Address review comments

.nf-core.yml

@@ -21,4 +21,4 @@ template:
   name: rnadnavar
   org: nf-core
   outdir: .
-  version: "1.0"
+  version: "1.0.0"

CHANGELOG.md

@@ -3,12 +3,27 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## v1.0dev - [2026-06-23]
+## 1.0.0 - [2026-06-23]
+
+Initial release of nf-core/rnadnavar.
 
 ### `Added`
 
+- RNA and DNA integrated analysis pipeline for somatic mutation detection
+- Support for multiple variant callers (Mutect2, Strelka2, SAGE)
+- Comprehensive preprocessing with GATK4 best practices
+- VEP annotation and filtering capabilities
+- Consensus variant calling approach
+- RNA-specific filtering and realignment steps
+- MultiQC reporting and quality control
+- Support for both BWA-MEM and STAR alignment
 - Added support for optional Mutect2 force-calling inputs (`mutect2_alleles` and `mutect2_alleles_tbi`)
 - Added `conf/empty.config` to support strict-syntax-safe config loading
+- Added full pipeline nf-test (`test_full.nf.test`) and test snapshots
+- Added VCF simple test data for annotation testing
+- Added GitHub Actions for automated testing with nf-test
+- Added support for multiple template versions (3.2.0, 3.2.1, 3.3.1)
+- Restored rnadnavar logo in pipeline output with color support
 
 ### `Fixed`
 
@@ -23,6 +38,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed non-deterministic nf-test outputs and updated snapshots accordingly
 - Fixed `includeConfig` handling in `nextflow.config` for newer Nextflow strict syntax
 - Fixed VEP cache initialisation and updated unzip-dependent wiring
+- Fixed help text and documentation URLs
+- Fixed pipeline-specific parameter descriptions in schema
+- Fixed workflow path references and documentation links
+- Fixed consensus module caller value to avoid warnings
+- Fixed VEP cache handling and empty RNA edits processing
+- Fixed issue with run_consensus.R plotting
+- **Major Fix**: Resolved ConcurrentModificationException error from Java processes
+- Fixed local module implementations and configurations
+- Fixed subworkflow naming and structure issues
+- Fixed SAGE variant caller integration and configuration
+- Fixed nf-core subworkflow integrations
 
 ### `Changed`
 
@@ -33,111 +59,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Updated local GATK and Picard integrations, including restored patches for `picard/filtersamreads` and `gatk4/splitncigarreads`
 - Replaced deprecated tabix usage with current htslib-based handling where appropriate
 - Updated nf-test plugin configuration and test snapshots
-
-### `Removed`
-
-- Removed obsolete tabix modules and deprecated module usage paths
-- Removed leftover config and workflow parameters no longer used after the template/module refresh (for example `hook_url`)
-
----
-
-## v1.0dev - [2025-08-12]
-
-### `Added`
-
-- Added full pipeline nf-test (`test_full.nf.test`)
-- Added test snapshots
-- Restored rnadnavar logo in pipeline output with color support
-
-### `Fixed`
-
-- Fixed help text and documentation URLs
-- Fixed pipeline-specific parameter descriptions in schema
-- Fixed workflow path references and documentation links
-- Fixed consensus module caller value to avoid warnings
-- Fixed VEP cache handling and empty RNA edits processing
-- Fixed issue with run_consensus.R plotting
-
-### `Changed`
-
 - Cleaned up code formatting and style across configuration files
 - Updated test configurations and `.nftignore` files
-- Improved subworkflow organization and consistency (typos, remove unused code blocks, spacing, comments, readability)
+- Improved subworkflow organization and consistency
 - Massive speed up to run_consensus.R
 - Migrated consensus module from custom Docker container to Seqera Wave containers
+- Updated all nf-core modules to latest versions
+- Updated template to nf-core/tools version 3.3.1
+- Updated GitHub workflows and CI/CD configurations
+- Updated Nextflow minimum version requirement from >=23.04.0 to >=24.04.2
 
