comparison id_converter_UniProt.R @ 14:659f1248f535 draft

planemo upload commit 688c456ca57914a63c20eba942ec5fe81e896099-dirty

13:4fcc5e5c0902

  
  # Help section
  if("--help" %in% args) {
    cat("Selection and Annotation HPA
    Arguments:
        --ref_file: path to reference file (human_id_mapping_file.txt)
        --input_type: type of input (list of id or filename)
        --id_type: type of input IDs
        --input: list of IDs (text or filename)
        --column_number: the column number which contains list of input IDs
        --header: true/false if your file contains a header

  # Parse arguments
  parseArgs <- function(x) strsplit(sub("^--", "", x), "=")
  argsDF <- as.data.frame(do.call("rbind", parseArgs(args)))
  args <- as.list(as.character(argsDF$V2))
  names(args) <- argsDF$V1

  input_id_type = args$id_type # Uniprot, ENSG....
  list_id_input_type = args$input_type # list or file
  options = strsplit(args$target_ids, ",")[[1]]
  output = args$output
  human_id_mapping_file = args$ref_file
    
  # Extract input IDs
  if (list_id_input_type == "list") {
    print(args$input)
    list_id = strsplit(args$input, "[ \t\n]+")[[1]]
    # Remove isoform accession number (e.g. "-2")
    list_id = gsub("-.+", "", list_id)
  }
  else if (list_id_input_type == "file") {
    filename = args$input
    column_number = as.numeric(gsub("c", "" ,args$column_number))
    header = args$header
    file_all = readfile(filename, header)
    list_id = c()
    list_id = sapply(strsplit(file_all[,column_number], ";"), "[", 1)
    # Remove isoform accession number (e.g. "-2")
    list_id = gsub("-.+", "", list_id)
  }

  # Extract ID maps
  human_id_map = read.table(human_id_mapping_file, header = TRUE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings = "", quote = "")
  
  names = c()
    
  # Map IDs
  res = matrix(nrow=length(list_id), ncol=0)

  for (opt in options) {
    names = c(names, opt)
    mapped = human_id_map[match(list_id, human_id_map[input_id_type][,]),][opt][,]
    res = cbind(res, matrix(mapped))
  }
     
  # Write output
  if (list_id_input_type == "list") {

    colnames(res) = names
    write.table(res, output, row.names = FALSE, sep = "\t", quote = FALSE)
  }
  else if (list_id_input_type == "file") {
    names(res) = options
    names = c(names(file_all), names)
    output_content = cbind(file_all, res)
    colnames(output_content) = names
    write.table(output_content, output, row.names = FALSE, sep = "\t", quote = FALSE)
  }

14:659f1248f535

  
  # Help section
  if("--help" %in% args) {
    cat("Selection and Annotation HPA
    Arguments:
        --ref_file: path to reference file (id_mapping_file.txt)
        --input_type: type of input (list of id or filename)
        --id_type: type of input IDs
        --input: list of IDs (text or filename)
        --column_number: the column number which contains list of input IDs
        --header: true/false if your file contains a header

  # Parse arguments
  parseArgs <- function(x) strsplit(sub("^--", "", x), "=")
  argsDF <- as.data.frame(do.call("rbind", parseArgs(args)))
  args <- as.list(as.character(argsDF$V2))
  names(args) <- argsDF$V1
  
  input_id_type = args$id_type # Uniprot, ENSG....
  list_id_input_type = args$input_type # list or file
  options = strsplit(args$target_ids, ",")[[1]]
  output = args$output
  id_mapping_file = args$ref_file
    
  # Extract input IDs
  if (list_id_input_type == "list") {
    print(args$input)
    list_id = trimws(strsplit(args$input, ",")[[1]])
    list_id = list_id[list_id != ""]    #remove empty entry
    # Remove isoform accession number (e.g. "-2")
    list_id = gsub("-.+", "", list_id)
  } else if (list_id_input_type == "file") {
    filename = args$input
    column_number = as.numeric(gsub("c", "" ,args$column_number))
    header = args$header
    file_all = readfile(filename, header)
    list_id = trimws(gsub("[$,\xc2\xa0]","",sapply(strsplit(file_all[,column_number], ";"), "[", 1)))
    # Remove isoform accession number (e.g. "-2")
    list_id = gsub("-.+", "", list_id)
  }

  # Extract ID maps
  id_map = read.table(id_mapping_file, header = TRUE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings = "", quote = "")
  
  names = c()
    
  # Map IDs
  res = matrix(nrow=length(list_id), ncol=0)

  for (opt in options) {
    names = c(names, opt)
    mapped = id_map[match(list_id, id_map[input_id_type][,]),][opt][,]
    res = cbind(res, matrix(mapped))
  }
     
  # Write output
  if (list_id_input_type == "list") {

    colnames(res) = names
    write.table(res, output, row.names = FALSE, sep = "\t", quote = FALSE)
  }
  else if (list_id_input_type == "file") {
    names(res) = options
    if (all(names(file_all) == file_all[1,1:length(names(file_all))])){ #if header of file is the same as the first line of file
      names(file_all)[column_number] = input_id_type
    }
    names = c(names(file_all), names)
    output_content = cbind(file_all, res)
    colnames(output_content) = names
    write.table(output_content, output, row.names = FALSE, sep = "\t", quote = FALSE)
  }