nf-core · pontushojer · Jul 9, 2025 · Oct 7, 2025 · Oct 7, 2025 · Oct 7, 2025
diff --git a/.nf-core.yml b/.nf-core.yml
@@ -3,6 +3,9 @@ lint:
     - tests/default.nf.test
   files_unchanged:
     - .github/CONTRIBUTING.md
+    - docs/images/nf-core-seqinspector_logo_dark.png
+    - docs/images/nf-core-seqinspector_logo_light.png
+    - assets/nf-core-seqinspector_logo_light.png
   nextflow_config:
     - config_defaults:
         - params.fastq_screen_references

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -29,13 +29,16 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#127](https://github.com/nf-core/seqinspector/pull/127) Added alignment tools - bwamem2 - index and mem
 - [#128](https://github.com/nf-core/seqinspector/pull/128) Added Picard tools - Collect Multiple Mterics to collect QC metrics
 - [#132](https://github.com/nf-core/seqinspector/pull/132) Added a bwamem2 index params for faster output
+- [#151](https://github.com/nf-core/seqinspector/pull/151) Added a prepare_genome subworkflow to handle bwamem2 indexing
+- [#159](https://github.com/nf-core/seqinspector/pull/159) Added a subworkflow QC_BAM including picard_collecthsmetrics for alignment QC of hybrid-selection data
 
 ### `Fixed`
 
 - [#71](https://github.com/nf-core/seqinspector/pull/71) FASTQSCREEN does not fail when multiple reads are provided.
 - [#99](https://github.com/nf-core/seqinspector/pull/99) Fix group reports for paired reads
 - [#107](https://github.com/nf-core/seqinspector/pull/107) Put SeqFU-stats section reports together
 - [#112](https://github.com/nf-core/seqinspector/pull/112) Making fastq_screen_references value to use parentDir
+- [#120](https://github.com/nf-core/seqinspector/pull/120) Run FastqScreen with subsampled data if available 
 - [#94] (https://github.com/nf-core/seqinspector/issues/94) Go through and validate test data
 
 ### `Dependencies`

diff --git a/CITATIONS.md b/CITATIONS.md
@@ -38,6 +38,8 @@
 
 - [Picard Tools](https://broadinstitute.github.io/picard/)
 
+> Broad Institute, “Picard Toolkit.” 2019. GitHub Repository. https://broadinstitute.github.io/picard/
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

diff --git a/README.md b/README.md
@@ -37,16 +37,17 @@
 
 <!-- TODO: add a search tool that accepts a tree for `Compatibility with Data`. -->
 
