Merge pull request #68 from nf-core/initial-release-review-changes

Apply the fifth set of reviewer recommendations

docs/usage.md

@@ -69,9 +69,9 @@ Currently only non-interleaved paired-end reads are accepted as FASTQ input.
 
 ```csv title="samplesheet.csv"
 group_id,subject_id,sample_id,sample_type,sequence_type,filetype,info,filepath
-P1__wgts,P1,SA,normal,dna,fastq,library_id:SA_library;lane:001,/path/to/P1.SA.normal.dna.wgs.001.R1.fastq.gz;/path/to/P1.SA.normal.dna.wgs.001.R2.fastq.gz
-P1__wgts,P1,SB,tumor,dna,fastq,library_id:SB_library;lane:001,/path/to/P1.SB.tumor.dna.wgs.001.R1.fastq.gz;/path/to/P1.SB.tumor.dna.wgs.001.R2.fastq.gz
-P1__wgts,P1,SC,tumor,rna,fastq,library_id:SC_library;lane:001,/path/to/P1.SC.tumor.rna.wts.001.R1.fastq.gz;/path/to/P1.SC.tumor.rna.wts.001.R2.fastq.gz
+P1_wgts,P1,SA,normal,dna,fastq,library_id:SA_library;lane:001,/path/to/P1.SA.normal.dna.wgs.001.R1.fastq.gz;/path/to/P1.SA.normal.dna.wgs.001.R2.fastq.gz
+P1_wgts,P1,SB,tumor,dna,fastq,library_id:SB_library;lane:001,/path/to/P1.SB.tumor.dna.wgs.001.R1.fastq.gz;/path/to/P1.SB.tumor.dna.wgs.001.R2.fastq.gz
+P1_wgts,P1,SC,tumor,rna,fastq,library_id:SC_library;lane:001,/path/to/P1.SC.tumor.rna.wts.001.R1.fastq.gz;/path/to/P1.SC.tumor.rna.wts.001.R2.fastq.gz
 ```
 
 #### BAM
@@ -94,30 +94,30 @@ Please note there are other essential requirements around the use of BAMs as inp
 
 ```csv title="samplesheet.csv"
 group_id,subject_id,sample_id,sample_type,sequence_type,filetype,filepath
-P1__wgts,P1,SA,normal,dna,bam,/path/to/P1.SA.normal.dna.wgs.bam
-P1__wgts,P1,SB,tumor,dna,bam,/path/to/P1.SB.tumor.dna.wgs.bam
-P1__wgts,P1,SC,tumor,rna,bam,/path/to/P1.SC.tumor.rna.wts.bam
+P1_wgts,P1,SA,normal,dna,bam,/path/to/P1.SA.normal.dna.wgs.bam
+P1_wgts,P1,SB,tumor,dna,bam,/path/to/P1.SB.tumor.dna.wgs.bam
+P1_wgts,P1,SC,tumor,rna,bam,/path/to/P1.SC.tumor.rna.wts.bam
 ```
 
 ### Multiple lanes
 
 ```csv title="samplesheet.csv"
 group_id,subject_id,sample_id,sample_type,sequence_type,filetype,info,filepath
-P1__wgts,P1,SA,normal,dna,fastq,library_id:SA_library;lane:001,/path/to/P1.SA.normal.dna.wgs.001.R1.fastq.gz;/path/to/P1.SA.normal.dna.wgs.001.R2.fastq.gz
-P1__wgts,P1,SA,normal,dna,fastq,library_id:SA_library;lane:002,/path/to/P1.SA.normal.dna.wgs.002.R1.fastq.gz;/path/to/P1.SA.normal.dna.wgs.002.R2.fastq.gz
-P1__wgts,P1,SB,tumor,dna,fastq,library_id:SB_library;lane:001,/path/to/P1.SB.tumor.dna.wgs.001.R1.fastq.gz;/path/to/P1.SB.tumor.dna.wgs.001.R2.fastq.gz
-P1__wgts,P1,SB,tumor,dna,fastq,library_id:SB_library;lane:002,/path/to/P1.SB.tumor.dna.wgs.002.R1.fastq.gz;/path/to/P1.SB.tumor.dna.wgs.002.R2.fastq.gz
-P1__wgts,P1,SC,tumor,rna,fastq,library_id:SC_library;lane:001,/path/to/P1.SC.tumor.rna.wts.001.R1.fastq.gz;/path/to/P1.SC.tumor.rna.wts.001.R2.fastq.gz
+P1_wgts,P1,SA,normal,dna,fastq,library_id:SA_library;lane:001,/path/to/P1.SA.normal.dna.wgs.001.R1.fastq.gz;/path/to/P1.SA.normal.dna.wgs.001.R2.fastq.gz
+P1_wgts,P1,SA,normal,dna,fastq,library_id:SA_library;lane:002,/path/to/P1.SA.normal.dna.wgs.002.R1.fastq.gz;/path/to/P1.SA.normal.dna.wgs.002.R2.fastq.gz
+P1_wgts,P1,SB,tumor,dna,fastq,library_id:SB_library;lane:001,/path/to/P1.SB.tumor.dna.wgs.001.R1.fastq.gz;/path/to/P1.SB.tumor.dna.wgs.001.R2.fastq.gz
+P1_wgts,P1,SB,tumor,dna,fastq,library_id:SB_library;lane:002,/path/to/P1.SB.tumor.dna.wgs.002.R1.fastq.gz;/path/to/P1.SB.tumor.dna.wgs.002.R2.fastq.gz
+P1_wgts,P1,SC,tumor,rna,fastq,library_id:SC_library;lane:001,/path/to/P1.SC.tumor.rna.wts.001.R1.fastq.gz;/path/to/P1.SC.tumor.rna.wts.001.R2.fastq.gz
 ```
 
