mskcc-omics-workflows · johnoooh · Aug 26, 2026 · Aug 26, 2026
@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "ANNOTATE_HLAHD=HERE"
@@ -0,0 +1,50 @@
+process ANNOTATE_HLAHD {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'docker://ghcr.io/mskcc-omics-workflows/hlahd-tools:1.0.0':
+        'ghcr.io/mskcc-omics-workflows/hlahd-tools:1.0.0' }"
+
+    input:
+    tuple val(meta), path(result_dir)
+    path pgroup_file
+
+    output:
+    tuple val(meta), path("${prefix}_annotated.tsv"), emit: tsv
+    tuple val(meta), path("${prefix}_report.html"),   emit: report, optional: true
+    path "versions.yml",                              emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix   = task.ext.prefix ?: "${meta.id}"
+    """
+    annotate_hlahd \\
+        --result_dir ${result_dir} \\
+        --sample ${prefix} \\
+        --pgroup_file ${pgroup_file} \\
+        --outdir . \\
+        ${args}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$(python3 --version | sed 's/Python //')
+    END_VERSIONS
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    echo -e "locus\\tallele1\\tallele2\\tp_group" > ${prefix}_annotated.tsv
+    echo "<html><body>stub report</body></html>" > ${prefix}_report.html
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: 3.11
+    END_VERSIONS
+    """
+}
@@ -0,0 +1,64 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "annotate_hlahd"
+description: Annotate HLA-HD class I output with IMGT P-groups and quality flags
+keywords:
+  - hla
+  - hlahd
+  - annotation
+  - immunogenomics
+tools:
+  - "annotate_hlahd":
+      description: "Post-processes HLA-HD's per-sample final.result.txt/*.est.txt class I output, mapping each allele call to its IMGT P-group and flagging low-confidence calls."
+      homepage: "https://github.com/mskcc/hla-annotate"
+      documentation: "https://github.com/mskcc/hla-annotate"
+      licence:
+        - "MIT"
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - result_dir:
+        type: directory
+        description: Directory containing HLA-HD's <sample>_final.result.txt and <sample>_{A,B,C}.est.txt
+        pattern: "*"
+  - - pgroup_file:
+        type: file
+        description: IMGT wmda/hla_nom_p.txt P-group reference table
+        pattern: "*.txt"
+output:
+  - tsv:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - ${prefix}_annotated.tsv:
+          type: file
+          description: Per-allele annotated TSV with P-group and quality-flag columns
+          pattern: "*_annotated.tsv"
+  - report:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - ${prefix}_report.html:
+          type: file
+          description: |
+            Self-contained HTML report for the sample. Optional — pass `--skip_html`
+            via `task.ext.args` to skip generating it.
+          pattern: "*_report.html"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+          ontologies:
+            - edam: http://edamontology.org/format_3750
+authors:
+  - "@johnoooh"
+maintainers:
+  - "@johnoooh"
@@ -0,0 +1,115 @@
+nextflow_process {
+
+    name "Test Process ANNOTATE_HLAHD"
+    script "../main.nf"
+    process "ANNOTATE_HLAHD"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "modules_msk"
+    tag "annotate_hlahd"
+
+    // Test 1: full run with real (synthetic) data.
+    // The module's result_dir input expects a single directory containing
+    // <sample>_final.result.txt and <sample>_{A,B,C}.est.txt; test_data.config
+    // registers those as individual files, so this test stages them into one
+    // directory before invoking the process.
+    test("annotate_hlahd - result_dir - annotated tsv and html") {
+
+        when {
+            process {
+                """
+                def resultDir = File.createTempDir()
+                new File(resultDir, "test_sample_final.result.txt")
+                    .bytes = file(params.test_data_mskcc['annotate_hlahd']['final_result_txt'], checkIfExists: true).bytes
+                new File(resultDir, "test_sample_A.est.txt")
+                    .bytes = file(params.test_data_mskcc['annotate_hlahd']['est_a_txt'], checkIfExists: true).bytes
+                new File(resultDir, "test_sample_B.est.txt")
+                    .bytes = file(params.test_data_mskcc['annotate_hlahd']['est_b_txt'], checkIfExists: true).bytes
+                new File(resultDir, "test_sample_C.est.txt")
+                    .bytes = file(params.test_data_mskcc['annotate_hlahd']['est_c_txt'], checkIfExists: true).bytes
+
+                input[0] = [
+                    [ id:'test_sample' ],
+                    file(resultDir)
+                ]
+                input[1] = file(params.test_data_mskcc['annotate_hlahd']['pgroup_file'], checkIfExists: true)
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.tsv,
+                    process.out.report,
+                    process.out.versions
+                ).match() }
+            )
+        }
+    }
+
+    // Test 2: --skip_html should suppress the (optional) report output.