 ### `Removed`
 
+- Removed obsolete tabix modules and deprecated module usage paths
+- Removed leftover config and workflow parameters no longer used after the template/module refresh (for example `hook_url`)
 - Cleaned up unused VCFlib and VT variant processing modules
 - Removed obsolete module configurations and test files
-
----
-
-## v1.0dev - [2025-08-01]
-
-### `Added`
-
-- Added VCF simple test data for annotation testing
-- Added comprehensive nf-test framework integration
-- Added GitHub Actions for automated testing with nf-test
-- Added support for multiple template versions (3.2.0, 3.2.1, 3.3.1)
-
-### `Fixed`
-
-- **Major Fix**: Resolved ConcurrentModificationException error from Java processes
-- Fixed local module implementations and configurations
-- Fixed subworkflow naming and structure issues
-- Fixed indentation and formatting issues across multiple files
-- Fixed redundancies in workflow logic
-- Fixed SAGE variant caller integration and configuration
-- Fixed local utilities and helper functions
-- Fixed nf-core subworkflow integrations
-
-### `Changed`
-
-- **Massive Module Update**: Updated all nf-core modules to latest versions including:
-  - bcftools/sort and bcftools/stats
-  - BWA, BWA-MEM2, and DRAGMAP aligners
-  - GATK4 modules (applybqsr, baserecalibrator)
-  - FastQC, FastP, and other QC tools
-  - VEP annotation modules
-  - All associated test files and metadata
-- Updated VEP cache version parameter from string '110' to integer 110
-- Cleaned up main workflow structure and organization
-- Cleaned up local subworkflows and removed redundant code
-- Cleaned up configuration files and parameter definitions
-- Updated template to nf-core/tools version 3.3.1
-- Reorganized and cleaned up local modules
-- Updated GitHub workflows and CI/CD configurations
-- Added new configuration parameters: `help_full`, `show_hidden`, `trace_report_suffix`, `modules_testdata_base_path`
-- Improved parameter organization and formatting in nextflow.config
-
-### `Dependencies`
-
-- Updated all nf-core modules to their latest stable versions
-- Updated container images and Conda environments for all processes
-- **Updated Nextflow minimum version requirement from >=23.04.0 to >=24.04.2**
-- Updated nf-core template to version 3.3.1
-
-### `Deprecated`
-
 - Removed redundant workflow components
-- Cleaned up deprecated configuration parameters
-- Removed obsolete test configurations
-
----
-
-## Initial Release
-
-Initial release of nf-core/rnadnavar, created with the [nf-core](https://nf-co.re/) template.
-
-### `Added`
-
-- RNA and DNA integrated analysis pipeline for somatic mutation detection
-- Support for multiple variant callers (Mutect2, Strelka2, SAGE)
-- Comprehensive preprocessing with GATK4 best practices
-- VEP annotation and filtering capabilities
-- Consensus variant calling approach
-- RNA-specific filtering and realignment steps
-- MultiQC reporting and quality control
-- Support for both BWA-MEM and STAR alignment

assets/multiqc_config.yml

@@ -3,9 +3,7 @@ custom_logo_url: https://github.com/nf-core/rnadnavar/
 custom_logo_title: "nf-core/rnadnavar"
 
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/rnadnavar/releases/tag/1.0" target="_blank">nf-core/rnadnavar</a>
-  analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/rnadnavar/1.0/docs/output" target="_blank">documentation</a>.
+  This report has been generated by the <a href="https://github.com/nf-core/rnadnavar/releases/tag/1.0.0" target="_blank">nf-core/rnadnavar</a> analysis pipeline. For information about how to interpret these results, please see the <a href="https://nf-co.re/rnadnavar/1.0.0/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-rnadnavar-methods-description":
     order: -1000
@@ -59,7 +57,7 @@ extra_fn_clean_exts:
     pattern: "^.*.(md|recal).mosdepth.(global|region).dist"
     module: mosdepth
 
