Merge pull request #4 from jannikseidelQBiC/merging-template-updates

Merging template updates

.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/deta
 - [ ] If necessary, also make a PR on the nf-core/detaxizer _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

@@ -28,7 +28,7 @@ jobs:
           - "latest-everything"
     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

.github/workflows/release-announcements.yml

@@ -0,0 +1,68 @@
+name: release-announcements
+# Automatic release toot and tweet anouncements
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+jobs:
+  toot:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: rzr/fediverse-action@master
+        with:
+          access-token: ${{ secrets.MASTODON_ACCESS_TOKEN }}
+          host: "mstdn.science" # custom host if not "mastodon.social" (default)
+          # GitHub event payload
+          # https://docs.github.com/en/developers/webhooks-and-events/webhooks/webhook-events-and-payloads#release
+          message: |
+            Pipeline release! ${{ github.repository }} v${{ github.event.release.tag_name }} - ${{ github.event.release.name }}!
+
+            Please see the changelog: ${{ github.event.release.html_url }}
+
+  send-tweet:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install dependencies
+        run: pip install tweepy==4.14.0
+      - name: Send tweet
+        shell: python
+        run: |
+          import os
+          import tweepy
+
+          client = tweepy.Client(
+              access_token=os.getenv("TWITTER_ACCESS_TOKEN"),
+              access_token_secret=os.getenv("TWITTER_ACCESS_TOKEN_SECRET"),
+              consumer_key=os.getenv("TWITTER_CONSUMER_KEY"),
+              consumer_secret=os.getenv("TWITTER_CONSUMER_SECRET"),
+          )
+          tweet = os.getenv("TWEET")
+          client.create_tweet(text=tweet)
+        env:
+          TWEET: |
+            Pipeline release! ${{ github.repository }} v${{ github.event.release.tag_name }} - ${{ github.event.release.name }}!
+
+            Please see the changelog: ${{ github.event.release.html_url }}
+          TWITTER_CONSUMER_KEY: ${{ secrets.TWITTER_CONSUMER_KEY }}
+          TWITTER_CONSUMER_SECRET: ${{ secrets.TWITTER_CONSUMER_SECRET }}
+          TWITTER_ACCESS_TOKEN: ${{ secrets.TWITTER_ACCESS_TOKEN }}
+          TWITTER_ACCESS_TOKEN_SECRET: ${{ secrets.TWITTER_ACCESS_TOKEN_SECRET }}
+
+  bsky-post:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: zentered/bluesky-post-action@v0.0.2
+        with:
+          post: |
+            Pipeline release! ${{ github.repository }} v${{ github.event.release.tag_name }} - ${{ github.event.release.name }}!
+
+            Please see the changelog: ${{ github.event.release.html_url }}
+        env:
+          BSKY_IDENTIFIER: ${{ secrets.BSKY_IDENTIFIER }}
+          BSKY_PASSWORD: ${{ secrets.BSKY_PASSWORD }}
+          #

.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

CITATIONS.md

@@ -10,10 +10,22 @@
 
 ## Pipeline tools
 
+- [blastn](https://blast.ncbi.nlm.nih.gov/Blast.cgi)
+
+  > Altschul, S. F., Gish, W., Miller, W., Myers, E. W. & Lipman, D. J. Basic local alignment search tool. Journal of Molecular Biology 215, 403–410 (1990). doi:10.1016/s0022-2836(05)80360-2.
+
+- [fastp](https://github.com/OpenGene/fastp)
+
+  > Chen, S., Zhou, Y., Chen, Y. & Gu, J. fastp: an ultra-fast all-in-one FASTQ preprocessor. Bioinformatics 34, i884–i890 (2018). doi:10.1093/bioinformatics/bty560
+
 - [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
 
   > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
 
+- [Kraken2](https://ccb.jhu.edu/software/kraken2/)
+
+  > Wood, D. E., Lu, J. & Langmead, B. Improved metagenomic analysis with Kraken 2. Genome Biol 20, 257 (2019). doi:10.1186/s13059-019-1891-0
+
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
   > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.

README.md

@@ -13,7 +13,7 @@
 
 ## Introduction
 
-**nf-core/detaxizer** is a bioinformatics pipeline that ...
+**nf-core/detaxizer** is a bioinformatics pipeline that initially checks for the presence of a specific taxon in fastq files and offers the option to filter out this taxon or taxonomic subtree. The process begins with preprocessing using fastp and quality assessment via FastQC, followed by taxon classification with kraken2, and employs blastn for validation of the reads associated with the identified taxa. Users must provide a samplesheet to indicate the fastq files and, if utilizing the validation step, a fasta file for creating the blastn database to verify the targeted taxon.
 
