Mercurial > repos > davidvanzessen > argalaxy_tools

comparison report_clonality/RScript.r @ 12:010402c959aa draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Tue, 04 Aug 2015 10:00:20 -0400
parents
children b45a74248628
comparison
equal deleted inserted replaced
11:0510cf1f7cbc 12:010402c959aa
1 # ---------------------- load/install packages ----------------------
2
3 if (!("gridExtra" %in% rownames(installed.packages()))) {
4 install.packages("gridExtra", repos="http://cran.xl-mirror.nl/")
5 }
6 library(gridExtra)
7 if (!("ggplot2" %in% rownames(installed.packages()))) {
8 install.packages("ggplot2", repos="http://cran.xl-mirror.nl/")
9 }
10 library(ggplot2)
11 if (!("plyr" %in% rownames(installed.packages()))) {
12 install.packages("plyr", repos="http://cran.xl-mirror.nl/")
13 }
14 library(plyr)
15
16 if (!("data.table" %in% rownames(installed.packages()))) {
17 install.packages("data.table", repos="http://cran.xl-mirror.nl/")
18 }
19 library(data.table)
20
21 if (!("reshape2" %in% rownames(installed.packages()))) {
22 install.packages("reshape2", repos="http://cran.xl-mirror.nl/")
23 }
24 library(reshape2)
25
26 if (!("lymphclon" %in% rownames(installed.packages()))) {
27 install.packages("lymphclon", repos="http://cran.xl-mirror.nl/")
28 }
29 library(lymphclon)
30
31 # ---------------------- parameters ----------------------
32
33 args <- commandArgs(trailingOnly = TRUE)
34
35 infile = args[1] #path to input file
36 outfile = args[2] #path to output file
37 outdir = args[3] #path to output folder (html/images/data)
38 clonaltype = args[4] #clonaltype definition, or 'none' for no unique filtering
39 ct = unlist(strsplit(clonaltype, ","))
40 species = args[5] #human or mouse
41 locus = args[6] # IGH, IGK, IGL, TRB, TRA, TRG or TRD
42 filterproductive = ifelse(args[7] == "yes", T, F) #should unproductive sequences be filtered out? (yes/no)
43 clonality_method = args[8]
44
45 # ---------------------- Data preperation ----------------------
46
47 inputdata = read.table(infile, sep="\t", header=TRUE, fill=T, comment.char="")
48
49 setwd(outdir)
50
51 # remove weird rows
52 inputdata = inputdata[inputdata$Sample != "",]
53
54 #remove the allele from the V,D and J genes
55 inputdata$Top.V.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.V.Gene)
56 inputdata$Top.D.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.D.Gene)
57 inputdata$Top.J.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.J.Gene)
58
59 inputdata$clonaltype = 1:nrow(inputdata)
60
61 PRODF = inputdata
62 UNPROD = inputdata
63 if(filterproductive){
64 if("Functionality" %in% colnames(inputdata)) { # "Functionality" is an IMGT column
65 PRODF = inputdata[inputdata$Functionality == "productive" | inputdata$Functionality == "productive (see comment)", ]
66 UNPROD = inputdata[!(inputdata$Functionality == "productive" | inputdata$Functionality == "productive (see comment)"), ]
67 } else {
68 PRODF = inputdata[inputdata$VDJ.Frame != "In-frame with stop codon" & inputdata$VDJ.Frame != "Out-of-frame" & inputdata$CDR3.Found.How != "NOT_FOUND" , ]
69 UNPROD = inputdata[!(inputdata$VDJ.Frame != "In-frame with stop codon" & inputdata$VDJ.Frame != "Out-of-frame" & inputdata$CDR3.Found.How != "NOT_FOUND" ), ]
70 }
71 }
72
73 clonalityFrame = PRODF
74
75 #remove duplicates based on the clonaltype
76 if(clonaltype != "none"){
77 clonaltype = paste(clonaltype, ",Sample", sep="") #add sample column to clonaltype, unique within samples
78 PRODF$clonaltype = do.call(paste, c(PRODF[unlist(strsplit(clonaltype, ","))], sep = ":"))
79 PRODF = PRODF[!duplicated(PRODF$clonaltype), ]
80
81 UNPROD$clonaltype = do.call(paste, c(UNPROD[unlist(strsplit(clonaltype, ","))], sep = ":"))
82 UNPROD = UNPROD[!duplicated(UNPROD$clonaltype), ]
83
84 #again for clonalityFrame but with sample+replicate
85 clonalityFrame$clonaltype = do.call(paste, c(clonalityFrame[unlist(strsplit(clonaltype, ","))], sep = ":"))
86 clonalityFrame$clonality_clonaltype = do.call(paste, c(clonalityFrame[unlist(strsplit(paste(clonaltype, ",Replicate", sep=""), ","))], sep = ":"))
87 clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$clonality_clonaltype), ]
88 }
89
90 PRODF$freq = 1
91
92 if(any(grepl(pattern="_", x=PRODF$ID))){ #the frequency can be stored in the ID with the pattern ".*_freq_.*"
93 PRODF$freq = gsub("^[0-9]+_", "", PRODF$ID)
94 PRODF$freq = gsub("_.*", "", PRODF$freq)
95 PRODF$freq = as.numeric(PRODF$freq)
96 if(any(is.na(PRODF$freq))){ #if there was an "_" in the ID, but not the frequency, go back to frequency of 1 for every sequence
97 PRODF$freq = 1
98 }
99 }
100
101
102
