Merge branch 'develop' into lk-paired-tag-trimming

kshakir · Apr 3, 2024 · 07ce4e7 · 07ce4e7
2 parents 5e07125 + a4aa631
commit 07ce4e7
Show file tree

Hide file tree

Showing 40 changed files with 121 additions and 37 deletions.
diff --git a/pipelines/broad/arrays/single_sample/Arrays.changelog.md b/pipelines/broad/arrays/single_sample/Arrays.changelog.md
@@ -1,3 +1,8 @@
+# 2.6.23
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 2.6.22
 2023-12-18 (Date of Last Commit)
 

diff --git a/pipelines/broad/arrays/single_sample/Arrays.wdl b/pipelines/broad/arrays/single_sample/Arrays.wdl
@@ -23,7 +23,7 @@ import "../../../../tasks/broad/Utilities.wdl" as utils
 
 workflow Arrays {
 
-  String pipeline_version = "2.6.22"
+  String pipeline_version = "2.6.23"
 
   input {
     String chip_well_barcode

diff --git a/...nes/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.changelog.md b/...nes/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.changelog.md
@@ -1,3 +1,8 @@
+# 2.1.12
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list. This is useful for WGS samples that were previously running out of memory.
+
 # 2.1.11
 2023-12-18 (Date of Last Commit)
 

diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.wdl b/pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.wdl
@@ -5,7 +5,7 @@ import "../../../../../../tasks/broad/Qc.wdl" as QC
 
 workflow ReblockGVCF {
 
-  String pipeline_version = "2.1.11"
+  String pipeline_version = "2.1.12"
 
 
   input {
@@ -48,6 +48,7 @@ workflow ReblockGVCF {
         ref_dict = ref_dict,
         calling_interval_list = select_first([calling_interval_list, gvcf]), #nice trick so we don't have to pass around intervals; shouldn't be too much slower
         calling_interval_list_index = gvcf_index,
+        calling_intervals_defined = defined(calling_interval_list),
         is_gvcf = true,
         extra_args = "--no-overlaps",
         gatk_docker = "us.gcr.io/broad-gatk/gatk:4.5.0.0"

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 @@
+# 3.1.19
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 3.1.18
 2023-12-18 (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
@@ -44,7 +44,7 @@ import "../../../../../../structs/dna_seq/DNASeqStructs.wdl"
 # WORKFLOW DEFINITION
 workflow ExomeGermlineSingleSample {
 
-  String pipeline_version = "3.1.18"
+  String pipeline_version = "3.1.19"
 
 
   input {

diff --git a/...seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.changelog.md b/...seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.changelog.md
@@ -1,3 +1,8 @@
+# 1.0.16
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 1.0.15
 2023-12-18 (Date of Last Commit)
 

diff --git a/pipelines/broad/dna_seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.wdl b/pipelines/broad/dna_seq/germline/single_sample/ugwgs/UltimaGenomicsWholeGenomeGermline.wdl
@@ -50,7 +50,7 @@ workflow UltimaGenomicsWholeGenomeGermline {
     filtering_model_no_gt_name: "String describing the optional filtering model; default set to rf_model_ignore_gt_incl_hpol_runs"
   }
 
-  String pipeline_version = "1.0.15"
+  String pipeline_version = "1.0.16"
 
 
   References references = alignment_references.references

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 @@
+# 3.1.20
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 3.1.19
 2023-12-18 (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 = "3.1.19"
+  String pipeline_version = "3.1.20"
 
 
   input {

diff --git a/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.changelog.md b/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.changelog.md
@@ -1,3 +1,8 @@
+# 2.1.18
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 2.1.17
 2023-12-18 (Date of Last Commit)
 

diff --git a/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.wdl b/pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.wdl
@@ -9,7 +9,7 @@ import "../../../../../tasks/broad/DragenTasks.wdl" as DragenTasks
 workflow VariantCalling {
 
