From b5d2e299d21c4e595caf8fe829582cf33733c445 Mon Sep 17 00:00:00 2001
From: rpoplin <rpoplin@348d0f76-0448-11de-a6fe-93d51630548a>
Date: Wed, 15 Sep 2010 17:29:31 +0000
Subject: [PATCH] Make it more clear what is going on with the by-hapmap
 validation status in the dbSNP rod

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@4289 348d0f76-0448-11de-a6fe-93d51630548a
---
 .../GenerateVariantClustersWalker.java                     | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/java/src/org/broadinstitute/sting/gatk/walkers/variantrecalibration/GenerateVariantClustersWalker.java b/java/src/org/broadinstitute/sting/gatk/walkers/variantrecalibration/GenerateVariantClustersWalker.java
index c347af681..f00958888 100755
--- a/java/src/org/broadinstitute/sting/gatk/walkers/variantrecalibration/GenerateVariantClustersWalker.java
+++ b/java/src/org/broadinstitute/sting/gatk/walkers/variantrecalibration/GenerateVariantClustersWalker.java
@@ -145,6 +145,7 @@ public class GenerateVariantClustersWalker extends RodWalker<ExpandingArrayList<
                 logger.info("Found input variant track with name " + d.getName());
             } else if ( d.getName().equals(DbSNPHelper.STANDARD_DBSNP_TRACK_NAME) ) {
                 logger.info("Found dbSNP track for use in training with weight = " + WEIGHT_DBSNP);
+                logger.info("\tsites in dbSNP track tagged with by-hapmap validation status will be used in training with weight = " + WEIGHT_HAPMAP);
                 foundDBSNP = true;
             } else if ( d.getName().equals("hapmap") ) {
                 logger.info("Found HapMap track for use in training with weight = " + WEIGHT_HAPMAP);
@@ -230,12 +231,12 @@ public class GenerateVariantClustersWalker extends RodWalker<ExpandingArrayList<
 
     public void onTraversalDone( ExpandingArrayList<VariantDatum> reduceSum ) {
 
+        logger.info( "There are " + reduceSum.size() + " variants with > 0 clustering weight and qual > threshold (--qualThreshold = " + QUAL_THRESHOLD + ")" );
+        logger.info( "The annotations used for clustering are: " + annotationKeys );
+
         final VariantDataManager dataManager = new VariantDataManager( reduceSum, annotationKeys );
         reduceSum.clear(); // Don't need this ever again, clean up some memory
 
-        logger.info( "There are " + dataManager.numVariants + " variants with > 0 clustering weight and qual > threshold (--qualThreshold = " + QUAL_THRESHOLD + ")" );
-        logger.info( "The annotations used for clustering are: " + annotationKeys );
-
         dataManager.normalizeData(); // Each data point is now [ (x - mean) / standard deviation ]
 
         // Create either the Gaussian Mixture Model or the Nearest Neighbors model and run it