerSample, by="Sample")
176 VGenes$Frequency = VGenes$Count * 100 / VGenes$total
177 VPlot = ggplot(VGenes)
178 VPlot = VPlot + geom_bar(aes( x = Top.V.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
179 ggtitle("Distribution of V gene families") +
180 ylab("Percentage of sequences")
181 png("VFPlot.png")
182 VPlot
183 dev.off();
184 write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
185
186 if(useD){
187 DGenes = PRODF[,c("Sample", "Top.D.Gene")]
188 DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene)
189 DGenes = data.frame(data.table(DGenes)[, list(Count=.N), by=c("Sample", "Top.D.Gene")])
190 TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample])
191 DGenes = merge(DGenes, TotalPerSample, by="Sample")
192 DGenes$Frequency = DGenes$Count * 100 / DGenes$total
193 DPlot = ggplot(DGenes)
194 DPlot = DPlot + geom_bar(aes( x = Top.D.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
195 ggtitle("Distribution of D gene families") +
196 ylab("Percentage of sequences")
197 png("DFPlot.png")
198 print(DPlot)
199 dev.off();
200 write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
201 }
202
203 JGenes = PRODF[,c("Sample", "Top.J.Gene")]
204 JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene)
205 JGenes = data.frame(data.table(JGenes)[, list(Count=.N), by=c("Sample", "Top.J.Gene")])
206 TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample])
207 JGenes = merge(JGenes, TotalPerSample, by="Sample")
208 JGenes$Frequency = JGenes$Count * 100 / JGenes$total
209 JPlot = ggplot(JGenes)
210 JPlot = JPlot + geom_bar(aes( x = Top.J.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
211 ggtitle("Distribution of J gene families") +
212 ylab("Percentage of sequences")
213 png("JFPlot.png")
214 JPlot
215 dev.off();
216 write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
217
218 CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length.DNA")])
219 TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample])
220 CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample")
221 CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total
222 CDR3LengthPlot = ggplot(CDR3Length)
223 CDR3LengthPlot = CDR3LengthPlot + geom_bar(aes( x = CDR3.Length.DNA, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
224 ggtitle("Length distribution of CDR3") +
225 xlab("CDR3 Length") +
226 ylab("Percentage of sequences")
227 png("CDR3LengthPlot.png",width = 1280, height = 720)
228 CDR3LengthPlot
229 dev.off()
230 write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T)
231
232 revVchain = Vchain
233 revDchain = Dchain
234 revVchain$chr.orderV = rev(revVchain$chr.orderV)
235 revDchain$chr.orderD = rev(revDchain$chr.orderD)
236
237 if(useD){
238 plotVD <- function(dat){
239 if(length(dat[,1]) == 0){
240 return()
241 }
242 img = ggplot() +
243 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
244 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
245 scale_fill_gradient(low="gold", high="blue", na.value="white") +
246 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
247 xlab("D genes") +
248 ylab("V Genes")
249
250 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
251 print(img)
252 dev.off()
253 write.table(x=acast(dat, Top.V.Gene~Top.D.Gene, value.var="Length"), file=paste("HeatmapVD_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
254 }
255
256 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
257
258 VandDCount$l = log(VandDCount$Length)
259 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
260 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
261 VandDCount$relLength = VandDCount$l / VandDCount$max
262
263 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(test$Sample))
264
265 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
266 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
267 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
268 VDList = split(completeVD, f=completeVD[,"Sample"])
269
270 lapply(VDList, FUN=plotVD)
271 }
272
273 plotVJ <- function(dat){
274 if(length(dat[,1]) == 0){
275 return()
276 }
277 cat(paste(unique(dat[3])[1,1]))
278 img = ggplot() +
279 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
280 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
281 scale_fill_gradient(low="gold", high="blue", na.value="white") +
282 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
283 xlab("J genes") +
284 ylab("V Genes")
285
286 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
287 print(img)
288 dev.off()
289 write.table(x=acast(dat, Top.V.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapVJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
290 }
291
292 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
293
294 VandJCount$l = log(VandJCount$Length)
295 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
296 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
297 VandJCount$relLength = VandJCount$l / VandJCount$max
298
299 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
300
301 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
302 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
303 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
304 VJList = split(completeVJ, f=completeVJ[,"Sample"])
305 lapply(VJList, FUN=plotVJ)
306
307 if(useD){
308 plotDJ <- function(dat){
309 if(length(dat[,1]) == 0){
310 return()
311 }
312 img = ggplot() +
313 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
