Renaming of ATK to GATK, the genome analysis TK.

Also added several more layers of error checking 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@54 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
depristo 2009-03-15 22:23:25 +00:00
parent c9cb7a3596
commit 24ae381c97
17 changed files with 72 additions and 618 deletions

View File

@ -1,7 +1,8 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.gatk.refdata.ReferenceOrderedDatum;
import org.broadinstitute.sting.atk.LocusIterator;
import org.broadinstitute.sting.atk.LocusContext;
import org.broadinstitute.sting.utils.ReferenceOrderedDatum;
import net.sf.samtools.SAMRecord;
import java.util.List;

View File

@ -1,8 +1,8 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import net.sf.samtools.SAMRecord;
import org.broadinstitute.sting.gatk.walkers.ReadWalker;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.atk.ReadWalker;
import org.broadinstitute.sting.atk.LocusContext;
/**
* Created by IntelliJ IDEA.
@ -27,7 +27,7 @@ public class BaseQualityHistoWalker implements ReadWalker<Integer, Integer> {
return true; // We are keeping all the reads
}
// Map over the org.broadinstitute.sting.gatk.LocusContext
// Map over the org.broadinstitute.sting.atk.LocusContext
public Integer map(LocusContext context, SAMRecord read) {
for ( byte qual : read.getBaseQualities() ) {
//System.out.println(qual);

View File

@ -1,8 +1,10 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import org.broadinstitute.sting.gatk.walkers.LocusWalker;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.gatk.refdata.ReferenceOrderedDatum;
import org.broadinstitute.sting.atk.LocusWalker;
import org.broadinstitute.sting.atk.LocusIterator;
import org.broadinstitute.sting.atk.LocusContext;
import org.broadinstitute.sting.utils.ReferenceOrderedDatum;
import net.sf.samtools.SAMRecord;
import java.util.List;
@ -25,8 +27,7 @@ public abstract class BasicLociWalker<MapType, ReduceType> implements LocusWalke
return true; // We are keeping all the reads
}
public void onTraversalDone() {
;
public void onTraveralDone() {
}
// These three capabilities must be overidden

View File

@ -1,8 +1,8 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import net.sf.samtools.SAMRecord;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.gatk.walkers.ReadWalker;
import org.broadinstitute.sting.atk.LocusContext;
import org.broadinstitute.sting.atk.ReadWalker;
/**
* Created by IntelliJ IDEA.
@ -20,8 +20,8 @@ public abstract class BasicReadWalker<MapType, ReduceType> implements ReadWalker
return true;
}
public void onTraversalDone() {
;
public void onTraveralDone() {
}
// Three basic abstract function that *must* be overridden

View File

@ -1,7 +1,7 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.gatk.refdata.ReferenceOrderedDatum;
import org.broadinstitute.sting.atk.LocusContext;
import org.broadinstitute.sting.utils.ReferenceOrderedDatum;
import java.util.List;

View File

@ -1,7 +1,7 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import net.sf.samtools.SAMRecord;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.atk.LocusContext;
public class CountReadsWalker extends BasicReadWalker<Integer, Integer> {
public Integer map(LocusContext context, SAMRecord read) {

View File

@ -1,10 +1,12 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.gatk.refdata.ReferenceOrderedDatum;
import org.broadinstitute.sting.atk.LocusContext;
import org.broadinstitute.sting.utils.ReferenceOrderedDatum;
import java.util.List;
import net.sf.samtools.SAMRecord;
/**
* Created by IntelliJ IDEA.
* User: mdepristo

View File

@ -1,8 +1,12 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import org.broadinstitute.sting.gatk.walkers.LocusWalker;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.gatk.refdata.ReferenceOrderedDatum;
import org.broadinstitute.sting.atk.LocusWalker;
import org.broadinstitute.sting.atk.LocusIterator;
import org.broadinstitute.sting.atk.LocusContext;
import org.broadinstitute.sting.utils.ReferenceOrderedDatum;
import org.broadinstitute.sting.utils.rodDbSNP;
import org.broadinstitute.sting.utils.Utils;
import net.sf.samtools.SAMRecord;
import java.util.List;
@ -20,7 +24,7 @@ public class NullWalker implements LocusWalker<Integer, Integer> {
return true; // We are keeping all the reads
}
// Map over the org.broadinstitute.sting.gatk.LocusContext
// Map over the org.broadinstitute.sting.atk.LocusContext
public Integer map(List<ReferenceOrderedDatum> rodData, char ref, LocusContext context)
{
return 1;
@ -36,6 +40,6 @@ public class NullWalker implements LocusWalker<Integer, Integer> {
return 0;
}
public void onTraversalDone() {
public void onTraveralDone() {
}
}

