Merge pull request #113 from sanger-tol/dev

Release 1.1.7

Author: sainsachiko

CHANGELOG.md

@@ -3,6 +3,25 @@
 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).
 
+## [[1.1.7](https://github.com/sanger-tol/variantcalling/releases/tag/1.1.7)] - Shang Tang (patch 7) - [2025-06-26]
+
+### Enhancements & fixes
+
+- Update Deepvariant to version 1.9.0 (conda-free)
+- Add module [DEEPVARIANT_VCFSTATSREPORT](https://github.com/nf-core/modules/tree/master/modules/nf-core/deepvariant/vcfstatsreport) to generate visual report from Deepvariant
+- Compress and index concatenated VCFs
+
+### Software dependencies
+
+Note, since the pipeline is using Nextflow DSL2, each process will be run with its own [Biocontainer](https://biocontainers.pro/#/registry). This means that on occasion it is entirely possible for the pipeline to be using different versions of the same tool. However, the overall software dependency changes compared to the last release have been listed below for reference. Only `Docker` or `Singularity` containers are supported, `conda` is not supported.
+
+| Dependency  | Old version | New version |
+| ----------- | ----------- | ----------- |
+| Deepvariant | 1.6.1       | 1.9.0       |
+| HTSlib      |             | 1.21        |
+
+> **NB:** Dependency has been **updated** if both old and new version information is present. </br> **NB:** Dependency has been **added** if just the new version information is present. </br> **NB:** Dependency has been **removed** if version information isn't present.
+
 ## [[1.1.6](https://github.com/sanger-tol/variantcalling/releases/tag/1.1.6)] - Shang Tang (patch 6) - [2025-02-10]
 
 ### Enhancements & fixes

CITATION.cff

@@ -1,34 +1,52 @@
-# This CITATION.cff file was generated with cffinit.
-# Visit https://bit.ly/cffinit to generate yours today!
-
-cff-version: 1.2.0
-title: sanger-tol/variantcalling v1.1.0
-message: >-
-    If you use this software, please cite it using the
-    metadata from this file.
-type: software
 authors:
-    - given-names: Guoying
+    - affiliation: Universidade Federal do Rio Grande do Norte
+      family-names: Apolonio de Amorim
+      given-names: Julia
+      orcid: https://orcid.org/0000-0002-8539-527X
+      website: https://github.com/juliaapolonio
+    - affiliation: Wellcome Sanger Institute
+      email: tc25@sanger.ac.uk
+      family-names: Chafin
+      given-names: Tyler
+      orcid: https://orcid.org/0000-0001-8687-5905
+      website: https://github.com/tkchafin
+    - affiliation: Wellcome Sanger Institute
+      family-names: "Ho\xE0ng"
+      given-names: "H\u1EA1nh"
+      orcid: https://orcid.org/0009-0008-6911-9903
+      website: https://github.com/sainsachiko
+    - affiliation: Wellcome Sanger Institute
+      email: mm49@sanger.ac.uk
+      family-names: Muffato
+      given-names: Matthieu
+      orcid: https://orcid.org/0000-0002-7860-3560
+      website: https://github.com/muffato
+    - affiliation: Wellcome Sanger Institute
+      email: 729395+gq1@users.noreply.github.com
       family-names: Qi
-      affiliation: Wellcome Sanger Institute
-      orcid: "https://orcid.org/0000-0003-1262-8973"
-    - given-names: Priyanka
+      given-names: Guoying
+      orcid: https://orcid.org/0000-0003-1262-8973
+      website: https://github.com/gq1
+    - affiliation: Wellcome Sanger Institute
+      email: ps22@sanger.ac.uk
       family-names: Surana
-      affiliation: Wellcome Sanger Institute
-      orcid: "https://orcid.org/0000-0002-7167-0875"
-    - given-names: Matthieu
-      family-names: Muffato
-      affiliation: Wellcome Sanger Institute
-      orcid: "https://orcid.org/0000-0002-7860-3560"
-    - given-names: Tyler
-      family-names: Chafin
-      affiliation: Wellcome Sanger Institute
-      orcid: "https://orcid.org/0000-0001-8687-5905"
-identifiers:
-    - type: doi
-      value: 10.5281/zenodo.7890528
-repository-code: "https://github.com/sanger-tol/variantcalling"
+      given-names: Priyanka
+      orcid: https://orcid.org/0000-0002-7167-0875
+      website: https://github.com/priyanka-surana
+    - affiliation: Wellcome Sanger Institute
+      email: naranbjg@gmail.com
+      family-names: Zhang
+      given-names: Yunjia
+      orcid: https://orcid.org/0000-0001-7029-0785
+      website: https://github.com/yz533cb
+cff-version: 1.2.0
+date-released: "2025-06-25"
+doi: 10.5281/zenodo.7890527
 license: MIT
-commit: TODO
-version: 1.1.0
-date-released: "2022-12-20"
+message: If you use this software, please cite it using the metadata from this file
+    and all references from CITATIONS.md .
+repository-code: https://github.com/sanger-tol/variantcalling
+title: sanger-tol/variantcalling v1.1.7 - Shang Tang (patch 7)
+type: software
+url: https://pipelines.tol.sanger.ac.uk/variantcalling
+version: 1.1.7

