Important! Template update for nf-core/tools v2.10

.devcontainer/devcontainer.json

@@ -2,6 +2,7 @@
     "name": "nfcore",
     "image": "nfcore/gitpod:latest",
     "remoteUser": "gitpod",
+    "runArgs": ["--privileged"],
 
     // Configure tool-specific properties.
     "customizations": {

.github/CONTRIBUTING.md

@@ -9,7 +9,9 @@ Please use the pre-filled template to save time.
 However, don't be put off by this template - other more general issues and suggestions are welcome!
 Contributions to the code are even more welcome ;)
 
-> If you need help using or modifying nf-core/sarek then the best place to ask is on the nf-core Slack [#sarek](https://nfcore.slack.com/channels/sarek) channel ([join our Slack here](https://nf-co.re/join/slack)).
+:::info
+If you need help using or modifying nf-core/sarek then the best place to ask is on the nf-core Slack [#sarek](https://nfcore.slack.com/channels/sarek) channel ([join our Slack here](https://nf-co.re/join/slack)).
+:::
 
 ## Contribution workflow
 

.github/workflows/linting.yml

@@ -78,7 +78,7 @@ jobs:
 
       - uses: actions/setup-python@v4
         with:
-          python-version: "3.8"
+          python-version: "3.11"
           architecture: "x64"
 
       - name: Install dependencies

.github/workflows/release-announcments.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/[email protected]
+        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 }}
+          #

.nf-core.yml

@@ -11,4 +11,3 @@ lint:
     - lib/NfcoreTemplate.groovy
     - lib/NfcoreSchema.groovy
   template_strings: False
-  multiqc_config: False

CITATIONS.md

@@ -66,7 +66,7 @@
 
 - [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
 
-  > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online]. Available online https://www.bioinformatics.babraham.ac.uk/projects/fastqc/.
+  > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
 
 - [FGBio](https://github.com/fulcrumgenomics/fgbio)
 

README.md

@@ -1,7 +1,5 @@
 # ![nf-core/sarek](docs/images/nf-core-sarek_logo_light.png#gh-light-mode-only) ![nf-core/sarek](docs/images/nf-core-sarek_logo_dark.png#gh-dark-mode-only)
 
-> **An open-source analysis pipeline to detect germline or somatic variants from whole genome or targeted sequencing**
-
 [![GitHub Actions CI Status](https://github.com/nf-core/sarek/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/sarek/actions?query=workflow%3A%22nf-core+CI%22)
 [![GitHub Actions Linting Status](https://github.com/nf-core/sarek/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/sarek/actions?query=workflow%3A%22nf-core+linting%22)
 [![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/sarek/results)
@@ -61,10 +59,11 @@ Depending on the options and samples provided, the pipeline can currently perfor
 
