view RScript.r @ 7:a9053212a462 draft

Uploaded

# ---------------------- load/install packages ----------------------

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

if (!("data.table" %in% rownames(installed.packages()))) {
  install.packages("data.table", repos="http://cran.xl-mirror.nl/") 
}
library(data.table)

if (!("reshape2" %in% rownames(installed.packages()))) {
  install.packages("reshape2", repos="http://cran.xl-mirror.nl/") 
}
library(reshape2)

# ---------------------- parameters ----------------------

args <- commandArgs(trailingOnly = TRUE)

infile = args[1] #path to input file
outfile = args[2] #path to output file
outdir = args[3] #path to output folder (html/images/data)
clonaltype = args[4] #clonaltype definition, or 'none' for no unique filtering
species = args[5] #human or mouse
locus = args[6] # IGH, IGK, IGL, TRB, TRA, TRG or TRD
filterproductive = ifelse(args[7] == "yes", T, F) #should unproductive sequences be filtered out? (yes/no)

# ---------------------- Data preperation ----------------------

inputdata = read.table(infile, sep="\t", header=TRUE, fill=T, comment.char="")

setwd(outdir)

# remove weird rows
inputdata = inputdata[inputdata$Sample != "",] 

#remove the allele from the V,D and J genes
inputdata$Top.V.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.V.Gene)
inputdata$Top.D.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.D.Gene)
inputdata$Top.J.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.J.Gene)
inputdata$clonaltype = 1:nrow(inputdata)
PRODF = inputdata
if(filterproductive){
  if("Functionality" %in% colnames(inputdata)) { # "Functionality" is an IMGT column
    PRODF = inputdata[inputdata$Functionality == "productive" | inputdata$Functionality == "productive (see comment)", ]
  } else {
    PRODF = inputdata[inputdata$VDJ.Frame != "In-frame with stop codon" & inputdata$VDJ.Frame != "Out-of-frame" & inputdata$CDR3.Found.How != "NOT_FOUND" , ]
  }
}

#remove duplicates based on the clonaltype
if(clonaltype != "none"){
  PRODF$clonaltype = do.call(paste, c(PRODF[unlist(strsplit(clonaltype, ","))], sep = ":"))
  PRODF = PRODF[!duplicated(PRODF$clonaltype), ]
}

PRODF$freq = 1

if(any(grepl(pattern="_", x=PRODF$ID))){ #the frequency can be stored in the ID with the pattern ".*_freq_.*"
  PRODF$freq = gsub("^[0-9]+_", "", PRODF$ID)
  PRODF$freq = gsub("_.*", "", PRODF$freq)
  PRODF$freq = as.numeric(PRODF$freq)
  if(any(is.na(PRODF$freq))){ #if there was an "_" in the ID, but not the frequency, go back to frequency of 1 for every sequence
    PRODF$freq = 1
  }
}



#write the complete dataset that is left over, will be the input if 'none' for clonaltype and 'no' for filterproductive
write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T)

#write the samples to a file
sampleFile <- file("samples.txt")
un = unique(inputdata$Sample)
un = paste(un, sep="\n")
writeLines(un, sampleFile)
close(sampleFile)

# ---------------------- Counting the productive/unproductive and unique sequences ----------------------

inputdata.dt = data.table(inputdata) #for speed

ct = unlist(strsplit(clonaltype, ","))
if(clonaltype == "none"){
	ct = c("ID")
}

inputdata.dt$samples_replicates = paste(inputdata.dt$Sample, inputdata.dt$Replicate, sep="_")
samples_replicates = c(unique(inputdata.dt$samples_replicates), unique(as.character(inputdata.dt$Sample)))
frequency_table = data.frame(ID = samples_replicates[order(samples_replicates)])


sample_productive_count = inputdata.dt[, list(All=.N, 
                                              Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]), 
                                              perc_prod = 1,
                                              Productive_unique = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",list(count=.N),by=ct]), 
                                              perc_prod_un = 1,
                                              Unproductive= nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",]),
                                              perc_unprod = 1,
                                              Unproductive_unique =nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",list(count=.N),by=ct]),
                                              perc_unprod_un = 1),
                                       by=c("Sample")]