103 #write the complete dataset that is left over, will be the input if 'none' for clonaltype and 'no' for filterproductive
104 write.table(PRODF, "allUnique.txt", sep=",",quote=F,row.names=F,col.names=T)
105 write.table(PRODF, "allUnique.csv", sep="\t",quote=F,row.names=F,col.names=T)
106 write.table(UNPROD, "allUnproductive.csv", sep=",",quote=F,row.names=F,col.names=T)
107
108 #write the samples to a file
109 sampleFile <- file("samples.txt")
110 un = unique(inputdata$Sample)
111 un = paste(un, sep="\n")
112 writeLines(un, sampleFile)
113 close(sampleFile)
114
115 # ---------------------- Counting the productive/unproductive and unique sequences ----------------------
116
117 inputdata.dt = data.table(inputdata) #for speed
118
119 if(clonaltype == "none"){
120 ct = c("clonaltype")
121 }
122
123 inputdata.dt$samples_replicates = paste(inputdata.dt$Sample, inputdata.dt$Replicate, sep="_")
124 samples_replicates = c(unique(inputdata.dt$samples_replicates), unique(as.character(inputdata.dt$Sample)))
125 frequency_table = data.frame(ID = samples_replicates[order(samples_replicates)])
126
127
128 sample_productive_count = inputdata.dt[, list(All=.N,
129 Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]),
130 perc_prod = 1,
131 Productive_unique = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",list(count=.N),by=ct]),
132 perc_prod_un = 1,
133 Unproductive= nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",]),
134 perc_unprod = 1,
135 Unproductive_unique =nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",list(count=.N),by=ct]),
136 perc_unprod_un = 1),
137 by=c("Sample")]
138
139 sample_productive_count$perc_prod = round(sample_productive_count$Productive / sample_productive_count$All * 100)
140 sample_productive_count$perc_prod_un = round(sample_productive_count$Productive_unique / sample_productive_count$All * 100)
141
142 sample_productive_count$perc_unprod = round(sample_productive_count$Unproductive / sample_productive_count$All * 100)
143 sample_productive_count$perc_unprod_un = round(sample_productive_count$Unproductive_unique / sample_productive_count$All * 100)
144
145
146 sample_replicate_productive_count = inputdata.dt[, list(All=.N,
147 Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]),
148 perc_prod = 1,
149 Productive_unique = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",list(count=.N),by=ct]),
150 perc_prod_un = 1,
151 Unproductive= nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",]),
152 perc_unprod = 1,
153 Unproductive_unique =nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",list(count=.N),by=ct]),
154 perc_unprod_un = 1),
155 by=c("samples_replicates")]
156
157 sample_replicate_productive_count$perc_prod = round(sample_replicate_productive_count$Productive / sample_replicate_productive_count$All * 100)
158 sample_replicate_productive_count$perc_prod_un = round(sample_replicate_productive_count$Productive_unique / sample_replicate_productive_count$All * 100)
159
160 sample_replicate_productive_count$perc_unprod = round(sample_replicate_productive_count$Unproductive / sample_replicate_productive_count$All * 100)
161 sample_replicate_productive_count$perc_unprod_un = round(sample_replicate_productive_count$Unproductive_unique / sample_replicate_productive_count$All * 100)
162
163 setnames(sample_replicate_productive_count, colnames(sample_productive_count))
164
165 counts = rbind(sample_replicate_productive_count, sample_productive_count)
166 counts = counts[order(counts$Sample),]
167
168 write.table(x=counts, file="productive_counting.txt", sep=",",quote=F,row.names=F,col.names=F)
169
170 # ---------------------- Frequency calculation for V, D and J ----------------------
171
172 PRODFV = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.V.Gene")])
173 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
174 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
175 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
176
177 PRODFD = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.D.Gene")])
178 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
179 PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
180 PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))
181
182 PRODFJ = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.J.Gene")])
183 Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
184 PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
185 PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))
186
187 # ---------------------- Setting up the gene names for the different species/loci ----------------------
188
189 Vchain = ""
190 Dchain = ""
