Add wittyer as module (nf-core#5171)

* feat: add wittyer as module * fix: adjust output and version * fix: copy output and script from local * feat: fill in in meta file * fix: remove config file input * fix: run prettier * feat: explain how to create docker image * fix: README for Docker image * fix: modify environment file * fix: stub and file extensions * fix: remove custom extensions * feat: add test file - failing * fix: correct input for tests * fix: licence * fix: container name * fix: finally correct container * fix syntax errors * normal test works, stub fails * fix expected outputs * fix: mention making image public * fix add stageAs, use dotnet * run prettier * [automated] Fix linting with Prettier * add comment for run * fix trailing whitespace * add dependencies to fix linting * fix harmonize inputs in meta and main * fix: run prettier * [automated] Fix linting with Prettier * fix index names * fix version to stub_version in stub test Co-authored-by: Nicolas Vannieuwkerke <[email protected]> * extend tests to capture as much as possible * test with bed file * fix: remove stageAs * fix tests for stageAs removal * remove '' in meta file * exclude conda test for wittyer --------- Co-authored-by: nf-core-bot <[email protected]> Co-authored-by: Nicolas Vannieuwkerke <[email protected]>
RSC-RP · Mar 20, 2024 · dd61350 · dd61350
1 parent 8091d0a
commit dd61350
Show file tree

Hide file tree

Showing 8 changed files with 621 additions and 0 deletions.
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -585,6 +585,8 @@ jobs:
             tags: subworkflows/vcf_annotate_ensemblvep
           - profile: singularity
             tags: bases2fastq
+          - profile: conda
+            tags: wittyer
     env:
       NXF_ANSI_LOG: false
       SENTIEON_LICENSE_BASE64: ${{ secrets.SENTIEON_LICENSE_BASE64 }}

