Mercurial > repos > davidvanzessen > argalaxy_tools

comparison report_clonality/RScript.r @ 0:f90fbc15b35a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Thu, 16 Jul 2015 08:30:43 -0400
parents
children edbf4fba5fc7
comparison
equal deleted inserted replaced
-1:000000000000 0:f90fbc15b35a
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$freq = 1
98 }
99 }
100
101
102
103 #write the complete dataset that is left over, will be the input if 'none' for clonaltype and 'no' for filterproductive
104 write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T)
105 write.table(UNPROD, "allUnproductive.csv", sep=",",quote=F,row.names=F,col.names=T)
106
107 #write the samples to a file
108 sampleFile <- file("samples.txt")
109 un = unique(inputdata$Sample)
110 un = paste(un, sep="\n")
111 writeLines(un, sampleFile)
112 close(sampleFile)
113
114 # ---------------------- Counting the productive/unproductive and unique sequences ----------------------
115
116 inputdata.dt = data.table(inputdata) #for speed
117
118 if(clonaltype == "none"){
119 ct = c("clonaltype")
120 }
121
122 inputdata.dt$samples_replicates = paste(inputdata.dt$Sample, inputdata.dt$Replicate, sep="_")
123 samples_replicates = c(unique(inputdata.dt$samples_replicates), unique(as.character(inputdata.dt$Sample)))
124 frequency_table = data.frame(ID = samples_replicates[order(samples_replicates)])
125
126
127 sample_productive_count = inputdata.dt[, list(All=.N,
128 Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]),
129 perc_prod = 1,
130 Productive_unique = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",list(count=.N),by=ct]),
131 perc_prod_un = 1,
132 Unproductive= nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",]),
133 perc_unprod = 1,
134 Unproductive_unique =nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",list(count=.N),by=ct]),
135 perc_unprod_un = 1),
136 by=c("Sample")]
137
138 sample_productive_count$perc_prod = round(sample_productive_count$Productive / sample_productive_count$All * 100)
139 sample_productive_count$perc_prod_un = round(sample_productive_count$Productive_unique / sample_productive_count$All * 100)
140
141 sample_productive_count$perc_unprod = round(sample_productive_count$Unproductive / sample_productive_count$All * 100)
142 sample_productive_count$perc_unprod_un = round(sample_productive_count$Unproductive_unique / sample_productive_count$All * 100)
143
144
145 sample_replicate_productive_count = inputdata.dt[, list(All=.N,
146 Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]),
147 perc_prod = 1,
148 Productive_unique = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",list(count=.N),by=ct]),
149 perc_prod_un = 1,
150 Unproductive= nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",]),
151 perc_unprod = 1,
152 Unproductive_unique =nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",list(count=.N),by=ct]),
153 perc_unprod_un = 1),
154 by=c("samples_replicates")]
155
156 sample_replicate_productive_count$perc_prod = round(sample_replicate_productive_count$Productive / sample_replicate_productive_count$All * 100)
157 sample_replicate_productive_count$perc_prod_un = round(sample_replicate_productive_count$Productive_unique / sample_replicate_productive_count$All * 100)
158
159 sample_replicate_productive_count$perc_unprod = round(sample_replicate_productive_count$Unproductive / sample_replicate_productive_count$All * 100)
160 sample_replicate_productive_count$perc_unprod_un = round(sample_replicate_productive_count$Unproductive_unique / sample_replicate_productive_count$All * 100)
161
162 setnames(sample_replicate_productive_count, colnames(sample_productive_count))
163
164 counts = rbind(sample_replicate_productive_count, sample_productive_count)
165 counts = counts[order(counts$Sample),]
166
167 write.table(x=counts, file="productive_counting.txt", sep=",",quote=F,row.names=F,col.names=F)
168
169 # ---------------------- Frequency calculation for V, D and J ----------------------
170
171 PRODFV = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.V.Gene")])
172 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
173 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
174 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
175
176 PRODFD = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.D.Gene")])
177 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
178 PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
179 PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))
180
