diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 1de1e12694..c66c4c23c8 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -5,6 +5,8 @@ on: branches: - dev pull_request: + paths-ignore: + - "docs/**" release: types: [published] workflow_dispatch: @@ -12,7 +14,7 @@ on: env: NFT_DIFF: "pdiff" NFT_DIFF_ARGS: "--line-numbers --width 120 --expand-tabs=2" - NFT_VER: "0.9.0" + NFT_VER: "0.9.2" NFT_WORKDIR: "~" NXF_ANSI_LOG: false NXF_SINGULARITY_CACHEDIR: ${{ github.workspace }}/.singularity diff --git a/CHANGELOG.md b/CHANGELOG.md index bce2ba6729..2b70b0a659 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,10 +5,36 @@ All notable changes to this project will be documented in this file. 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). -## dev +## [3dev](https://github.com/nf-core/sarek/releases/tag/dev) - dev ### Added +- [1759](https://github.com/nf-core/sarek/pull/1759) - Back to dev + +### Changed + +### Fixed + +### Removed + +### Dependencies + +| Dependency | Old version | New version | +| ---------- | ----------- | ----------- | + +### Parameters + +| Params | Status | +| ------ | ------ | + +## [3.5.0](https://github.com/nf-core/sarek/releases/tag/3.5.0) - Áhkájiegna + +A set of connecting glaciers. + +### Added + +- [1613](https://github.com/nf-core/sarek/pull/1613) - add indexcov +- [1638](https://github.com/nf-core/sarek/pull/1638) - Added additional documentation detailing ASCAT WES usage. - [1640](https://github.com/nf-core/sarek/pull/1620) - Add `lofreq` as a tumor-only variant caller - [1642](https://github.com/nf-core/sarek/pull/1642) - Back to dev - [1653](https://github.com/nf-core/sarek/pull/1653) - Updates `sarek_subway` files with `lofreq` @@ -20,6 +46,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Changed +- [1579](https://github.com/nf-core/sarek/pull/1579) - Update Sentieon usage docs +- [1635](https://github.com/nf-core/sarek/pull/1635) - Fix docs to reflect variant calling tool - data type correctly - [1668](https://github.com/nf-core/sarek/pull/1668) - Add nf-test sharding CI - [1669](https://github.com/nf-core/sarek/pull/1669) - Better nf-test pipeline level tests - [1677](https://github.com/nf-core/sarek/pull/1677) - Migrate pytest aligner and pipeline default tests to nf-test @@ -31,6 +59,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - [1707](https://github.com/nf-core/sarek/pull/1707) - Un-hide parameters and clean up Json schema - [1708](https://github.com/nf-core/sarek/pull/1708) - Migrate pipeline pytest alignment and annotation tests to nf-test - [1711](https://github.com/nf-core/sarek/pull/1711) - Migrate pipeline pytest strelka tests to nf-test +- [1731](https://github.com/nf-core/sarek/pull/1731) - Migrate pipeline pytest controlfreec tests to nf-test ### Fixed @@ -44,6 +73,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - [1702](https://github.com/nf-core/sarek/pull/1702) - Update nf-schema tests that were not failing on lenient mode - [1712](https://github.com/nf-core/sarek/pull/1712) - Fix missing import statements on error messages when starting without samplesheet - [1743](https://github.com/nf-core/sarek/pull/1743) - Add setup java 17 in GHA for latest Nextflow version +- [1745](https://github.com/nf-core/sarek/pull/1745) - Fix bug where workflow can hang if the email parameter is set +- [1746](https://github.com/nf-core/sarek/pull/1746) - Fix Sentieon module inputs +- [1752](https://github.com/nf-core/sarek/pull/1752) - Add `indexcov` and `lofreq` to full size tests. Amend overview figures. +- [1754](https://github.com/nf-core/sarek/pull/1754) - Fix test string +- [1755](https://github.com/nf-core/sarek/pull/1755) - Remove `default` channel and name from local modules +- [1757](https://github.com/nf-core/sarek/pull/1757) - Fix Changelog by adding missing new parameters ### Removed @@ -59,6 +94,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 | `deepvariant` | 1.5.0 | 1.6.1 | | `ensemblvep` | 