Merge branch 'master' of ssh://gsa1/humgen/gsa-scr1/gsa-engineering/git/unstable

public/java/src/org/broadinstitute/sting/gatk/walkers/phasing/ReadBackedPhasingWalker.java

@@ -220,6 +220,9 @@ public class ReadBackedPhasingWalker extends RodWalker<PhasingStatsAndOutput, Ph
             }
             else {
                 unprocessedList.add(vc); // Finished with the unprocessed variant, and writer can enforce sorting on-the-fly
+
+                if (DEBUG)
+                    logger.debug("Unprocessed variant = " + VariantContextUtils.getLocation(getToolkit().getGenomeLocParser(), vc));
             }
 
             int numReads = 0;
@@ -1105,7 +1108,7 @@ public class ReadBackedPhasingWalker extends RodWalker<PhasingStatsAndOutput, Ph
             this.alleles = vc.getAlleles();
             this.genotypes = new HashMap<String, Genotype>(vc.getGenotypes()); // since vc.getGenotypes() is unmodifiable
             this.negLog10PError = vc.getNegLog10PError();
-            this.filters = vc.getFilters();
+            this.filters = vc.filtersWereApplied() ? vc.getFilters() : null;
             this.attributes = new HashMap<String, Object>(vc.getAttributes());
         }
 

public/java/src/org/broadinstitute/sting/gatk/walkers/variantutils/VariantsToVCF.java

@@ -199,8 +199,8 @@ public class VariantsToVCF extends RodWalker<Integer, Integer> {
             // setup the header fields
             Set<VCFHeaderLine> hInfo = new HashSet<VCFHeaderLine>();
             hInfo.addAll(VCFUtils.getHeaderFields(getToolkit()));
-            hInfo.add(new VCFHeaderLine("source", "VariantsToVCF"));
+            //hInfo.add(new VCFHeaderLine("source", "VariantsToVCF"));
-            hInfo.add(new VCFHeaderLine("reference", getToolkit().getArguments().referenceFile.getName()));
+            //hInfo.add(new VCFHeaderLine("reference", getToolkit().getArguments().referenceFile.getName()));
 
             allowedGenotypeFormatStrings.add(VCFConstants.GENOTYPE_KEY);
             for ( VCFHeaderLine field : hInfo ) {

public/java/src/org/broadinstitute/sting/utils/codecs/vcf/StandardVCFWriter.java

@@ -444,9 +444,10 @@ public class StandardVCFWriter implements VCFWriter {
                     break;
             }
 
-            for (String s : attrs ) {
+            for (int i = 0; i < attrs.size(); i++) {
-                mWriter.write(VCFConstants.GENOTYPE_FIELD_SEPARATOR);
+                if ( i > 0 || genotypeFormatKeys.contains(VCFConstants.GENOTYPE_KEY) )
-                mWriter.write(s);
+                    mWriter.write(VCFConstants.GENOTYPE_FIELD_SEPARATOR);
+                mWriter.write(attrs.get(i));
             }
         }
     }

public/java/test/org/broadinstitute/sting/gatk/walkers/variantutils/VariantsToVCFIntegrationTest.java

@@ -20,7 +20,7 @@ public class VariantsToVCFIntegrationTest extends WalkerTest {
     @Test
     public void testVariantsToVCFUsingGeliInput() {
         List<String> md5 = new ArrayList<String>();
-        md5.add("815b82fff92aab41c209eedce2d7e7d9");
+        md5.add("4accae035d271b35ee2ec58f403c68c6");
 
         WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec(
                 "-R " + b36KGReference +
@@ -38,7 +38,7 @@ public class VariantsToVCFIntegrationTest extends WalkerTest {
     @Test
     public void testGenotypesToVCFUsingGeliInput() {
         List<String> md5 = new ArrayList<String>();
-        md5.add("22336ee9c12aa222ce29c3c5babca7d0");
+        md5.add("71e8c98d7c3a73b6287ecc339086fe03");
 
         WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec(
                 "-R " + b36KGReference +
@@ -56,7 +56,7 @@ public class VariantsToVCFIntegrationTest extends WalkerTest {
     @Test
     public void testGenotypesToVCFUsingHapMapInput() {
         List<String> md5 = new ArrayList<String>();
-        md5.add("9bedaa7670b86a07be5191898c3727cf");
+        md5.add("f343085305e80c7a2493422e4eaad983");
 
         WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec(
                 "-R " + b36KGReference +
@@ -73,7 +73,7 @@ public class VariantsToVCFIntegrationTest extends WalkerTest {
     @Test
     public void testGenotypesToVCFUsingVCFInput() {
         List<String> md5 = new ArrayList<String>();
-        md5.add("cc215edec9ca28e5c79ab1b67506f9f7");
+        md5.add("86f02e2e764ba35854cff2aa05a1fdd8");
 
         WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec(
                 "-R " + b36KGReference +

public/java/test/org/broadinstitute/sting/utils/codecs/vcf/VCFIntegrationTest.java

@@ -0,0 +1,28 @@
+package org.broadinstitute.sting.utils.codecs.vcf;
+
+import org.broadinstitute.sting.WalkerTest;
+import org.testng.annotations.Test;
+
+import java.io.File;
+import java.util.Arrays;
+import java.util.List;
+
+public class VCFIntegrationTest extends WalkerTest {
+
+    @Test
+    public void testReadingAndWritingWitHNoChanges() {
+
+        String md5ofInputVCF = "a990ba187a69ca44cb9bc2bb44d00447";
+        String testVCF = validationDataLocation + "vcf4.1.example.vcf";
+
+        String baseCommand = "-R " + b37KGReference + " -NO_HEADER -o %s ";
+
+        String test1 = baseCommand + "-T VariantAnnotator -BTI variant -B:variant,vcf " + testVCF;
+        WalkerTestSpec spec1 = new WalkerTestSpec(test1, 1, Arrays.asList(md5ofInputVCF));
+        List<File> result = executeTest("Test Variant Annotator with no changes", spec1).getFirst();
+
+        String test2 = baseCommand + "-T VariantsToVCF -B:variant,vcf " + result.get(0).getAbsolutePath();
+        WalkerTestSpec spec2 = new WalkerTestSpec(test2, 1, Arrays.asList(md5ofInputVCF));
+        executeTest("Test Variants To VCF from new output", spec2);
+    }
+}

public/scala/qscript/org/broadinstitute/sting/queue/qscripts/DataProcessingPipeline.scala

@@ -147,13 +147,22 @@ class DataProcessingPipeline extends QScript {
       }
     }
 
+    println("\n\n*** DEBUG ***\n")
     // Creating one file for each sample in the dataset
     val sampleBamFiles = scala.collection.mutable.Map.empty[String, File]
     for ((sample, flist) <- sampleTable) {
+
+      println(sample + ":")
+      for (f <- flist)
+        println (f)
+      println()
+
       val sampleFileName = new File(qscript.outputDir + qscript.projectName + "." + sample + ".bam")
       sampleBamFiles(sample) = sampleFileName
       add(joinBams(flist, sampleFileName))
     }
+    println("*** DEBUG ***\n\n")
+
     return sampleBamFiles.toMap
   }
 
@@ -211,8 +220,10 @@ class DataProcessingPipeline extends QScript {
     if (in.toString.endsWith("bam"))
       return List(in)
     var l: List[File] = List()
-    for (bam <- fromFile(in).getLines)
+    for (bam <- fromFile(in).getLines) {
-      l :+= new File(bam)
+      if (!bam.startsWith("#") && !bam.isEmpty)
+        l :+= new File(bam.trim)
+    }
     return l
   }
 
@@ -234,9 +245,6 @@ class DataProcessingPipeline extends QScript {
     // Generate a BAM file per sample joining all per lane files if necessary
     val sampleBamFiles: Map[String, File] = createSampleFiles(bams, realignedBams)
 
-
-    println("nContigs: " + nContigs)
-
     // Final output list of processed bam files
     var cohortList: List[File] = List()
 
@@ -244,6 +252,7 @@ class DataProcessingPipeline extends QScript {
     println("\nFound the following samples: ")
     for ((sample, file) <- sampleBamFiles)
       println("\t" + sample + " -> " + file)
+    println("\n")
 
     // If this is a 'knowns only' indel realignment run, do it only once for all samples.
     val globalIntervals = new File(outputDir + projectName + ".intervals")

public/scala/qscript/org/broadinstitute/sting/queue/qscripts/RecalibrateBaseQualities.scala

@@ -41,11 +41,11 @@ class RecalibrateBaseQualities extends QScript {
 
     nContigs = getNumberOfContigs(input)
 
-    val recalFile1: File = swapExt(input, ".bam", "recal1.csv")
+    val recalFile1: File = swapExt(input, ".bam", ".recal1.csv")
-    val recalFile2: File = swapExt(input, ".bam", "recal2.csv")
+    val recalFile2: File = swapExt(input, ".bam", ".recal2.csv")
-    val recalBam: File   = swapExt(input, ".bam", "recal.bam")
+    val recalBam: File   = swapExt(input, ".bam", ".recal.bam")
-    val path1: String    = "before"
+    val path1: String    = input + "before"
-    val path2: String    = "after"
+    val path2: String    = input + "after"
     
     add(cov(input, recalFile1),
         recal(input, recalFile1, recalBam),