 ### Multiple patients
 
 ```csv title="samplesheet.csv"
 group_id,subject_id,sample_id,sample_type,sequence_type,filetype,info,filepath
-P1__wgts,P1,SA,normal,dna,fastq,library_id:SA_library;lane:001,/path/to/P1.SA.normal.dna.wgs.001.R1.fastq.gz;/path/to/P1.SA.normal.dna.wgs.001.R2.fastq.gz
-P1__wgts,P1,SB,tumor,dna,fastq,library_id:SB_library;lane:001,/path/to/P1.SB.tumor.dna.wgs.001.R1.fastq.gz;/path/to/P1.SB.tumor.dna.wgs.001.R2.fastq.gz
-P2__wgts,P2,SA,normal,dna,fastq,library_id:SA_library;lane:001,/path/to/P2.SA.normal.dna.wgs.001.R1.fastq.gz;/path/to/P2.SA.normal.dna.wgs.001.R2.fastq.gz
-P2__wgts,P2,SB,tumor,dna,fastq,library_id:SB_library;lane:001,/path/to/P2.SB.tumor.dna.wgs.001.R1.fastq.gz;/path/to/P2.SB.tumor.dna.wgs.001.R2.fastq.gz
+P1_wgts,P1,SA,normal,dna,fastq,library_id:SA_library;lane:001,/path/to/P1.SA.normal.dna.wgs.001.R1.fastq.gz;/path/to/P1.SA.normal.dna.wgs.001.R2.fastq.gz
+P1_wgts,P1,SB,tumor,dna,fastq,library_id:SB_library;lane:001,/path/to/P1.SB.tumor.dna.wgs.001.R1.fastq.gz;/path/to/P1.SB.tumor.dna.wgs.001.R2.fastq.gz
+P2_wgts,P2,SA,normal,dna,fastq,library_id:SA_library;lane:001,/path/to/P2.SA.normal.dna.wgs.001.R1.fastq.gz;/path/to/P2.SA.normal.dna.wgs.001.R2.fastq.gz
+P2_wgts,P2,SB,tumor,dna,fastq,library_id:SB_library;lane:001,/path/to/P2.SB.tumor.dna.wgs.001.R1.fastq.gz;/path/to/P2.SB.tumor.dna.wgs.001.R2.fastq.gz
 ```
 
 ### Column descriptions
@@ -191,12 +191,13 @@ The above pipeline run specified with a params file in yaml format:
 nextflow run nf-core/oncoanalyser -profile docker -params-file params.yaml
 ```
 
-with `params.yaml` containing:
+with `params.yaml` containing the following as an example:
 
 ```yaml
+mode: 'wgts'
+genome: 'GRCh38_hmf'
 input: './samplesheet.csv'
 outdir: './results/'
-genome: 'GRCh37'
 <...>
 ```
 
@@ -216,7 +217,7 @@ It is a good idea to specify a pipeline version when running the pipeline on you
 
 First, go to the [nf-core/oncoanalyser releases page](https://github.com/nf-core/oncoanalyser/releases) and find the latest pipeline version - numeric only (eg. `1.0.0`). Then specify this when running the pipeline with `-r` (one hyphen) - eg. `-r 1.0.0`. Of course, you can switch to another version by changing the number after the `-r` flag.
 
-This version number will be logged in reports when you run the pipeline, so that you'll know what you used when you look back in the future. For example, at the bottom of the MultiQC reports.
+This version number will be logged in reports when you run the pipeline, so that you'll know what you used when you look back in the future. For example, in the `<outdir>/pipeline_info/software_versions.yml` file.
 
 To further assist in reproducbility, you can share and re-use [parameter files](#running-the-pipeline) to repeat pipeline runs with the same settings without having to write out a command with every single parameter.
 
@@ -255,9 +256,9 @@ that all upstream variant calling can be skipped:
 
