|
0
|
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
|
|
6
|
28 if (!("reshape2" %in% rownames(installed.packages()))) {
|
|
|
29 install.packages("reshape2", repos="http://cran.xl-mirror.nl/")
|
|
|
30 }
|
|
|
31 library(reshape2)
|
|
|
32
|
|
0
|
33
|
|
|
34 test = read.table(inFile, sep="\t", header=TRUE, fill=T, comment.char="")
|
|
|
35
|
|
|
36 test = test[test$Sample != "",]
|
|
|
37
|
|
|
38 test$Top.V.Gene = gsub("[*]([0-9]+)", "", test$Top.V.Gene)
|
|
|
39 test$Top.D.Gene = gsub("[*]([0-9]+)", "", test$Top.D.Gene)
|
|
|
40 test$Top.J.Gene = gsub("[*]([0-9]+)", "", test$Top.J.Gene)
|
|
|
41
|
|
|
42 #test$VDJCDR3 = do.call(paste, c(test[c("Top.V.Gene", "Top.D.Gene", "Top.J.Gene","CDR3.Seq.DNA")], sep = ":"))
|
|
|
43 test$VDJCDR3 = do.call(paste, c(test[unlist(strsplit(clonalType, ","))], sep = ":"))
|
|
|
44
|
|
|
45 PROD = test[test$VDJ.Frame != "In-frame with stop codon" & test$VDJ.Frame != "Out-of-frame" & test$CDR3.Found.How != "NOT_FOUND" , ]
|
|
|
46 if("Functionality" %in% colnames(test)) {
|
|
|
47 PROD = test[test$Functionality == "productive" | test$Functionality == "productive (see comment)", ]
|
|
|
48 }
|
|
|
49
|
|
|
50 NONPROD = test[test$VDJ.Frame == "In-frame with stop codon" | test$VDJ.Frame == "Out-of-frame" | test$CDR3.Found.How == "NOT_FOUND" , ]
|
|
|
51
|
|
|
52 #PRODF = PROD[ -1]
|
|
|
53
|
|
|
54 PRODF = PROD
|
|
|
55
|
|
|
56 #PRODF = unique(PRODF)
|
|
|
57 PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ]
|
|
|
58
|
|
|
59 PRODFV = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.V.Gene")])
|
|
|
60 PRODFV$Length = as.numeric(PRODFV$Length)
|
|
|
61 Total = 0
|
|
|
62 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
|
|
|
63 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
|
|
|
64 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
|
|
|
65
|
|
|
66 PRODFD = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.D.Gene")])
|
|
|
67 PRODFD$Length = as.numeric(PRODFD$Length)
|
|
|
68 Total = 0
|
|
|
69 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
|
|
|
70 PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
|
|
|
71 PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))
|
|
|
72
|
|
|
73 PRODFJ = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.J.Gene")])
|
|
|
74 PRODFJ$Length = as.numeric(PRODFJ$Length)
|
|
|
75 Total = 0
|
|
|
76 Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
|
|
|
77 PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
|
|
|
78 PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))
|
|
|
79
|
|
|
80 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")
|
|
|
81 tcV = textConnection(V)
|
|
|
82 Vchain = read.table(tcV, sep="\t", header=TRUE)
|
|
|
83 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
|
|
|
84 close(tcV)
|
|
|
85
|
|
|
86 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")
|
|
|
87 tcD = textConnection(D)
|
|
|
88 Dchain = read.table(tcD, sep="\t", header=TRUE)
|
|
|
89 PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
|
|
|
90 close(tcD)
|
|
|
91
|
|
|
92
|
|
|
93 J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6")
|
|
|
94 tcJ = textConnection(J)
|
|
|
95 Jchain = read.table(tcJ, sep="\t", header=TRUE)
|
|
|
96 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
|
|
|
97 close(tcJ)
|
|
|
98
|
|
|
99 setwd(outDir)
|
|
|
100
|
|
6
|
101 write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T)
|
|
0
|
102
|
|
|
103 pV = ggplot(PRODFV)
|
|
|
104 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))
|
|
|
105 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
|
|
6
|
106 write.table(x=PRODFV, file="VFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
|
|
0
|
107
|
|
|
108 png("VPlot.png",width = 1280, height = 720)
|
|
|
109 pV
|
|
|
110 dev.off();
|
|
|
111
|
|
|
112 pD = ggplot(PRODFD)
|
|
|
113 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))
|
|
|
114 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
|
|
6
|
115 write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
|
|
0
|
116
|
|
|
117 png("DPlot.png",width = 800, height = 600)
|
|
|
118 pD
|
|
|
119 dev.off();
|
|
|
120
|
|
|
121 pJ = ggplot(PRODFJ)
|
|
|
122 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))
|
|
|
123 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
|
|
6
|
124 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
