Merge pull request nf-core#1267 from grantn5/add_bcftools_annotate

Add bcftools annotate
asp8200 · Oct 18, 2023 · 2336ae3 · 2336ae3
2 parents 2d02bc0 + 33464b2
commit 2336ae3
Show file tree

Hide file tree

Showing 18 changed files with 354 additions and 6 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -62,6 +62,7 @@ A lake near the Rapaselet delta.
 ### Added
 
 - [#1231](https://github.com/nf-core/sarek/pull/1231) - Back to dev
+- [#1244](https://github.com/nf-core/sarek/pull/1244) - Add bcf annotate module
 
 ### Changed
 

diff --git a/README.md b/README.md
@@ -50,7 +50,7 @@ Depending on the options and samples provided, the pipeline can currently perfor
   - `Sentieon Haplotyper`
   - `Strelka2`
   - `TIDDIT`
-- Variant filtering and annotation (`SnpEff`, `Ensembl VEP`)
+- Variant filtering and annotation (`SnpEff`, `Ensembl VEP`, `BCFtools annotate`)
 - Summarise and represent QC (`MultiQC`)
 
 <p align="center">
@@ -131,6 +131,7 @@ We thank the following people for their extensive assistance in the development
 - [Francesco Lescai](https://github.com/lescai)
 - [Gavin Mackenzie](https://github.com/GCJMackenzie)
 - [Gisela Gabernet](https://github.com/ggabernet)
+- [Grant Neilson](https://github.com/grantn5)
 - [gulfshores](https://github.com/gulfshores)
 - [Harshil Patel](https://github.com/drpatelh)
 - [James A. Fellows Yates](https://github.com/jfy133)

diff --git a/conf/modules/annotate.config b/conf/modules/annotate.config
@@ -60,6 +60,19 @@ process {
         }
     }
 
+    // BCFTOOLS ANNOTATE
+    if (params.tools && params.tools.split(',').contains('bcfann')) {
+        withName: 'NFCORE_SAREK:SAREK:VCF_ANNOTATE_ALL:VCF_ANNOTATE_BCFTOOLS:BCFTOOLS_ANNOTATE' {
+            ext.args         = '--output-type z'
+            ext.prefix       = { "${vcf.baseName.minus(".vcf")}_BCF.ann" }
+            publishDir       = [
+                    mode: params.publish_dir_mode,
+                    path: { "${params.outdir}/annotation/${meta.variantcaller}/${meta.id}/" },
+                    pattern: "*{gz}"
+                ]
+        }
+    }
+
     // SNPEFF THEN VEP
     if (params.tools && params.tools.split(',').contains('merge')) {
         withName: "NFCORE_SAREK:SAREK:VCF_ANNOTATE_ALL:VCF_ANNOTATE_MERGE:ENSEMBLVEP_VEP" {
@@ -69,7 +82,7 @@ process {
     }
 
     // ALL ANNOTATION TOOLS
-    if (params.tools && (params.tools.split(',').contains('snpeff') || params.tools.split(',').contains('vep') || params.tools.split(',').contains('merge'))) {
+    if (params.tools && (params.tools.split(',').contains('snpeff') || params.tools.split(',').contains('vep') || params.tools.split(',').contains('merge') || params.tools.split(',').contains('bcfann'))) {
         withName: "NFCORE_SAREK:SAREK:VCF_ANNOTATE_ALL:.*:(TABIX_BGZIPTABIX|TABIX_TABIX)" {
             ext.prefix       = { input.name - ".vcf" }
             publishDir       = [

diff --git a/conf/test.config b/conf/test.config
@@ -36,6 +36,9 @@ params {
     vep_cache_version = 110
     vep_genome        = 'WBcel235'
     vep_species       = 'caenorhabditis_elegans'
+    bcftools_annotations       = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/illumina/vcf/test2.vcf.gz"
+    bcftools_annotations_index  = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/illumina/vcf/test2.vcf.gz.tbi"
+    bcftools_header_lines = "${projectDir}/tests/config/bcfann_test_header.txt"
 
     // default params
     split_fastq       = 0         // no FASTQ splitting

diff --git a/docs/output.md b/docs/output.md
@@ -886,6 +886,18 @@ plus any additional filed selected via the plugins: [dbNSFP](https://sites.googl
 
 </details>
 
+### BCFtools annotate
+
+[BCFtools annotate](https://samtools.github.io/bcftools/bcftools.html#annotate) is used to add annotations to VCF files. The annotations are added to the INFO column of the VCF file. The annotations are added to the VCF header and the VCF header is updated with the new annotations. For further reading and documentation see the [BCFtools annotate manual](https://samtools.github.io/bcftools/bcftools.html#annotate).
+
+<details markdown="1">
+<summary>Output files for all samples</summary>
+
+- `{sample,tumorsample_vs_normalsample}.<variantcaller>_bcf.ann.vcf.gz` and `{sample,tumorsample_vs_normalsample}.<variantcaller>_bcf.ann.vcf.gz.tbi`
+  - VCF with tabix index
+
+</details>
+
 ## Quality control and reporting
 
 ### Quality control

diff --git a/docs/usage.md b/docs/usage.md
@@ -1048,6 +1048,14 @@ Enable with `--vep_spliceregion`.
 
