Mercurial > repos > davidvanzessen > combined_immune_repertoire_pipeline

comparison RScript.r @ 0:4e3df2384422 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Wed, 20 Nov 2013 10:00:28 -0500
parents
children 87fb14480352
comparison
equal deleted inserted replaced
-1:000000000000 0:4e3df2384422
1 options( show.error.messages=F, error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )
2
3 args <- commandArgs(trailingOnly = TRUE)
4
5 inFile = args[1]
6 outFile = args[2]
7 outDir = args[3]
8
9 if (!("gridExtra" %in% rownames(installed.packages()))) {
10 install.packages("gridExtra", repos="http://cran.xl-mirror.nl/")
11 }
12 library(gridExtra)
13 if (!("ggplot2" %in% rownames(installed.packages()))) {
14 install.packages("ggplot2", repos="http://cran.xl-mirror.nl/")
15 }
16 require(ggplot2)
17 if (!("plyr" %in% rownames(installed.packages()))) {
18 install.packages("plyr", repos="http://cran.xl-mirror.nl/")
19 }
20 require(plyr)
21
22 if (!("data.table" %in% rownames(installed.packages()))) {
23 install.packages("data.table", repos="http://cran.xl-mirror.nl/")
24 }
25 library(data.table)
26
27
28 test = read.table(inFile, sep="\t", header=TRUE, fill=T)
29
30 test = test[test$Sample != "",]
31
32 test$Top.V.Gene = gsub("[*]([0-9]+)", "", test$Top.V.Gene)
33 test$Top.D.Gene = gsub("[*]([0-9]+)", "", test$Top.D.Gene)
34 test$Top.J.Gene = gsub("[*]([0-9]+)", "", test$Top.J.Gene)
35
36 test$VDJCDR3 = do.call(paste, c(test[c("Top.V.Gene", "Top.D.Gene", "Top.J.Gene","CDR3.Seq.DNA")], sep = ":"))
37
38 PROD = test[test$VDJ.Frame != "In-frame with stop codon" & test$VDJ.Frame != "Out-of-frame" & test$CDR3.Found.How != "NOT_FOUND" , ]
39
40 NONPROD = test[test$VDJ.Frame == "In-frame with stop codon" | test$VDJ.Frame == "Out-of-frame" | test$CDR3.Found.How == "NOT_FOUND" , ]
41
42 #PRODF = PROD[ -1]
43
44 PRODF = PROD
45
46 #PRODF = unique(PRODF)
47 PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ]
48
49 PRODFV = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.V.Gene")])
50 PRODFV$Length = as.numeric(PRODFV$Length)
51 Total = 0
52 Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
53 PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
54 PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
55
56 PRODFD = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.D.Gene")])
57 PRODFD$Length = as.numeric(PRODFD$Length)
58 Total = 0
59 Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
60 PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
61 PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))
62
63 PRODFJ = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.J.Gene")])
64 PRODFJ$Length = as.numeric(PRODFJ$Length)
65 Total = 0
66 Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
67 PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
68 PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))
69
70 V = c("v.name\tchr.orderV\nIGHV7-81\t1\nIGHV3-74\t2\nIGHV3-73\t3\nIGHV3-72\t4\nIGHV3-71\t5\nIGHV2-70\t6\nIGHV1-69\t7\nIGHV3-66\t8\nIGHV3-64\t9\nIGHV4-61\t10\nIGHV4-59\t11\nIGHV1-58\t12\nIGHV3-53\t13\nIGHV3-52\t14\nIGHV5-a\t15\nIGHV5-51\t16\nIGHV3-49\t17\nIGHV3-48\t18\nIGHV3-47\t19\nIGHV1-46\t20\nIGHV1-45\t21\nIGHV3-43\t22\nIGHV4-39\t23\nIGHV3-35\t24\nIGHV4-34\t25\nIGHV3-33\t26\nIGHV4-31\t27\nIGHV4-30-4\t28\nIGHV4-30-2\t29\nIGHV3-30-3\t30\nIGHV3-30\t31\nIGHV4-28\t32\nIGHV2-26\t33\nIGHV1-24\t34\nIGHV3-23\t35\nIGHV3-22\t36\nIGHV3-21\t37\nIGHV3-20\t38\nIGHV3-19\t39\nIGHV1-18\t40\nIGHV3-15\t41\nIGHV3-13\t42\nIGHV3-11\t43\nIGHV3-9\t44\nIGHV1-8\t45\nIGHV3-7\t46\nIGHV2-5\t47\nIGHV7-4-1\t48\nIGHV4-4\t49\nIGHV4-b\t50\nIGHV1-3\t51\nIGHV1-2\t52\nIGHV6-1\t53")
71 tcV = textConnection(V)
72 Vchain = read.table(tcV, sep="\t", header=TRUE)
73 PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
74 close(tcV)
75
76 D = c("v.name\tchr.orderD\nIGHD1-1\t1\nIGHD2-2\t2\nIGHD3-3\t3\nIGHD6-6\t4\nIGHD1-7\t5\nIGHD2-8\t6\nIGHD3-9\t7\nIGHD3-10\t8\nIGHD4-11\t9\nIGHD5-12\t10\nIGHD6-13\t11\nIGHD1-14\t12\nIGHD2-15\t13\nIGHD3-16\t14\nIGHD4-17\t15\nIGHD5-18\t16\nIGHD6-19\t17\nIGHD1-20\t18\nIGHD2-21\t19\nIGHD3-22\t20\nIGHD4-23\t21\nIGHD5-24\t22\nIGHD6-25\t23\nIGHD1-26\t24\nIGHD7-27\t25")
77 tcD = textConnection(D)
78 Dchain = read.table(tcD, sep="\t", header=TRUE)
79 PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
80 close(tcD)
81
82
83 J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6")
84 tcJ = textConnection(J)
85 Jchain = read.table(tcJ, sep="\t", header=TRUE)
86 PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
