Added filter for SNPs cleaned out by the realigner.

It uses the realigner output for filtering; in addition, dbsnp indels partially work; IndelGenotyper calls don't yet work.


git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@1489 348d0f76-0448-11de-a6fe-93d51630548a

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

@@ -0,0 +1,21 @@
+package org.broadinstitute.sting.gatk.refdata;
+
+import org.broadinstitute.sting.utils.GenomeLoc;
+import org.broadinstitute.sting.utils.GenomeLocParser;
+
+
+public class CleanedOutSNPROD extends TabularROD {
+
+    private static final String REAL_SNP_STRING = "SAME_SNP";
+    private static final String FALSE_SNP_STRING = "NOT_SNP";
+
+    public CleanedOutSNPROD(String name) {
+        super(name);
+    }
+
+    public GenomeLoc getLocation() {
+        return GenomeLocParser.parseGenomeLoc(this.get("0"));
+    }
+
+    public boolean isRealSNP() { return this.get("1").equals(REAL_SNP_STRING); }
+ }

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

@@ -72,6 +72,7 @@ public class ReferenceOrderedData<ROD extends ReferenceOrderedDatum> implements
         addModule("Table", TabularROD.class);
         addModule("PooledEM", PooledEMSNPROD.class);
         addModule("1KGSNPs", KGenomesSNPROD.class);
+        addModule("CleanedOutSNP", CleanedOutSNPROD.class);
         addModule("SangerSNP", SangerSNPROD.class);
         addModule("SimpleIndel", SimpleIndelROD.class);
         addModule("HapMapGenotype", HapMapGenotypeROD.class);

java/src/org/broadinstitute/sting/playground/gatk/walkers/variants/VECIndelArtifact.java

@@ -0,0 +1,59 @@
+package org.broadinstitute.sting.playground.gatk.walkers.variants;
+
+import org.broadinstitute.sting.gatk.contexts.VariantContext;
+import org.broadinstitute.sting.gatk.refdata.*;
+
+
+public class VECIndelArtifact implements VariantExclusionCriterion {
+    private boolean exclude;
+    private String source = "N/A";
+
+    public void initialize(String arguments) {
+        if (arguments != null && !arguments.isEmpty()) {
+        }
+    }
+
+    public void compute(VariantContextWindow contextWindow) {
+        VariantContext context = contextWindow.getContext();
+        RefMetaDataTracker tracker = context.getTracker();
+
+        CleanedOutSNPROD cleanedSNP = (CleanedOutSNPROD)tracker.lookup("cleaned", null);
+        if ( cleanedSNP != null && !cleanedSNP.isRealSNP() ) {
+            exclude = true;
+            source = "Cleaner";
+            return;
+        }
+
+        AllelicVariant indelCall = (AllelicVariant)tracker.lookup("indels", null);
+        // TODO - fix indel call capability to span full indel
+        if ( indelCall != null ) {
+            exclude = true;
+            source = "IndelCall";
+            return;
+        }
+
+        rodDbSNP dbsnp = (rodDbSNP)tracker.lookup("dbSNP", null);
+        // TODO - fix dbsnp capability to span full indel
+        if ( dbsnp != null && dbsnp.isIndel() ) {
+            exclude = true;
+            source = "dbsnp";
+            return;
+        }
+
+        exclude = false;
+    }
+
+    public double inclusionProbability() {
+        return exclude ? 0.0 : 1.0;
+    }
+
+    public String getStudyHeader() {
+        return "IndelArtifact\tSource";
+    }
+
+    public String getStudyInfo() {
+        return (exclude ? "fail" : "pass") + "\t" + source;
+    }
+
+    public boolean useZeroQualityReads() { return false; }
+}