From 573ab99a85679341ca51fed6b0868d983c9bc2f1 Mon Sep 17 00:00:00 2001
From: asp8200 <aspe@clin.au.dk>
Date: Wed, 8 Jun 2022 18:15:55 +0200
Subject: [PATCH 01/12] WIP: Adding option for setting file-output-format for
 VEP

---
 conf/modules.config                           | 14 +++++++++++---
 modules/nf-core/modules/ensemblvep/main.nf    | 16 ++++++++++------
 nextflow.config                               |  1 +
 subworkflows/local/annotate.nf                | 19 ++++++++++++-------
 .../nf-core/annotation/ensemblvep/main.nf     |  5 ++++-
 workflows/sarek.nf                            |  1 +
 6 files changed, 39 insertions(+), 17 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index 7a4e0b055d..e8c0f4ede2 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -1028,11 +1028,19 @@ process{
             (params.vep_spliceai && params.spliceai_snv && params.spliceai_indel) ? '--plugin SpliceAI,snv=spliceai_scores.raw.snv.hg38.vcf.gz,indel=spliceai_scores.raw.indel.hg38.vcf.gz'                     : '',
             (params.vep_spliceregion)                                             ? '--plugin SpliceRegion'                                                                                                     : ''
         ].join(' ').trim()
+        ext.suffix = '_VEP'
         if (!params.vep_cache)    container = { params.vep_genome ? "nfcore/vep:104.3.${params.vep_genome}" : "nfcore/vep:104.3.${params.genome}" }
         publishDir       = [
-            mode: params.publish_dir_mode,
-            path: { "${params.outdir}/reports/EnsemblVEP/${meta.id}/${meta.variantcaller}" },
-            pattern: "*html"
+            [
+                mode: params.publish_dir_mode,
+                path: { "${params.outdir}/reports/EnsemblVEP/${meta.id}/${meta.variantcaller}" },
+                pattern: "*html"
+            ],
+            [
+                mode: params.publish_dir_mode,
+                path: { "${params.outdir}/annotation/${meta.id}/${meta.variantcaller}" },
+                pattern: "*{json,tab}"
+            ]
         ]
     }
 
diff --git a/modules/nf-core/modules/ensemblvep/main.nf b/modules/nf-core/modules/ensemblvep/main.nf
index a5a9b1abcc..9847182ec1 100644
--- a/modules/nf-core/modules/ensemblvep/main.nf
+++ b/modules/nf-core/modules/ensemblvep/main.nf
@@ -9,6 +9,7 @@ process ENSEMBLVEP {
 
     input:
     tuple val(meta), path(vcf)
+    val   vep_output
     val   genome
     val   species
     val   cache_version
@@ -16,15 +17,18 @@ process ENSEMBLVEP {
     path  extra_files
 
     output:
-    tuple val(meta), path("*.ann.vcf"), emit: vcf
-    path "*.summary.html"             , emit: report
-    path "versions.yml"               , emit: versions
+    tuple val(meta), path("*.ann.vcf")  , optional:true, emit: vcf
+    tuple val(meta), path("*.ann.tab")  , optional:true, emit: tab
+    tuple val(meta), path("*.ann.json") , optional:true, emit: json
+    path "*.summary.html"               , emit: report
+    path "versions.yml"                 , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
+    def suffix = task.ext.suffix ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     def dir_cache = cache ? "\${PWD}/${cache}" : "/.vep"
     """
@@ -32,7 +36,7 @@ process ENSEMBLVEP {
 
     vep \\
         -i $vcf \\
-        -o ${prefix}.ann.vcf \\
+        -o ${prefix}${suffix}.ann.$vep_output \\
         $args \\
         --assembly $genome \\
         --species $species \\
@@ -40,8 +44,8 @@ process ENSEMBLVEP {
         --cache_version $cache_version \\
         --dir_cache $dir_cache \\
         --fork $task.cpus \\
-        --vcf \\
-        --stats_file ${prefix}.summary.html
+        --stats_file ${prefix}.summary.html \\
+        --$vep_output
 
     rm -rf $prefix
 
diff --git a/nextflow.config b/nextflow.config
index 3c98b3ebb8..043a171083 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -69,6 +69,7 @@ params {
     joint_germline = false //
 
     // Annotation
+    vep_output = 'vcf'
     vep_dbnsfp = null // dbnsfp plugin disabled within VEP
     dbnsfp = null // No dbnsfp processed file
     dbnsfp_tbi = null // No dbnsfp processed file index
diff --git a/subworkflows/local/annotate.nf b/subworkflows/local/annotate.nf
index a9c386b011..fd2a9a7d5a 100644
--- a/subworkflows/local/annotate.nf
+++ b/subworkflows/local/annotate.nf
@@ -12,6 +12,7 @@ workflow ANNOTATE {
     tools
     snpeff_db
     snpeff_cache
+    vep_output
     vep_genome
     vep_species
     vep_cache_version
@@ -41,15 +42,19 @@ workflow ANNOTATE {
     }
 
     if (tools.contains('vep')) {
-        ANNOTATION_ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
+        ANNOTATION_ENSEMBLVEP(vcf, vep_output, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
 