-sample_names_replace_regex: True
+sample_names_replace_regex: true
 sample_names_replace:
   "\\.[0-9]{4}$": ".md" # should match ".0001" but only at the end of strings for module Markduplicates/EstimateLibraryComplexity
   module: picard

bin/filter_rna_mutations.py

@@ -18,15 +18,15 @@ def argparser():
     parser = argparse.ArgumentParser(description="")
     parser.add_argument("--maf", help="Input MAF file")
     parser.add_argument("--maf_realign", help="Input MAF file after a second pass")
-    parser.add_argument("--pon2", help="Path to optional second binary pon")
-    parser.add_argument("--pon", help="Path to binary pon")
+    parser.add_argument("--secondary-pon", dest="secondary_pon", help="Path to optional secondary RNA PoN binary generated for RNA-specific filtering (see DOI: 10.1016/j.cels.2018.03.002)")
+    parser.add_argument("--reference-pon", dest="reference_pon", help="Path to primary RNA PoN binary generated for RNA-specific filtering (see DOI: 10.1016/j.cels.2018.03.002)")
     parser.add_argument("--whitelist", help="BED file with variants to keep (CHROM POS REF ALT)")
     parser.add_argument("--output", help="output file name")
     parser.add_argument("--out_suffix", help="Suffix for intermediate output", default="withRNAfilters")
-    parser.add_argument("--ref", help="FASTA - e.g. HG38")
-    parser.add_argument("--refname", help="e.g. hg38", default="hg38")
-    parser.add_argument("--ref2", help="FASTA - e.g. hg19 (hs37d5)")
-    parser.add_argument("--refname2", help="e.g. HG19", default="hg19")
+    parser.add_argument("--reference-fasta", dest="reference_fasta", help="Primary reference FASTA - e.g. hg38")
+    parser.add_argument("--reference-name", dest="reference_name", help="Primary reference name - e.g. hg38", default="hg38")
+    parser.add_argument("--secondary-reference-fasta", dest="secondary_reference_fasta", help="Secondary reference FASTA - e.g. hg19 (hs37d5)")
+    parser.add_argument("--secondary-reference-name", dest="secondary_reference_name", help="Secondary reference name - e.g. hg19", default="hg19")
     parser.add_argument("--rnaedits", help="BED file(s) with known RNA editing events separated by space", nargs="+", default=[])
     parser.add_argument("--thr", default=-2.8)
     parser.add_argument("--chain", help="Chain file")
@@ -115,16 +115,16 @@ def extract_coords(df):
     return coords
 