191 Jchain = ""
192
193 if(species == "custom"){
194 print("Custom genes: ")
195 splt = unlist(strsplit(locus, ";"))
196 print(paste("V:", splt[1]))
197 print(paste("D:", splt[2]))
198 print(paste("J:", splt[3]))
199
200 Vchain = unlist(strsplit(splt[1], ","))
201 Vchain = data.frame(v.name = Vchain, chr.orderV = 1:length(Vchain))
202
203 Dchain = unlist(strsplit(splt[2], ","))
204 if(length(Dchain) > 0){
205 Dchain = data.frame(v.name = Dchain, chr.orderD = 1:length(Dchain))
206 } else {
207 Dchain = data.frame(v.name = character(0), chr.orderD = numeric(0))
208 }
209
210 Jchain = unlist(strsplit(splt[3], ","))
211 Jchain = data.frame(v.name = Jchain, chr.orderJ = 1:length(Jchain))
212
213 } else {
214 genes = read.table("genes.txt", sep="\t", header=TRUE, fill=T, comment.char="")
215
216 Vchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "V",c("IMGT.GENE.DB", "chr.order")]
217 colnames(Vchain) = c("v.name", "chr.orderV")
218 Dchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "D",c("IMGT.GENE.DB", "chr.order")]
219 colnames(Dchain) = c("v.name", "chr.orderD")
220 Jchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "J",c("IMGT.GENE.DB", "chr.order")]
221 colnames(Jchain) = c("v.name", "chr.orderJ")
222 }
223 useD = TRUE
224 if(nrow(Dchain) == 0){
225 useD = FALSE
226 cat("No D Genes in this species/locus")
227 }
228 print(paste("useD:", useD))
229
230 # ---------------------- merge with the frequency count ----------------------
231
232 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
233
234 PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
235
236 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
237
238 # ---------------------- Create the V, D and J frequency plots and write the data.frame for every plot to a file ----------------------
239
240 pV = ggplot(PRODFV)
241 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))
242 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
243 write.table(x=PRODFV, file="VFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
244
245 png("VPlot.png",width = 1280, height = 720)
246 pV
247 dev.off();
248
249 if(useD){
250 pD = ggplot(PRODFD)
251 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))
252 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
253 write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
254
255 png("DPlot.png",width = 800, height = 600)
256 print(pD)
257 dev.off();
258 }
259
260 pJ = ggplot(PRODFJ)
261 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))
262 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
263 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
264
265 png("JPlot.png",width = 800, height = 600)
266 pJ
267 dev.off();
268
269 pJ = ggplot(PRODFJ)
270 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))
271 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
272 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
273
274 png("JPlot.png",width = 800, height = 600)
275 pJ
276 dev.off();
277
278 # ---------------------- Now the frequency plots of the V, D and J families ----------------------
279
280 VGenes = PRODF[,c("Sample", "Top.V.Gene")]
281 VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene)
282 VGenes = data.frame(data.table(VGenes)[, list(Count=.N), by=c("Sample", "Top.V.Gene")])
283 TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample])
284 VGenes = merge(VGenes, TotalPerSample, by="Sample")
285 VGenes$Frequency = VGenes$Count * 100 / VGenes$total
286 VPlot = ggplot(VGenes)
287 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)) +
288 ggtitle("Distribution of V gene families") +
289 ylab("Percentage of sequences")
290 png("VFPlot.png")
291 VPlot
292 dev.off();
293 write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
294
295 if(useD){
296 DGenes = PRODF[,c("Sample", "Top.D.Gene")]
297 DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene)
298 DGenes = data.frame(data.table(DGenes)[, list(Count=.N), by=c("Sample", "Top.D.Gene")])
299 TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample])
300 DGenes = merge(DGenes, TotalPerSample, by="Sample")
301 DGenes$Frequency = DGenes$Count * 100 / DGenes$total
302 DPlot = ggplot(DGenes)
303 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)) +
304 ggtitle("Distribution of D gene families") +
305 ylab("Percentage of sequences")
306 png("DFPlot.png")
307 print(DPlot)
308 dev.off();
309 write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
310 }
311
312 JGenes = PRODF[,c("Sample", "Top.J.Gene")]
313 JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene)
314 JGenes = data.frame(data.table(JGenes)[, list(Count=.N), by=c("Sample", "Top.J.Gene")])
