Revert "Merge branch 'dev' into add-found-in-cnv"

This reverts commit 44939b0, reversing changes made to bc5c57b.
genomic-medicine-sweden · Oct 4, 2024 · f19c2a1 · f19c2a1
1 parent 04cba18
commit f19c2a1
Show file tree

Hide file tree

Showing 11 changed files with 153 additions and 30 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -42,15 +42,9 @@ jobs:
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
-        with:
-          fetch-depth: 0
-      - name: Fetch ${{ github.event.pull_request.base.ref }} branch
-        run: |
-          git remote add upstream ${{ github.event.repository.clone_url }}
-          git fetch upstream ${{ github.event.pull_request.base.ref }}
 
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v2
+        uses: nf-core/setup-nextflow@b9f764e8ba5c76b712ace14ecbfcef0e40ae2dd8 # v1
         with:
           version: "${{ matrix.NXF_VER }}"
 
@@ -70,13 +64,18 @@ jobs:
 
       - name: Run nf-test
         run: |
-          nf-test test \
-            --ci \
-            --changed-since upstream/${{ github.event.pull_request.base.ref }} \
-            --verbose \
-            --tag ${{ matrix.tags }} \
-            --profile "+${{ matrix.profile }}" \
-            --junitxml=test.xml
+          nf-test test --verbose --tag ${{ matrix.tags }} --profile "+${{ matrix.profile }}" --junitxml=test.xml --tap=test.tap
+
+      - uses: pcolby/tap-summary@v1
+        with:
+          path: >-
+            test.tap
+
+      - name: Output log on failure
+        if: failure()
+        run: |
+          sudo apt install bat > /dev/null
+          batcat --decorations=always --color=always ${{ github.workspace }}/.nf-test/tests/*/meta/nextflow.log
 
       - name: Publish Test Report
         uses: mikepenz/action-junit-report@v3

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -19,6 +19,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#388](https://github.com/genomic-medicine-sweden/nallo/pull/388) - Added longphase as the default phaser
 - [#388](https://github.com/genomic-medicine-sweden/nallo/pull/388) - Added single-sample tbi output to the short variant calling subworkflow
 - [#393](https://github.com/genomic-medicine-sweden/nallo/pull/393) - Added a new `--minimap2_read_mapping_preset` parameter
+- [#408](https://github.com/genomic-medicine-sweden/nallo/pull/408) - Added a new subworkflow to annotate SVs
 
 ### `Changed`
 
@@ -38,7 +39,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#393](https://github.com/genomic-medicine-sweden/nallo/pull/393) - Changed the default minimap2 preset for PacBio data from `map-hifi` to `lr:hqae`
 - [#397](https://github.com/genomic-medicine-sweden/nallo/pull/397) - Changed `pipelines_testdata_base_path` to pin a specific commit
 - [#402](https://github.com/genomic-medicine-sweden/nallo/pull/402) - Updated broken test profile link added in [#397](https://github.com/genomic-medicine-sweden/nallo/pull/397)
-- [#404](https://github.com/genomic-medicine-sweden/nallo/pull/404) - Changed to only run nf-tests where files have changes compared to the base branch
 
