Patch to dev (#565)

* Fix pipeline can't run without * CHANGELOG * docs * docs * update snaps * fix CI * Update CHANGELOG.md * changelog date * Add vep_plugin_files to files check * CHANGELOG * Update CHANGELOG.md * always failing CI because of nf-core update
genomic-medicine-sweden · Feb 18, 2025 · 9d926b1 · 9d926b1
1 parent 880a328
commit 9d926b1
Show file tree

Hide file tree

Showing 6 changed files with 60 additions and 41 deletions.
diff --git a/.github/workflows/ci_master.yml b/.github/workflows/ci_master.yml
@@ -18,9 +18,6 @@ on:
       - synchronize
     branches:
       - master
-  pull_request_target:
-    branches:
-      - master
 
 env:
   NXF_ANSI_LOG: false

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -65,6 +65,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 > Version has been added if just the new version information is present.
 > Version has been removed if new version information isn't present.
 
+## 0.4.1 - [2025-02-17]
+
+### `Fixed`
+
+- [#553](https://github.com/genomic-medicine-sweden/nallo/pull/553) - Fixed pipeline always requiring `--vep_cache` to run, and clarified documentation
+- [#553](https://github.com/genomic-medicine-sweden/nallo/pull/553) - Fixed `process.shell` in `nextflow.config` causing CI runners to fail
+
 ## 0.4.0 - [2025-01-15]
 
 ### `Added`

diff --git a/docs/usage.md b/docs/usage.md
@@ -290,9 +290,12 @@ Turned off with `--skip_rank_variants`.
 
 This subworkflow relies on the alignment subworkflow, and requires the following additional files:
 
-| Parameter                        | Description                                                           |
-| -------------------------------- | --------------------------------------------------------------------- |
-| `svdb_sv_databases` <sup>1</sup> | Csv file with databases (VCFs) used for structural variant annotation |
+| Parameter                        | Description                                                                                                                                                                                                                                                                                                                                        |
+| -------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `svdb_sv_databases` <sup>1</sup> | Csv file with databases (VCFs) used for structural variant annotation                                                                                                                                                                                                                                                                              |
+| `vep_cache`                      | VEP cache matching your reference genome, either as a `.tar.gz` archive or path to a directory (e.g. [homo_sapiens_vep_110_GRCh38.tar.gz](https://ftp.ensembl.org/pub/release-110/variation/vep/homo_sapiens_vep_110_GRCh38.tar.gz))                                                                                                               |
+| `vep_plugin_files` <sup>2</sup>  | A csv file with VEP plugin files, pLI and LoFtool are required. Example provided below.                                                                                                                                                                                                                                                            |
+| `variant_consequences_svs`       | A list of SO terms listed in the order of severity from most severe to lease severe for annotating SVs. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/variant_consequences_v2.txt). You can learn more about these terms [here](https://ensembl.org/info/genome/variation/prediction/predicted_data.html) |
 
 <sup>1</sup> Example file for input with `--svdb_sv_databases`:
 
@@ -303,6 +306,17 @@ https://github.com/genomic-medicine-sweden/test-datasets/raw/b9ff54b59cdd39df5b6
 
 These databases could for example come from [CoLoRSdb](https://zenodo.org/records/13145123).
 
+<sup>2</sup> Example file for input with `--vep_plugin_files`
+
+```
+vep_files
+https://raw.githubusercontent.com/genomic-medicine-sweden/test-datasets/nallo/reference/vep_plugins/spliceai_21_scores_raw_indel_-v1.3-.vcf.gz.tbi
+https://raw.githubusercontent.com/genomic-medicine-sweden/test-datasets/nallo/reference/vep_plugins/spliceai_21_scores_raw_indel_-v1.3-.vcf.gz
+https://raw.githubusercontent.com/genomic-medicine-sweden/test-datasets/nallo/reference/vep_plugins/spliceai_21_scores_raw_snv_-v1.3-.vcf.gz.tbi
+https://raw.githubusercontent.com/genomic-medicine-sweden/test-datasets/nallo/reference/vep_plugins/pLI_values.txt
+https://raw.githubusercontent.com/genomic-medicine-sweden/test-datasets/nallo/reference/vep_plugins/LoFtool_scores.txt
+```
+
 Turned off with `--skip_sv_annotation`.
 
 ### Rank SVs

diff --git a/nextflow.config b/nextflow.config
@@ -244,14 +244,13 @@ env {
 }
 
 // Set bash options
-process.shell = """\
-bash
-
-set -e # Exit if a tool returns a non-zero status/exit code
-set -u # Treat unset variables and parameters as an error
-set -o pipefail # Returns the status of the last command to exit with a non-zero status or zero if all successfully execute
-set -C # No clobber - prevent output redirection from overwriting files.
-"""
+process.shell = [
+    "bash",
+    "-C",         // No clobber - prevent output redirection from overwriting files.
+    "-e",         // Exit if a tool returns a non-zero status/exit code
+    "-u",         // Treat unset variables and parameters as an error
+    "-o pipefail" // Returns the status of the last command to exit with a non-zero status or zero if all successfully execute
+]
 