sample_productive_count$perc_prod = round(sample_productive_count$Productive / sample_productive_count$All * 100)
sample_productive_count$perc_prod_un = round(sample_productive_count$Productive_unique / sample_productive_count$All * 100)

sample_productive_count$perc_unprod = round(sample_productive_count$Unproductive / sample_productive_count$All * 100)
sample_productive_count$perc_unprod_un = round(sample_productive_count$Unproductive_unique / sample_productive_count$All * 100)


sample_replicate_productive_count = inputdata.dt[, list(All=.N, 
                                                        Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]), 
                                                        perc_prod = 1,
                                                        Productive_unique = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",list(count=.N),by=ct]), 
                                                        perc_prod_un = 1,
                                                        Unproductive= nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",]),
                                                        perc_unprod = 1,
                                                        Unproductive_unique =nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",list(count=.N),by=ct]),
                                                        perc_unprod_un = 1),
                                                 by=c("samples_replicates")]

sample_replicate_productive_count$perc_prod = round(sample_replicate_productive_count$Productive / sample_replicate_productive_count$All * 100)
sample_replicate_productive_count$perc_prod_un = round(sample_replicate_productive_count$Productive_unique / sample_replicate_productive_count$All * 100)

sample_replicate_productive_count$perc_unprod = round(sample_replicate_productive_count$Unproductive / sample_replicate_productive_count$All * 100)
sample_replicate_productive_count$perc_unprod_un = round(sample_replicate_productive_count$Unproductive_unique / sample_replicate_productive_count$All * 100)

setnames(sample_replicate_productive_count, colnames(sample_productive_count))

counts = rbind(sample_replicate_productive_count, sample_productive_count)
counts = counts[order(counts$Sample),]

write.table(x=counts, file="productive_counting.txt", sep=",",quote=F,row.names=F,col.names=F)

# ---------------------- Frequency calculation for V, D and J ----------------------

PRODFV = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.V.Gene")])
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 = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.D.Gene")])
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 = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.J.Gene")])
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))

# ---------------------- Setting up the gene names for the different T/B, human/mouse and locus ----------------------

V = c("v.name\tchr.orderV\n")
D = c("v.name\tchr.orderD\n")  
J = c("v.name\tchr.orderJ\n")

