added --preserve-map-align-order (#1367)

* Added parameter to avoid non-determinism in DRAGEN aligner
broadinstitute · Sep 17, 2024 · 1bd7527 · 1bd7527
1 parent 58285d0
commit 1bd7527
Show file tree

Hide file tree

Showing 14 changed files with 70 additions and 40 deletions.
diff --git a/pipeline_versions.txt b/pipeline_versions.txt
@@ -1,42 +1,42 @@
 Pipeline Name	Version	Date of Last Commit
-MultiSampleSmartSeq2SingleNucleus	 2.0.0	2024-09-11 
+RNAWithUMIsPipeline	 1.0.17	2024-09-06 
+CheckFingerprint	 1.0.21	2024-09-06 
+CramToUnmappedBams	 1.1.3	2024-08-02 
+ExomeReprocessing	 3.3.1	2024-09-17 
+ExternalExomeReprocessing	 3.3.1	2024-09-17 
+ExternalWholeGenomeReprocessing	 2.3.1	2024-09-17 
+WholeGenomeReprocessing	 3.3.1	2024-09-17 
+AnnotationFiltration	 1.2.6	2024-09-06 
+IlluminaGenotypingArray	 1.12.22	2024-09-06 
+UltimaGenomicsWholeGenomeGermline	 1.1.0	2024-09-06 
+ExomeGermlineSingleSample	 3.2.1	2024-09-17 
+WholeGenomeGermlineSingleSample	 3.3.1	2024-09-17 
+JointGenotypingByChromosomePartTwo	 1.5.1	2024-09-10 
+JointGenotypingByChromosomePartOne	 1.5.1	2024-09-10 
+ReblockGVCF	 2.3.0	2024-09-06 
+JointGenotyping	 1.7.1	2024-09-10 
+UltimaGenomicsJointGenotyping	 1.2.1	2024-09-10 
+VariantCalling	 2.2.2	2024-09-06 
+UltimaGenomicsWholeGenomeCramOnly	 1.0.21	2024-09-06 
+GDCWholeGenomeSomaticSingleSample	 1.3.3	2024-09-06 
+Imputation	 1.1.14	2024-09-06 
+Arrays	 2.6.28	2024-09-06 
+MultiSampleArrays	 1.6.2	2024-08-02 
+ValidateChip	 1.16.6	2024-09-06 
+BroadInternalRNAWithUMIs	 1.0.34	2024-09-06 
+BroadInternalUltimaGenomics	 1.1.0	2024-09-06 
+BroadInternalImputation	 1.1.13	2024-09-06 
+BroadInternalArrays	 1.1.12	2024-09-06 
 MultiSampleSmartSeq2	 2.2.22	2024-09-11 
+MultiSampleSmartSeq2SingleNucleus	 2.0.0	2024-09-11 
 PairedTag	 1.6.1	2024-09-11 
-Optimus	 7.6.1	2024-09-11 
-atac	 2.3.1	2024-09-11 
-snm3C	 4.0.4	2024-08-06 
 SmartSeq2SingleSample	 5.1.21	2024-09-11 
-Multiome	 5.6.1	2024-09-11 
 scATAC	 1.3.2	2023-08-03 
+Optimus	 7.6.1	2024-09-11 
+Multiome	 5.6.1	2024-09-11 
+snm3C	 4.0.4	2024-08-06 
 BuildIndices	 3.0.0	2023-12-06 
+atac	 2.3.1	2024-09-11 
 SlideSeq	 3.4.1	2024-09-11 
 BuildCembaReferences	 1.0.0	2020-11-15 
 CEMBA	 1.1.7	2024-09-06 
-GDCWholeGenomeSomaticSingleSample	 1.3.3	2024-09-06 
-UltimaGenomicsWholeGenomeCramOnly	 1.0.21	2024-09-06 
-JointGenotypingByChromosomePartOne	 1.5.1	2024-09-10 
-JointGenotypingByChromosomePartTwo	 1.5.1	2024-09-10 
-UltimaGenomicsJointGenotyping	 1.2.1	2024-09-10 
-JointGenotyping	 1.7.1	2024-09-10 
-ReblockGVCF	 2.3.0	2024-09-06 
-VariantCalling	 2.2.2	2024-09-06 
-WholeGenomeGermlineSingleSample	 3.3.0	2024-09-06 
-UltimaGenomicsWholeGenomeGermline	 1.1.0	2024-09-06 
-ExomeGermlineSingleSample	 3.2.0	2024-09-06 
-ValidateChip	 1.16.6	2024-09-06 
-Arrays	 2.6.28	2024-09-06 
-Imputation	 1.1.14	2024-09-06 
-MultiSampleArrays	 1.6.2	2024-08-02 
-BroadInternalUltimaGenomics	 1.1.0	2024-09-06 
-BroadInternalArrays	 1.1.12	2024-09-06 
-BroadInternalImputation	 1.1.13	2024-09-06 
-BroadInternalRNAWithUMIs	 1.0.34	2024-09-06 
-CramToUnmappedBams	 1.1.3	2024-08-02 
-ExternalWholeGenomeReprocessing	 2.3.0	2024-09-06 
-ExternalExomeReprocessing	 3.3.0	2024-09-06 
-WholeGenomeReprocessing	 3.3.0	2024-09-06 
-ExomeReprocessing	 3.3.0	2024-09-06 
-IlluminaGenotypingArray	 1.12.22	2024-09-06 
-CheckFingerprint	 1.0.21	2024-09-06 
-AnnotationFiltration	 1.2.6	2024-09-06 
-RNAWithUMIsPipeline	 1.0.17	2024-09-06 
diff --git a/...oad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.changelog.md b/...oad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.changelog.md
@@ -1,3 +1,8 @@
+# 3.2.1
+2024-09-17 (Date of Last Commit)
+
+* Updated DRAGEN aligner parameters to fix non-determinism; this does not affect the Exome workflow 
+
 # 3.2.0
 2024-09-06 (Date of Last Commit)
 

diff --git a/pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.wdl b/pipelines/broad/dna_seq/germline/single_sample/exome/ExomeGermlineSingleSample.wdl
@@ -45,7 +45,7 @@ import "../../../../../../tasks/broad/Utilities.wdl" as utils
 # WORKFLOW DEFINITION
 workflow ExomeGermlineSingleSample {
 