 // Disable process selector warnings by default. Use debug profile to enable warnings.
 nextflow.enable.configProcessNamesValidation = false

diff --git a/subworkflows/local/utils_nfcore_nallo_pipeline/main.nf b/subworkflows/local/utils_nfcore_nallo_pipeline/main.nf
@@ -87,7 +87,7 @@ def parameterStatus = [
     workflow: [
         skip_snv_calling         : params.skip_snv_calling,
         skip_phasing             : params.skip_phasing,
-        skip_methylation_pileups: params.skip_methylation_pileups,
+        skip_methylation_pileups : params.skip_methylation_pileups,
         skip_rank_variants       : params.skip_rank_variants,
         skip_repeat_calling      : params.skip_repeat_calling,
         skip_repeat_annotation   : params.skip_repeat_annotation,
@@ -115,8 +115,9 @@ def parameterStatus = [
         genmod_reduced_penetrance: params.genmod_reduced_penetrance,
         genmod_score_config_snvs : params.genmod_score_config_snvs,
         genmod_score_config_svs  : params.genmod_score_config_svs,
-        variant_consequences_snvs : params.variant_consequences_snvs,
+        variant_consequences_snvs: params.variant_consequences_snvs,
         variant_consequences_svs : params.variant_consequences_svs,
+        vep_plugin_files         : params.vep_plugin_files,
     ]
 ]
 
@@ -450,18 +451,22 @@ def checkWorkflowDependencies(String skip, Map combinationsMap, Map statusMap, M
 // Lookup if a file is required by any workflows, and add to errors
 //
 def checkFileDependencies(String file, Map combinationsMap, Map statusMap, Map workflowMap, List errors) {
-    // Get the the workflow required by file
-    def workflowThatRequiresFile = findKeyForValue(file, combinationsMap)
-    // Get the "--skip" for that workflow
-    def workflowSkip = workflowMap[workflowThatRequiresFile]
-    // Get the status of the "--skip", if false then workflow is active
-    def WorkflowIsActive = !statusMap["workflow"][workflowSkip]
-    // Get the file path
-    def FilePath = statusMap["files"][file]
-    // If the workflow that requires the file is active & theres no file available
-    if(WorkflowIsActive && FilePath == null) {
-        errors << "--$workflowSkip is NOT active, the following files are required: --$file"
+    // Get all workflows required by a file
+    def workflowThatRequiresFile = findKeysForValue(file, combinationsMap)
+
+    for (workflow in workflowThatRequiresFile) {
+        // Get the "--skip" for that workflow
+        def workflowSkip = workflowMap[workflow]
+        // Get the status of the "--skip", if false then workflow is active
+        def WorkflowIsActive = !statusMap["workflow"][workflowSkip]
+        // Get the file path
+        def FilePath = statusMap["files"][file]
+        // If the workflow that requires the file is active & theres no file available
+        if(WorkflowIsActive && FilePath == null) {
+            errors << "--$workflowSkip is NOT active, the following files are required: --$file"
+        }
     }
+
     return errors
 }
 
@@ -487,22 +492,19 @@ def findRequiredSkips(paramType, Set<String> requiredWorkflows, Map statusMap, M
     return requiredSkips
 }
 
-def findKeyForValue(def valueToFind, Map map) {
+def findKeysForValue(def valueToFind, Map map) {
+
+    def keys = []
+
     for (entry in map) {
         def key = entry.key
         def value = entry.value
 
-        if (value instanceof List) {
-            if (value.contains(valueToFind)) {
-                return key
-            }
-        } else {
-            if (value == valueToFind) {
-                return key
-            }
+        if ((value instanceof List && value.contains(valueToFind)) || value == valueToFind) {
+            keys << key
         }
     }
-    return null // Value not found
+    return keys.isEmpty() ? null : keys
 }
 
 // Utility function to create channels from references

diff --git a/workflows/nallo.nf b/workflows/nallo.nf
@@ -87,9 +87,9 @@ workflow NALLO {
     ch_par                       = createReferenceChannelFromPath(params.par_regions)
     ch_trgt_bed                  = createReferenceChannelFromPath(params.trgt_repeats)
     ch_stranger_repeat_catalog   = createReferenceChannelFromPath(params.stranger_repeat_catalog)
-    ch_variant_consequences_snvs  = createReferenceChannelFromPath(params.variant_consequences_snvs)
+    ch_variant_consequences_snvs = createReferenceChannelFromPath(params.variant_consequences_snvs)
     ch_variant_consequences_svs  = createReferenceChannelFromPath(params.variant_consequences_svs)
-    ch_vep_cache_unprocessed     = createReferenceChannelFromPath(params.vep_cache, Channel.value([]))
+    ch_vep_cache_unprocessed     = createReferenceChannelFromPath(params.vep_cache, Channel.value([[],[]]))
     ch_expected_xy_bed           = createReferenceChannelFromPath(params.hificnv_expected_xy_cn)
     ch_expected_xx_bed           = createReferenceChannelFromPath(params.hificnv_expected_xx_cn)
     ch_exclude_bed               = createReferenceChannelFromPath(params.hificnv_excluded_regions)
@@ -127,8 +127,8 @@ workflow NALLO {
         PREPARE_GENOME (
             ch_fasta,
             ch_vep_cache_unprocessed,
-            params.fasta.endsWith('.gz'),       // should we unzip fasta
-            params.vep_cache.endsWith("tar.gz") // should we untar vep cache
+            params.fasta.endsWith('.gz'),                           // should we unzip fasta
+            params.vep_cache && params.vep_cache.endsWith("tar.gz") // should we untar vep cache
         )
         ch_versions = ch_versions.mix(PREPARE_GENOME.out.versions)