181 PRODFJ = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.J.Gene")])
182 Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
183 PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
184 PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))
185
186 # ---------------------- Setting up the gene names for the different species/loci ----------------------
187
188 Vchain = ""
189 Dchain = ""
190 Jchain = ""
191
192 if(species == "custom"){
193 print("Custom genes: ")
194 splt = unlist(strsplit(locus, ";"))
195 print(paste("V:", splt[1]))
196 print(paste("D:", splt[2]))
197 print(paste("J:", splt[3]))
198
199 Vchain = unlist(strsplit(splt[1], ","))
200 Vchain = data.frame(v.name = Vchain, chr.orderV = 1:length(Vchain))
201
202 Dchain = unlist(strsplit(splt[2], ","))
203 if(length(Dchain) > 0){
204 Dchain = data.frame(v.name = Dchain, chr.orderD = 1:length(Dchain))
205 } else {
206 Dchain = data.frame(v.name = character(0), chr.orderD = numeric(0))
207 }
208
209 Jchain = unlist(strsplit(splt[3], ","))
210 Jchain = data.frame(v.name = Jchain, chr.orderJ = 1:length(Jchain))
211
212 } else {
213 genes = read.table("genes.txt", sep="\t", header=TRUE, fill=T, comment.char="")
214
215 Vchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "V",c("IMGT.GENE.DB", "chr.order")]
216 colnames(Vchain) = c("v.name", "chr.orderV")
217 Dchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "D",c("IMGT.GENE.DB", "chr.order")]
218 colnames(Dchain) = c("v.name", "chr.orderD")
219 Jchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "J",c("IMGT.GENE.DB", "chr.order")]
220 colnames(Jchain) = c("v.name", "chr.orderJ")
221 }
222 useD = TRUE
223 if(nrow(Dchain) == 0){
224 useD = FALSE
225 cat("No D Genes in this species/locus")
226 }
227 print(paste("useD:", useD))
228
229 # ---------------------- merge with the frequency count ----------------------
230
231 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
232
233 PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
234
235 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
236
237 # ---------------------- Create the V, D and J frequency plots and write the data.frame for every plot to a file ----------------------
238
239 pV = ggplot(PRODFV)
240 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))
241 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
242 write.table(x=PRODFV, file="VFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
243
244 png("VPlot.png",width = 1280, height = 720)
245 pV
246 dev.off();
247
248 if(useD){
249 pD = ggplot(PRODFD)
250 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))
251 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
252 write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
253
254 png("DPlot.png",width = 800, height = 600)
255 print(pD)
256 dev.off();
257 }
258
259 pJ = ggplot(PRODFJ)
260 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))
261 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
262 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
263
264 png("JPlot.png",width = 800, height = 600)
265 pJ
266 dev.off();
267
268 pJ = ggplot(PRODFJ)
269 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))
270 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
271 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
272
273 png("JPlot.png",width = 800, height = 600)
274 pJ
275 dev.off();
276
277 # ---------------------- Now the frequency plots of the V, D and J families ----------------------
278
279 VGenes = PRODF[,c("Sample", "Top.V.Gene")]
280 VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene)
281 VGenes = data.frame(data.table(VGenes)[, list(Count=.N), by=c("Sample", "Top.V.Gene")])
282 TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample])
283 VGenes = merge(VGenes, TotalPerSample, by="Sample")
284 VGenes$Frequency = VGenes$Count * 100 / VGenes$total
285 VPlot = ggplot(VGenes)
286 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)) +
287 ggtitle("Distribution of V gene families") +
288 ylab("Percentage of sequences")
289 png("VFPlot.png")
290 VPlot
291 dev.off();
292 write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
293
294 if(useD){
295 DGenes = PRODF[,c("Sample", "Top.D.Gene")]
296 DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene)
297 DGenes = data.frame(data.table(DGenes)[, list(Count=.N), by=c("Sample", "Top.D.Gene")])
298 TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample])
299 DGenes = merge(DGenes, TotalPerSample, by="Sample")