315 TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample])
316 JGenes = merge(JGenes, TotalPerSample, by="Sample")
317 JGenes$Frequency = JGenes$Count * 100 / JGenes$total
318 JPlot = ggplot(JGenes)
319 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)) +
320 ggtitle("Distribution of J gene families") +
321 ylab("Percentage of sequences")
322 png("JFPlot.png")
323 JPlot
324 dev.off();
325 write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
326
327 # ---------------------- Plotting the cdr3 length ----------------------
328
329 CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length.DNA")])
330 TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample])
331 CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample")
332 CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total
333 CDR3LengthPlot = ggplot(CDR3Length)
334 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)) +
335 ggtitle("Length distribution of CDR3") +
336 xlab("CDR3 Length") +
337 ylab("Percentage of sequences")
338 png("CDR3LengthPlot.png",width = 1280, height = 720)
339 CDR3LengthPlot
340 dev.off()
341 write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T)
342
343 # ---------------------- Plot the heatmaps ----------------------
344
345
346 #get the reverse order for the V and D genes
347 revVchain = Vchain
348 revDchain = Dchain
349 revVchain$chr.orderV = rev(revVchain$chr.orderV)
350 revDchain$chr.orderD = rev(revDchain$chr.orderD)
351
352 if(useD){
353 plotVD <- function(dat){
354 if(length(dat[,1]) == 0){
355 return()
356 }
357 img = ggplot() +
358 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
359 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
360 scale_fill_gradient(low="gold", high="blue", na.value="white") +
361 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
362 xlab("D genes") +
363 ylab("V Genes")
364
365 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
366 print(img)
367 dev.off()
368 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)
369 }
370
371 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
372
373 VandDCount$l = log(VandDCount$Length)
374 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
375 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
376 VandDCount$relLength = VandDCount$l / VandDCount$max
377
378 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(inputdata$Sample))
379
380 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
381 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
382 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
383 VDList = split(completeVD, f=completeVD[,"Sample"])
384
385 lapply(VDList, FUN=plotVD)
386 }
387
388 plotVJ <- function(dat){
389 if(length(dat[,1]) == 0){
390 return()
391 }
392 cat(paste(unique(dat[3])[1,1]))
393 img = ggplot() +
394 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
395 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
396 scale_fill_gradient(low="gold", high="blue", na.value="white") +
397 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
398 xlab("J genes") +
399 ylab("V Genes")
400
401 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
402 print(img)
403 dev.off()
404 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)
405 }
406
407 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
408
409 VandJCount$l = log(VandJCount$Length)
410 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
411 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
412 VandJCount$relLength = VandJCount$l / VandJCount$max
413
414 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(inputdata$Sample))
415
416 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
417 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
418 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
419 VJList = split(completeVJ, f=completeVJ[,"Sample"])
420 lapply(VJList, FUN=plotVJ)
421
422 if(useD){
423 plotDJ <- function(dat){
424 if(length(dat[,1]) == 0){
425 return()
426 }
427 img = ggplot() +
428 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
429 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
430 scale_fill_gradient(low="gold", high="blue", na.value="white") +
431 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
432 xlab("J genes") +
433 ylab("D Genes")
434
435 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
436 print(img)
437 dev.off()
438 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)
439 }
440
441
442 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
443
444 DandJCount$l = log(DandJCount$Length)
445 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
