🔧 configure MultiQC analysis

.vscode/settings.json

@@ -13,6 +13,7 @@
         "downsampling",
         "fasta",
         "fastq",
+        "flagstat",
         "freebayes",
         "ibba",
         "markduplicate",

assets/methods_description_template.yml

@@ -0,0 +1,29 @@
+id: "nf-resequencing-mem-methods-description"
+description: "Suggested text and references to use when describing pipeline usage within the methods section of a publication."
+section_name: "cnr-ibba/nf-resequencing-mem Methods Description"
+section_href: "https://github.com/cnr-ibba/nf-resequencing-mem"
+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 '${workflow}' object
+data: |
+  <h4>Methods</h4>
+  <p>Data was processed using cnr-ibba/nf-resequencing-mem v${workflow.manifest.version} ${doi_text} of the nf-core collection of workflows (<a href="https://doi.org/10.1038/s41587-020-0439-x">Ewels <em>et al.</em>, 2020</a>), utilising reproducible software environments from the Bioconda (<a href="https://doi.org/10.1038/s41592-018-0046-7">Grüning <em>et al.</em>, 2018</a>) and Biocontainers (<a href="https://doi.org/10.1093/bioinformatics/btx192">da Veiga Leprevost <em>et al.</em>, 2017</a>) projects.</p>
+  <p>The pipeline was executed with Nextflow v${workflow.nextflow.version} (<a href="https://doi.org/10.1038/nbt.3820">Di Tommaso <em>et al.</em>, 2017</a>) with the following command:</p>
+  <pre><code>${workflow.commandLine}</code></pre>
+  <p>${tool_citations}</p>
+  <h4>References</h4>
+  <ul>
+    <li>Di Tommaso, P., Chatzou, M., Floden, E. W., Barja, P. P., Palumbo, E., & Notredame, C. (2017). Nextflow enables reproducible computational workflows. Nature Biotechnology, 35(4), 316-319. doi: <a href="https://doi.org/10.1038/nbt.3820">10.1038/nbt.3820</a></li>
+    <li>Ewels, P. A., Peltzer, A., Fillinger, S., Patel, H., Alneberg, J., Wilm, A., Garcia, M. U., Di Tommaso, P., & Nahnsen, S. (2020). The nf-core framework for community-curated bioinformatics pipelines. Nature Biotechnology, 38(3), 276-278. doi: <a href="https://doi.org/10.1038/s41587-020-0439-x">10.1038/s41587-020-0439-x</a></li>
+    <li>Grüning, B., Dale, R., Sjödin, A., Chapman, B. A., Rowe, J., Tomkins-Tinch, C. H., Valieris, R., Köster, J., & Bioconda Team. (2018). Bioconda: sustainable and comprehensive software distribution for the life sciences. Nature Methods, 15(7), 475–476. doi: <a href="https://doi.org/10.1038/s41592-018-0046-7">10.1038/s41592-018-0046-7</a></li>
+    <li>da Veiga Leprevost, F., Grüning, B. A., Alves Aflitos, S., Röst, H. L., Uszkoreit, J., Barsnes, H., Vaudel, M., Moreno, P., Gatto, L., Weber, J., Bai, M., Jimenez, R. C., Sachsenberg, T., Pfeuffer, J., Vera Alvarez, R., Griss, J., Nesvizhskii, A. I., & Perez-Riverol, Y. (2017). BioContainers: an open-source and community-driven framework for software standardization. Bioinformatics (Oxford, England), 33(16), 2580–2582. doi: <a href="https://doi.org/10.1093/bioinformatics/btx192">10.1093/bioinformatics/btx192</a></li>
+    ${tool_bibliography}
+  </ul>
+  <div class="alert alert-info">
+    <h5>Notes:</h5>
+    <ul>
+      ${nodoi_text}
+      <li>The command above does not include parameters contained in any configs or profiles that may have been used. Ensure the config file is also uploaded with your publication!</li>
+      <li>You should also cite all software used within this run. Check the "Software Versions" of this report to get version information.</li>
+    </ul>
+  </div>

assets/multiqc_config.yml

@@ -3,13 +3,31 @@ report_comment: >
   analysis pipeline. For information about how to interpret these results, please see the
   <a href="https://github.com/cnr-ibba/nf-resequencing-mem/blob/v0.5.2/README.md" target="_blank">documentation</a>.
 report_section_order:
-  software_versions:
+  "nf-resequencing-mem-methods-description":
     order: -1000
-  cnr-ibba/nf-resequencing-mem-summary:
+  software_versions:
     order: -1001
+  cnr-ibba-nf-resequencing-mem-summary:
+    order: -1002
 
 export_plots: true
 
 custom_logo: "cnr-ibba.png"
 custom_logo_url: "https://ibba.cnr.it/en/"
 custom_logo_title: "CNR-IBBA"
+
+extra_fn_clean_exts:
+  - ".cram"
+  - type: remove
+    pattern: _T1
+
+top_modules:
+  - fastqc
+
+module_order:
+  - fastqc
+  - cutadapt
+  - samtools
+  - picard
+  - bcftools
+  - snpeff

conf/modules.config

@@ -139,6 +139,14 @@ process {
         ]
     }
 
+    withName: SAMTOOLS_DEPTH {
+        publishDir = [
+            path: { "${params.outdir}/coverage" },
+            mode: params.publish_dir_mode,
+            pattern: "*.gz"
+        ]
+    }
+
     withName: FREEBAYES_SPLITCRAM {
         publishDir = [
             enabled: false