if(species == "human"){
  if(locus == "trb"){		
    V = c("v.name\tchr.orderV\nTRBV2\t1\nTRBV3-1\t2\nTRBV4-1\t3\nTRBV5-1\t4\nTRBV6-1\t5\nTRBV4-2\t6\nTRBV6-2\t7\nTRBV4-3\t8\nTRBV6-3\t9\nTRBV7-2\t10\nTRBV6-4\t11\nTRBV7-3\t12\nTRBV9\t13\nTRBV10-1\t14\nTRBV11-1\t15\nTRBV10-2\t16\nTRBV11-2\t17\nTRBV6-5\t18\nTRBV7-4\t19\nTRBV5-4\t20\nTRBV6-6\t21\nTRBV5-5\t22\nTRBV7-6\t23\nTRBV5-6\t24\nTRBV6-8\t25\nTRBV7-7\t26\nTRBV6-9\t27\nTRBV7-8\t28\nTRBV5-8\t29\nTRBV7-9\t30\nTRBV13\t31\nTRBV10-3\t32\nTRBV11-3\t33\nTRBV12-3\t34\nTRBV12-4\t35\nTRBV12-5\t36\nTRBV14\t37\nTRBV15\t38\nTRBV16\t39\nTRBV18\t40\nTRBV19\t41\nTRBV20-1\t42\nTRBV24-1\t43\nTRBV25-1\t44\nTRBV27\t45\nTRBV28\t46\nTRBV29-1\t47\nTRBV30\t48")
    D = c("v.name\tchr.orderD\nTRBD1\t1\nTRBD2\t2\n")	
    J = c("v.name\tchr.orderJ\nTRBJ1-1\t1\nTRBJ1-2\t2\nTRBJ1-3\t3\nTRBJ1-4\t4\nTRBJ1-5\t5\nTRBJ1-6\t6\nTRBJ2-1\t7\nTRBJ2-2\t8\nTRBJ2-3\t9\nTRBJ2-4\t10\nTRBJ2-5\t11\nTRBJ2-6\t12\nTRBJ2-7\t13")
  } else if (locus == "tra"){
    V = c("v.name\tchr.orderVTRAV1-1\t1\nTRAV1-2\t2\nTRAV2\t3\nTRAV3\t4\nTRAV4\t5\nTRAV5\t6\nTRAV6\t7\nTRAV7\t8\nTRAV8-1\t9\nTRAV9-1\t10\nTRAV10\t11\nTRAV12-1\t12\nTRAV8-2\t13\nTRAV8-3\t14\nTRAV13-1\t15\nTRAV12-2\t16\nTRAV8-4\t17\nTRAV13-2\t18\nTRAV14/DV4\t19\nTRAV9-2\t20\nTRAV12-3\t21\nTRAV8-6\t22\nTRAV16\t23\nTRAV17\t24\nTRAV18\t25\nTRAV19\t26\nTRAV20\t27\nTRAV21\t28\nTRAV22\t29\nTRAV23/DV6\t30\nTRAV24\t31\nTRAV25\t32\nTRAV26-1\t33\nTRAV27\t34\nTRAV29/DV5\t35\nTRAV30\t36\nTRAV26-2\t37\nTRAV34\t38\nTRAV35\t39\nTRAV36/DV7\t40\nTRAV38-1\t41\nTRAV38-2/DV8\t42\nTRAV39\t43\nTRAV40\t44\nTRAV41\t45\n")
    D = c("v.name\tchr.orderD\n")	
    J = c("v.name\tchr.orderJ\nTRAJ57\t1\nTRAJ56\t2\nTRAJ54\t3\nTRAJ53\t4\nTRAJ52\t5\nTRAJ50\t6\nTRAJ49\t7\nTRAJ48\t8\nTRAJ47\t9\nTRAJ46\t10\nTRAJ45\t11\nTRAJ44\t12\nTRAJ43\t13\nTRAJ42\t14\nTRAJ41\t15\nTRAJ40\t16\nTRAJ39\t17\nTRAJ38\t18\nTRAJ37\t19\nTRAJ36\t20\nTRAJ34\t21\nTRAJ33\t22\nTRAJ32\t23\nTRAJ31\t24\nTRAJ30\t25\nTRAJ29\t26\nTRAJ28\t27\nTRAJ27\t28\nTRAJ26\t29\nTRAJ24\t30\nTRAJ23\t31\nTRAJ22\t32\nTRAJ21\t33\nTRAJ20\t34\nTRAJ18\t35\nTRAJ17\t36\nTRAJ16\t37\nTRAJ15\t38\nTRAJ14\t39\nTRAJ13\t40\nTRAJ12\t41\nTRAJ11\t42\nTRAJ10\t43\nTRAJ9\t44\nTRAJ8\t45\nTRAJ7\t46\nTRAJ6\t47\nTRAJ5\t48\nTRAJ4\t49\nTRAJ3\t50")
