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

.github/workflows/cd.yaml

@@ -13,6 +13,7 @@ jobs:
         uses: actions/checkout@v7
         with:
           path: workflows
+      - name: Install Sprocket
         uses: stjude-rust-labs/setup-sprocket@v1
         with:
           github-token: ${{ github.token }}

.github/workflows/docker-build.yaml

@@ -70,25 +70,6 @@ jobs:
           tags: ${{ env.REGISTRY }}/${{ github.repository_owner }}/${{ env.TOOL }}:local
           cache-from: type=registry,ref=${{ env.REGISTRY }}/${{ github.repository_owner }}/${{ env.TOOL }}:buildcache
           cache-to: type=registry,ref=${{ env.REGISTRY }}/${{ github.repository_owner }}/${{ env.TOOL }}:buildcache,mode=max
-      - name: Run Snyk to check Docker image for vulnerabilities
-        # Snyk can be used to break the build when it detects vulnerabilities.
-        # In this case we want to upload the issues to GitHub Code Scanning
-        continue-on-error: true
-        uses: snyk/actions/docker@v0
-        env:
-          SNYK_TOKEN: ${{ secrets.SNYK_TOKEN }}
-        with:
-          image: ${{ env.REGISTRY }}/${{ github.repository_owner }}/${{ env.TOOL }}:local
-          args: --file=${{ matrix.image }}/Dockerfile
-      - name: Clean Snyk SARIF file
-        continue-on-error: true
-        run: |
-          sed -i 's/"security-severity": "null"/"security-severity": "0"/g' snyk.sarif
-      - name: Upload result to GitHub Code Scanning
-        continue-on-error: true
-        uses: github/codeql-action/upload-sarif@v3
-        with:
-          sarif_file: snyk.sarif
       - name: Push image
         run: |
           docker tag ${{ env.REGISTRY }}/${{ github.repository_owner }}/${{ env.TOOL }}:local ${{ env.REGISTRY }}/${{ github.repository_owner }}/${{ env.TOOL }}:${{ env.IMAGE_TAG }}

.github/workflows/sprocket-test.yaml

@@ -36,4 +36,4 @@ jobs:
       env: 
         RUNNER: ${{ matrix.runner }}
       run: |
-        sprocket dev test --exclude-tag slow --exclude-tag high_mem ${{ matrix.file }}
+        sprocket dev test --exclude-tag slow --exclude-tag high_mem --exclude-tag gpu ${{ matrix.file }}

cspell.json

@@ -65,6 +65,23 @@
         "htseq",
         "minfi",
         "Infinium",
+        "bwamem",
+        "temurin",
+        "ngsep",
+        "NGSEP",
+        "deepvariant",
+        "deepsomatic",
+        "mutect",
+        "Mutect",
+        "strelka",
+        "Strelka",
+        "clairs",
+        "hkubal",
+        "revio",
+        "lintr",
+        "Basecaller",
+        "ssrs",
+        "SMRTbell",
         // tool subcommands & flags
         "flagstat",
         "markdup",
@@ -94,6 +111,27 @@
         "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 +186,16 @@
         "recal",
         "recalibrated",
         "recalibrator",
+        "genotyping",
+        "FFPE",
+        "exome",
+        "snvs",
+        "gnom",
+        "gnomad",
+        "finetuned",
+        "shortread",
+        "withzip",
+        "zipcodes",
         "dbsnp",
         "gencode",
         "genelengths",
@@ -171,6 +219,7 @@
         "Nanopore",
         "PACBIO",
         "unpatterned",
+        "MASSEQ",
         "mers",
         // STAR / Picard / GATK option fragments
         "Ftag",
@@ -260,6 +309,7 @@
         "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 September
+
+### Changed
+
+- `read_group.inner_read_group_to_string` can now convert a `ReadGroup` struct to `Array[String]` when `split_on_field == true`[#282](https://github.com/stjudecloud/workflows/pull/282)
+
 ## 2026 February
 
 ### Changed

data_structures/read_group.wdl

@@ -27,19 +27,6 @@
 ## - `PU`: Platform unit (e.g., flowcell-barcode.lane for Illumina or slide
 ##     for SOLiD). Unique identifier.
 ## - `SM`: Sample. Use pool name where a pool is being sequenced.
-##
-## An example input JSON entry for `read_group` might look like this:
-## ```json
-## {
-##     "read_group": {
-##         "ID": "rg1",
-##         "PI": 150,
-##         "PL": "ILLUMINA",
-##         "SM": "Sample",
-##         "LB": "Sample"
-##     }
-## }
-## ```
 version 1.1
 
 #@ except: SnakeCase
@@ -65,8 +52,10 @@ workflow read_group_to_string {
         name: "ReadGroup to String"
         description: "Validates a `ReadGroup` struct is well-formed and then converts it to a `String`"
         category: "Utility"
+        warning: "If both `format_as_sam_record` and `split_on_field` are `true`, behavior is undefined. This combination may become an error in the future."
         outputs: {
-            validated_read_group: "The validated input `ReadGroup` as a `String`",
+            validated_read_group: "The validated input `ReadGroup` as a `String`. Undefined if `split_on_field == true`.",
+            validated_read_group_array: "The validated input `ReadGroup` as an `Array[String]`, one entry per field. Undefined if `split_on_field == false`.",
         }
     }
 