-        ch_reports  = ch_reports.mix(ANNOTATION_ENSEMBLVEP.out.reports)
-        ch_vcf_ann  = ch_vcf_ann.mix(ANNOTATION_ENSEMBLVEP.out.vcf_tbi)
-        ch_versions = ch_versions.mix(ANNOTATION_ENSEMBLVEP.out.versions.first())
+        ch_reports   = ch_reports.mix(ANNOTATION_ENSEMBLVEP.out.reports)
+        ch_vcf_ann   = ch_vcf_ann.mix(ANNOTATION_ENSEMBLVEP.out.vcf_tbi)
+        ch_tab_ann   = ch_vcf_ann.mix(ANNOTATION_ENSEMBLVEP.out.tab)
+        ch_json_ann  = ch_vcf_ann.mix(ANNOTATION_ENSEMBLVEP.out.json)
+        ch_versions  = ch_versions.mix(ANNOTATION_ENSEMBLVEP.out.versions.first())
     }
 
     emit:
-    vcf_ann  = ch_vcf_ann      // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
-    reports  = ch_reports      //    path: *.html
-    versions = ch_versions     //    path: versions.yml
+    vcf_ann   = ch_vcf_ann      // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
+    tab_ann   = ch_tab_ann
+    json_ann  = ch_json_ann
+    reports   = ch_reports      //    path: *.html
+    versions  = ch_versions     //    path: versions.yml
 }
diff --git a/subworkflows/nf-core/annotation/ensemblvep/main.nf b/subworkflows/nf-core/annotation/ensemblvep/main.nf
index 4c7d0e3e69..8d1cc849b6 100644
--- a/subworkflows/nf-core/annotation/ensemblvep/main.nf
+++ b/subworkflows/nf-core/annotation/ensemblvep/main.nf
@@ -8,6 +8,7 @@ include { TABIX_BGZIPTABIX } from '../../../../modules/nf-core/modules/tabix/bgz
 workflow ANNOTATION_ENSEMBLVEP {
     take:
     vcf               // channel: [ val(meta), vcf ]
+    vep_output
     vep_genome        //   value: genome to use
     vep_species       //   value: species to use
     vep_cache_version //   value: cache version to use
@@ -17,7 +18,7 @@ workflow ANNOTATION_ENSEMBLVEP {
     main:
     ch_versions = Channel.empty()
 
-    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
+    ENSEMBLVEP(vcf, vep_output, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
     TABIX_BGZIPTABIX(ENSEMBLVEP.out.vcf)
 
     // Gather versions of all tools used
@@ -26,6 +27,8 @@ workflow ANNOTATION_ENSEMBLVEP {
 
     emit:
     vcf_tbi  = TABIX_BGZIPTABIX.out.gz_tbi // channel: [ val(meta), vcf.gz, vcf.gz.tbi ]
+    json     = ENSEMBLVEP.out.json
+    tab      = ENSEMBLVEP.out.tab
     reports  = ENSEMBLVEP.out.report       //    path: *.html
     versions = ch_versions                 //    path: versions.yml
 }
diff --git a/workflows/sarek.nf b/workflows/sarek.nf
index dec5b15ca3..6fffb38fe7 100644
--- a/workflows/sarek.nf
+++ b/workflows/sarek.nf
@@ -867,6 +867,7 @@ workflow SAREK {
                 params.tools,
                 snpeff_db,
                 snpeff_cache,
+                params.vep_output,
                 vep_genome,
                 vep_species,
                 vep_cache_version,

From 81e0a7865143628ff8b918f4d97b6a0d04d041de Mon Sep 17 00:00:00 2001
From: Lasse Folkersen <lassefolkersen@gmail.com>
Date: Fri, 10 Jun 2022 06:43:03 +0000
Subject: [PATCH 02/12] suggestion on how to get the output extension in the
 args instead

---
 modules/nf-core/modules/ensemblvep/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/nf-core/modules/ensemblvep/main.nf b/modules/nf-core/modules/ensemblvep/main.nf
index 9847182ec1..e1ee948237 100644
--- a/modules/nf-core/modules/ensemblvep/main.nf
+++ b/modules/nf-core/modules/ensemblvep/main.nf
@@ -29,7 +29,7 @@ process ENSEMBLVEP {
     script:
     def args = task.ext.args ?: ''
     def suffix = task.ext.suffix ?: ''
-    def prefix = task.ext.prefix ?: "${meta.id}"
+    def prefix = args.prefix ? "$args.prefix" : "${meta.id}"
     def dir_cache = cache ? "\${PWD}/${cache}" : "/.vep"
     """
     mkdir $prefix

From 93e90978b4901972855238c985660e8fab2819b9 Mon Sep 17 00:00:00 2001
From: asp8200 <aspe@clin.au.dk>
Date: Fri, 10 Jun 2022 16:19:09 +0200
Subject: [PATCH 03/12] Setting vep-output-format via task.ext.vep_output