  } else if (locus == "trg"){
    V = c("v.name\tchr.orderV\nTRGV9\t1\nTRGV8\t2\nTRGV5\t3\nTRGV4\t4\nTRGV3\t5\nTRGV2\t6")
    D = c("v.name\tchr.orderD\n")	
    J = c("v.name\tchr.orderJ\nTRGJ2\t1\nTRGJP2\t2\nTRGJ1\t3\nTRGJP1\t4")
  } else if (locus == "trd"){
    V = c("v.name\tchr.orderV\nTRDV1\t1\nTRDV2\t2\nTRDV3\t3")
    D = c("v.name\tchr.orderD\nTRDD1\t1\nTRDD2\t2\nTRDD3\t3")	
    J = c("v.name\tchr.orderJ\nTRDJ1\t1\nTRDJ4\t2\nTRDJ2\t3\nTRDJ3\t4")
  } else if(locus == "igh"){
    V = c("v.name\tchr.orderV\nIGHV3-74\t1\nIGHV3-73\t2\nIGHV3-72\t3\nIGHV2-70\t4\nIGHV1-69D\t5\nIGHV1-69-2\t6\nIGHV2-70D\t7\nIGHV1-69\t8\nIGHV3-66\t9\nIGHV3-64\t10\nIGHV4-61\t11\nIGHV4-59\t12\nIGHV1-58\t13\nIGHV3-53\t14\nIGHV5-51\t15\nIGHV3-49\t16\nIGHV3-48\t17\nIGHV1-46\t18\nIGHV1-45\t19\nIGHV3-43\t20\nIGHV4-39\t21\nIGHV3-43D\t22\nIGHV4-38-2\t23\nIGHV4-34\t24\nIGHV3-33\t25\nIGHV4-31\t26\nIGHV3-30-5\t27\nIGHV4-30-4\t28\nIGHV3-30-3\t29\nIGHV4-30-2\t30\nIGHV4-30-1\t31\nIGHV3-30\t32\nIGHV4-28\t33\nIGHV2-26\t34\nIGHV1-24\t35\nIGHV3-23D\t36\nIGHV3-23\t37\nIGHV3-21\t38\nIGHV3-20\t39\nIGHV1-18\t40\nIGHV3-15\t41\nIGHV3-13\t42\nIGHV3-11\t43\nIGHV5-10-1\t44\nIGHV3-9\t45\nIGHV1-8\t46\nIGHV3-64D\t47\nIGHV3-7\t48\nIGHV2-5\t49\nIGHV7-4-1\t50\nIGHV4-4\t51\nIGHV1-3\t52\nIGHV1-2\t53\nIGHV6-1\t54")
    D = c("v.name\tchr.orderD\nIGHD1-7\t1\nIGHD2-8\t2\nIGHD3-9\t3\nIGHD3-10\t4\nIGHD5-12\t5\nIGHD6-13\t6\nIGHD2-15\t7\nIGHD3-16\t8\nIGHD4-17\t9\nIGHD5-18\t10\nIGHD6-19\t11\nIGHD1-20\t12\nIGHD2-21\t13\nIGHD3-22\t14\nIGHD5-24\t15\nIGHD6-25\t16\nIGHD1-26\t17\nIGHD7-27\t18")
    J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6")
  } else if (locus == "igk"){
