From f142fa6c09a55d9244c3d5ef837d485e3afdb993 Mon Sep 17 00:00:00 2001 From: Stephen Watts Date: Wed, 31 Jul 2024 15:35:16 +1000 Subject: [PATCH 1/9] Add summary note on pipeline function in README.md --- README.md | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index f0e49dc0..8fa4a863 100644 --- a/README.md +++ b/README.md @@ -25,9 +25,13 @@ ## 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 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. 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)_): From c0d6b071d5900e8f6427f70eaf7e3732b09cef44 Mon Sep 17 00:00:00 2001 From: Stephen Watts Date: Wed, 31 Jul 2024 15:35:37 +1000 Subject: [PATCH 2/9] Correct Conda GRIDSS build version --- modules/local/gridss/index/environment.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/local/gridss/index/environment.yml b/modules/local/gridss/index/environment.yml index 3f1fee42..ed9cb011 100644 --- a/modules/local/gridss/index/environment.yml +++ b/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 From 7394aa2761aed98270c221404e067096139627b5 Mon Sep 17 00:00:00 2001 From: Stephen Watts Date: Wed, 31 Jul 2024 15:35:53 +1000 Subject: [PATCH 3/9] Correct Conda SAGE version --- modules/local/sage/append/environment.yml | 2 +- modules/local/sage/germline/environment.yml | 2 +- modules/local/sage/somatic/environment.yml | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/modules/local/sage/append/environment.yml b/modules/local/sage/append/environment.yml index dd57ccbb..e6f84927 100644 --- a/modules/local/sage/append/environment.yml +++ b/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 diff --git a/modules/local/sage/germline/environment.yml b/modules/local/sage/germline/environment.yml index 1f44d1c5..40abd45c 100644 --- a/modules/local/sage/germline/environment.yml +++ b/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 diff --git a/modules/local/sage/somatic/environment.yml b/modules/local/sage/somatic/environment.yml index 35e0b137..5befb17f 100644 --- a/modules/local/sage/somatic/environment.yml +++ b/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 From b660853e9f1ef509957215a5e16aa3e6ebd0dc3f Mon Sep 17 00:00:00 2001 From: Stephen Watts Date: Wed, 31 Jul 2024 15:36:19 +1000 Subject: [PATCH 4/9] Comment out any hint of citations --- .../local/utils_nfcore_oncoanalyser_pipeline/main.nf | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/subworkflows/local/utils_nfcore_oncoanalyser_pipeline/main.nf b/subworkflows/local/utils_nfcore_oncoanalyser_pipeline/main.nf index f52693ff..f36242b9 100644 --- a/subworkflows/local/utils_nfcore_oncoanalyser_pipeline/main.nf +++ b/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() { From a6b5cc2e9f61b18b4347c3198e1835af0829b294 Mon Sep 17 00:00:00 2001 From: Stephen Watts Date: Wed, 31 Jul 2024 15:38:10 +1000 Subject: [PATCH 5/9] Use the HMF abbreviation more in README.md --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 8fa4a863..89e4062d 100644 --- a/README.md +++ b/README.md @@ -29,8 +29,8 @@ workflow from the Hartwig Medical Foundation (HMF). The workflow starts from FAS 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 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 +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 @@ -38,7 +38,7 @@ below from _[COLO829_wgts.orange_report.pdf](https://pub-29f2e5b2b7384811bdbbcba

-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 From 76cb7802529b70e07aa6a8fcf1ac01913a336ea2 Mon Sep 17 00:00:00 2001 From: Stephen Watts Date: Wed, 31 Jul 2024 16:02:56 +1000 Subject: [PATCH 6/9] Update input samplesheet URL for tests --- conf/test.config | 2 +- conf/test_full.config | 2 +- conf/test_stub.config | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/conf/test.config b/conf/test.config index 666424da..c9ede07f 100644 --- a/conf/test.config +++ b/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' diff --git a/conf/test_full.config b/conf/test_full.config index c719a30b..a2bd6f4c 100644 --- a/conf/test_full.config +++ b/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' diff --git a/conf/test_stub.config b/conf/test_stub.config index 34906f4c..0a8b47ff 100644 --- a/conf/test_stub.config +++ b/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/fastq_eval.subject_a.wgts.tndna_trna.minimal.csv' // Reference data genomes { From 3a835c630eb580ea1339672f2c5af2336b49c8df Mon Sep 17 00:00:00 2001 From: Stephen Watts Date: Wed, 31 Jul 2024 18:38:52 +1000 Subject: [PATCH 7/9] Fix MarkDups URLs --- docs/output.md | 6 +++--- modules/local/markdups/meta.yml | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/output.md b/docs/output.md index 5197066e..1d9ac032 100644 --- a/docs/output.md +++ b/docs/output.md @@ -112,9 +112,9 @@ _No outputs are published directly from STAR, see [Picard MarkDuplicates](#picar -[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_ diff --git a/modules/local/markdups/meta.yml b/modules/local/markdups/meta.yml index a9297b68..b621748f 100644 --- a/modules/local/markdups/meta.yml +++ b/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: From 3f7d8181be655d72bfbd750871e67b4f0e90110c Mon Sep 17 00:00:00 2001 From: Stephen Watts Date: Wed, 31 Jul 2024 19:10:48 +1000 Subject: [PATCH 8/9] Use stub samplesheet for test_stub profile --- conf/test_stub.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/test_stub.config b/conf/test_stub.config index 0a8b47ff..a8dd8d3b 100644 --- a/conf/test_stub.config +++ b/conf/test_stub.config @@ -20,7 +20,7 @@ params { max_time = '6.h' // Input data - input = 'https://github.com/nf-core/test-datasets/raw/oncoanalyser/samplesheet/fastq_eval.subject_a.wgts.tndna_trna.minimal.csv' + input = 'https://github.com/nf-core/test-datasets/raw/oncoanalyser/samplesheet/fastq_eval.subject_a.wgts.tndna_trna.minimal.stub.csv' // Reference data genomes { From f876e1844c895ce77a8ca4665893ec3508180959 Mon Sep 17 00:00:00 2001 From: Stephen Watts Date: Wed, 31 Jul 2024 19:21:17 +1000 Subject: [PATCH 9/9] Switch to BAM inputs for test_stub samplesheet --- conf/test_stub.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/test_stub.config b/conf/test_stub.config index a8dd8d3b..e7d08d0a 100644 --- a/conf/test_stub.config +++ b/conf/test_stub.config @@ -20,7 +20,7 @@ params { max_time = '6.h' // Input data - input = 'https://github.com/nf-core/test-datasets/raw/oncoanalyser/samplesheet/fastq_eval.subject_a.wgts.tndna_trna.minimal.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 {