View File

@ -1,8 +1,11 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.gatk.refdata.ReferenceOrderedDatum;
import org.broadinstitute.sting.gatk.refdata.rodDbSNP;
import org.broadinstitute.sting.atk.LocusWalker;
import org.broadinstitute.sting.atk.LocusIterator;
import org.broadinstitute.sting.atk.LocusContext;
import org.broadinstitute.sting.utils.ReferenceOrderedDatum;
import org.broadinstitute.sting.utils.rodDbSNP;
import org.broadinstitute.sting.utils.Utils;
import net.sf.samtools.SAMRecord;
import java.util.List;
@ -14,7 +17,7 @@ import java.util.List;
* Time: 3:22:14 PM
* To change this template use File | Settings | File Templates.
*/
public class PileupWalker extends BasicLociWalker<Integer, Integer> {
public class PileupWalker implements LocusWalker<Integer, Integer> {
public void initialize() {
}
@ -25,7 +28,7 @@ public class PileupWalker extends BasicLociWalker<Integer, Integer> {
return true; // We are keeping all the reads
}
// Map over the org.broadinstitute.sting.gatk.LocusContext
// Map over the org.broadinstitute.sting.atk.LocusContext
public Integer map(List<ReferenceOrderedDatum> rodData, char ref, LocusContext context) {
//System.out.printf("Reads %s:%d %d%n", context.getContig(), context.getPosition(), context.getReads().size());
//for ( SAMRecord read : context.getReads() ) {
@ -81,4 +84,7 @@ public class PileupWalker extends BasicLociWalker<Integer, Integer> {
public Integer reduce(Integer value, Integer sum) {
return value + sum;
}
public void onTraveralDone() {
}
}

View File

@ -1,7 +1,7 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import net.sf.samtools.SAMRecord;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.atk.LocusContext;
public class PrintReadsWalker extends BasicReadWalker<Integer, Integer> {
public Integer map(LocusContext context, SAMRecord read) {

View File

@ -1,8 +1,10 @@
package org.broadinstitute.sting.gatk.walkers;
package org.broadinstitute.sting.atk.modules;
import org.broadinstitute.sting.gatk.LocusContext;
import org.broadinstitute.sting.gatk.refdata.ReferenceOrderedDatum;
import org.broadinstitute.sting.gatk.refdata.rodDbSNP;
import org.broadinstitute.sting.atk.LocusWalker;
import org.broadinstitute.sting.atk.LocusIterator;
import org.broadinstitute.sting.atk.LocusContext;
import org.broadinstitute.sting.utils.ReferenceOrderedDatum;
import org.broadinstitute.sting.utils.rodDbSNP;
import org.broadinstitute.sting.utils.Utils;
import net.sf.samtools.SAMRecord;
@ -11,7 +13,13 @@ import java.util.List;
// Draft single sample genotyper
// j.maguire 3-7-2009
public class SingleSampleGenotyper extends BasicLociWalker<Integer, Integer> {
public class SingleSampleGenotyper implements LocusWalker<Integer, Integer> {
public void initialize() {
}
public String walkerType() { return "ByLocus"; }
// Do we actually want to operate on the context?
public boolean filter(List<ReferenceOrderedDatum> rodData, char ref, LocusContext context) {
return true; // We are keeping all the reads
}
@ -78,7 +86,7 @@ public class SingleSampleGenotyper extends BasicLociWalker<Integer, Integer> {
}
// Map over the org.broadinstitute.sting.gatk.LocusContext
// Map over the org.broadinstitute.sting.atk.LocusContext
public Integer map(List<ReferenceOrderedDatum> rodData, char ref, LocusContext context) {
//System.out.printf("Reads %s:%d %d%n", context.getContig(), context.getPosition(), context.getReads().size());
//for ( SAMRecord read : context.getReads() ) {
@ -97,7 +105,7 @@ public class SingleSampleGenotyper extends BasicLociWalker<Integer, Integer> {
{
if ( datum != null )
{
if ( datum instanceof rodDbSNP)
if ( datum instanceof rodDbSNP)
{
rodDbSNP dbsnp = (rodDbSNP)datum;
rodString += dbsnp.toMediumString();
@ -136,4 +144,7 @@ public class SingleSampleGenotyper extends BasicLociWalker<Integer, Integer> {
public Integer reduce(Integer value, Integer sum) {
return value + sum;
}
public void onTraveralDone() {
}
}