@@ -77,13 +66,15 @@ workflow read_group_to_string {
             description: "Format the `ReadGroup` as a SAM record?",
             help: "If `true`, the read group string will be prefixed with `@RG` and tab escape sequence (`\t`) delimiters will be used instead of space delimiters.",
         }
+        split_on_field: "Split the ReadGroup into separate array elements, one per field, instead of a single `String`. Behavior is undefined if `format_as_sam_record == true`."
         restrictive: "If true, run a stricter validation of field values. Otherwise, check against SAM spec-defined values."
     }
 
     input {
         ReadGroup read_group
         Array[String] required_fields = ["SM"]
         Boolean format_as_sam_record = false
+        Boolean split_on_field = false
         Boolean restrictive = true
     }
 
@@ -95,10 +86,12 @@ workflow read_group_to_string {
     call inner_read_group_to_string after validate_read_group { input:
         read_group,
         format_as_sam_record,
+        split_on_field,
     }
 
     output {
-        String validated_read_group = inner_read_group_to_string.stringified_read_group
+        String? validated_read_group = inner_read_group_to_string.stringified_read_group
+        Array[String]? validated_read_group_array = inner_read_group_to_string.read_group_array
     }
 }
 
@@ -371,9 +364,10 @@ task validate_read_group {
 task inner_read_group_to_string {
     meta {
         description: "Converts a `ReadGroup` struct to a `String` **without any validation**."
-        warning: "Please use the `read_group_to_string` workflow, which has validation of the `ReadGroup` contents."
+        warning: "Please use the `read_group_to_string` workflow, which has validation of the `ReadGroup` contents. Additionally, if both `format_as_sam_record` and `split_on_field` are `true`, behavior is undefined. This combination may become an error in the future."
         outputs: {
-            stringified_read_group: "Input `ReadGroup` as a string",
+            stringified_read_group: "Input `ReadGroup` as a string. Undefined if `split_on_field == true`.",
+            read_group_array: "Input `ReadGroup` as an `Array[String]`. Undefined if `split_on_field == false`.",
         }
     }
 
@@ -383,14 +377,20 @@ task inner_read_group_to_string {
             description: "Format the `ReadGroup` as a SAM record?",
             help: "If `true`, the read group string will be prefixed with `@RG` and tab escape sequence (`\t`) delimiters will be used instead of space delimiters.",
         }
+        split_on_field: "Split the ReadGroup into separate lines for each field. Behavior is undefined if `format_as_sam_record == true`."
     }
 
     input {
         ReadGroup read_group
-        Boolean format_as_sam_record
+        Boolean format_as_sam_record = false
+        Boolean split_on_field = false
     }
 
-    String delimiter = if format_as_sam_record then "\\t" else " "
+    String delimiter = if format_as_sam_record
+        then "\\t"
+        else if split_on_field
+        then "\n"
+        else " "
 
     command <<<
         set -euo pipefail
@@ -417,7 +417,12 @@ task inner_read_group_to_string {
     >>>
 
     output {
-        String stringified_read_group = read_string("out.txt")
+        String? stringified_read_group = if split_on_field
+            then None
+            else read_string("out.txt")
+        Array[String]? read_group_array = if split_on_field
+            then read_lines("out.txt")
+            else None
     }
 
     runtime {

data_structures/test/read_group.yaml

@@ -23,6 +23,8 @@ read_group_to_string:
         validated_read_group:
           - Contains: R1
           - Contains: sampleFoo
+        validated_read_group_array:
+          - Defined: false
   - name: id_with_spaces
     inputs:
       read_group:
@@ -82,6 +84,23 @@ read_group_to_string:
           LB: lib
       required_fields:
         - []
+  - name: split_on_field
+    inputs:
+      read_group:
+        - ID: R1
+          SM: sampleFoo
+      split_on_field:
+        - true
+    assertions:
+      outputs:
+        validated_read_group:
+          - Defined: false
+        validated_read_group_array:
+          - Length: 2
+          - First:
+              StrEquals: "ID:R1"
+          - Last:
+              StrEquals: "SM:sampleFoo"
 
 get_read_groups:
   - name: works
@@ -91,3 +110,71 @@ get_read_groups:
         - bams/Aligned.sortedByCoord.chr9_chr22.bam
         - bams/test_rnaseq_variant.bam
         - bams/test.bam
+
+inner_read_group_to_string:
+  - name: space_delimited
+    inputs:
+      read_group:
+        - ID: R1
+          SM: sampleFoo
+    assertions:
+      outputs:
+        stringified_read_group:
+          - Defined: true
+          - StrEquals: "ID:R1 SM:sampleFoo"
+        read_group_array:
+          - Defined: false
+  - name: sam_record
+    inputs:
+      read_group:
+        - ID: R1
+          SM: sampleFoo
+      format_as_sam_record:
+        - true
+    assertions:
+      outputs:
+        stringified_read_group:
+          - Defined: true
+          - Contains: "@RG"
+          - Contains: "ID:R1"
+          - Contains: "SM:sampleFoo"
+        read_group_array:
+          - Defined: false
+  - name: split_on_field
+    inputs:
+      read_group:
+        - ID: R1
+          SM: sampleFoo
+      split_on_field:
+        - true
+    assertions:
+      outputs:
+        stringified_read_group:
+          - Defined: false
+        read_group_array:
+          - Defined: true
+          - Length: 2
+          - First:
+              StrEquals: "ID:R1"
+          - Last:
+              StrEquals: "SM:sampleFoo"
+  - name: sam_record_delimiter_with_split_on_field
+    inputs:
+      read_group:
+        - ID: R1
+          SM: sampleFoo
+      format_as_sam_record:
+        - true
+      split_on_field:
+        - true
+    assertions:
+      outputs:
+        stringified_read_group:
+          - Defined: false
+        read_group_array:
+          - Defined: true
+          # `format_as_sam_record` takes precedence for delimiter selection, so
+          # the tab-delimited content is still a single array element.
+          - Length: 1
+          - First:
+              Contains: "@RG"

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/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"
+}