446 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
447 DandJCount$relLength = DandJCount$l / DandJCount$max
448
449 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(inputdata$Sample))
450
451 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
452 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
453 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
454 DJList = split(completeDJ, f=completeDJ[,"Sample"])
455 lapply(DJList, FUN=plotDJ)
456 }
457
458
459 # ---------------------- calculating the clonality score ----------------------
460
461 if("Replicate" %in% colnames(inputdata)) #can only calculate clonality score when replicate information is available
462 {
463 if(clonality_method == "boyd"){
464 samples = split(clonalityFrame, clonalityFrame$Sample, drop=T)
465
466 for (sample in samples){
467 res = data.frame(paste=character(0))
468 sample_id = unique(sample$Sample)[[1]]
469 for(replicate in unique(sample$Replicate)){
470 tmp = sample[sample$Replicate == replicate,]
471 clone_table = data.frame(table(tmp$clonaltype))
472 clone_col_name = paste("V", replicate, sep="")
473 colnames(clone_table) = c("paste", clone_col_name)
474 res = merge(res, clone_table, by="paste", all=T)
475 }
476
477 res[is.na(res)] = 0
478 infer.result = infer.clonality(as.matrix(res[,2:ncol(res)]))
479
480 write.table(data.table(infer.result[[12]]), file=paste("lymphclon_clonality_", sample_id, ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=F)
481
482 res$type = rowSums(res[,2:ncol(res)])
483
484 coincidence.table = data.frame(table(res$type))
485 colnames(coincidence.table) = c("Coincidence Type", "Raw Coincidence Freq")
486 write.table(coincidence.table, file=paste("lymphclon_coincidences_", sample_id, ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
487 }
488 } else {
489 write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T)
490
491 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "clonaltype")])
492 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
493 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
494 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
495 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
496
497 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
498 tcct = textConnection(ct)
499 CT = read.table(tcct, sep="\t", header=TRUE)
500 close(tcct)
501 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
502 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
503
504 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "clonaltype")])
505 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
506 clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads)
507 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
508
509 ReplicatePrint <- function(dat){
510 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
511 }
512
513 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
514 lapply(ReplicateSplit, FUN=ReplicatePrint)
515
516 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(as.numeric(Reads)), ReadsSquaredSum=sum(as.numeric(squared))), by=c("Sample")])
517 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
518
519 ReplicateSumPrint <- function(dat){
520 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
521 }
522
523 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
524 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
525
526 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
527 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
528 clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow
529 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
530 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
531
532 ClonalityScorePrint <- function(dat){
533 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
534 }
535
536 clonalityScore = clonalFreqCount[c("Sample", "Result")]
537 clonalityScore = unique(clonalityScore)
538
539 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
540 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
541
542 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
543
544
545
546 ClonalityOverviewPrint <- function(dat){
547 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
548 }
549
550 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
551 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
552 }
553 }
554
555 imgtcolumns = c("X3V.REGION.trimmed.nt.nb","P3V.nt.nb", "N1.REGION.nt.nb", "P5D.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "P3D.nt.nb", "N2.REGION.nt.nb", "P5J.nt.nb", "X5J.REGION.trimmed.nt.nb", "X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb")
