1.1.3 Patch release

.github/CONTRIBUTING.md

@@ -27,6 +27,9 @@ 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/PULL_REQUEST_TEMPLATE.md

@@ -19,6 +19,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/taxp
 - [ ] If necessary, also make a PR on the nf-core/taxprofiler _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
 - [ ] 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/ci.yml

@@ -42,7 +42,7 @@ jobs:
 
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Install Nextflow
         uses: nf-core/setup-nextflow@v1

.github/workflows/fix-linting.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       # Use the @nf-core-bot token to check out so we can push later
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           token: ${{ secrets.nf_core_bot_auth_token }}
 
@@ -24,7 +24,7 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.nf_core_bot_auth_token }}
 
-      - uses: actions/setup-node@v3
+      - uses: actions/setup-node@v4
 
       - name: Install Prettier
         run: npm install -g prettier @prettier/plugin-php

.github/workflows/linting.yml

@@ -14,9 +14,9 @@ jobs:
   EditorConfig:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
-      - uses: actions/setup-node@v3
+      - uses: actions/setup-node@v4
 
       - name: Install editorconfig-checker
         run: npm install -g editorconfig-checker
@@ -27,9 +27,9 @@ jobs:
   Prettier:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
-      - uses: actions/setup-node@v3
+      - uses: actions/setup-node@v4
 
       - name: Install Prettier
         run: npm install -g prettier
@@ -40,7 +40,7 @@ jobs:
   PythonBlack:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Check code lints with Black
         uses: psf/black@stable
@@ -71,7 +71,7 @@ jobs:
     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

.gitpod.yml

@@ -4,7 +4,9 @@ tasks:
     command: |
       pre-commit install --install-hooks
       nextflow self-update
-
+  - name: unset JAVA_TOOL_OPTIONS
+    command: |
+      unset JAVA_TOOL_OPTIONS
 vscode:
   extensions: # based on nf-core.nf-core-extensionpack
     - codezombiech.gitignore # Language support for .gitignore files

CHANGELOG.md

@@ -3,6 +3,26 @@
 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).
 
+## v1.1.3 - Augmented Akita Patch [2024-01-12]
+
+### `Added`
+
+- [#424](https://github.com/nf-core/taxprofiler/pull/424) Updated to nf-core pipeline template v2.11.1 (added by @LilyAnderssonLee & @sofstam)
+
+### `Fixed`
+
+- [#419](https://github.com/nf-core/taxprofiler/pull/419) Added improved syntax highlighting for tables in documentation (fix by @mashehu)
+- [#421](https://github.com/nf-core/taxprofiler/pull/421) Updated the krakenuniq/preloadedkrakenuniq module that contained a fix for saving the output reads (❤️ to @SannaAb for reporting, fix by @Midnighter)
+- [#427](https://github.com/nf-core/taxprofiler/pull/427) Fixed preprint information in the recommended methods text (fix by @jfy133)
+
+### `Dependencies`
+
+| Tool          | Previous version | New version |
+| ------------- | ---------------- | ----------- |
+| multiqc       | 1.15             | 1.19        |
+| fastqc        | 11.9             | 12.1        |
+| nf-validation | unpinned         | 1.1.3       |
+
 ## v1.1.2 - Augmented Akita Patch [2023-10-27]
 
 ### `Added`

README.md

@@ -47,11 +47,8 @@
 
 ## Usage
 
-:::note
-If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how
-to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline)
-with `-profile test` before running the workflow on actual data.
-:::
+> [!NOTE]
+> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.
 
 First, prepare a samplesheet with your input data that looks as follows:
 