---
 conf/modules.config                                | 1 +
 modules/nf-core/modules/ensemblvep/main.nf         | 4 ++--
 subworkflows/local/annotate.nf                     | 3 +--
 subworkflows/nf-core/annotation/ensemblvep/main.nf | 3 +--
 workflows/sarek.nf                                 | 1 -
 5 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index e8c0f4ede2..cbd99a07a0 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -1029,6 +1029,7 @@ process{
             (params.vep_spliceregion)                                             ? '--plugin SpliceRegion'                                                                                                     : ''
         ].join(' ').trim()
         ext.suffix = '_VEP'
+        ext.vep_output = params.vep_output
         if (!params.vep_cache)    container = { params.vep_genome ? "nfcore/vep:104.3.${params.vep_genome}" : "nfcore/vep:104.3.${params.genome}" }
         publishDir       = [
             [
diff --git a/modules/nf-core/modules/ensemblvep/main.nf b/modules/nf-core/modules/ensemblvep/main.nf
index e1ee948237..51cef6b991 100644
--- a/modules/nf-core/modules/ensemblvep/main.nf
+++ b/modules/nf-core/modules/ensemblvep/main.nf
@@ -9,7 +9,6 @@ process ENSEMBLVEP {
 
     input:
     tuple val(meta), path(vcf)
-    val   vep_output
     val   genome
     val   species
     val   cache_version
@@ -28,8 +27,9 @@ process ENSEMBLVEP {
 
     script:
     def args = task.ext.args ?: ''
+    def vep_output = task.ext.vep_output ?: 'vcf'
     def suffix = task.ext.suffix ?: ''
-    def prefix = args.prefix ? "$args.prefix" : "${meta.id}"
+    def prefix = task.ext.prefix ?: "${meta.id}"
     def dir_cache = cache ? "\${PWD}/${cache}" : "/.vep"
     """
     mkdir $prefix
diff --git a/subworkflows/local/annotate.nf b/subworkflows/local/annotate.nf
index fd2a9a7d5a..06cf473a5e 100644
--- a/subworkflows/local/annotate.nf
+++ b/subworkflows/local/annotate.nf
@@ -12,7 +12,6 @@ workflow ANNOTATE {
     tools
     snpeff_db
     snpeff_cache
-    vep_output
     vep_genome
     vep_species
     vep_cache_version
@@ -42,7 +41,7 @@ workflow ANNOTATE {
     }
 
     if (tools.contains('vep')) {
-        ANNOTATION_ENSEMBLVEP(vcf, vep_output, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
+        ANNOTATION_ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
 
         ch_reports   = ch_reports.mix(ANNOTATION_ENSEMBLVEP.out.reports)
         ch_vcf_ann   = ch_vcf_ann.mix(ANNOTATION_ENSEMBLVEP.out.vcf_tbi)
diff --git a/subworkflows/nf-core/annotation/ensemblvep/main.nf b/subworkflows/nf-core/annotation/ensemblvep/main.nf
index 8d1cc849b6..08ada62294 100644
--- a/subworkflows/nf-core/annotation/ensemblvep/main.nf
+++ b/subworkflows/nf-core/annotation/ensemblvep/main.nf
@@ -8,7 +8,6 @@ include { TABIX_BGZIPTABIX } from '../../../../modules/nf-core/modules/tabix/bgz
 workflow ANNOTATION_ENSEMBLVEP {
     take:
     vcf               // channel: [ val(meta), vcf ]
-    vep_output
     vep_genome        //   value: genome to use
     vep_species       //   value: species to use
     vep_cache_version //   value: cache version to use
@@ -18,7 +17,7 @@ workflow ANNOTATION_ENSEMBLVEP {
     main:
     ch_versions = Channel.empty()
 
-    ENSEMBLVEP(vcf, vep_output, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
+    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
     TABIX_BGZIPTABIX(ENSEMBLVEP.out.vcf)
 
     // Gather versions of all tools used
diff --git a/workflows/sarek.nf b/workflows/sarek.nf
index 6fffb38fe7..dec5b15ca3 100644
--- a/workflows/sarek.nf
+++ b/workflows/sarek.nf
@@ -867,7 +867,6 @@ workflow SAREK {
                 params.tools,
                 snpeff_db,
                 snpeff_cache,
-                params.vep_output,
                 vep_genome,
                 vep_species,
                 vep_cache_version,

From d5cc7887acfbdda245940eb090c1b2a185a1f845 Mon Sep 17 00:00:00 2001
From: asp8200 <aspe@clin.au.dk>
Date: Mon, 13 Jun 2022 13:59:23 +0200
Subject: [PATCH 04/12] Including vep-output-format in args for
 ENSEMBLVEP-module

---
 conf/modules.config                        | 10 +++++++---
 modules/nf-core/modules/ensemblvep/main.nf |  9 ++-------
 nextflow.config                            |  2 +-
 3 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index cbd99a07a0..de039e3ff1 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -1026,10 +1026,9 @@ process{
             (params.vep_dbnsfp && params.dbnsfp)                                  ? '--plugin dbNSFP,dbNSFP.gz,rs_dbSNP,HGVSc_VEP,HGVSp_VEP,1000Gp3_EAS_AF,1000Gp3_AMR_AF,LRT_score,GERP++_RS,gnomAD_exomes_AF' : '',
             (params.vep_loftee)                                                   ? '--plugin LoF,loftee_path:/opt/conda/envs/nf-core-vep-104.3/share/ensembl-vep-104.3-0'                                      : '',
             (params.vep_spliceai && params.spliceai_snv && params.spliceai_indel) ? '--plugin SpliceAI,snv=spliceai_scores.raw.snv.hg38.vcf.gz,indel=spliceai_scores.raw.indel.hg38.vcf.gz'                     : '',
-            (params.vep_spliceregion)                                             ? '--plugin SpliceRegion'                                                                                                     : ''
+            (params.vep_spliceregion)                                             ? '--plugin SpliceRegion'                                                                                                     : '',
+            (params.vep_out_format)                                               ? "--${params.vep_out_format}"                                                                                                : '--vcf'
         ].join(' ').trim()
-        ext.suffix = '_VEP'
-        ext.vep_output = params.vep_output
         if (!params.vep_cache)    container = { params.vep_genome ? "nfcore/vep:104.3.${params.vep_genome}" : "nfcore/vep:104.3.${params.genome}" }
         publishDir       = [
             [
@@ -1045,6 +1044,11 @@ process{
         ]
     }
 