 
-  String pipeline_version = "2.1.17"
+  String pipeline_version = "2.1.18"
 
 
   input {

diff --git a/..._seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.changelog.md b/..._seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.changelog.md
@@ -1,3 +1,8 @@
+# 1.0.16
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 1.0.15
 2023-12-18 (Date of Last Commit)
 

diff --git a/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.wdl b/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/UltimaGenomicsWholeGenomeCramOnly.wdl
@@ -43,7 +43,7 @@ workflow UltimaGenomicsWholeGenomeCramOnly {
     save_bam_file: "If true, then save intermeidate ouputs used by germline pipeline (such as the output BAM) otherwise they won't be kept as outputs."
   }
 
-  String pipeline_version = "1.0.15"
+  String pipeline_version = "1.0.16"
 
   References references = alignment_references.references
 

diff --git a/pipelines/broad/genotyping/illumina/IlluminaGenotypingArray.changelog.md b/pipelines/broad/genotyping/illumina/IlluminaGenotypingArray.changelog.md
@@ -1,3 +1,8 @@
+# 1.12.17
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 1.12.16
 2023-12-18 (Date of Last Commit)
 

diff --git a/pipelines/broad/genotyping/illumina/IlluminaGenotypingArray.wdl b/pipelines/broad/genotyping/illumina/IlluminaGenotypingArray.wdl
@@ -21,7 +21,7 @@ import "../../../../tasks/broad/Qc.wdl" as Qc
 
 workflow IlluminaGenotypingArray {
 
-  String pipeline_version = "1.12.16"
+  String pipeline_version = "1.12.17"
 
   input {
     String sample_alias

diff --git a/pipelines/broad/internal/arrays/single_sample/BroadInternalArrays.changelog.md b/pipelines/broad/internal/arrays/single_sample/BroadInternalArrays.changelog.md
@@ -1,3 +1,8 @@
+# 1.1.7
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 1.1.6
 2023-12-18 (Date of Last Commit)
 

diff --git a/pipelines/broad/internal/arrays/single_sample/BroadInternalArrays.wdl b/pipelines/broad/internal/arrays/single_sample/BroadInternalArrays.wdl
@@ -9,7 +9,7 @@ workflow BroadInternalArrays {
         description: "Push outputs of Arrays.wdl to TDR dataset table ArraysOutputsTable."
     }
 
-    String pipeline_version = "1.1.6"
+    String pipeline_version = "1.1.7"
 
     input {
         # inputs to wrapper task

diff --git a/.../germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.changelog.md b/.../germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.changelog.md
@@ -1,3 +1,8 @@
+# 1.0.17
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 1.0.16
 2023-12-18 (Date of Last Commit)
 

diff --git a/...ad/internal/dna_seq/germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.wdl b/...ad/internal/dna_seq/germline/single_sample/UltimaGenomics/BroadInternalUltimaGenomics.wdl
@@ -6,7 +6,7 @@ import "../../../../../../../pipelines/broad/qc/CheckFingerprint.wdl" as FP
 
 workflow BroadInternalUltimaGenomics {
 
-  String pipeline_version = "1.0.16"
+  String pipeline_version = "1.0.17"
 
   input {
 

diff --git a/pipelines/broad/internal/rna_seq/BroadInternalRNAWithUMIs.changelog.md b/pipelines/broad/internal/rna_seq/BroadInternalRNAWithUMIs.changelog.md
@@ -1,3 +1,8 @@
+# 1.0.29
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 1.0.28
 2023-12-18 (Date of Last Commit)
 

diff --git a/pipelines/broad/internal/rna_seq/BroadInternalRNAWithUMIs.wdl b/pipelines/broad/internal/rna_seq/BroadInternalRNAWithUMIs.wdl
@@ -7,7 +7,7 @@ import "../../../../tasks/broad/Utilities.wdl" as utils
 
 workflow BroadInternalRNAWithUMIs {
 
-  String pipeline_version = "1.0.28"
+  String pipeline_version = "1.0.29"
 