556 if(all(imgtcolumns %in% colnames(inputdata)))
557 {
558 print("MEAN P3V.nt.nb:")
559 print(PRODF$P3V.nt.nb)
560 print(mean(PRODF$P3V.nt.nb, na.rm=T))
561 print(head(PRODF))
562 newData = data.frame(data.table(PRODF)[,list(unique=.N,
563 VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T),
564 P1=mean(.SD$P3V.nt.nb, na.rm=T),
565 N1=mean(.SD$N1.REGION.nt.nb, na.rm=T),
566 P2=mean(.SD$P5D.nt.nb, na.rm=T),
567 DEL.DH=mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T),
568 DH.DEL=mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T),
569 P3=mean(.SD$P3D.nt.nb, na.rm=T),
570 N2=mean(.SD$N2.REGION.nt.nb, na.rm=T),
571 P4=mean(.SD$P5J.nt.nb, na.rm=T),
572 DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T),
573 Total.Del=( mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T) +
574 mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T) +
575 mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T) +
576 mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T)),
577
578 Total.N=( mean(.SD$N1.REGION.nt.nb, na.rm=T) +
579 mean(.SD$N2.REGION.nt.nb, na.rm=T)),
580
581 Total.P=( mean(.SD$P3V.nt.nb, na.rm=T) +
582 mean(.SD$P5D.nt.nb, na.rm=T) +
583 mean(.SD$P3D.nt.nb, na.rm=T) +
584 mean(.SD$P5J.nt.nb, na.rm=T))),
585 by=c("Sample")])
586 write.table(newData, "junctionAnalysisProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
587
588 newData = data.frame(data.table(UNPROD)[,list(unique=.N,
589 VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T),
590 P1=mean(.SD$P3V.nt.nb, na.rm=T),
591 N1=mean(.SD$N1.REGION.nt.nb, na.rm=T),
592 P2=mean(.SD$P5D.nt.nb, na.rm=T),
593 DEL.DH=mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T),
594 DH.DEL=mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T),
595 P3=mean(.SD$P3D.nt.nb, na.rm=T),
596 N2=mean(.SD$N2.REGION.nt.nb, na.rm=T),
597 P4=mean(.SD$P5J.nt.nb, na.rm=T),
598 DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T),
599 Total.Del=( mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T) +
600 mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T) +
601 mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T) +
602 mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T)),
603
604 Total.N=( mean(.SD$N1.REGION.nt.nb, na.rm=T) +
605 mean(.SD$N2.REGION.nt.nb, na.rm=T)),
606
607 Total.P=( mean(.SD$P3V.nt.nb, na.rm=T) +
608 mean(.SD$P5D.nt.nb, na.rm=T) +
609 mean(.SD$P3D.nt.nb, na.rm=T) +
610 mean(.SD$P5J.nt.nb, na.rm=T))),
611 by=c("Sample")])
612 write.table(newData, "junctionAnalysisUnProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
613 }
614
615 # ---------------------- AA composition in CDR3 ----------------------
616
617 AACDR3 = PRODF[,c("Sample", "CDR3.Seq")]
618
619 TotalPerSample = data.frame(data.table(AACDR3)[, list(total=sum(nchar(as.character(.SD$CDR3.Seq)))), by=Sample])
620
621 AAfreq = list()
622
623 for(i in 1:nrow(TotalPerSample)){
624 sample = TotalPerSample$Sample[i]
625 AAfreq[[i]] = data.frame(table(unlist(strsplit(as.character(AACDR3[AACDR3$Sample == sample,c("CDR3.Seq")]), ""))))
626 AAfreq[[i]]$Sample = sample
627 }
628
629 AAfreq = ldply(AAfreq, data.frame)
630 AAfreq = merge(AAfreq, TotalPerSample, by="Sample", all.x = T)
631 AAfreq$freq_perc = as.numeric(AAfreq$Freq / AAfreq$total * 100)
632
633
634 AAorder = read.table(sep="\t", header=TRUE, text="order.aa\tAA\n1\tR\n2\tK\n3\tN\n4\tD\n5\tQ\n6\tE\n7\tH\n8\tP\n9\tY\n10\tW\n11\tS\n12\tT\n13\tG\n14\tA\n15\tM\n16\tC\n17\tF\n18\tL\n19\tV\n20\tI")
635 AAfreq = merge(AAfreq, AAorder, by.x='Var1', by.y='AA', all.x=TRUE)
636
637 AAfreq = AAfreq[!is.na(AAfreq$order.aa),]
638
639 AAfreqplot = ggplot(AAfreq)
640 AAfreqplot = AAfreqplot + geom_bar(aes( x=factor(reorder(Var1, order.aa)), y = freq_perc, fill = Sample), stat='identity', position='dodge' )
641 AAfreqplot = AAfreqplot + annotate("rect", xmin = 0.5, xmax = 2.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2)
642 AAfreqplot = AAfreqplot + annotate("rect", xmin = 3.5, xmax = 4.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2)
643 AAfreqplot = AAfreqplot + annotate("rect", xmin = 5.5, xmax = 6.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2)
644 AAfreqplot = AAfreqplot + annotate("rect", xmin = 6.5, xmax = 7.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2)
645 AAfreqplot = AAfreqplot + ggtitle("Amino Acid Composition in the CDR3") + xlab("Amino Acid, from Hydrophilic (left) to Hydrophobic (right)") + ylab("Percentage")
646
647 png("AAComposition.png",width = 1280, height = 720)
648 AAfreqplot
649 dev.off()
650 write.table(AAfreq, "AAComposition.csv" , sep=",",quote=F,na="-",row.names=F,col.names=T)
651
652