Removed snpeff bits, we only annotate with VEP. Adapt parameters acco…

…rding to skip_tools as well.
nrhorner · Aug 17, 2023 · 6f3d36b · 6f3d36b
1 parent 87e5339
commit 6f3d36b
Show file tree

Hide file tree

Showing 10 changed files with 65 additions and 190 deletions.
diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -42,7 +42,7 @@ module_order:
       name: "Read Alignment (STAR)"
   - picard:
       name: "GATK4 MarkDuplicates"
-      info: " metrics generated either by GATK4 MarkDuplicates or EstimateLibraryComplexity (with --use_gatk_spark)."
+      info: " metrics generated either by GATK4 MarkDuplicates."
   - samtools:
       name: "Samtools Flagstat"
   - mosdepth:

diff --git a/conf/modules.config b/conf/modules.config
@@ -325,10 +325,8 @@ process {
         }
 
         withName: ".*:GATK4_MAPPING:(BWAMEM.*_MEM|DRAGMAP_ALIGN)" {
-            // Markduplicates Spark NEEDS name-sorted reads or runtime goes through the roof
             // However if it's skipped, reads need to be coordinate-sorted
-            // Only name sort if Spark for Markduplicates + duplicate marking is not skipped
-            ext.args2        = { params.use_gatk_spark && params.use_gatk_spark.contains('markduplicates') && (!params.skip_tools || (params.skip_tools && !params.skip_tools.split(',').contains('markduplicates'))) ? '-n' : '' }
+            ext.args2        = { (!params.skip_tools || (params.skip_tools && !params.skip_tools.split(',').contains('markduplicates'))) ? '-n' : '' }
             ext.prefix       = { params.split_fastq > 1 ? "${meta.id}".concat('.').concat(reads.get(0).name.tokenize('.')[0]) : "" }
             publishDir       = [
                 mode: params.publish_dir_mode,
@@ -650,21 +648,9 @@ process {
 //        ]
 //    }
 
-    if (params.use_gatk_spark && params.use_gatk_spark.split(',').contains('markduplicates')) {
-        withName: '.*:GATK_PREPROCESSING:MARKDUPLICATES_SPARK:SAMTOOLS_CRAMTOBAM'{
-            ext.prefix       = { "${meta.id}.md" }
-            ext.when         = { params.save_output_as_bam}
-            publishDir       = [
-                enabled: params.save_output_as_bam,
-                mode: params.publish_dir_mode,
-                path: { "${params.outdir}/preprocessing/markduplicates/${meta.patient}/${meta.id}/" },
-                pattern: "*{md.bam,md.bam.bai}"
-            ]
-        }
-    }
 
     // PREPARE_RECALIBRATION
-    withName: 'BASERECALIBRATOR|BASERECALIBRATOR_SPARK' {
+    withName: 'BASERECALIBRATOR' {
         ext.args         = { meta.status == 2 ? "--lenient" : "" }
         ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.recal" : "${meta.id}_${intervals.simpleName}.recal" }
         publishDir       = [
@@ -687,7 +673,7 @@ process {
 
 // RECALIBRATE
 
-    withName: 'APPLYBQSR|APPLYBQSR_SPARK' {
+    withName: 'APPLYBQSR' {
         ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.recal" : "${meta.id}_${intervals.simpleName}.recal" }
         publishDir       = [
             enabled: !params.save_output_as_bam,
@@ -700,7 +686,7 @@ process {
 
 
     if ((params.step == 'mapping' || params.step == 'markduplicates'|| params.step == 'prepare_recalibration'|| params.step == 'recalibrate') && (!(params.skip_tools && params.skip_tools.split(',').contains('baserecalibrator')))) {
-        withName: '.*:GATK_PREPROCESSING:(RECALIBRATE|RECALIBRATE_SPARK):MERGE_INDEX_CRAM:MERGE_CRAM' {
+        withName: '.*:GATK_PREPROCESSING:RECALIBRATE:MERGE_INDEX_CRAM:MERGE_CRAM' {
             ext.prefix       = { "${meta.id}.recal" }
             ext.when         = { meta.num_intervals > 1 }
             publishDir       = [
@@ -711,7 +697,7 @@ process {
             ]
         }
 