-| Tool Type           | Tool Name                                                                          | Tool Description                            | Compatibility with Data | Dependencies        |
-| ------------------- | ---------------------------------------------------------------------------------- | ------------------------------------------- | ----------------------- | ------------------- |
-| `Subsampling`       | [`Seqtk`](https://github.com/lh3/seqtk)                                            | Global subsampling of reads                 | [RNA, DNA, synthetic]   | [N/A]               |
-| `QC`                | [`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)             | Read QC                                     | [RNA, DNA]              | [N/A]               |
-| `QC`                | [`FastqScreen`](https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/)  | Basic contamination detection               | [RNA, DNA]              | [N/A]               |
-| `QC`                | [`SeqFu Stats`](https://github.com/telatin/seqfu2)                                 | Sequence statistics                         | [RNA, DNA]              | [N/A]               |
-| `Indexing, Mapping` | [`Bwamem2`](https://github.com/bwa-mem2/bwa-mem2)                                  | Align reads to reference                    | [RNA, DNA]              | [N/A]               |
-| `Indexing`          | [`SAMtools`](http://github.com/samtools)                                           | Index aligned BAM files, create FASTA index | [DNA]                   | [N/A]               |
-| `QC`                | [`Picard`](https://broadinstitute.github.io/picard/picard-metric-definitions.html) | Collect multiple QC metrics                 | [RNA, DNA]              | [Bwamem2, SAMtools] |
-| `Reporting`         | [`MultiQC`](http://multiqc.info/)                                                  | Aggregate and visualise results             | [RNA, DNA, synthetic]   | [N/A]               |
+| Tool Type           | Tool Name                                                                                                           | Tool Description                                                                              | Compatibility with Data | Dependencies                                                                                                              | Default tool |
+| ------------------- | ------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------- | ------------ |
+| `Subsampling`       | [`Seqtk`](https://github.com/lh3/seqtk)                                                                             | Global subsampling of reads. Only performs subsampling if `--sample_size` parameter is given. | [RNA, DNA, synthetic]   | [N/A]                                                                                                                     | no           |
+| `Indexing, Mapping` | [`Bwamem2`](https://github.com/bwa-mem2/bwa-mem2)                                                                   | Align reads to reference                                                                      | [RNA, DNA]              | [N/A]                                                                                                                     | yes          |
+| `Indexing`          | [`SAMtools`](http://github.com/samtools)                                                                            | Index aligned BAM files, create FASTA index                                                   | [DNA]                   | [N/A]                                                                                                                     | yes          |
+| `QC`                | [`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)                                              | Read QC                                                                                       | [RNA, DNA]              | [N/A]                                                                                                                     | yes          |
+| `QC`                | [`FastqScreen`](https://www.bioinformatics.babraham.ac.uk/projects/fastq_screen/)                                   | Basic contamination detection                                                                 | [RNA, DNA]              | [N/A]                                                                                                                     | yes          |
+| `QC`                | [`SeqFu Stats`](https://github.com/telatin/seqfu2)                                                                  | Sequence statistics                                                                           | [RNA, DNA]              | [N/A]                                                                                                                     | yes          |
+| `QC`                | [`Picard collect multiple metrics`](https://broadinstitute.github.io/picard/picard-metric-definitions.html)         | Collect multiple QC metrics                                                                   | [RNA, DNA]              | [Bwamem2, SAMtools, `--genome`]                                                                                           | yes          |
+| `QC`                | [`Picard_collecthsmetrics`](https://gatk.broadinstitute.org/hc/en-us/articles/360036856051-CollectHsMetrics-Picard) | Collect alignment QC metrics of hybrid-selection data.                                        | [RNA, DNA]              | [Bwamem2, SAMtools, `--fasta`, `--run_picard_collecths_metrics`, `--bait_intervals`, `--target_intervals` (`--ref_dict`)] | no           |
+| `Reporting`         | [`MultiQC`](http://multiqc.info/)                                                                                   | Present QC for raw reads                                                                      | [RNA, DNA, synthetic]   | [N/A]                                                                                                                     | yes          |
 
 <picture>
   <source media="(prefers-color-scheme: dark)" srcset="docs/images/seqinspector_tubemap_V1.0_dark.png">
@@ -92,7 +93,7 @@ For more details about the output files and reports, please refer to the
 
 ## Credits
 
-nf-core/seqinspector was originally written by the Swedish [@NationalGenomicsInfrastructure](https://github.com/NationalGenomicsInfrastructure/).
+nf-core/seqinspector was originally written by the Swedish [@NationalGenomicsInfrastructure](https://github.com/NationalGenomicsInfrastructure/) and [Clinical Genomics Stockholm](https://clinical.scilifelab.se/).
 
 We thank the following people for their extensive assistance in the development of this pipeline:
 
@@ -106,9 +107,6 @@ 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/seqinspector 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 -->
 
 An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.

diff --git a/assets/methods_description_template.yml b/assets/methods_description_template.yml
@@ -3,8 +3,6 @@ description: "Suggested text and references to use when describing pipeline usag
 section_name: "nf-core/seqinspector Methods Description"
 section_href: "https://github.com/nf-core/seqinspector"
 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 '${workflow}' object
 data: |
   <h4>Methods</h4>
   <p>Data was processed using nf-core/seqinspector v${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>

diff --git a/assets/nf-core-seqinspector_logo_light.png b/assets/nf-core-seqinspector_logo_light.png
diff --git a/conf/modules.config b/conf/modules.config
@@ -59,6 +59,15 @@ process {
         ]
     }
 