    V = c("v.name\tchr.orderV\nIGKV3D-7\t1\nIGKV1D-8\t2\nIGKV1D-43\t3\nIGKV3D-11\t4\nIGKV1D-12\t5\nIGKV1D-13\t6\nIGKV3D-15\t7\nIGKV1D-16\t8\nIGKV1D-17\t9\nIGKV3D-20\t10\nIGKV2D-26\t11\nIGKV2D-28\t12\nIGKV2D-29\t13\nIGKV2D-30\t14\nIGKV1D-33\t15\nIGKV1D-39\t16\nIGKV2D-40\t17\nIGKV2-40\t18\nIGKV1-39\t19\nIGKV1-33\t20\nIGKV2-30\t21\nIGKV2-29\t22\nIGKV2-28\t23\nIGKV1-27\t24\nIGKV2-24\t25\nIGKV3-20\t26\nIGKV1-17\t27\nIGKV1-16\t28\nIGKV3-15\t29\nIGKV1-13\t30\nIGKV1-12\t31\nIGKV3-11\t32\nIGKV1-9\t33\nIGKV1-8\t34\nIGKV1-6\t35\nIGKV1-5\t36\nIGKV5-2\t37\nIGKV4-1\t38")
    D = c("v.name\tchr.orderD\n")
    J = c("v.name\tchr.orderJ\nIGKJ1\t1\nIGKJ2\t2\nIGKJ3\t3\nIGKJ4\t4\nIGKJ5\t5")
  } else if (locus == "igl"){
    V = c("v.name\tchr.orderV\nIGLV4-69\t1\nIGLV8-61\t2\nIGLV4-60\t3\nIGLV6-57\t4\nIGLV5-52\t5\nIGLV1-51\t6\nIGLV9-49\t7\nIGLV1-47\t8\nIGLV7-46\t9\nIGLV5-45\t10\nIGLV1-44\t11\nIGLV7-43\t12\nIGLV1-41\t13\nIGLV1-40\t14\nIGLV5-39\t15\nIGLV5-37\t16\nIGLV1-36\t17\nIGLV3-27\t18\nIGLV3-25\t19\nIGLV2-23\t20\nIGLV3-22\t21\nIGLV3-21\t22\nIGLV3-19\t23\nIGLV2-18\t24\nIGLV3-16\t25\nIGLV2-14\t26\nIGLV3-12\t27\nIGLV2-11\t28\nIGLV3-10\t29\nIGLV3-9\t30\nIGLV2-8\t31\nIGLV4-3\t32\nIGLV3-1\t33")
    D = c("v.name\tchr.orderD\n")
    J = c("v.name\tchr.orderJ\nIGLJ1\t1\nIGLJ2\t2\nIGLJ3\t3\nIGLJ6\t4\nIGLJ7\t5")
  }
} else if (species == "mouse"){
  if(locus == "trb"){
    V = c("v.name\tchr.orderV\nTRBV1\t1\nTRBV2\t2\nTRBV3\t3\nTRBV4\t4\nTRBV5\t5\nTRBV12-1\t6\nTRBV13-1\t7\nTRBV12-2\t8\nTRBV13-2\t9\nTRBV13-3\t10\nTRBV14\t11\nTRBV15\t12\nTRBV16\t13\nTRBV17\t14\nTRBV19\t15\nTRBV20\t16\nTRBV23\t17\nTRBV24\t18\nTRBV26\t19\nTRBV29\t20\nTRBV30\t21\nTRBV31\t22")
    D = c("v.name\tchr.orderD\nTRBD1\t1\nTRBD2\t2")
    J = c("v.name\tchr.orderJ\nTRBJ1-1\t1\nTRBJ1-2\t2\nTRBJ1-3\t3\nTRBJ1-4\t4\nTRBJ1-5\t5\nTRBJ2-1\t6\nTRBJ2-2\t7\nTRBJ2-3\t8\nTRBJ2-4\t9\nTRBJ2-5\t10\nTRBJ2-6\t11\nTRBJ2-7\t12")
  } else if (locus == "tra"){
    cat("mouse tra not yet implemented")
  } else if (locus == "trg"){
    cat("mouse trg not yet implemented")
  } else if (locus == "trd"){
    cat("mouse trd not yet implemented")
  } else if(locus == "igh"){
    cat("mouse igh not yet implemented")
  } else if (locus == "igk"){
    cat("mouse igk not yet implemented")
  } else if (locus == "igl"){
    cat("mouse igl not yet implemented")
  }
}