   input {
     # input needs to be either "hg19" or "hg38"

diff --git a/pipelines/broad/qc/CheckFingerprint.changelog.md b/pipelines/broad/qc/CheckFingerprint.changelog.md
@@ -1,3 +1,8 @@
+# 1.0.16
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 1.0.15
 2023-12-18 (Date of Last Commit)
 

diff --git a/pipelines/broad/qc/CheckFingerprint.wdl b/pipelines/broad/qc/CheckFingerprint.wdl
@@ -24,7 +24,7 @@ import "../../../tasks/broad/Qc.wdl" as Qc
 
 workflow CheckFingerprint {
 
-  String pipeline_version = "1.0.15"
+  String pipeline_version = "1.0.16"
 
   input {
     File? input_vcf

diff --git a/pipelines/broad/reprocessing/exome/ExomeReprocessing.changelog.md b/pipelines/broad/reprocessing/exome/ExomeReprocessing.changelog.md
@@ -1,3 +1,8 @@
+# 3.1.19
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 3.1.18
 2023-12-18 (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 = "3.1.18"
+  String pipeline_version = "3.1.19"
 
   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 @@
+# 3.1.21
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 3.1.20
 2023-12-18 (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 = "3.1.20"
+  String pipeline_version = "3.1.21"
 
 
   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 @@
+# 2.1.21
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 2.1.20
 2023-12-18 (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 = "2.1.20"
+  String pipeline_version = "2.1.21"
 
   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 @@
+# 3.1.20
+2024-03-26 (Date of Last Commit)
+
+* ValidateVcfs requires less memory when run without interval list; this does not affect this pipeline
+
 # 3.1.19
 2023-12-18 (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 = "3.1.19"
+  String pipeline_version = "3.1.20"
 
   input {
     File? input_cram

diff --git a/tasks/broad/Qc.wdl b/tasks/broad/Qc.wdl
@@ -617,17 +617,17 @@ task ValidateVCF {
     File? dbsnp_vcf
     File? dbsnp_vcf_index
     File calling_interval_list
-    File? calling_interval_list_index  # if the interval list is a VCF, than an index file is also required
+    File? calling_interval_list_index  # if the interval list is a VCF, than an index file makes VcfToIntervalList run faster
+    Boolean calling_intervals_defined = true
     Int preemptible_tries = 3
     Boolean is_gvcf = true
     String? extra_args
     String gatk_docker = "us.gcr.io/broad-gatk/gatk:4.5.0.0"
     Int machine_mem_mb = 7000
   }
 
-  Boolean calling_intervals_is_vcf = defined(calling_interval_list_index)
   String calling_interval_list_basename = basename(calling_interval_list)
-  String calling_interval_list_index_basename = if calling_intervals_is_vcf then basename(select_first([calling_interval_list_index])) else ""
+  String calling_interval_list_index_basename = if calling_intervals_defined then "" else basename(select_first([calling_interval_list_index]))
 
   Int command_mem_mb = machine_mem_mb - 2000
   Float ref_size = size(ref_fasta, "GiB") + size(ref_fasta_index, "GiB") + size(ref_dict, "GiB")
@@ -636,18 +636,21 @@ task ValidateVCF {
   command {
     set -e
     
-    # We can't always assume the index was located with the vcf, so make a link so that the paths look the same
-    ln -s ~{calling_interval_list} ~{calling_interval_list_basename}
-    if [ ~{calling_intervals_is_vcf} == "true" ]; then
+    if [ ~{calling_intervals_defined} == "false" ]; then
+      # We can't always assume the index was located with the vcf, so make a link so that the paths look the same
+      ln -s ~{calling_interval_list} ~{calling_interval_list_basename}
       ln -s ~{calling_interval_list_index} ~{calling_interval_list_index_basename}
+      gatk VcfToIntervalList -I ~{calling_interval_list_basename} -O intervals_from_gvcf.interval_list
+      INTERVALS="intervals_from_gvcf.interval_list"
+    else
+      INTERVALS="~{calling_interval_list}"
     fi
     
