Test for Orthologues

None

import java.io.*;import java.util.*;path = "D:/DATA/demo/orthoResults.txt"; File f1,f2,f3;if( arg.equals("test") ){	f1 = new File("D:/DATA/proteome/sa.fasta");	f2 = new File("D:/DATA/proteome/sa.ortho");}else{	f1 = new File("D:/DATA/proteome/22602.S_aureus_USA300.fasta");  	f2 = new File("D:/DATA/proteome/22602.S_aureus_USA300.orthologues");}HashSet targetHashSet = new HashSet();HashSet sourceHashSet = new HashSet();readTargetFile(File f) {	try {	BufferedReader br = new BufferedReader(new FileReader(f));	String line = br.readLine();	while (line != null) {		//  Note:  many lines will contain "Putative uncharacterized protein"				int start = line.indexOf("|");		int end = line.indexOf("|", start+1);		if(start >= 0 && end >= 0) {			String proteinID = line.substring(start+1,end);			targetHashSet.add(proteinID);  // would need HashMap for  K,V pair			//System.out.println("target >>" + proteinID + "<<");		}				line = br.readLine();	}		br.close();	} catch(Exception ex) { 		System.out.println(ex);	}}readOrthoFile(File f) {	try 	{		BufferedReader br = new BufferedReader(new FileReader(f));		String line = br.readLine();		while (line != null) 		{			String [] fields = line.split("\t");			//int start = line.indexOf("|");			//int end = line.indexOf("|", start+1);			//String proteinID = line.substring(start+1,end);						if (fields != null && fields.length > 2) {						if(fields[5].contains("B.subtilis") ) {					sourceHashSet.add(fields[2]);					// System.out.println("source >>" + fields[2] + "<<");					// String orthoProteinID = fields[7].replace(";","");					//System.out.println("ortho >>" + orthoProteinID + "<<");				}			}		line = br.readLine();		}		br.close();			} catch(Exception ex) { 		System.out.println(ex);	}}purge(HashSet target, HashSet source) {       int i = 0;	Iterator it = source.iterator();	while( it.hasNext() ) {		String s = (String) it.next();		target.remove(s);	} }readTargetFile(f1);readOrthoFile(f2);File f = new File("D:/DATA/demo/orthoResults.txt");try{	FileWriter fw = new FileWriter(f);	fw.write("target proteins = " + targetHashSet.size() + ",  orthologous source proteins = " + sourceHashSet.size() + "\n");	fw.write("Percent orthologs = " +  (100 * sourceHashSet.size())/targetHashSet.size() + "%\n\n" );		purge(targetHashSet, sourceHashSet);	fw.write("target proteins = " + targetHashSet.size()  + " if orthologs removed.\n\n");	fw.flush();	fw.close();	System.out.println("done");}catch(Exception ex) { System.err.println(ex); }

Name	Description	Inputs	Outputs
test_for_orthologs		arg	path
read_report		path	content path

Name	Description
output	Report generated Report
report_location	Report Location, where it is found

Source	Sink
test_or_not	test_for_orthologs:arg
test_for_orthologs:path	read_report:path
read_report:content	output
read_report:path	report_location

Test for Orthologues

Preview

Run

Run this Workflow in the Taverna Workbench...

Workflow Components

Script

Script

Reviews (0)

Comments (0)

Other workflows that use similar services (0)