|
|
0
|
125
|
|
|
126 png("JPlot.png",width = 800, height = 600)
|
|
|
127 pJ
|
|
|
128 dev.off();
|
|
|
129
|
|
6
|
130 VGenes = PRODF[,c("Sample", "Top.V.Gene")]
|
|
|
131 VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene)
|
|
|
132 VGenes = data.frame(data.table(VGenes)[, list(Count=.N), by=c("Sample", "Top.V.Gene")])
|
|
|
133 TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample])
|
|
|
134 VGenes = merge(VGenes, TotalPerSample, by="Sample")
|
|
|
135 VGenes$Frequency = VGenes$Count * 100 / VGenes$total
|
|
|
136 VPlot = ggplot(VGenes)
|
|
8
|
137 VPlot = VPlot + geom_bar(aes( x = Top.V.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
|
|
|
138 ggtitle("Distribution of V gene families") +
|
|
|
139 ylab("Percentage of sequences")
|
|
6
|
140 png("VFPlot.png")
|
|
|
141 VPlot
|
|
|
142 dev.off();
|
|
|
143 write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
|
|
|
144
|
|
|
145 DGenes = PRODF[,c("Sample", "Top.D.Gene")]
|
|
|
146 DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene)
|
|
|
147 DGenes = data.frame(data.table(DGenes)[, list(Count=.N), by=c("Sample", "Top.D.Gene")])
|
|
|
148 TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample])
|
|
|
149 DGenes = merge(DGenes, TotalPerSample, by="Sample")
|
|
|
150 DGenes$Frequency = DGenes$Count * 100 / DGenes$total
|
|
|
151 DPlot = ggplot(DGenes)
|
|
8
|
152 DPlot = DPlot + geom_bar(aes( x = Top.D.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
|
|
|
153 ggtitle("Distribution of D gene families") +
|
|
|
154 ylab("Percentage of sequences")
|
|
6
|
155 png("DFPlot.png")
|
|
|
156 DPlot
|
|
|
157 dev.off();
|
|
|
158 write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
|
|
|
159
|
|
|
160 JGenes = PRODF[,c("Sample", "Top.J.Gene")]
|
|
|
161 JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene)
|
|
|
162 JGenes = data.frame(data.table(JGenes)[, list(Count=.N), by=c("Sample", "Top.J.Gene")])
|
|
|
163 TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample])
|
|
|
164 JGenes = merge(JGenes, TotalPerSample, by="Sample")
|
|
|
165 JGenes$Frequency = JGenes$Count * 100 / JGenes$total
|
|
|
166 JPlot = ggplot(JGenes)
|
|
8
|
167 JPlot = JPlot + geom_bar(aes( x = Top.J.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
|
|
|
168 ggtitle("Distribution of J gene families") +
|
|
|
169 ylab("Percentage of sequences")
|
|
6
|
170 png("JFPlot.png")
|
|
|
171 JPlot
|
|
|
172 dev.off();
|
|
|
173 write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
|
|
|
174
|
|
8
|
175 CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length.DNA")])
|
|
|
176 TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample])
|
|
|
177 CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample")
|
|
|
178 CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total
|
|
|
179 CDR3LengthPlot = ggplot(CDR3Length)
|
|
|
180 CDR3LengthPlot = CDR3LengthPlot + geom_bar(aes( x = CDR3.Length.DNA, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
|
|
|
181 ggtitle("Length distribution of CDR3") +
|
|
|
182 xlab("CDR3 Length") +
|
|
|
183 ylab("Percentage of sequences")
|
|
|
184 png("CDR3LengthPlot.png",width = 1280, height = 720)
|
|
|
185 CDR3LengthPlot
|
|
|
186 dev.off()
|
|
|
187 write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T)
|
|
|
188
|
|
0
|
189 revVchain = Vchain
|
|
|
190 revDchain = Dchain
|
|
|
191 revVchain$chr.orderV = rev(revVchain$chr.orderV)
|
|
|
192 revDchain$chr.orderD = rev(revDchain$chr.orderD)
|
|
|
193
|
|
|
194 plotVD <- function(dat){
|
|
|
195 if(length(dat[,1]) == 0){
|
|
|
196 return()
|
|
|
197 }
|
|
|
198 img = ggplot() +
|
|
|
199 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
|
|
|
200 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
|
|
|
201 scale_fill_gradient(low="gold", high="blue", na.value="white") +
|
|
|
202 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
|
|
|
203 xlab("D genes") +
|
|
|
204 ylab("V Genes")
|
|
|
205
|
|
|
206 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
|
|
|
207 print(img)
|
|
6
|
208
|
|
0
|
209 dev.off()
|
|
6
|
210 write.table(x=acast(dat, Top.V.Gene~Top.D.Gene, value.var="Length"), file=paste("HeatmapVD_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
|
|
0
|
211 }
|
|
|
212
|
|
|
213 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
|
|
|
214
|
|
|
