diff --git a/build.xml b/build.xml index e5ad9daf0..1f26e7b7a 100644 --- a/build.xml +++ b/build.xml @@ -163,6 +163,14 @@ + + + + diff --git a/ivy.xml b/ivy.xml index 115f4062a..f90b9a010 100644 --- a/ivy.xml +++ b/ivy.xml @@ -15,10 +15,8 @@ - - - - + + diff --git a/public/java/src/org/broadinstitute/sting/utils/sam/ReadUtils.java b/public/java/src/org/broadinstitute/sting/utils/sam/ReadUtils.java index 62bbb0307..5d3ef3086 100644 --- a/public/java/src/org/broadinstitute/sting/utils/sam/ReadUtils.java +++ b/public/java/src/org/broadinstitute/sting/utils/sam/ReadUtils.java @@ -118,31 +118,40 @@ public class ReadUtils { /** * This enum represents all the different ways in which a read can overlap an interval. * - * NO_OVERLAP: + * NO_OVERLAP_CONTIG: + * read and interval are in different contigs. + * + * NO_OVERLAP_LEFT: + * the read does not overlap the interval. + * + * |----------------| (interval) + * <----------------> (read) + * + * NO_OVERLAP_RIGHT: * the read does not overlap the interval. * * |----------------| (interval) * <----------------> (read) * - * LEFT_OVERLAP: + * OVERLAP_LEFT: * the read starts before the beginning of the interval but ends inside of it * * |----------------| (interval) * <----------------> (read) * - * RIGHT_OVERLAP: + * OVERLAP_RIGHT: * the read starts inside the interval but ends outside of it * * |----------------| (interval) * <----------------> (read) * - * FULL_OVERLAP: + * OVERLAP_LEFT_AND_RIGHT: * the read starts before the interval and ends after the interval * * |-----------| (interval) * <-------------------> (read) * - * CONTAINED: + * OVERLAP_CONTAINED: * the read starts and ends inside the interval * * |----------------| (interval) @@ -658,7 +667,7 @@ public class ReadUtils { return ReadAndIntervalOverlap.OVERLAP_RIGHT; } - @Ensures({"result >= read.getUnclippedStart()", "result <= read.getUnclippedEnd()"}) + @Ensures({"result >= read.getUnclippedStart()", "result <= read.getUnclippedEnd() || readIsEntirelyInsertion(read)"}) public static int getRefCoordSoftUnclippedStart(SAMRecord read) { int start = read.getUnclippedStart(); for (CigarElement cigarElement : read.getCigar().getCigarElements()) { @@ -670,9 +679,13 @@ public class ReadUtils { return start; } - @Ensures({"result >= read.getUnclippedStart()", "result <= read.getUnclippedEnd()"}) + @Ensures({"result >= read.getUnclippedStart()", "result <= read.getUnclippedEnd() || readIsEntirelyInsertion(read)"}) public static int getRefCoordSoftUnclippedEnd(SAMRecord read) { int stop = read.getUnclippedStart(); + + if (readIsEntirelyInsertion(read)) + return stop; + int shift = 0; CigarOperator lastOperator = null; for (CigarElement cigarElement : read.getCigar().getCigarElements()) { @@ -686,6 +699,14 @@ public class ReadUtils { return (lastOperator == CigarOperator.HARD_CLIP) ? stop-1 : stop+shift-1 ; } + private static boolean readIsEntirelyInsertion(SAMRecord read) { + for (CigarElement cigarElement : read.getCigar().getCigarElements()) { + if (cigarElement.getOperator() != CigarOperator.INSERTION) + return false; + } + return true; + } + /** * Looks for a read coordinate that corresponds to the reference coordinate in the soft clipped region before * the alignment start of the read. diff --git a/public/scala/qscript/org/broadinstitute/sting/queue/qscripts/GATKResourcesBundle.scala b/public/scala/qscript/org/broadinstitute/sting/queue/qscripts/GATKResourcesBundle.scala index 59c00b8cd..036a77b58 100755 --- a/public/scala/qscript/org/broadinstitute/sting/queue/qscripts/GATKResourcesBundle.scala +++ b/public/scala/qscript/org/broadinstitute/sting/queue/qscripts/GATKResourcesBundle.scala @@ -131,11 +131,11 @@ class GATKResourcesBundle extends QScript { addResource(new Resource("/humgen/gsa-hpprojects/GATK/data/Comparisons/Validated/HapMap/3.3/genotypes_r27_nr.b37_fwd.vcf", "hapmap_3.3", b37, true, true)) - addResource(new Resource("/humgen/gsa-hpprojects/GATK/data/Comparisons/Unvalidated/AFR+EUR+ASN+1KG.dindel_august_release_merged_pilot1.20110126.sites.vcf", - "1000G_indels_for_realignment", b37, true, false)) + addResource(new Resource("/humgen/1kg/processing/official_release/phase1/ALL.wgs.VQSR_consensus_biallelic.20101123.indels.sites.vcf", + "1000G_biallelic.indels", b37, true, false)) addResource(new Resource("/humgen/gsa-hpprojects/GATK/data/Comparisons/Validated/Mills_Devine_Indels_2011/ALL.wgs.indels_mills_devine_hg19_leftAligned_collapsed_double_hit.sites.vcf", - "indels_mills_devine", b37, true, true)) + "Mills_Devine_2hit.indels", b37, true, true)) // // example call set for wiki tutorial @@ -300,9 +300,9 @@ class GATKResourcesBundle extends QScript { bamFile = bamIn } - class IndexVCF(@Input vcf: File, @Input ref: File) extends CountRod with UNIVERSAL_GATK_ARGS { + class IndexVCF(@Input vcf: File, @Input ref: File) extends CountRODs with UNIVERSAL_GATK_ARGS { //@Output val vcfIndex: File = swapExt(vcf.getParent, vcf, ".vcf", ".vcf.idx") - this.rodBind :+= RodBind(vcf.getName, "VCF", vcf) + this.rod :+= vcf this.reference_sequence = ref } @@ -313,7 +313,7 @@ class GATKResourcesBundle extends QScript { } class MakeDBSNP129(@Input dbsnp: File, @Input ref: File, @Output dbsnp129: File) extends SelectVariants with UNIVERSAL_GATK_ARGS { - this.rodBind :+= RodBind("variant", "VCF", dbsnp) + this.variant = dbsnp this.select ++= List("\"dbSNPBuildID <= 129\"") this.reference_sequence = ref this.out = dbsnp129