300 DGenes$Frequency = DGenes$Count * 100 / DGenes$total
301 DPlot = ggplot(DGenes)
302 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)) +
303 ggtitle("Distribution of D gene families") +
304 ylab("Percentage of sequences")
305 png("DFPlot.png")
306 print(DPlot)
307 dev.off();
308 write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
309 }
310
311 JGenes = PRODF[,c("Sample", "Top.J.Gene")]
312 JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene)
313 JGenes = data.frame(data.table(JGenes)[, list(Count=.N), by=c("Sample", "Top.J.Gene")])
314 TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample])
315 JGenes = merge(JGenes, TotalPerSample, by="Sample")
316 JGenes$Frequency = JGenes$Count * 100 / JGenes$total
317 JPlot = ggplot(JGenes)
318 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)) +
319 ggtitle("Distribution of J gene families") +
320 ylab("Percentage of sequences")
321 png("JFPlot.png")
322 JPlot
323 dev.off();
324 write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
325
326 # ---------------------- Plotting the cdr3 length ----------------------
327
328 CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length.DNA")])
329 TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample])
330 CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample")
331 CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total
332 CDR3LengthPlot = ggplot(CDR3Length)
333 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)) +
334 ggtitle("Length distribution of CDR3") +
335 xlab("CDR3 Length") +
336 ylab("Percentage of sequences")
337 png("CDR3LengthPlot.png",width = 1280, height = 720)
338 CDR3LengthPlot
339 dev.off()
340 write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T)
341
342 # ---------------------- Plot the heatmaps ----------------------
343
344
345 #get the reverse order for the V and D genes
346 revVchain = Vchain
347 revDchain = Dchain
348 revVchain$chr.orderV = rev(revVchain$chr.orderV)
349 revDchain$chr.orderD = rev(revDchain$chr.orderD)
350
351 if(useD){
352 plotVD <- function(dat){
353 if(length(dat[,1]) == 0){
354 return()
355 }
356 img = ggplot() +
357 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
358 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
359 scale_fill_gradient(low="gold", high="blue", na.value="white") +
360 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
361 xlab("D genes") +
362 ylab("V Genes")
363
364 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
365 print(img)
366 dev.off()
367 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)
368 }
369
370 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
371
372 VandDCount$l = log(VandDCount$Length)
373 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
374 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
375 VandDCount$relLength = VandDCount$l / VandDCount$max
376
377 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(inputdata$Sample))
378
379 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
380 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
381 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
382 VDList = split(completeVD, f=completeVD[,"Sample"])
383
384 lapply(VDList, FUN=plotVD)
385 }
386
387 plotVJ <- function(dat){
388 if(length(dat[,1]) == 0){
389 return()
390 }
391 cat(paste(unique(dat[3])[1,1]))
392 img = ggplot() +
393 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
394 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
395 scale_fill_gradient(low="gold", high="blue", na.value="white") +
396 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
397 xlab("J genes") +
398 ylab("V Genes")
399
400 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
401 print(img)
402 dev.off()
403 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)
404 }
405
406 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
407
408 VandJCount$l = log(VandJCount$Length)
409 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
410 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
411 VandJCount$relLength = VandJCount$l / VandJCount$max
412
413 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(inputdata$Sample))
414
415 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
416 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
417 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
418 VJList = split(completeVJ, f=completeVJ[,"Sample"])
419 lapply(VJList, FUN=plotVJ)
420
421 if(useD){
422 plotDJ <- function(dat){
423 if(length(dat[,1]) == 0){
424 return()
425 }