-        withName: '.*:GATK_PREPROCESSING:(RECALIBRATE|RECALIBRATE_SPARK):MERGE_INDEX_CRAM:INDEX_CRAM' {
+        withName: '.*:GATK_PREPROCESSING:RECALIBRATE:MERGE_INDEX_CRAM:INDEX_CRAM' {
             publishDir       = [
                 enabled: !params.save_output_as_bam,
                 mode: params.publish_dir_mode,
@@ -1326,7 +1312,7 @@ process {
             path: { "${params.outdir}/reports"},
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
-            enabled: !params.skip_multiqc
+            enabled: !(params.tools && (params.skip_tools.split(',').contains('multiqc')))
         ]
         errorStrategy = {task.exitStatus == 143 ? 'retry' : 'ignore'}
     }

diff --git a/nextflow.config b/nextflow.config
@@ -32,7 +32,6 @@ params {
 
     // Alignment
     aligner                         = 'bwa-mem'    // Only STAR is currently supported.
-    use_gatk_spark                  = null       // GATK Spark implementation of their tools in local mode not used by default
     star_twopass                    = true
     star_ignore_sjdbgtf             = false     // Ignore GTF file while creating index or alignment by STAR
     star_max_memory_bamsort         = 0         // STAR parameter limitBAMsortRAM to specify maximum RAM for sorting BAM
@@ -48,12 +47,6 @@ params {
     dragmap = null
     hisat2_build_memory = null
 
-    // Skip steps
-    skip_baserecalibration          = false
-    skip_intervallisttools          = false
-    skip_variantfiltration          = false
-    skip_variantannotation          = false
-    skip_multiqc                    = false
 
     // Preprocessing of alignment
     remove_duplicates               = false
@@ -95,16 +88,9 @@ params {
     ignore_soft_clipped_bases       = true
     // Variant annotation
     tools                           = null  // No default Variant_Calling or Annotation tools
-    annotate_tools                  = null  // List of annotation tools to run - snpeff or vep or merge
+    annotate_tools                  = null  // List of annotation tools to run - only vep available
     annotation_cache                = false // Annotation cache disabled
-    cadd_cache                      = null // CADD cache disabled
-    cadd_indels                     = null // No CADD InDels file
-    cadd_indels_tbi                 = null // No CADD InDels index
-    cadd_wg_snvs                    = null // No CADD SNVs file
-    cadd_wg_snvs_tbi                = null // No CADD SNVs index
     genesplicer                     = null // genesplicer disabled within VEP
-    snpeff_cache                    = null // No directory for snpEff cache
-    snpeff_db                       = null // No default db for snpeff
     vep_cache                       = null // No directory for VEP cache
     vep_genome                      = null // No default genome for VEP
 //    vep_cache_version               = '106' // No default cache version for VEP

