fix annotation

nf-core · Jan 28, 2025 · ac66238 · ac66238
1 parent e0e6289
commit ac66238
Show file tree

Hide file tree

Showing 9 changed files with 50 additions and 131 deletions.
diff --git a/main.nf b/main.nf
@@ -32,6 +32,10 @@ include { PIPELINE_COMPLETION             } from './subworkflows/local/utils_nfc
 include { PIPELINE_INITIALISATION         } from './subworkflows/local/utils_nfcore_sarek_pipeline'
 include { PREPARE_INTERVALS               } from './subworkflows/local/prepare_intervals'
 include { PREPARE_REFERENCE_CNVKIT        } from './subworkflows/local/prepare_reference_cnvkit'
+include { extract_references_file        } from './subworkflows/local/yaml_references'
+include { extract_references_value      } from './subworkflows/local/yaml_references'
+include { extract_references_vcf        } from './subworkflows/local/yaml_references'
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     RUN MAIN WORKFLOW
@@ -277,42 +281,3 @@ workflow NFCORE_SAREK {
     emit:
     multiqc_report = SAREK.out.multiqc_report // channel: /path/to/multiqc_report.html
 }
-
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    FUNCTIONS TO EXTRACT REFERENCES FILES OR VALUES FROM THE REFERENCES YAML OR PARAMS
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
-
-def extract_references_file(references, param, attribute) {
-    references.map { meta, _readme ->
-        if (param || meta[attribute]) {
-            return [meta.subMap(['id']), file(param ?: meta[attribute] ?: [])]
-        }
-        else {
-            return null
-        }
-    }
-}
-
-def extract_references_vcf(references, param, vcf_attribute, attribute) {
-    references.map { meta, _readme ->
-        if (param || meta.vcf[vcf_attribute][attribute]) {
-            return [meta.subMap(['id']), file(param ?: meta.vcf[vcf_attribute][attribute] ?: [])]
-        }
-        else {
-            return null
-        }
-    }
-}
-
-def extract_references_value(references, param, attribute) {
-    references.map { meta, _readme ->
-        if (param || meta[attribute]) {
-            return [meta.subMap(['id']), param ?: meta[attribute] ?: []]
-        }
-        else {
-            return null
-        }
-    }
-}
diff --git a/subworkflows/local/vcf_annotate_all/main.nf b/subworkflows/local/vcf_annotate_all/main.nf
@@ -39,7 +39,7 @@ workflow VCF_ANNOTATE_ALL {
 
 
     if (tools.split(',').contains('merge') || tools.split(',').contains('snpeff')) {
-        VCF_ANNOTATE_SNPEFF(vcf, snpeff_db, snpeff_cache)
+        VCF_ANNOTATE_SNPEFF(vcf, snpeff_db.map { _meta, snpeff_db_ -> snpeff_db_ }, snpeff_cache)
 
         reports = reports.mix(VCF_ANNOTATE_SNPEFF.out.reports.map { _meta, reports_ -> [reports_] })
         vcf_ann = vcf_ann.mix(VCF_ANNOTATE_SNPEFF.out.vcf_tbi)

diff --git a/subworkflows/local/yaml_references/main.nf b/subworkflows/local/yaml_references/main.nf
@@ -0,0 +1,38 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    FUNCTIONS TO EXTRACT REFERENCES FILES OR VALUES FROM THE REFERENCES YAML OR PARAMS
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+def extract_references_file(references, param, attribute) {
+    references.map { meta, _readme ->
+        if (param || meta[attribute]) {
+            return [meta.subMap(['id']), file(param ?: meta[attribute] ?: [])]
+        }
+        else {
+            return null
+        }
+    }
+}
+
+def extract_references_vcf(references, param, vcf_attribute, attribute) {
+    references.map { meta, _readme ->
+        if (param || meta.vcf[vcf_attribute][attribute]) {
+            return [meta.subMap(['id']), file(param ?: meta.vcf[vcf_attribute][attribute] ?: [])]
+        }
+        else {
+            return null
+        }
+    }
+}
+
+def extract_references_value(references, param, attribute) {
+    references.map { meta, _readme ->
+        if (param || meta[attribute]) {
+            return [meta.subMap(['id']), param ?: meta[attribute] ?: []]
+        }
+        else {
+            return null
+        }
+    }
+}
diff --git a/tests/annotation_bcfann.nf.test.snap b/tests/annotation_bcfann.nf.test.snap
@@ -37,4 +37,4 @@
         },
         "timestamp": "2024-10-29T09:38:54.991004"
     }
-}
+}
diff --git a/tests/annotation_merge.nf.test b/tests/annotation_merge.nf.test
@@ -13,8 +13,6 @@ nextflow_pipeline {
                 outdir = "$outputDir"
                 input = "${projectDir}/tests/csv/3.0/vcf_single.csv"
                 step  = 'annotate'
-                snpeff_cache = 's3://annotation-cache/snpeff_cache/'
-                vep_cache = 's3://annotation-cache/vep_cache/'
                 tools = 'merge'
             }
         }
@@ -48,8 +46,6 @@ nextflow_pipeline {
                 outdir = "$outputDir"
                 input = "${projectDir}/tests/csv/3.0/vcf_single.csv"
                 step  = 'annotate'
-                snpeff_cache = 's3://annotation-cache/snpeff_cache/'
-                vep_cache = 's3://annotation-cache/vep_cache/'
                 tools = 'merge,snpeff,vep'
             }
         }

diff --git a/tests/annotation_merge.nf.test.snap b/tests/annotation_merge.nf.test.snap
@@ -197,9 +197,9 @@
             ]
         ],
         "meta": {
-            "nf-test": "0.9.1",
-            "nextflow": "24.10.0"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2024-10-29T09:56:59.385257"
+        "timestamp": "2025-01-28T17:58:56.512301159"
     }
-}
+}
diff --git a/tests/annotation_snpeff.nf.test b/tests/annotation_snpeff.nf.test
@@ -5,51 +5,14 @@ nextflow_pipeline {
     tag "pipeline"
     tag "pipeline_sarek"
 
