Merge pull request #72 from nf-core/initial-release-review-changes

Apply the seventh set of reviewer recommendations

README.md

@@ -25,16 +25,20 @@
 ## Introduction
 
 **nf-core/oncoanalyser** is a Nextflow implementation of the comprehensive cancer DNA/RNA analysis and reporting
-workflow from the Hartwig Medical Foundation. Both the Hartwig WGS/WTS workflow and targeted sequencing workflow are
-available in oncoanalyser. The targeted sequencing workflow has built-in support for the TSO500 panel and can also run
-custom panels with externally-generated normalisation data.
+workflow from the Hartwig Medical Foundation (HMF). The workflow starts from FASTQ or BAM and calls genomic variants,
+analyses transcript data, infers important biomarkers and features (e.g. TMB, HRD, mutational signatures, HLA alleles,
+oncoviral content, tissue of origin, etc), annotates and interprets results in the clinical context, and more.
+
+Both the HMF WGS/WTS workflow and targeted sequencing workflow are available in oncoanalyser. The targeted sequencing
+workflow has built-in support for the TSO500 panel and can also run custom panels with externally-generated
+normalisation data.
 
 The key analysis results for each sample are summarised and presented in an ORANGE report (summary page excerpt shown
 below from _[COLO829_wgts.orange_report.pdf](https://pub-29f2e5b2b7384811bdbbcba44f8b5083.r2.dev/oncoanalyser/other/example_report/COLO829_wgts.orange_report.pdf)_):
 
 <p align="center"><img width="750" src="docs/images/COLO829_wgts.orange_report.summary_section.png"></p>
 
-For detailed information on each component of the Hartwig workflow, please refer to
+For detailed information on each component of the HMF workflow, please refer to
 [hartwigmedical/hmftools](https://github.com/hartwigmedical/hmftools/).
 
 ## Pipeline summary

conf/test.config

@@ -27,7 +27,7 @@ params {
     max_time   = '6.h'
 
     // Input data
-    input = 'https://pub-349bcb8decb44bf7acbddf90b270a061.r2.dev/simulated_reads/24.0/samplesheets/fastq_eval.subject_a-subject_b.wgts.tndna_trna.1.csv'
+    input = 'https://github.com/nf-core/test-datasets/raw/oncoanalyser/samplesheet/fastq_eval.subject_a.wgts.tndna_trna.minimal.csv'
 
     // Reference data
     ref_data_virusbreakenddb_path = 'https://pub-349bcb8decb44bf7acbddf90b270a061.r2.dev/virusbreakend/virusbreakenddb_test-24.04.0.tar.gz'

conf/test_full.config

@@ -21,7 +21,7 @@ params {
     config_profile_description = 'Full test dataset to check pipeline function'
 
     // Input data for full size test
-    input = 'https://pub-349bcb8decb44bf7acbddf90b270a061.r2.dev/simulated_reads/24.0/samplesheets/fastq_eval.subject_a-subject_b.wgts.tndna_trna.1.csv'
+    input = 'https://github.com/nf-core/test-datasets/raw/oncoanalyser/samplesheet/fastq_eval.subject_a.wgts.tndna_trna.minimal.csv'
 
     // Analysis config
     mode              = 'wgts'

conf/test_stub.config

@@ -20,7 +20,7 @@ params {
     max_time   = '6.h'
 
     // Input data
-    input = 'https://pub-29f2e5b2b7384811bdbbcba44f8b5083.r2.dev/oncoanalyser/test_data/other/samplesheet.colo829_mini.dna_rna.grch38_hmf.stub.csv'
+    input = 'https://github.com/nf-core/test-datasets/raw/oncoanalyser/samplesheet/bam_eval.subject_a.wgts.tndna_trna.minimal.stub.csv'
 
     // Reference data
     genomes {

docs/output.md

@@ -112,9 +112,9 @@ _No outputs are published directly from STAR, see [Picard MarkDuplicates](#picar
 
 </details>
 
-[MarkDups](https://github.com/hartwigmedical/hmftools/tree/master/mark-dups) applies various alignment post-processing
-routines such as duplicate marking and unmapping of problematic regions. It can also handle UMIs when configured to do
-so.
+[MarkDups](https://github.com/hartwigmedical/hmftools/tree/mark-dups-v1.1.7/mark-dups) applies various alignment
+post-processing routines such as duplicate marking and unmapping of problematic regions. It can also handle UMIs when
+configured to do so.
 
 _MarkDups is only run on DNA alignments_
 

modules/local/gridss/index/environment.yml

@@ -4,4 +4,4 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::gridss=2.13.2=hdfd78af_3
+  - bioconda::gridss=2.13.2=h50ea8bc_3

modules/local/markdups/meta.yml

@@ -6,8 +6,8 @@ keywords:
 tools:
   - MarkDups:
       description: Identify and mark duplicate reads ifrom alignment data
-      homepage: https://github.com/hartwigmedical/hmftools/tree/master/mark-dups
-      documentation: https://github.com/hartwigmedical/hmftools/tree/master/mark-dups
+      homepage: https://github.com/hartwigmedical/hmftools/tree/mark-dups-v1.1.7/mark-dups
+      documentation: https://github.com/hartwigmedical/hmftools/tree/mark-dups-v1.1.7/mark-dups
       licence: ["GPL v3"]
 input:
   - meta:

modules/local/sage/append/environment.yml

@@ -4,4 +4,4 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::hmftools-sage=3.4.3
+  - bioconda::hmftools-sage=3.4.4

modules/local/sage/germline/environment.yml

@@ -4,4 +4,4 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::hmftools-sage=3.4.3
+  - bioconda::hmftools-sage=3.4.4

modules/local/sage/somatic/environment.yml

@@ -4,4 +4,4 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::hmftools-sage=3.4.3
+  - bioconda::hmftools-sage=3.4.4

subworkflows/local/utils_nfcore_oncoanalyser_pipeline/main.nf

@@ -176,9 +176,12 @@ def genomeExistsError() {
 // Generate methods description for MultiQC
 //
 def toolCitationText() {
-    // TODO nf-core: Optionally add in-text citation tools to this list.
-    // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "Tool (Foo et al. 2023)" : "",
-    // Uncomment function in methodsDescriptionText to render in MultiQC report
+    def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" +
+        "  The toolCitationText function is not currently implemented and should not be used." +
+        "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
+    error(error_string)
+
+    /*
     def citation_text = [
             "Tools used in the workflow included:",
             "FastQC (Andrews 2010),",
@@ -187,6 +190,7 @@ def toolCitationText() {
         ].join(' ').trim()
 
     return citation_text
+    */
 }
 
 def toolBibliographyText() {