comparison report_clonality/RScript.r~ @ 26:28fbbdfd7a87 draft

Uploaded
author davidvanzessen
date Mon, 13 Feb 2017 09:08:46 -0500
parents
children
comparison
equal deleted inserted replaced
25:94765af0db1f 26:28fbbdfd7a87
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 if(!("Functionality" %in% inputdata)){ #add a functionality column to the igblast data
118 inputdata$Functionality = "unproductive"
119 search = (inputdata$VDJ.Frame != "In-frame with stop codon" & inputdata$VDJ.Frame != "Out-of-frame" & inputdata$CDR3.Found.How != "NOT_FOUND")
120 if(sum(search) > 0){
121 inputdata[search,]$Functionality = "productive"
122 }
123 }
124
125 inputdata.dt = data.table(inputdata) #for speed
126
127 if(clonaltype == "none"){
128 ct = c("clonaltype")
129 }
130
131 inputdata.dt$samples_replicates = paste(inputdata.dt$Sample, inputdata.dt$Replicate, sep="_")
132 samples_replicates = c(unique(inputdata.dt$samples_replicates), unique(as.character(inputdata.dt$Sample)))
133 frequency_table = data.frame(ID = samples_replicates[order(samples_replicates)])
134
135
136 sample_productive_count = inputdata.dt[, list(All=.N,
137 Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]),
138 perc_prod = 1,
139 Productive_unique = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",list(count=.N),by=ct]),
140 perc_prod_un = 1,
141 Unproductive= nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",]),
142 perc_unprod = 1,
143 Unproductive_unique =nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",list(count=.N),by=ct]),
144 perc_unprod_un = 1),
145 by=c("Sample")]
146
147 sample_productive_count$perc_prod = round(sample_productive_count$Productive / sample_productive_count$All * 100)
148 sample_productive_count$perc_prod_un = round(sample_productive_count$Productive_unique / sample_productive_count$All * 100)
149
150 sample_productive_count$perc_unprod = round(sample_productive_count$Unproductive / sample_productive_count$All * 100)
151 sample_productive_count$perc_unprod_un = round(sample_productive_count$Unproductive_unique / sample_productive_count$All * 100)
152
153
154 sample_replicate_productive_count = inputdata.dt[, list(All=.N,
155 Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]),
156 perc_prod = 1,
157 Productive_unique = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",list(count=.N),by=ct]),
158 perc_prod_un = 1,
159 Unproductive= nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",]),
160 perc_unprod = 1,
161 Unproductive_unique =nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",list(count=.N),by=ct]),
162 perc_unprod_un = 1),
163 by=c("samples_replicates")]
164
165 sample_replicate_productive_count$perc_prod = round(sample_replicate_productive_count$Productive / sample_replicate_productive_count$All * 100)
166 sample_replicate_productive_count$perc_prod_un = round(sample_replicate_productive_count$Productive_unique / sample_replicate_productive_count$All * 100)
167
168 sample_replicate_productive_count$perc_unprod = round(sample_replicate_productive_count$Unproductive / sample_replicate_productive_count$All * 100)
169 sample_replicate_productive_count$perc_unprod_un = round(sample_replicate_productive_count$Unproductive_unique / sample_replicate_productive_count$All * 100)
170
171 setnames(sample_replicate_productive_count, colnames(sample_productive_count))
172
173 counts = rbind(sample_replicate_productive_count, sample_productive_count)
174 counts = counts[order(counts$Sample),]
175
176 write.table(x=counts, file="productive_counting.txt", sep=",",quote=F,row.names=F,col.names=F)
177
178 # ---------------------- Frequency calculation for V, D and J ----------------------
179
180 PRODFV = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.V.Gene")])
181 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
182 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
183 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
184
185 PRODFD = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.D.Gene")])
186 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
187 PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
188 PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))
189
190 PRODFJ = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.J.Gene")])
191 Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
192 PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
193 PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))
194
195 # ---------------------- Setting up the gene names for the different species/loci ----------------------
196
197 Vchain = ""
198 Dchain = ""
199 Jchain = ""
200
201 if(species == "custom"){