useD = TRUE
if(species == "human" && locus == "tra"){
  useD = FALSE
  cat("No D Genes in this species/locus")
}

# ---------------------- load the gene names into a data.frame and merge with the frequency count ----------------------

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)

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)

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)

# ---------------------- Create the V, D and J frequency plots and write the data.frame for every plot to a file ----------------------

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 = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
write.table(x=PRODFV, file="VFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)

png("VPlot.png",width = 1280, height = 720)
pV
dev.off();

if(useD){
  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 = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
  write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
  
  png("DPlot.png",width = 800, height = 600)
  print(pD)
  dev.off();
}

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 = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)

png("JPlot.png",width = 800, height = 600)
pJ
dev.off();

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 = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)

png("JPlot.png",width = 800, height = 600)
pJ
dev.off();

# ---------------------- Now the frequency plots of the V, D and J families ----------------------

VGenes = PRODF[,c("Sample", "Top.V.Gene")]
VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene)
VGenes = data.frame(data.table(VGenes)[, list(Count=.N), by=c("Sample", "Top.V.Gene")])
TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample])
VGenes = merge(VGenes, TotalPerSample, by="Sample")
VGenes$Frequency = VGenes$Count * 100 / VGenes$total
VPlot = ggplot(VGenes)
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)) + 
  ggtitle("Distribution of V gene families") + 
  ylab("Percentage of sequences")
png("VFPlot.png")
VPlot
dev.off();
write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)

if(useD){
  DGenes = PRODF[,c("Sample", "Top.D.Gene")]
  DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene)
  DGenes = data.frame(data.table(DGenes)[, list(Count=.N), by=c("Sample", "Top.D.Gene")])
  TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample])
  DGenes = merge(DGenes, TotalPerSample, by="Sample")
  DGenes$Frequency = DGenes$Count * 100 / DGenes$total
  DPlot = ggplot(DGenes)
  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)) + 
    ggtitle("Distribution of D gene families") + 
    ylab("Percentage of sequences")
  png("DFPlot.png")
  print(DPlot)
  dev.off();
  write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)
}

JGenes = PRODF[,c("Sample", "Top.J.Gene")]
JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene)
JGenes = data.frame(data.table(JGenes)[, list(Count=.N), by=c("Sample", "Top.J.Gene")])
TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample])
JGenes = merge(JGenes, TotalPerSample, by="Sample")
JGenes$Frequency = JGenes$Count * 100 / JGenes$total
JPlot = ggplot(JGenes)
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)) + 
  ggtitle("Distribution of J gene families") + 
  ylab("Percentage of sequences")
png("JFPlot.png")
JPlot
dev.off();
write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T)

# ---------------------- Plotting the cdr3 length ----------------------

CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length.DNA")])
TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample])
CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample")
CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total
CDR3LengthPlot = ggplot(CDR3Length)
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)) + 
  ggtitle("Length distribution of CDR3") + 
  xlab("CDR3 Length") + 
  ylab("Percentage of sequences")
png("CDR3LengthPlot.png",width = 1280, height = 720)
CDR3LengthPlot
dev.off()
write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T)

# ---------------------- Plot the heatmaps ----------------------


#get the reverse order for the V and D genes
revVchain = Vchain
revDchain = Dchain
revVchain$chr.orderV = rev(revVchain$chr.orderV)
revDchain$chr.orderD = rev(revDchain$chr.orderD)

if(useD){
  plotVD <- function(dat){
    if(length(dat[,1]) == 0){
      return()
    }
    img = ggplot() + 
      geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) + 
      theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
      scale_fill_gradient(low="gold", high="blue", na.value="white") + 
      ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + 
      xlab("D genes") + 
      ylab("V Genes")
    
    png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
    print(img)
    dev.off()
    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)
  }
  
  VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
  
  VandDCount$l = log(VandDCount$Length)
  maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
  VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
  VandDCount$relLength = VandDCount$l / VandDCount$max
  
  cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(inputdata$Sample))
  
  completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
  completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
  completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
  VDList = split(completeVD, f=completeVD[,"Sample"])
  
  lapply(VDList, FUN=plotVD)
}

plotVJ <- function(dat){
  if(length(dat[,1]) == 0){
    return()
  }
  cat(paste(unique(dat[3])[1,1]))
  img = ggplot() + 
    geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) + 
    theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
    scale_fill_gradient(low="gold", high="blue", na.value="white") + 
    ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + 
    xlab("J genes") + 
    ylab("V Genes")
  
  png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
  print(img)
  dev.off()
  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)
}

VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])

VandJCount$l = log(VandJCount$Length)
maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
VandJCount$relLength = VandJCount$l / VandJCount$max

cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(inputdata$Sample))

completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
VJList = split(completeVJ, f=completeVJ[,"Sample"])
lapply(VJList, FUN=plotVJ)

if(useD){
  plotDJ <- function(dat){
    if(length(dat[,1]) == 0){
      return()
    }
    img = ggplot() + 
      geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) + 
      theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
      scale_fill_gradient(low="gold", high="blue", na.value="white") + 
      ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + 
      xlab("J genes") + 
      ylab("D Genes")
    
    png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
    print(img)
    dev.off()
    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)
  }
  
  
  DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
  
  DandJCount$l = log(DandJCount$Length)
  maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
  DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
  DandJCount$relLength = DandJCount$l / DandJCount$max
  
  cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(inputdata$Sample))
  
  completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
  completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
  completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
  DJList = split(completeDJ, f=completeDJ[,"Sample"])
  lapply(DJList, FUN=plotDJ)
}