314 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
315 scale_fill_gradient(low="gold", high="blue", na.value="white") +
316 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
317 xlab("J genes") +
318 ylab("D Genes")
319
320 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
321 print(img)
322 dev.off()
323 write.table(x=acast(dat, Top.D.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapDJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
324 }
325
326
327 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
328
329 DandJCount$l = log(DandJCount$Length)
330 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
331 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
332 DandJCount$relLength = DandJCount$l / DandJCount$max
333
334 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
335
336 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
337 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
338 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
339 DJList = split(completeDJ, f=completeDJ[,"Sample"])
340 lapply(DJList, FUN=plotDJ)
341 }
342
343 sampleFile <- file("samples.txt")
344 un = unique(test$Sample)
345 un = paste(un, sep="\n")
346 writeLines(un, sampleFile)
347 close(sampleFile)
348
349
350 if("Replicate" %in% colnames(test))
351 {
352 clonalityFrame = PROD
353 clonalityFrame$ReplicateConcat = do.call(paste, c(clonalityFrame[c("VDJCDR3", "Sample", "Replicate")], sep = ":"))
354 clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ]
355 write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T)
356
357 ClonalitySampleReplicatePrint <- function(dat){
358 write.table(dat, paste("clonality_", unique(dat$Sample) , "_", unique(dat$Replicate), ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
359 }
360
361 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,c("Sample", "Replicate")])
362 #lapply(clonalityFrameSplit, FUN=ClonalitySampleReplicatePrint)
363
364 ClonalitySamplePrint <- function(dat){
365 write.table(dat, paste("clonality_", unique(dat$Sample) , ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
366 }
367
368 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,"Sample"])
369 #lapply(clonalityFrameSplit, FUN=ClonalitySamplePrint)
370
371 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "VDJCDR3")])
372 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
373 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
374 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
375 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
376
377 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
378 tcct = textConnection(ct)
379 CT = read.table(tcct, sep="\t", header=TRUE)
380 close(tcct)
381 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
382 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
383
384 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "VDJCDR3")])
385 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
386 clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads)
387 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
388
389 ReplicatePrint <- function(dat){
390 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
391 }
392
393 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
394 lapply(ReplicateSplit, FUN=ReplicatePrint)
395
396 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")])
397 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
398
399
400 ReplicateSumPrint <- function(dat){
401 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
402 }
403
404 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
405 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
406
407 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
408 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
409 clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow
410 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
411 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
412
413 ClonalityScorePrint <- function(dat){
414 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
415 }
416
417 clonalityScore = clonalFreqCount[c("Sample", "Result")]
418 clonalityScore = unique(clonalityScore)
419
420 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
421 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
422
423 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
424
425
426
427 ClonalityOverviewPrint <- function(dat){
428 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
429 }
430
431 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
432 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
433 }
434
435 if("Functionality" %in% colnames(test))
436 {
437 newData = data.frame(data.table(PROD)[,list(unique=.N,
438 VH.DEL=mean(X3V.REGION.trimmed.nt.nb),
439 P1=mean(P3V.nt.nb),
440 N1=mean(N1.REGION.nt.nb),
441 P2=mean(P5D.nt.nb),
442 DEL.DH=mean(X5D.REGION.trimmed.nt.nb),
443 DH.DEL=mean(X3D.REGION.trimmed.nt.nb),
444 P3=mean(P3D.nt.nb),
445 N2=mean(N2.REGION.nt.nb),
446 P4=mean(P5J.nt.nb),
447 DEL.JH=mean(X5J.REGION.trimmed.nt.nb),
448 Total.Del=( mean(X3V.REGION.trimmed.nt.nb) +
449 mean(X5D.REGION.trimmed.nt.nb) +
450 mean(X3D.REGION.trimmed.nt.nb) +
451 mean(X5J.REGION.trimmed.nt.nb)),
452
453 Total.N=( mean(N1.REGION.nt.nb) +
454 mean(N2.REGION.nt.nb)),
455
456 Total.P=( mean(P3V.nt.nb) +
457 mean(P5D.nt.nb) +
458 mean(P3D.nt.nb) +
459 mean(P5J.nt.nb))),
460 by=c("Sample")])
461 write.table(newData, "junctionAnalysis.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
462 }