 ### `Removed`
 

diff --git a/assets/svdb_query_vcf_schema.json b/assets/svdb_query_vcf_schema.json
@@ -0,0 +1,40 @@
+{
+    "$schema": "http://json-schema.org/draft-07/schema",
+    "$id": "https://raw.githubusercontent.com/nf-core/raredisease/master/assets/mobile_element_references_schema.json",
+    "title": "Schema for SVDB query - VCF",
+    "description": "Schema for the SVDB query database input, VCF version",
+    "type": "array",
+    "items": {
+        "type": "object",
+        "properties": {
+            "filename": {
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^\\S+\\.vcf?(\\.gz)?$",
+                "errorMessage": "Path to query database cannot contain spaces and must be a vcf file"
+            },
+            "in_freq_info_key": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "In frequency key cannot contain spaces"
+            },
+            "in_allele_count_info_key": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "In allele count key cannot contain spaces"
+            },
+            "out_freq_info_key": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "Out frequency key must be provided and cannot contain spaces"
+            },
+            "out_allele_count_info_key": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "Out allele count key must be provided and cannot contain spaces"
+            }
+        },
+        "required": ["filename", "out_freq_info_key", "out_allele_count_info_key"]
+    }
+}
diff --git a/conf/modules/annotate_svs.config b/conf/modules/annotate_svs.config
@@ -0,0 +1,57 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Config file for defining DSL2 per module options and publishing paths
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Available keys to override module options:
+        ext.args   = Additional arguments appended to command in module.
+        ext.args2  = Second set of arguments appended to command in module (multi-tool modules).
+        ext.args3  = Third set of arguments appended to command in module (multi-tool modules).
+        ext.prefix = File name prefix for output files.
+----------------------------------------------------------------------------------------
+*/
+
+process {
+
+    /*
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Annotate SVs
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    */
+
+    withName: '.*:ANNOTATE_SVS:.*' {
+        publishDir = [
+            enabled: false,
+        ]
+    }
+
+    withName: '.*ANNOTATE_SVS:ENSEMBLVEP_SV' {
+        ext.args = { [
+            "${params.extra_vep_options}",
+            "--dir_plugins .",
+            '--plugin pLI,pLI_values.txt',
+            '--appris --biotype --buffer_size 100 --canonical --cache --ccds',
+            '--compress_output bgzip --distance 5000 --domains',
+            '--exclude_predicted --force_overwrite --format vcf',
+            '--fork 4 --hgvs --humdiv --max_sv_size 248387328',
+            '--no_progress --numbers --per_gene --polyphen p',
+            '--protein --offline --sift p', // Add back regulatory with VEP 113
+            '--symbol --tsl --uniprot --vcf',
+            '--no_stats'
+        ].join(' ') }
+        ext.prefix = { "${meta.id}_svs_annotated" }
+        publishDir = [
+            path: { "${params.outdir}/svs/multi_sample/${meta.id}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: '.*ANNOTATE_SVS:TABIX_VEP' {
+        publishDir = [
+            path: { "${params.outdir}/svs/multi_sample/${meta.id}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+}
diff --git a/conf/modules/call_svs.config b/conf/modules/call_svs.config
@@ -55,7 +55,7 @@ process {
         publishDir = [
             path: { "${params.outdir}/svs/multi_sample/${meta.id}" },
             mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+            saveAs: { filename -> filename.equals('versions.yml') || params.skip_sv_annotation ? null : filename }
         ]
     }
 

diff --git a/nextflow.config b/nextflow.config
@@ -21,6 +21,7 @@ params {
     reduced_penetrance           = null
     score_config_snv             = null
     snp_db                       = null
+    svdb_dbs                     = null
     variant_consequences_snv     = null
     vep_cache                    = null
     vep_plugin_files             = null
@@ -42,6 +43,7 @@ params {
     skip_repeat_annotation       = params.preset == 'ONT_R10' ? true : false
     skip_short_variant_calling   = false
     skip_snv_annotation          = false
+    skip_sv_annotation           = false
 
     deepvariant_model_type       = params.preset == 'ONT_R10' ? 'ONT_R104' : 'PACBIO'
     minimap2_read_mapping_preset = params.preset == 'ONT_R10' ? 'lr:hq' : 'lr:hqae'
@@ -303,6 +305,7 @@ includeConfig 'conf/base.config'
 includeConfig 'conf/modules/annotate_cadd.config'
 includeConfig 'conf/modules/annotate_consequence_pli.config'
 includeConfig 'conf/modules/annotate_repeat_expansions.config'
+includeConfig 'conf/modules/annotate_svs.config'
 includeConfig 'conf/modules/general.config'
 includeConfig 'conf/modules/bam_infer_sex.config'
 includeConfig 'conf/modules/call_paralogs.config'

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -64,6 +64,11 @@
                     "description": "Skip short variant annotation",
                     "default": false
                 },
+                "skip_sv_annotation": {
+                    "type": "boolean",
+                    "description": "Skip structural variant annotation",
+                    "default": false
+                },
                 "skip_cnv_calling": {
                     "type": "boolean",
                     "description": "Skip CNV calling",
@@ -489,6 +494,17 @@
                     "description": "A csv file with echtvar databases to annotate SNVs with",
                     "exists": true
                 },
+                "svdb_dbs": {
+                    "type": "string",
+                    "exists": true,
+                    "format": "file-path",
+                    "description": "Databases used for structural variant annotation in vcf format.",
+                    "fa_icon": "fas fa-file-csv",
+                    "help_text": "Path to comma-separated file containing information about the databases used for structural variant annotation.",
+                    "pattern": "^\\S+\\.csv$",
+                    "mimetype": "text/csv",
+                    "schema": "assets/svdb_query_vcf_schema.json"
+                },
                 "variant_catalog": {
                     "type": "string",
                     "description": "A variant catalog json-file for stranger",

diff --git a/nf-test.config b/nf-test.config
@@ -7,5 +7,5 @@ config {
     workDir ".nf-test"
     configFile "tests/nextflow.config"
     profile "docker"
-    triggers 'nextflow.config', 'nf-test.config', 'test-data/**/*'
+
 }
diff --git a/subworkflows/local/annotate_svs/main.nf b/subworkflows/local/annotate_svs/main.nf
@@ -39,15 +39,15 @@ workflow ANNOTATE_SVS {
     )
 