+    withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_ENSEMBLVEP:ENSEMBLVEP' {
+        ext.prefix      = {"${meta.id}_VEP.ann"}
+        ext.args2       = {"${params.vep_out_format}"}
+    }
+
     withName: ".*:ANNOTATION_MERGE:ENSEMBLVEP" {
         ext.prefix       = {"${meta.id}_snpEff"}
     }
diff --git a/modules/nf-core/modules/ensemblvep/main.nf b/modules/nf-core/modules/ensemblvep/main.nf
index 51cef6b991..3886f8a804 100644
--- a/modules/nf-core/modules/ensemblvep/main.nf
+++ b/modules/nf-core/modules/ensemblvep/main.nf
@@ -27,16 +27,13 @@ process ENSEMBLVEP {
 
     script:
     def args = task.ext.args ?: ''
-    def vep_output = task.ext.vep_output ?: 'vcf'
-    def suffix = task.ext.suffix ?: ''
+    def args2 = task.ext.args2 ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     def dir_cache = cache ? "\${PWD}/${cache}" : "/.vep"
     """
-    mkdir $prefix
-
     vep \\
         -i $vcf \\
-        -o ${prefix}${suffix}.ann.$vep_output \\
+        -o ${prefix}.${args2} \\
         $args \\
         --assembly $genome \\
         --species $species \\
@@ -45,9 +42,7 @@ process ENSEMBLVEP {
         --dir_cache $dir_cache \\
         --fork $task.cpus \\
         --stats_file ${prefix}.summary.html \\
-        --$vep_output
 
-    rm -rf $prefix
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/nextflow.config b/nextflow.config
index 043a171083..47d0373f6b 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -69,7 +69,7 @@ params {
     joint_germline = false //
 
     // Annotation
-    vep_output = 'vcf'
+    vep_out_format = 'vcf'
     vep_dbnsfp = null // dbnsfp plugin disabled within VEP
     dbnsfp = null // No dbnsfp processed file
     dbnsfp_tbi = null // No dbnsfp processed file index

From 58a26f2c6159abf52efd147a739c16c9710858d4 Mon Sep 17 00:00:00 2001
From: asp8200 <aspe@clin.au.dk>
Date: Tue, 14 Jun 2022 15:49:21 +0200
Subject: [PATCH 05/12] Fetching vep-output-file-extension from args. (No
 longer using args2.)

---
 conf/modules.config                        | 2 +-
 modules/nf-core/modules/ensemblvep/main.nf | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index de039e3ff1..babe099e84 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -1045,7 +1045,7 @@ process{
     }
 
     withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_ENSEMBLVEP:ENSEMBLVEP' {
-        ext.prefix      = {"${meta.id}_VEP.ann"}
+        ext.prefix      = {"${meta.id}_VEP"}
         ext.args2       = {"${params.vep_out_format}"}
     }
 
diff --git a/modules/nf-core/modules/ensemblvep/main.nf b/modules/nf-core/modules/ensemblvep/main.nf
index 3886f8a804..debebbc049 100644
--- a/modules/nf-core/modules/ensemblvep/main.nf
+++ b/modules/nf-core/modules/ensemblvep/main.nf
@@ -27,13 +27,13 @@ process ENSEMBLVEP {
 
     script:
     def args = task.ext.args ?: ''
-    def args2 = task.ext.args2 ?: ''
+    def file_extension = args.contains("--vcf") ? 'vcf' : args.contains("--json")? 'json' : args.contains("--tab")? 'tab' : 'vcf'
     def prefix = task.ext.prefix ?: "${meta.id}"
     def dir_cache = cache ? "\${PWD}/${cache}" : "/.vep"
     """
     vep \\
         -i $vcf \\
-        -o ${prefix}.${args2} \\
+        -o ${prefix}.ann.${file_extension} \\
         $args \\
         --assembly $genome \\
         --species $species \\

From c7b85196dd020d2f3828c87dcf9e1ec87b970991 Mon Sep 17 00:00:00 2001
From: asp8200 <aspe@clin.au.dk>
Date: Tue, 14 Jun 2022 16:44:22 +0200
Subject: [PATCH 06/12] Initializing empty channels for tab_ann and json_ann

