feat: aligners & variant callers

.gitattributes

@@ -17,3 +17,8 @@ bin/check-job-alive !text !filter !merge !diff
 *.conf !text !filter !merge !diff
 .fa filter=lfs diff=lfs merge=lfs -text
 *.fa filter=lfs diff=lfs merge=lfs -text
+*.mmi filter=lfs diff=lfs merge=lfs -text
+*.gbz filter=lfs diff=lfs merge=lfs -text
+*.dist filter=lfs diff=lfs merge=lfs -text
+*.min filter=lfs diff=lfs merge=lfs -text
+*.zipcodes filter=lfs diff=lfs merge=lfs -text

cspell.json

@@ -65,6 +65,22 @@
         "htseq",
         "minfi",
         "Infinium",
+        "bwamem",
+        "hisat",
+        "HISAT",
+        "temurin",
+        "ngsep",
+        "NGSEP",
+        "deepvariant",
+        "deepsomatic",
+        "mutect",
+        "Mutect",
+        "strelka",
+        "Strelka",
+        "clairs",
+        "hkubal",
+        "revio",
+        "lintr",
         // tool subcommands & flags
         "flagstat",
         "markdup",
@@ -94,6 +110,27 @@
         "bklist",
         "probelist",
         "incompat",
+        "dont",
+        "bmax",
+        "bmaxdivn",
+        "nodc",
+        "offrate",
+        "ftabchars",
+        "localoffrate",
+        "localftabchars",
+        "bitpacked",
+        "Djava",
+        "pyflow",
+        "mpmap",
+        "rpvg",
+        "srold",
+        "calmd",
+        "vqsr",
+        "gvcf",
+        "gvcfs",
+        "ctgs",
+        "xeuo",
+        "kwdof",
         // genomics / sequencing terms
         "phred",
         "mapq",
@@ -148,6 +185,16 @@
         "recal",
         "recalibrated",
         "recalibrator",
+        "genotyping",
+        "FFPE",
+        "exome",
+        "snvs",
+        "gnom",
+        "gnomad",
+        "finetuned",
+        "shortread",
+        "withzip",
+        "zipcodes",
         "dbsnp",
         "gencode",
         "genelengths",
@@ -259,6 +306,7 @@
         "dplyr",
         "argparse",
         "elif",
+        "pyproject",
         // HPC / infra
         "pipefail",
         "bjobs",

data_structures/CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](http://keepachangelog.com/).
 
+## 2026 May
+
+### Added
+
+- New `read_group.read_group_to_array` task to convert a `ReadGroup` struct to `Array[String]` [#282](https://github.com/stjudecloud/workflows/pull/282)
+
 ## 2026 February
 
 ### Changed

data_structures/read_group.wdl

@@ -425,3 +425,51 @@ task inner_read_group_to_string {
         maxRetries: 1
     }
 }
+
+task read_group_to_array {
+    meta {
+        description: "Converts a `ReadGroup` struct to a `Array[String]` **without any validation**."
+        outputs: {
+            converted_read_group: "Input `ReadGroup` as a `Array[String]`",
+        }
+    }
+
+    parameter_meta {
+        read_group: "`ReadGroup` struct to convert to array"
+    }
+
+    input {
+        ReadGroup read_group
+    }
+
+    String delimiter = "\n"
+
+    command <<<
+        set -euo pipefail
+        {
+            echo -n "~{"ID:" + read_group.ID}"  # required field. All others optional
+            echo -n "~{delimiter + "BC:" + read_group.BC}"
+            echo -n "~{delimiter + "CN:" + read_group.CN}"
+            echo -n "~{delimiter + "DS:" + read_group.DS}"
+            echo -n "~{delimiter + "DT:" + read_group.DT}"
+            echo -n "~{delimiter + "FO:" + read_group.FO}"
+            echo -n "~{delimiter + "KS:" + read_group.KS}"
+            echo -n "~{delimiter + "LB:" + read_group.LB}"
+            echo -n "~{delimiter + "PG:" + read_group.PG}"
+            echo -n "~{delimiter + "PI:" + read_group.PI}"
+            echo -n "~{delimiter + "PL:" + read_group.PL}"
+            echo -n "~{delimiter + "PM:" + read_group.PM}"
+            echo -n "~{delimiter + "PU:" + read_group.PU}"
+            echo "~{delimiter + "SM:" + read_group.SM}"
+        } >> out.txt
+    >>>
+
+    output {
+        Array[String] converted_read_group = read_lines("out.txt")
+    }
+
+    runtime {
+        container: "ghcr.io/stjudecloud/util:3.0.4"
+        maxRetries: 1
+    }
+}

docker/bwamem2/Dockerfile

@@ -0,0 +1,8 @@
+FROM quay.io/biocontainers/samtools:1.17--h00cdaf9_0 AS samtools
+FROM quay.io/biocontainers/bwa-mem2:2.3--he70b90d_0
+
+COPY --from=samtools /usr/local/bin/ /usr/local/bin/
+COPY --from=samtools /usr/local/lib/ /usr/local/lib/
+COPY --from=samtools /usr/local/libexec/ /usr/local/libexec/
+
+ENTRYPOINT [ "bwa-mem2" ]

