A Picard class for switching read names according to a translation table in a white space separated file.

ReplaceSampleNameInReadGroup.java

package net.sf.picard.sam;

import java.io.BufferedReader;
import java.io.DataInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import net.sf.picard.cmdline.CommandLineProgram;
import net.sf.picard.cmdline.Option;
import net.sf.picard.cmdline.StandardOptionDefinitions;
import net.sf.picard.cmdline.Usage;
import net.sf.picard.io.IoUtil;
import net.sf.picard.util.Log;
import net.sf.samtools.SAMFileHeader;
import net.sf.samtools.SAMFileHeader.SortOrder;
import net.sf.samtools.SAMFileReader;
import net.sf.samtools.SAMFileWriter;
import net.sf.samtools.SAMFileWriterFactory;
import net.sf.samtools.SAMReadGroupRecord;
import net.sf.samtools.SAMRecord;


public class ReplaceSampleNameInReadGroup extends CommandLineProgram{

	@Usage(programVersion="1.0")
	public String USAGE = "Replaces the read group sample names as defined in the input csv file.";

	@Option(shortName= StandardOptionDefinitions.INPUT_SHORT_NAME, doc="Input file (bam or sam).")
	public File INPUT = null;

	@Option(shortName=StandardOptionDefinitions.OUTPUT_SHORT_NAME, doc="Output file (bam or sam).")
	public File OUTPUT = null;

	@Option(shortName=StandardOptionDefinitions.SORT_ORDER_SHORT_NAME, optional=true,
			doc="Optional sort order to output in. If not supplied OUTPUT is in the same order as INPUT.")
	public SortOrder SORT_ORDER;

	@Option(shortName="TR",doc="Whitespace separated translation file with current names in first column and the new names in the second column.")
	public File TRANSLATION_FILE;

	private final Log log = Log.getInstance(ReplaceSampleNameInReadGroup.class);

	/** Required main method implementation. */
	public static void main(final String[] argv) {
		new ReplaceSampleNameInReadGroup().instanceMainWithExit(argv);
	}

	protected int doWork() {
		IoUtil.assertFileIsReadable(INPUT);
		IoUtil.assertFileIsReadable(TRANSLATION_FILE);
		IoUtil.assertFileIsWritable(OUTPUT);
		
		//Initialize the translation file
		Map<String, String> translationTable = initializeTranslationTable(TRANSLATION_FILE);

		SAMFileReader in = new SAMFileReader(INPUT);		
		
		// create the new header and output file
		final SAMFileHeader inHeader = in.getFileHeader();
		final SAMFileHeader outHeader = inHeader.clone();
		
		List<SAMReadGroupRecord> readGroups = outHeader.getReadGroups();
			
		for (SAMReadGroupRecord samReadGroupRecord : readGroups) {
			// Change from the old sample name to the new.
			samReadGroupRecord.setSample(translationTable.get(samReadGroupRecord.getSample()));			
		}
		
		outHeader.setReadGroups(readGroups);
		if (SORT_ORDER != null) outHeader.setSortOrder(SORT_ORDER);

		final SAMFileWriter outWriter = new SAMFileWriterFactory().makeSAMOrBAMWriter(outHeader,
				outHeader.getSortOrder() == inHeader.getSortOrder(),
				OUTPUT);
	
		for (final SAMRecord read : in) {
			outWriter.addAlignment(read);
		}

		// cleanup
		in.close();
		outWriter.close();
		return 0;
	}
	
	private Map<String, String> initializeTranslationTable(File transFile) {

		Map<String,String> translations = new HashMap<String,String>();		

		try{
			FileInputStream fstream = new FileInputStream(transFile);
			DataInputStream in = new DataInputStream(fstream);
			BufferedReader br = new BufferedReader(new InputStreamReader(in));
			
			String strLine;
			while((strLine = br.readLine()) != null) {
				String key = strLine.split("\\s+")[0];
				String value = strLine.split("\\s+")[1];
				translations.put(key, value);
			}
			
		}
		catch (Exception e)
		{
			System.err.println("Error: " + e.getMessage());
		}

		return translations;
	}	
}