---
 conf/modules.config                        | 1 -
 modules/nf-core/modules/ensemblvep/main.nf | 2 +-
 subworkflows/local/annotate.nf             | 8 +++++---
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index babe099e84..d8e9efd1ca 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -1046,7 +1046,6 @@ process{
 
     withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_ENSEMBLVEP:ENSEMBLVEP' {
         ext.prefix      = {"${meta.id}_VEP"}
-        ext.args2       = {"${params.vep_out_format}"}
     }
 
     withName: ".*:ANNOTATION_MERGE:ENSEMBLVEP" {
diff --git a/modules/nf-core/modules/ensemblvep/main.nf b/modules/nf-core/modules/ensemblvep/main.nf
index debebbc049..ccc6838c38 100644
--- a/modules/nf-core/modules/ensemblvep/main.nf
+++ b/modules/nf-core/modules/ensemblvep/main.nf
@@ -27,7 +27,7 @@ process ENSEMBLVEP {
 
     script:
     def args = task.ext.args ?: ''
-    def file_extension = args.contains("--vcf") ? 'vcf' : args.contains("--json")? 'json' : args.contains("--tab")? 'tab' : 'vcf'
+    def file_extension = args.contains("--vcf") ? 'vcf' : args.contains("--json") ? 'json' : args.contains("--tab") ? 'tab' : 'vcf'
     def prefix = task.ext.prefix ?: "${meta.id}"
     def dir_cache = cache ? "\${PWD}/${cache}" : "/.vep"
     """
diff --git a/subworkflows/local/annotate.nf b/subworkflows/local/annotate.nf
index 06cf473a5e..dde37b7a3b 100644
--- a/subworkflows/local/annotate.nf
+++ b/subworkflows/local/annotate.nf
@@ -19,9 +19,11 @@ workflow ANNOTATE {
     vep_extra_files
 
     main:
-    ch_reports  = Channel.empty()
-    ch_vcf_ann  = Channel.empty()
-    ch_versions = Channel.empty()
+    ch_reports   = Channel.empty()
+    ch_vcf_ann   = Channel.empty()
+    ch_tab_ann   = Channel.empty()
+    ch_json_ann  = Channel.empty()
+    ch_versions  = Channel.empty()
 
     if (tools.contains('merge') || tools.contains('snpeff')) {
         ANNOTATION_SNPEFF(vcf, snpeff_db, snpeff_cache)

From ec7df344bb5c7803fdb7fa7fe573d1c3ab73bfbe Mon Sep 17 00:00:00 2001
From: Anders Sune Pedersen <aspe@clin.au.dk>
Date: Tue, 14 Jun 2022 17:10:00 +0200
Subject: [PATCH 07/12] Adding new CLI-option vep_out_format to
 nextflow_schema.json

---
 nextflow_schema.json | 33 ++++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index e5e029de25..47cd44572d 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -10,7 +10,11 @@
             "type": "object",
             "fa_icon": "fas fa-terminal",
             "description": "Define where the pipeline should find input data and save output data.",
-            "required": ["step", "input", "outdir"],
+            "required": [
+                "step",
+                "input",
+                "outdir"
+            ],
             "properties": {
                 "step": {
                     "type": "string",
@@ -199,7 +203,11 @@
                     "type": "string",
                     "default": "bwa-mem",
                     "fa_icon": "fas fa-puzzle-piece",
-                    "enum": ["bwa-mem", "bwa-mem2", "dragmap"],
+                    "enum": [
+                        "bwa-mem",
+                        "bwa-mem2",
+                        "dragmap"
+                    ],
                     "description": "Specify aligner to be used to map reads to reference genome.",
                     "help_text": "> **WARNING** Current indices for `bwa` in AWS iGenomes are not compatible with `bwa-mem2` and `dragmap`.\n> `Sarek` will build them automatically if not provided.\n\n> **WARNING** BWA-mem2 is in active development\n> Sarek might not be able to require the right amount of resources for it at the moment\n> We recommend to use pre-built indexes.",
                     "hidden": true
@@ -557,6 +565,18 @@
                     "description": "VEP cache version.",
                     "help_text": "If you use AWS iGenomes, this has already been set for you appropriately."
                 },
+                "vep_out_format": {
+                    "type": "string",
+                    "default": "vcf",
+                    "description": "VEP output-file format.",
+                    "enum": [
+                        "json",
+                        "tab",
+                        "vcf"
+                    ],
+                    "help_text": "Sets the format of the output-file from VEP. Available formats: json, tab and vcf.",
+                    "fa_icon": "fas fa-table"
+                },
                 "save_reference": {
                     "type": "boolean",
                     "fa_icon": "fas fa-download",
@@ -694,7 +714,14 @@
                     "description": "Method used to save pipeline results to output directory.",
                     "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
                     "fa_icon": "fas fa-copy",
-                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
+                    "enum": [
+                        "symlink",
+                        "rellink",
+                        "link",
+                        "copy",
+                        "copyNoFollow",
+                        "move"
+                    ],
                     "hidden": true
                 },
                 "email": {

From 383d3d12f1668fb7d0150f168aafec2f547c4302 Mon Sep 17 00:00:00 2001
From: asp8200 <aspe@clin.au.dk>
Date: Wed, 15 Jun 2022 15:54:43 +0200
Subject: [PATCH 08/12] New version of VEP-module from nf-core/modules