+    test("annotate_hlahd - skip_html - no report emitted") {
+
+        config "./nextflow.config"
+
+        when {
+            process {
+                """
+                def resultDir = File.createTempDir()
+                new File(resultDir, "test_sample_final.result.txt")
+                    .bytes = file(params.test_data_mskcc['annotate_hlahd']['final_result_txt'], checkIfExists: true).bytes
+                new File(resultDir, "test_sample_A.est.txt")
+                    .bytes = file(params.test_data_mskcc['annotate_hlahd']['est_a_txt'], checkIfExists: true).bytes
+                new File(resultDir, "test_sample_B.est.txt")
+                    .bytes = file(params.test_data_mskcc['annotate_hlahd']['est_b_txt'], checkIfExists: true).bytes
+                new File(resultDir, "test_sample_C.est.txt")
+                    .bytes = file(params.test_data_mskcc['annotate_hlahd']['est_c_txt'], checkIfExists: true).bytes
+
+                input[0] = [
+                    [ id:'test_sample' ],
+                    file(resultDir)
+                ]
+                input[1] = file(params.test_data_mskcc['annotate_hlahd']['pgroup_file'], checkIfExists: true)
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.report == [] },
+                { assert snapshot(process.out.tsv, process.out.versions).match() }
+            )
+        }
+    }
+
+    // Test 3: stub run (no container needed)
+    test("annotate_hlahd - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test_sample' ],
+                    file('result_dir')
+                ]
+                input[1] = file('hla_nom_p.txt')
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert path(process.out.tsv.get(0).get(1)).exists() },
+                { assert path(process.out.report.get(0).get(1)).exists() },
+                { assert snapshot(process.out.versions).match() }
+            )
+        }
+    }
+}
@@ -0,0 +1,62 @@
+{
+    "annotate_hlahd - skip_html - no report emitted": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test_sample"
+                    },
+                    "test_sample_annotated.tsv:md5,a8636bc09b81afefdd01e388317b1978"
+                ]
+            ],
+            [
+                "versions.yml:md5,7303efd9ae753a785695afaae7bca831"
+            ]
+        ],
+        "timestamp": "2026-08-26T17:30:52.702765",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "26.04.6"
+        }
+    },
+    "annotate_hlahd - stub": {
+        "content": [
+            [
+                "versions.yml:md5,e1c7ca2bd9524d224402cef26a5fca25"
+            ]
+        ],
+        "timestamp": "2026-08-26T17:30:57.636612",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "26.04.6"
+        }
+    },
+    "annotate_hlahd - result_dir - annotated tsv and html": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test_sample"
+                    },
+                    "test_sample_annotated.tsv:md5,a8636bc09b81afefdd01e388317b1978"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test_sample"
+                    },
+                    "test_sample_report.html:md5,c78df8f69cf678d42b6aa6fad40d223a"
+                ]
+            ],
+            [
+                "versions.yml:md5,7303efd9ae753a785695afaae7bca831"
+            ]
+        ],
+        "timestamp": "2026-08-26T17:30:44.124301",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "26.04.6"
+        }
+    }
+}
@@ -0,0 +1,5 @@
+process {
+    withName: 'ANNOTATE_HLAHD' {
+        ext.args = '--skip_html'
+    }
+}
@@ -0,0 +1,2 @@
+annotate_hlahd:
+  - "modules/msk/annotate_hlahd/**"
@@ -816,5 +816,13 @@ params {
                 test_chr22_collapsed_grouped_bam               = "${params.test_data_base_msk}/feature/fgbio_collectduplexseqmetrics/testdata/chr22_collapsed_grouped.bam"
                 test_chr22_collapsed_grouped_bam_bai           = "${params.test_data_base_msk}/feature/fgbio_collectduplexseqmetrics/testdata/chr22_collapsed_grouped.bam.bai"
             }
+            // NOTE: data lives on the feature/annotate_hlahd branch pending Review Team promotion to an official 'annotate_hlahd' branch.
+            'annotate_hlahd' {
+                final_result_txt                               = "${params.test_data_base_msk}/feature/annotate_hlahd/annotate_hlahd/test_sample_final.result.txt"
+                est_a_txt                                       = "${params.test_data_base_msk}/feature/annotate_hlahd/annotate_hlahd/test_sample_A.est.txt"
+                est_b_txt                                       = "${params.test_data_base_msk}/feature/annotate_hlahd/annotate_hlahd/test_sample_B.est.txt"
+                est_c_txt                                       = "${params.test_data_base_msk}/feature/annotate_hlahd/annotate_hlahd/test_sample_C.est.txt"
+                pgroup_file                                     = "${params.test_data_base_msk}/feature/annotate_hlahd/annotate_hlahd/hla_nom_p_demo.txt"
+            }
     }
 }
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		annotate_hlahd:
		- "modules/msk/annotate_hlahd/**"