+    withName: 'PICARD_COLLECTHSMETRICS' {
+        publishDir = [
+            path: { "${params.outdir}/picard_collecthsmetrics" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+        ext.args = {"--TMP_DIR ."}
+    }
+
     withName: 'SAMTOOLS_FAIDX' {
         publishDir = [
             path: { "${params.outdir}/samtools_faidx" },

diff --git a/docs/images/nf-core-seqinspector_logo_dark.png b/docs/images/nf-core-seqinspector_logo_dark.png
diff --git a/docs/images/nf-core-seqinspector_logo_light.png b/docs/images/nf-core-seqinspector_logo_light.png
diff --git a/docs/output.md b/docs/output.md
@@ -14,6 +14,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [FastQC](#fastqc) - Raw read QC
 - [SeqFu Stats](#seqfu_stats) - Statistics for FASTA or FASTQ files
 - [FastQ Screen](#fastqscreen) - Mapping against a set of references for basic contamination QC
+- [Picard collecthsmetrics](#picard-collecthsmetrics) - Collect alignment QC metrics of hybrid-selection data
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
@@ -80,6 +81,18 @@ The `.csv` is provided as a pipeline parameter `fastq_screen_references` and is
 
 [SeqFu](https://telatin.github.io/seqfu2/) is general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files. Includes functions to interleave and de-interleave FASTQ files, to rename sequences and to count and print statistics on sequence lengths. In this pipeline, the `seqfu stats` module is used to produce general quality metrics statistics.
 
+### Picard CollectHSmetrics
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `picard_collecthsmetrics/`
+  - `*.coverage_metrics`: Tab-separated file containing quality metrics for hybrid-selection data.
+
+</details>
+
+[Picard_collecthsmetrics](https://gatk.broadinstitute.org/hc/en-us/articles/360036856051-CollectHsMetrics-Picard) is a tool to collect metrics on the aligment SAM/BAM files that are specific for sequence datasets generated through hybrid-selection (mostly used to capture exon-specific sequences for targeted sequencing).
+
 ### MultiQC
 
 nf-core/seqinspector will generate the following MultiQC reports:

diff --git a/docs/usage.md b/docs/usage.md
@@ -2,15 +2,21 @@
 
 ## :warning: Please read this documentation on the nf-core website: [https://nf-co.re/seqinspector/usage](https://nf-co.re/seqinspector/usage)
 
-> _Documentation of pipeline parameters is generated automatically from the pipeline schema and can no longer be found in markdown files._
-
 ## Introduction
 
-<!-- TODO nf-core: Add documentation about anything specific to running your pipeline. For general topics, please point to (and add to) the main nf-core website. -->
+### General points
+
+The nf-core/seqinspector pipeline is a general QC pipeline for sequencing data. The current version only supports data in fastq format.
+The pipeline is meant to include a large amount of possible QC tools to chose from, but not all of them may be relevant to your data. As such we highly recommend to familiarize yourself with the different QC tools available and to remove any QC tool you would like to exclude with the `--skip-tools` command line parameter. For repeated use we suggest to create a params file containing the `--skip-tools` parameters (for details see the "Running the pipeline" section).
+Be aware that some tools are skipped by default and will need to be included in the list of skipped tools when curating your own list. To identify defaults included or excluded please check out the overview table in the Introduction.
+
+### What nf-core/seqinspector is not for
+
+The results of the nf-core/seqinspector pipeline are not meant to be used for any downstream analysis, but are exclusively for QC purposes. Even tools that may be used in other pipelines as a starting point for analysis are run in a QC perspective, most likely with a downsampled input.
 
