Merge pull request #14 from nf-cmgg/dev

merge latest changes (v1.0.1)
nf-cmgg · Jul 2, 2024 · 3c717db · 3c717db
2 parents f99472b + 36c111d
commit 3c717db
Show file tree

Hide file tree

Showing 17 changed files with 111 additions and 43 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,10 +3,23 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## v1.0.0 - 2024-06-12
+## v1.0.0 - Dashing Doku - [2024-06-12]
 
 Initial release of nf-cmgg/exomecnv, created with the [nf-core](https://nf-co.re/) template v2.13.
 
 ### `Added`
 
 - First release of the pipeline - CNV calling using [ExomeDepth](https://github.com/vplagnol/ExomeDepth)
+
+## v1.0.1 - Lightning Lukaku [2024-06-19]
+
+### `Improvements`
+
+- Index the VEP annotated VCF with TABIX
+- Do not copy output of SAMTOOLS_CONVERT module (BAM files) to the `publishDir`
+- update versions of multiqc and samtools_convert modules
+- optimize module resources
+
+### `Fixes`
+
+- Sort file of merged CNV calls to fix an issue with TABIX (needs sorted VCF files)
diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -1,5 +1,5 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-cmgg/exomecnv/releases/tag/1.0.0" target="_blank">nf-cmgg/exomecnv</a>
+  This report has been generated by the <a href="https://github.com/nf-cmgg/exomecnv/releases/tag/1.0.1" target="_blank">nf-cmgg/exomecnv</a>
   analysis pipeline.
 report_section_order:
   "nf-cmgg-exomecnv-methods-description":

diff --git a/conf/modules.config b/conf/modules.config
@@ -50,12 +50,28 @@ process {
             '--fields "SYMBOL,Gene"',
             '--transcript_filter "stable_id match ENST"'
         ].join(' ').trim()}
+        publishDir = [
+            path: {"$params.outdir/exomedepth/cnv_call_vep"},
+            mode: params.publish_dir_mode
+        ]
     }
 
-    withName: 'TABIX_TABIX' {
+    withName: 'TABIX' {
         publishDir = [
             path: {"$params.outdir/exomedepth/cnv_call"},
             mode: params.publish_dir_mode
         ]
     }
+    withName: 'TABIX_VEP' {
+        publishDir = [
+            path: {"$params.outdir/exomedepth/cnv_call_vep"},
+            mode: params.publish_dir_mode
+        ]
+    }
+
+    withName: 'SAMTOOLS_CONVERT' {
+        publishDir = [
+            enabled: false
+        ]
+    }
 }
diff --git a/docs/output.md b/docs/output.md
@@ -24,7 +24,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 ### Cram Prepare
 
-If CRAM/CRAI files were provided in the samplesheet, they will be converted into BAM/BAI first before continuing with the pipeline.
+If CRAM/CRAI files were provided in the samplesheet, they will be converted into BAM/BAI first before continuing with the pipeline. If the directive `publishDir` option `enabled` is set to `true` (default: `false`) , the BAM/BAI are in the output folder.
 
 <details markdown="1">
 <summary>Output files</summary>
@@ -120,8 +120,10 @@ A TBI index file is generated for each VCF file. While these TBI index files are
 <details markdown="1">
 <summary>Output files</summary>
 
-- `vep/`
-  - `<sample>.vep.vcf.gz`: VEP annotated file
+- `exomedepth/`
+  - `cnv_call_vep/`
+    - `<sample>.vep.vcf.gz`: VEP annotated file
+    - `<sample>.vep.vcf.gz.tbi`: index of VEP annotated file
 
 </details>
 

diff --git a/modules.json b/modules.json
@@ -13,17 +13,19 @@
                     "ensemblvep/vep": {
                         "branch": "master",
                         "git_sha": "b42fec6f7c6e5d0716685cabb825ef6bf6e386b5",
-                        "installed_by": ["modules"]
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/ensemblvep/vep/ensemblvep-vep.diff"
                     },
                     "multiqc": {
                         "branch": "master",
-                        "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",
+                        "git_sha": "8f2062e7b4185590fb9f43c275381a31a6544fc0",
                         "installed_by": ["modules"]
                     },
                     "samtools/convert": {
                         "branch": "master",
-                        "git_sha": "b42fec6f7c6e5d0716685cabb825ef6bf6e386b5",
-                        "installed_by": ["modules"]
+                        "git_sha": "04fbbc7c43cebc0b95d5b126f6d9fe4effa33519",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/samtools/convert/samtools-convert.diff"
                     },
                     "tabix/tabix": {
                         "branch": "master",