     ENSEMBLVEP_SV (
-        SVDB_QUERY.out.vcf,
+        SVDB_QUERY.out.vcf.map { meta, vcf -> [ meta, vcf, [] ] },
         "GRCh38",
         "homo_sapiens",
         val_vep_cache_version,
         ch_vep_cache,
         ch_fasta,
         ch_vep_extra_files
     )
-    ch_versions = ch_versions.mix(ENSEMBLVEP_VEP.out.versions)
+    ch_versions = ch_versions.mix(ENSEMBLVEP_SV.out.versions)
 
     TABIX_ENSEMBLVEP_SV (
         ENSEMBLVEP_SV.out.vcf

diff --git a/subworkflows/local/utils_nfcore_nallo_pipeline/main.nf b/subworkflows/local/utils_nfcore_nallo_pipeline/main.nf
@@ -39,6 +39,7 @@ def workflowSkips = [
     mapping          : "skip_mapping_wf",
     snv_calling      : "skip_short_variant_calling",
     snv_annotation   : "skip_snv_annotation",
+    sv_annotation    : "skip_sv_annotation",
     call_paralogs    : "skip_call_paralogs",
     cnv_calling      : "skip_cnv_calling",
     phasing          : "skip_phasing_wf",
@@ -57,6 +58,7 @@ def workflowDependencies = [
     call_paralogs    : ["mapping"],
     snv_calling      : ["mapping"],
     qc               : ["mapping"],
+    sv_annotation    : ["mapping"],
     snv_annotation   : ["mapping", "snv_calling"],
     cnv_calling      : ["mapping", "snv_calling"],
     phasing          : ["mapping", "snv_calling"],
@@ -74,6 +76,7 @@ def fileDependencies = [
     assembly         : ["fasta", "par_regions"], // The assembly workflow should be split into two - assembly and variant calling (requires ref)
     snv_calling      : ["fasta", "par_regions"],
     snv_annotation   : ["snp_db", "vep_cache", "vep_plugin_files", "variant_consequences_snv"],
+    sv_annotation    : ["svdb_dbs", "vep_cache", "vep_plugin_files", "variant_consequences_snv"],
     cnv_calling      : ["hificnv_xy", "hificnv_xx", "hificnv_exclude"],
     rank_variants    : ["reduced_penetrance", "score_config_snv"],
     repeat_calling   : ["trgt_repeats"],

diff --git a/workflows/nallo.nf b/workflows/nallo.nf
@@ -105,6 +105,8 @@ workflow NALLO {
                                                                     : Channel.value([])
     ch_somalier_sites           = params.somalier_sites             ? Channel.fromPath(params.somalier_sites).map { [ it.simpleName, it ] }.collect()
                                                                     : ''
+    ch_svdb_dbs                 = params.svdb_dbs                   ? Channel.fromPath(params.svdb_dbs).map { [ it.simpleName, it ] }.collect()
+                                                                    : ''
 
     // Check parameter that doesn't conform to schema validation here
     if (params.phaser.matches('hiphase') && params.preset == 'ONT_R10') { error "The HiPhase license only permits analysis of data from PacBio. For details see: https://github.com/PacificBiosciences/HiPhase/blob/main/LICENSE.md" }
@@ -311,17 +313,20 @@ workflow NALLO {
         )
         ch_versions = ch_versions.mix(CALL_SVS.out.versions)
 
-	//
- 	// Annotate structural variants
-	//
-	ANNOTATE_SVS (
-	    CALL_SVS.out.ch_multisample_vcf,
-	    fasta,
-        svdb_dbs,
-        ch_vep_cache,
-        params.vep_cache_version,
-        ch_vep_extra_files
-    )
+
+        //
+        // Annotate structural variants
+        //
+        if(!params.skip_sv_annotation) {
+            ANNOTATE_SVS (
+                CALL_SVS.out.ch_multisample_vcf,
+                fasta,
+                ch_svdb_dbs,
+                ch_vep_cache,
+                params.vep_cache_version,
+                ch_vep_extra_files
+            )
+        }
 
         //
         // Call (and annotate and rank) SNVs