docker/bwamem2/package.json

@@ -0,0 +1,5 @@
+{
+    "name": "bwamem2",
+    "version": "2.3",
+    "revision": "0"
+}

docker/hisat2/Dockerfile

@@ -0,0 +1,8 @@
+FROM quay.io/biocontainers/samtools:1.17--h00cdaf9_0 AS samtools
+FROM quay.io/biocontainers/hisat2:2.2.1--hdbdd923_7
+
+COPY --from=samtools /usr/local/bin/ /usr/local/bin/
+COPY --from=samtools /usr/local/lib/ /usr/local/lib/
+COPY --from=samtools /usr/local/libexec/ /usr/local/libexec/
+
+ENTRYPOINT [ "hisat2" ]

docker/hisat2/package.json

@@ -0,0 +1,5 @@
+{
+    "name": "hisat2",
+    "version": "2.2.1",
+    "revision": "0"
+}

docker/mako/Dockerfile

@@ -0,0 +1,3 @@
+FROM rust:1.97
+
+RUN cargo install fg-mako@0.1.3

docker/mako/package.json

@@ -0,0 +1,5 @@
+{
+    "name": "mako",
+    "version": "0.1.3",
+    "revision": "0"
+}

docker/minimap2/Dockerfile

@@ -0,0 +1,8 @@
+FROM quay.io/biocontainers/samtools:1.17--h00cdaf9_0 AS samtools
+FROM quay.io/biocontainers/minimap2:2.30--h577a1d6_0
+
+COPY --from=samtools /usr/local/bin/ /usr/local/bin/
+COPY --from=samtools /usr/local/lib/ /usr/local/lib/
+COPY --from=samtools /usr/local/libexec/ /usr/local/libexec/
+
+ENTRYPOINT [ "minimap2" ]

docker/minimap2/package.json

@@ -0,0 +1,5 @@
+{
+    "name": "minimap2",
+    "version": "2.30",
+    "revision": "0"
+}

docker/ngsep/Dockerfile

@@ -0,0 +1,5 @@
+FROM eclipse-temurin:21
+
+RUN wget https://github.com/NGSEP/NGSEPcore/releases/download/v5.1.0/NGSEPcore_5.1.0.jar -O /usr/local/bin/NGSEPcore.jar
+
+ENTRYPOINT [ "java", "-jar", "/usr/local/bin/NGSEPcore.jar" ]

docker/ngsep/package.json

@@ -0,0 +1,5 @@
+{
+    "name": "ngsep",
+    "version": "5.1.0",
+    "revision": "0"
+}

test/fixtures/bams/README.md

@@ -40,6 +40,14 @@ Coordinate sorted BAM with 1 read group (`ID:test`). Aligned using BWA `aln` (us
 
 BAM index corresponding to `test.bwa_aln_pe.chrY_chrM.bam`.
 
+## test.bwa_aln_pe.with_variants.chrY_chrM.bam
+
+Coordinate sorted BAM with 1 read group (`ID:test`). Aligned using BWA `aln` (using the `bwa.bwa_aln_pe` WDL task). 100,000 Paired-End reads mapped to GRCh38 `chrY` and `chrM` from `test_variants_R1.fq.gz` and `test_variants_R2.fq.gz`.
+
+## test.bwa_aln_pe.with_variants.chrY_chrM.bam.bai
+
+BAM index corresponding to `test.bwa_aln_pe.with_variants.chrY_chrM.bam`.
+
 ## test.extra_RG.bam
 
 A duplicate of `test.bam` with an added `@RG` entry with the ID `no_match`. There are no reads corresponding to the `no_match` RG entry.

test/fixtures/fastqs/README.md

@@ -19,3 +19,11 @@ The following list is sorted alphabetically:
 ## test_R2.fq.gz
 
 10,000 reads in FASTQ format. Can be used by itself to represent a Single-End sample or used with `test_R1.fq.gz` to represent a Paired-End sample. Generated with `fq generate`.
+
+## test_variants_R1.fq.gz
+
+10,000 reads in FASTQ format. Can be used by itself to represent a Single-End sample or used with `test_variants.R2.fq.gz` to represent a Paired-End sample. Generated with `fq generate` on `chrY` and `chrM`. Simulated from a reference sequence containing variants.
+
+## test_variants_R2.fq.gz
+
+10,000 reads in FASTQ format. Can be used by itself to represent a Single-End sample or used with `test_variants.R1.fq.gz` to represent a Paired-End sample. Generated with `fq generate` on `chrY` and `chrM`. Simulated from a reference sequence containing variants.