215 VandDCount$l = log(VandDCount$Length)
|
|
|
216 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
|
|
|
217 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
|
|
|
218 VandDCount$relLength = VandDCount$l / VandDCount$max
|
|
|
219
|
|
|
220 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(test$Sample))
|
|
|
221
|
|
|
222 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
|
|
|
223 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
|
|
|
224 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
|
|
|
225 VDList = split(completeVD, f=completeVD[,"Sample"])
|
|
|
226
|
|
|
227 lapply(VDList, FUN=plotVD)
|
|
|
228
|
|
|
229
|
|
|
230
|
|
|
231 plotVJ <- function(dat){
|
|
|
232 if(length(dat[,1]) == 0){
|
|
|
233 return()
|
|
|
234 }
|
|
|
235 img = ggplot() +
|
|
|
236 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
|
|
|
237 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
|
|
|
238 scale_fill_gradient(low="gold", high="blue", na.value="white") +
|
|
|
239 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
|
|
|
240 xlab("J genes") +
|
|
|
241 ylab("V Genes")
|
|
|
242
|
|
|
243 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
|
|
|
244 print(img)
|
|
|
245 dev.off()
|
|
6
|
246 write.table(x=acast(dat, Top.V.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapVJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
|
|
0
|
247 }
|
|
|
248
|
|
|
249 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
|
|
|
250
|
|
|
251 VandJCount$l = log(VandJCount$Length)
|
|
|
252 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
|
|
|
253 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
|
|
|
254 VandJCount$relLength = VandJCount$l / VandJCount$max
|
|
|
255
|
|
|
256 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
|
|
|
257
|
|
|
258 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
|
|
|
259 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
|
|
|
260 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
|
|
|
261 VJList = split(completeVJ, f=completeVJ[,"Sample"])
|
|
|
262 lapply(VJList, FUN=plotVJ)
|
|
|
263
|
|
|
264 plotDJ <- function(dat){
|
|
|
265 if(length(dat[,1]) == 0){
|
|
|
266 return()
|
|
|
267 }
|
|
|
268 img = ggplot() +
|
|
|
269 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
|
|
|
270 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
|
|
|
271 scale_fill_gradient(low="gold", high="blue", na.value="white") +
|
|
|
272 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
|
|
|
273 xlab("J genes") +
|
|
|
274 ylab("D Genes")
|
|
|
275
|
|
|
276 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
|
|
|
277 print(img)
|
|
|
278 dev.off()
|
|
6
|
279 write.table(x=acast(dat, Top.D.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapDJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
|
|
0
|
280 }
|
|
|
281
|
|
|
282 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
|
|
|
283
|
|
|
284 DandJCount$l = log(DandJCount$Length)
|
|
|
285 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
|
|
|
286 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
|
|
|
287 DandJCount$relLength = DandJCount$l / DandJCount$max
|
|
|
288
|
|
|
289 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
|
|
|
290
|
|
|
291 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
|
|
|
292 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
|
|
|
293 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
|
|
|
294 DJList = split(completeDJ, f=completeDJ[,"Sample"])
|
|
|
295 lapply(DJList, FUN=plotDJ)
|
|
|
296
|
|
|
297
|
|
|
298 sampleFile <- file("samples.txt")
|
|
|
299 un = unique(test$Sample)
|
|
|
300 un = paste(un, sep="\n")
|
|
|
301 writeLines(un, sampleFile)
|
|
|
302 close(sampleFile)
|
|
|
303
|
|
|
304
|
|
|
305 if("Replicate" %in% colnames(test))
|
|
|
306 {
|
|
|
307 clonalityFrame = PROD
|
|
|
308 clonalityFrame$ReplicateConcat = do.call(paste, c(clonalityFrame[c("VDJCDR3", "Sample", "Replicate")], sep = ":"))
|
|
|
309 clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ]
|
|
6
|
310 write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T)
|
|
0
|
311
|
|
|
312 ClonalitySampleReplicatePrint <- function(dat){
|
|
6
|
313 write.table(dat, paste("clonality_", unique(dat$Sample) , "_", unique(dat$Replicate), ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
|
|
0
|
314 }
|
|
|