---
 modules.json                                  |  2 +-
 modules/nf-core/modules/ensemblvep/Dockerfile |  4 ++--
 modules/nf-core/modules/ensemblvep/build.sh   | 12 ++++++------
 .../modules/ensemblvep/environment.yml        |  4 ++--
 modules/nf-core/modules/ensemblvep/main.nf    |  6 +++++-
 modules/nf-core/modules/ensemblvep/meta.yml   | 19 +++++++++++++++++--
 6 files changed, 33 insertions(+), 14 deletions(-)

diff --git a/modules.json b/modules.json
index fab922331e..46418f7c0f 100644
--- a/modules.json
+++ b/modules.json
@@ -70,7 +70,7 @@
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
             },
             "ensemblvep": {
-                "git_sha": "40dd662fd26c3eb3160b7c8cbbe9bff80bbe2c30"
+                "git_sha": "30f72e24822576c6f90a0bf9db678b403c70eccf"
             },
             "fastqc": {
                 "git_sha": "49b18b1639f4f7104187058866a8fab33332bdfe"
diff --git a/modules/nf-core/modules/ensemblvep/Dockerfile b/modules/nf-core/modules/ensemblvep/Dockerfile
index b4a1c66471..4ada7c6bbb 100644
--- a/modules/nf-core/modules/ensemblvep/Dockerfile
+++ b/modules/nf-core/modules/ensemblvep/Dockerfile
@@ -11,8 +11,8 @@ RUN conda env create -f /environment.yml && conda clean -a
 # Setup default ARG variables
 ARG GENOME=GRCh38
 ARG SPECIES=homo_sapiens
-ARG VEP_VERSION=104
-ARG VEP_TAG=104.3
+ARG VEP_VERSION=105
+ARG VEP_TAG=105.0
 
 # Add conda installation dir to PATH (instead of doing 'conda activate')
 ENV PATH /opt/conda/envs/nf-core-vep-${VEP_TAG}/bin:$PATH
diff --git a/modules/nf-core/modules/ensemblvep/build.sh b/modules/nf-core/modules/ensemblvep/build.sh
index 650c8704e5..6f340c0f3d 100644
--- a/modules/nf-core/modules/ensemblvep/build.sh
+++ b/modules/nf-core/modules/ensemblvep/build.sh
@@ -20,9 +20,9 @@ build_push() {
     docker push nfcore/vep:${VEP_TAG}.${GENOME}
 }
 
-build_push "GRCh37"    "homo_sapiens"           "104" "104.3"
-build_push "GRCh38"    "homo_sapiens"           "104" "104.3"
-build_push "GRCm38"    "mus_musculus"           "102" "104.3"
-build_push "GRCm39"    "mus_musculus"           "104" "104.3"
-build_push "CanFam3.1" "canis_lupus_familiaris" "104" "104.3"
-build_push "WBcel235"  "caenorhabditis_elegans" "104" "104.3"
+build_push "GRCh37"    "homo_sapiens"           "105" "105.0"
+build_push "GRCh38"    "homo_sapiens"           "105" "105.0"
+build_push "GRCm38"    "mus_musculus"           "102" "105.0"
+build_push "GRCm39"    "mus_musculus"           "105" "105.0"
+build_push "CanFam3.1" "canis_lupus_familiaris" "104" "105.0"
+build_push "WBcel235"  "caenorhabditis_elegans" "105" "105.0"
diff --git a/modules/nf-core/modules/ensemblvep/environment.yml b/modules/nf-core/modules/ensemblvep/environment.yml
index c0731c26d8..5df85b805d 100644
--- a/modules/nf-core/modules/ensemblvep/environment.yml
+++ b/modules/nf-core/modules/ensemblvep/environment.yml
@@ -1,10 +1,10 @@
 # You can use this file to create a conda environment for this module:
 #   conda env create -f environment.yml
-name: nf-core-vep-104.3
+name: nf-core-vep-105.0
 channels:
   - conda-forge
   - bioconda
   - defaults
 
 dependencies:
-  - bioconda::ensembl-vep=104.3
+  - bioconda::ensembl-vep=105.0
diff --git a/modules/nf-core/modules/ensemblvep/main.nf b/modules/nf-core/modules/ensemblvep/main.nf
index ccc6838c38..391a182def 100644
--- a/modules/nf-core/modules/ensemblvep/main.nf
+++ b/modules/nf-core/modules/ensemblvep/main.nf
@@ -13,6 +13,7 @@ process ENSEMBLVEP {
     val   species
     val   cache_version
     path  cache
+    path  fasta
     path  extra_files
 
