Raw-reads preprocesing: qc, trimming and decont

.github/CONTRIBUTING.md

@@ -23,6 +23,9 @@ If you're not used to this workflow with git, you can start with some [docs from
 
 ## Tests
 
+You can optionally test your changes by running the pipeline locally. Then it is recommended to use the `debug` profile to
+receive warnings about process selectors and other debug info. Example: `nextflow run . -profile debug,test,docker --outdir <OUTDIR>`.
+
 When you create a pull request with changes, [GitHub Actions](https://github.com/features/actions) will run automatic tests.
 Typically, pull-requests are only fully reviewed when these tests are passing, though of course we can help out before then.
 

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -2,53 +2,53 @@ name: Bug report
 description: Report something that is broken or incorrect
 labels: bug
 body:
-- type: textarea
-  id: description
-  attributes:
-    label: Description of the bug
-    description: A clear and concise description of what the bug is.
-  validations:
-    required: true
-- type: textarea
-  id: command_used
-  attributes:
-    label: Command used and terminal output
-    description: Steps to reproduce the behaviour. Please paste the command you used
-      to launch the pipeline and the output from your terminal.
-    render: console
-    placeholder: '$ nextflow run ...
-
-
-      Some output where something broke
-
-      '
-- type: textarea
-  id: files
-  attributes:
-    label: Relevant files
-    description: 'Please drag and drop the relevant files here. Create a `.zip` archive
-      if the extension is not allowed.
-
-      Your verbose log file `.nextflow.log` is often useful _(this is a hidden file
-      in the directory where you launched the pipeline)_ as well as custom Nextflow
-      configuration files.
-
-      '
-- type: textarea
-  id: system
-  attributes:
-    label: System information
-    description: '* Nextflow version _(eg. 23.04.0)_
-
-      * Hardware _(eg. HPC, Desktop, Cloud)_
-
-      * Executor _(eg. slurm, local, awsbatch)_
-
-      * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud,
-      or Apptainer)_
-
-      * OS _(eg. CentOS Linux, macOS, Linux Mint)_
-
-      * Version of ebi-metagenomics/shallowmapping _(eg. 1.1, 1.5, 1.8.2)_
-
-      '
+  - type: textarea
+    id: description
+    attributes:
+      label: Description of the bug
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    id: command_used
+    attributes:
+      label: Command used and terminal output
+      description: Steps to reproduce the behaviour. Please paste the command you used
+        to launch the pipeline and the output from your terminal.
+      render: console
+      placeholder: "$ nextflow run ...
+
+
+        Some output where something broke
+
+        "
+  - type: textarea
+    id: files
+    attributes:
+      label: Relevant files
+      description: "Please drag and drop the relevant files here. Create a `.zip` archive
+        if the extension is not allowed.
+
+        Your verbose log file `.nextflow.log` is often useful _(this is a hidden file
+        in the directory where you launched the pipeline)_ as well as custom Nextflow
+        configuration files.
+
+        "
+  - type: textarea
+    id: system
+    attributes:
+      label: System information
+      description: "* Nextflow version _(eg. 23.04.0)_
+
+        * Hardware _(eg. HPC, Desktop, Cloud)_
+
+        * Executor _(eg. slurm, local, awsbatch)_
+
+        * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud,
+        or Apptainer)_
+
+        * OS _(eg. CentOS Linux, macOS, Linux Mint)_
+
+        * Version of ebi-metagenomics/shallowmapping _(eg. 1.1, 1.5, 1.8.2)_
+
+        "

.github/PULL_REQUEST_TEMPLATE.md

@@ -18,6 +18,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/ebi-metageno
 - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/ebi-metagenomics/shallowmapping/tree/master/.github/CONTRIBUTING.md)
 - [ ] Make sure your code lints (`nf-core lint`).
 - [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
+- [ ] Check for unexpected warnings in debug mode (`nextflow run . -profile debug,test,docker --outdir <OUTDIR>`).
 - [ ] Usage Documentation in `docs/usage.md` is updated.
 - [ ] Output Documentation in `docs/output.md` is updated.
 - [ ] `CHANGELOG.md` is updated.

