Merge branch 'main' into 0.7.0

Author: qclayssen

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.6.0
+current_version = 0.6.3
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>[a-z0-9+]+)

CHANGELOG.md

@@ -15,6 +15,56 @@ Initial release of umccr/sash, created with the [nf-core](https://nf-co.re/) tem
 
 ### `Deprecated`
 
+## [0.6.3] - 2025-10-07
+
+### Added
+
+- Validate input files in `prepare_run`: warn when optional files are missing; fail when mandatory files are missing. (see PR #29)
+
+## [0.6.2] - 2025-10-01
+
+### Changed
+
+- Made Dragen HRD file optional in the cancer report
+
+### Dependencies
+
+| Tool | Old | New |
+|------|-----|-----|
+| bolt | 0.2.15 | 0.2.17 |
+| gpgr | 2.2.0 | 2.2.1 |
+
+## [0.6.1] - 2025-09-16
+
+### Added
+
+- Support for oncoanalyser v2.2.0 data structure
+- PAVE MNV filtering to remove variants with MNVTAG annotations (see [discussion](https://github.com/umccr/sash/issues/19))
+
+### Changed
+
+- **Reference data updates:**
+  - Updated to hmf_pipeline_resources.38_v2.2.0--3
+- **Process update:**
+  - eSVee parameter updates
+  - PAVE parameter updates for v1.8 compatibility
+- Updated prepare_input paths for oncoanalyser v2.2.0 structure
+
+### Removed
+
+- Unused reference data files (gridss_region_blocklist, lilac, orange, sigs_signatures, disease_ontology)
+
+### Dependencies
+
+| Tool | Old | New |
+|------|-----|-----|
+| eSVee | 1.0.3 | 1.1.2 |
+| LINX | 2.0.2 | 2.1 |
+| PAVE | 1.7.1 | 1.8 |
+| PURPLE | 4.1 | 4.2 |
+| bolt | 0.2.14 | 0.2.15 |
+| gpgr | 2.1.3 | 2.2.0 |
+
 ## [0.6.0] - 2025-06-04
 
 ### Added
@@ -38,7 +88,7 @@ Initial release of umccr/sash, created with the [nf-core](https://nf-co.re/) tem
   - PR (Paired-Read) → DF (Discordant Fragments)
 - Linx v1.25 → v2.0 (affects all Linx reports/files)
 - Purple v4.0.1 → v4.1.0
-  - MSI calculation relay on SAGE-specific tags #7
+  - MSI calculation relies on SAGE-specific tags (#7)
   - (reverted) Circos have link sizes dependent on the size of SV #6
 - Filter PoN SV in cancer report tables #8
 

README.md

@@ -28,6 +28,7 @@ The general processes `sash` runs include:
 - PURPLE for TMB, MSI, CNV calling, and purity / ploidy estimation
 - HRDetect and CHORD for HRD inference
 - MutationalPatterns to fit mutational signatures
+- PAVE for somatic variant annotation with MNV filtering (see [discussion](https://github.com/umccr/sash/issues/19))
 
