Mercurial > repos > davidvanzessen > report_clonality_igg

changeset 25:ea5c2a2cc1f3 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Mon, 09 Feb 2015 05:02:33 -0500
parents 5454af6fece1
children 01f05258f672
files RScript.r
diffstat 1 files changed, 8 insertions(+), 7 deletions(-) [+]
line wrap: on
line diff
--- a/RScript.r	Fri Jan 23 03:06:43 2015 -0500
+++ b/RScript.r	Mon Feb 09 05:02:33 2015 -0500
@@ -64,11 +64,18 @@
   }
 }
 
+clonalityFrame = PRODF
+
 #remove duplicates based on the clonaltype
 if(clonaltype != "none"){
   clonaltype = paste(clonaltype, ",Sample", sep="") #add sample column to clonaltype, unique within samples
   PRODF$clonaltype = do.call(paste, c(PRODF[unlist(strsplit(clonaltype, ","))], sep = ":"))
   PRODF = PRODF[!duplicated(PRODF$clonaltype), ]
+  
+  #again for clonalityFrame but with sample+replicate
+  clonalityFrame$clonaltype = do.call(paste, c(clonalityFrame[unlist(strsplit(clonaltype, ","))], sep = ":"))
+  clonalityFrame$clonality_clonaltype = do.call(paste, c(clonalityFrame[unlist(strsplit(paste(clonaltype, ",Replicate", sep=""), ","))], sep = ":"))
+  clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$clonality_clonaltype), ]
 }
 
 PRODF$freq = 1
@@ -443,12 +450,6 @@
 
 if("Replicate" %in% colnames(inputdata)) #can only calculate clonality score when replicate information is available
 {
-  clonalityFrame = inputdata
-  if(clonaltype != "none"){
-    clonalityFrame$clonaltype = do.call(paste, c(clonalityFrame[unlist(strsplit(clonaltype, ","))], sep = ":"))
-    clonalityFrame$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){
@@ -478,7 +479,7 @@
   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(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "clonality_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