Merge branch 'dev' into metaphlan4_profiler

nf-core · Jul 17, 2023 · 14bed9d · 14bed9d
2 parents bc27e8a + 71c9275
commit 14bed9d
Show file tree

Hide file tree

Showing 7 changed files with 38 additions and 26 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -15,12 +15,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - [#303](https://github.com/nf-core/taxprofiler/pull/303) Add support for taxpasta profile standardisation in single sample pipeline runs (❤️ to @artur-matysik for request, added by @jfy133)
   - [#315](https://github.com/nf-core/taxprofiler/pull/315) Updated to nf-core pipeline template v2.9 (added by @sofstam & @jfy133)
   - [#319](https://github.com/nf-core/taxprofiler/pull/319) Added support for virus hit expansion in Kaiju (❤️ to @dnlrxn for requesting, added by @jfy133)
+  - [#323](https://github.com/nf-core/taxprofiler/pull/323) Add ability to skip sequencing quality control tools (❤️ to @vinisalazar for requesting, added by @jfy133)
   - [#318](https://github.com/nf-core/taxprofiler/pull/318) Added the profiler MetaPhlAn4 and removed MetaPhlAn3 (added by@LilyAnderssonLee)
 
 ### `Fixed`
 
 - [#271](https://github.com/nf-core/taxprofiler/pull/271) Improved standardised table generation documentation for mOTUs manual database download tutorial (♥ to @prototaxites for reporting, fix by @jfy133)
-- [#269](https://github.com/nf-core/taxprofiler/pull/269) Reduced output files in AWS full test output due to very large files
+- [#269](https://github.com/nf-core/taxprofiler/pull/269) Reduced output files in AWS full test output due to very large files (fix by @jfy133)
 - [#270](https://github.com/nf-core/taxprofiler/pull/270) Fixed warning for host removal index parameter, and improved index checks (♥ to @prototaxites for reporting, fix by @jfy133)
 - [#274](https://github.com/nf-core/taxprofiler/pull/274) Substituted the samtools/bam2fq module with samtools/fastq module (fix by @sofstam)
 - [#275](https://github.com/nf-core/taxprofiler/pull/275) Replaced function used for error reporting to more Nextflow friendly method (fix by @jfy133)
@@ -37,7 +38,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | Tool     | Previous version | New version |
 | -------- | ---------------- | ----------- |
 | MultiQC  | 1.13             | 1.14        |
-| taxpasta | 0.2.3            | 0.4.0       |
+| taxpasta | 0.2.3            | 0.4.1       |
 
 ### `Deprecated`
 

diff --git a/modules.json b/modules.json
@@ -224,12 +224,12 @@
                     },
                     "taxpasta/merge": {
                         "branch": "master",
-                        "git_sha": "ef280893021dd1e877db163966022cabae06dfdb",
+                        "git_sha": "72230a81d2a1e61d171dbfc427d48d53ac7b1d86",
                         "installed_by": ["modules"]
                     },
                     "taxpasta/standardise": {
                         "branch": "master",
-                        "git_sha": "ef280893021dd1e877db163966022cabae06dfdb",
+                        "git_sha": "72230a81d2a1e61d171dbfc427d48d53ac7b1d86",
                         "installed_by": ["modules"]
                     },
                     "untar": {

diff --git a/modules/nf-core/taxpasta/merge/main.nf b/modules/nf-core/taxpasta/merge/main.nf
diff --git a/modules/nf-core/taxpasta/standardise/main.nf b/modules/nf-core/taxpasta/standardise/main.nf
diff --git a/nextflow.config b/nextflow.config
@@ -59,6 +59,7 @@ params {
     databases = null
 
     // FASTQ preprocessing
+    skip_preprocessing_qc            = false
     preprocessing_qc_tool            = 'fastqc'
 
     perform_shortread_qc             = false

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -56,6 +56,12 @@
             "description": "Common options across both long and short read preprocessing QC steps",
             "default": "",
             "properties": {
+                "skip_preprocessing_qc": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-forward",
+                    "description": "Specify to skip sequencing quality control of raw sequencing reads",
+                    "help": "Skipping running of FastQC or Falco maybe useful in cases where you are already running with preprocessed data (e.g. you are also skipping short/long read qc steps) that you already know the quality of"
+                },
                 "preprocessing_qc_tool": {
                     "type": "string",
                     "default": "fastqc",

diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf
@@ -144,13 +144,16 @@ workflow TAXPROFILER {
     */
     ch_input_for_fastqc = INPUT_CHECK.out.fastq.mix( INPUT_CHECK.out.nanopore )
 
-    if ( params.preprocessing_qc_tool == 'falco' ) {
-        FALCO ( ch_input_for_fastqc )
-        ch_versions = ch_versions.mix(FALCO.out.versions.first())
-    } else {
-        FASTQC ( ch_input_for_fastqc )
-        ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+    if ( !params.skip_preprocessing_qc ) {
+        if ( params.preprocessing_qc_tool == 'falco' ) {
+            FALCO ( ch_input_for_fastqc )
+            ch_versions = ch_versions.mix(FALCO.out.versions.first())
+        } else {
+            FASTQC ( ch_input_for_fastqc )
+            ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+        }
     }
+
     /*
         SUBWORKFLOW: PERFORM PREPROCESSING
     */
@@ -281,18 +284,19 @@ workflow TAXPROFILER {
     ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml'))
     ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
 
-    if ( params.preprocessing_qc_tool == 'falco' ) {
-        // only mix in files actually used by MultiQC
-        ch_multiqc_files = ch_multiqc_files.mix(FALCO.out.txt
-                            .map { meta, reports -> reports }
-                            .flatten()
-                            .filter { path -> path.name.endsWith('_data.txt')}
-                            .ifEmpty([]))
-    } else {
-        ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
+    if ( !params.skip_preprocessing_qc ) {
+        if ( params.preprocessing_qc_tool == 'falco' ) {
+            // only mix in files actually used by MultiQC
+            ch_multiqc_files = ch_multiqc_files.mix(FALCO.out.txt
+                                .map { meta, reports -> reports }
+                                .flatten()
+                                .filter { path -> path.name.endsWith('_data.txt')}
+                                .ifEmpty([]))
+        } else {
+            ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
+        }
     }
 
-
     if (params.perform_shortread_qc) {
         ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
     }