Merge pull request nf-core#1335 from FriederikeHanssen/fix_annotate_docs

add docs for bcftools annotate params
FriederikeHanssen · Nov 20, 2023 · 7f114f7 · 7f114f7
2 parents e44db9e + fa45aab
commit 7f114f7
Show file tree

Hide file tree

Showing 7 changed files with 126 additions and 93 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -10,12 +10,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 
 - [#1333](https://github.com/nf-core/sarek/pull/1333) - Back to dev
+- [#1335](https://github.com/nf-core/sarek/pull/1335) - Add index computation of `bcftools_annotations`, if not provided
 
 ### Changed
 
 ### Fixed
 
 - [#1334](https://github.com/nf-core/sarek/pull/1334) - Remove extra v, when reporting tower runs on slack
+- [#1335](https://github.com/nf-core/sarek/pull/1335) - Add docs and validation for bcftools annotation parameters
 
 ### Removed
 
@@ -29,6 +31,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | script | Old name | New name |
 | ------ | -------- | -------- |
 
+### Parameter
+
+| Old name                   | New name                 |
+| -------------------------- | ------------------------ |
+| bcftools_annotations_index | bcftools_annotations_tbi |
+
 ## [3.4.0](https://github.com/nf-core/sarek/releases/tag/3.4.0) - Pårtetjåkko
 
 Pårtetjåkko is a mountain in the south of the park.

diff --git a/conf/modules/prepare_genome.config b/conf/modules/prepare_genome.config
@@ -96,6 +96,16 @@ process {
         ]
     }
 
+    withName: 'TABIX_BCFTOOLS_ANNOTATIONS' {
+        ext.when         = { !params.bcftools_annotations_tbi && params.bcftools_annotations && params.tools && params.tools.split(',').contains('bcfann') }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/reference/bcfann" },
+            pattern: "*vcf.gz.tbi",
+            saveAs: { params.save_reference || params.build_only_index ? it : null }
+        ]
+    }
+
     withName: 'TABIX_DBSNP' {
         ext.when         = { !params.dbsnp_tbi && params.dbsnp && ((params.step == "mapping" || params.step == "markduplicates" || params.step == "prepare_recalibration") || params.tools && (params.tools.split(',').contains('controlfreec') || params.tools.split(',').contains('haplotypecaller') || params.tools.split(',').contains('sentieon_haplotyper') || params.tools.split(',').contains('sentieon_dnascope') || params.tools.split(',').contains('mutect2'))) }
         publishDir       = [

diff --git a/nextflow.config b/nextflow.config
@@ -77,26 +77,26 @@ params {
     wes                               = false // Set to true, if data is exome/targeted sequencing data. Used to use correct models in various variant callers
 
     // Annotation
-    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
-    dbnsfp                     = null // No dbnsfp processed file
-    dbnsfp_consequence         = null // No default consequence for dbnsfp plugin
-    dbnsfp_fields              = "rs_dbSNP,HGVSc_VEP,HGVSp_VEP,1000Gp3_EAS_AF,1000Gp3_AMR_AF,LRT_score,GERP++_RS,gnomAD_exomes_AF" // Default fields for dbnsfp plugin
-    dbnsfp_tbi                 = null // No dbnsfp processed file index
-    outdir_cache               = null // No default outdir cache
-    spliceai_indel             = null // No spliceai_indel file
-    spliceai_indel_tbi         = null // No spliceai_indel file index
-    spliceai_snv               = null // No spliceai_snv file
-    spliceai_snv_tbi           = null // No spliceai_snv file index
-    vep_custom_args            = "--everything --filter_common --per_gene --total_length --offline --format vcf" // Default arguments for VEP
-    vep_dbnsfp                 = null // dbnsfp plugin disabled within VEP
-    vep_include_fasta          = false // Don't use fasta file for annotation with VEP
-    vep_loftee                 = null // loftee plugin disabled within VEP
-    vep_out_format             = "vcf"
-    vep_spliceai               = null // spliceai plugin disabled within VEP
-    vep_spliceregion           = null // spliceregion plugin disabled within VEP
-    vep_version                = "110.0-0"      // Should be updated when we update VEP, needs this to get full path to some plugins
+    bcftools_annotations     = null  // No extra annotation file
+    bcftools_annotations_tbi = null  // No extra annotation file index
+    bcftools_header_lines    = null  // No header lines to be added to the VCF file
+    dbnsfp                   = null // No dbnsfp processed file
+    dbnsfp_consequence       = null // No default consequence for dbnsfp plugin
+    dbnsfp_fields            = "rs_dbSNP,HGVSc_VEP,HGVSp_VEP,1000Gp3_EAS_AF,1000Gp3_AMR_AF,LRT_score,GERP++_RS,gnomAD_exomes_AF" // Default fields for dbnsfp plugin
+    dbnsfp_tbi               = null // No dbnsfp processed file index
+    outdir_cache             = null // No default outdir cache
+    spliceai_indel           = null // No spliceai_indel file
+    spliceai_indel_tbi       = null // No spliceai_indel file index
+    spliceai_snv             = null // No spliceai_snv file
+    spliceai_snv_tbi         = null // No spliceai_snv file index
+    vep_custom_args          = "--everything --filter_common --per_gene --total_length --offline --format vcf" // Default arguments for VEP
+    vep_dbnsfp               = null // dbnsfp plugin disabled within VEP
+    vep_include_fasta        = false // Don't use fasta file for annotation with VEP
+    vep_loftee               = null // loftee plugin disabled within VEP
+    vep_out_format           = "vcf"
+    vep_spliceai             = null // spliceai plugin disabled within VEP
+    vep_spliceregion         = null // spliceregion plugin disabled within VEP
+    vep_version              = "110.0-0"      // Should be updated when we update VEP, needs this to get full path to some plugins
 