modules.json

@@ -64,7 +64,7 @@
           },
           "multiqc": {
             "branch": "master",
-            "git_sha": "4ab13872435962dadc239979554d13709e20bf29",
+            "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",
             "installed_by": ["modules"]
           },
           "picard/markduplicates": {

nextflow.config

@@ -17,7 +17,7 @@ params {
     genome_bwa_index           = null
 
     // MultiQC options
-    multiqc_config             = "$baseDir/assets/multiqc_config.yml"
+    multiqc_config             = null
     multiqc_logo               = "$baseDir/assets/cnr-ibba.png"
     multiqc_title              = null
     max_multiqc_email_size     = '25.MB'

workflows/resequencing-mem.nf

@@ -64,13 +64,13 @@ workflow RESEQUENCING_MEM {
   )
   .reads
   .map {
-      meta, fastq ->
-        def meta_clone = meta.clone()
-        tmp = meta_clone.id.split('_')
-        if (tmp.size() > 1) {
-          meta_clone.id = tmp[0..-2].join('_')
-        }
-        [ meta_clone, fastq ]
+    meta, fastq ->
+      def meta_clone = meta.clone()
+      tmp = meta_clone.id.split('_')
+      if (tmp.size() > 1) {
+        meta_clone.id = tmp[0..-2].join('_')
+      }
+      [ meta_clone, fastq ]
     }
     .groupTuple(by: [0])
     .branch {
@@ -213,25 +213,39 @@ workflow RESEQUENCING_MEM {
   }
 
   // get only the data I need for a MultiQC step
-  multiqc_input = FASTQC.out.html.map{it[1]}.ifEmpty([])
-        .concat(FASTQC.out.zip.map{it[1]}.ifEmpty([]))
-        .concat(TRIMGALORE.out.log.map{it[1]}.ifEmpty([]))
-        .concat(CRAM_MARKDUPLICATES_PICARD.out.metrics.map{it[1]}.ifEmpty([]))
-        .concat(CRAM_MARKDUPLICATES_PICARD.out.stats.map{it[1]}.ifEmpty([]))
-        .concat(CRAM_MARKDUPLICATES_PICARD.out.idxstats.map{it[1]}.ifEmpty([]))
-        .concat(CRAM_MARKDUPLICATES_PICARD.out.flagstat.map{it[1]}.ifEmpty([]))
-        .concat(CRAM_MARKDUPLICATES_PICARD.out.stats.map{it[1]}.ifEmpty([]))
-        .concat(snpeff_report.map{it[1]}.ifEmpty([]))
-        .collect()
-        // .view()
+  ch_multiqc_files = FASTQC.out.html.map{it[1]}.ifEmpty([])
+    .concat(FASTQC.out.zip.map{it[1]}.ifEmpty([]))
+    .concat(TRIMGALORE.out.log.map{it[1]}.ifEmpty([]))
+    .concat(CRAM_MARKDUPLICATES_PICARD.out.metrics.map{it[1]}.ifEmpty([]))
+    .concat(CRAM_MARKDUPLICATES_PICARD.out.stats.map{it[1]}.ifEmpty([]))
+    .concat(CRAM_MARKDUPLICATES_PICARD.out.idxstats.map{it[1]}.ifEmpty([]))
+    .concat(CRAM_MARKDUPLICATES_PICARD.out.flagstat.map{it[1]}.ifEmpty([]))
+    .concat(CRAM_MARKDUPLICATES_PICARD.out.coverage.map{it[1]}.ifEmpty([]))
+    .concat(BCFTOOLS_STATS.out.stats.map{it[1]}.ifEmpty([]))
+    .concat(snpeff_report.map{it[1]}.ifEmpty([]))
+    // .view()
 
   // prepare multiqc_config file
-  multiqc_config = Channel.fromPath(params.multiqc_config)
-  multiqc_logo = Channel.fromPath(params.multiqc_logo)
+  ch_multiqc_config                     = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true)
+  ch_multiqc_custom_config              = params.multiqc_config ? Channel.fromPath(params.multiqc_config, checkIfExists: true) : Channel.empty()
+  ch_multiqc_logo                       = params.multiqc_logo ? Channel.fromPath(params.multiqc_logo, checkIfExists: true) : Channel.empty()
+
+  // TODO: requires nf-validation plugin and other stuff
+  // summary_params                        = paramsSummaryMap(workflow, parameters_schema: "nextflow_schema.json")
+  // ch_workflow_summary                   = Channel.value(paramsSummaryMultiqc(summary_params))
+  // ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
+  // ch_methods_description                = Channel.value(methodsDescriptionText(ch_multiqc_custom_methods_description))
+  // ch_multiqc_files                      = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
+  // ch_multiqc_files                      = ch_multiqc_files.mix(ch_collated_versions)
+  // ch_multiqc_files                      = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml', sort: false))
 
   // calling MultiQC
-  MULTIQC(multiqc_input, multiqc_config, [], multiqc_logo)
-  ch_versions = ch_versions.mix(MULTIQC.out.versions)
+  MULTIQC (
+    ch_multiqc_files.collect(),
+    ch_multiqc_config.toList(),
+    ch_multiqc_custom_config.toList(),
+    ch_multiqc_logo.toList()
+  )
 
   // return software version
   CUSTOM_DUMPSOFTWAREVERSIONS (