426 img = ggplot() +
427 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
428 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
429 scale_fill_gradient(low="gold", high="blue", na.value="white") +
430 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
431 xlab("J genes") +
432 ylab("D Genes")
433
434 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
435 print(img)
436 dev.off()
437 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)
438 }
439
440
441 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
442
443 DandJCount$l = log(DandJCount$Length)
444 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
445 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
446 DandJCount$relLength = DandJCount$l / DandJCount$max
447
448 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(inputdata$Sample))
449
450 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
451 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
452 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
453 DJList = split(completeDJ, f=completeDJ[,"Sample"])
454 lapply(DJList, FUN=plotDJ)
455 }
456
457
458 # ---------------------- calculating the clonality score ----------------------
459
460 if("Replicate" %in% colnames(inputdata)) #can only calculate clonality score when replicate information is available
461 {
462 if(clonality_method == "boyd"){
463 samples = split(clonalityFrame, clonalityFrame$Sample, drop=T)
464
465 for (sample in samples){
466 res = data.frame(paste=character(0))
467 sample_id = unique(sample$Sample)[[1]]
468 for(replicate in unique(sample$Replicate)){
469 tmp = sample[sample$Replicate == replicate,]
470 clone_table = data.frame(table(tmp$clonaltype))
471 clone_col_name = paste("V", replicate, sep="")
472 colnames(clone_table) = c("paste", clone_col_name)
473 res = merge(res, clone_table, by="paste", all=T)
474 }
475
476 res[is.na(res)] = 0
477 infer.result = infer.clonality(as.matrix(res[,2:ncol(res)]))
478
479 write.table(data.table(infer.result[[12]]), file=paste("lymphclon_clonality_", sample_id, ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=F)
480
481 res$type = rowSums(res[,2:ncol(res)])
482
483 coincidence.table = data.frame(table(res$type))
484 colnames(coincidence.table) = c("Coincidence Type", "Raw Coincidence Freq")
485 write.table(coincidence.table, file=paste("lymphclon_coincidences_", sample_id, ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
486 }
487 } else {
488 write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T)
489
490 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "clonaltype")])
491 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
492 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
493 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
494 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
495
496 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
497 tcct = textConnection(ct)
498 CT = read.table(tcct, sep="\t", header=TRUE)
499 close(tcct)
500 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
501 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
502
503 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "clonaltype")])
504 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
505 clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads)
506 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
507
508 ReplicatePrint <- function(dat){
509 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
510 }
511
512 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
513 lapply(ReplicateSplit, FUN=ReplicatePrint)
514
515 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(as.numeric(Reads)), ReadsSquaredSum=sum(as.numeric(squared))), by=c("Sample")])
516 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
517
518 ReplicateSumPrint <- function(dat){
519 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
520 }
521
522 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
523 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
524
525 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
526 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
527 clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow
528 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
529 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
530
531 ClonalityScorePrint <- function(dat){
532 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
533 }
534
535 clonalityScore = clonalFreqCount[c("Sample", "Result")]
536 clonalityScore = unique(clonalityScore)
537
