Retention Time Prediction with X!Tandem

Script

BufferedReader getReader (String fileUrl, String encoding) throws IOException {
		InputStreamReader reader;
		try {
			if (encoding == null) {
				reader = new FileReader(fileUrl);
			} else {
				reader = new InputStreamReader(new FileInputStream(fileUrl),encoding); 
			}
		}
		catch (FileNotFoundException e) {
			// try a real URL instead
			URL url = new URL(fileUrl);
			if (encoding == null) {
				reader = new InputStreamReader (url.openStream());
			} else {
				reader = new InputStreamReader (url.openStream(), encoding);
			}
		}
		return new BufferedReader(reader);
	}



StringBuffer sb = new StringBuffer(4000);

if (encoding == void) {
	encoding = null;
}

BufferedReader in = getReader(fileurl, encoding);
String str;
String lineEnding = System.getProperty("line.separator");

while ((str = in.readLine()) != null) {
	sb.append(str);
	sb.append(lineEnding);
}
in.close();
filecontents = sb.toString();
  

Xpath Expression

/default:msms_pipeline_analysis/default:msms_run_summary/default:spectrum_query/default:search_result/default:search_hit/@peptide

Xpath Expression

/default:msms_pipeline_analysis/default:msms_run_summary/default:spectrum_query/@start_scan

Script

String out = new String();

for (i=0; i

Script

#
# Plot_Predicted_vs_Measured_RT
# By Wendy Plugge and Magnus Palmblad 2012
#

# Load and convert text data from RT.exe to dataframe

data_AA_rt=in2
file_split=unlist(strsplit(data_AA_rt, split="\\n")) # split data into lines
extract_AA_RT=file_split[1:25]

AminoAcids=as.character(lapply(strsplit(extract_AA_RT,"\\t"), function(x) x[1])) # create string vector using every first element of extract_AA_RT  
RetTime=as.numeric(lapply(strsplit(extract_AA_RT,"\\t"), function(x) x[2]))      # create string vector using every second element of extract_AA_RT  
frame_AA_RT=data.frame(AminoAcids, RetTime, stringsAsFactors=FALSE)            # create data frame with headers


# Load peptide data from PeptideProphet and convert this to a data frame

data_pep=in1
file_split_pep=unlist(strsplit(data_pep, split="\\n"))                          # split data into lines
peptide=as.character(lapply(strsplit(file_split_pep,"\\t"), function(x) x[1]))  # create string vector using every first element of file_split_pep
pep_RetTime=as.numeric(lapply(strsplit(file_split_pep,"\\t"), function(x) x[2]))# create string vector using every second element of file_split_pep
data_pep_frame=data.frame(peptide, pep_RetTime, stringsAsFactors=FALSE)         # create data frame with headers
 
offset=frame_AA_RT$RetTime[25] # For offset ("void time")


# Create filename for output

file_name=in3
extension=".RT_prediction.pdf"               # new extension of PDF image
txt_name=paste(file_name, extension, sep="") # join input name with new extension
output_file_name=txt_name


# Calculate predicted retention times for peptides

list_value=list()
for(x in data_pep_frame$peptide){
      split_pep=unlist(strsplit(x, split=NULL))
      value=offset
      for(x in split_pep){
         place=grep(x,frame_AA_RT$AminoAcids)
         value=value+frame_AA_RT$RetTime[place]
}
list_value<-c(list_value,value)
}
Predicted_RT=as.numeric(list_value ) # convert character strings to numeric values
res=lm(Predicted_RT~data_pep_frame$pep_RetTime)
pdf(output_file_name)
plot(data_pep_frame$pep_RetTime, Predicted_RT,col="black", pch=19, xlab="measured retention time (scan number)", ylab="predicted retention time (scan number)")
abline(res,col="red",lwd=1.5)
dev.off()

R Server

Script

#
# Plot_Retention_Coefficients
# By Wendy Plugge and Magnus Palmblad 2012
#

# Load files

read_file=in1
file_name=in2


# Create filename for output file

extension=".R_coefficient_AA.pdf"
pdf_name=paste(file_name, extension, sep="")
output_file_name=pdf_name


