From a49e41f2f78d06623e6f9dbaab50f2b83445a3e7 Mon Sep 17 00:00:00 2001
From: Ramprasad Neethiraj <20065894+ramprasadn@users.noreply.github.com>
Date: Tue, 4 Feb 2025 14:03:36 +0100
Subject: [PATCH] add skip_haplogrep3

---
 CHANGELOG.md                           |  2 ++
 conf/test.config                       |  1 +
 conf/test_sentieon.config              |  1 +
 nextflow.config                        |  1 +
 nextflow_schema.json                   |  5 +++++
 subworkflows/local/annotate_mt_snvs.nf | 20 ++++++++++++--------
 6 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 10dd84096..9b16e7eb2 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- A new option `skip_haplogrep3` to skip haplogrep3 [#675](https://github.com/nf-core/raredisease/pull/675)
 - A new analysis option `mito` to call and annotate only mitochondrial variants [#608](https://github.com/nf-core/raredisease/pull/608)
 - An option `extract_alignments` to restrict analysis to specific contigs [#644](https://github.com/nf-core/raredisease/pull/644)
 - Fastp and ngsbits output files as input of MultiQC [#647](https://github.com/nf-core/raredisease/pull/647/).
@@ -40,6 +41,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | ------------- | ------------------- |
 |               | extract_alignments  |
 |               | restrict_to_contigs |
+|               | skip_haplogrep3     |
 
 ### Tool updates
 
diff --git a/conf/test.config b/conf/test.config
index 6c9e687b6..76f74acd7 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -31,6 +31,7 @@ params {
     skip_mt_annotation     = System.getenv("GITHUB_ACTIONS").equals(null) ? false : true // skip annotation on Github CI
     skip_mt_subsample      = System.getenv("GITHUB_ACTIONS").equals(null) ? false : true // skip subsample on Github CI
     skip_peddy             = true
+    skip_haplogrep3        = true
 
     // Input data
 
diff --git a/conf/test_sentieon.config b/conf/test_sentieon.config
index 6776eb6aa..ed0ce58c3 100644
--- a/conf/test_sentieon.config
+++ b/conf/test_sentieon.config
@@ -26,6 +26,7 @@ params {
     // analysis params
     skip_germlinecnvcaller = true
     skip_peddy             = true
+    skip_haplogrep3        = true
 
     // Input data
     input          = 'https://raw.githubusercontent.com/nf-core/test-datasets/raredisease/testdata/samplesheet_trio.csv'
diff --git a/nextflow.config b/nextflow.config
index 5ee47f6de..f8247247f 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -33,6 +33,7 @@ params {
     skip_fastp                 = false
     skip_gens                  = true
     skip_germlinecnvcaller     = false
+    skip_haplogrep3            = false
     skip_peddy                 = false
     skip_me_calling            = false
     skip_me_annotation         = false
diff --git a/nextflow_schema.json b/nextflow_schema.json
index fced33ea3..91fda19c0 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -564,6 +564,11 @@
                     "description": "Specifies whether or not to skip CNV calling using GATK's GermlineCNVCaller",
                     "fa_icon": "fas fa-toggle-on"
                 },
+                "skip_haplogrep3": {
+                    "type": "boolean",
+                    "description": "Specifies whether or not to skip haplogrep3.",
+                    "fa_icon": "fas fa-toggle-on"
+                },
                 "skip_peddy": {
                     "type": "boolean",
                     "description": "Specifies whether or not to skip peddy.",
diff --git a/subworkflows/local/annotate_mt_snvs.nf b/subworkflows/local/annotate_mt_snvs.nf
index 9393ee03e..41d8da907 100644
--- a/subworkflows/local/annotate_mt_snvs.nf
+++ b/subworkflows/local/annotate_mt_snvs.nf
@@ -31,6 +31,7 @@ workflow ANNOTATE_MT_SNVS {
 
     main:
         ch_versions = Channel.empty()
+        ch_haplog   = Channel.empty()
 
         // add prefix to meta
         ch_mt_vcf
@@ -98,22 +99,25 @@ workflow ANNOTATE_MT_SNVS {
 
         TABIX_TABIX_VEP_MT(ENSEMBLVEP_MT.out.vcf)
 
-        // Running haplogrep2
-        HAPLOGREP3_CLASSIFY_MT(ch_haplogrep_in)
+        // Running haplogrep3
+        if (!params.skip_haplogrep3) {
+            HAPLOGREP3_CLASSIFY_MT(ch_haplogrep_in)
+            ch_haplog   = HAPLOGREP3_CLASSIFY_MT.out.txt
+            ch_versions = ch_versions.mix(HAPLOGREP3_CLASSIFY_MT.out.versions)
+        }
 
         ch_versions = ch_versions.mix(ENSEMBLVEP_MT.out.versions)
         ch_versions = ch_versions.mix(TABIX_TABIX_VEP_MT.out.versions)
         ch_versions = ch_versions.mix(VCFANNO_MT.out.versions)
         ch_versions = ch_versions.mix(HMTNOTE_ANNOTATE.out.versions)
-        ch_versions = ch_versions.mix(HAPLOGREP3_CLASSIFY_MT.out.versions)
         ch_versions = ch_versions.mix(ZIP_TABIX_VCFANNO_MT.out.versions)
         ch_versions = ch_versions.mix(ZIP_TABIX_HMTNOTE_MT.out.versions)
         ch_versions = ch_versions.mix(REPLACE_SPACES_IN_VCFINFO.out.versions)
 
     emit:
-        haplog    = HAPLOGREP3_CLASSIFY_MT.out.txt // channel: [ val(meta), path(txt) ]
-        vcf_ann   = ENSEMBLVEP_MT.out.vcf          // channel: [ val(meta), path(vcf) ]
-        tbi       = TABIX_TABIX_VEP_MT.out.tbi     // channel: [ val(meta), path(tbi) ]
-        report    = ENSEMBLVEP_MT.out.report       // channel: [ path(html) ]
-        versions  = ch_versions                    // channel: [ path(versions.yml) ]
+        haplog    = ch_haplog                   // channel: [ val(meta), path(txt) ]
+        vcf_ann   = ENSEMBLVEP_MT.out.vcf       // channel: [ val(meta), path(vcf) ]
+        tbi       = TABIX_TABIX_VEP_MT.out.tbi  // channel: [ val(meta), path(tbi) ]
+        report    = ENSEMBLVEP_MT.out.report    // channel: [ path(html) ]
+        versions  = ch_versions                 // channel: [ path(versions.yml) ]
 }