-  String pipeline_version = "3.2.0"
+  String pipeline_version = "3.2.1"
 
 
   input {

diff --git a/...dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.changelog.md b/...dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.changelog.md
@@ -1,3 +1,8 @@
+# 3.3.1
+2024-09-17 (Date of Last Commit)
+
+* Updated DRAGEN aligner parameters to fix non-determinism
+
 # 3.3.0
 2024-09-06 (Date of Last Commit)
 

diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.wdl b/pipelines/broad/dna_seq/germline/single_sample/wgs/WholeGenomeGermlineSingleSample.wdl
@@ -40,7 +40,7 @@ import "../../../../../../structs/dna_seq/DNASeqStructs.wdl"
 workflow WholeGenomeGermlineSingleSample {
 
 
-  String pipeline_version = "3.3.0"
+  String pipeline_version = "3.3.1"
 
 
   input {

diff --git a/pipelines/broad/reprocessing/exome/ExomeReprocessing.changelog.md b/pipelines/broad/reprocessing/exome/ExomeReprocessing.changelog.md
@@ -1,3 +1,8 @@
+# 3.3.1
+2024-09-17 (Date of Last Commit)
+
+* Updated DRAGEN aligner parameters to fix non-determinism; this does not affect the exome workflow 
+
 # 3.3.0
 2024-09-06 (Date of Last Commit)
 

diff --git a/pipelines/broad/reprocessing/exome/ExomeReprocessing.wdl b/pipelines/broad/reprocessing/exome/ExomeReprocessing.wdl
@@ -7,7 +7,7 @@ import "../../../../structs/dna_seq/DNASeqStructs.wdl"
 workflow ExomeReprocessing {
 
 
-  String pipeline_version = "3.3.0"
+  String pipeline_version = "3.3.1"
 
   input {
     File? input_cram

diff --git a/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.changelog.md b/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.changelog.md
@@ -1,3 +1,8 @@
+# 3.3.1
+2024-09-17 (Date of Last Commit)
+
+* Updated DRAGEN aligner parameters to fix non-determinism; this does not affect the Exome workflow
+
 # 3.3.0
 2024-09-06 (Date of Last Commit)
 

diff --git a/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.wdl b/pipelines/broad/reprocessing/external/exome/ExternalExomeReprocessing.wdl
@@ -5,7 +5,7 @@ import "../../../../../tasks/broad/CopyFilesFromCloudToCloud.wdl" as Copy
 
 workflow ExternalExomeReprocessing {
 
-  String pipeline_version = "3.3.0"
+  String pipeline_version = "3.3.1"
 
 
   input {

diff --git a/...es/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.changelog.md b/...es/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.changelog.md
@@ -1,3 +1,8 @@
+# 2.3.1
+2024-09-17 (Date of Last Commit)
+
+* Updated DRAGEN aligner parameters to fix non-determinism
+
 # 2.3.0
 2024-09-06 (Date of Last Commit)
 

diff --git a/pipelines/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.wdl b/pipelines/broad/reprocessing/external/wgs/ExternalWholeGenomeReprocessing.wdl
@@ -6,7 +6,7 @@ import "../../../../../tasks/broad/CopyFilesFromCloudToCloud.wdl" as Copy
 workflow ExternalWholeGenomeReprocessing {
 
 
-  String pipeline_version = "2.3.0"
+  String pipeline_version = "2.3.1"
 
   input {
     File? input_cram

diff --git a/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.changelog.md b/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.changelog.md
@@ -1,3 +1,8 @@
+# 3.3.1
+2024-09-17 (Date of Last Commit)
+
+* Updated DRAGEN aligner parameters to fix non-determinism
+
 # 3.3.0
 2024-09-06 (Date of Last Commit)
 

diff --git a/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.wdl b/pipelines/broad/reprocessing/wgs/WholeGenomeReprocessing.wdl
@@ -6,7 +6,7 @@ import "../../../../structs/dna_seq/DNASeqStructs.wdl"
 
 workflow WholeGenomeReprocessing {
 
-  String pipeline_version = "3.3.0"
+  String pipeline_version = "3.3.1"
 
   input {
     File? input_cram

diff --git a/tasks/broad/DragmapAlignment.wdl b/tasks/broad/DragmapAlignment.wdl
@@ -55,7 +55,7 @@ task SamToFastqAndDragmapAndMba {
     mkdir dragen_reference
     mv ~{dragmap_reference.reference_bin} ~{dragmap_reference.hash_table_cfg_bin} ~{dragmap_reference.hash_table_cmp} dragen_reference
 
-    dragen-os -b ~{input_bam} -r dragen_reference --interleaved=1 2> >(tee ~{output_bam_basename}.dragmap.stderr.log >&2) | samtools view -h -O BAM - > aligned.bam
+    dragen-os -b ~{input_bam} -r dragen_reference --interleaved=1 --preserve-map-align-order true 2> >(tee ~{output_bam_basename}.dragmap.stderr.log >&2) | samtools view -h -O BAM - > aligned.bam
     java -Dsamjdk.compression_level=~{compression_level} -Xms1000m -Xmx1000m -jar /picard/picard.jar \
       MergeBamAlignment \
       VALIDATION_STRINGENCY=SILENT \