BWA Mem Sorting optimization

.github/actions/nf-test/action.yml

@@ -54,6 +54,40 @@ runs:
         conda-solver: libmamba
         conda-remove-defaults: true
 
+    - name: Check if disk cleanup is needed
+      id: disk-cleanup-check
+      shell: bash
+      env:
+        NFT_WORKDIR: ${{ env.NFT_WORKDIR }}
+      run: |
+        nf-test test \
+          --profile=+${{ inputs.profile }} \
+          $(if [ -n "${{ inputs.tags }}" ]; then echo "--tag ${{ inputs.tags }}"; fi) \
+          --ci \
+          --changed-since HEAD^ \
+          --verbose \
+          --shard ${{ inputs.shard }}/${{ inputs.total_shards }} \
+          --dry-run \
+          &> nf-test.log
+
+        if grep -q 'full - stub' nf-test.log; then
+          echo "cleanup=YES" >> $GITHUB_OUTPUT
+        else
+          echo "cleanup=NO" >> $GITHUB_OUTPUT
+        fi
+
+    - name: Disk space cleanup
+      if: steps.disk-cleanup-check.outputs.cleanup == 'YES'
+      uses: jlumbroso/free-disk-space@v1.3.1
+      with:
+        tool-cache: false
+        android: true
+        dotnet: false
+        haskell: false
+        large-packages: false
+        docker-images: false
+        swap-storage: false
+
     - name: Run nf-test
       shell: bash
       env:

.github/workflows/branch.yml

@@ -11,11 +11,11 @@ jobs:
   test:
     runs-on: ubuntu-latest
     steps:
-      # PRs to the nf-core repo main/master branch are only ok if coming from the nf-core repo `dev` or any `patch` branches
+      # PRs to the nf-core repo main/master branch are only ok if coming from the nf-core repo `dev` or any `patch` or `fix` branches
       - name: Check PRs
         if: github.repository == 'Plant-Food-Research-Open/assemblyqc'
         run: |
-          { [[ ${{ github.event.pull_request.head.repo.full_name }} == Plant-Food-Research-Open/assemblyqc ]] && [[ $GITHUB_HEAD_REF == "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]]
+          { [[ ${{ github.event.pull_request.head.repo.full_name }} == Plant-Food-Research-Open/assemblyqc ]] && [[ $GITHUB_HEAD_REF == "dev" ]]; } || [[ "${GITHUB_HEAD_REF%%/*}" == "patch" ]] || [[ "${GITHUB_HEAD_REF%%/*}" == "fix" ]]
 
       # If the above check failed, post a comment on the PR explaining the failure
       # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets

.github/workflows/linting_comment.yml

@@ -21,7 +21,7 @@ jobs:
         run: echo "pr_number=$(cat linting-logs/PR_number.txt)" >> $GITHUB_OUTPUT
 
       - name: Post PR comment
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728 # v2
+        uses: marocchino/sticky-pull-request-comment@773744901bac0e8cbb5a0dc842800d45e9b2b405 # v2
         with:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           number: ${{ steps.pr_number.outputs.pr_number }}

.nf-core.yml

@@ -48,4 +48,4 @@ template:
     - igenomes
     - multiqc
     - fastqc
-  version: 3.0.0
+  version: 3.0.1

CHANGELOG.md

@@ -3,6 +3,23 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v3.0.1 - [14-Oct-2025]
+
+### `Added`
+
+1. Added disk cleanup to nf-test GitHub CI action to avoid the runner running out of disk space for `full - stub` runs
+2. Added hic.bam file speedup by skipping name sort.
+
+### `Fixed`
+
+1. Fixed an issue in Synteny workflow which caused a pipeline crash when Syri failed for one of the synteny combinations [#315](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/315)
+2. Fixed an issue which cause parameter validation to fail for `hic_map_combinations` when `hic` parameter was set to `null` [#317](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/317)
+
+### `Dependencies`
+
+1. Nextflow!>=24.10.5
+2. nf-schema@2.4.2
+
 ## v3.0.0 - [22-Sep-2025]
 
 ### `Added`

CITATION.cff

@@ -25,7 +25,7 @@ authors:
   - family-names: "Deng"
     given-names: "Cecilia"
 title: "AssemblyQC: A Nextflow pipeline for reproducible reporting of assembly quality"
-version: 3.0.0
+version: 3.0.1
 date-released: 2024-07-30
 url: "https://github.com/Plant-Food-Research-Open/assemblyqc"
 doi: 10.1093/bioinformatics/btae477

conf/modules.config

@@ -358,7 +358,7 @@ process {
     withName: '.*:FQ2HIC:FASTQ_BWA_MEM_SAMBLASTER:BWA_MEM' {
         ext.prefix = { "${meta.id}.on.${meta.ref_id}.bwa.mem" }
         ext.args = '-5SP'
-        ext.args2 = '-n'
+        // ext.args2 = '-n'
     }
 
     withName: '.*:FQ2HIC:FASTQ_BWA_MEM_SAMBLASTER:SAMBLASTER' {

docs/output.md

@@ -183,7 +183,7 @@ Kraken 2 [assigns taxonomic labels](https://ccb.jhu.edu/software/kraken2/) to se
     - `*_1_fastqc.html/*_2_fastqc.html`: FastQC html report for the reads passed by FASTP.
     - `*_1_fastqc.zip/*_2_fastqc.zip`: FastQC stats for the reads passed by FASTP.
   - `hicqc`
-    - `*_qc_report.pdf`: HiC QC report for reads mapped to an assembly.
+    - `*_qc_report.pdf`: HiC QC report for 5% of the HiC reads mapped to an assembly.
   - `*.hic`: The HiC contact map stored as a multi-resolution `.hic` file.
   - `*.assembly`: Assembly file created when the `hic_assembly_mode` is `true`
   - `*.bed`: The bed file listing the names of the contigs on the `assembly` super-scaffold when `hic_assembly_mode` is `true`

modules/local/samtools_subsample_sort.nf

@@ -0,0 +1,48 @@
+process SAMTOOLS_SUBSAMPLE_SORT {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/samtools:1.21--h50ea8bc_0' :
+        'biocontainers/samtools:1.21--h50ea8bc_0' }"
+
+    input:
+    tuple val(meta), path(bam)
+    val(sample_fraction)  // Fraction of reads to sample (e.g., 0.05 for 5%)
+
+    output:
+    tuple val(meta), path("*.subsampled.sorted.bam"), emit: bam
+    path "versions.yml"                              , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def fraction = sample_fraction ?: 0.05
+
+    """
+    # Subsample reads and sort by name in one go
+    # Format for -s is SEED.FRACTION (e.g., 42.05 for 5% with seed 42)
+    samtools view -@ ${task.cpus} -s ${fraction} -b ${bam} \\
+        | samtools sort -n -@ ${task.cpus} ${args} -o ${prefix}.subsampled.sorted.bam -
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.subsampled.sorted.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

nextflow.config

@@ -329,7 +329,7 @@ manifest {
     mainScript      = 'main.nf'
     defaultBranch   = 'main'
     nextflowVersion = '!>=24.10.5'
-    version         = '3.0.0'
+    version         = '3.0.1'
     doi             = 'https://doi.org/10.1093/bioinformatics/btae477'
 }