View File

@ -1,213 +0,0 @@
package org.broadinstitute.sting.gatk.refdata;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.util.Iterator;
import java.util.ArrayList;
import java.util.Collections;
import edu.mit.broad.picard.util.TabbedTextFileParser;
import org.broadinstitute.sting.gatk.iterators.PushbackIterator;
import org.broadinstitute.sting.utils.GenomeLoc;
/**
* Class for representing arbitrary reference ordered data sets
*
* User: mdepristo
* Date: Feb 27, 2009
* Time: 10:47:14 AM
* To change this template use File | Settings | File Templates.
*/
public class ReferenceOrderedData<ROD extends ReferenceOrderedDatum> implements Iterable<ROD> {
private File file = null;
private Class<ROD> type = null; // runtime type information for object construction
public ReferenceOrderedData(File file, Class<ROD> type ) {
this.file = file;
this.type = type;
}
public RODIterator iterator() {
return new RODIterator(new SimpleRODIterator());
}
// ----------------------------------------------------------------------
//
// Testing
//
// ----------------------------------------------------------------------
public void testMe() {
ReferenceOrderedDatum last = null;
for ( ReferenceOrderedDatum rec : this ) {
if ( last == null || ! last.getLocation().onSameContig(rec.getLocation()) ) {
System.out.println(rec.toString());
}
last = rec;
}
System.exit(1);
}
// ----------------------------------------------------------------------
//
// Manipulations of all of the data
//
// ----------------------------------------------------------------------
public ArrayList<ReferenceOrderedDatum> readAll() {
ArrayList<ReferenceOrderedDatum> elts = new ArrayList<ReferenceOrderedDatum>();
for ( ReferenceOrderedDatum rec : this ) {
elts.add(rec);
}
elts.trimToSize();
return elts;
}
public static void sortRODDataInMemory(ArrayList<ReferenceOrderedDatum> data) {
Collections.sort(data);
}
public static void write(ArrayList<ReferenceOrderedDatum> data, File output) throws IOException {
final FileWriter out = new FileWriter(output);
for ( ReferenceOrderedDatum rec : data ) {
out.write(rec.repl() + "\n");
}
out.close();
}
public boolean validateFile() throws Exception {
ReferenceOrderedDatum last = null;
for ( ReferenceOrderedDatum rec : this ) {
if ( last != null && last.compareTo(rec) == 1 ) {
// It's out of order
throw new Exception("Out of order elements at \n" + last.toString() + "\n" + rec.toString());
}
last = rec;
}
return true;
}
public void indexFile() {
// Fixme -- get access to the linear index system from Jim
}
// ----------------------------------------------------------------------
//
// Iteration
//
// ----------------------------------------------------------------------
private class SimpleRODIterator implements Iterator<ROD> {
//private WhitespaceTextFileParser parser = null;
private TabbedTextFileParser parser = null;
public SimpleRODIterator() {
parser = new TabbedTextFileParser(true, file);
}
public boolean hasNext() {
return parser.hasNext();
}
public ROD next() {
String parts[] = parser.next();
return parseLine(parts);
}
public void remove() {
throw new UnsupportedOperationException();
}
}
public class RODIterator implements Iterator<ROD> {
private PushbackIterator<ROD> it;
private ROD prev = null;
public RODIterator(SimpleRODIterator it) {
this.it = new PushbackIterator<ROD>(it);
}
public boolean hasNext() { return it.hasNext(); }
public ROD next() {
prev = it.next();
return prev;
}
//
// Seeks forward in the file until we reach (or cross) a record at contig / pos
// If we don't find anything and cross beyond contig / pos, we return null
// Otherwise we return the first object who's start is at pos
//
public ROD seekForward(final GenomeLoc loc) {
return seekForward(loc.getContig(), loc.getStart());
}
protected ROD seekForward(final String contigName, final long pos) {
final boolean DEBUG = false;
ROD result = null;
if ( DEBUG ) System.out.printf(" *** starting seek to %s %d %s%n", contigName, pos, prev);
while ( hasNext() ) {
ROD current = next();
//System.out.printf(" -> Seeking to %s %d AT %s %d%n", contigName, pos, current.getContig(), current.getStart());
int strCmp = GenomeLoc.compareContigs( contigName, prev.getContig() );// contigName.compareTo( prev.getContig() );
if ( strCmp == 0 ) {
// The contigs are equal
if ( current.getStart() > pos ) {
// There was nothing to find, push back next and return null
it.pushback(current);
break;
}
else if ( pos == current.getStart() ) {
// We found a record at contig / pos, return it
result = current;
break;
}
}
else if ( strCmp < 0 ) {
if ( DEBUG ) System.out.printf(" -> Jumped to contig %s%n", contigName);
// We've gone past the desired contig, break
it.pushback(current);
break;
}
}
if ( DEBUG ) {
if ( result == null )
;
//System.out.printf(" --- seek result to %s %d is NULL%n", contigName, pos);
else
System.out.printf(" ### Found %s %d%n", result.getContig(), result.getStart());
}
// we ran out of elements or found something
return result;
}
public void remove() {
throw new UnsupportedOperationException();
}
}
// ----------------------------------------------------------------------
//
// Parsing
//
// ----------------------------------------------------------------------
ROD parseLine(final String[] parts) {
//System.out.printf("Parsing GFFLine %s%n", Utils.join(" ", parts));
try {
ROD obj = type.newInstance();
obj.parseLine(parts);
return obj;
} catch ( java.lang.InstantiationException e ) {
System.out.println(e);
return null; // wow, unsafe!
} catch ( java.lang.IllegalAccessException e ) {
System.out.println(e);
return null; // wow, unsafe!
}
}
}