 ## 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:
 
@@ -86,14 +85,11 @@ nextflow run nf-core/sarek \
    --outdir <OUTDIR>
 ```
 
-See [usage docs](https://nf-co.re/sarek/usage) for all of the available options when running the pipeline.
-
-## Documentation
-
-> **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/sarek/usage) and the [parameter documentation](https://nf-co.re/sarek/parameters).
 

assets/multiqc_config.yml

@@ -3,9 +3,9 @@ custom_logo_url: https://github.com/nf-core/sarek/
 custom_logo_title: "nf-core/sarek"
 
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/sarek/releases/tag/3.3.0" target="_blank">nf-core/sarek</a>
+  This report has been generated by the <a href="https://github.com/nf-core/sarek/releases/tag/dev" target="_blank">nf-core/sarek</a>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/sarek/3.3.0/docs/output/" target="_blank">documentation</a>.
+  <a href="https://nf-co.re/sarek/dev/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-sarek-methods-description":
     order: -1000

docs/output.md

@@ -10,30 +10,35 @@ The directories listed below will be created in the results directory after the
 
 The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps:
 
+- [Directory Structure](#directory-structure)
 - [Preprocessing](#preprocessing)
-  - [Prepare input files](#preparation-of-input-files-fastq-or-ubam)
+  - [Preparation of input files (FastQ or (u)BAM)](#preparation-of-input-files-fastq-or-ubam)
     - [Trim adapters](#trim-adapters)
     - [Split FastQ files](#split-fastq-files)
+    - [UMI consensus](#umi-consensus)
   - [Map to Reference](#map-to-reference)
     - [BWA](#bwa)
     - [BWA-mem2](#bwa-mem2)
     - [DragMap](#dragmap)
-    - [Sentieon bwa mem](#sentieon-bwa-mem)
-  - [Duplicate Marking](#mark-duplicates)
+    - [Sentieon BWA mem](#sentieon-bwa-mem)
+  - [Mark Duplicates](#mark-duplicates)
     - [GATK MarkDuplicates (Spark)](#gatk-markduplicates-spark)
-    - [Sentieon LocusCollector and Dedup](#sentieon-locuscollector-dedup)
+  - [Sentieon LocusCollector and Dedup](#sentieon-locuscollector-and-dedup)
   - [Base Quality Score Recalibration](#base-quality-score-recalibration)
     - [GATK BaseRecalibrator (Spark)](#gatk-baserecalibrator-spark)
     - [GATK ApplyBQSR (Spark)](#gatk-applybqsr-spark)
   - [CSV files](#csv-files)
 - [Variant Calling](#variant-calling)
   - [SNVs and small indels](#snvs-and-small-indels)
+    - [bcftools](#bcftools)
     - [DeepVariant](#deepvariant)
     - [FreeBayes](#freebayes)
     - [GATK HaplotypeCaller](#gatk-haplotypecaller)
-    - [Sentieon Haplotyper](#sentieon-haplotyper)
+      - [GATK Germline Single Sample Variant Calling](#gatk-germline-single-sample-variant-calling)
+      - [GATK Joint Germline Variant Calling](#gatk-joint-germline-variant-calling)
     - [GATK Mutect2](#gatk-mutect2)
-    - [bcftools](#bcftools)
+    - [Sentieon Haplotyper](#sentieon-haplotyper)
+      - [Sentieon Joint Germline Variant Calling](#sentieon-joint-germline-variant-calling)
     - [Strelka2](#strelka2)
   - [Structural Variants](#structural-variants)
     - [Manta](#manta)
@@ -42,22 +47,22 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
     - [ASCAT](#ascat)
     - [CNVKit](#cnvkit)
     - [Control-FREEC](#control-freec)
-  - [MSI status](#msi-status)
+  - [Microsatellite instability (MSI)](#microsatellite-instability-msi)
     - [MSIsensorPro](#msisensorpro)
-  - [Concatenation](#concatentation)
+  - [Concatenation](#concatenation)
 - [Variant annotation](#variant-annotation)
   - [snpEff](#snpeff)
   - [VEP](#vep)
-- [Quality control and reporting](#qc-and-reporting)
+- [Quality control and reporting](#quality-control-and-reporting)
   - [Quality control](#quality-control)
     - [FastQC](#fastqc)
     - [FastP](#fastp)
+    - [Mosdepth](#mosdepth)
     - [GATK MarkDuplicates reports](#gatk-markduplicates-reports)
     - [Sentieon Dedup reports](#sentieon-dedup-reports)
-    - [mosdepth](#mosdepth)
     - [samtools stats](#samtools-stats)
     - [bcftools stats](#bcftools-stats)
-    - [vcftools](#vcftools)
+    - [VCFtools](#vcftools)
     - [snpEff reports](#snpeff-reports)
     - [VEP reports](#vep-reports)
   - [Reporting](#reporting)
@@ -762,7 +767,7 @@ It requires a normal sample for each tumour to differentiate the somatic and ger
   - Germline sites detected.
   </details>
 
-### Concatentation
+### Concatenation
 
 Germline VCFs from `DeepVariant`, `FreeBayes`, `HaplotypeCaller`, `Haplotyper`, `Manta`, `bcftools mpileup`, `Strelka2`, or `Tiddit` are concatenated with `bcftools concat`. The field `SOURCE` is added to the VCF header to report the variant caller.
 
@@ -853,6 +858,9 @@ The plots display:
 <details markdown="1">
 <summary>Output files for all samples</summary>
 
+:::note
+The FastQC plots displayed in the MultiQC report shows _untrimmed_ reads. They may contain adapter sequence and potentially regions with low quality.
+:::
 **Output directory: `{outdir}/reports/fastqc/<sample-lane>`**
 
 - `<sample-lane_1>_fastqc.html` and `<sample-lane_2>_fastqc.html`
@@ -1072,6 +1080,7 @@ Results generated by MultiQC collect pipeline QC from supported tools e.g. FastQ
   - Reports generated by Nextflow: `execution_report.html`, `execution_timeline.html`, `execution_trace.txt` and `pipeline_dag.dot`/`pipeline_dag.svg`.
   - Reports generated by the pipeline: `pipeline_report.html`, `pipeline_report.txt` and `software_versions.yml`. The `pipeline_report*` files will only be present if the `--email` / `--email_on_fail` parameter's are used when running the pipeline.