 ```csv title='samplesheet.existing_purple.csv'
 group_id,subject_id,sample_id,sample_type,sequence_type,filetype,filepath
-P1__wgts,P1,SA,normal,dna,bam,/path/to/P1.SA.normal.dna.wgs.bam
-P1__wgts,P1,SB,tumor,dna,bam,/path/to/P1.SB.tumor.dna.wgs.bam
-P1__wgts,P1,SB,tumor,dna,purple_dir,/path/to/P1.purple_dir/
+P1_wgts,P1,SA,normal,dna,bam,/path/to/P1.SA.normal.dna.wgs.bam
+P1_wgts,P1,SB,tumor,dna,bam,/path/to/P1.SB.tumor.dna.wgs.bam
+P1_wgts,P1,SB,tumor,dna,purple_dir,/path/to/P1.purple_dir/
 ```
 
 :::note
@@ -334,9 +335,9 @@ indices, reference data, and databases required to run a WGTS analysis for tumor
 
 ```csv title="samplesheet.csv"
 group_id,subject_id,sample_id,sample_type,sequence_type,filetype,filepath
-P1__wgts,P1,SA,normal,dna,bam,/path/to/P1.SA.normal.dna.wgs.bam
-P1__wgts,P1,SB,tumor,dna,bam,/path/to/P1.SB.tumor.dna.wgs.bam
-P1__wgts,P1,SC,tumor,rna,bam,/path/to/P1.SC.tumor.rna.wts.bam
+P1_wgts,P1,SA,normal,dna,bam,/path/to/P1.SA.normal.dna.wgs.bam
+P1_wgts,P1,SB,tumor,dna,bam,/path/to/P1.SB.tumor.dna.wgs.bam
+P1_wgts,P1,SC,tumor,rna,bam,/path/to/P1.SC.tumor.rna.wts.bam
 ```
 
 ```bash

modules/local/pave/germline/main.nf

@@ -2,8 +2,6 @@
 //  - https://github.com/hartwigmedical/pipeline5/blob/v5.33/cluster/src/main/java/com/hartwig/pipeline/tertiary/pave/PaveGermline.java#L36-L41
 //  - https://github.com/hartwigmedical/pipeline5/blob/v5.33/cluster/src/main/java/com/hartwig/pipeline/tertiary/pave/PaveArguments.java#L31-L43
 
-import nextflow.Nextflow
-
 process PAVE_GERMLINE {
     tag "${meta.id}"
     label 'process_medium'
@@ -43,8 +41,7 @@ process PAVE_GERMLINE {
     } else if (genome_ver.toString() == '38') {
         gnomad_args = "-gnomad_freq_dir ${gnomad_resource}"
     } else {
-        log.error "got bad genome version: ${genome_ver}"
-        Nextflow.exit(1)
+        error "got bad genome version: ${genome_ver}"
     }
 
     """

modules/local/pave/somatic/main.nf

@@ -1,5 +1,3 @@
-import nextflow.Nextflow
-
 process PAVE_SOMATIC {
     tag "${meta.id}"
     label 'process_medium'
@@ -44,8 +42,7 @@ process PAVE_SOMATIC {
         pon_filters = 'HOTSPOT:5:5;PANEL:2:5;UNKNOWN:2:0'
         gnomad_args = "-gnomad_freq_dir ${gnomad_resource}"
     } else {
-        log.error "got bad genome version: ${genome_ver}"
-        Nextflow.exit(1)
+        error "got bad genome version: ${genome_ver}"
     }
 
     // Targeted mode

nextflow_schema.json

@@ -47,11 +47,12 @@
                 "mode": {
                     "type": "string",
                     "description": "Workflow run mode.",
-                    "fa_icon": "fas fa-diagram-project"
+                    "fa_icon": "fas fa-diagram-project",
+                    "pattern": "^(wgts|targeted)"
                 },
                 "panel": {
                     "type": "string",
-                    "description": "Name of pane to use.",
+                    "description": "Name of panel to use.",
                     "fa_icon": "fas fa-book"
                 },
                 "force_genome": {