# ---------------------- calculating the clonality score ----------------------

if("Replicate" %in% colnames(inputdata)) #can only calculate clonality score when replicate information is available
{
  clonalityFrame = inputdata
  if(clonaltype != "none"){
    clonalityFrame$ReplicateConcat = paste(clonalityFrame$clonaltype, clonalityFrame$Sample, clonalityFrame$Replicate, sep = ":")
    clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ]
  }
  write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T)
  
  ClonalitySampleReplicatePrint <- function(dat){
    write.table(dat, paste("clonality_", unique(inputdata$Sample) , "_", unique(dat$Replicate), ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
  }
  
  clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,c("Sample", "Replicate")])
  #lapply(clonalityFrameSplit, FUN=ClonalitySampleReplicatePrint)
  
  ClonalitySamplePrint <- function(dat){
    write.table(dat, paste("clonality_", unique(inputdata$Sample) , ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T)
  }
  
  clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,"Sample"])
  #lapply(clonalityFrameSplit, FUN=ClonalitySamplePrint)
  
  clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "clonaltype")])
  clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
  clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
  clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
  clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
  
  ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
  tcct = textConnection(ct)
  CT  = read.table(tcct, sep="\t", header=TRUE)
  close(tcct)
  clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
  clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
  
  ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "clonaltype")])
  ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
  clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads)
  ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
  
  ReplicatePrint <- function(dat){
    write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
  }
  
  ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
  lapply(ReplicateSplit, FUN=ReplicatePrint)
  
  ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")])
  clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
  
  
  ReplicateSumPrint <- function(dat){
    write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
  }
  
  ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
  lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
  
  clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
  clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
  clonalFreqCount$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow
  clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
  clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
  
  ClonalityScorePrint <- function(dat){
    write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
  }
  
  clonalityScore = clonalFreqCount[c("Sample", "Result")]
  clonalityScore = unique(clonalityScore)
  
  clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
  lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
  
  clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
  
  
  
  ClonalityOverviewPrint <- function(dat){
    write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
  }
  
  clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
  lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
}

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")
if(all(imgtcolumns %in% colnames(inputdata)))
{
  newData = data.frame(data.table(inputdata)[,list(unique=.N, 
                                              VH.DEL=mean(X3V.REGION.trimmed.nt.nb, na.rm=T),
                                              P1=mean(P3V.nt.nb, na.rm=T),
                                              N1=mean(N1.REGION.nt.nb, na.rm=T),
                                              P2=mean(P5D.nt.nb, na.rm=T),
                                              DEL.DH=mean(X5D.REGION.trimmed.nt.nb, na.rm=T),
                                              DH.DEL=mean(X3D.REGION.trimmed.nt.nb, na.rm=T),
                                              P3=mean(P3D.nt.nb, na.rm=T),
                                              N2=mean(N2.REGION.nt.nb, na.rm=T),
                                              P4=mean(P5J.nt.nb, na.rm=T),
                                              DEL.JH=mean(X5J.REGION.trimmed.nt.nb, na.rm=T),
                                              Total.Del=(	mean(X3V.REGION.trimmed.nt.nb, na.rm=T) + 
                                                            mean(X5D.REGION.trimmed.nt.nb, na.rm=T) + 
                                                            mean(X3D.REGION.trimmed.nt.nb, na.rm=T) +
                                                            mean(X5J.REGION.trimmed.nt.nb, na.rm=T)),
                                              
                                              Total.N=(	mean(N1.REGION.nt.nb, na.rm=T) +
                                                          mean(N2.REGION.nt.nb, na.rm=T)),
                                              
                                              Total.P=(	mean(P3V.nt.nb, na.rm=T) +
                                                          mean(P5D.nt.nb, na.rm=T) +
                                                          mean(P3D.nt.nb, na.rm=T) +
                                                          mean(P5J.nt.nb, na.rm=T))),
                                        by=c("Sample")])
  write.table(newData, "junctionAnalysis.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
}