 ## Samplesheet input
 
-You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location.
+You will need to create a samplesheet with information about the samples/fastq files you would like to analyse before running the pipeline. Use this parameter to specify its location.
 
 ```bash
 --input '[path to samplesheet file]'
@@ -51,7 +57,7 @@ Another [example samplesheet](../assets/samplesheet.csv) has been provided with
 
 ## Running the pipeline
 
-The typical command for running the pipeline is as follows:
+A typical command for running the pipeline is as follows:
 
 ```bash
 nextflow run nf-core/seqinspector --input ./samplesheet.csv --outdir ./results --genome GRCh37 -profile docker
@@ -100,7 +106,7 @@ nextflow run nf-core/seqinspector --input ./samplesheet.csv --outdir ./results -
 
 ### Skipping tools
 
-Some tools might not be compatible with your data. In this case it might be desired to skip some of them. This can be done easily by providing a comma-separated list of tools to be skipped with the `--skip_tools` parameter.
+Some tools might not be compatible with your data. In this case you can skip them by providing a comma-separated list of tools to be skipped with the `--skip_tools` parameter.
 
 In case you want to make this more permanent, it is recommended to specify this in a params file, or even in your own nextflow configuration file. The nextflow configuration file can also be use to customise tool arguments. See official [nexflow](https://www.nextflow.io/docs/latest/config.html) and [nf-core](https://nf-co.re/docs/usage/configuration#customising-tool-arguments) documentation for further details.
 
@@ -123,7 +129,7 @@ This version number will be logged in reports when you run the pipeline, so that
 To further assist in reproducibility, you can use share and reuse [parameter files](#running-the-pipeline) to repeat pipeline runs with the same settings without having to write out a command with every single parameter.
 
 > [!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.
+> If you wish to share such profiles (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
 
@@ -221,3 +227,7 @@ We recommend adding the following line to your environment to limit this (typica
 ```bash
 NXF_OPTS='-Xms1g -Xmx4g'
 ```
+
+## Hybrid-selection QC metrics
+
+The pipeline supports hybrid-selection (HS) QC metrics collection . Use `--run_picard_collecthsmetrics true` to run the QC tool [picard CollectHSmetrics](https://gatk.broadinstitute.org/hc/en-us/articles/360036856051-CollectHsMetrics-Picard). This tool is otherwise not run by default.
diff --git a/main.nf b/main.nf
@@ -16,6 +16,7 @@
 
 params.fasta = getGenomeAttribute('fasta')
 
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     IMPORT FUNCTIONS / MODULES / SUBWORKFLOWS / WORKFLOWS
@@ -44,10 +45,13 @@ workflow NFCORE_SEQINSPECTOR {
     //
     // WORKFLOW: Run pipeline
     //
+    skip_tools = params.skip_tools ? params.skip_tools.split(',') : []
 
     SEQINSPECTOR(
         samplesheet,
         params.fasta,
+        skip_tools,
+        params.bwamem2
     )
 
     emit:

diff --git a/modules.json b/modules.json
@@ -42,11 +42,21 @@
                         "git_sha": "82a79183037a403ad1b6714e5dbcff25500efaf6",
                         "installed_by": ["modules"]
                     },
+                    "picard/collecthsmetrics": {
+                        "branch": "master",
+                        "git_sha": "e753770db613ce014b3c4bc94f6cba443427b726",
+                        "installed_by": ["modules"]
+                    },
                     "picard/collectmultiplemetrics": {
                         "branch": "master",
                         "git_sha": "df124e87c74d8b40285199f8cc20151f5aa57255",
                         "installed_by": ["modules"]
                     },
+                    "picard/createsequencedictionary": {
+                        "branch": "master",
+                        "git_sha": "df124e87c74d8b40285199f8cc20151f5aa57255",
+                        "installed_by": ["modules"]
+                    },
                     "samtools/faidx": {
                         "branch": "master",
                         "git_sha": "e753770db613ce014b3c4bc94f6cba443427b726",

diff --git a/modules/nf-core/picard/collecthsmetrics/environment.yml b/modules/nf-core/picard/collecthsmetrics/environment.yml