315
|
|
|
316 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,c("Sample", "Replicate")])
|
|
5
|
317 #lapply(clonalityFrameSplit, FUN=ClonalitySampleReplicatePrint)
|
|
0
|
318
|
|
|
319 ClonalitySamplePrint <- function(dat){
|
|
6
|
320 write.table(dat, paste("clonality_", unique(dat$Sample) , ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
|
|
0
|
321 }
|
|
|
322
|
|
|
323 clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,"Sample"])
|
|
5
|
324 #lapply(clonalityFrameSplit, FUN=ClonalitySamplePrint)
|
|
0
|
325
|
|
|
326 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "VDJCDR3")])
|
|
|
327 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
|
|
|
328 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
|
|
|
329 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
|
|
|
330 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
|
|
|
331
|
|
|
332 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
|
|
|
333 tcct = textConnection(ct)
|
|
|
334 CT = read.table(tcct, sep="\t", header=TRUE)
|
|
|
335 close(tcct)
|
|
|
336 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
|
|
|
337 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
|
|
|
338
|
|
|
339 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "VDJCDR3")])
|
|
|
340 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
|
|
|
341 clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads)
|
|
|
342 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
|
|
|
343
|
|
|
344 ReplicatePrint <- function(dat){
|
|
|
345 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
|
|
|
346 }
|
|
|
347
|
|
|
348 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
|
|
|
349 lapply(ReplicateSplit, FUN=ReplicatePrint)
|
|
|
350
|
|
|
351 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")])
|
|
|
352 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
|
|
|
353
|
|
|
354
|
|
|
355 ReplicateSumPrint <- function(dat){
|
|
|
356 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
|
|
|
357 }
|
|
|
358
|
|
|
359 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
|
|
|
360 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
|
|
|
361
|
|
|
362 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
|
|
|
363 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
|
|
|
364 clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow
|
|
|
365 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
|
|
|
366 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
|
|
|
367
|
|
|
368 ClonalityScorePrint <- function(dat){
|
|
|
369 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
|
|
|
370 }
|
|
|
371
|
|
|
372 clonalityScore = clonalFreqCount[c("Sample", "Result")]
|
|
|
373 clonalityScore = unique(clonalityScore)
|
|
|
374
|
|
|
375 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
|
|
|
376 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
|
|
|
377
|
|
|
378 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
|
|
|
379
|
|
|
380
|
|
|
381
|
|
|
382 ClonalityOverviewPrint <- function(dat){
|
|
|
383 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
|
|
|
384 }
|
|
|
385
|
|
|
386 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
|
|
|
387 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
|
|
|
388 }
|
|
1
|
389
|
|
|
390 if("Functionality" %in% colnames(test))
|
|
|
391 {
|
|
|
392 newData = data.frame(data.table(PROD)[,list(unique=.N,
|
|
5
|
393 VH.DEL=mean(X3V.REGION.trimmed.nt.nb),
|
|
|
394 P1=mean(P3V.nt.nb),
|
|
|
395 N1=mean(N1.REGION.nt.nb),
|
|
|
396 P2=mean(P5D.nt.nb),
|
|
|
397 DEL.DH=mean(X5D.REGION.trimmed.nt.nb),
|
|
|
398 DH.DEL=mean(X3D.REGION.trimmed.nt.nb),
|
|
|
399 P3=mean(P3D.nt.nb),
|
|
|
400 N2=mean(N2.REGION.nt.nb),
|
|
|
401 P4=mean(P5J.nt.nb),
|
|
|
402 DEL.JH=mean(X5J.REGION.trimmed.nt.nb),
|
|
|
403 Total.Del=( mean(X3V.REGION.trimmed.nt.nb) +
|
|
|
404 mean(X5D.REGION.trimmed.nt.nb) +
|
|
|
405 mean(X3D.REGION.trimmed.nt.nb) +
|
|
|
406 mean(X5J.REGION.trimmed.nt.nb)),
|
|
|
407
|
|
|
408 Total.N=( mean(N1.REGION.nt.nb) +
|
|
|
409 mean(N2.REGION.nt.nb)),
|
|
|
410
|
|
|
411 Total.P=( mean(P3V.nt.nb) +
|
|
|
412 mean(P5D.nt.nb) +
|
|
|
413 mean(P3D.nt.nb) +
|
|
|
414 mean(P5J.nt.nb))),
|
|
|
415 by=c("Sample")])
|
|
1
|
416 write.table(newData, "junctionAnalysis.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
|
|
5
|
417 }
|