-    # Note that WGS needs a lot of memory to do the -L *.vcf if an interval file is not supplied
     gatk --java-options "-Xms~{command_mem_mb}m -Xmx~{command_mem_mb}m" \
       ValidateVariants \
       -V ~{input_vcf} \
       -R ~{ref_fasta} \
-      -L ~{calling_interval_list_basename} \
+      -L $INTERVALS \
       ~{true="-gvcf" false="" is_gvcf} \
       --validation-type-to-exclude ALLELES \
       ~{"--dbsnp " + dbsnp_vcf} \

diff --git a/website/docs/Pipelines/Exome_Germline_Single_Sample_Pipeline/README.md b/website/docs/Pipelines/Exome_Germline_Single_Sample_Pipeline/README.md
@@ -7,7 +7,7 @@ slug: /Pipelines/Exome_Germline_Single_Sample_Pipeline/README
 
 | Pipeline Version | Date Updated | Documentation Author | Questions or Feedback |
 | :----: | :---: | :----: | :--------------: |
-| [ExomeGermlineSingleSample_v3.1.18](https://github.com/broadinstitute/warp/releases?q=ExomeGermlineSingleSample_v3.0.0&expanded=true) | February, 2024 | [Elizabeth Kiernan](mailto:ekiernan@broadinstitute.org) | Please file GitHub issues in WARP or contact [the WARP team](mailto:warp-pipelines-help@broadinstitute.org) |
+| [ExomeGermlineSingleSample_v3.1.19](https://github.com/broadinstitute/warp/releases?q=ExomeGermlineSingleSample_v3.0.0&expanded=true) | March, 2024 | [Elizabeth Kiernan](mailto:ekiernan@broadinstitute.org) | Please file GitHub issues in WARP or contact [the WARP team](mailto:warp-pipelines-help@broadinstitute.org) |
 
 
 The Exome Germline Single Sample pipeline implements data pre-processing and initial variant calling according to the GATK Best Practices for germline SNP and Indel discovery in human exome sequencing data.

diff --git a/website/docs/Pipelines/Exome_Germline_Single_Sample_Pipeline/exome.methods.md b/website/docs/Pipelines/Exome_Germline_Single_Sample_Pipeline/exome.methods.md
@@ -2,13 +2,13 @@
 sidebar_position: 2
 ---
 
-# Exome Germline Single Sample v3.1.18 Methods
+# Exome Germline Single Sample v3.1.19 Methods
 
 The following contains a detailed methods description outlining the pipeline’s process, software, and tools that can be modified for a publication methods section.
 
 ## Detailed Methods
 
-Preprocessing and variant calling was performed using the ExomeGermlineSingleSample 3.1.17 pipeline using Picard 2.26.10, GATK 4.5.0.0, and Samtools 1.11 with default tool parameters unless otherwise specified. All reference files are available in the public [Broad References Google Bucket](https://console.cloud.google.com/storage/browser/gcp-public-data--broad-references/hg38/v0). The pipeline follows GATK Best Practices as previously described ([Van der Auwera & O'Connor, 2020](https://www.oreilly.com/library/view/genomics-in-the/9781491975183/)) as well as the Functional Equivalence specification ([Regier et al., 2018](https://www.nature.com/articles/s41467-018-06159-4)).
+Preprocessing and variant calling was performed using the ExomeGermlineSingleSample 3.1.19 pipeline using Picard 2.26.10, GATK 4.5.0.0, and Samtools 1.11 with default tool parameters unless otherwise specified. All reference files are available in the public [Broad References Google Bucket](https://console.cloud.google.com/storage/browser/gcp-public-data--broad-references/hg38/v0). The pipeline follows GATK Best Practices as previously described ([Van der Auwera & O'Connor, 2020](https://www.oreilly.com/library/view/genomics-in-the/9781491975183/)) as well as the Functional Equivalence specification ([Regier et al., 2018](https://www.nature.com/articles/s41467-018-06159-4)).
 