@@ -89,11 +86,9 @@ nextflow run nf-core/taxprofiler \
    --run_kraken2 --run_metaphlan
 ```
 
-:::warning
-Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those
-provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_;
-see [docs](https://nf-co.re/usage/configuration#custom-configuration-files).
-:::
+> [!WARNING]
+> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_;
+> see [docs](https://nf-co.re/usage/configuration#custom-configuration-files).
 
 For more details and further functionality, please refer to the [usage documentation](https://nf-co.re/taxprofiler/usage) and the [parameter documentation](https://nf-co.re/taxprofiler/parameters).
 

assets/methods_description_template.yml

@@ -3,8 +3,6 @@ description: "Suggested text and references to use when describing pipeline usag
 section_name: "nf-core/taxprofiler Methods Description"
 section_href: "https://github.com/nf-core/taxprofiler"
 plot_type: "html"
-## TODO nf-core: Update the HTML below to your preferred methods description, e.g. add publication citation for this pipeline
-## You inject any metadata in the Nextflow '${workflow}' object
 data: |
   <h4>Methods</h4>
   <p>Data was processed using nf-core/taxprofiler v${workflow.manifest.version} ${doi_text} of the nf-core collection of workflows (<a href="https://doi.org/10.1038/s41587-020-0439-x">Ewels <em>et al.</em>, 2020</a>), utilising reproducible software environments from the Bioconda (<a href="https://doi.org/10.1038/s41592-018-0046-7">Grüning <em>et al.</em>, 2018</a>) and Biocontainers (<a href="https://doi.org/10.1093/bioinformatics/btx192">da Veiga Leprevost <em>et al.</em>, 2017</a>) projects.</p>
@@ -17,12 +15,13 @@ data: |
     <li>Ewels, P. A., Peltzer, A., Fillinger, S., Patel, H., Alneberg, J., Wilm, A., Garcia, M. U., Di Tommaso, P., & Nahnsen, S. (2020). The nf-core framework for community-curated bioinformatics pipelines. Nature Biotechnology, 38(3), 276-278. doi: <a href="https://doi.org/10.1038/s41587-020-0439-x">10.1038/s41587-020-0439-x</a></li>
     <li>Grüning, B., Dale, R., Sjödin, A., Chapman, B. A., Rowe, J., Tomkins-Tinch, C. H., Valieris, R., Köster, J., & Bioconda Team. (2018). Bioconda: sustainable and comprehensive software distribution for the life sciences. Nature Methods, 15(7), 475–476. doi: <a href="https://doi.org/10.1038/s41592-018-0046-7">10.1038/s41592-018-0046-7</a></li>
     <li>da Veiga Leprevost, F., Grüning, B. A., Alves Aflitos, S., Röst, H. L., Uszkoreit, J., Barsnes, H., Vaudel, M., Moreno, P., Gatto, L., Weber, J., Bai, M., Jimenez, R. C., Sachsenberg, T., Pfeuffer, J., Vera Alvarez, R., Griss, J., Nesvizhskii, A. I., & Perez-Riverol, Y. (2017). BioContainers: an open-source and community-driven framework for software standardization. Bioinformatics (Oxford, England), 33(16), 2580–2582. doi: <a href="https://doi.org/10.1093/bioinformatics/btx192">10.1093/bioinformatics/btx192</a></li>
+    <li>Stamouli, S., Beber, M. E., Normark, T., Christensen, T. A., Andersson-Li, L., Borry, M., Jamy, M., nf-core community, & Fellows Yates, J. A. (2023). nf-core/taxprofiler: Highly parallelised and flexible pipeline for metagenomic taxonomic classification and profiling. (Preprint). bioRxiv 2023.10.20.563221. doi: <a href="https://doi.org/10.1101/2023.10.20.563221">10.1101/2023.10.20.563221</a></li>
     ${tool_bibliography}
   </ul>
   <div class="alert alert-info">
     <h5>Notes:</h5>
     <ul>
-      ${nodoi_text}
+      ${doi_text}
       <li>The command above does not include parameters contained in any configs or profiles that may have been used. Ensure the config file is also uploaded with your publication!</li>
       <li>You should also cite all software used within this run. Check the "Software Versions" of this report to get version information.</li>
     </ul>

assets/multiqc_config.yml

@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/taxprofiler/releases/tag/1.1.2" target="_blank">nf-core/taxprofiler</a>
+  This report has been generated by the <a href="https://github.com/nf-core/taxprofiler/releases/tag/1.1.3" target="_blank">nf-core/taxprofiler</a>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/taxprofiler/1.1.2/docs/output" target="_blank">documentation</a>.
+  <a href="https://nf-co.re/taxprofiler/1.1.3/docs/output" target="_blank">documentation</a>.
 
 report_section_order:
   "nf-core-taxprofiler-methods-description":

assets/slackreport.json

@@ -3,7 +3,7 @@
         {
             "fallback": "Plain-text summary of the attachment.",
             "color": "<% if (success) { %>good<% } else { %>danger<%} %>",
-            "author_name": "nf-core/taxprofiler v${version} - ${runName}",
+            "author_name": "nf-core/taxprofiler ${version} - ${runName}",
             "author_icon": "https://www.nextflow.io/docs/latest/_static/favicon.ico",
             "text": "<% if (success) { %>Pipeline completed successfully!<% } else { %>Pipeline completed with errors<% } %>",
             "fields": [

conf/modules.config

@@ -500,7 +500,7 @@ process {
         publishDir = [
             path: { "${params.outdir}/krakenuniq/${meta.db_name}/" },
             mode: params.publish_dir_mode,
-            pattern: '*.{txt,fastq.gz}'
+            pattern: '*.{txt,fasta.gz}'
         ]
     }
 
@@ -769,7 +769,7 @@ process {
     }
 
     withName: 'MULTIQC' {
-        ext.args   = params.multiqc_title ? "--title \"$params.multiqc_title\"" : ''