202 print("Custom genes: ")
203 splt = unlist(strsplit(locus, ";"))
204 print(paste("V:", splt[1]))
205 print(paste("D:", splt[2]))
206 print(paste("J:", splt[3]))
207
208 Vchain = unlist(strsplit(splt[1], ","))
209 Vchain = data.frame(v.name = Vchain, chr.orderV = 1:length(Vchain))
210
211 Dchain = unlist(strsplit(splt[2], ","))
212 if(length(Dchain) > 0){
213 Dchain = data.frame(v.name = Dchain, chr.orderD = 1:length(Dchain))
214 } else {
215 Dchain = data.frame(v.name = character(0), chr.orderD = numeric(0))
216 }
217
218 Jchain = unlist(strsplit(splt[3], ","))
219 Jchain = data.frame(v.name = Jchain, chr.orderJ = 1:length(Jchain))
220
221 } else {
222 genes = read.table("genes.txt", sep="\t", header=TRUE, fill=T, comment.char="")
223
224 Vchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "V",c("IMGT.GENE.DB", "chr.order")]
225 colnames(Vchain) = c("v.name", "chr.orderV")
226 Dchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "D",c("IMGT.GENE.DB", "chr.order")]
227 colnames(Dchain) = c("v.name", "chr.orderD")
228 Jchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "J",c("IMGT.GENE.DB", "chr.order")]
229 colnames(Jchain) = c("v.name", "chr.orderJ")
230 }
231 useD = TRUE
232 if(nrow(Dchain) == 0){
233 useD = FALSE
234 cat("No D Genes in this species/locus")
235 }
236 print(paste("useD:", useD))
237
238 # ---------------------- merge with the frequency count ----------------------
239
240 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
241
242 PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
243
244 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
245
246 # ---------------------- Create the V, D and J frequency plots and write the data.frame for every plot to a file ----------------------
247
248 pV = ggplot(PRODFV)
249 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))
250 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
251 write.table(x=PRODFV, file="VFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
252
253 png("VPlot.png",width = 1280, height = 720)
254 pV
255 dev.off();
256
257 if(useD){
258 pD = ggplot(PRODFD)
259 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))
260 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
261 write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
262
263 png("DPlot.png",width = 800, height = 600)
264 print(pD)
265 dev.off();
266 }
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 pJ = ggplot(PRODFJ)
278 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))
279 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
280 write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
281
282 png("JPlot.png",width = 800, height = 600)
283 pJ
284 dev.off();
285
286 # ---------------------- Now the frequency plots of the V, D and J families ----------------------
287
288 VGenes = PRODF[,c("Sample", "Top.V.Gene")]
289 VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene)
290 VGenes = data.frame(data.table(VGenes)[, list(Count=.N), by=c("Sample", "Top.V.Gene")])
291 TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample])
292 VGenes = merge(VGenes, TotalPerSample, by="Sample")
293 VGenes$Frequency = VGenes$Count * 100 / VGenes$total
294 VPlot = ggplot(VGenes)
295 VPlot = VPlot + geom_bar(aes( x = Top.V.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
296 ggtitle("Distribution of V gene families") +
297 ylab("Percentage of sequences")
298 png("VFPlot.png")
299 VPlot
300 dev.off();
301 write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
302
303 if(useD){
304 DGenes = PRODF[,c("Sample", "Top.D.Gene")]
305 DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene)
306 DGenes = data.frame(data.table(DGenes)[, list(Count=.N), by=c("Sample", "Top.D.Gene")])
307 TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample])
308 DGenes = merge(DGenes, TotalPerSample, by="Sample")
309 DGenes$Frequency = DGenes$Count * 100 / DGenes$total
310 DPlot = ggplot(DGenes)
311 DPlot = DPlot + geom_bar(aes( x = Top.D.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
312 ggtitle("Distribution of D gene families") +
313 ylab("Percentage of sequences")
314 png("DFPlot.png")
315 print(DPlot)
316 dev.off();
317 write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
318 }
319
320 JGenes = PRODF[,c("Sample", "Top.J.Gene")]
321 JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene)
322 JGenes = data.frame(data.table(JGenes)[, list(Count=.N), by=c("Sample", "Top.J.Gene")])
323 TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample])
324 JGenes = merge(JGenes, TotalPerSample, by="Sample")
325 JGenes$Frequency = JGenes$Count * 100 / JGenes$total