.github/workflows/branch.yml

@@ -19,7 +19,7 @@ jobs:
       # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets
       - name: Post PR comment
         if: failure()
-        uses: mshick/add-pr-comment@v1
+        uses: mshick/add-pr-comment@v2
         with:
           message: |
             ## This PR is against the `master` branch :x:

.github/workflows/linting.yml

@@ -11,72 +11,33 @@ on:
     types: [published]
 
 jobs:
-  EditorConfig:
+  pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
-      - uses: actions/setup-node@v3
-
-      - name: Install editorconfig-checker
-        run: npm install -g editorconfig-checker
-
-      - name: Run ECLint check
-        run: editorconfig-checker -exclude README.md $(find .* -type f | grep -v '.git\|.py\|.md\|json\|yml\|yaml\|html\|css\|work\|.nextflow\|build\|nf_core.egg-info\|log.txt\|Makefile')
-
-  Prettier:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-
-      - uses: actions/setup-node@v3
-
-      - name: Install Prettier
-        run: npm install -g prettier
-
-      - name: Run Prettier --check
-        run: prettier --check ${GITHUB_WORKSPACE}
-
-  PythonBlack:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Check code lints with Black
-        uses: psf/black@stable
-
-      # If the above check failed, post a comment on the PR explaining the failure
-      - name: Post PR comment
-        if: failure()
-        uses: mshick/add-pr-comment@v1
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v5
         with:
-          message: |
-            ## Python linting (`black`) is failing
-
-            To keep the code consistent with lots of contributors, we run automated code consistency checks.
-            To fix this CI test, please run:
-
-            * Install [`black`](https://black.readthedocs.io/en/stable/): `pip install black`
-            * Fix formatting errors in your pipeline: `black .`
-
-            Once you push these changes the test should pass, and you can hide this comment :+1:
+          python-version: 3.11
+          cache: "pip"
 
-            We highly recommend setting up Black in your code editor so that this formatting is done automatically on save. Ask about it on Slack for help!
+      - name: Install pre-commit
+        run: pip install pre-commit
 
-            Thanks again for your contribution!
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
-          allow-repeats: false
+      - name: Run pre-commit
+        run: pre-commit run --all-files
 
   nf-core:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Install Nextflow
         uses: nf-core/setup-nextflow@v1
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: "3.11"
           architecture: "x64"
@@ -99,7 +60,7 @@ jobs:
 
       - name: Upload linting log file artifact
         if: ${{ always() }}
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: linting-logs
           path: |

.github/workflows/linting_comment.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download lint results
-        uses: dawidd6/action-download-artifact@v2
+        uses: dawidd6/action-download-artifact@v3
         with:
           workflow: linting.yml
           workflow_conclusion: completed

assets/email_template.html

@@ -12,7 +12,7 @@
 
 <img src="cid:nfcorepipelinelogo">
 
-<h1>ebi-metagenomics/shallowmapping v${version}</h1>
+<h1>ebi-metagenomics/shallowmapping ${version}</h1>
 <h2>Run Name: $runName</h2>
 
 <% if (!success){

conf/codon_dbs.config

@@ -5,13 +5,13 @@
 */
 
 params {
-    sourmash_db    = "/hps/nobackup/rdf/metagenomics/service-team/ref-dbs/shallow-mapping/$params.biome/sourmash_reps_k51.sbt.zip"
+    //sourmash_db    = "/hps/nobackup/rdf/metagenomics/service-team/ref-dbs/shallow-mapping/$params.biome/sourmash_reps_k51.sbt.zip"
 
-    bwa_db         = "/hps/nobackup/rdf/metagenomics/service-team/ref-dbs/shallow-mapping/$params.biome/bwa_reps.fa"
+    //bwa_db         = "/hps/nobackup/rdf/metagenomics/service-team/ref-dbs/shallow-mapping/$params.biome/bwa_reps.fa"
 
-    pangenome_db   = "/hps/nobackup/rdf/metagenomics/service-team/ref-dbs/shallow-mapping/$params.biome/functional_profiles_DB/"
+    //pangenome_db   = "/hps/nobackup/rdf/metagenomics/service-team/ref-dbs/shallow-mapping/$params.biome/functional_profiles_DB/"
 