 <!-- TODO nf-core:
    Complete this sentence with a 2-3 sentence summary of what types of data the pipeline ingests, a brief overview of the
@@ -26,15 +26,17 @@
 <!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
 
 1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+2. Pre-processing ([`fastp`](https://github.com/OpenGene/fastp))
+3. Classification of reads ([`Kraken2`](https://ccb.jhu.edu/software/kraken2/))
+4. Optional validation of searched taxon/taxa ([`blastn`](https://blast.ncbi.nlm.nih.gov/Blast.cgi))
+5. Optional filtering of the searched taxon/taxa from the reads (either from the raw files or the processed reads)
+6. Summary of the processes
+7. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
 
 ## 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.
 
 <!-- TODO nf-core: Describe the minimum required steps to execute the pipeline, e.g. how to prepare samplesheets.
      Explain what rows and columns represent. For instance (please edit as appropriate):
@@ -44,11 +46,11 @@ First, prepare a samplesheet with your input data that looks as follows:
 `samplesheet.csv`:
 
 ```csv
-sample,fastq_1,fastq_2
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+sample,fastq_1,fastq_2,fastq_3
+CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,AEG588A1_S1_L002_R3_001.fastq.gz
 ```
 
-Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
+Each row represents a fastq file (single-end) or a pair of fastq files (paired end). A third fastq file can be provided if long reads are present in your project.
 
 -->
 
@@ -63,11 +65,9 @@ nextflow run nf-core/detaxizer \
    --outdir <OUTDIR>
 ```
 
-:::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/detaxizer/usage) and the [parameter documentation](https://nf-co.re/detaxizer/parameters).
 
@@ -83,6 +83,8 @@ nf-core/detaxizer was originally written by Jannik Seidel.
 
 We thank the following people for their extensive assistance in the development of this pipeline:
 
+Daniel Straub
+
 <!-- TODO nf-core: If applicable, make list of people who have also contributed -->
 
 ## Contributions and Support
@@ -94,7 +96,7 @@ For further information or help, don't hesitate to get in touch on the [Slack `#
 ## Citations
 
 <!-- TODO nf-core: Add citation for pipeline after first release. Uncomment lines below and update Zenodo doi and badge at the top of this file. -->
-<!-- If you use  nf-core/detaxizer for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->
+<!-- If you use nf-core/detaxizer for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->
 
 <!-- TODO nf-core: Add bibliography of tools and data used in your pipeline -->
 

assets/multiqc_config.yml

@@ -1,5 +1,5 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/detaxizer/releases/tag/dev" target="_blank">nf-core/detaxizer</a>
+  This report has been generated by the <a href="https://github.com/nf-core/detaxizer/tree/dev" target="_blank">nf-core/detaxizer</a>
   analysis pipeline. For information about how to interpret these results, please see the
   <a href="https://nf-co.re/detaxizer/dev/docs/output" target="_blank">documentation</a>.
 report_section_order:

assets/slackreport.json

@@ -3,7 +3,7 @@
         {
             "fallback": "Plain-text summary of the attachment.",
             "color": "<% if (success) { %>good<% } else { %>danger<%} %>",
-            "author_name": "nf-core/detaxizer v${version} - ${runName}",
+            "author_name": "nf-core/detaxizer ${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

@@ -139,12 +139,13 @@ process {
         ]
     }
 
-    withName: MULTIQC {
+    withName: 'MULTIQC' {
+        ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [
-            path: { "${params.outdir}/MultiQC" },
+            path: { "${params.outdir}/multiqc" },
             mode: params.publish_dir_mode,
-            pattern: "multiqc*",
-            enabled: true
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
+
 }

conf/test.config

@@ -25,10 +25,10 @@ params {
     input  = "${projectDir}/assets/samplesheet.csv"
 
     // Genome references
-    fasta       = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta"
+    fasta               = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta"
 
     // Kraken2 test db
-    kraken2db        = "https://github.com/jannikseidelQBiC/detaxizer/raw/dev/testdata/minigut_kraken.tar.gz"
+    kraken2db           = "https://github.com/jannikseidelQBiC/detaxizer/raw/dev/testdata/minigut_kraken.tar.gz"
     kraken2confidence   = 0.00
     tax2filter          = 'unclassified'
 

conf/test_full.config

@@ -16,10 +16,10 @@ params {
     // Input data for full size test
     // TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA)
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = "${projectDir}/assets/samplesheet.csv"
+    input               = "${projectDir}/assets/samplesheet.csv"
 
     // Genome references
-    fasta         = "s3://ngi-igenomes/igenomes/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa"
+    fasta               = "s3://ngi-igenomes/igenomes/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa"
     // Kraken2 test db
     kraken2db           = "https://genome-idx.s3.amazonaws.com/kraken/k2_standard_08gb_20231009.tar.gz"
     kraken2confidence   = 0.00

docs/usage.md

@@ -20,7 +20,7 @@ You will need to create a samplesheet with information about the samples you wou
 
 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 the raw reads before performing any downstream analysis. Below is an example for the same sample sequenced across 3 lanes:
 
-```console
+```csv title="samplesheet.csv"
 sample,fastq_1,fastq_2
 CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
 CONTROL_REP1,AEG588A1_S1_L003_R1_001.fastq.gz,AEG588A1_S1_L003_R2_001.fastq.gz
@@ -33,7 +33,7 @@ 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 may look something like the one below. This is for 6 samples, where `TREATMENT_REP3` has been sequenced twice.
 
-```console
+```csv title="samplesheet.csv"
 sample,fastq_1,fastq_2
 CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
 CONTROL_REP2,AEG588A2_S2_L002_R1_001.fastq.gz,AEG588A2_S2_L002_R2_001.fastq.gz