From cde829899dd8c2d65edf0efaa9a9757134925c1a Mon Sep 17 00:00:00 2001 From: Mauricio Carneiro Date: Mon, 14 Nov 2011 18:07:41 -0500 Subject: [PATCH] compress Reduce Read counts bytes by offset compressed the representation of the reduce reads counts by offset results in 17% average compression in final BAM file size. Example compression --> from : 10, 10, 11, 11, 12, 12, 12, 11, 10 to: 10, 0, 1, 1,2, 2, 2, 1, 0 --- .../org/broadinstitute/sting/utils/sam/GATKSAMRecord.java | 4 +++- .../org/broadinstitute/sting/utils/ReadUtilsUnitTest.java | 5 +++-- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/public/java/src/org/broadinstitute/sting/utils/sam/GATKSAMRecord.java b/public/java/src/org/broadinstitute/sting/utils/sam/GATKSAMRecord.java index 3fe1060dd..6d7c8dad9 100755 --- a/public/java/src/org/broadinstitute/sting/utils/sam/GATKSAMRecord.java +++ b/public/java/src/org/broadinstitute/sting/utils/sam/GATKSAMRecord.java @@ -188,7 +188,9 @@ public class GATKSAMRecord extends BAMRecord { } public final byte getReducedCount(final int i) { - return getReducedReadCounts()[i]; + byte firstCount = getReducedReadCounts()[0]; + byte offsetCount = getReducedReadCounts()[i]; + return (i==0) ? firstCount : (byte) Math.min(firstCount + offsetCount, Byte.MAX_VALUE); } diff --git a/public/java/test/org/broadinstitute/sting/utils/ReadUtilsUnitTest.java b/public/java/test/org/broadinstitute/sting/utils/ReadUtilsUnitTest.java index 46134cd24..53368c339 100755 --- a/public/java/test/org/broadinstitute/sting/utils/ReadUtilsUnitTest.java +++ b/public/java/test/org/broadinstitute/sting/utils/ReadUtilsUnitTest.java @@ -16,7 +16,8 @@ public class ReadUtilsUnitTest extends BaseTest { GATKSAMRecord read, reducedRead; final static String BASES = "ACTG"; final static String QUALS = "!+5?"; - final private static byte[] REDUCED_READ_COUNTS = new byte[]{10, 20, 30, 40}; + final private static byte[] REDUCED_READ_COUNTS = new byte[]{10, 20, 30, 40}; + final private static byte[] REDUCED_READ_COUNTS_TAG = new byte[]{10, 10, 20, 30}; // just the offsets @BeforeTest public void init() { @@ -29,7 +30,7 @@ public class ReadUtilsUnitTest extends BaseTest { reducedRead = ArtificialSAMUtils.createArtificialRead(header, "reducedRead", 0, 1, BASES.length()); reducedRead.setReadBases(BASES.getBytes()); reducedRead.setBaseQualityString(QUALS); - reducedRead.setAttribute(GATKSAMRecord.REDUCED_READ_CONSENSUS_TAG, REDUCED_READ_COUNTS); + reducedRead.setAttribute(GATKSAMRecord.REDUCED_READ_CONSENSUS_TAG, REDUCED_READ_COUNTS_TAG); } private void testReadBasesAndQuals(GATKSAMRecord read, int expectedStart, int expectedStop) {