-    host_ref       = "/hps/nobackup/rdf/metagenomics/service-team/ref-dbs/shallow-mapping/$params.biome/host.fa
+    //host_ref       = "/hps/nobackup/rdf/metagenomics/service-team/ref-dbs/shallow-mapping/$params.biome/host.fa"
 
-    human_ref      = "/hps/nobackup/rdf/metagenomics/service-team/ref-dbs/bwa-mem2/hg38.fa"
+    reference_genomes_folder      = "/hps/nobackup/rdf/metagenomics/service-team/ref-dbs/bwa-mem2/"
 }

conf/test.config

@@ -24,6 +24,4 @@ params {
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
     input  = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'
 
-    // Fasta references
-    fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.fna.gz'
 }

conf/test_full.config

@@ -19,6 +19,4 @@ params {
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_full_illumina_amplicon.csv'
 
-    // Fasta references
-    fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.fna.gz'
 }

lib/NfcoreTemplate.groovy

@@ -4,6 +4,7 @@
 
 import org.yaml.snakeyaml.Yaml
 import groovy.json.JsonOutput
+import nextflow.extension.FilesEx
 
 class NfcoreTemplate {
 
@@ -141,12 +142,14 @@ class NfcoreTemplate {
             try {
                 if (params.plaintext_email) { throw GroovyException('Send plaintext e-mail, not HTML') }
                 // Try to send HTML e-mail using sendmail
+                def sendmail_tf = new File(workflow.launchDir.toString(), ".sendmail_tmp.html")
+                sendmail_tf.withWriter { w -> w << sendmail_html }
                 [ 'sendmail', '-t' ].execute() << sendmail_html
                 log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (sendmail)-"
             } catch (all) {
                 // Catch failures and try with plaintext
                 def mail_cmd = [ 'mail', '-s', subject, '--content-type=text/html', email_address ]
-                if ( mqc_report.size() <= max_multiqc_email_size.toBytes() ) {
+                if ( mqc_report != null && mqc_report.size() <= max_multiqc_email_size.toBytes() ) {
                     mail_cmd += [ '-A', mqc_report ]
                 }
                 mail_cmd.execute() << email_html
@@ -155,14 +158,16 @@ class NfcoreTemplate {
         }
 
         // Write summary e-mail HTML to a file
-        def output_d = new File("${params.outdir}/pipeline_info/")
-        if (!output_d.exists()) {
-            output_d.mkdirs()
-        }
-        def output_hf = new File(output_d, "pipeline_report.html")
+        def output_hf = new File(workflow.launchDir.toString(), ".pipeline_report.html")
         output_hf.withWriter { w -> w << email_html }
-        def output_tf = new File(output_d, "pipeline_report.txt")
+        FilesEx.copyTo(output_hf.toPath(), "${params.outdir}/pipeline_info/pipeline_report.html");
+        output_hf.delete()
+
+        // Write summary e-mail TXT to a file
+        def output_tf = new File(workflow.launchDir.toString(), ".pipeline_report.txt")
         output_tf.withWriter { w -> w << email_txt }
+        FilesEx.copyTo(output_tf.toPath(), "${params.outdir}/pipeline_info/pipeline_report.txt");
+        output_tf.delete()
     }
 
     //
@@ -227,15 +232,14 @@ class NfcoreTemplate {
     // Dump pipeline parameters in a json file
     //
     public static void dump_parameters(workflow, params) {
-        def output_d = new File("${params.outdir}/pipeline_info/")
-        if (!output_d.exists()) {
-            output_d.mkdirs()
-        }
-
         def timestamp  = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss')
-        def output_pf  = new File(output_d, "params_${timestamp}.json")
+        def filename   = "params_${timestamp}.json"
+        def temp_pf    = new File(workflow.launchDir.toString(), ".${filename}")
         def jsonStr    = JsonOutput.toJson(params)
-        output_pf.text = JsonOutput.prettyPrint(jsonStr)
+        temp_pf.text   = JsonOutput.prettyPrint(jsonStr)
+
+        FilesEx.copyTo(temp_pf.toPath(), "${params.outdir}/pipeline_info/params_${timestamp}.json")
+        temp_pf.delete()
     }
 
     //