comparison add_protein_features.R @ 18:0a9ae3d7dbf2 draft default tip

"planemo upload commit 7afd4b3ee25f024257ccbac6e51076d25b2a04e7"

17:2952bae8a1ea

        --input: input
        --nextprot: path to nextprot information file
        --column: the column number which you would like to apply...
        --header: true/false if your file contains a header
        --type: the type of input IDs (Uniprot_AC/EntrezID)
        --pc_features: IsoPoint,SeqLength,MW
        --localization: Chr,SubcellLocations
        --diseases_info: Diseases
        --output: text output filename \n")
    
    q(save="no")
  }
  

  return(res)
}

# Get information from neXtProt
get_nextprot_info <- function(nextprot,input,pc_features,localization,diseases_info){
  if(diseases_info){
    cols = c("NextprotID",pc_features,localization,"Diseases")
  } else {
    cols = c("NextprotID",pc_features,localization)
  }
  
  cols=cols[cols!="None"]
  info = nextprot[match(input,nextprot$NextprotID),cols]
  return(info)
}

protein_features = function() {

  nextprot = read_file(args$nextprot,T)
  
  # Parse arguments
  id_type = args$type
  pc_features = strsplit(args$pc_features, ",")[[1]]
  localization = strsplit(args$localization, ",")[[1]]
  diseases_info = str2bool(args$diseases_info)
  output = args$output

  # Change the sample ids if they are Uniprot_AC ids to be able to match them with
  # Nextprot data
  if (id_type=="Uniprot_AC"){

  #Select user input protein ids in nextprot
  #NextprotID = unique(NextprotID[which(!is.na(NextprotID[NextprotID!=""]))])
  if (all(!NextprotID %in% nextprot[,1])){
    write.table("None of the input ids can be found in Nextprot",file=output,sep="\t",quote=FALSE,col.names=TRUE,row.names=FALSE)
  } else {
    res <- get_nextprot_info(nextprot,NextprotID,pc_features,localization,diseases_info)
    res = res[!duplicated(res$NextprotID),]
    output_content = merge(file, res,by.x=ncol,by.y="NextprotID",incomparables = NA,all.x=T)
    output_content = order_columns(output_content,ncol,id_type,file)
    if (id_type=="Uniprot_AC"){output_content = output_content[,-which(colnames(output_content)=="NextprotID")]}      #remove nextprotID column
    output_content <- as.data.frame(apply(output_content, c(1,2), function(x) gsub("^$|^ $", NA, x)))  #convert "" et " " to NA

18:0a9ae3d7dbf2

        --input: input
        --nextprot: path to nextprot information file
        --column: the column number which you would like to apply...
        --header: true/false if your file contains a header
        --type: the type of input IDs (Uniprot_AC/EntrezID)
        --pc_features: IsoPoint,SeqLength,MW,Chr,SubcellLocations,Diseases,protein_name,function,post_trans_mod,protein_family,pathway
        --output: text output filename \n")
    
    q(save="no")
  }
  

  return(res)
}

# Get information from neXtProt
get_nextprot_info <- function(nextprot,input,pc_features,localization,diseases_info){
  cols = c("NextprotID",pc_features)
  cols=cols[cols!="None"]
  info = nextprot[match(input,nextprot$NextprotID),intersect(colnames(nextprot),cols)]
  return(info)
}

protein_features = function() {

  nextprot = read_file(args$nextprot,T)
  
  # Parse arguments
  id_type = args$type
  pc_features = strsplit(args$pc_features, ",")[[1]]
  output = args$output

  # Change the sample ids if they are Uniprot_AC ids to be able to match them with
  # Nextprot data
  if (id_type=="Uniprot_AC"){

  #Select user input protein ids in nextprot
  #NextprotID = unique(NextprotID[which(!is.na(NextprotID[NextprotID!=""]))])
  if (all(!NextprotID %in% nextprot[,1])){
    write.table("None of the input ids can be found in Nextprot",file=output,sep="\t",quote=FALSE,col.names=TRUE,row.names=FALSE)
  } else {
    res <- get_nextprot_info(nextprot,NextprotID,pc_features)
    res = res[!duplicated(res$NextprotID),]
    output_content = merge(file, res,by.x=ncol,by.y="NextprotID",incomparables = NA,all.x=T)
    output_content = order_columns(output_content,ncol,id_type,file)
    if (id_type=="Uniprot_AC"){output_content = output_content[,-which(colnames(output_content)=="NextprotID")]}      #remove nextprotID column
    output_content <- as.data.frame(apply(output_content, c(1,2), function(x) gsub("^$|^ $", NA, x)))  #convert "" et " " to NA