View File

@ -1,30 +0,0 @@
package org.broadinstitute.sting.gatk.refdata;
import org.broadinstitute.sting.utils.GenomeLoc;
/**
* Created by IntelliJ IDEA.
* User: mdepristo
* Date: Feb 27, 2009
* Time: 10:49:47 AM
* To change this template use File | Settings | File Templates.
*/
public abstract class ReferenceOrderedDatum implements Comparable<ReferenceOrderedDatum> {
public ReferenceOrderedDatum() { }
public abstract void parseLine(final String[] parts);
public abstract String toString();
public abstract String toSimpleString();
public abstract String repl();
public abstract GenomeLoc getLocation();
public int compareTo( ReferenceOrderedDatum that ) {
return getLocation().compareTo(that.getLocation());
}
public final String getContig() { return getLocation().getContig(); }
public final long getStart() { return getLocation().getStart(); }
public final long getStop() { return getLocation().getStop(); }
}

View File

@ -1,157 +0,0 @@
package org.broadinstitute.sting.gatk.refdata;
import edu.mit.broad.picard.util.SequenceUtil;
import java.util.*;
import org.broadinstitute.sting.gatk.refdata.ReferenceOrderedDatum;
import org.broadinstitute.sting.utils.GenomeLoc;
import org.broadinstitute.sting.utils.Utils;
/**
* Example format:
* 585 chr1 433 433 rs56289060 0 + - - -/C genomic insertion unknown 0 0 unknown between 1
* 585 chr1 491 492 rs55998931 0 + C C C/T genomic single unknown 0 0 unknown exact 1
*
* User: mdepristo
* Date: Feb 27, 2009
* Time: 10:47:14 AM
* To change this template use File | Settings | File Templates.
*/
public class rodDbSNP extends ReferenceOrderedDatum {
public GenomeLoc loc; // genome location of SNP
// Reference sequence chromosome or scaffold
// Start and stop positions in chrom
public String name; // Reference SNP identifier or Affy SNP name
public String strand; // Which DNA strand contains the observed alleles
public String refBases; // the reference base according to NCBI, in the dbSNP file
public String observed; // The sequences of the observed alleles from rs-fasta files
public String molType; // Sample type from exemplar ss
public String varType; // The class of variant (simple, insertion, deletion, range, etc.)
// Can be 'unknown','single','in-del','het','microsatellite','named','mixed','mnp','insertion','deletion'
public String validationStatus; // The validation status of the SNP
// one of set('unknown','by-cluster','by-frequency','by-submitter','by-2hit-2allele','by-hapmap')
public double avHet; // The average heterozygosity from all observations
public double avHetSE; // The Standard Error for the average heterozygosity
public String func; // The functional category of the SNP (coding-synon, coding-nonsynon, intron, etc.)
// set('unknown','coding-synon','intron','cds-reference','near-gene-3','near-gene-5',
// 'nonsense','missense','frameshift','untranslated-3','untranslated-5','splice-3','splice-5')
public String locType; // How the variant affects the reference sequence
// enum('range','exact','between','rangeInsertion','rangeSubstitution','rangeDeletion')
public int weight; // The quality of the alignment
// ----------------------------------------------------------------------
//
// Constructors
//
// ----------------------------------------------------------------------
public rodDbSNP() {}
