Merge branch 'master' of ssh://gsa2.broadinstitute.org/humgen/gsa-scr1/gsa-engineering/git/unstable

protected/java/test/org/broadinstitute/sting/gatk/walkers/bqsr/BQSRIntegrationTest.java

@@ -75,10 +75,11 @@ public class BQSRIntegrationTest extends WalkerTest {
                 Arrays.asList(params.md5));
         executeTest("testBQSR-"+params.args, spec).getFirst();
 
-        WalkerTestSpec specNT2 = new WalkerTestSpec(
-                params.getCommandLine() + " -nt 2",
-                Arrays.asList(params.md5));
-        executeTest("testBQSR-nt2-"+params.args, specNT2).getFirst();
+        // TODO -- re-enable once parallelization is fixed in BaseRecalibrator
+        //WalkerTestSpec specNT2 = new WalkerTestSpec(
+        //        params.getCommandLine() + " -nt 2",
+        //        Arrays.asList(params.md5));
+        //executeTest("testBQSR-nt2-"+params.args, specNT2).getFirst();
     }
 
     @Test

public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/DepthOfCoverage.java

@@ -22,19 +22,10 @@ import java.util.Map;
 /**
  * Total (unfiltered) depth over all samples.
  *
- * This and AD are complementary fields that are two important ways of thinking about the depth of the data for this sample
- * at this site.  The DP field describe the total depth of reads that passed the Unified Genotypers internal
- * quality control metrics (like MAPQ > 17, for example), whatever base was present in the read at this site.
- * The AD values (one for each of REF and ALT fields) is the count of all reads that carried with them the
- * REF and ALT alleles. The reason for this distinction is that the DP is in some sense reflective of the
- * power I have to determine the genotype of the sample at this site, while the AD tells me how many times
- * I saw each of the REF and ALT alleles in the reads, free of any bias potentially introduced by filtering
- * the reads. If, for example, I believe there really is a an A/T polymorphism at a site, then I would like
- * to know the counts of A and T bases in this sample, even for reads with poor mapping quality that would
- * normally be excluded from the statistical calculations going into GQ and QUAL.
- *
- * Note that the DP is affected by downsampling (-dcov) though, so the max value one can obtain for N samples with
- * -dcov D is N * D
+ * While the sample-level (FORMAT) DP field describes the total depth of reads that passed the Unified Genotyper's
+ * internal quality control metrics (like MAPQ > 17, for example), the INFO field DP represents the unfiltered depth
+ * over all samples.  Note though that the DP is affected by downsampling (-dcov), so the max value one can obtain for
+ * N samples with -dcov D is N * D
  */
 public class DepthOfCoverage extends InfoFieldAnnotation implements StandardAnnotation, ActiveRegionBasedAnnotation {
 

public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/DepthPerAlleleBySample.java

@@ -24,10 +24,10 @@ import java.util.List;
 /**
  * The depth of coverage of each VCF allele in this sample.
  *
- * This and DP are complementary fields that are two important ways of thinking about the depth of the data for this sample
- * at this site. The DP field describe the total depth of reads that passed the Unified Genotypers internal
- * quality control metrics (like MAPQ > 17, for example), whatever base was present in the read at this site.
- * The AD values (one for each of REF and ALT fields) is the count of all reads that carried with them the
+ * The AD and DP are complementary fields that are two important ways of thinking about the depth of the data for this
+ * sample at this site.  While the sample-level (FORMAT) DP field describes the total depth of reads that passed the
+ * Unified Genotyper's internal quality control metrics (like MAPQ > 17, for example), the AD values (one for each of
+ * REF and ALT fields) is the unfiltered count of all reads that carried with them the
  * REF and ALT alleles. The reason for this distinction is that the DP is in some sense reflective of the
  * power I have to determine the genotype of the sample at this site, while the AD tells me how many times
  * I saw each of the REF and ALT alleles in the reads, free of any bias potentially introduced by filtering
@@ -35,10 +35,10 @@ import java.util.List;
  * to know the counts of A and T bases in this sample, even for reads with poor mapping quality that would
  * normally be excluded from the statistical calculations going into GQ and QUAL. Please note, however, that
  * the AD isn't necessarily calculated exactly for indels (it counts as non-reference only those indels that
- * are actually present and correctly left-aligned in the alignments themselves). Because of this fact and
+ * are unambiguously informative about the alternate allele). Because of this fact and
  * because the AD includes reads and bases that were filtered by the Unified Genotyper, <b>one should not base
  * assumptions about the underlying genotype based on it</b>; instead, the genotype likelihoods (PLs) are what
- * determine the genotype calls (see below).
+ * determine the genotype calls.
  */
 public class DepthPerAlleleBySample extends GenotypeAnnotation implements StandardAnnotation {
 

public/java/src/org/broadinstitute/sting/gatk/walkers/bqsr/BaseRecalibrator.java

@@ -136,6 +136,10 @@ public class BaseRecalibrator extends LocusWalker<Long, Long> implements TreeRed
      */
     public void initialize() {
 
+        // TODO -- remove me after the 2.1 release
+        if ( getToolkit().getArguments().numberOfThreads > 1 )
+            throw new UserException("We have temporarily disabled the ability to run BaseRecalibrator multi-threaded for performance reasons.  We hope to have this fixed for the next GATK release (2.2) and apologize for the inconvenience.");
+
         // check for unsupported access
         if (getToolkit().isGATKLite() && !getToolkit().getArguments().disableIndelQuals)
             throw new UserException.NotSupportedInGATKLite("base insertion/deletion recalibration is not supported, please use the --disable_indel_quals argument");