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -333,8 +333,8 @@
                     "type": "string",
                     "fa_icon": "fas fa-toolbox",
                     "description": "Tools to use for 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, HaplotypeCaller, mpileup, 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": "^((freebayes|manta|merge|sage|mutect2|snpeff|strelka|vep|consensus|filtering|normalise|normalize|rna_filtering|vcf_qc|vcf2maf|preprocessing|second_run)*,?)*$"
+                    "help_text": "Multiple tools separated with commas.\n\n**Variant Calling:**\n\nSomatic variant calling can currently only be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, Mutect2, Strelka2, SAGE\n\n> **NB** Mutect2 for somatic variant calling cannot be combined with `--no_intervals`\n\n**Annotation:**\n \n- VEP (only).\n\n> **NB** As RNADNAVAR will use bgzip and tabix to compress and index VCF files annotated, it expects VCF files to be sorted when starting from `--step annotate`.",
+                    "pattern": "^((freebayes|manta|merge|sage|mutect2|strelka|vep|consensus|filtering|normalise|normalize|rna_filtering|vcf_qc|vcf2maf|preprocessing|second_run)*,?)*$"
                 },
                 "skip_tools": {
                     "type": "string",
@@ -504,79 +504,93 @@
                 "annotate_tools": {
                     "type": "string",
                     "fa_icon": "fas fa-hammer",
-                    "description": "Specify which tools RNADNAvar should use for annotating variants. Values can be 'snpeff', 'vep' or 'merge'. If you specify 'merge', the pipeline runs both snpeff and VEP annotation.",
+                    "description": "Specify which tools RNADNAvar should use for annotating variants. Only VEP implemented.",
                     "help_text": "List of tools to be used for variant annotation.",
-                    "pattern": "^((snpeff|vep|merge)*(,)*)*$",
+                    "pattern": "^((vep)*(,)*)*$",
                     "hidden": true
                 },
                 "annotation_cache": {
                     "type": "boolean",
                     "fa_icon": "fas fa-database",
                     "description": "Enable the use of cache for annotation",
-                    "help_text": "And disable usage of snpeff and vep specific containers for annotation\n\nTo be used with `--snpeff_cache` and/or `--vep_cache`",
+                    "help_text": "And disable usage of vep specific containers for annotation\n\nTo be used with `--vep_cache`",
                     "hidden": true
                 },
-                "cadd_cache": {
+                "genesplicer": {
                     "type": "boolean",
-                    "fa_icon": "fas fa-database",
-                    "description": "Enable CADD cache.",
+                    "fa_icon": "fas fa-gavel",
+                    "description": "Enable the use of the VEP GeneSplicer plugin.",
                     "hidden": true
                 },
-                "cadd_indels": {
-                    "type": "string",
-                    "fa_icon": "fas fa-file",
-                    "description": "Path to CADD InDels file.",
-                    "hidden": true
+                "vep_loftee": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-database",
+                    "description": "Enable the use of the VEP LOFTEE plugin.",
+                    "hidden": true,
+                    "help_text": "For details, see [here](https://github.com/konradjk/loftee)."
                 },
-                "cadd_indels_tbi": {
+                "vep_cache": {
                     "type": "string",
-                    "fa_icon": "fas fa-file",
-                    "description": "Path to CADD InDels index.",
+                    "fa_icon": "fas fa-database",
+                    "description": "Path to VEP cache",
+                    "help_text": "To be used with `--annotation_cache`",
                     "hidden": true
                 },
-                "cadd_wg_snvs": {
+                "vep_dbnsfp": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-database",
+                    "description": "Enable the use of the VEP dbNSFP plugin.",
+                    "hidden": true,
+                    "help_text": "For details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#dbnsfp)."
+                },
+                "vep_spliceai": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-database",
+                    "description": "Enable the use of the VEP SpliceAI plugin.",
+                    "hidden": true,
+                    "help_text": "For details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#spliceai)."
+                },
+                "spliceai_snv": {
                     "type": "string",
                     "fa_icon": "fas fa-file",
-                    "description": "Path to CADD SNVs file.",
+                    "description": "Path to spliceai raw scores snv file.",
+                    "help_text": "To be used with `--vep_spliceai`.",
                     "hidden": true
                 },
-                "cadd_wg_snvs_tbi": {
+                "spliceai_snv_tbi": {
                     "type": "string",
                     "fa_icon": "fas fa-file",
-                    "description": "Path to CADD SNVs index.",
-                    "hidden": true
-                },
-                "genesplicer": {
-                    "type": "boolean",
-                    "fa_icon": "fas fa-gavel",
-                    "description": "Enable the use of the VEP GeneSplicer plugin.",
+                    "description": "Path to spliceai raw scores snv tabix indexed file.",
+                    "help_text": "To be used with `--vep_spliceai`.",
                     "hidden": true
                 },
-                "snpeff_cache": {
+                "spliceai_indel": {
                     "type": "string",
-                    "fa_icon": "fas fa-database",
-                    "description": "Path to snpEff cache",
-                    "help_text": "To be used with `--annotation_cache`",
+                    "fa_icon": "fas fa-file",
+                    "description": "Path to spliceai raw scores indel file.",
+                    "help_text": "To be used with `--vep_spliceai`.",
                     "hidden": true
                 },
-                "vep_cache": {
+                "spliceai_indel_tbi": {
                     "type": "string",
-                    "fa_icon": "fas fa-database",
-                    "description": "Path to VEP cache",
-                    "help_text": "To be used with `--annotation_cache`",
+                    "fa_icon": "fas fa-file",
+                    "description": "Path to spliceai raw scores indel tabix indexed file.",
+                    "help_text": "To be used with `--vep_spliceai`.",
                     "hidden": true
                 },
-                "vep_dbnsfp": {
+                "vep_spliceregion": {
                     "type": "boolean",
                     "fa_icon": "fas fa-database",
-                    "description": "Enable the use of the VEP dbNSFP plugin.",
+                    "description": "Enable the use of the VEP SpliceRegion plugin.",
                     "hidden": true,
-                    "help_text": "For details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#dbnsfp)."
+                    "help_text": "For 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/)."
                 },
-                "snpeff_db": {
+                "vep_custom_args": {
                     "type": "string",
-                    "fa_icon": "fas fa-database",
-                    "description": "snpEff DB version"
+                    "fa_icon": "fas fa-toolbox",
+                    "description": "Add an extra custom argument to VEP.",
+                    "hidden": true,
+                    "help_text": "Using this params you can add custom args to VEP."
                 },
                 "vep_genome": {
                     "type": "string",