87 close(tcJ)
88
89 setwd(outDir)
90
91 pV = ggplot(PRODFV)
92 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))
93 pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
94
95 png("VPlot.png",width = 1280, height = 720)
96 pV
97 dev.off();
98
99 pD = ggplot(PRODFD)
100 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))
101 pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
102
103 png("DPlot.png",width = 800, height = 600)
104 pD
105 dev.off();
106
107 pJ = ggplot(PRODFJ)
108 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))
109 pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
110
111 png("JPlot.png",width = 800, height = 600)
112 pJ
113 dev.off();
114
115 revVchain = Vchain
116 revDchain = Dchain
117 revVchain$chr.orderV = rev(revVchain$chr.orderV)
118 revDchain$chr.orderD = rev(revDchain$chr.orderD)
119
120 plotVD <- function(dat){
121 if(length(dat[,1]) == 0){
122 return()
123 }
124 img = ggplot() +
125 geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
126 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
127 scale_fill_gradient(low="gold", high="blue", na.value="white", limits=c(0,1)) +
128 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
129 xlab("D genes") +
130 ylab("V Genes")
131
132 png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
133 print(img)
134 dev.off()
135 }
136
137 VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
138
139 VandDCount$l = log(VandDCount$Length)
140 maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
141 VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
142 VandDCount$relLength = VandDCount$l / VandDCount$max
143
144 cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(test$Sample))
145
146 completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
147 completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
148 completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
149 VDList = split(completeVD, f=completeVD[,"Sample"])
150
151 lapply(VDList, FUN=plotVD)
152
153
154
155 plotVJ <- function(dat){
156 if(length(dat[,1]) == 0){
157 return()
158 }
159 img = ggplot() +
160 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) +
161 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
162 scale_fill_gradient(low="gold", high="blue", na.value="white", limits=c(0,1)) +
163 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
164 xlab("J genes") +
165 ylab("V Genes")
166
167 png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
168 print(img)
169 dev.off()
170 }
171
172 VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
173
174 VandJCount$l = log(VandJCount$Length)
175 maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
176 VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
177 VandJCount$relLength = VandJCount$l / VandJCount$max
178
179 cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
180
181 completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
182 completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
183 completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
184 VJList = split(completeVJ, f=completeVJ[,"Sample"])
185 lapply(VJList, FUN=plotVJ)
186
187 plotDJ <- function(dat){
188 if(length(dat[,1]) == 0){
189 return()
190 }
191 img = ggplot() +
192 geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) +
193 theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
194 scale_fill_gradient(low="gold", high="blue", na.value="white", limits=c(0,1)) +
195 ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) +
196 xlab("J genes") +
197 ylab("D Genes")
198
199 png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
200 print(img)
201 dev.off()
202 }
203
204 DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
205
206 DandJCount$l = log(DandJCount$Length)
207 maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
208 DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
209 DandJCount$relLength = DandJCount$l / DandJCount$max
210
211 cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
212
213 completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
214 completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
215 completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
216 DJList = split(completeDJ, f=completeDJ[,"Sample"])
217 lapply(DJList, FUN=plotDJ)
218
219
220 sampleFile <- file("samples.txt")
221 un = unique(test$Sample)
222 un = paste(un, sep="\n")
223 writeLines(un, sampleFile)
224 close(sampleFile)