Merge pull request #3129 from mirpedrol/template-customisation-fastqc

Template: add option to exclude fastqc from pipeline template

CHANGELOG.md

@@ -30,6 +30,7 @@
 - add option to exclude changelog from custom pipeline template ([#3104](https://github.com/nf-core/tools/pull/3104))
 - add option to exclude license from pipeline template ([#3125](https://github.com/nf-core/tools/pull/3125))
 - add option to exclude email from pipeline template ([#3126](https://github.com/nf-core/tools/pull/3126))
+- add option to exclude fastqc from pipeline template ([#3129](https://github.com/nf-core/tools/pull/3129))
 
 ### Linting
 

nf_core/components/lint/__init__.py

@@ -114,9 +114,7 @@ def __init__(
                         )
                     )
             if not self.all_remote_components:
-                raise LookupError(
-                    f"No {self.component_type} from {self.modules_repo.remote_url} installed in pipeline."
-                )
+                log.warning(f"No {self.component_type} from {self.modules_repo.remote_url} installed in pipeline.")
             local_component_dir = Path(self.directory, self.component_type, "local")
 
             if local_component_dir.exists():
@@ -146,7 +144,7 @@ def __init__(
             ]
             self.all_local_components = []
             if not self.all_remote_components:
-                raise LookupError(f"No {self.component_type} in '{self.component_type}' directory")
+                log.warning(f"No {self.component_type} in '{self.component_type}' directory")
 
             # This could be better, perhaps glob for all nextflow.config files in?
             self.config = nf_core.utils.fetch_wf_config(self.directory / "tests" / "config", cache_config=True)

nf_core/modules/lint/__init__.py

@@ -110,7 +110,7 @@ def lint(
         """
         # TODO: consider unifying modules and subworkflows lint() function and add it to the ComponentLint class
         # Prompt for module or all
-        if module is None and not all_modules:
+        if module is None and not all_modules and len(self.all_remote_components) > 0:
             questions = [
                 {
                     "type": "list",

nf_core/pipeline-template/CITATIONS.md

@@ -12,11 +12,10 @@
 
 ## Pipeline tools
 
-- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+{% if fastqc %}- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
 
-  > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
-
-{% if multiqc %}- [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
+> Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
+> {% endif %} > {% if multiqc %}- [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.
 > {%- endif %}

nf_core/pipeline-template/README.md

@@ -44,8 +44,8 @@
      workflows use the "tube map" design for that. See https://nf-co.re/docs/contributing/design_guidelines#examples for examples.   -->
 <!-- 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/))
-   {% if multiqc %}2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)){% endif %}
+{% if fastqc %}1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)){% endif %}
+{% if multiqc %}2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)){% endif %}
 
 ## Usage
 

nf_core/pipeline-template/conf/modules.config

@@ -18,9 +18,11 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
+    {% if fastqc -%}
     withName: FASTQC {
         ext.args = '--quiet'
     }
+    {%- endif %}
 
     {%- if multiqc %}
     withName: 'MULTIQC' {

nf_core/pipeline-template/docs/output.md

@@ -12,10 +12,13 @@ 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:
 
-- [FastQC](#fastqc) - Raw read QC
-  {% if multiqc %}- [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline{% endif %}
+{% if fastqc %}- [FastQC](#fastqc) - Raw read QC{% endif %}
+{% if multiqc %}- [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline{% endif %}
+
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
+{%- if fastqc %}
+
 ### FastQC
 
 <details markdown="1">
@@ -28,7 +31,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 </details>
 
 [FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/).
-
+{%- endif %}
 {%- if multiqc %}
 
 ### MultiQC

nf_core/pipeline-template/modules.json

@@ -5,11 +5,12 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
+                    {%- if fastqc %}
                     "fastqc": {
                         "branch": "master",
                         "git_sha": "285a50500f9e02578d90b3ce6382ea3c30216acd",
                         "installed_by": ["modules"]
-                    }{%- if multiqc %},
+                    }{% endif %}{%- if multiqc %}{% if fastqc %},{% endif %}
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",

nf_core/pipeline-template/subworkflows/local/utils_nfcore_pipeline_pipeline/main.nf

@@ -230,8 +230,8 @@ def toolCitationText() {
     // Uncomment function in methodsDescriptionText to render in MultiQC report
     def citation_text = [
             "Tools used in the workflow included:",
-            "FastQC (Andrews 2010),",
-            "MultiQC (Ewels et al. 2016)",
+            {% if fastqc %}"FastQC (Andrews 2010),",{% endif %}
+            {% if multiqc %}"MultiQC (Ewels et al. 2016)",{% endif %}
             "."
         ].join(' ').trim()
 