diff --git a/modules/nf-core/wittyer/README.md b/modules/nf-core/wittyer/README.md
@@ -0,0 +1,28 @@
+# Updating the docker container and making a new module release
+
+witty.er is a commercial tool from Illumina. The container provided for the witty.er nf-core module is not provided nor supported by Illumina. Updating the witty.er versions in the container and pushing the update to Dockerhub needs to be done manually.
+
+1. Navigate to the witty.er github repository. - [witty.er](https://github.com/Illumina/witty.er)
+2. Download the latest release.
+   ```bash
+   wget https://github.com/Illumina/witty.er/archive/refs/tags/<VERSION>.tar.gz
+   ```
+3. Uncompress the released package.
+   ```bash
+   tar -xvf <VERSION>.tar.gz
+   ```
+4. Change to the uncompressed directory.
+5. Build docker image using provided Dockerfile.
+
+   ```bash
+   docker build -t wittyer:<VERSION> --platform linux/amd64 .
+   ```
+
+6. Access rights are needed to push the container to the Dockerhub nfcore organization, please ask a core team member to do so.
+
+   ```bash
+   docker tag wittyer:<VERSION> quay.io/nf-core/wittyer:<VERSION>
+   docker push quay.io/nf-core/wittyer:<VERSION>
+   ```
+
+7. Make the image public.
diff --git a/modules/nf-core/wittyer/environment.yml b/modules/nf-core/wittyer/environment.yml
@@ -0,0 +1,7 @@
+name: wittyer
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - tabix
diff --git a/modules/nf-core/wittyer/main.nf b/modules/nf-core/wittyer/main.nf
@@ -0,0 +1,69 @@
+process WITTYER {
+    tag "$meta.id"
+    label 'process_single'
+
+    container "nf-core/wittyer:0.3.3.0"
+
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "WITTYER module does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
+
+    input:
+    tuple val(meta), path(query_vcf), path(query_vcf_index), path(truth_vcf), path(truth_vcf_index), path(bed)
+
+    output:
+    tuple val(meta),    path("*.json")         , emit: report
+    tuple val(meta),    path("*.vcf.gz")       , emit: bench_vcf
+    tuple val(meta),    path("*.vcf.gz.tbi")   , emit: bench_vcf_tbi
+    path  "versions.yml"                       , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args  = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def regions = bed ? "--includeBed=$bed" : ""
+    if ("$truth_vcf" == "${prefix}.vcf.gz")         error "Input and output names are the same, set prefix in module configuration to disambiguate!"
+    if ("$query_vcf" == "${prefix}.vcf.gz")         error "Input and output names are the same, set prefix in module configuration to disambiguate!"
+    if ("$query_vcf_index" == "${prefix}.vcf.gz.tbi") error "Input and output names are the same, set prefix in module configuration to disambiguate!"
+    if ("$query_vcf_index" == "${prefix}.vcf.gz.tbi") error "Input and output names are the same, set prefix in module configuration to disambiguate!"
+
+    // dotnet /opt/Wittyer/Wittyer.dll might need to be replaced with new docker image
+    """
+    mkdir bench
+
+    dotnet /opt/Wittyer/Wittyer.dll \\
+        --truthVcf=${truth_vcf} \\
+        --inputVcf=${query_vcf} \\
+        --outputDirectory=bench \\
+        ${regions} \\
+        ${args}
+
+    mv bench/Wittyer.Stats.json ${prefix}.json
+    mv bench/*.vcf.gz ${prefix}.vcf.gz
+    mv bench/*.vcf.gz.tbi ${prefix}.vcf.gz.tbi
+
+    rm -rf bench
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        wittyer: \$(dotnet /opt/Wittyer/Wittyer.dll --version  |& sed '1!d ; s/witty.er //')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.json
+    echo "" | gzip > ${prefix}.vcf.gz
+    touch ${prefix}.vcf.gz.tbi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        wittyer: \$(dotnet /opt/Wittyer/Wittyer.dll --version  |& sed '1!d ; s/witty.er //')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/wittyer/meta.yml b/modules/nf-core/wittyer/meta.yml
@@ -0,0 +1,66 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: wittyer
+description: A large variant benchmarking tool analogous to hap.py for small variants.
+keywords:
+  - structural-variants
+  - benchmarking
+  - vcf
+tools:
+  - wittyer:
+      description: "Illumina tool for large variant benchmarking"
+      homepage: "https://github.com/Illumina/witty.er"
+      documentation: "https://github.com/Illumina/witty.er"
+      tool_dev_url: "https://github.com/Illumina/witty.er"
+      licence: ["BSD-2"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - query_vcf:
+      type: file
+      description: A VCF with called variants to benchmark against the standard
+      pattern: "*.{vcf,vcf.gz}"
+  - query_vcf_index:
+      type: file
+      description: The index of the called VCF (optional)
+      pattern: "*.tbi"
+  - truth_vcf:
+      type: file
+      description: A standard VCF to compare against
+      pattern: "*.{vcf,vcf.gz}"
+  - truth_vcf_index:
+      type: file
+      description: The index of the standard VCF (optional)
+      pattern: "*.tbi"
+  - bed:
+      type: file
+      description: A BED file specifying regions to be included in the analysis (optional)
+      pattern: "*.bed"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - report:
+      type: file
+      description: Detailed per-sample-pair, per-svtype, per-bin stats
+      pattern: "*.json"
+  - bench_vcf:
+      type: file
+      description: Updated query and truth entries merged into one file
+      pattern: "*.vcf.gz"
+  - bench_vcf_tbi:
+      type: file
+      description: Index of merged query and truth entries VCF file
+      pattern: "*.vcf.gz.tbi"
+authors:
+  - "@famosab"
+maintainers:
+  - "@famosab"
diff --git a/modules/nf-core/wittyer/tests/main.nf.test b/modules/nf-core/wittyer/tests/main.nf.test
@@ -0,0 +1,100 @@
+nextflow_process {
+
+    name "Test Process WITTYER"
+    script "../main.nf"
+    process "WITTYER"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "wittyer"
+
+    test("human - simulatedSV - vcf_gz") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv_tbi'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv2'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv2_tbi'], checkIfExists: true),
+                    []
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() },
+                { assert snapshot(process.out.bench_vcf).match("bench_vcf") },
+                { assert snapshot(process.out.bench_vcf_tbi).match("bench_vcf_tbi") },
+                { assert snapshot(process.out.report).match("report") },
+                { assert snapshot(process.out.version).match("version") }
+            )
+        }
+
+    }
+
+    test("human - simulatedSV - vcf_gz - bed") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test_bed', single_end:false ], // meta map
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv_tbi'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv2'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv2_tbi'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() },
+                { assert snapshot(process.out.bench_vcf).match("bed_bench_vcf") },
+                { assert snapshot(process.out.bench_vcf_tbi).match("bed_bench_vcf_tbi") },
+                { assert snapshot(process.out.report).match("bed_report") },
+                { assert snapshot(process.out.version).match("bed_version") }
+            )
+        }
+
+    }
+
+    test("human - simulatedSV - vcf_gz - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """             
+                input[0] = [
+                    [ id:'test_stub', single_end:false ], // meta map
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv_tbi'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv2'], checkIfExists: true),
+                    file(params.test_data['homo_sapiens']['illumina']['simulated_sv2_tbi'], checkIfExists: true),
+                    []
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() },
+                { assert snapshot(process.out.version).match("stub_version") }
+            )
+        }
+
+    }
+
+}