 For more details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#spliceregion) and [here](https://www.ensembl.info/2018/10/26/cool-stuff-the-vep-can-do-splice-site-variant-annotation/)."
 
+### BCFTOOLS Annotate
+
+It is possible to annotate a VCF file with a custom annotation file using [BCFTOOLS Annotate](https://samtools.github.io/bcftools/bcftools.html#annotate). This can be done by setting adding bcfann to the tools list and setting the following parameters:
+
+- annotations: path to vcf annotation file
+- annotations_index: path to vcf annotation index file
+- header_lines: path to header lines file
+
 ## MultiQC related issues
 
 ### Plots for SnpEff are missing

diff --git a/modules.json b/modules.json
@@ -10,6 +10,12 @@
                         "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220",
                         "installed_by": ["modules"]
                     },
+                    "bcftools/annotate": {
+                        "branch": "master",
+                        "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/bcftools/annotate/bcftools-annotate.diff"
+                    },
                     "bcftools/concat": {
                         "branch": "master",
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",

diff --git a/modules/nf-core/bcftools/annotate/bcftools-annotate.diff b/modules/nf-core/bcftools/annotate/bcftools-annotate.diff
diff --git a/modules/nf-core/bcftools/annotate/main.nf b/modules/nf-core/bcftools/annotate/main.nf
diff --git a/modules/nf-core/bcftools/annotate/meta.yml b/modules/nf-core/bcftools/annotate/meta.yml
diff --git a/nextflow.config b/nextflow.config
@@ -95,6 +95,9 @@ params {
     vep_out_format            = "vcf"
     vep_spliceai              = null // spliceai plugin disabled within VEP
     vep_spliceregion          = null // spliceregion plugin disabled within VEP
+    bcftools_annotations               = null  // No extra annotation file
+    bcftools_annotations_index         = null  // No extra annotation file index
+    bcftools_header_lines              = null  // No header lines to be added to the VCF file
 
     // MultiQC options
     multiqc_config             = null

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -100,7 +100,7 @@
                     "fa_icon": "fas fa-toolbox",
                     "description": "Tools to use for duplicate marking, variant calling and/or for annotation.",
                     "help_text": "Multiple tools separated with commas.\n\n**Variant Calling:**\n\nGermline variant calling can currently be performed with the following variant callers:\n- SNPs/Indels: DeepVariant, FreeBayes, GATK HaplotypeCaller, mpileup, Sentieon Haplotyper, Strelka\n- Structural Variants: Manta, TIDDIT\n- Copy-number: CNVKit\n\nTumor-only somatic variant calling can currently be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, mpileup, Mutect2, Strelka\n- Structural Variants: Manta, TIDDIT\n- Copy-number: CNVKit, ControlFREEC\n\nSomatic variant calling can currently only be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, Mutect2, Strelka2\n- Structural variants: Manta, TIDDIT\n- Copy-Number: ASCAT, CNVKit, Control-FREEC\n- Microsatellite Instability: MSIsensorpro\n\n> **NB** Mutect2 for somatic variant calling cannot be combined with `--no_intervals`\n\n**Annotation:**\n \n- snpEff, VEP, merge (both consecutively).\n\n> **NB** As Sarek will use bgzip and tabix to compress and index VCF files annotated, it expects VCF files to be sorted when starting from `--step annotate`.",
-                    "pattern": "^((ascat|cnvkit|controlfreec|deepvariant|freebayes|haplotypecaller|sentieon_dnascope|sentieon_haplotyper|manta|merge|mpileup|msisensorpro|mutect2|sentieon_dedup|snpeff|strelka|tiddit|vep)?,?)*(?<!,)$"
+                    "pattern": "^((ascat|bcfann|cnvkit|controlfreec|deepvariant|freebayes|haplotypecaller|sentieon_dnascope|sentieon_haplotyper|manta|merge|mpileup|msisensorpro|mutect2|sentieon_dedup|snpeff|strelka|tiddit|vep)?,?)*(?<!,)$"
                 },
                 "skip_tools": {
                     "type": "string",
@@ -561,6 +561,18 @@
                     "help_text": "Sets the format of the output-file from VEP. Available formats: json, tab and vcf.",
                     "fa_icon": "fas fa-table",
                     "hidden": true
+                },
+                "bcftools_annotations": {
+                    "type": "string",
+                    "fa_icon": "fas fa-file"
+                },
+                "bcftools_annotations_index": {
+                    "type": "string",
+                    "fa_icon": "fas fa-file"
+                },
+                "bcftools_header_lines": {
+                    "type": "string",
+                    "fa_icon": "fas fa-align-center"
                 }
             }
         },