326 JPlot = ggplot(JGenes)
327 JPlot = JPlot + geom_bar(aes( x = Top.J.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
328 ggtitle("Distribution of J gene families") +
329 ylab("Percentage of sequences")
330 png("JFPlot.png")
331 JPlot
332 dev.off();
333 write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
334
335 # ---------------------- Plotting the cdr3 length ----------------------
336
337 CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length.DNA")])
338 TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample])
339 CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample")
340 CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total
341 CDR3LengthPlot = ggplot(CDR3Length)
342 CDR3LengthPlot = CDR3LengthPlot + geom_bar(aes( x = CDR3.Length.DNA, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
343 ggtitle("Length distribution of CDR3") +
344 xlab("CDR3 Length") +
345 ylab("Percentage of sequences")
346 png("CDR3LengthPlot.png",width = 1280, height = 720)
347 CDR3LengthPlot
348 dev.off()
349 write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T)
350
351 # ---------------------- Plot the heatmaps ----------------------
352
353
354 #get the reverse order for the V and D genes
355 revVchain = Vchain
356 revDchain = Dchain
357 revVchain$chr.orderV = rev(revVchain$chr.orderV)
358 revDchain$chr.orderD = rev(revDchain$chr.orderD)
359
360 if(useD){
361 plotVD <- function(dat){
362 if(length(dat[,1]) == 0){
363 return()
364 }
365 img = ggplot() +
366 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
367 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
368 scale_fill_gradient(low="gold", high="blue", na.value="white") +
369 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
370 xlab("D genes") +
371 ylab("V Genes")
372
373 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
374 print(img)
375 dev.off()
376 write.table(x=acast(dat, Top.V.Gene~Top.D.Gene, value.var="Length"), file=paste("HeatmapVD_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
377 }
378
379 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
380
381 VandDCount$l = log(VandDCount$Length)
382 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
383 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
384 VandDCount$relLength = VandDCount$l / VandDCount$max
385
386 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(inputdata$Sample))
387
388 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
389 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
390 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
391 VDList = split(completeVD, f=completeVD[,"Sample"])
392
393 lapply(VDList, FUN=plotVD)
394 }
395
396 plotVJ <- function(dat){
397 if(length(dat[,1]) == 0){
398 return()
399 }
400 cat(paste(unique(dat[3])[1,1]))
401 img = ggplot() +
402 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
403 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
404 scale_fill_gradient(low="gold", high="blue", na.value="white") +
405 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
406 xlab("J genes") +
407 ylab("V Genes")
408
409 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
410 print(img)
411 dev.off()
412 write.table(x=acast(dat, Top.V.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapVJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
413 }
414
415 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
416
417 VandJCount$l = log(VandJCount$Length)
418 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
419 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
420 VandJCount$relLength = VandJCount$l / VandJCount$max
421
422 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(inputdata$Sample))
423
424 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
425 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
426 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
427 VJList = split(completeVJ, f=completeVJ[,"Sample"])
428 lapply(VJList, FUN=plotVJ)
429
430 if(useD){
431 plotDJ <- function(dat){
432 if(length(dat[,1]) == 0){
433 return()
434 }
435 img = ggplot() +
436 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
437 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
438 scale_fill_gradient(low="gold", high="blue", na.value="white") +
439 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
440 xlab("J genes") +
441 ylab("D Genes")
442
443 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
444 print(img)
445 dev.off()
446 write.table(x=acast(dat, Top.D.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapDJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA)
447 }
448
449