// ----------------------------------------------------------------------
//
// manipulating the SNP information
//
// ----------------------------------------------------------------------
public GenomeLoc getLocation() { return loc; }
public boolean onFwdStrand() {
return strand.equals("+");
}
// Get the reference bases on the forward strand
public String getRefBasesFWD() {
if ( onFwdStrand() )
return refBases;
else
return SequenceUtil.reverseComplement(refBases);
}
public List<String> getAllelesFWD() {
List<String> alleles = null;
if ( onFwdStrand() )
alleles = Arrays.asList(observed.split("/"));
else
alleles = Arrays.asList(SequenceUtil.reverseComplement(observed).split("/"));
//System.out.printf("getAlleles %s on %s %b => %s %n", observed, strand, onFwdStrand(), Utils.join("/", alleles));
return alleles;
}
public String getAllelesFWDString() {
return Utils.join("/", getAllelesFWD());
}
// ----------------------------------------------------------------------
//
// What kind of variant are we?
//
// ----------------------------------------------------------------------
public boolean isSNP() { return varType.contains("single"); }
public boolean isInsertion() { return varType.contains("insertion"); }
public boolean isDeletion() { return varType.contains("deletion"); }
public boolean isIndel() { return varType.contains("in-del"); }
public boolean isHapmap() { return validationStatus.contains("by-hapmap"); }
public boolean is2Hit2Allele() { return validationStatus.contains("by-2hit-2allele"); }
// ----------------------------------------------------------------------
//
// formatting
//
// ----------------------------------------------------------------------
public String toString() {
return String.format("%s\t%d\t%d\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%f\t%f\t%s\t%s\t%d",
getContig(), getStart(), getStop(), name, strand, refBases, observed, molType,
varType, validationStatus, avHet, avHetSE, func, locType, weight );
}
public String toSimpleString() {
return String.format("%s:%s:%s", name, observed, strand);
}
public String toMediumString() {
String s = String.format("%s:%s:%s", getLocation().toString(), name, getAllelesFWDString());
if ( isSNP() ) s += ":SNP";
if ( isIndel() ) s += ":Indel";
if ( isHapmap() ) s += ":Hapmap";
if ( is2Hit2Allele() ) s += ":2Hit";
return s;
}
public String repl() {
return String.format("%d\t%s\t%d\t%d\t%s\t0\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%f\t%f\t%s\t%s\t%d",
585, getContig(), getStart()-1, getStop()-1, name, strand, refBases, refBases, observed, molType,
varType, validationStatus, avHet, avHetSE, func, locType, weight );
}
public void parseLine(final String[] parts) {
try {
String contig = parts[1];
long start = Long.parseLong(parts[2]) + 1; // The final is 0 based
long stop = Long.parseLong(parts[3]) + 1; // The final is 0 based
loc = new GenomeLoc(contig, start, stop);
name = parts[4];
refBases = parts[5];
strand = parts[6];
observed = parts[9];
molType = parts[10];
varType = parts[11];
validationStatus = parts[12];
avHet = Double.parseDouble(parts[13]);
avHetSE = Double.parseDouble(parts[14]);
func = parts[15];
locType = parts[16];
weight = Integer.parseInt(parts[17]);
} catch ( RuntimeException e ) {
System.out.printf(" Exception caught during parsing GFFLine %s%n", Utils.join(" <=> ", parts));
throw e;
}
}
}

