[R] question

[arun]

HI,
directory<- "/home/arunksa111/NewData"
GetFileList <- function(directory,number){
  setwd(directory)
 filelist1<-dir()[file.info(dir())$isdir]
    direct<-dir(directory,pattern = paste("MSMS_",number,"PepInfo.txt",sep=""), full.names = FALSE, recursive = TRUE)
 direct<-lapply(direct,function(x) paste(directory,"/",x,sep=""))
    lista<-unlist(direct)
 output<- list(filelist1,lista)
 return(output)
    }

 file.list.names<-GetFileList(directory,23) [[1]]
 lista<-GetFileList(directory,23) [[2]]
FacGroup<-c(0,1,1,1,0,2,2,2)

ReadDir<-function(FacGroup){
 list.new<-lista[FacGroup!=0]
 read.list<-lapply(list.new, function(x) read.table(x,header=TRUE, sep = "\t",stringsAsFactors=FALSE))
 names(read.list)<-file.list.names[FacGroup!=0]
 return (read.list)
}

ListFacGroup<-ReadDir(FacGroup)
ListFacGroupSub<-lapply(ListFacGroup,head)


Pro<- function(lista,FDR_k) {
split.list<- split(lista,names(lista))
seq.mod.z<- lapply(seq_along(split.list),function(i) lapply(split.list[[i]],function(x) x[x[["FDR"]]< FDR_k,c("Seq","Mod","z","Pro")]))
names(seq.mod.z)<- names(split.list)
folder.name<-lapply(seq.mod.z,function(x) lapply(names(x),function(i) do.call(rbind,lapply(x[i],function(x) cbind(folder_name=i,x)))))
  library(plyr)
  library(data.table)
merge.data<-lapply(folder.name,function(x) lapply(x,function(x1) {x1<- data.table(x1);x1[,Pro:=paste(Pro,collapse=","),by=c("Seq","Mod","z")]}))
count.Pro<-lapply(merge.data,function(x) lapply(x,function(x1) { x1$counts<-sapply(x1$Pro,function(x2) length(gsub("\\s","",unlist(strsplit(x2,",")))));x3<-as.data.frame(x1);names(x3)[6]<- as.character(unique(x3$folder_name));x3[,-c(1,5)]}))
count.ProUnique<-lapply(count.Pro,function(x) lapply(x,unique))
  #count Pro by group (2-columns)
  Pro.group<-lapply(count.ProUnique,function(x) Reduce(function(...) merge(...,by=c("Seq","Mod","z"),all=TRUE),x))
   #Pro.group1<-Pro.group[lapply(Pro.group,length)!=0]
   res<- Reduce(function(...) merge(...,by=c("Seq","Mod","z"),all=TRUE),Pro.group)
  res[is.na(res)] <- 0
 res<- as.data.frame(res,stringsAsFactors=FALSE)
 res
}

 Pro(ListFacGroupSub,0.05)
#                        Seq                 Mod z c2 c3 c4 t2 t3 t4
#1     aAAAAAAAAAAAAAATATAGPR          1-n_acPro/ 2  0  0  1  1  0  1
#2      aAAAAAAAAAAASSPVGVGQR          1-n_acPro/ 2  0  0  1  1  0  1
#3           aAAAAAAAAAGAAGGR          1-n_acPro/ 2  2  0  2  2  2  2
#4      aAAAAAAAGAAGGRGSGPGRR          1-n_acPro/ 2  0  0  2  0  0  2
#5                AAAAAAAkAAK             8-K_ac/ 2  1  0  0  0  0  0
#6                AAAAAAALQAK                     2  0  2  0  2  0  0
#7             aAAAAAGAGPEMVR          1-n_acPro/ 2  2  2  2  2  2  2
#8            aAAAAATAAAAASIR          1-n_acPro/ 2  0  0  0  0  1  0
#9  aAAAAEQQQFYLLLGNLLSPDNVVR 1-<_Carbamoylation/ 2  0  0  0 18  0  0
#10 aAAAAEQQQFYLLLGNLLSPDNVVR          1-n_acPro/ 2 18  0  0  0  0  0
#11 aAAAAEQQQFYLLLGNLLSPDNVVR          1-n_acPro/ 3  0 18  0  0  0  0
#12           aAAAAVGNAVPCGAR          1-n_acPro/ 2  0  1  0  0  0  0


ProCt<-Pro(ListFacGroup,0.05)
 dim(ProCt)
#[1] 29429     9

A.K.

________________________________
From: Vera Costa <veracosta.rt at gmail.com>
To: arun <smartpink111 at yahoo.com> 
Sent: Thursday, May 16, 2013 1:37 PM
Subject: Re: question



Hi. 

Other thing that I need (and I sent a new format data) is to count data like function spec, but for the variable "pro". The idea is exactly the same, but I'm with some dificulties because the format of the data... The Pro is like ">sp|Q86U42|PABP2_HUMAN,>sp|Q86U42-2|PABP2_HUMAN". The comma split 2 pro's.