450 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
451
452 DandJCount$l = log(DandJCount$Length)
453 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
454 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
455 DandJCount$relLength = DandJCount$l / DandJCount$max
456
457 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(inputdata$Sample))
458
459 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
460 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
461 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
462 DJList = split(completeDJ, f=completeDJ[,"Sample"])
463 lapply(DJList, FUN=plotDJ)
464 }
465
466
467 # ---------------------- calculating the clonality score ----------------------
468
469 if("Replicate" %in% colnames(inputdata)) #can only calculate clonality score when replicate information is available
470 {
471 if(clonality_method == "boyd"){
472 samples = split(clonalityFrame, clonalityFrame$Sample, drop=T)
473
474 for (sample in samples){
475 res = data.frame(paste=character(0))
476 sample_id = unique(sample$Sample)[[1]]
477 for(replicate in unique(sample$Replicate)){
478 tmp = sample[sample$Replicate == replicate,]
479 clone_table = data.frame(table(tmp$clonaltype))
480 clone_col_name = paste("V", replicate, sep="")
481 colnames(clone_table) = c("paste", clone_col_name)
482 res = merge(res, clone_table, by="paste", all=T)
483 }
484
485 res[is.na(res)] = 0
486 infer.result = infer.clonality(as.matrix(res[,2:ncol(res)]))
487
488 write.table(data.table(infer.result[[12]]), file=paste("lymphclon_clonality_", sample_id, ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=F)
489
490 res$type = rowSums(res[,2:ncol(res)])
491
492 coincidence.table = data.frame(table(res$type))
493 colnames(coincidence.table) = c("Coincidence Type", "Raw Coincidence Freq")
494 write.table(coincidence.table, file=paste("lymphclon_coincidences_", sample_id, ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
495 }
496 } else {
497 write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T)
498
499 clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "clonaltype")])
500 clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
501 clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
502 clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
503 clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
504
505 ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
506 tcct = textConnection(ct)
507 CT = read.table(tcct, sep="\t", header=TRUE)
508 close(tcct)
509 clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
510 clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
511
512 ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "clonaltype")])
513 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
514 clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads)
515 ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
516
517 ReplicatePrint <- function(dat){
518 write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
519 }
520
521 ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
522 lapply(ReplicateSplit, FUN=ReplicatePrint)
523
524 ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(as.numeric(Reads)), ReadsSquaredSum=sum(as.numeric(squared))), by=c("Sample")])
525 clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
526
527 ReplicateSumPrint <- function(dat){
528 write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
529 }
530
531 ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
532 lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
533
534 clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
535 clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
536 clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow
537 clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
538 clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
539
540 ClonalityScorePrint <- function(dat){
541 write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
542 }
543
544 clonalityScore = clonalFreqCount[c("Sample", "Result")]
545 clonalityScore = unique(clonalityScore)
546
547 clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
548 lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
549
550 clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
551
552
553
554 ClonalityOverviewPrint <- function(dat){
555 write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
556 }
557
558 clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
559 lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
560 }
561 }
562
563 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")
564 if(all(imgtcolumns %in% colnames(inputdata)))
565 {