 
-def run_capy(M, pon, ref, thr, chroms, suffix="_hg38", refname2="hg19"):
+def run_capy(M, pon, reference_fasta, thr, chroms, suffix="_hg38", secondary_reference_name="hg19"):
     """
     Runs CApy with RNA PoN generated with tokenizer (https://github.com/getzlab/aggregate_tokens_files_TOOL)
     """
     print("- Running CApy" + suffix)
     chrom = "Chromosome"
     start = "Start_Position"
-    if refname2:
-        chrom += "_" + refname2
-        start += "_" + refname2
+    if secondary_reference_name:
+        chrom += "_" + secondary_reference_name
+        start += "_" + secondary_reference_name
     # Remove alt contigs
     M = M[M[chrom].isin(chroms)]
     # Perform string replacements and type casting
@@ -138,7 +138,7 @@ def run_capy(M, pon, ref, thr, chroms, suffix="_hg38", refname2="hg19"):
     M = M.astype({"chr": "int32", "pos": "int32"})
     M.reset_index(inplace=True, drop=True)
     # Get PoN scores
-    pon_scores = mut.filter_mutations_against_token_PoN(M=M, ponfile=pon, ref=ref)
+    pon_scores = mut.filter_mutations_against_token_PoN(M=M, ponfile=pon, ref=reference_fasta)
     assert len(pon_scores) == M.shape[0], "PoN scores are not same length as nrow"
     # Create a DataFrame with the necessary columns including PoN scores and threshold
     pon_scores_df = pd.DataFrame({
@@ -239,14 +239,14 @@ def main():
         if calls.empty:
             results[idx] = calls
             continue
-        if "Chromosome"+args.refname2 in calls.columns:
-            calls.drop(["Chromosome"+args.refname2, "Start_Position"+args.refname2], axis=1, inplace=True)
+        if "Chromosome"+args.secondary_reference_name in calls.columns:
+            calls.drop(["Chromosome"+args.secondary_reference_name, "Start_Position"+args.secondary_reference_name], axis=1, inplace=True)
         # RNA panel of normals
-        if args.pon2 is not None and args.chain is not None and args.ref2 is not None:
-            calls = add_coords2_with_liftover(calls, chain_file=args.chain,ref1=args.refname,ref2=args.refname2)
-            calls = run_capy(M=calls, pon=args.pon2, ref=args.ref2, thr=args.thr, suffix='_'+args.refname2, chroms=chroms, refname2=args.refname2)
-        if args.pon:
-            calls = run_capy(M=calls, pon=args.pon,  ref=args.ref,  thr=args.thr, suffix='_'+args.refname, chroms=chroms, refname2=False)
+        if args.secondary_pon is not None and args.chain is not None and args.secondary_reference_fasta is not None:
+            calls = add_coords2_with_liftover(calls, chain_file=args.chain,ref1=args.reference_name,ref2=args.secondary_reference_name)
+            calls = run_capy(M=calls, pon=args.secondary_pon, reference_fasta=args.secondary_reference_fasta, thr=args.thr, suffix='_'+args.secondary_reference_name, chroms=chroms, secondary_reference_name=args.secondary_reference_name)
+        if args.reference_pon:
+            calls = run_capy(M=calls, pon=args.reference_pon, reference_fasta=args.reference_fasta, thr=args.thr, suffix='_'+args.reference_name, chroms=chroms, secondary_reference_name=False)
         # Annotate known RNA editing
         if args.rnaedits:
             rnadbs = check_rnaediting(args.rnaedits)

conf/modules/alignment/bam_align.config

@@ -139,7 +139,7 @@ process { // bam_align
     // HISAT2 for realignment
     withName: '.*:FASTQ_ALIGN_HISAT2:HISAT2_ALIGN' {
         ext.prefix = {"${meta.sample}"}
-        ext.args   = {meta.status < 2 ? "--met-stderr --new-summary --no-spliced-alignment" : "--met-stderr --new-summary " }
+        ext.args   = {meta.status < 2 ? "--temp-directory \${PWD} --met-stderr --new-summary --no-spliced-alignment" : "--temp-directory \${PWD} --met-stderr --new-summary " }
         publishDir = [
             [
                 path: { "${params.outdir}/report/hisat2/${meta.patient}/${meta.id}" },

conf/modules/consensus/vcf_consensus.config

@@ -15,6 +15,13 @@
 
 process {  // consensus
 
+    withName: "GUNZIP_VCF2MAF" {
+        // No need to publish decompress VCF, this is just an intermediary step
+        publishDir = [
+            enabled: false
+        ]
+    }
+
     withName: "VCF2MAF" {
         ext.args =  { [
             "--inhibit-vep",