111.0 | 113.0 | | `fgbio` | 2.0.2 | 2.1.2 | +| `gawk` | 5.1.0 | 5.3.0 | | `htslib` | 1.20 | 1.21 | | `lofreq` | | 2.1.5 | | `multiqc` | 1.21 | 1.25.1 | @@ -72,6 +108,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 | Params | Status | | ------------------------------------ | ------- | | `--help_full` | New | +| `--length_required` | New | | `--show_hidden` | New | | `--snpeff_db` | Updated | | `--snpeff_genome` | Removed | diff --git a/README.md b/README.md index 6c501e24c9..fbbe1e5cdd 100644 --- a/README.md +++ b/README.md @@ -54,6 +54,7 @@ Depending on the options and samples provided, the pipeline can currently perfor - `freebayes` - `GATK HaplotypeCaller` - `Manta` + - `indexcov` - `mpileup` - `MSIsensor-pro` - `Mutect2` @@ -172,6 +173,7 @@ We thank the following people for their extensive assistance in the development - [pallolason](https://github.com/pallolason) - [Paul Cantalupo](https://github.com/pcantalupo) - [Phil Ewels](https://github.com/ewels) +- [Pierre Lindenbaum](https://github.com/lindenb) - [Sabrina Krakau](https://github.com/skrakau) - [Sam Minot](https://github.com/sminot) - [Sebastian-D](https://github.com/Sebastian-D) diff --git a/conf/modules/aligner.config b/conf/modules/aligner.config index 5f44e199b0..70926d573a 100644 --- a/conf/modules/aligner.config +++ b/conf/modules/aligner.config @@ -30,11 +30,11 @@ process { } withName: 'SENTIEON_BWAMEM' { + ext.prefix = { params.split_fastq > 1 ? "${meta.id}".concat('.').concat(reads.get(0).name.tokenize('.')[0]).concat('.bam') : "${meta.id}.sorted.bam" } ext.when = { params.aligner == 'sentieon-bwamem' } } withName: 'BWAMEM.*_MEM|DRAGMAP_ALIGN|SENTIEON_BWAMEM' { - ext.prefix = { params.split_fastq > 1 ? "${meta.id}".concat('.').concat(reads.get(0).name.tokenize('.')[0]) : "${meta.id}.sorted" } publishDir = [ mode: params.publish_dir_mode, path: { "${params.outdir}/preprocessing/" }, @@ -56,6 +56,7 @@ process { } withName: 'BWAMEM.*_MEM|DRAGMAP_ALIGN' { + ext.prefix = { params.split_fastq > 1 ? "${meta.id}".concat('.').concat(reads.get(0).name.tokenize('.')[0]) : "${meta.id}.sorted" } // Markduplicates Spark NEEDS name-sorted reads or runtime goes through the roof // However if it's skipped, reads need to be coordinate-sorted // Only name sort if Spark for Markduplicates + duplicate marking is not skipped diff --git a/conf/modules/indexcov.config b/conf/modules/indexcov.config new file mode 100644 index 0000000000..082ea3b7cc --- /dev/null +++ b/conf/modules/indexcov.config @@ -0,0 +1,21 @@ + +// INDEXCOV + +process { + if (params.tools && params.tools.split(',').contains('indexcov')) { + + withName: 'SAMTOOLS_REINDEX_BAM' { + ext.args = { ' -F 3844 -q 30 ' } // high mapq , primary read paired properly mapped + } + + withName: 'GOLEFT_INDEXCOV' { + publishDir = [ + mode: params.publish_dir_mode, + path: { "${params.outdir}/variant_calling/indexcov/" } + ] + + } + + } + +} diff --git a/conf/modules/sentieon_dedup.config b/conf/modules/sentieon_dedup.config index df52c3bb95..35f89720f7 100644 --- a/conf/modules/sentieon_dedup.config +++ b/conf/modules/sentieon_dedup.config @@ -16,7 +16,7 @@ process { withName: 'SENTIEON_DEDUP' { - ext.prefix = { "${meta.id}.dedup" } + ext.prefix = { "${meta.id}.dedup.cram" } ext.when = { params.tools && params.tools.split(',').contains('sentieon_dedup') } publishDir = [ [ diff --git a/conf/test_full.config b/conf/test_full.config index 8febf40be4..d5bf5d3234 100644 --- a/conf/test_full.config +++ b/conf/test_full.config @@ -18,7 +18,7 @@ params { input = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/csv/HCC1395_WXS_somatic_full_test.csv' // Other params - tools = 'ngscheckmate,strelka,mutect2,freebayes,ascat,manta,cnvkit,tiddit,controlfreec,vep,snpeff,muse' + tools = 'ngscheckmate,lofreq,strelka,mutect2,muse,freebayes,ascat,manta,cnvkit,tiddit,controlfreec,vep,snpeff' split_fastq = 20000000 intervals = 's3://ngi-igenomes/test-data/sarek/S07604624_Padded_Agilent_SureSelectXT_allexons_V6_UTR.bed' wes = true diff --git a/conf/test_full_germline.config b/conf/test_full_germline.config index d731a25709..4b2421c625 100644 --- a/conf/test_full_germline.config +++ b/conf/test_full_germline.config @@ -18,6 +18,6 @@ params { input = 'https://raw.githubusercontent.com/nf-core/test-datasets/sarek/testdata/csv/NA12878_WGS_30x_full_test.csv' // Other params - tools = 'strelka,freebayes,haplotypecaller,deepvariant,manta,tiddit,cnvkit,vep,snpeff' + tools = 'indexcov,strelka,freebayes,haplotypecaller,deepvariant,manta,tiddit,cnvkit,vep,snpeff' split_fastq = 50000000 } diff --git a/docs/images/sarek_subway.png b/docs/images/sarek_subway.png index f2f20ffc01..a381343500 100644 Binary files a/docs/images/sarek_subway.png and b/docs/images/sarek_subway.png differ diff --git a/docs/images/sarek_subway.svg b/docs/images/sarek_subway.svg index 62544b70fc..6d8d172652 100644 --- a/docs/images/sarek_subway.svg +++ b/docs/images/sarek_subway.svg @@ -32,12 +32,12 @@ inkscape:pagecheckerboard="false" inkscape:document-units="mm" showgrid="true" - inkscape:zoom="0.61695405" - inkscape:cx="709.12898" - inkscape:cy="403.59569" - inkscape:window-width="1440" - inkscape:window-height="847" - inkscape:window-x="0" + inkscape:zoom="1.8101934" + inkscape:cx="659.04562" + inkscape:cy="459.61941" + inkscape:window-width="2560" + inkscape:window-height="1027" + inkscape:window-x="1512" inkscape:window-y="25" inkscape:window-maximized="1" inkscape:current-layer="layer4" @@ -795,13 +795,27 @@ id="rect6693-4" style="display:inline;fill:#e6e6e6;fill-opacity:1;stroke:none;stroke-width:4.00201;stroke-linecap:butt;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:normal" />indexcovdeepvariantfreebayeshaplotypecallerstrelka2tidditmutect2freebayesmantalofreqlofreqExample analysis pathwaysmpileupmpileupSentieon haplotyperSentieon dnascopeSNPs & IndelsMSI + style="color:#000000;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:medium;line-height:normal;font-family:sans-serif;font-variant-ligatures:normal;font-variant-position:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-alternates:normal;font-feature-settings:normal;text-indent:0;text-align:start;text-decoration:none;text-decoration-line:none;text-decoration-style:solid;text-decoration-color:#000000;letter-spacing:normal;word-spacing:normal;text-transform:none;writing-mode:lr-tb;direction:ltr;text-orientation:mixed;dominant-baseline:auto;baseline-shift:baseline;text-anchor:start;white-space:normal;shape-padding:0;clip-rule:nonzero;display:inline;overflow:visible;visibility:visible;opacity:1;isolation:auto;mix-blend-mode:normal;color-interpolation:sRGB;color-interpolation-filters:linearRGB;solid-color:#000000;solid-opacity:1;vector-effect:none;fill:#000000;fill-opacity:1;fill-rule:nonzero;stroke:none;stroke-width:4.00004;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;color-rendering:auto;image-rendering:auto;shape-rendering:auto;text-rendering:auto;enable-background:accumulate" />strelka2 diff --git a/docs/images/sarek_workflow.png b/docs/images/sarek_workflow.png index 3f47f10829..8b993ab268 100644 Binary files a/docs/images/sarek_workflow.png and b/docs/images/sarek_workflow.png differ diff --git a/docs/images/sarek_workflow.svg b/docs/images/sarek_workflow.svg index 416bbb1553..c28d400a13 100644 --- a/docs/images/sarek_workflow.svg +++ b/docs/images/sarek_workflow.svg @@ -25,10 +25,20 @@ rdf:about="">image/svg+xmlfastqfastq/spring/ubamfastq|spring| ubamfastq/spring/ubamfastq|spring| ubamSomaticfreebayes, mutect2, strelka2, lofreq• manta, tiddit• ascat, cnvkit, controlfreecGermline + y="845.03542" + id="tspan1">Germline deepvariant, freebayes + id="tspan3">• deepvariant, freebayes GATK haplotypecaller, + id="tspan5"> GATK haplotypecaller, mpileup, strelka2, + id="tspan7"> Sentieon haplotyper Sentieon haplotyper + id="tspan9"> mpileup, strelka2 • manta, tiddit + id="tspan11">• indexcov,manta, tiddit • cnvkit• cnvkit