# Convert input of read_file to data frame

file_split=unlist(strsplit(read_file, split="\\n")) # split data into lines
extract_AA_RT=file_split[1:25]

AminoAcids=as.character(lapply(strsplit(extract_AA_RT,"\\t"), function(x) x[1])) # create string vector using every first element of extract_AA_RT 
RetTime=as.numeric(lapply(strsplit(extract_AA_RT,"\\t"), function(x) x[2]))      # create string vector using every second element of extract_AA_RT  
frame_AA_RT=data.frame(AminoAcids, RetTime, stringsAsFactors=FALSE)            # create data frame


# Add column to data frame

frame_AA_RT["color_AA"]<-c("orange","blue","magenta","red","green","red","magenta","orange","blue","green","green","blue","green","green","green","orange","orange","green","green","green","yellow","yellow","yellow","yellow","black")

sortData<-frame_AA_RT[order(frame_AA_RT$RetTime),]                           # sort data frame according to retention time
sortData["number"]<-c(1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25) # add numbers for x-axis

color <- as.character(sortData$color_AA)


# Open PDF file and create graphics

pdf(pdf_name)
plot(sortData$number,sortData$RetTime, xaxt="n", xlab="", pch=19, cex=3.5, col=color, ylab="best fit to experimental retention data (scans/residue)", main="predicted retention coefficients of amino acids")
grid(NA, NULL, lty=2, col="black")
points(sortData$number,sortData$RetTime,pch=19, cex=3.5, col=color)
text(sortData$number,sortData$RetTime,sortData$AminoAcids, col="white",font=2)
legend("topleft",inset=.02, c("small nonpolar","hydrophobic", "polar", "acidic", "basic", "modified residue", "offset"), pch=19, pt.cex=1.5, col=c("orange", "green", "magenta", "red", "blue", "yellow", "black"),bg="white")

dev.off() # close PDF file




 

R Server

Script

/****************** Input descriptions ****************/
// input port: String mzxml_file (Depth 0)
// input port: String fasta_file (Depth 0)
// input port: String parameter_file (Depth 0)
// input port: String log_file (Depth 0)
// output port: String tandem_file (Depth 0)
// output port: String pepxml_file (Depth 0)
// output port: String interact_file (Depth 0)

/****************** Class Declarations ****************/
class InProcStreamReader extends Thread
{
    private StringBuffer sb;
    public  InputStream is;
    
    InProcStreamReader(InputStream is) {
        this.is = is;
    }// InProcStreamReader(InputStream is) 
    
    public void run() {
        try {
            InputStreamReader isr = new InputStreamReader(is);
            sb = new StringBuffer();
            while ((c = isr.read()) != -1)
                sb.append((char) c);
        } catch (IOException ioe)
        {
          ioe.printStackTrace();  
        }/// catch
    }// run

    public String getOutput() { 
      return sb.toString();
    }// getOutput
}// InProcStreamReader


/****************** Global variables ******************/
tppDir = "C:\\Inetpub\\tpp-bin\\";
installDir = "C:\\Taverna\\programs\\";

/****************** Global functions ******************/
// Replaces substrings in a string with a replacement string
String replace(String str, String pattern, String replace) { 
  int s = 0; 
  int e = 0; 
  StringBuffer result = new StringBuffer(); 
  while ((e = str.indexOf(pattern, s)) >= 0) { 
    result.append(str.substring(s, e)); 
    result.append(replace); 
    s = e+pattern.length(); 
  } // while
  result.append(str.substring(s)); 
  return result.toString(); 
}//  String replace(String str, String pattern, String replace) 

// Generates a file based on a name and a new extension (without the .)
String genNewFileName(String inputFile, String extension) {
  int dotPos = inputFile.lastIndexOf(".");
  String strFilename = inputFile.substring(0, dotPos);
  return strFilename + "." + extension;
}// String genNewFileName(String inputFile, String extension) 

// Generates tandem output file name
String genOutputFileName(String inputFile) {
  return genNewFileName(inputFile, "tandem");
}// String genOutputFileName(String inputFile)

// Generates taxonomy file name
String genTaxonomyFileName(String inputFile) {
  return genNewFileName(inputFile, "taxonomy.xml");
}// String genTaxonomyFileName((String inputFile)