 ## Requirements
 
@@ -55,3 +56,9 @@ nextflow run scwatts/sash \
   --ref_data_path /path/to/reference_data/ \
   --outdir output/
 ```
+
+## Citations
+
+You can cite a specific version of `sash` from the Zenodo record [10.5281/zenodo.15833492](https://doi.org/10.5281/zenodo.15833492) such as:
+
+> Watts, S. C., Savelyev, V., Diakumis, P., Clayssen, Q., Mitchell, H., & Hofmann, O. (2025). umccr/sash: 0.6.0 (0.6.0). Zenodo. https://doi.org/10.5281/zenodo.15833493

conf/refdata.config

@@ -2,7 +2,7 @@ params {
 
     data_versions {
         umccr_reference_data = '2--0'
-        hmf_reference_data = '5.34_38--2'
+        hmf_reference_data = 'hmf_pipeline_resources.38_v2.2.0--3'
 
         pcgr = '20250314'
         vep = "113"
@@ -62,46 +62,35 @@ params {
     // NOTE(SW): this should be shared with oncoanalyser
     hmfdata_paths {
         // AMBER
-        heterozygous_sites            = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/copy_number/AmberGermlineSites.38.tsv.gz"
+        heterozygous_sites            = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/copy_number/AmberGermlineSites.38.tsv.gz"
         // COBALT
-        gc_profile                    = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/copy_number/GC_profile.1000bp.38.cnp"
-        diploid_bed                   = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/copy_number/DiploidRegions.38.bed.gz"
+        gc_profile                    = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/copy_number/GC_profile.1000bp.38.cnp"
+        diploid_bed                   = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/copy_number/DiploidRegions.38.bed.gz"
         // CUPPA
-        cuppa_resources               = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/cuppa/"
+        cuppa_resources               = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/misc/cuppa/"
         // SV Prep
-        sv_prep_blocklist             = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/sv/sv_prep_blacklist.38.bed"
+        sv_prep_blocklist             = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/sv/sv_prep_blacklist.38.bed"
         // GRIDSS, GRIPSS
-        gridss_pon_breakends          = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/sv/sgl_pon.38.bed.gz"
-        gridss_pon_breakpoints        = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/sv/sv_pon.38.bedpe.gz"
-        gridss_region_blocklist       = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/sv/gridss_blacklist.38.bed.gz"
-        repeatmasker_annotations      = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/sv/repeat_mask_data.38.fa.gz"
+        gridss_pon_breakends          = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/sv/sgl_pon.38.bed.gz"
+        gridss_pon_breakpoints        = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/sv/sv_pon.38.bedpe.gz"
+        repeatmasker_annotations      = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/sv/repeat_mask_data.38.fa.gz"
         // Isofox
-        isofox_counts                 = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/rna_pipeline/read_151_exp_counts.csv"
-        isofox_gc_ratios              = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/rna_pipeline/read_100_exp_gc_ratios.csv"
-        // LILAC
-        lilac_resources               = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/immune/"
-        // ORANGE
-        cohort_mapping                = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/orange/cohort_mapping.tsv"
-        cohort_percentiles            = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/orange/cohort_percentiles.tsv"
-        alt_sj_distribution           = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/rna_pipeline/isofox.hmf_3444.alt_sj_cohort.38.csv"
-        gene_exp_distribution         = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/rna_pipeline/isofox.hmf_3444.gene_distribution.38.csv"
+        isofox_counts                 = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/rna/read_151_exp_counts.38.csv"
+        isofox_gc_ratios              = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/rna/read_100_exp_gc_ratios.38.csv"
         // SAGE
-        clinvar_annotations           = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/variants/clinvar.38.vcf.gz"
-        sage_blocklist_regions        = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/variants/KnownBlacklist.germline.38.bed"
-        sage_highconf_regions         = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/variants/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed.gz"
-        sage_known_hotspots_somatic   = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/variants/KnownHotspots.somatic.38.vcf.gz"
-        sage_pon                      = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/variants/SageGermlinePon.98x.38.tsv.gz"
-        // Sigs
-        sigs_signatures               = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/sigs/snv_cosmic_signatures.csv"
