nf-core · nggvs · Oct 30, 2024 · Oct 28, 2024 · Oct 28, 2024 · Oct 28, 2024
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -12,6 +12,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
 - [#49](https://github.com/nf-core/seqinspector/pull/49) Merge with template 3.0.2.
+- [#50](https://github.com/nf-core/seqinspector/pull/50) Add an optional subsampling step.
 
 ### `Fixed`
 

diff --git a/docs/output.md b/docs/output.md
@@ -10,10 +10,23 @@ 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:
 
+- [seqkit](#seqkit) - Subsample a specific number of reads per sample
 - [FastQC](#fastqc) - Raw read QC
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
+### Seqkit
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `seqtk/`
+  - `*_fastq`: FastQ file after being subsampled to the sample_size value.
+
+</details>
+
+[SeqKit](https://bioinf.shenwei.me/seqkit/) samples sequences by number. For further reading and documentation see the [Seqkit sample](https://bioinf.shenwei.me/seqkit/usage/#sample).
+
 ### FastQC
 
 <details markdown="1">

diff --git a/docs/usage.md b/docs/usage.md
@@ -93,6 +93,12 @@ genome: 'GRCh37'
 
 You can also generate such `YAML`/`JSON` files via [nf-core/launch](https://nf-co.re/launch).
 
+Optionally, the `sample_size` parameter allows you to subset a random number of reads to be analysed.
+
+```bash
+nextflow run nf-core/seqinspector --input ./samplesheet.csv --outdir ./results --sample_size 90 -profile docker
+```
+
 ### Updating the pipeline
 
 When you run the above command, Nextflow automatically pulls the pipeline code from GitHub and stores it as a cached version. When running the pipeline after this, it will always use the cached version if available - even if the pipeline has been updated since. To make sure that you're running the latest version of the pipeline, make sure that you regularly update the cached version of the pipeline:

diff --git a/modules.json b/modules.json
@@ -14,6 +14,11 @@
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
                         "installed_by": ["modules"]
+                    },
+                    "seqtk/sample": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
                     }
                 }
             },

diff --git a/modules/nf-core/seqtk/sample/environment.yml b/modules/nf-core/seqtk/sample/environment.yml
diff --git a/modules/nf-core/seqtk/sample/main.nf b/modules/nf-core/seqtk/sample/main.nf
diff --git a/modules/nf-core/seqtk/sample/meta.yml b/modules/nf-core/seqtk/sample/meta.yml
diff --git a/modules/nf-core/seqtk/sample/tests/main.nf.test b/modules/nf-core/seqtk/sample/tests/main.nf.test
diff --git a/modules/nf-core/seqtk/sample/tests/main.nf.test.snap b/modules/nf-core/seqtk/sample/tests/main.nf.test.snap
diff --git a/modules/nf-core/seqtk/sample/tests/standard.config b/modules/nf-core/seqtk/sample/tests/standard.config
diff --git a/modules/nf-core/seqtk/sample/tests/tags.yml b/modules/nf-core/seqtk/sample/tests/tags.yml
diff --git a/nextflow.config b/nextflow.config
@@ -12,7 +12,7 @@ params {
     // TODO nf-core: Specify your pipeline's command line flags
     // Input options
     input                      = null
-
+    sample_size                = 0
     // References
     genome                     = null
     fasta                      = null

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -23,8 +23,15 @@
                     "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row. See [usage docs](https://nf-co.re/seqinspector/usage#samplesheet-input).",
                     "fa_icon": "fas fa-file-csv"
                 },
+                "sample_size": {
+                    "type": "integer",
+                    "default": 0,
+                    "description": "Subset this number of reads.",
+                    "help_text": "Samples will be subsetted to this number of reads. If 0 (default), no subsampling will be performed."
+                },
                 "outdir": {
                     "type": "string",
+                    "default": null,
                     "format": "directory-path",
                     "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
                     "fa_icon": "fas fa-folder-open"