conf/modules/filtering/maf_filtering.config

@@ -31,13 +31,13 @@ process {  // maf filtering
 
     withName: 'RNA_FILTERING' {
             ext.prefix       = {"${meta.id}.rna_filt"}
-            ext.args   = { [params.rnaedits?       "--rnaedits ${params.rnaedits}"  : "",
-                            params.rna_pon?        "--pon ${params.rna_pon}"        : "",
-                            params.chain?          "--chain ${params.chain}"        : "",
-                            params.fasta2?         "--ref2 ${params.fasta2}"        : "",
-                            params.rna_pon2?       "--pon2 ${params.rna_pon2}"      : "",
-                            params.refname2?       "--refname2 ${params.refname2}"  : "",
-                            params.refname?        "--refname ${params.refname}"    : ""
+            ext.args   = { [params.rnaedits?                  "--rnaedits ${params.rnaedits}"                                  : "",
+                            params.reference_pon?             "--reference-pon ${params.reference_pon}"                        : "",
+                            params.chain?                     "--chain ${params.chain}"                                        : "",
+                            params.secondary_reference_fasta? "--secondary-reference-fasta ${params.secondary_reference_fasta}" : "",
+                            params.secondary_pon?             "--secondary-pon ${params.secondary_pon}"                        : "",
+                            params.secondary_reference_name?  "--secondary-reference-name ${params.secondary_reference_name}"   : "",
+                            params.reference_name?            "--reference-name ${params.reference_name}"                      : ""
                             ].join(' ').trim() }
 
             publishDir       = [

conf/test_full.config

@@ -36,9 +36,9 @@ params {
     germline_resource    = "https://raw.githubusercontent.com/nf-core/test-datasets/rnadnavar/reference/chr7_hg38/af-only-gnomad.hg38.chr7.mini2.vcf.gz"
     no_intervals         = true
     gtf                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/rnadnavar/reference/chr7_hg38/gencode.v36.annotation.chr7.mini.gtf'
-    sage_highconfidence  = 'https://github.com/nf-core/test-datasets/raw/rnadnavar/resources/hmftools/variants/HighConfidence.38.bed.gz'
-    sage_actionablepanel = 'https://github.com/nf-core/test-datasets/raw/rnadnavar/resources/hmftools/variants/ActionableCodingPanel.38.bed.gz'
-    sage_knownhotspots   = 'https://github.com/nf-core/test-datasets/raw/rnadnavar/resources/hmftools/variants/KnownHotspots.somatic.38.vcf.gz'
+    sage_high_confidence  = 'https://github.com/nf-core/test-datasets/raw/rnadnavar/resources/hmftools/variants/HighConfidence.38.bed.gz'
+    sage_actionable_panel = 'https://github.com/nf-core/test-datasets/raw/rnadnavar/resources/hmftools/variants/ActionableCodingPanel.38.bed.gz'
+    sage_known_hotspots   = 'https://github.com/nf-core/test-datasets/raw/rnadnavar/resources/hmftools/variants/KnownHotspots.somatic.38.vcf.gz'
     sage_ensembl_dir     = 'https://github.com/nf-core/test-datasets/raw/rnadnavar/resources/hmftools/common/sage_ensembl.zip'
     vep_cache            = 'https://github.com/nf-core/test-datasets/raw/rnadnavar/resources/vep/vep_hs.zip'
     vep_cache_version    = 999

modules.json

@@ -320,6 +320,11 @@
                         "git_sha": "1c43a7e22f04cf19c9f9d3de7e7e5a3addd9382a",
                         "installed_by": ["modules"]
                     },
+                    "vcf2maf": {
+                        "branch": "master",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "installed_by": ["modules"]
+                    },
                     "vcftools": {
                         "branch": "master",
                         "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",

modules/local/consensus/main.nf

@@ -4,7 +4,7 @@ process RUN_CONSENSUS {
 
     conda "${moduleDir}/environment.yml"
     container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
-        ? 'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/ed/ed5e97c2fc53fb46675998f4f5472807f217043994cd4f490b0eb8887c31ceed/data'
+        ? 'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/00/0003a3962c416b4c458909d28e343758adf347e614507137b70ac5e4a3c094bb/data'
         : 'community.wave.seqera.io/library/bioconductor-complexheatmap_bioconductor-rtracklayer_r-data.table_r-dplyr_pruned:b2d4632cc9bf5c6e'}"
 
     input:

modules/local/maf_rna_filtering/main.nf

@@ -23,7 +23,7 @@ process RNA_FILTERING {
         """
         filter_rna_mutations.py \\
             --maf $maf \\
-            --ref $fasta \\
+            --reference-fasta $fasta \\
             --output ${prefix}.maf \\
             $maf_realign_opt \\
             $args