+        clinvar_annotations           = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/variants/clinvar.38.vcf.gz"
+        sage_blocklist_regions        = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/variants/KnownBlacklist.germline.38.bed"
+        sage_highconf_regions         = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/variants/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed.gz"
+        sage_known_hotspots_somatic   = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/variants/KnownHotspots.somatic.38.vcf.gz"
+        sage_pon                      = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/variants/hmf_wgs_sage_pon_1000.38.tsv.gz"
         // Virus Interpreter
-        virus_reporting_db            = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/virusinterpreter/virus_reporting_db.tsv"
-        virus_taxonomy_db             = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/virusinterpreter/taxonomy_db.tsv"
+        virus_reporting_db            = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/misc/virusinterpreter/virus_reporting_db.tsv"
+        virus_taxonomy_db             = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/misc/virusinterpreter/taxonomy_db.tsv"
         // Misc
-        disease_ontology              = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/disease_ontology/doid.json"
-        gnomad_resource               = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/variants/gnomad/"
-        gridss_config                 = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/sv/gridss.properties"
-        purple_germline_del           = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/copy_number/cohort_germline_del_freq.38.csv"
-        segment_mappability           = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna_pipeline/variants/mappability_150.38.bed.gz"
+        gnomad_resource               = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/variants/gnomad/"
+        gridss_config                 = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/sv/gridss.properties"
+        purple_germline_del           = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/copy_number/cohort_germline_del_freq.38.csv"
+        segment_mappability           = "hmf_reference_data/hmftools/${data_versions.hmf_reference_data}/dna/variants/mappability_150.38.bed.gz"
     }
 
 }

modules/local/bolt/other/cancer_report/main.nf

@@ -2,7 +2,7 @@ process BOLT_OTHER_CANCER_REPORT {
     tag "${meta.id}"
     label 'process_low'
 
-    container 'docker.io/qclayssen/bolt:0.3.0-dev-gpgr'
+    container 'ghcr.io/umccr/bolt:0.2.17-gpgr'
 
     input:
     tuple val(meta), path(smlv_somatic_vcf), path(smlv_somatic_bcftools_stats), path(smlv_somatic_counts_process), path(sv_somatic_tsv), path(sv_somatic_vcf), path(cnv_somatic_tsv), path(af_global), path(af_keygenes), path(purple_baf_plot), path(purple_dir), path(virusbreakend_dir), path(dragen_hrd), path(smlv_somatic_mutpat), path(smlv_somatic_hrdetect), path(smlv_somatic_chord)
@@ -19,6 +19,8 @@ process BOLT_OTHER_CANCER_REPORT {
 
     script:
 
+    def dragen_hrd_arg = dragen_hrd ? "--dragen_hrd_fp \$(pwd)/${dragen_hrd}" : ''
+
     """
     # NOTE(SW): gpgr requires aboslute paths
 
@@ -46,7 +48,7 @@ process BOLT_OTHER_CANCER_REPORT {
         --purple_dir \$(pwd)/${purple_dir} \\
         --virusbreakend_dir \$(pwd)/${virusbreakend_dir} \\
         \\
-        --dragen_hrd_fp \$(pwd)/${dragen_hrd} \\
+        ${dragen_hrd_arg} \\
         \\
         --cancer_genes_fp \$(pwd)/${somatic_driver_panel} \\
         --oncokb_genes_fp \$(pwd)/${oncokb_genes} \\

modules/local/bolt/other/multiqc_report/main.nf

@@ -2,7 +2,7 @@ process BOLT_OTHER_MULTIQC_REPORT {
     tag "${meta.id}"
     label 'process_low'
 
-    container 'ghcr.io/umccr/bolt:0.3.0-dev-6-multiqc'
+    container 'ghcr.io/umccr/bolt:0.2.17-multiqc'
 
     input:
     tuple val(meta), path(input_files)

modules/local/bolt/other/purple_baf_plot/main.nf

@@ -2,7 +2,7 @@ process BOLT_OTHER_PURPLE_BAF_PLOT {
     tag "${meta.id}"
     label 'process_low'
 
-    container 'ghcr.io/umccr/bolt:0.3.0-dev-6-circos'
+    container 'ghcr.io/umccr/bolt:0.2.17-circos'
 
     input:
     tuple val(meta), path(purple_dir)

modules/local/bolt/smlv_germline/prepare/main.nf

@@ -2,7 +2,7 @@ process BOLT_SMLV_GERMLINE_PREPARE {
     tag "${meta.id}"
     label 'process_low'
 
-    container 'ghcr.io/umccr/bolt:0.3.0-dev-6'
+    container 'ghcr.io/umccr/bolt:0.2.17'
 
     input:
     tuple val(meta), path(smlv_vcf)

modules/local/bolt/smlv_germline/report/main.nf

@@ -2,7 +2,7 @@ process BOLT_SMLV_GERMLINE_REPORT {
     tag "${meta.id}"
     label 'process_low'
 
-    container 'ghcr.io/umccr/bolt:0.3.0-dev-6-pcgr'
+    container 'ghcr.io/umccr/bolt:0.2.17-pcgr'
 
     input:
     tuple val(meta), path(smlv_vcf), path(smlv_unfiltered_vcf)

modules/local/bolt/smlv_somatic/annotate/main.nf

@@ -2,7 +2,7 @@ process BOLT_SMLV_SOMATIC_ANNOTATE {
     tag "${meta.id}"
     label 'process_low'
 
-    container 'ghcr.io/umccr/bolt:0.3.0-dev-6-pcgr'
+    container 'ghcr.io/umccr/bolt:0.2.17-pcgr'
 
     input:
     tuple val(meta), path(smlv_vcf)