Merge pull request #124 from LANL-Bioinformatics/123-add-assembly-stats-output-html

123 add assembly stats output html

Author: chienchi

.github/workflows/build-and-push-image_assembly.yaml

@@ -0,0 +1,66 @@
+name: Build and push container image to GHCR
+
+# Run this workflow whenever a Dockerfile is updated.
+on:
+    workflow_dispatch:
+    push:
+        branches:
+            - main
+        paths:
+            - 'workflows/Nextflow/modules/runAssembly/Dockerfile'
+
+jobs:
+    build-and-push-image:
+        runs-on: ubuntu-latest
+        steps:
+            - name: Checkout branch
+              uses: actions/checkout@v4
+            - name: Get Version
+              id: get_version
+              run: |
+                  VERSION=$(grep -oP 'version=\K.*' workflows/Nextflow/modules/runAssembly/Dockerfile)
+                  VERSION=${VERSION:-1.0.0}
+                  echo "version=${VERSION}" >> "$GITHUB_OUTPUT"
+            - name: Authenticate with container registry
+              uses: docker/login-action@v3
+              with:
+                  registry: ghcr.io
+                  username: ${{ github.actor }}
+                  password: ${{ secrets.GITHUB_TOKEN }}
+              # Use the `docker/build-push-action` action to build the image described
+              # by the specified Dockerfile. If the build succeeds, push the image to GHCR.
+              # This action uses the `tags` parameters to tag the image with the Git tag name
+              # the image, respectively, with the output from the "get_version" step above.
+              # For more info: https://github.com/docker/build-push-action#usage.
+            - name: Build and push container image
+              id: push
+              uses: docker/build-push-action@v5
+              with:
+                  context: .
+                  file: workflows/Nextflow/modules/runAssembly/Dockerfile
+                  push: true
+                  tags: ghcr.io/lanl-bioinformatics/edge_run_assembly:${{ steps.get_version.outputs.version }}
+            - name: update image tag ID and version in the config
+              run: |
+                 imageName="ghcr.io/lanl-bioinformatics/edge_run_assembly:${{ steps.get_version.outputs.version }}"
+                 version="${{ steps.get_version.outputs.version }}"
+                 sed -i -E "s#apwat/run_assembly:[0-9a-zA-Z._-]+#${imageName}#" workflows/Nextflow/configs/container.config
+                 sed -i -E "s#edge_run_assembly:[0-9a-zA-Z._-]+#edge_run_assembly:${version}#" workflows/Nextflow/configs/container.config
+            #A GitHub Action to detect changed files during a Workflow run and to commit and push them back to the GitHub repository. 
+            #By default, the commit is made in the name of "GitHub Actions" and co-authored by the user that made the last commit.
+            - name: auto-commit image version update
+              uses: stefanzweifel/git-auto-commit-action@v5
+              with:
+                  branch: auto-update-${{ github.run_id }}
+                  create_branch: true
+                  commit_message: "Auto update of run assembly docker image version ${{ steps.get_version.outputs.version }}"
+            - name: Create Pull Request
+              run: |
+                  title="Automated PR: update assembly docker image version ${{ steps.get_version.outputs.version }}"
+                  gh pr create \
+                      --base main \
+                      --head auto-update-${{ github.run_id }} \
+                      --title "$title" \
+                      --body "Created by GitHub Action"
+              env:
+                  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

workflows/Nextflow/modules/runAssembly/Dockerfile

@@ -1,4 +1,5 @@
 FROM continuumio/miniconda3:23.5.2-0 AS build
+ENV version=1.7.0
 
 ENV container=docker
 
@@ -23,6 +24,7 @@ RUN conda install -n assembly -c bioconda minimap2=2.26
 RUN conda install -n assembly -c bioconda megahit=1.2.9
 RUN conda install -n assembly -c bioconda idba=1.1.3
 RUN conda install -n assembly -c bioconda unicycler=0.5.0
+RUN conda install -n assembly -c bioconda quast=5.2.0
 RUN wget https://github.com/ruanjue/wtdbg2/releases/download/v2.5/wtdbg-2.5_x64_linux.tgz \
     && tar -xvzf wtdbg-2.5_x64_linux.tgz \
     && cp wtdbg-2.5_x64_linux/* /opt/conda/envs/assembly/bin

workflows/Nextflow/modules/runAssembly/runAssembly.nf

@@ -494,6 +494,38 @@ process bestIncompleteAssembly {
 
 }
 
+process assembly_vis {
+    label "assembly"
+    label "tiny"
+
+    publishDir(
+        path: "${settings["assemblyOutDir"]}",
+        mode: 'copy'
+    )
+
+    input:
+    val settings
+    path contigs
+
+    output:
+    path "stats/assembly_stats_report.html" , emit: stats_html
+    path "stats/assembly_stats_report.txt" , emit: stats_txt
+
+    script:
+    """
+    set -euo pipefail
+    metaquast.py --version > version.txt
+    metaquast.py -o ./stats -m ${settings["minContigSize"]} --no-icarus --max-ref-number 0 ${contigs}
+    if [ -f ./stats/report.html ]; then
+        sed -e 's/.top-panel {/.top-panel {\\n display:none;/' ./stats/report.html > ./stats/assembly_stats_report.html
+        mv ./stats/report.txt ./stats/assembly_stats_report.txt
+    else
+        ERR_MSG="MetaQUAST failed to generate report. Please check the input contigs file. Contigs should >= ${settings["minContigSize"]} bp for the report"
+        echo "\$ERR_MSG" > stats/assembly_stats_report.html
+        echo "\$ERR_MSG" > stats/assembly_stats_report.txt
+    fi
+    """
+}
 //main workflow logic
 workflow ASSEMBLY {
     take:
@@ -598,6 +630,9 @@ workflow ASSEMBLY {
         error "Invalid assembler: ${settings["assembler"]}"
     }
 
+    //assembly visualization
+    assembly_vis(settings, outContigs)
+
     emit:
     outContigs
     annotationContigs