-    test("Run with profile test | --tools snpeff --download_cache") {
-
-        when {
-            params {
-                modules_testdata_base_path = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/'
-                outdir = "$outputDir"
-                input = "${projectDir}/tests/csv/3.0/vcf_single.csv"
-                step  = 'annotate'
-                download_cache = true
-                tools = 'snpeff'
-            }
-        }
-
-        then {
-            // stable_name: All files + folders in ${params.outdir}/ with a stable name
-            def stable_name = getAllFilesFromDir(params.outdir, relative: true, includeDir: true, ignore: ['pipeline_info/*.{html,json,txt}'])
-            // stable_path: All files in ${params.outdir}/ with stable content
-            def stable_path = getAllFilesFromDir(params.outdir, ignoreFile: 'tests/.nftignore')
-            assertAll(
-                { assert workflow.success},
-                { assert snapshot(
-                    // Number of successful tasks
-                    workflow.trace.succeeded().size(),
-                    // pipeline versions.yml file for multiqc from which Nextflow version is removed because we tests pipelines on multiple Nextflow versions
-                    removeNextflowVersion("$outputDir/pipeline_info/nf_core_sarek_software_mqc_versions.yml"),
-                    // All stable path name, with a relative path
-                    stable_name,
-                    // All files with stable contents
-                    stable_path
-                ).match() }
-            )
-        }
-    }
-
-    test("Fails with profile test | --tools snpeff --snpeff_db na --build_only_index") {
+    test("Fails with profile test | --tools snpeff --snpeff_db na") {
         when {
             params {
                 modules_testdata_base_path = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/'
                 outdir = "$outputDir"
                 input = "${projectDir}/tests/csv/3.0/vcf_single.csv"
                 step  = 'annotate'
-                snpeff_cache = 's3://annotation-cache/snpeff_cache/'
                 snpeff_db = "na"
-                input = false
-                build_only_index = true
                 tools = 'snpeff'
             }
         }

diff --git a/tests/annotation_vep.nf.test b/tests/annotation_vep.nf.test
@@ -5,41 +5,7 @@ nextflow_pipeline {
     tag "pipeline"
     tag "pipeline_sarek"
 
-    test("Run with profile test | --tools vep --download_cache --vep_include_fasta") {
-
-        when {
-            params {
-                modules_testdata_base_path = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/'
-                outdir = "$outputDir"
-                input = "${projectDir}/tests/csv/3.0/vcf_single.csv"
-                step  = 'annotate'
-                download_cache = true
-                tools = 'vep'
-            }
-        }
-
-        then {
-            // stable_name: All files + folders in ${params.outdir}/ with a stable name
-            def stable_name = getAllFilesFromDir(params.outdir, relative: true, includeDir: true, ignore: ['pipeline_info/*.{html,json,txt}'])
-            // stable_path: All files in ${params.outdir}/ with stable content
-            def stable_path = getAllFilesFromDir(params.outdir, ignoreFile: 'tests/.nftignore')
-            assertAll(
-                { assert workflow.success},
-                { assert snapshot(
-                    // Number of successful tasks
-                    workflow.trace.succeeded().size(),
-                    // pipeline versions.yml file for multiqc from which Nextflow version is removed because we tests pipelines on multiple Nextflow versions
-                    removeNextflowVersion("$outputDir/pipeline_info/nf_core_sarek_software_mqc_versions.yml"),
-                    // All stable path name, with a relative path
-                    stable_name,
-                    // All files with stable contents
-                    stable_path
-                ).match() }
-            )
-        }
-    }
-
-    test("Fails with profile test | --tools vep --vep_cache_version 1 --build_only_index") {
+    test("Fails with profile test | --tools vep --vep_cache_version 1") {
         when {
             params {
                 modules_testdata_base_path = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/'
@@ -48,8 +14,6 @@ nextflow_pipeline {
                 step  = 'annotate'
                 vep_cache = 's3://annotation-cache/vep_cache/'
                 vep_cache_version = 1
-                input = false
-                build_only_index = true
                 tools = 'vep'
             }
         }

diff --git a/workflows/sarek/main.nf b/workflows/sarek/main.nf
@@ -861,13 +861,6 @@ workflow SAREK {
 
             vep_fasta = params.vep_include_fasta ? fasta : [[id: 'null'], []]
 
-            println("vep_fasta: ${vep_fasta}")
-            vep_genome.view()
-            vep_species.view()
-            vep_cache_version.view()
-            vep_cache.view()
-            println("vep_extra_files: ${vep_extra_files}")
-
             VCF_ANNOTATE_ALL(
                 vcf_to_annotate.map { meta, vcf -> [meta + [file_name: vcf.baseName], vcf] },
                 vep_fasta,
-Original file line number
+Diff line change
@@ Expand Up / @@ -37,4 +37,4 @@ @@
             },
             "timestamp": "2024-10-29T09:38:54.991004"
         }
-    }
+    }