Merge pull request #68 from Aratz/tool_selector

Aratz · web-flow · commit ec9570d0e975 · 2025-01-17T14:17:08.000+01:00
Add skip tools parameter for tool selection
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 
 ### `Added`
 
+- [#68](https://github.com/nf-core/seqinspector/pull/68) Add tool selector
 - [#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.
diff --git a/docs/usage.md b/docs/usage.md
@@ -98,6 +98,12 @@ Optionally, the `sample_size` parameter allows you to subset a random number of
 nextflow run nf-core/seqinspector --input ./samplesheet.csv --outdir ./results --sample_size 1000000 -profile docker
 ```
 
+### 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.
+
+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.
+
 ### 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/nextflow.config b/nextflow.config
@@ -13,6 +13,7 @@ params {
     // Input options
     input                      = null
     sample_size                = 0
+    skip_tools                 = ''
     // References
     genome                     = null
     fasta                      = null
diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -25,9 +25,9 @@
                 },
                 "sample_size": {
                     "type": "integer",
-                    "default": 0,
                     "description": "Take this number of reads as a subset.",
-                    "help_text": "Choose the size of the subset or 0, if no subsampling shall be performed. Note that it refers to an absolute number."
+                    "help_text": "Choose the size of the subset or 0, if no subsampling shall be performed. Note that it refers to an absolute number.",
+                    "default": 0
                 },
                 "outdir": {
                     "type": "string",
@@ -47,6 +47,11 @@
                     "type": "string",
                     "description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.",
                     "fa_icon": "fas fa-file-signature"
+                },
+                "skip_tools": {
+                    "type": "string",
+                    "description": "Comma-separated string of tools to skip",
+                    "pattern": "^((fastqc|fastqscreen|seqfu_stats|seqtk_sample)?,?)*(?<!,)$"
                 }
             }
         },
diff --git a/tests/MiSeq.main.nf.test b/tests/MiSeq.main.nf.test
@@ -27,4 +27,27 @@ nextflow_pipeline {
             )
         }
     }
+
+    test("Miseq data test (skip fastqc)") {
+        when {
+            config "./MiSeq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+                skip_tools = "fastqc"
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                    path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
+                    ).match()
+                },
+                {
+                    assert !path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt").exists()
+                }
+            )
+        }
+    }
 }
diff --git a/tests/MiSeq.main.nf.test.snap b/tests/MiSeq.main.nf.test.snap
@@ -10,6 +10,16 @@
             "nf-test": "0.9.0",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-05T15:15:09.227024034"
+        "timestamp": "2024-12-13T16:10:21.816261"
+    },
+    "Miseq data test (skip fastqc)": {
+        "content": [
+            "multiqc_citations.txt:md5,5f52d7a0141e4234c6069df9ef575c9a"
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.10.2"
+        },
+        "timestamp": "2024-12-13T16:10:53.718831"
     }
 }
diff --git a/workflows/seqinspector.nf b/workflows/seqinspector.nf
@@ -31,6 +31,7 @@ workflow SEQINSPECTOR {
     ch_samplesheet               // channel: samplesheet read in from --input
 
     main:
+    skip_tools = params.skip_tools ? params.skip_tools.split(',') : []
 
     ch_versions            = Channel.empty()
     ch_multiqc_files       = Channel.empty()
@@ -40,38 +41,42 @@ workflow SEQINSPECTOR {
     //
     // MODULE: Run Seqtk sample to perform subsampling
     //
-    if (params.sample_size > 0 ) {
+    if (!("seqtk_sample" in skip_tools) && params.sample_size > 0) {
         ch_sample_sized = SEQTK_SAMPLE(
             ch_samplesheet.map {
                 meta, reads -> [meta, reads, params.sample_size]
             }
         ).reads
         ch_versions = ch_versions.mix(SEQTK_SAMPLE.out.versions.first())
     } else {
-        // No do subsample
+        // No subsampling
         ch_sample_sized = ch_samplesheet
     }
 
     //
     // MODULE: Run FastQC
     //
-    FASTQC (
-        ch_sample_sized.map {
-            meta, subsampled -> [meta, subsampled]
-        }
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
-    ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+    if (!("fastqc" in skip_tools)) {
+        FASTQC (
+            ch_sample_sized.map {
+                meta, subsampled -> [meta, subsampled]
+            }
+        )
+        ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
+        ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+    }
 
 
     //
     // Module: Run SeqFu stats
     //
-    SEQFU_STATS (
-        ch_samplesheet
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(SEQFU_STATS.out.multiqc)
-    ch_versions = ch_versions.mix(SEQFU_STATS.out.versions.first())
+    if (!("seqfu_stats" in skip_tools)) {
+        SEQFU_STATS (
+            ch_samplesheet
+        )
+        ch_multiqc_files = ch_multiqc_files.mix(SEQFU_STATS.out.multiqc)
+        ch_versions = ch_versions.mix(SEQFU_STATS.out.versions.first())
+    }
 
     //
     // MODULE: Run FastQ Screen
@@ -80,21 +85,23 @@ workflow SEQINSPECTOR {
     // Parse the reference info needed to create a FastQ Screen config file
     // and transpose it into a tuple containing lists for each property
 
-    ch_fastqscreen_refs = Channel
-        .fromList(samplesheetToList(
-            "${projectDir}/assets/example_fastq_screen_references.csv",
-            "${projectDir}/assets/schema_fastq_screen_references.json"
-        ))
-        .toList()
-        .transpose()
-        .toList()
-
-    FASTQSCREEN_FASTQSCREEN (
-        ch_samplesheet,
-        ch_fastqscreen_refs
-    )
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
-    ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())
+    if (!("fastqscreen" in skip_tools)) {
+        ch_fastqscreen_refs = Channel
+            .fromList(samplesheetToList(
+                "${projectDir}/assets/example_fastq_screen_references.csv",
+                "${projectDir}/assets/schema_fastq_screen_references.json"
+            ))
+            .toList()
+            .transpose()
+            .toList()
+
+        FASTQSCREEN_FASTQSCREEN (
+            ch_samplesheet,
+            ch_fastqscreen_refs
+        )
+        ch_multiqc_files = ch_multiqc_files.mix(FASTQSCREEN_FASTQSCREEN.out.txt)
+        ch_versions = ch_versions.mix(FASTQSCREEN_FASTQSCREEN.out.versions.first())
+    }
 
     //
     // Collate and save software versions