538 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
539 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
540
541 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
542
543
544
545 ClonalityOverviewPrint <- function(dat){
546 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
547 }
548
549 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
550 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
551 }
552 }
553
554 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")
555 if(all(imgtcolumns %in% colnames(inputdata)))
556 {
557 newData = data.frame(data.table(PRODF)[,list(unique=.N,
558 VH.DEL=mean(X3V.REGION.trimmed.nt.nb, na.rm=T),
559 P1=mean(P3V.nt.nb, na.rm=T),
560 N1=mean(N1.REGION.nt.nb, na.rm=T),
561 P2=mean(P5D.nt.nb, na.rm=T),
562 DEL.DH=mean(X5D.REGION.trimmed.nt.nb, na.rm=T),
563 DH.DEL=mean(X3D.REGION.trimmed.nt.nb, na.rm=T),
564 P3=mean(P3D.nt.nb, na.rm=T),
565 N2=mean(N2.REGION.nt.nb, na.rm=T),
566 P4=mean(P5J.nt.nb, na.rm=T),
567 DEL.JH=mean(X5J.REGION.trimmed.nt.nb, na.rm=T),
568 Total.Del=( mean(X3V.REGION.trimmed.nt.nb, na.rm=T) +
569 mean(X5D.REGION.trimmed.nt.nb, na.rm=T) +
570 mean(X3D.REGION.trimmed.nt.nb, na.rm=T) +
571 mean(X5J.REGION.trimmed.nt.nb, na.rm=T)),
572
573 Total.N=( mean(N1.REGION.nt.nb, na.rm=T) +
574 mean(N2.REGION.nt.nb, na.rm=T)),
575
576 Total.P=( mean(P3V.nt.nb, na.rm=T) +
577 mean(P5D.nt.nb, na.rm=T) +
578 mean(P3D.nt.nb, na.rm=T) +
579 mean(P5J.nt.nb, na.rm=T))),
580 by=c("Sample")])
581 write.table(newData, "junctionAnalysisProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
582
583 newData = data.frame(data.table(UNPROD)[,list(unique=.N,
584 VH.DEL=mean(X3V.REGION.trimmed.nt.nb, na.rm=T),
585 P1=mean(P3V.nt.nb, na.rm=T),
586 N1=mean(N1.REGION.nt.nb, na.rm=T),
587 P2=mean(P5D.nt.nb, na.rm=T),
588 DEL.DH=mean(X5D.REGION.trimmed.nt.nb, na.rm=T),
589 DH.DEL=mean(X3D.REGION.trimmed.nt.nb, na.rm=T),
590 P3=mean(P3D.nt.nb, na.rm=T),
591 N2=mean(N2.REGION.nt.nb, na.rm=T),
592 P4=mean(P5J.nt.nb, na.rm=T),
593 DEL.JH=mean(X5J.REGION.trimmed.nt.nb, na.rm=T),
594 Total.Del=( mean(X3V.REGION.trimmed.nt.nb, na.rm=T) +
595 mean(X5D.REGION.trimmed.nt.nb, na.rm=T) +
596 mean(X3D.REGION.trimmed.nt.nb, na.rm=T) +
597 mean(X5J.REGION.trimmed.nt.nb, na.rm=T)),
598
599 Total.N=( mean(N1.REGION.nt.nb, na.rm=T) +
600 mean(N2.REGION.nt.nb, na.rm=T)),
601
602 Total.P=( mean(P3V.nt.nb, na.rm=T) +
603 mean(P5D.nt.nb, na.rm=T) +
604 mean(P3D.nt.nb, na.rm=T) +
605 mean(P5J.nt.nb, na.rm=T))),
606 by=c("Sample")])
607 write.table(newData, "junctionAnalysisUnProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
608 }
609
610 # ---------------------- AA composition in CDR3 ----------------------
611
612 AACDR3 = PRODF[,c("Sample", "CDR3.Seq")]
613
614 TotalPerSample = data.frame(data.table(AACDR3)[, list(total=sum(nchar(as.character(.SD$CDR3.Seq)))), by=Sample])
615
616 AAfreq = list()
617
618 for(i in 1:nrow(TotalPerSample)){
619 sample = TotalPerSample$Sample[i]
620 AAfreq[[i]] = data.frame(table(unlist(strsplit(as.character(AACDR3[AACDR3$Sample == sample,c("CDR3.Seq")]), ""))))
621 AAfreq[[i]]$Sample = sample
622 }
623
624 AAfreq = ldply(AAfreq, data.frame)
625 AAfreq = merge(AAfreq, TotalPerSample, by="Sample", all.x = T)
626 AAfreq$freq_perc = as.numeric(AAfreq$Freq / AAfreq$total * 100)
627
628
629 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")
630 AAfreq = merge(AAfreq, AAorder, by.x='Var1', by.y='AA', all.x=TRUE)
631
632 AAfreq = AAfreq[!is.na(AAfreq$order.aa),]
633
634 AAfreqplot = ggplot(AAfreq)
635 AAfreqplot = AAfreqplot + geom_bar(aes( x=factor(reorder(Var1, order.aa)), y = freq_perc, fill = Sample), stat='identity', position='dodge' )
636 AAfreqplot = AAfreqplot + annotate("rect", xmin = 0.5, xmax = 2.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2)
637 AAfreqplot = AAfreqplot + annotate("rect", xmin = 3.5, xmax = 4.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2)
638 AAfreqplot = AAfreqplot + annotate("rect", xmin = 5.5, xmax = 6.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2)
639 AAfreqplot = AAfreqplot + annotate("rect", xmin = 6.5, xmax = 7.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2)
640 AAfreqplot = AAfreqplot + ggtitle("Amino Acid Composition in the CDR3") + xlab("Amino Acid, from Hydrophilic (left) to Hydrophobic (right)") + ylab("Percentage")
641
642 png("AAComposition.png",width = 1280, height = 720)
643 AAfreqplot
644 dev.off()
645 write.table(AAfreq, "AAComposition.csv" , sep=",",quote=F,na="-",row.names=F,col.names=T)
646
647