Bcftools roh logic update

CHANGELOG.md

@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- Print warning messages if user intends to perform ranking when there are no affected samples [#579](https://github.com/nf-core/raredisease/pull/579)
 - Two new parameters `skip_repeat_annotation` and `skip_repeat_calling` to skip calling and annotation of repeat expansions [#574](https://github.com/nf-core/raredisease/pull/574)
 - A new parameter `skip_smncopynumbercaller` to skip smncopynumbercaller module[#574](https://github.com/nf-core/raredisease/pull/574)
 - A new parameter `skip_sv_calling` to skip sv calling workflow [#572](https://github.com/nf-core/raredisease/pull/572)
@@ -15,6 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Changed`
 
+- Skip ROH calling with bcftools if there are no affected samples [#579](https://github.com/nf-core/raredisease/pull/579)
 - Refactored tool citation list [#577](https://github.com/nf-core/raredisease/pull/577)
 - Removed `skip_repeat_analysis` added in #571 [#574](https://github.com/nf-core/raredisease/pull/574)
 - Remove several skip parameters that had been included in the pipeline to avoid failed CI tests (see parameters table below) [#574](https://github.com/nf-core/raredisease/pull/574)

conf/modules/annotate_genome_snvs.config

@@ -18,6 +18,7 @@
 process {
 
     withName: '.*ANNOTATE_GENOME_SNVS:BCFTOOLS_ROH' {
+        ext.when = { meta.probands.size()>0 }
         ext.args = { "--samples ${meta.probands.unique().first()} --skip-indels " }
         ext.prefix = { "${meta.id}_roh" }
     }
@@ -31,7 +32,7 @@ process {
     }
 
     withName: '.*ANNOTATE_GENOME_SNVS:VCFANNO' {
-        ext.prefix = { "${vcf.simpleName}_vcfanno" }
+        ext.prefix = { "${meta.prefix}_vcfanno" }
     }
 
     withName: '.*ANNOTATE_GENOME_SNVS:UPD_SITES' {

docs/output.md

@@ -387,8 +387,8 @@ Based on VEP annotations, custom scripts used by the pipeline further annotate e
 <summary>Output files</summary>
 
 - `annotate_snv/genome`
-  - `<case_id>_rhocall_vcfanno_filter_<cadd_vep|vep>.vcf.gz`: file containing bcftools roh, vcfanno, cadd and vep annotations.
-  - `<case_id>_rhocall_vcfanno_filter_<cadd_vep|vep>.vcf.gz.tbi`: index of the file containing bcftools roh, vcfanno, cadd and vep annotations.
+  - `<case_id>_<rhocall_vcfanno|vcfanno>_filter_<cadd_vep|vep>.vcf.gz`: file containing bcftools roh, vcfanno, cadd and vep annotations.
+  - `<case_id>_<rhocall_vcfanno|vcfanno>_filter_<cadd_vep|vep>.vcf.gz.tbi`: index of the file containing bcftools roh, vcfanno, cadd and vep annotations.
 
 </details>
 

subworkflows/local/annotate_genome_snvs.nf

@@ -53,11 +53,21 @@ workflow ANNOTATE_GENOME_SNVS {
 
         ZIP_TABIX_ROHCALL (RHOCALL_ANNOTATE.out.vcf)
 
-        ZIP_TABIX_ROHCALL.out.gz_tbi
-            .map { meta, vcf, tbi -> return [meta, vcf, tbi, []]}
-            .set { ch_vcf_in }
+        ch_vcf
+            .join(ZIP_TABIX_ROHCALL.out.gz_tbi, remainder: true)
+            .branch { it  ->
+                noroh: it[3].equals(null)
+                    return [it[0] + [prefix: it[0].id], it[1], it[2]]
+                roh: !(it[3].equals(null))
+                    return [it[0] + [prefix: it[0].id + "_rhocall"], it[3], it[4]]
+            }
+            .set { ch_for_mix }
+
+        ch_for_mix.noroh.mix(ch_for_mix.roh)
+            .map { meta, vcf, tbi -> return [meta, vcf, tbi, []] }
+            .set { ch_vcfanno_in }
 
-        VCFANNO (ch_vcf_in, ch_vcfanno_toml, ch_vcfanno_lua, ch_vcfanno_resources)
+        VCFANNO (ch_vcfanno_in, ch_vcfanno_toml, ch_vcfanno_lua, ch_vcfanno_resources)
 
         VCFANNO.out.vcf
             .map {meta, vcf ->

workflows/raredisease.nf

@@ -541,8 +541,17 @@ workflow RAREDISEASE {
             )
             ch_versions = ch_versions.mix(ANN_CSQ_PLI_SNV.out.versions)
 
+            ANN_CSQ_PLI_SNV.out.vcf_ann
+                .filter { it ->
+                    if (it[0].probands.size()==0) {
+                        log.warn("Skipping nuclear SNV ranking since no affected samples are detected in the case")
+                    }
+                    it[0].probands.size()>0
+                }
+                .set {ch_ranksnv_nuclear_in}
+
             RANK_VARIANTS_SNV (
-                ANN_CSQ_PLI_SNV.out.vcf_ann,
+                ch_ranksnv_nuclear_in,
                 ch_pedfile,
                 ch_reduced_penetrance,
                 ch_score_config_snv
@@ -582,8 +591,17 @@ workflow RAREDISEASE {
             )
             ch_versions = ch_versions.mix(ANN_CSQ_PLI_MT.out.versions)
 
+            ANN_CSQ_PLI_MT.out.vcf_ann
+                .filter { it ->
+                    if (it[0].probands.size()==0) {
+                        log.warn("Skipping mitochondrial SNV ranking since no affected samples are detected in the case")
+                    }
+                    it[0].probands.size()>0
+                }
+                .set {ch_ranksnv_mt_in}
+
             RANK_VARIANTS_MT (
-                ANN_CSQ_PLI_MT.out.vcf_ann,
+                ch_ranksnv_mt_in,
                 ch_pedfile,
                 ch_reduced_penetrance,
                 ch_score_config_mt
@@ -648,8 +666,17 @@ workflow RAREDISEASE {
             )
             ch_versions = ch_versions.mix(ANN_CSQ_PLI_SV.out.versions)
 
+            ANN_CSQ_PLI_SV.out.vcf_ann
+                .filter { it ->
+                    if (it[0].probands.size()==0) {
+                        log.warn("Skipping SV ranking since no affected samples are detected in the case")
+                    }
+                    it[0].probands.size()>0
+                }
+                .set {ch_ranksnv_sv_in}
+
             RANK_VARIANTS_SV (
-                ANN_CSQ_PLI_SV.out.vcf_ann,
+                ch_ranksnv_sv_in,
                 ch_pedfile,
                 ch_reduced_penetrance,
                 ch_score_config_sv