// Modifies the taxonomy predicate file and returns the path of the new file */
String modTaxonomyPredicate(String fasta_location, String inputFile) {   
  String taxFileName = genTaxonomyFileName( inputFile );
  BufferedReader input = new BufferedReader( new FileReader( installDir + "Tools\\Tandem\\taxonomy_pred.xml" ));
  BufferedWriter output = new BufferedWriter( new FileWriter( taxFileName ));
  try {
    String line = null; 
    while (( line = input.readLine()) != null){      
      if (line.indexOf("$FASTA_LOCATION$") >= 0) {  
        line = replace( line, "$FASTA_LOCATION$", fasta_location );
        output.write( line + '\n');
      } else {
        output.write( line + '\n');
      }// else
    }// while
  }// try
  finally {
    input.close();
    output.close();
  }// finally

  return taxFileName;

}// String modTaxonomyPredicate(String fasta_location) 

// Generates parameter file name
String genParameterFileName(String inputFile) {
  return genNewFileName(inputFile, "param.xml");
}// String genParameterFileName((String inputFile)

// Modifies the param predicate file and returns the path of the new file */
String modParamPredicate(String mzxmlFile, String taxonFile, String paramFile, String outputFile) {   
  BufferedReader input = new BufferedReader(new FileReader(installDir + "Tools\\Tandem\\tandem_pred.params"));
  BufferedReader parinput = new BufferedReader(new FileReader(paramFile));
  String paramFileName = genParameterFileName( mzxmlFile );
  BufferedWriter output = new BufferedWriter( new FileWriter( paramFileName ));
  String line = null; //not declared within while loop
  try {
    while (( line = input.readLine()) != null){
      if (line.indexOf("$PARAMS$") >= 0) {
        while (( line = parinput.readLine()) != null){
          output.write( line + '\n'); 
        }
      } else if (line.indexOf("$TAXONOMY_LOCATION$") >= 0) {
        line = replace( line, "$TAXONOMY_LOCATION$", taxonFile );
        output.write( line + '\n'); 
      } else if (line.indexOf("$SPECTRUM_LOCATION$") >= 0) {
        line = replace( line, "$SPECTRUM_LOCATION$", mzxmlFile );
        output.write( line + '\n');
      } else if (line.indexOf("$OUTPUT_LOCATION$") >= 0) {
        line = replace( line, "$OUTPUT_LOCATION$", outputFile );
        output.write( line + '\n');
      } else {
        output.write( line + '\n');
      }// else
    }// while
  }// try
  finally {
    input.close();
    parinput.close();
    output.close();
  }// finally

  return paramFileName;

}// String modParamPredicate(String mzxmlFile, String taxonFile, String outputFile) 


/************** Main matter, input checking ************/
if (mzxml_file == void || mzxml_file.equals("")) {
	throw new RuntimeException("The 'mzxml_file' port cannot be null.");
} else if (fasta_file == void || fasta_file.equals("")) {
	throw new RuntimeException("The 'fasta_file' port cannot be null.");
} else if (parameter_file == void || parameter_file.equals("")) {
	throw new RuntimeException("The 'parameter_file' port cannot be null.");
}// else

/************ Main matter, Running executable **********/
// Setting up the command line 
appArray = new ArrayList();

// Adding the command itself
appArray.add(tppDir + "Tandem.exe");

// Creating tandem configuration files and setting them as input
taxonFile = modTaxonomyPredicate(fasta_file, mzxml_file);
tmpout = genOutputFileName(mzxml_file);
appArray.add(modParamPredicate(mzxml_file, taxonFile, parameter_file, tmpout));

// Preparing execution of tandem
workDir = new File(tppDir);
launcher = new ProcessBuilder(appArray);
launcher.directory = workDir;
proc = launcher.start();

outputReader = new InProcStreamReader(proc.getInputStream());
outputReader.start();

// any error???
exitVal = proc.waitFor();
outputReader.join();


/************** Main matter, generating log ************/
fstream = new FileWriter(log_file, true);
out = new BufferedWriter(fstream);

if (!(log_file == void || log_file.equals(""))) {
  out.write("=============== X!Tandem ==============="); 
  out.newLine();
  out.write("Parameters: ");
  for (i=0; i