##  This source code file is part of the analysis of variable protein complexes (VariableComplexes).
##  Copyright (C) 2016  Murat Iskar, Alessandro Ori
## 
##  This program is free software: you can redistribute it and/or modify
##  it under the terms of the GNU General Public License as published by
##  the Free Software Foundation, either version 3 of the License, or
##  (at your option) any later version.
## 
##  This program is distributed in the hope that it will be useful,
##  but WITHOUT ANY WARRANTY; without even the implied warranty of
##  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
##  GNU General Public License for more details.
## 
##  You should have received a copy of the GNU General Public License
##  along with this program.  If not, see <http://www.gnu.org/licenses/>.
##
##  Please check the publication "Spatiotemporal variation of mammalian protein complex stoichiometries", XXX
##  and the supplementary website: www.bork.embl.de/variable_complexes
##
## preprocessing_id_matching.R
## v1
## Murat Iskar <muratiskar at gmail.com>
## Alessandro Ori <alessandro.ori at embl.de> 
##  20.1.2016
## 
## 
## input files:
## Hansson_etal_Cell_Rep_2012_reprogramming_proteomic_dataset.csv
## Protein-Complexes-Ensembl_Protein_Ids_Mus_musculus.txt
## 
## output files: 
## matched-protein-complexes-reprogramming-dataset.txt
## Reprogramming-dataset-only-Protein-complexes.txt

options(max.print=200)
options(stringsAsFactors=FALSE)

########################################################
########################################################
# INPUTS
########################################################

#DEFINE DATASET, ALREADY LOG2 TRANSFORMED AND WITH ROWNAME = PROTEIN IDs ";" SEPARATED
dataset = read.delim("input-files/Hansson_etal_Cell_Rep_2012_reprogramming_proteomic_dataset.csv", sep=",", row.names=1)
dataset = as.matrix(dataset)

#GET COMPLEXES DEFINITIONS
comps = read.csv("input-files/Protein-Complexes-Ensembl_Protein_Ids_Mus_musculus.txt",sep="\t",quote="",comment.char="",header=TRUE)

#DEFINE SAMPLE NAMES
colnames(dataset) = c("D3.D0.1","D3.D0.2","D6.D3.1","D6.D3.2","D9.D6.1","D9.D6.2","D12.D9.1","D12.D9.2","iPS.D12.1","iPS.D12.2")

##########################################################
comp.sel<-as.character(unique(comps$ProteinComplex))
comps2<-c()
data2<-c()
for(h in 1:length(comp.sel))
{
  print(h)
  subcomp = as.matrix(comps[comps$ProteinComplex==comp.sel[h],])
  subunitRedundantNames = subcomp[,"OrthologEnsemblinMusmusculus"]
  for(m in 1:length(subunitRedundantNames))
  {
    subunitname = unique(unlist(strsplit(as.character(subunitRedundantNames[m]),":")))
    match = c()
    idmatch = c()
    for(s in 1:length(dataset[,1]))
    {
      subjectids = unique(unlist(strsplit(rownames(dataset)[s],";")))
      if(sum(subunitname%in%subjectids))
      {
        if(length(match)==0)
        {
          match = subunitname[subunitname%in%subjectids][1];
          idmatch = s;
        }
        else
        {
          print(c("reporting redundantcase in name matching:",h,m,s,subunitname))
        }
      }
    }
    if(length(match)>0)
    {
      subcomp[m,"OrthologEnsemblinMusmusculus"] = match;
      rownames(dataset)[idmatch] = match;
      comps2 = rbind(comps2,subcomp[m,]);
    }
  }
}



# we only retain complexes having at least 5 members quantified.
comp.count<-table(comps2[,"ProteinComplex"])
compsmin5members<-comps2[comps2[,"ProteinComplex"]%in%names(comp.count)[comp.count>=5],]
# Finally, we also get the subset of the proteomics dataset that matches with the protein complexes.
ProteinCompDataset<-dataset[rownames(dataset)%in%compsmin5members[,3],]

# writing output files that will be used in further analysis.
write.table(compsmin5members,"output-files/matched-protein-complexes-reprogramming-dataset.txt",sep="\t",quote=FALSE,row.names=FALSE)
write.table(ProteinCompDataset,"output-files/Reprogramming-dataset-only-Protein-complexes.txt",sep="\t",quote=FALSE)

writeLines(capture.output(sessionInfo()), "sessionInfo.txt")