adding an interface so that the current @Requires with ROD annotations work in walkers like VariantEval

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@1700 348d0f76-0448-11de-a6fe-93d51630548a

java/src/org/broadinstitute/sting/gatk/refdata/RodGLF.java

@@ -5,7 +5,6 @@ import org.broadinstitute.sting.utils.GenomeLocParser;
 import org.broadinstitute.sting.utils.StingException;
 import org.broadinstitute.sting.utils.Utils;
 import org.broadinstitute.sting.utils.genotype.LikelihoodObject;
-import org.broadinstitute.sting.utils.genotype.Variation;
 import org.broadinstitute.sting.utils.genotype.glf.GLFReader;
 import org.broadinstitute.sting.utils.genotype.glf.GLFRecord;
 import org.broadinstitute.sting.utils.genotype.glf.SinglePointCall;
@@ -14,9 +13,9 @@ import org.broadinstitute.sting.utils.genotype.glf.VariableLengthCall;
 import java.io.File;
 import java.io.FileNotFoundException;
 import java.io.IOException;
+import java.util.ArrayList;
 import java.util.Iterator;
 import java.util.List;
-import java.util.ArrayList;
 
 
 /**
@@ -26,7 +25,7 @@ import java.util.ArrayList;
  *         <p/>
  *         the rod class for GLF data.
  */
-public class RodGLF implements ReferenceOrderedDatum, Variation, Iterator<RodGLF> {
+public class RodGLF implements VariationRod, Iterator<RodGLF> {
     static int count = 0;
     public GLFReader mReader;
     private final String mName;

java/src/org/broadinstitute/sting/gatk/refdata/RodGeliText.java

@@ -29,16 +29,15 @@ import org.broadinstitute.sting.utils.GenomeLoc;
 import org.broadinstitute.sting.utils.GenomeLocParser;
 import org.broadinstitute.sting.utils.genotype.BasicGenotype;
 import org.broadinstitute.sting.utils.genotype.DiploidGenotype;
-import org.broadinstitute.sting.utils.genotype.VariantBackedByGenotype;
-import org.broadinstitute.sting.utils.genotype.Variation;
 import org.broadinstitute.sting.utils.genotype.Genotype;
+import org.broadinstitute.sting.utils.genotype.VariantBackedByGenotype;
 
 import java.io.IOException;
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.List;
 
-public class RodGeliText extends BasicReferenceOrderedDatum implements Variation, VariantBackedByGenotype, AllelicVariant {
+public class RodGeliText extends BasicReferenceOrderedDatum implements VariationRod, VariantBackedByGenotype, AllelicVariant {
     public enum Genotype_Strings {
         AA, AC, AG, AT, CC, CG, CT, GG, GT, TT
     }

java/src/org/broadinstitute/sting/gatk/refdata/RodGenotypeChipAsGFF.java

@@ -18,7 +18,7 @@ import java.util.regex.Pattern;
  * Time: 10:47:14 AM
  * To change this template use File | Settings | File Templates.
  */
-public class RodGenotypeChipAsGFF extends BasicReferenceOrderedDatum implements AllelicVariant, Variation, VariantBackedByGenotype {
+public class RodGenotypeChipAsGFF extends BasicReferenceOrderedDatum implements AllelicVariant, VariationRod, VariantBackedByGenotype {
     private String contig, source, feature, strand, frame;
     private long start, stop;
     private double score;

java/src/org/broadinstitute/sting/gatk/refdata/RodVCF.java

@@ -25,7 +25,7 @@ import java.util.List;
  *         <p/>
  *         An implementation of the ROD for VCF.
  */
-public class RodVCF extends BasicReferenceOrderedDatum implements Variation, VariantBackedByGenotype, Iterator<RodVCF> {
+public class RodVCF extends BasicReferenceOrderedDatum implements VariationRod, VariantBackedByGenotype, Iterator<RodVCF> {
     // our VCF related information
     private VCFReader mReader;
     public VCFRecord mCurrentRecord;

java/src/org/broadinstitute/sting/gatk/refdata/SimpleIndelROD.java

@@ -3,9 +3,10 @@ package org.broadinstitute.sting.gatk.refdata;
 import org.broadinstitute.sting.utils.GenomeLoc;
 import org.broadinstitute.sting.utils.GenomeLocParser;
 
-import java.util.*;
+import java.util.Arrays;
+import java.util.List;
 
-public class SimpleIndelROD extends TabularROD implements Genotype, AllelicVariant {
+public class SimpleIndelROD extends TabularROD implements Genotype, AllelicVariant, VariationRod {
 
     private boolean KGENOMES_FORMAT = false, checkedFormat = false;
 
@@ -18,6 +19,16 @@ public class SimpleIndelROD extends TabularROD implements Genotype, AllelicVaria
         return GenomeLocParser.createGenomeLoc(this.get("0"), pos, (isDeletion() ? pos+length() : pos+1));
     }
 
