comparison RScript.r @ 0:54e18dcfc47c draft default tip

Uploaded

0:54e18dcfc47c

options( show.error.messages=F, error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )

args <- commandArgs(trailingOnly = TRUE)

inFile = args[1]
outFile = args[2]

if (!require("gridExtra")) {
install.packages("gridExtra", repos="http://cran.xl-mirror.nl/") 
}
library (gridExtra)
if (!require("ggplot2")) {
install.packages("ggplot2", repos="http://cran.xl-mirror.nl/") 
}
require(ggplot2)
if (!require("plyr")) {
install.packages("plyr", repos="http://cran.xl-mirror.nl/") 
}			
require(plyr)

test = read.table(inFile, sep="\t", header=TRUE)

test$Top.V.Gene = gsub("[*]([0-9]+)", "", test$Top.V.Gene)
test$Top.D.Gene = gsub("[*]([0-9]+)", "", test$Top.D.Gene)
test$Top.J.Gene = gsub("[*]([0-9]+)", "", test$Top.J.Gene)

test$VDJCDR3 = do.call(paste, c(test[c("Top.V.Gene", "Top.D.Gene", "Top.J.Gene","CDR3.Seq.DNA")], sep = ":"))

PROD = test[test$VDJ.Frame != "In-frame with stop codon" & test$VDJ.Frame != "Out-of-frame" & test$CDR3.Found.How != "NOT_FOUND" , ]

NONPROD = test[test$VDJ.Frame == "In-frame with stop codon" | test$VDJ.Frame == "Out-of-frame" | test$CDR3.Found.How == "NOT_FOUND" , ]

PRODF = PROD[ -1]

#unique(PRODF[duplicated(PRODF),])
#length(row.names(PRODF[duplicated(PRODF),]))

#length(row.names(PRODF))
PRODF = unique(PRODF)
#length(row.names(PRODF))

PRODFV = ddply(PRODF, c("Sample", "Top.V.Gene"), function(x) summary(x$VDJCDR3))
PRODFV$Length = as.numeric(PRODFV$Length)
Total = 0
Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))

PRODFD = ddply(PRODF, c("Sample", "Top.D.Gene"), function(x) summary(x$VDJCDR3))
PRODFD$Length = as.numeric(PRODFD$Length)
Total = 0
Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))

PRODFJ = ddply(PRODF, c("Sample", "Top.J.Gene"), function(x) summary(x$VDJCDR3))
PRODFJ$Length = as.numeric(PRODFJ$Length)
Total = 0
Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))

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")
tcV = textConnection(V)
Vchain = read.table(tcV, sep="\t", header=TRUE)
PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
close(tcV)

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")
tcD = textConnection(D)
Dchain = read.table(tcD, sep="\t", header=TRUE)
PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
close(tcD)


J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6")
tcJ = textConnection(J)
Jchain = read.table(tcJ, sep="\t", header=TRUE)
PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
close(tcJ)

pV = ggplot(PRODFV)
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))
#pV

pD = ggplot(PRODFD)
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))
#pD

pJ = ggplot(PRODFJ)
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))
#pJ

#plotall = grid.arrange(pV, arrangeGrob(pD, pJ, ncol=2), ncol=1, widths=c(1,1.2))
#plotall
#ggsave(outFile, dpi=125)


png(outFile,width = 1920, height = 1200)
print(plotall = grid.arrange(pV, arrangeGrob(pD, pJ, ncol=2), ncol=1, widths=c(1,1.2)))
dev.off()