assets/samplesheet_test_full.csv

@@ -1,2 +1,2 @@
 sample,datatype,datafile
-icCanRufa1,pacbio,/lustre/scratch123/tol/resources/nextflow/test-data/Cantharis_rufa/analysis/icCanRufa1/read_mapping/pacbio/GCA_947369205.1.unmasked.pacbio.icCanRufa1.cram
+icCanRufa1,pacbio,/nfs/treeoflife-01/resources/nextflow/test-data/Cantharis_rufa/analysis/icCanRufa1/read_mapping/pacbio/GCA_947369205.1.unmasked.pacbio.icCanRufa1.cram

assets/samplesheet_test_full_align.csv

@@ -1,2 +1,2 @@
 sample,datatype,datafile
-ilPolIcar1,pacbio,/lustre/scratch124/tol/projects/darwin/data/insects/Polyommatus_icarus/genomic_data/ilPolIcar1/pacbio/m64016_191206_183623.ccs.bc1019_BAK8B_OA--bc1019_BAK8B_OA.bam
+ilPolIcar1,pacbio,/lustre/scratch122/tol/data/c/2/0/7/e/5/Polyommatus_icarus/genomic_data/ilPolIcar1/pacbio/m64016_191206_183623.ccs.bc1019_BAK8B_OA--bc1019_BAK8B_OA.bam

conf/modules.config

@@ -93,22 +93,56 @@ process {
 
     withName: '.*:DEEPVARIANT_CALLER:BCFTOOLS_CONCAT_VCF' {
         ext.prefix = { "${meta.id}_deepvariant" }
+    }
+
+    withName: '.*:DEEPVARIANT_CALLER:BCFTOOLS_CONCAT_GVCF' {
+        ext.prefix = { "${meta.id}_deepvariant.g" }
+    }
+
+    withName: 'BGZIP' {
+        ext.prefix = { "${input.baseName}" }
         publishDir = [
             path: { "${params.outdir}/variant_calling" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
 
-    withName: '.*:DEEPVARIANT_CALLER:BCFTOOLS_CONCAT_GVCF' {
-        ext.prefix = { "${meta.id}_deepvariant.g" }
+    withName: 'TABIX_CSI' {
+        ext.args = "--preset vcf --csi"
+        publishDir = [
+            path: { "${params.outdir}/variant_calling" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+    withName: 'TABIX_TBI' {
+        ext.args = "--preset vcf"
         publishDir = [
             path: { "${params.outdir}/variant_calling" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
 