test/fixtures/mutect2/README.md

@@ -0,0 +1,29 @@
+# Mutect2 fixtures
+
+Inputs and intermediate artifacts used by the per-task tests in `tools/test/mutect2.yaml` for `tools/mutect2.wdl`. Files are downsampled to `chrY` and `chrM` to match the reference at `test/fixtures/reference/GRCh38.chrY_chrM.fa` and the BAMs at `test/fixtures/bams/test.bwa_aln_pe*.chrY_chrM.bam`.
+
+The following list is sorted alphabetically:
+
+## af-only-gnomad.hg38.chrY_chrM.vcf.gz
+
+GATK best-practices germline resource (`af-only-gnomad.hg38.vcf.gz` from the GATK resource bundle), subset to `chrY` and `chrM`. Used as the `germline_resource_vcf` input for the `mutect2` task and as both `intervals` and `variants` inputs for the `get_pileup_summaries` task.
+
+## af-only-gnomad.hg38.chrY_chrM.vcf.gz.tbi
+
+Tabix index for `af-only-gnomad.hg38.chrY_chrM.vcf.gz`.
+
+## test.bwa_aln_pe.chrY_chrM_pileup_summaries.table
+
+Output of `gatk GetPileupSummaries` run on `test/fixtures/bams/test.bwa_aln_pe.chrY_chrM.bam` (normal sample) over the sites in `af-only-gnomad.hg38.chrY_chrM.vcf.gz`. Used as the `normal_pileups` input for the `calculate_contamination` task.
+
+## test.bwa_aln_pe.with_variants.chrY_chrM_pileup_summaries.contamination.table
+
+Output of `gatk CalculateContamination` run on the tumor and normal pileup tables (matched-normal mode). Used as the `contamination_table` input for the `filter_mutect` task.
+
+## test.bwa_aln_pe.with_variants.chrY_chrM_pileup_summaries.segments.table
+
+Tumor segmentation output of the same `gatk CalculateContamination` invocation that produced the contamination table. Used as the `maf_segments` input for the `filter_mutect` task.
+
+## test.bwa_aln_pe.with_variants.chrY_chrM_pileup_summaries.table
+
+Output of `gatk GetPileupSummaries` run on `test/fixtures/bams/test.bwa_aln_pe.with_variants.chrY_chrM.bam` (tumor sample) over the sites in `af-only-gnomad.hg38.chrY_chrM.vcf.gz`. Used as the `tumor_pileups` input for the `calculate_contamination` task.

test/fixtures/mutect2/test.bwa_aln_pe.chrY_chrM_pileup_summaries.table

@@ -0,0 +1,2 @@
+#<METADATA>SAMPLE=test
+contig	position	ref_count	alt_count	other_alt_count	allele_frequency

test/fixtures/mutect2/test.bwa_aln_pe.with_variants.chrY_chrM_pileup_summaries.contamination.table

@@ -0,0 +1,2 @@
+sample	contamination	error
+test	0.0	1.0

test/fixtures/mutect2/test.bwa_aln_pe.with_variants.chrY_chrM_pileup_summaries.segments.table

@@ -0,0 +1,2 @@
+#<METADATA>SAMPLE=test
+contig	start	end	minor_allele_fraction

test/fixtures/mutect2/test.bwa_aln_pe.with_variants.chrY_chrM_pileup_summaries.table

@@ -0,0 +1,2 @@
+#<METADATA>SAMPLE=test
+contig	position	ref_count	alt_count	other_alt_count	allele_frequency

test/fixtures/vcfs/README.md

@@ -4,6 +4,18 @@ All the files in this directory were either randomly generated or sourced from p
 
 The following list is sorted alphabetically:
 
+## test.bwa_aln_pe.chrY_chrM.mutect2.vcf.gz
+
+Unfiltered Mutect2 somatic VCF produced by running `gatk Mutect2` with `test/fixtures/bams/test.bwa_aln_pe.with_variants.chrY_chrM.bam` as the tumor sample and `test/fixtures/bams/test.bwa_aln_pe.chrY_chrM.bam` as the matched normal, against `test/fixtures/reference/GRCh38.chrY_chrM.fa`. Used as the `unfiltered_somatic_vcf` input for the `filter_mutect` task in `tools/mutect2.wdl`.
+
+## test.bwa_aln_pe.chrY_chrM.mutect2.vcf.gz.tbi
+
+Tabix index for `test.bwa_aln_pe.chrY_chrM.mutect2.vcf.gz`.
+
+## test.bwa_aln_pe.chrY_chrM.mutect2.vcf.gz.stats
+
+Mutect2 stats sidecar emitted alongside `test.bwa_aln_pe.chrY_chrM.mutect2.vcf.gz`. Used as the `unfiltered_somatic_vcf_stats` input for the `filter_mutect` task.
+
 ## test1.vcf.gz
 
 Single position VCF file
@@ -19,3 +31,11 @@ Single position VCF file
 ## test2.vcf.gz.tbi
 
 Index file for `test2.vcf.gz`.
+
+## testY.vcf.gz
+
+Single position VCF file on `chrY`
+
+## testY.vcf.gz.tbi
+
+Index file for `testY.vcf.gz`.

test/fixtures/vcfs/test.bwa_aln_pe.chrY_chrM.mutect2.vcf.gz.stats

@@ -0,0 +1,2 @@
+statistic	value
+callable	157175.0