566 print("found IMGT columns, running junction analysis")
567 newData = data.frame(data.table(PRODF)[,list(unique=.N,
568 VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T),
569 P1=mean(.SD$P3V.nt.nb, na.rm=T),
570 N1=mean(.SD$N1.REGION.nt.nb, na.rm=T),
571 P2=mean(.SD$P5D.nt.nb, na.rm=T),
572 DEL.DH=mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T),
573 DH.DEL=mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T),
574 P3=mean(.SD$P3D.nt.nb, na.rm=T),
575 N2=mean(.SD$N2.REGION.nt.nb, na.rm=T),
576 P4=mean(.SD$P5J.nt.nb, na.rm=T),
577 DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T),
578 Total.Del=( mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T) +
579 mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T) +
580 mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T) +
581 mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T)),
582
583 Total.N=( mean(.SD$N1.REGION.nt.nb, na.rm=T) +
584 mean(.SD$N2.REGION.nt.nb, na.rm=T)),
585
586 Total.P=( mean(.SD$P3V.nt.nb, na.rm=T) +
587 mean(.SD$P5D.nt.nb, na.rm=T) +
588 mean(.SD$P3D.nt.nb, na.rm=T) +
589 mean(.SD$P5J.nt.nb, na.rm=T))),
590 by=c("Sample")])
591 print(newData)
592 newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
593 write.table(newData, "junctionAnalysisProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
594
595 newData = data.frame(data.table(UNPROD)[,list(unique=.N,
596 VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T),
597 P1=mean(.SD$P3V.nt.nb, na.rm=T),
598 N1=mean(.SD$N1.REGION.nt.nb, na.rm=T),
599 P2=mean(.SD$P5D.nt.nb, na.rm=T),
600 DEL.DH=mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T),
601 DH.DEL=mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T),
602 P3=mean(.SD$P3D.nt.nb, na.rm=T),
603 N2=mean(.SD$N2.REGION.nt.nb, na.rm=T),
604 P4=mean(.SD$P5J.nt.nb, na.rm=T),
605 DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T),
606 Total.Del=(mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T) +
607 mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T) +
608 mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T) +
609 mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T)),
610 Total.N=( mean(.SD$N1.REGION.nt.nb, na.rm=T) +
611 mean(.SD$N2.REGION.nt.nb, na.rm=T)),
612 Total.P=( mean(.SD$P3V.nt.nb, na.rm=T) +
613 mean(.SD$P5D.nt.nb, na.rm=T) +
614 mean(.SD$P3D.nt.nb, na.rm=T) +
615 mean(.SD$P5J.nt.nb, na.rm=T))),
616 by=c("Sample")])
617 newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
618 write.table(newData, "junctionAnalysisUnProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
619 }
620
621 # ---------------------- AA composition in CDR3 ----------------------
622
623 AACDR3 = PRODF[,c("Sample", "CDR3.Seq")]
624
625 TotalPerSample = data.frame(data.table(AACDR3)[, list(total=sum(nchar(as.character(.SD$CDR3.Seq)))), by=Sample])
626
627 AAfreq = list()
628
629 for(i in 1:nrow(TotalPerSample)){
630 sample = TotalPerSample$Sample[i]
631 AAfreq[[i]] = data.frame(table(unlist(strsplit(as.character(AACDR3[AACDR3$Sample == sample,c("CDR3.Seq")]), ""))))
632 AAfreq[[i]]$Sample = sample
633 }
634
635 AAfreq = ldply(AAfreq, data.frame)
636 AAfreq = merge(AAfreq, TotalPerSample, by="Sample", all.x = T)
637 AAfreq$freq_perc = as.numeric(AAfreq$Freq / AAfreq$total * 100)
638
639
640 AAorder = read.table(sep="\t", header=TRUE, text="order.aa\tAA\n1\tR\n2\tK\n3\tN\n4\tD\n5\tQ\n6\tE\n7\tH\n8\tP\n9\tY\n10\tW\n11\tS\n12\tT\n13\tG\n14\tA\n15\tM\n16\tC\n17\tF\n18\tL\n19\tV\n20\tI")
641 AAfreq = merge(AAfreq, AAorder, by.x='Var1', by.y='AA', all.x=TRUE)
642
643 AAfreq = AAfreq[!is.na(AAfreq$order.aa),]
644
645 AAfreqplot = ggplot(AAfreq)
646 AAfreqplot = AAfreqplot + geom_bar(aes( x=factor(reorder(Var1, order.aa)), y = freq_perc, fill = Sample), stat='identity', position='dodge' )
647 AAfreqplot = AAfreqplot + annotate("rect", xmin = 0.5, xmax = 2.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2)
648 AAfreqplot = AAfreqplot + annotate("rect", xmin = 3.5, xmax = 4.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2)
649 AAfreqplot = AAfreqplot + annotate("rect", xmin = 5.5, xmax = 6.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2)
650 AAfreqplot = AAfreqplot + annotate("rect", xmin = 6.5, xmax = 7.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2)
651 AAfreqplot = AAfreqplot + ggtitle("Amino Acid Composition in the CDR3") + xlab("Amino Acid, from Hydrophilic (left) to Hydrophobic (right)") + ylab("Percentage")
652
653 png("AAComposition.png",width = 1280, height = 720)
654 AAfreqplot
655 dev.off()
656 write.table(AAfreq, "AAComposition.csv" , sep=",",quote=F,na="-",row.names=F,col.names=T)
657
658