diff --git a/subworkflows/nf-core/annotation/snpeff/main.nf b/subworkflows/nf-core/annotation/snpeff/main.nf
diff --git a/subworkflows/nf-core/annotation/snpeff/meta.yml b/subworkflows/nf-core/annotation/snpeff/meta.yml
diff --git a/subworkflows/nf-core/snpeff_annotate.nf b/subworkflows/nf-core/snpeff_annotate.nf
diff --git a/tests/test_annotation.yml b/tests/test_annotation.yml
@@ -1,27 +1,8 @@
-- name: Run snpEff
-  command: nextflow run main.nf -profile test,docker --annotate_tools snpeff
-  tags:
-    - annotation
-    - snpeff
-  files:
-    - path: results/variant_annotation/GM12878/GM12878_snpEff.ann.vcf.gz
-    - path: results/variant_annotation/GM12878/GM12878_snpEff.ann.vcf.gz.tbi
-    - path: results/reports/multiqc_report.html
 - name: Run VEP
-  command: nextflow run main.nf -profile test,docker --annotate_tools vep --skip_multiqc
+  command: nextflow run main.nf -profile test,docker --tools vep --skip_tools 'multiqc'
   tags:
     - annotation
     - vep
   files:
     - path: results/variant_annotation/GM12878/GM12878_VEP.ann.vcf.gz
-    - path: results/variant_annotation/GM12878/GM12878_VEP.ann.vcf.gz.tbi
-- name: Run snpEff followed by VEP
-  command: nextflow run main.nf -profile test,docker --annotate_tools merge --skip_multiqc
-  tags:
-    - annotation
-    - merge
-    - snpeff
-    - vep
-  files:
-    - path: results/variant_annotation/GM12878/GM12878_snpEff_VEP.ann.vcf.gz
-    - path: results/variant_annotation/GM12878/GM12878_snpEff_VEP.ann.vcf.gz.tbi
+    - path: results/variant_annotation/GM12878/GM12878_VEP.ann.vcf.gz.tbi
diff --git a/tests/test_skipbasecalib.yml b/tests/test_skipbasecalib.yml
@@ -1,5 +1,5 @@
 - name: Run pipeline without base calibration step
-  command: nextflow run main.nf -profile test,docker --skip_baserecalibration true
+  command: nextflow run main.nf -profile test,docker --skip_tools 'baserecalibrator'
   tags:
     - skipbasecalib
     - preprocessing