     output:
@@ -27,14 +28,17 @@ process ENSEMBLVEP {
 
     script:
     def args = task.ext.args ?: ''
-    def file_extension = args.contains("--vcf") ? 'vcf' : args.contains("--json") ? 'json' : args.contains("--tab") ? 'tab' : 'vcf'
+    def file_extension = args.contains("--vcf") ? 'vcf' : args.contains("--json")? 'json' : args.contains("--tab")? 'tab' : 'vcf'
     def prefix = task.ext.prefix ?: "${meta.id}"
     def dir_cache = cache ? "\${PWD}/${cache}" : "/.vep"
+    def reference = fasta ? "--fasta $fasta" : ""
+
     """
     vep \\
         -i $vcf \\
         -o ${prefix}.ann.${file_extension} \\
         $args \\
+        $reference \\
         --assembly $genome \\
         --species $species \\
         --cache \\
diff --git a/modules/nf-core/modules/ensemblvep/meta.yml b/modules/nf-core/modules/ensemblvep/meta.yml
index 418bb970d9..a4dde8a6fd 100644
--- a/modules/nf-core/modules/ensemblvep/meta.yml
+++ b/modules/nf-core/modules/ensemblvep/meta.yml
@@ -1,5 +1,5 @@
 name: ENSEMBLVEP
-description: Ensembl Variant Effect Predictor (VEP)
+description: Ensembl Variant Effect Predictor (VEP). The output-file-format is controlled through `task.ext.args`.
 keywords:
   - annotation
 tools:
@@ -36,6 +36,11 @@ input:
       type: file
       description: |
         path to VEP cache (optional)
+  - fasta:
+      type: file
+      description: |
+        reference FASTA file (optional)
+      pattern: "*.{fasta,fa}"
   - extra_files:
       type: tuple
       description: |
@@ -44,8 +49,18 @@ output:
   - vcf:
       type: file
       description: |
-        annotated vcf
+        annotated vcf (optional)
       pattern: "*.ann.vcf"
+  - tab:
+      type: file
+      description: |
+        tab file with annotated variants (optional)
+      pattern: "*.ann.tab"
+  - json:
+      type: file
+      description: |
+        json file with annotated variants (optional)
+      pattern: "*.ann.json"
   - report:
       type: file
       description: VEP report file

From b776282a148e8bcc4c10e76ab8764df407b804f9 Mon Sep 17 00:00:00 2001
From: asp8200 <aspe@clin.au.dk>
Date: Wed, 15 Jun 2022 16:08:10 +0200
Subject: [PATCH 09/12] Prettier nextflow_schema.json

---
 nextflow_schema.json | 27 ++++-----------------------
 1 file changed, 4 insertions(+), 23 deletions(-)

diff --git a/nextflow_schema.json b/nextflow_schema.json
index 47cd44572d..2dc41543c3 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -10,11 +10,7 @@
             "type": "object",
             "fa_icon": "fas fa-terminal",
             "description": "Define where the pipeline should find input data and save output data.",
-            "required": [
-                "step",
-                "input",
-                "outdir"
-            ],
+            "required": ["step", "input", "outdir"],
             "properties": {
                 "step": {
                     "type": "string",
@@ -203,11 +199,7 @@
                     "type": "string",
                     "default": "bwa-mem",
                     "fa_icon": "fas fa-puzzle-piece",
-                    "enum": [
-                        "bwa-mem",
-                        "bwa-mem2",
-                        "dragmap"
-                    ],
+                    "enum": ["bwa-mem", "bwa-mem2", "dragmap"],
                     "description": "Specify aligner to be used to map reads to reference genome.",
                     "help_text": "> **WARNING** Current indices for `bwa` in AWS iGenomes are not compatible with `bwa-mem2` and `dragmap`.\n> `Sarek` will build them automatically if not provided.\n\n> **WARNING** BWA-mem2 is in active development\n> Sarek might not be able to require the right amount of resources for it at the moment\n> We recommend to use pre-built indexes.",
                     "hidden": true
@@ -569,11 +561,7 @@
                     "type": "string",
                     "default": "vcf",
                     "description": "VEP output-file format.",
-                    "enum": [
-                        "json",
-                        "tab",
-                        "vcf"
-                    ],
+                    "enum": ["json", "tab", "vcf"],
                     "help_text": "Sets the format of the output-file from VEP. Available formats: json, tab and vcf.",
                     "fa_icon": "fas fa-table"
                 },
@@ -714,14 +702,7 @@
                     "description": "Method used to save pipeline results to output directory.",
                     "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
                     "fa_icon": "fas fa-copy",
-                    "enum": [
-                        "symlink",
-                        "rellink",
-                        "link",
-                        "copy",
-                        "copyNoFollow",
-                        "move"
-                    ],
+                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
                     "hidden": true
                 },
                 "email": {

From e582f1923c2dbcc258ae051c6fa07a61dabc1282 Mon Sep 17 00:00:00 2001
From: asp8200 <aspe@clin.au.dk>
Date: Thu, 16 Jun 2022 12:14:11 +0200
Subject: [PATCH 10/12] Parsing fasta down to VEP-module. Trying to fix
 snpEff/VEP-related CI-tests.

---
 conf/modules.config                                | 2 +-
 subworkflows/local/annotate.nf                     | 5 +++--
 subworkflows/nf-core/annotation/ensemblvep/main.nf | 3 ++-
 workflows/sarek.nf                                 | 1 +
 4 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/conf/modules.config b/conf/modules.config
index d8e9efd1ca..b8353337ab 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -1049,7 +1049,7 @@ process{
     }
 
     withName: ".*:ANNOTATION_MERGE:ENSEMBLVEP" {
-        ext.prefix       = {"${meta.id}_snpEff"}
+        ext.prefix       = {"${meta.id}_snpEff_VEP"}
     }
 
