comparison protein_features.R @ 6:fc0118aa432a draft

planemo upload commit 5221e042cb207f593b144ed857106235b8f5fbde-dirty

5:867d47ff782c

# Read file and return file content as data.frame
readfile = function(filename, header) {
  if (header == "true") {
    # Read only first line of the file as header:
    headers <- read.table(filename, nrows = 1, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE)
    #Read the data of the files (skipping the first row)
    file <- read.table(filename, skip = 1, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE)
    # Remove empty rows
    file <- file[!apply(is.na(file) | file == "", 1, all), , drop=FALSE]
    #And assign the header to the data
    names(file) <- headers
  }
  else {
    file <- read.table(filename, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE)
    # Remove empty rows
    file <- file[!apply(is.na(file) | file == "", 1, all), , drop=FALSE]
  }
  return(file)
}

  args <- as.list(as.character(argsDF$V2))
  names(args) <- argsDF$V1 

  inputtype = args$inputtype
  if (inputtype == "copypaste") {
    input = strsplit(args$input, " ")[[1]]
  }
  else if (inputtype == "tabfile") {
    filename = args$input
    ncol = args$column
    # Check ncol

    input = gsub("^","NX_",input)
  }

  # Select user input protein ids in nextprot
  if ((length(input[input %in% nextprot[,1]]))==0){
    write.table("None of the input ids are can be found in Nextprot",file=filename,sep="\t",quote=FALSE,col.names=TRUE,row.names=FALSE)
  } else {
    names = c()
    res = matrix(nrow=length(input), ncol=0)

    # Get information from neXtProt

        names = c(names, arg)
        info = nextprot[match(input, nextprot["NextprotID"][,]),][arg][,]
        res = cbind(res, info)
      }
    }

    # Write output
    if (inputtype == "copypaste") {
      res = cbind(as.matrix(input), res)
      names = c(typeid, names)

6:fc0118aa432a

# Read file and return file content as data.frame
readfile = function(filename, header) {
  if (header == "true") {
    # Read only first line of the file as header:
    headers <- read.table(filename, nrows = 1, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE, quote = "")
    #Read the data of the files (skipping the first row)
    file <- read.table(filename, skip = 1, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE, quote = "")
    # Remove empty rows
    file <- file[!apply(is.na(file) | file == "", 1, all), , drop=FALSE]
    #And assign the header to the data
    names(file) <- headers
  }
  else {
    file <- read.table(filename, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE, quote = "")
    # Remove empty rows
    file <- file[!apply(is.na(file) | file == "", 1, all), , drop=FALSE]
  }
  return(file)
}

  args <- as.list(as.character(argsDF$V2))
  names(args) <- argsDF$V1 

  inputtype = args$inputtype
  if (inputtype == "copypaste") {
    input = strsplit(args$input, "[ \t\n]+")[[1]]
  }
  else if (inputtype == "tabfile") {
    filename = args$input
    ncol = args$column
    # Check ncol

    input = gsub("^","NX_",input)
  }

  # Select user input protein ids in nextprot
  if ((length(input[input %in% nextprot[,1]]))==0){
    write.table("None of the input ids are can be found in Nextprot",file=output,sep="\t",quote=FALSE,col.names=TRUE,row.names=FALSE)
  } else {
    names = c()
    res = matrix(nrow=length(input), ncol=0)

    # Get information from neXtProt

        names = c(names, arg)
        info = nextprot[match(input, nextprot["NextprotID"][,]),][arg][,]
        res = cbind(res, info)
      }
    }
    --inputtype="tabfile" --input="Galaxy50-[ID_Converter_on_data_47].tabular" --header='true' --natlas="proteinatlas.csv" --column='c7' --select='Gene,Gene.description,Evidence,RNA.tissue.category,Reliability.IH,TPM.max.in.non.specific' --output="test.txt"

    # Write output
    if (inputtype == "copypaste") {
      res = cbind(as.matrix(input), res)
      names = c(typeid, names)