+    withName: 'VCF_STATS_REPORT' {
+        ext.prefix = { "${meta.id}_vcf.stats" }
+        publishDir = [
+            path: { "${params.outdir}/variant_calling/report" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: 'GVCF_STATS_REPORT' {
+        ext.prefix = { "${meta.id}_gvcf.stats" }
+        publishDir = [
+            path: { "${params.outdir}/variant_calling/report" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: '.*:PROCESS_VCF:VCFTOOLS_SITE_PI' {
         ext.args = '--site-pi'
         if( params.include_positions ){

conf/test_full.config

@@ -18,8 +18,8 @@ params {
     input = "${projectDir}/assets/samplesheet_test_full.csv"
 
     // Fasta references
-    fasta = '/lustre/scratch124/tol/projects/darwin/data/insects/Cantharis_rufa/assembly/release/icCanRufa1.1/insdc/GCA_947369205.1.fasta.gz'
+    fasta = '/lustre/scratch122/tol/data/1/f/4/a/0/9/Cantharis_rufa/assembly/release/icCanRufa1.1/insdc/GCA_947369205.1.fasta.gz'
 
     // Reference index file
-    fai = '/lustre/scratch124/tol/projects/darwin/data/insects/Cantharis_rufa/assembly/release/icCanRufa1.1/insdc/GCA_947369205.1.fasta.gz.gzi'
+    fai = '/lustre/scratch122/tol/data/1/f/4/a/0/9/Cantharis_rufa/assembly/release/icCanRufa1.1/insdc/GCA_947369205.1.fasta.gz.gzi'
 }

conf/test_full_align.config

@@ -19,6 +19,6 @@ params {
     align = true
 
     // Fasta references
-    fasta = "/lustre/scratch124/tol/projects/darwin/data/insects/Polyommatus_icarus/assembly/release/ilPolIcar1.1/insdc/GCA_937595015.1.fasta.gz"
+    fasta = "/lustre/scratch122/tol/data/c/2/0/7/e/5/Polyommatus_icarus/assembly/release/ilPolIcar1.1/insdc/GCA_937595015.1.fasta.gz"
 
 }

docs/output.md

@@ -62,7 +62,11 @@ The aligned PacBio read data is used to call variants with DeepVariant. This is
 
 - `variant_calling`
   - Compressed VCF files: `<fasta_name>.pacbio.<sample_name>_deepvariant.vcf.gz`.
+  - Index of compressed VCF files: `<fasta_name>.pacbio.<sample_name>_deepvariant.vcf.gz.[tbi|csi]`.
   - Compressed GVCF files: `<fasta_name>.pacbio.<sample_name>_deepvariant.g.vcf.gz`.
+  - Index of compressed GVCF files: `<fasta_name>.pacbio.<sample_name>_deepvariant.g.vcf.gz.[tbi|csi]`.
+  - `reports`
+    - HTML files: `<fasta_name>.pacbio.<sample_name>_[vcf|gvcf].stats.visual_report.html`.
 
 </details>
 

modules.json

@@ -33,10 +33,15 @@
                     },
                     "deepvariant/rundeepvariant": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "git_sha": "123fdbae2bf2c827b2e11ae09c4d481f446b8ffb",
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/deepvariant/rundeepvariant/deepvariant-rundeepvariant.diff"
                     },
+                    "deepvariant/vcfstatsreport": {
+                        "branch": "master",
+                        "git_sha": "123fdbae2bf2c827b2e11ae09c4d481f446b8ffb",
+                        "installed_by": ["modules"]
+                    },
                     "gunzip": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
@@ -98,6 +103,16 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/samtools/view/samtools-view.diff"
                     },
+                    "tabix/bgzip": {
+                        "branch": "master",
+                        "git_sha": "52a49a8807214ba93b0fdc9fa401876d9845f62a",
+                        "installed_by": ["modules"]
+                    },
+                    "tabix/tabix": {
+                        "branch": "master",
+                        "git_sha": "05954dab2ff481bcb999f24455da29a5828af08d",
+                        "installed_by": ["modules"]
+                    },
                     "untar": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",