View File

@ -1,113 +0,0 @@
package org.broadinstitute.sting.gatk.refdata;
import java.util.HashMap;
import org.broadinstitute.sting.gatk.refdata.ReferenceOrderedDatum;
import org.broadinstitute.sting.utils.GenomeLoc;
/**
* Class for representing arbitrary reference ordered data sets
*
* User: mdepristo
* Date: Feb 27, 2009
* Time: 10:47:14 AM
* To change this template use File | Settings | File Templates.
*/
public class rodGFF extends ReferenceOrderedDatum {
private String contig, source, feature, strand, frame;
private long start, stop;
private double score;
private HashMap<String, String> attributes;
// ----------------------------------------------------------------------
//
// Constructors
//
// ----------------------------------------------------------------------
public rodGFF() {
}
public void setValues(final String contig, final String source, final String feature,
final long start, final long stop, final double score,
final String strand, final String frame, HashMap<String, String> attributes) {
this.contig = contig;
this.source = source;
this.feature = feature;
this.start = start;
this.stop= stop;
this.score = score;
this.strand = strand;
this.frame = frame;
this.attributes = attributes;
}
// ----------------------------------------------------------------------
//
// Accessors
//
// ----------------------------------------------------------------------
public String getSource() {
return source;
}
public String getFeature() {
return feature;
}
public String getStrand() {
return strand;
}
public String getFrame() {
return frame;
}
public double getScore() {
return score;
}
public GenomeLoc getLocation() {
return new GenomeLoc(contig, start, stop);
}
public String getAttribute(final String key) {
return attributes.get(key);
}
// ----------------------------------------------------------------------
//
// formatting
//
// ----------------------------------------------------------------------
public String toString() {
return String.format("%s\t%s\t%s\t%d\t%d\t%f\t%s\t%s", contig, source, feature, start, stop, score, strand, frame);
}
public String repl() {
return this.toString();
}
public String toSimpleString() {
return String.format("%s", feature);
}
public void parseLine(final String[] parts) {
//System.out.printf("Parsing GFFLine %s%n", Utils.join(" ", parts));
final String contig = parts[0];
final String source = parts[1];
final String feature = parts[2];
final long start = Long.parseLong(parts[3]);
final long stop = Long.parseLong(parts[4]);
double score = Double.NaN;
if ( ! parts[5].equals(".") )
score = Double.parseDouble(parts[5]);
final String strand = parts[6];
final String frame = parts[7];
HashMap<String, String> attributes = null;
setValues(contig, source, feature, start, stop, score, strand, frame, attributes);
}
}

View File

@ -1,30 +0,0 @@
package org.broadinstitute.sting.gatk.walkers;
import org.broadinstitute.sting.gatk.refdata.ReferenceOrderedDatum;
import org.broadinstitute.sting.gatk.LocusContext;
import java.util.List;
/**
* Created by IntelliJ IDEA.
* User: mdepristo
* Date: Feb 22, 2009
* Time: 2:52:28 PM
* To change this template use File | Settings | File Templates.
*/
public interface LocusWalker<MapType, ReduceType> {
void initialize();
public String walkerType();
// Do we actually want to operate on the context?
boolean filter(List<ReferenceOrderedDatum> rodData, char ref, LocusContext context);
// Map over the org.broadinstitute.sting.gatk.LocusContext
MapType map(List<ReferenceOrderedDatum> rodData, char ref, LocusContext context);
// Given result of map function
ReduceType reduceInit();
ReduceType reduce(MapType value, ReduceType sum);
void onTraversalDone();
}

View File

@ -1,28 +0,0 @@
package org.broadinstitute.sting.gatk.walkers;
import net.sf.samtools.SAMRecord;
import org.broadinstitute.sting.gatk.LocusContext;
/**
* Created by IntelliJ IDEA.
* User: mdepristo
* Date: Feb 22, 2009
* Time: 2:52:28 PM
* To change this template use File | Settings | File Templates.
*/
public interface ReadWalker<MapType, ReduceType> {
void initialize();
public String walkerType();
// Do we actually want to operate on the context?
boolean filter(LocusContext context, SAMRecord read);
// Map over the org.broadinstitute.sting.gatk.LocusContext
MapType map(LocusContext context, SAMRecord read);
// Given result of map function
ReduceType reduceInit();
ReduceType reduce(MapType value, ReduceType sum);
void onTraversalDone();
}