diff --git a/modules/local/exomedepth/merge_cnv/main.nf b/modules/local/exomedepth/merge_cnv/main.nf
@@ -1,4 +1,4 @@
-//MERGE CNV CALL FILES
+//MERGE AND SORT (ON GENOMIC POSITION) EXOMEDEPTH CNV CALL FILES
 process CNV_MERGE {
     tag "$meta"
 
@@ -19,13 +19,15 @@ process CNV_MERGE {
     script:
     def prefix = task.ext.prefix ?: "${meta}_CNVs_ExomeDepth"
     """
-    cp $auto "${prefix}.txt"
-    tail +2 $chrx >> "${prefix}.txt"
+    { head -n 1 $auto && \
+    { tail -n +2 $auto && tail -n +2 $chrx ; } | \
+    sort -k7,7V -k5,5n -k6,6n ; } > "${prefix}.txt"
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
+        head: \$(head --version | sed '1!d; s/head (GNU coreutils) //')
         tail: \$(tail --version | sed '1!d; s/tail (GNU coreutils) //')
-        cp: \$(cp --version | sed '1!d; s/cp (GNU coreutils) //')
+        sort: \$(sort --version | sed '1!d; s/sort (GNU coreutils) //')
     END_VERSIONS
     """
 

diff --git a/modules/nf-core/ensemblvep/vep/ensemblvep-vep.diff b/modules/nf-core/ensemblvep/vep/ensemblvep-vep.diff
diff --git a/modules/nf-core/ensemblvep/vep/main.nf b/modules/nf-core/ensemblvep/vep/main.nf
diff --git a/modules/nf-core/multiqc/environment.yml b/modules/nf-core/multiqc/environment.yml
diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf
diff --git a/modules/nf-core/multiqc/tests/main.nf.test.snap b/modules/nf-core/multiqc/tests/main.nf.test.snap
diff --git a/modules/nf-core/samtools/convert/environment.yml b/modules/nf-core/samtools/convert/environment.yml
diff --git a/modules/nf-core/samtools/convert/main.nf b/modules/nf-core/samtools/convert/main.nf
diff --git a/modules/nf-core/samtools/convert/samtools-convert.diff b/modules/nf-core/samtools/convert/samtools-convert.diff
diff --git a/modules/nf-core/samtools/convert/tests/main.nf.test.snap b/modules/nf-core/samtools/convert/tests/main.nf.test.snap
diff --git a/nextflow.config b/nextflow.config
@@ -249,7 +249,7 @@ manifest {
     description     = """A nextflow pipeline for calling exome CNVs"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '1.0.0'
+    version         = '1.0.1'
     doi             = ''
 }
 

diff --git a/subworkflows/local/vcf_annotation/main.nf b/subworkflows/local/vcf_annotation/main.nf
@@ -5,7 +5,7 @@
 */
 
 include { ENSEMBLVEP_VEP as         VEP           } from '../../../modules/nf-core/ensemblvep/vep/main'
-
+include { TABIX_TABIX as TABIX_VEP                      } from '../../../modules/nf-core/tabix/tabix/main'
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     RUN ENSEMBLE VEP WORKFLOW
@@ -23,6 +23,7 @@ workflow VCF_ANNOTATION {
     main:
 
     ch_vep_extra_files = []
+    ch_versions     = Channel.empty()
 
     VEP (
         ch_vcfs,
@@ -33,8 +34,14 @@ workflow VCF_ANNOTATION {
         fasta,
         ch_vep_extra_files
     )
+    ch_versions = ch_versions.mix(VEP.out.versions)
+    // Index VCF file
+
+    TABIX_VEP ( VEP.out.vcf )
+    ch_versions = ch_versions.mix(TABIX_VEP.out.versions)
 
     emit:
     vcfs = VEP.out.vcf
-    versions = VEP.out.versions
+    tbi = TABIX_VEP.out.tbi
+    versions = ch_versions
 }