+        ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [
             path: { "${params.outdir}/multiqc" },
             mode: params.publish_dir_mode,

docs/output.md

@@ -375,23 +375,23 @@ You will only receive the `.fastq` and `*classifiedreads.txt` file if you supply
 
 ### KrakenUniq
 
-[KrakenUniq](https://github.com/fbreitwieser/krakenuniq) (formerly KrakenHLL) is an extenson to the fast k-mer-based classification [Kraken](https://github.com/DerrickWood/kraken) with an efficient algorithm for additionally assessing the coverage of unique k-mers found in each species in a dataset.
+[KrakenUniq](https://github.com/fbreitwieser/krakenuniq) (formerly KrakenHLL) is an extension to the fast k-mer-based classification performed by [Kraken](https://github.com/DerrickWood/kraken) with an efficient algorithm for additionally assessing the coverage of unique k-mers found in each species in a dataset.
 
 <details markdown="1">
 <summary>Output files</summary>
 
 - `krakenuniq/`
   - `<db_name>/`
-    - `<sample_id>_<db_name>.classified.fastq.gz`: FASTQ file containing all reads that had a hit against a reference in the database for a given sample
-    - `<sample_id>_<db_name>.unclassified.fastq.gz`: FASTQ file containing all reads that did not have a hit in the database for a given sample
-    - `<sample_id>_<db_name>.report.txt`: A Kraken2-style report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits, with an additional column for k-mer coverage, that allows for more accurate distinguishing between false-positive/true-postitive hits
-    - `<sample_id>_<db_name>.classifiedreads.txt`: A list of read IDs and the hits each read had against each database for a given sample
+    - `<sample_id>_<db_name>[.merged].classified.fasta.gz`: Optional FASTA file containing all reads that had a hit against a reference in the database for a given sample. Paired-end input reads are merged in this output.
+    - `<sample_id>_<db_name>[.merged].unclassified.fasta.gz`: Optional FASTA file containing all reads that did not have a hit in the database for a given sample. Paired-end input reads are merged in this output.
+    - `<sample_id>_<db_name>.krakenuniq.report.txt`: A Kraken2-style report that summarises the fraction abundance, taxonomic ID, number of Kmers, taxonomic path of all the hits, with an additional column for k-mer coverage, that allows for more accurate distinguishing between false-positive/true-postitive hits.
+    - `<sample_id>_<db_name>.krakenuniq.classified.txt`: An optional list of read IDs and the hits each read had against each database for a given sample.
 
 </details>
 
-The main taxonomic classification file from KrakenUniq is the `*report.txt` file. This is an extension of the Kraken2 report with the additional k-mer coverage information that provides more information about the accuracy of hits.
+The main taxonomic classification file from KrakenUniq is the `*.krakenuniq.report.txt` file. This is an extension of the Kraken2 report with the additional k-mer coverage information that provides more information about the accuracy of hits.
 
-You will only receive the `.fastq` and `*classifiedreads.txt` file if you supply `--krakenuniq_save_reads` and/or `--krakenuniq_save_readclassification` parameters to the pipeline.
+You will only receive the `.fasta.gz` and `*.krakenuniq.classified.txt` file if you supply `--krakenuniq_save_reads` and/or `--krakenuniq_save_readclassification` parameters to the pipeline.
 
 :::info
 The output system of KrakenUniq can result in other `stdout` or `stderr` logging information being saved in the report file, therefore you must check your report files before downstream use!

docs/usage.md

@@ -44,12 +44,11 @@ This samplesheet is then specified on the command line as follows:
 
 The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate different runs FASTQ files of the same sample before performing profiling, when `--perform_runmerging` is supplied. Below is an example for the same sample sequenced across 3 lanes:
 
-```console
+```csv title="samplesheet.csv"
 sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta
 2612,run1,ILLUMINA,2612_run1_R1.fq.gz,,
 2612,run2,ILLUMINA,2612_run2_R1.fq.gz,,
 2612,run3,ILLUMINA,2612_run3_R1.fq.gz,2612_run3_R2.fq.gz,
-
 ```
 
 :::warning
@@ -62,7 +61,7 @@ The pipeline will auto-detect whether a sample is single- or paired-end using th
 
 A final samplesheet file consisting of both single- and paired-end data, as well as long-read FASTA files may look something like the one below. This is for 6 samples, where `2612` has been sequenced twice.
 
-```console
+```csv title="samplesheet.csv"
 sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta
 2611,ERR5766174,ILLUMINA,,,/<path>/<to>/fasta/ERX5474930_ERR5766174_1.fa.gz
 2612,ERR5766176,ILLUMINA,/<path>/<to>/fastq/ERX5474932_ERR5766176_1.fastq.gz,/<path>/<to>/fastq/ERX5474932_ERR5766176_2.fastq.gz,
@@ -110,7 +109,7 @@ An example database sheet can look as follows, where 7 tools are being used, and
 
 `kraken2` will be run twice even though only having a single 'dedicated' database because specifying `bracken` implies first running `kraken2` on the `bracken` database, as required by `bracken`.
 
-```console
+```csv
 tool,db_name,db_params,db_path
 malt,malt85,-id 85,/<path>/<to>/malt/testdb-malt/
 malt,malt95,-id 90,/<path>/<to>/malt/testdb-malt.tar.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()
     }
 
     //