     withName: 'SNPEFF' {
diff --git a/subworkflows/local/annotate.nf b/subworkflows/local/annotate.nf
index dde37b7a3b..a0ee0e9ffa 100644
--- a/subworkflows/local/annotate.nf
+++ b/subworkflows/local/annotate.nf
@@ -9,6 +9,7 @@ include { ANNOTATION_ENSEMBLVEP                     } from '../nf-core/annotatio
 workflow ANNOTATE {
     take:
     vcf          // channel: [ val(meta), vcf ]
+    fasta
     tools
     snpeff_db
     snpeff_cache
@@ -35,7 +36,7 @@ workflow ANNOTATE {
 
     if (tools.contains('merge')) {
         vcf_ann_for_merge = ANNOTATION_SNPEFF.out.vcf_tbi.map{ meta, vcf, tbi -> [meta, vcf] }
-        ANNOTATION_MERGE(vcf_ann_for_merge, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
+        ANNOTATION_MERGE(vcf_ann_for_merge, fasta, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
 
         ch_reports  = ch_reports.mix(ANNOTATION_MERGE.out.reports)
         ch_vcf_ann  = ch_vcf_ann.mix(ANNOTATION_MERGE.out.vcf_tbi)
@@ -43,7 +44,7 @@ workflow ANNOTATE {
     }
 
     if (tools.contains('vep')) {
-        ANNOTATION_ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
+        ANNOTATION_ENSEMBLVEP(vcf, fasta, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
 
         ch_reports   = ch_reports.mix(ANNOTATION_ENSEMBLVEP.out.reports)
         ch_vcf_ann   = ch_vcf_ann.mix(ANNOTATION_ENSEMBLVEP.out.vcf_tbi)
diff --git a/subworkflows/nf-core/annotation/ensemblvep/main.nf b/subworkflows/nf-core/annotation/ensemblvep/main.nf
index 08ada62294..f62553e39e 100644
--- a/subworkflows/nf-core/annotation/ensemblvep/main.nf
+++ b/subworkflows/nf-core/annotation/ensemblvep/main.nf
@@ -8,6 +8,7 @@ include { TABIX_BGZIPTABIX } from '../../../../modules/nf-core/modules/tabix/bgz
 workflow ANNOTATION_ENSEMBLVEP {
     take:
     vcf               // channel: [ val(meta), vcf ]
+    fasta             //   value: fasta to use
     vep_genome        //   value: genome to use
     vep_species       //   value: species to use
     vep_cache_version //   value: cache version to use
@@ -17,7 +18,7 @@ workflow ANNOTATION_ENSEMBLVEP {
     main:
     ch_versions = Channel.empty()
 
-    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
+    ENSEMBLVEP(vcf, vep_genome, vep_species, vep_cache_version, vep_cache, fasta, vep_extra_files)
     TABIX_BGZIPTABIX(ENSEMBLVEP.out.vcf)
 
     // Gather versions of all tools used
diff --git a/workflows/sarek.nf b/workflows/sarek.nf
index dec5b15ca3..6d5e10944c 100644
--- a/workflows/sarek.nf
+++ b/workflows/sarek.nf
@@ -864,6 +864,7 @@ workflow SAREK {
         if (params.tools.contains('merge') || params.tools.contains('snpeff') || params.tools.contains('vep')) {
 
             ANNOTATE(vcf_to_annotate,
+                params.fasta,
                 params.tools,
                 snpeff_db,
                 snpeff_cache,

From 6f2fc9d413325db3622171186cb77420943ae194 Mon Sep 17 00:00:00 2001
From: Anders Sune Pedersen <37172585+asp8200@users.noreply.github.com>
Date: Thu, 16 Jun 2022 12:39:59 +0200
Subject: [PATCH 11/12] Update workflows/sarek.nf

Co-authored-by: Maxime U. Garcia <maxime.garcia@scilifelab.se>
---
 workflows/sarek.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflows/sarek.nf b/workflows/sarek.nf
index 6d5e10944c..0290af33bb 100644
--- a/workflows/sarek.nf
+++ b/workflows/sarek.nf
@@ -864,7 +864,7 @@ workflow SAREK {
         if (params.tools.contains('merge') || params.tools.contains('snpeff') || params.tools.contains('vep')) {
 
             ANNOTATE(vcf_to_annotate,
-                params.fasta,
+                fasta,
                 params.tools,
                 snpeff_db,
                 snpeff_cache,

From bc36841c9e15e90ee9a3a31a06946fc81f64d3d0 Mon Sep 17 00:00:00 2001
From: asp8200 <aspe@clin.au.dk>
Date: Thu, 16 Jun 2022 15:47:27 +0200
Subject: [PATCH 12/12] Updating CHANGELOG

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 47021b9e00..97b2d23be6 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -29,6 +29,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#540](https://github.com/nf-core/sarek/pull/540) - Add modules and subworkflows for `cnvkit` somatic mode
 - [#557](https://github.com/nf-core/sarek/pull/557) - Add `Haplotypecaller` single sample mode together with `CNNScoreVariants` and `FilterVariantTranches`
 - [#576](https://github.com/nf-core/sarek/pull/576) - Add modules and subworkflows for `cnvkit` germline mode
+- [#582](https://github.com/nf-core/sarek/pull/582) - Added option `--vep_out_format` for setting the format of the output-file from VEP to `json`, `tab` or `vcf` (default)
 
 ### Changed