   - Reformatted samplesheet files used as input to the pipeline: `samplesheet.valid.csv`.
+  - Parameters used by the pipeline run: `params.json`.
 
 </details>
 

docs/usage.md

@@ -37,7 +37,9 @@ If you wish to repeatedly use the same parameters for multiple runs, rather than
 
 Pipeline settings can be provided in a `yaml` or `json` file via `-params-file <file>`.
 
-> ⚠️ Do not use `-c <file>` to specify parameters as this will result in errors. Custom config files specified with `-c` must only be used for [tuning process resource specifications](https://nf-co.re/docs/usage/configuration#tuning-workflow-resources), other infrastructural tweaks (such as output directories), or module arguments (args).
+:::warning
+Do not use `-c <file>` to specify parameters as this will result in errors. Custom config files specified with `-c` must only be used for [tuning process resource specifications](https://nf-co.re/docs/usage/configuration#tuning-workflow-resources), other infrastructural tweaks (such as output directories), or module arguments (args).
+:::
 
 The above pipeline run specified with a params file in yaml format:
 
@@ -327,11 +329,15 @@ This version number will be logged in reports when you run the pipeline, so that
 
 To further assist in reproducbility, you can use share and re-use [parameter files](#running-the-pipeline) to repeat pipeline runs with the same settings without having to write out a command with every single parameter.
 
-> 💡 If you wish to share such profile (such as upload as supplementary material for academic publications), make sure to NOT include cluster specific paths to files, nor institutional specific profiles.
+:::tip
+If you wish to share such profile (such as upload as supplementary material for academic publications), make sure to NOT include cluster specific paths to files, nor institutional specific profiles.
+:::
 
 # Core Nextflow arguments
 
-> **NB:** These options are part of Nextflow and use a _single_ hyphen (pipeline parameters use a double-hyphen).
+:::note
+These options are part of Nextflow and use a _single_ hyphen (pipeline parameters use a double-hyphen).
+:::
 
 ## `-profile`
 
@@ -340,7 +346,9 @@ Profiles can give configuration presets for different compute environments.
 
 Several generic profiles are bundled with the pipeline which instruct the pipeline to use software packaged using different methods (Docker, Singularity, Podman, Shifter, Charliecloud, Apptainer, Conda) - see below.
 
-> We highly recommend the use of `Docker` or `Singularity` containers for full pipeline reproducibility, however when this is not possible, `Conda` is also supported.
+:::info
+We highly recommend the use of Docker or Singularity containers for full pipeline reproducibility, however when this is not possible, Conda is also supported.
+:::
 
 The pipeline also dynamically loads configurations from [github.com/nf-core/configs](https://github.com/nf-core/configs) when it runs, making multiple config profiles for various institutional clusters available at run time.
 For more information and to see if your system is available in these configs please see the [nf-core/configs documentation](https://github.com/nf-core/configs#documentation).

lib/NfcoreTemplate.groovy

@@ -3,6 +3,7 @@
 //
 
 import org.yaml.snakeyaml.Yaml
+import groovy.json.JsonOutput
 
 class NfcoreTemplate {
 
@@ -222,6 +223,21 @@ 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 jsonStr    = JsonOutput.toJson(params)
+        output_pf.text = JsonOutput.prettyPrint(jsonStr)
+    }
+
     //
     // Print pipeline summary on completion
     //

lib/WorkflowSarek.groovy

@@ -52,7 +52,7 @@ class WorkflowSarek {
 
     public static String toolCitationText(params) {
 
-        // TODO Optionally add in-text citation tools to this list.
+        // TODO nf-core: Optionally add in-text citation tools to this list.
         // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "Tool (Foo et al. 2023)" : "",
         // Uncomment function in methodsDescriptionText to render in MultiQC report
         def citation_text = [

nextflow.config

@@ -129,7 +129,7 @@ params {
     // Schema validation default options
     validationFailUnrecognisedParams = false
     validationLenientMode            = true
-    validationSchemaIgnoreParams     = 'genomes,cf_ploidy'
+    validationSchemaIgnoreParams     = 'cf_ploidy,genomes,igenomes_base'
     validationShowHiddenParams       = false
     validate_params                  = true
 }
@@ -229,6 +229,7 @@ profiles {
     }
     apptainer {
         apptainer.enabled      = true
+        apptainer.autoMounts   = true
         charliecloud.enabled   = false
         conda.enabled          = false
         docker.enabled         = false
@@ -237,8 +238,8 @@ profiles {
         singularity.enabled    = false
     }
     gitpod {
-        executor.cpus          = 16
-        executor.memory        = 60.GB
+        executor.cpus          = 4
+        executor.memory        = 8.GB
         executor.name          = 'local'
     }
     // Basic test profile for CI

workflows/sarek.nf

@@ -1292,7 +1292,10 @@ workflow SAREK {
 */
 
 workflow.onComplete {
-    if (params.email || params.email_on_fail) NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report)
+    if (params.email || params.email_on_fail) {
+        NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report)
+    }
+    NfcoreTemplate.dump_parameters(workflow, params)
     NfcoreTemplate.summary(workflow, params, log)
     if (params.hook_url) NfcoreTemplate.IM_notification(workflow, params, summary_params, projectDir, log)
 }