 ### Pre-processing and QC
 

diff --git a/...Pipelines/Illumina_Genotyping_Arrays_Pipeline/Illumina_genotyping_array_spec.md b/...Pipelines/Illumina_Genotyping_Arrays_Pipeline/Illumina_genotyping_array_spec.md
@@ -4,7 +4,7 @@ sidebar_position: 2
 
 # VCF Overview: Illumina Genotyping Array
 
-The [Illumina Genotyping Array Pipeline](https://github.com/broadinstitute/warp/blob/develop/pipelines/broad/genotyping/illumina/IlluminaGenotypingArray.wdl) v1.12.16 pipeline produces a VCF (Variant Call Format) output with data processing and sample-specific genotype information. The VCF follows the format listed in the [VCF 4.2 specification](https://samtools.github.io/hts-specs/VCFv4.2.pdf), but additionally contains fields and attributes that are unique to the Arrays pipeline.
+The [Illumina Genotyping Array Pipeline](https://github.com/broadinstitute/warp/blob/develop/pipelines/broad/genotyping/illumina/IlluminaGenotypingArray.wdl) v1.12.17 pipeline produces a VCF (Variant Call Format) output with data processing and sample-specific genotype information. The VCF follows the format listed in the [VCF 4.2 specification](https://samtools.github.io/hts-specs/VCFv4.2.pdf), but additionally contains fields and attributes that are unique to the Arrays pipeline.
 
 This document describes the Array pipeline’s unique VCF fields and attributes that are not listed in the standard VCF specification. To learn more about the pipeline, see the [Illumina Genotyping Array Pipeline Overview](./README.md).
 

diff --git a/website/docs/Pipelines/Illumina_Genotyping_Arrays_Pipeline/README.md b/website/docs/Pipelines/Illumina_Genotyping_Arrays_Pipeline/README.md
@@ -7,7 +7,7 @@ slug: /Pipelines/Illumina_Genotyping_Arrays_Pipeline/README
 
 | Pipeline Version | Date Updated | Documentation Author | Questions or Feedback |
 | :----: | :---: | :----: | :--------------: |
-| [Version 1.12.16](https://github.com/broadinstitute/warp/releases) | February, 2024 | [Elizabeth Kiernan](mailto:ekiernan@broadinstitute.org) | Please file GitHub issues in warp or contact [the WARP team](mailto:warp-pipelines-help@broadinstitute.org) |
+| [Version 1.12.17](https://github.com/broadinstitute/warp/releases) | March, 2024 | [Elizabeth Kiernan](mailto:ekiernan@broadinstitute.org) | Please file GitHub issues in warp or contact [the WARP team](mailto:warp-pipelines-help@broadinstitute.org) |
 
 ![The Illumina Genotyping Array Pipeline](./IlluminaGenotyping.png)
 
@@ -239,7 +239,7 @@ The Illumina Genotyping Array Pipeline is available on the cloud-based platform
 
 ## Citing the Illumina Genotyping Array Pipeline
 
-If you use the Illumina Genotyping Array Pipeline in your research, please consider citing our preprint:
+If you use the Illumina Genotyping Array Pipeline in your research, please cite our preprint:
 
 Degatano, K.; Awdeh, A.; Dingman, W.; Grant, G.; Khajouei, F.; Kiernan, E.; Konwar, K.; Mathews, K.; Palis, K.; Petrillo, N.; Van der Auwera, G.; Wang, C.; Way, J.; Pipelines, W. WDL Analysis Research Pipelines: Cloud-Optimized Workflows for Biological Data Processing and Reproducible Analysis. Preprints 2024, 2024012131. https://doi.org/10.20944/preprints202401.2131.v1