@@ -243,8 +243,8 @@ def toolBibliographyText() {
     // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "<li>Author (2023) Pub name, Journal, DOI</li>" : "",
     // Uncomment function in methodsDescriptionText to render in MultiQC report
     def reference_text = [
-            "<li>Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).</li>",
-            "<li>Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354</li>"
+            {% if fastqc %}"<li>Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).</li>",{% endif %}
+            {% if multiqc %}"<li>Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354</li>"{% endif %}
         ].join(' ').trim()
 
     return reference_text

nf_core/pipeline-template/workflows/pipeline.nf

@@ -4,7 +4,7 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-include { FASTQC                 } from '../modules/nf-core/fastqc/main'
+{% if fastqc %}include { FASTQC                 } from '../modules/nf-core/fastqc/main'{% endif %}
 {% if multiqc %}include { MULTIQC                } from '../modules/nf-core/multiqc/main'{% endif %}
 include { paramsSummaryMap       } from 'plugin/nf-validation'
 {% if multiqc %}include { paramsSummaryMultiqc   } from '../subworkflows/nf-core/utils_nfcore_pipeline'{% endif %}
@@ -27,6 +27,7 @@ workflow {{ short_name|upper }} {
     ch_versions = Channel.empty()
     {% if multiqc %}ch_multiqc_files = Channel.empty(){% endif %}
 
+    {%- if fastqc %}
     //
     // MODULE: Run FastQC
     //
@@ -35,14 +36,15 @@ workflow {{ short_name|upper }} {
     )
     {% if multiqc %}ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}){% endif %}
     ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+    {%- endif %}
 
     //
     // Collate and save software versions
     //
     softwareVersionsToYAML(ch_versions)
         .collectFile(
             storeDir: "${params.outdir}/pipeline_info",
-            name: 'nf_core_pipeline_software_mqc_versions.yml',
+            name: {% if is_nfcore %}'nf_core_' {% else %} '' {% endif %} + 'pipeline_software_' + {% if multiqc %} 'mqc_' {% else %} '' {% endif %} + 'versions.yml',
             sort: true,
             newLine: true
         ).set { ch_collated_versions }

nf_core/pipelines/create/templatefeatures.yml

@@ -228,6 +228,16 @@ multiqc:
     multiqc_config: False
   nfcore_pipelines: True
   custom_pipelines: True
+fastqc:
+  skippable_paths:
+    - "modules/nf-core/fastqc/"
+  short_description: "Use fastqc"
+  description: "The pipeline will include the FastQC module which performs quality control analysis of input FASTQ files."
+  help_text: |
+    FastQC is a tool which provides quality control checks on raw sequencing data.
+    The pipeline will include the FastQC module.
+  nfcore_pipelines: True
+  custom_pipelines: True
 changelog:
   skippable_paths:
     - "CHANGELOG.md"

tests/modules/test_lint.py

@@ -2,7 +2,6 @@
 from pathlib import Path
 from typing import Union
 
-import pytest
 import yaml
 from git.repo import Repo
 
@@ -191,8 +190,8 @@ def test_modules_lint_empty(self):
         """Test linting a pipeline with no modules installed"""
         self.mods_remove.remove("fastqc", force=True)
         self.mods_remove.remove("multiqc", force=True)
-        with pytest.raises(LookupError):
-            nf_core.modules.lint.ModuleLint(directory=self.pipeline_dir)
+        nf_core.modules.lint.ModuleLint(directory=self.pipeline_dir)
+        assert "No modules from https://github.com/nf-core/modules.git installed in pipeline" in self.caplog.text
 
     def test_modules_lint_new_modules(self):
         """lint a new module"""
@@ -206,8 +205,8 @@ def test_modules_lint_no_gitlab(self):
         """Test linting a pipeline with no modules installed"""
         self.mods_remove.remove("fastqc", force=True)
         self.mods_remove.remove("multiqc", force=True)
-        with pytest.raises(LookupError):
-            nf_core.modules.lint.ModuleLint(directory=self.pipeline_dir, remote_url=GITLAB_URL)
+        nf_core.modules.lint.ModuleLint(directory=self.pipeline_dir, remote_url=GITLAB_URL)
+        assert f"No modules from {GITLAB_URL} installed in pipeline" in self.caplog.text
 
     def test_modules_lint_gitlab_modules(self):
         """Lint modules from a different remote"""
@@ -566,7 +565,7 @@ def test_modules_meta_yml_input_mismatch(self):
             fh.write(main_nf)
         assert len(module_lint.failed) == 0, f"Linting failed with {[x.__dict__ for x in module_lint.failed]}"
         assert len(module_lint.passed) >= 0
-        assert len(module_lint.warned) == 2
+        assert len(module_lint.warned) == 2, f"Linting warning with {[x.__dict__ for x in module_lint.warned]}"
         lint_tests = [x.lint_test for x in module_lint.warned]
         # check that it is there twice:
         assert lint_tests.count("meta_input_meta_only") == 1