     // MultiQC options
     multiqc_config             = null

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -84,7 +84,7 @@
                     "description": "Path to target bed file in case of whole exome or targeted sequencing or intervals file."
                 },
                 "nucleotides_per_second": {
-                    "type": "number",
+                    "type": "integer",
                     "fa_icon": "fas fa-clock",
                     "description": "Estimate interval size.",
                     "help_text": "Intervals are parts of the chopped up genome used to speed up preprocessing and variant calling. See `--intervals` for more info. \n\nChanging this parameter, changes the number of intervals that are grouped and processed together. Bed files from target sequencing can contain thousands or small intervals. Spinning up a new process for each can be quite resource intensive. Instead it can be desired to process small intervals together on larger nodes. \nIn order to make use of this parameter, no runtime estimate can be present in the bed file (column 5). ",
@@ -100,8 +100,7 @@
                     "type": "string",
                     "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`.",
-
+                    "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), and bcftools annotate (needs `--bcftools_annotation`).\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|bcfann|cnvkit|controlfreec|deepvariant|freebayes|haplotypecaller|sentieon_dnascope|sentieon_haplotyper|manta|merge|mpileup|msisensorpro|mutect2|ngscheckmate|sentieon_dedup|snpeff|strelka|tiddit|vep)?,?)*(?<!,)$"
                 },
                 "skip_tools": {
@@ -261,23 +260,23 @@
                     "description": "Runs Mutect2 in joint (multi-sample) mode for better concordance among variant calls of tumor samples from the same patient. Mutect2 outputs will be stored in a subfolder named with patient ID under `variant_calling/mutect2/` folder. Only a single normal sample per patient is allowed. Tumor-only mode is also supported."
                 },
                 "ascat_min_base_qual": {
-                    "type": "number",
+                    "type": "integer",
                     "default": 20,
                     "fa_icon": "fas fa-greater-than",
                     "description": "Overwrite Ascat min base quality required for a read to be counted.",
                     "hidden": true,
                     "help_text": "For more details see [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf)"
                 },
                 "ascat_min_counts": {
-                    "type": "number",
+                    "type": "integer",
                     "default": 10,
                     "fa_icon": "fas fa-align-center",
                     "description": "Overwrite Ascat minimum depth required in the normal for a SNP to be considered.",
                     "hidden": true,
                     "help_text": "For more details, see [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf)."
                 },
                 "ascat_min_map_qual": {
-                    "type": "number",
+                    "type": "integer",
                     "default": 35,
                     "fa_icon": "fas fa-balance-scale-left",
                     "description": "Overwrite Ascat min mapping quality required for a read to be counted.",
@@ -321,23 +320,23 @@
                     "help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)."
                 },
                 "cf_contamination": {
-                    "type": "number",
+                    "type": "integer",
                     "default": 0,
                     "fa_icon": "fas fa-broom",
                     "description": "Design known contamination value for Control-FREEC",
                     "hidden": true,
                     "help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)."
                 },
                 "cf_minqual": {
-                    "type": "number",
+                    "type": "integer",
                     "default": 0,
                     "fa_icon": "fas fa-greater-than",
                     "hidden": true,
                     "description": "Minimal sequencing quality for a position to be considered in BAF analysis.",
                     "help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)."
                 },
                 "cf_mincov": {
-                    "type": "number",
+                    "type": "integer",
                     "default": 0,
                     "fa_icon": "fas fa-align-center",
                     "hidden": true,
@@ -533,15 +532,18 @@
                 },
                 "bcftools_annotations": {
                     "type": "string",
-                    "fa_icon": "fas fa-file"
+                    "fa_icon": "fas fa-file",
+                    "description": "A vcf file containing custom annotations to be used with bcftools annotate. Needs to be bgzipped."
                 },
-                "bcftools_annotations_index": {
+                "bcftools_annotations_tbi": {
                     "type": "string",
-                    "fa_icon": "fas fa-file"
+                    "fa_icon": "fas fa-file",
+                    "description": "Index file for `bcftools_annotations`"
                 },
                 "bcftools_header_lines": {
                     "type": "string",
-                    "fa_icon": "fas fa-align-center"
+                    "fa_icon": "fas fa-align-center",
+                    "description": "Text file with the header lines of `bcftools_annotations`"
                 }
             }
         },