+    /**
+     * get the reference base(s) at this position
+     *
+     * @return the reference base or bases, as a string
+     */
+    @Override
+    public String getReference() {
+        return String.valueOf(getRef());
+    }
+
     public List<String> getFWDAlleles() {
         if ( is1KGFormat() )
             return Arrays.asList(this.get("4"));
@@ -36,8 +47,46 @@ public class SimpleIndelROD extends TabularROD implements Genotype, AllelicVaria
     public boolean isGenotype() { return false; }
     public boolean isPointGenotype() { return false; }
     public boolean isIndelGenotype() { return true; }
+
+    /**
+     * get the frequency of this variant
+     *
+     * @return VariantFrequency with the stored frequency
+     */
+    @Override
+    public double getNonRefAlleleFrequency() {
+        return 0.0;
+    }
+
+    /** @return the VARIANT_TYPE of the current variant */
+    @Override
+    public VARIANT_TYPE getType() {
+        return VARIANT_TYPE.INDEL;
+    }
+
     public boolean isSNP() { return false; }
     public boolean isReference() { return false; }
+
+    /**
+     * gets the alternate base.  Use this method if we're biallelic
+     *
+     * @return
+     */
+    @Override
+    public String getAlternateBase() {
+       return "";
+    }
+
+    /**
+     * gets the alternate bases.  Use this method if teh allele count is greater then 2
+     *
+     * @return
+     */
+    @Override
+    public List<String> getAlternateBases() {
+        return Arrays.asList(new String[]{""});
+    }
+
     public boolean isInsertion() {
         if ( is1KGFormat() )
             return this.get("3").equals("I");
@@ -49,10 +98,43 @@ public class SimpleIndelROD extends TabularROD implements Genotype, AllelicVaria
         return this.get("3").charAt(0) == '-';
     }
     public boolean isIndel() { return true; }
+
+    /**
+     * gets the alternate base is the case of a SNP.  Throws an IllegalStateException if we're not a SNP
+     * of
+     *
+     * @return a char, representing the alternate base
+     */
+    @Override
+    public char getAlternativeBaseForSNP() {
+        return getAltSnpFWD();
+    }
+
+    /**
+     * gets the reference base is the case of a SNP.  Throws an IllegalStateException if we're not a SNP
+     *
+     * @return a char, representing the alternate base
+     */
+    @Override
+    public char getReferenceForSNP() {
+        return getRefSnpFWD();
+    }
+
     public double getVariantConfidence() { return 0.0; }
     public double getVariationConfidence() { return 0.0; }
     public double getConsensusConfidence() { return 0.0; }
     public boolean isBiallelic() { return true; }
+
+    /**
+     * get the -1 * (log 10 of the error value)
+     *
+     * @return the log based error estimate
+     */
+    @Override
+    public double getNegLog10PError() {
+        return getVariationConfidence();
+    }
+
     public boolean isHom() { return false; }
     public boolean isHet() { return false; }
     public double getHeterozygosity() { return 0.0; }

java/src/org/broadinstitute/sting/gatk/refdata/VariationRod.java

@@ -0,0 +1,15 @@
+package org.broadinstitute.sting.gatk.refdata;
+
+import org.broadinstitute.sting.utils.genotype.Variation;
+
+/**
+ * @author aaron
+ *         <p/>
+ *         Interface VariationRod
+ *         <p/>
+ *         This interface combines two interfaces: Variation and ReferenceOrderedDatum.  This
+ * was required so that the reference ordered data require attribute would have an interface
+ * that both specified variation and ROD compliance.   
+ */
+public interface VariationRod extends Variation, ReferenceOrderedDatum {
+}

java/src/org/broadinstitute/sting/gatk/refdata/rodDbSNP.java

@@ -18,7 +18,7 @@ import java.util.List;
  * Time: 10:47:14 AM
  * To change this template use File | Settings | File Templates.
  */
-public class rodDbSNP extends BasicReferenceOrderedDatum implements Variation, VariantBackedByGenotype, AllelicVariant {
+public class rodDbSNP extends BasicReferenceOrderedDatum implements VariationRod, VariantBackedByGenotype, AllelicVariant {
     public GenomeLoc loc;       // genome location of SNP
                                 // Reference sequence chromosome or scaffold
                                 // Start and stop positions in chrom

java/src/org/broadinstitute/sting/playground/gatk/walkers/varianteval/VariantEvalWalker.java

@@ -26,8 +26,8 @@ import java.util.*;
  *
  */
 @By(DataSource.REFERENCE)
-@Requires(value={DataSource.REFERENCE},referenceMetaData={@RMD(name="eval",type=RodGeliText.class)}) // right now we have no base variant class for rods, this should change
+@Requires(value={DataSource.REFERENCE},referenceMetaData={@RMD(name="eval",type=VariationRod.class)}) // right now we have no base variant class for rods, this should change
-@Allows(value={DataSource.REFERENCE},referenceMetaData = {@RMD(name="eval",type=RodGeliText.class), @RMD(name="dbsnp",type=rodDbSNP.class),@RMD(name="hapmap-chip",type=RodGenotypeChipAsGFF.class), @RMD(name="interval",type=IntervalRod.class)})
+@Allows(value={DataSource.REFERENCE},referenceMetaData = {@RMD(name="eval",type=VariationRod.class), @RMD(name="dbsnp",type=rodDbSNP.class),@RMD(name="hapmap-chip",type=RodGenotypeChipAsGFF.class), @RMD(name="interval",type=IntervalRod.class)})
 public class VariantEvalWalker extends RefWalker<Integer, Integer> {
     @Argument(shortName="minConfidenceScore", doc="Minimum confidence score to consider an evaluation SNP a variant", required=false)
     public int minConfidenceScore = -1;